pax_global_header00006660000000000000000000000064135211623760014520gustar00rootroot0000000000000052 comment=31badbab19cdaa51fe73da51f869f43ab215cbf1 txt2html-2.53/000077500000000000000000000000001352116237600132375ustar00rootroot00000000000000txt2html-2.53/Build.PL000066400000000000000000000023761352116237600145430ustar00rootroot00000000000000 use strict; use warnings; use Module::Build 0.3601; my %module_build_args = ( "build_requires" => { "Module::Build" => "0.3601" }, "configure_requires" => { "Module::Build" => "0.3601" }, "dist_abstract" => "convert plain text file to HTML.", "dist_author" => [ "Kathryn Andersen " ], "dist_name" => "txt2html", "dist_version" => "2.53", "license" => "gpl", "module_name" => "txt2html", "recommends" => {}, "recursive_test_files" => 1, "requires" => { "File::Basename" => 0, "Getopt::Long" => 0, "Pod::Usage" => 0, "YAML::Syck" => 0, "constant" => 0, "perl" => "v5.8.1", "strict" => 0 }, "script_files" => [ "scripts/txt2html" ], "test_requires" => { "File::Find" => 0, "File::Temp" => 0, "Test::More" => 0, "warnings" => 0 } ); unless ( eval { Module::Build->VERSION(0.4004) } ) { my $tr = delete $module_build_args{test_requires}; my $br = $module_build_args{build_requires}; for my $mod ( keys %$tr ) { if ( exists $br->{$mod} ) { $br->{$mod} = $tr->{$mod} if $tr->{$mod} > $br->{$mod}; } else { $br->{$mod} = $tr->{$mod}; } } } my $build = Module::Build->new(%module_build_args); $build->create_build_script; txt2html-2.53/CONTRIBUTING.md000066400000000000000000000017751352116237600155020ustar00rootroot00000000000000## HOW TO CONTRIBUTE TO TXT2HTML DEVELOPMENT txt2html is available at https://github.com/resurrecting-open-source-projects/txt2html If you are interested in contribute to txt2html development, please, follow these steps: 1. Send me a patch that fix an issue or that implement a new feature. Alternatively, you can do a 'pull request'[1] in GitHub. [1] https://help.github.com/articles/using-pull-requests 2. Ask for join to txt2html project in GitHub, if you want to work officially. Note that this second step is not compulsory. However, to accept you in project, I need a minimum collaboration before. To find issues and bugs to fix, you can check these addresses: - https://github.com/resurrecting-open-source-projects/txt2html/issues - https://bugs.debian.org/cgi-bin/pkgreport.cgi?dist=unstable;package=txt2html - https://bugs.launchpad.net/ubuntu/+source/txt2html/+bugs If you want to join, please contact me: eriberto at eriberto.pro.br -- Eriberto, Thu, 01 Aug 2019 21:55:53 -0300 txt2html-2.53/ChangeLog000066400000000000000000000577051352116237600150270ustar00rootroot00000000000000Revision History for txt2html ============================= 2.53 2019-08-02 * New repository for this project (now in GitHub). https://github.com/resurrecting-open-source-projects/txt2html * Added CONTRIBUTING.md file. * Added README.md and renamed old README file to README.txt2html. * Fixed the licensing in LICENSE file. * Fixed some spelling errors. * Fixed the path for Perl in scripts/txt2html. * Unified the changelogs. | ----------------------- | | ---- OLD CHANGELOG ---- | \ / ---- OLD UPSTREAM ---- \ / · ----------------------- · 2.52.01 (aka 2.5201) 2013-05-21 ------------------------------- * 2013-05-21 16:25:10 +1000 rebuilding with new version * 2012-05-11 14:20:41 +1000 Updating website. 2.51 Sun 4th March 2008 - fixed bug with underscores in links - fixed docs about escape_chars (should be escapechars) - fixed docs about DOCTYPE 2.50 Sat 22nd December 2007 - fixed bug with formatting and punctuation - removed old reference-to-an-array argument method - made --xhtml true by default (used to be false) - moved the debugging options to global variables 2.46 Fri 9th November 2007 - updated docs on custom_heading_regexp - fixed bug with xhtml output - documented all undocumented functions 2.45 Fri 26th January 2007 - fixed bug with umlauts - fixed bug with UTF-8 characters - added --underline_delimiter option. 2.44 Tue 17th January 2006 - fixed bug with delimiter tables - minor documentation fixes 2.43 Fri 7th October 2005 - fixed bug with interaction between #bolding# and #anchor links 2.42 Wed 10th August 2005 - new option to txt2html script: --instring, which enables one to process a string instead of a file. - new options to HTML::TextToHTML: * instring, as above * inhandle, which enables one to pass in input file handles to process * outhandle, which enables one to pass in an output file handle 2.41 Sun 8th May 2005 - solved the system links dictionary problem! No longer uses an external file at all, uses the DATA handle. This means that there is no longer a --system_link_dict option. - changed versioning scheme; now bugfix versions will be things like 2.4101 - removed the run_txt2html command; it isn't needed when the txt2html script is part of the package and does things much nicer. - generate the README from the PoD 2.40 Sat 12th February 2005 - much improved speed 2.37 Thu 10th February 2005 - another fix to installation - fixed CPAN module problem 2.36 Sun 23rd January 2005 - slight fix to installation 2.35 Wed 18th January 2005 - fixed bug where a Dos file was processed on a Unix system. - removed Makefile.PL; not needed with modern perls 2.34 Thu 6th January 2005 - fixed another bug with demoronize code (gah!) 2.33 Wed 5th January 2005 - darn, left out some files! 2.32 Wed 5th January 2005 - fixed bug with demoronize code - fixed documentation for lower_case_tags - changed around installation so that no custom Module::Builder is needed; also moved files into more customary places, and now use Filter::Simple to change the system dictionary path in the module and script files for installation. 2.31 Tue 21st September 2004 - fixed bug with install - did some changes to help version-changing 2.30 Fri 27th August 2004 - changed build system over to Module::Build to eliminate problems with different versions of ExtUtils::MakeMaker and the installation of the system links dictionary, as well as hoping to make the installation more portable. - changed build so that the system links dictionary (in defaults and documentation) is automatically set to where the system links dictionary is going to be installed (yay!) - improved the INSTALL document (thanks to Mark Schmidt) - improved the bold and italic processing (now it's not messed up by short lines putting a
in) - bug fix for paragraphs with "0" (thanks to Andrew Williams) 2.25 Sun 23rd May 2004 - the default location for the system links dictionary (txt2html.dict) is now "/usr/local/share/txt2html/txt2html.dict". (It uses SITEPREFIX not PREFIX now) - added --bold_delimiter and --italic_delimiter options; now the bold and italic matching is done separately, not as part of the links-dictionary stuff. This means it's much easier to change or turn off if you don't want it. - links-dictionary matching is now done on segments without structural tags in them so matching for things like '^

' should be replaced with just '^'. I don't think this will break anything, and will prevent certain kinds of illegal substitutions. - tidied up some of the links in the links dictionary 2.24 Sun 16th May 2004 - bug fixes for preformatting: fixed up loss of trailing PRE, and now preformats and lists no longer have a trailing blank line - documented the 'quote_mail' and 'quote_explicit' classes, and added the 'mail_header' class for mail-header paragraphs. - made the #bold# and *italic* matches more aggressive. - added Alan Jackson's "demoronize" patch from John Walker's demoronize script at 2.23 Wed 25th February 2004 - oops! Forgot to include one of the test files! 2.22 Sun 22nd February 2004 - bug fix with delimiter table 2.21 Sat 10th January 2004 - bugfixes with a stricter perl 5.8.2 - bugfix for processing empty file 2.20 Sun 7th December 2003 - added --table_type option to say which types of table will be recognised and parsed if the --make_tables option is true. In other words, there are now new types of table which can be parsed. * ALIGN is the original space-aligned table type * PGSQL is the type of table you get from a Postgresql query * BORDER is a table with +-----+ lines around it as a border * DELIM is delimited columns 2.10 Sat 6th December 2003 - changed process_para method to assume it has only one paragraph; and added process_chunk method to deal with processing strings which may contain more than one paragraph in them. - a fair few internal changes to make more things think in terms of paragraphs rather than lines; this changes the parsing of a few things, but doesn't break the conventions. - fixed a bug where unordered lists were allowed to have bullets which were more than one character wide. Well, I considered it a bug, it was annoying me. - added --bullets and --bullets_ordered options to enable the user to define the bullet characters used for unordered and ordered lists. - hooray! Figured out a way of having multi-paragraph list items! - woo hoo! Added definition lists! And managed to do it so that they are treated like the other lists, that is, you can nest lists in definition lists and visa versa. 2.06 Sun 15th November 2003 - fixed bug with processing STDIN (ie piping input to txt2html) - moved test input files into separate tfiles directory - added in most of Seth's old test files to the testing; and fixed resulting bugs that were flushed out of cover 2.05 Wed 5th November 2003 - error in fix to PREFIX! Argh! 2.04 Tue 4th November 2003 - changed Makefile.PL to fix PREFIX - use "#!/usr/bin/env perl" trick (courtesy of Sami Haahtinen) instead of using ExtUtils::configPL module - made Getopt::ArgvFile an official prerequisite - enabled CAPS tagging to be optional (just give an empty caps_tag) 2.03 Tue 15th July 2003 - fixed bug with para tests (it didn't fail on my system because it was using the already installed system links dictionary) 2.02 Sun 13th July 2003 - fixed bug in documentation about custom headings - moved tests into t/ directory - added is_fragment option to process_para to enable it to process a fragment without assuming that it was a paragraph. 2.01 Sun 1st June 2003 - fixed up a few documentation/reference things that I'd forgotten, changing names in sample.txt for example. 2.00 Sat 31st May 2003 - merge of HTML::TextToHTML and the official txt2html - hence the version jump. * the distribution name is now txt2html * renamed texthyper to txt2html, TextToHTML.dict to txt2html.dict * merged change history * split README into README, INSTALL and LICENSE files * updated DEVNOTES - merged in the changes from 1.28 to 1.35 as much as I could * corrected bugs that still applied * added --style_url option * added --body_deco option * added two CSS classes: quote_mail and quote_explicit - Did Not add the following, as it was rather more complicated: * multi-paragraph list items * the heading_callback_customize stuff ================================================== 1.12 Sat 15th February 2002 - removed heavily spammed email address from documentation and examples. 1.11 Fri 20th December 2002 - fixed bug in texthyper script which was giving warnings. 1.10 Wed 18th December 2002 - removed all dependency on AppConfig * all of the existing options now must use their full names. * However, one now has the choice between passing options as a hash, or the old way, as a reference to an array. - removed the do_help method; if you want the documentation of the module, use perldoc HTML::TextToHTML - moved the texthyper script into this distribution * It now uses Getopt::Long and Getopt::ArgvFile. * The format of .texthyperrc has changed to conform with Getopt::ArgvFile rather than AppConfig. * Changed the version number so that it was bigger than either the script or the module so that both could have the same version number (that's why the big jump). - the included system link dictionary (TextToHTML.dict) is now installed in /usr/share/txt2html as part of the install process. 0.09 Wed 20th November 2002 - improved the XHTML mode, so that open paragraphs get closed sooner. This fixed a bug related to paragraphs inside lists. 0.08 Wed 20th November 2002 - CPAN testers complained about a lack of explicitly stating all the dependencies of AppConfig, which either means that AppConfig has changed desperately, or their testing methods have changed, since I didn't think it was possible to get the AppConfig module without getting all its dependent modules, but, oh well. 0.07 Sun 17th November 2002 - fixed a bug in process_para to ensure that if one is using it standalone, any open lists will be closed - added --lower_case_tags option to force the tags to be output in lower-case - first pass at XHTML conformance; added --xhtml option. It isn't that pretty-looking, but the sample does pass the scrutiny of "tidy". When turned on it: * forces lower-case on * makes empty tags have the empty marker (eg

) * closes all open P and LI tags where they should be closed * table cell alignments are done as style attributes 0.06 Mon 2nd September 2002 - fine-tuned some of the links in the default links dictionary - some internal rewriting 0.05 Wed 5th June 2002 - fixed minor bugs 0.04 Sun 2nd June 2002 - fixed bug with detection of paragraphs by indentation - added --indent_par_break and --preserve_indent options - fixed error in documentation - fixed bug with nonexistant link dictionaries 0.03 Sun 26th May 2002 - documented the format of the Link Dictionary - added the do_help method, and changed the behaviour of --help and --manpage - added the --make_anchors option, which enables one to disable the making of anchors, so that if one prefers another method of anchor-making (such as that in HTML::GenToc) then one can use that instead. - altered the #bold# pattern in the link dictionary to only need one hash. This should still hopefully allow things like #1 without turning it bold, and being able to use ### as a separator. - gratuitous self-promotion: added HTML::GenToc to the sample links dictionary - removed the need for getline(), but rather pass the lines in to the methods, in order to parse by-paragraph and then by-line (mucho rewrite) which enabled me to: * implement the table-parsing from Gareth Rees's HTML::FromText module -- added the --make_tables option * now the links dictionary does multiline matches (useful for things like italics which break over lines) * enable converting passed-in strings rather than just files 0.02 Wed 15th May 2002 - fixed bug with link dictionary parsing - improved the tests - updated link dictionary to fix a few bugs (eg underlines) and add a few things (like using double # for ##bold## text). 0.01 Sun 12th May 2002 - conversion of Seth Golub's txt2html (version 1.28) to a module - made all global settings options (eg the location of the system link dictionary) - added "outfile" option - added use_mosaic_header option - changed the dynamic code generation completely. - removed the evil $* variable ----------------------------------------------------------------- ===================================================== (cvs log on Sourceforge) revision 1.35 date: 2002/12/03 03:47:46; author: suntong; state: Exp; lines: +14 -13 - Defines two CSS Style: quote_mail & quote_explicit - Mail quote mode and quote mode won't interfere with each other ---------------------------- revision 1.34 date: 2002/12/03 01:51:41; author: suntong; state: Exp; lines: +8 -7 - preformat should be dealed before other cases ---------------------------- revision 1.33 date: 2002/12/02 23:44:13; author: suntong; state: Exp; lines: +7 -7 Bug fixing (details in http://groups.yahoo.com/group/txt2html/message/89): - Changed incorrect entity names of "fraqfrac*" to "frac*". - redundant \| in [\||:] removed. - change misleading --style help to '--style ' ---------------------------- revision 1.32 date: 2002/12/01 19:59:09; author: suntong; state: Exp; lines: +39 -5 - Add Callback functions for HTML header handling so that users can customise their own heading, add horizon lines, change colors or write their own toc, etc - User can define/keep their callbacks locally without tampering main distribution - 'mailstuff' priority should be higher than 'preformat' ---------------------------- revision 1.31 date: 2002/12/01 18:59:30; author: suntong; state: Exp; lines: +5 -5 - solve the problem that txt2html can't html-ify its own anchor. ---------------------------- revision 1.30 date: 2002/12/01 18:51:20; author: suntong; state: Exp; lines: +53 -10 - All my previous patches are lost because yahoogroups doesn't keep my patch attachements. So, here they are in a big chunk. Major updates are: - Able to use a style sheet for the generated html file - Able to use body decoration for the generated html file customize your own background color/image/sound, etc... - Misc enhancements. ---------------------------- revision 1.29 date: 2002/12/01 18:28:35; author: suntong; state: Exp; lines: +3 -2 - Apply patch from http://groups.yahoo.com/group/txt2html/message/32 ,----- | I don't know when I'll get around to releasing a new version of | txt2html, but I have a few fixes I've been sitting on. I thought | I'd send them out on this list so people could take advantage of | them without having to wait until I finally package up a new release. | | * Changed incorrect entity names of "fraq*" to "frac*". | | * Allow paragraphs within lists by permitting blank lines within | list elements, as long as the following text has the same | indentation level. `----- ======================================================= 1.28 ---- - bugfix: reserved characters in titles created with --titlefirst are now escaped properly. - bugfix: when preformatting entire document, each line was getting its own 
 container (introduced
  with explicit preformatting feature in 1.26).

- dict: added some characters to those allowed in http urls (=&;,).

- dict: added "-" to allowed characters within *emphasized-pattern*.

1.27
----

- Changed names of default link dictionaries to txt2html.dict


1.26 (not released)
-------------------

- Added -8 (for 8-bit-clean) to disable conversion of non-ASCII
  characters to their corresponding Latin-1 character entities.

- Added -pm to allow explicit marking of preformatted text in source

- Changes => to , in mapping, to stay compatible with Perl 4

- Added debug flag 4, for observing link rules in action

- Fixed length checking bug in header underline analysis

- Change a regexp so Perl 5.6 doesn't complain.

- No longer add space after 
  •  tags

- Allow unindented lists to start after CAPS lines

- Use · as a bullet character

- Fixed bug that dropped a character when certain actions were
  taken on the last line of input that didn't end with a newline.

- Added more aggressive regexps for _underlined_ and *emphasized* text.

- Improved character markup rules

- Added link rule for news URLs.  (This must have been
  accidentally deleted at some point.)

- Added link rule for common explicit url markup: 

1.25
----

- Changed the official home page to 
  (the old page will have a working redirect indefinitely.)

- Added a LICENSE to the distribution.  (modified BSD-style)

- When no title is specified, an empty title element is inserted.
  (The old behavior was to omit the title element, which is
  forbidden by the spec.)

- Made heading anchors appear inside the heading, rather than
  surrounding it (which is forbidden by the HTML spec)

- Changed the DTD name

- Added the --linkonly option so people can use the links
  dictionary feature without doing any other markup.  This is
  useful for adding links to HTML fragments or documents.

- Added the --prepend_body option for prepending HTML to the body.

- Made in_link_context smarter so it won't link on attributes or
  tag names.  (This is good for adding hyperlinks, but may screw
  up some clever uses of the linking code.)

- Added link rules for _underlined text_ and *emphasized text*

- Added --noescapechars to suppress converting "&" "<" and
  ">" into "&" "<" and ">"

- Changed pattern rules to handle non-ascii letters properly in
  matching patterns.

- Added conversion of non-ascii letters into character entities.

- Lots of upgrades to the links dictionary patterns

1.24
----

- Changed behavior of custom headers to something much more
  useful: Header levels are assigned by regex in order seen.
  When a line matches a custom header regex, it is tagged as a
  header.  If it's the first time that particular regex has
  matched, the next available header level is associated with it
  and applied to the line.  Any later matches of that regex will
  use the same header level.

- Added the -EH / --explicit-headings option

- Added some unnecessary initialization to avoid warnings when
  perl is run with the -w switch.

1.23
----

- Added handling for when the consistent formatting of numbered
  lists is the position of the non-numeric character, not the
  amount of whitespace preceding the number.  (The numbers
  grow to the left instead of the right.)

1.22
----

- Fixed bug in unhyphenation

- Changed HTML version in default doctype line to 3.2

1.21
----

- Added 

1.20
----

- Added DOCTYPE tag and --doctype options.

- Syntax change to get rid of Perl 5 warning

- Added ability to use the first line of the text as the title

- Fixed some (unused) grossness in links dict file

1.19
----

- Added --append_head

- Mail and News name anchor surrounds just the first word
  ("Newsgroups:" or "From"), and not the whole line.  That way,
  newsgroup names and email addresses get HREF'd as normal.

1.18
----

- Cleaned up nested list handling & fixed a bug under Perl 5.

- Changed a couple minor things to get rid of some of the Perl 5 warnings.

1.17
----

- Lists can start even when not indented and not preceded by a
  blank line if the previous line was short or a header.

- New flag "o" added for dictionary entries.  Specifies that the
  link should only be done the first time a match is found.

1.16
----

- Added anchoring of custom headers

- Took the changelog out of the script

- Tweaked $line_indent in sub liststuff

- Insert 
     before each mail/news message

1.15
----

- Fixed options handling for -e/+e , -r

- Added "Newsgroups:" to trigger mail headers

- Fixed anchor naming

- took out -T option, since it isn't implemented yet.  Whoops..

- Fixed bug in endpreformat

1.14
----

- Fixed +l/--nolink option handling

- Fixed major bug in dynamic_make_dictionary_links that allowed
  nested links under some circumstances.

1.13
----

- Fixed usage message so it matches options.  (whoops)

- Added custom heading style feature

1.12
----

- Fixed bug in heading regexp

- Changed underline tolerance parameters from min & max length
  difference to length difference & offset difference

- Centralized line reading, added handling of DOS carriage returns

- Switched to heading style stack.  Styles still very limited.

- Changed heading anchor names from a simple count to a hierarchical
  section number.

1.11
----

- Blank lines are never considered underlined

- Shortline breaking slightly more intelligent (or at least different)

- Paragraph breaks much more intelligent

- Lowercased tags.  Style is so fickle.

- Added links dictionaries, link making, etc.

- Allow repeated bullet chars for unordered lists.  (Tiny mod to regexp)

- switched order of caps & liststuff in main()

- improved untabify() so it converts the whole line, not just beginning

- split up all lines >79 characters to avoid common downloading error
  (people would sometimes copy the script off the display,
  inadvertently adding a few newlines in bad places in the code)

- Handles option "--" now.

- Accepts named files as input as alternative to stdin

- Deals with stdin properly (no more extra EOFs needed)

- Improved mail handling

1.10
====

- Added --extract, etc.

1.9
---

- Changed from #!/usr/local/bin/perl to the more clever version in
  the man page.  (How did I manage not to read this for so long?)

- Swapped hrule & header back to handle double lines.  Why should
  this order screw up headers?


1.8
---

- put mail_anchor back in.  (Why did I take this out?)

- Finally added handling of lettered lists (ordered lists marked with
  letters)

- Added title option (--title, -t)

- Shortline now looks at how long the line was before txt2html
  started adding tags.   ($line_length)

- Changed list references to scalars where appropriate. (@foo[0] -> $foo[0])

- Added untabify() to homogenize leading indentation for list
  prefixes and functions that use line length

- Added "underline tolerance" for when underlines are not exactly the
  same length as what they underline.

- Added error message for unrecognized options

- removed \w matching on --capstag

- Tagline now removes leading & trailing whitespace before tagging

- swapped order of caps & heading in main loop

- Cleaned up code for speed and to get rid of warnings

- Added more restrictions to something being a mail header

- Added indentation for lists, just to make the output more readable.

- Fixed major bug in lists: $OL and $UL were never set, so when a
  list was ended "" was *always* used!

- swapped order of hrule & header to properly handle long underlines


1.7
---

- Added to comments in options section

- renamed blank to is_blank

- Page break is converted to horizontal rule 
    

- moved usage subroutine up top so people who look through code see
  it sooner


1.6
---

- Creates anchors at each heading

1.5
---

- Fixed minor bug in Headers

- Preformatting can be set to only start/stop when TWO lines of
  [non]formatted-looking-text are encountered.  Old behavior is still
  possible through command line options (-pb 1 -pe 1).

- Can preformat entire document (-pb 0) or disable preformatting
  completely (-pe 0).

- Fixed minor bug in CAPS handling (paragraph breaks broke)

- Puts paragraph tags *before* paragraphs, not just between them.


1.4
---

- Allow ':' for numbered lists (e.g. "1: Figs")

- Whitespace at end of line will not start or end preformatting

- Mailmode is now off by default

- Doesn't break short lines if they are the first line in a list
  item.  It *should* break them anyway if the next line is a
  continuation of the list item, but I haven't dealt with this yet.

- Added action on lines that are all capital letters.  You can change
  how these lines get tagged, as well as the minimum number of
  consecutive capital letters required to fire off this action.


1.3
---

- Tiny bugfix in unhyphenation


1.2
---

- Added unhyphenation

 seth@aigeek.com

txt2html-2.53/DEVNOTES000066400000000000000000000047261352116237600144220ustar00rootroot00000000000000Developer Notes
===============

This uses Dist::Zilla for building/testing/release.

Changing the version
--------------------

1. Edit the dist.ini file to increment the version
2. Replace the old version number with the new version in the tfiles files.
3. "dzil test"

Generating README
--------------------------

Make the README changes in HTML/TextToHTML.pm
Dist::Zilla will generate the README from that.

Adding Options
--------------

All new options need to be added in five places:
- lib/HTML/TextToHTML.pm init_our_args(), to initialize the default
- lib/HTML/TextToHTML.pm args() in the parse-the-array-ref part, unless
  it is a simple option-with-a-value.  If it is a boolean option,
  it also needs to be added in its "no" form.
- lib/HTML/TextToHTML.pm OPTIONS documentation
- scripts/txt2html Getopt call, including its type and possible shortnames
- scripts/txt2html OPTIONS documentation

Changing the Global Link Dictionary
-----------------------------------

The contents of the global link dictionary are kept inside
lib/HTML/TextToHTML.pm in the __DATA__ section.
Any changes or updates to it must be done there.

Release Notes
=============

Before releasing, don't forget to run

	dzil test
	dzil build # for a sanity check of the build
	dzil release

(and usually "dzil install" as well)

This bundle was released in three different external places in early:
- CPAN
- Sourceforge
- FreshMeat

Currently, txt2html is available in GitHub.

CPAN Release
------------

Dist::Zilla will do the CPAN release as part of the release process.

Sourceforge Release
-------------------

Do a git push if you haven't already.

Go to the Admin/Files section and follow the instructions.
You will need to ftp upload the .tar.gz file to upload.sourceforge.net
/incoming directory before doing certain steps.

One also needs to update the web-page.  Cd to txt2html/web/htdocs on
your home machine, and edit index.html to update the version number.
Then do
	make del_cpfiles
	make cpfiles
	make
        git add
	git commit
        git push
	cd ..
	make install

(The last copies it over with rsync)

One should also post a message to the txt2html mailing list.

FreshMeat Release
-----------------

Log in to freshmeat.net, and follow the instructions for new releases.
The "changes this release" will need to be a summary of the changes.
Since the file is on sourceforge, you won't need to alter the download
URL.

GitHub
------

Please, go to https://github.com/resurrecting-open-source-projects/txt2html
txt2html-2.53/LICENSE000066400000000000000000000003621352116237600142450ustar00rootroot00000000000000Copyright 1994-2000 Seth Golub seth AT aigeek.com
Copyright 2002-2013 Kathryn Andersen
Copyright 2018-2019 Joao Eriberto Mota Filho

This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
txt2html-2.53/MANIFEST000066400000000000000000000034751352116237600144010ustar00rootroot00000000000000Build.PL
ChangeLog
CONTRIBUTING.md
DEVNOTES
doc/UPDATE-CHECK
LICENSE
MANIFEST
MANIFEST.SKIP
META.yml
README.md
README.txt2html
TODO
lib/HTML/TextToHTML.pm
scripts/txt2html
t/00-compile.t
t/10para.t
t/20tfiles.t
t/25handles.t
t/30sample.t
t/50xsample.t
t/70bugs.t
t/release-distmeta.t
t/release-has-version.t
t/release-pod-coverage.t
t/release-pod-syntax.t
t/release-portability.t
tfiles/custom-headers.txt
tfiles/custom-headers2.txt
tfiles/empty.txt
tfiles/good_custom-headers.html
tfiles/good_custom-headers2.html
tfiles/good_empty.html
tfiles/good_heading1.html
tfiles/good_hyphens.html
tfiles/good_links.html
tfiles/good_links2.html
tfiles/good_links3.html
tfiles/good_links4.html
tfiles/good_list-2.html
tfiles/good_list-3.html
tfiles/good_list-4.html
tfiles/good_list-5.html
tfiles/good_list-advanced.html
tfiles/good_list-custom.html
tfiles/good_list-styles.html
tfiles/good_list.html
tfiles/good_mixed.html
tfiles/good_news.html
tfiles/good_pre.html
tfiles/good_pre2.html
tfiles/good_punct.html
tfiles/good_robo.html
tfiles/good_sample.html
tfiles/good_table-align.html
tfiles/good_table-border.html
tfiles/good_table-delim.html
tfiles/good_table-pgsql.html
tfiles/good_table-pgsql2.html
tfiles/good_umlauttest.html
tfiles/good_utf8.html
tfiles/good_xhtml_sample.html
tfiles/heading1.txt
tfiles/hyphens.txt
tfiles/links.txt
tfiles/links2.txt
tfiles/links3.txt
tfiles/links4.txt
tfiles/list-2.txt
tfiles/list-3.txt
tfiles/list-4.txt
tfiles/list-5.txt
tfiles/list-advanced.txt
tfiles/list-custom.txt
tfiles/list-styles.txt
tfiles/list.txt
tfiles/mixed.txt
tfiles/news.txt
tfiles/pre.txt
tfiles/pre2.txt
tfiles/punct.txt
tfiles/robo.txt
tfiles/sample.foot
tfiles/sample.foot2
tfiles/sample.txt
tfiles/table-align.txt
tfiles/table-border.txt
tfiles/table-delim.txt
tfiles/table-pgsql.txt
tfiles/table-pgsql2.txt
tfiles/umlauttest.txt
tfiles/utf8.txt
txt2html-2.53/MANIFEST.SKIP000066400000000000000000000005111352116237600151320ustar00rootroot00000000000000# version control files
\bRCS\b
\bCVS\b
,v$
\.svn\b
# archives
.*\.tar\.gz$
# the TODO file
^\.todo$
# other files

# MakeMaker files
^Makefile$
^blib/
^MakeMaker-\d
pm_to_blib
# Module::Build files
^_build/
^Build$

# development files
^dist.ini$
^profiling/

# temp, old, backup files
~$
\.old$
\.bak$
\.tmp$
\.#
\.swp$
^#.*#$
txt2html-2.53/META.yml000066400000000000000000000011341352116237600145070ustar00rootroot00000000000000---
abstract: 'convert plain text file to HTML.'
author:
  - 'Kathryn Andersen '
build_requires:
  File::Find: 0
  File::Temp: 0
  Module::Build: 0.3601
  Test::More: 0
  warnings: 0
configure_requires:
  Module::Build: 0.3601
dynamic_config: 0
generated_by: 'Dist::Zilla version 4.300034, CPAN::Meta::Converter version 2.120921'
license: gpl
meta-spec:
  url: http://module-build.sourceforge.net/META-spec-v1.4.html
  version: 1.4
name: txt2html
requires:
  File::Basename: 0
  Getopt::Long: 0
  Pod::Usage: 0
  YAML::Syck: 0
  constant: 0
  perl: v5.8.1
  strict: 0
version: 2.53
txt2html-2.53/README.md000066400000000000000000000050671352116237600145260ustar00rootroot00000000000000# txt2html
**Convert plain text file to HTML**




    
**1. HELP THIS PROJECT**
    
**2. WHAT IS TXT2HTML?**
    
**3. WHAT IS TXT2HTML NOT?**
    
**4. HOW TO INSTALL AND USE**
    



--------------------
1. HELP THIS PROJECT
--------------------

txt2html needs your help. **If you are a Perl programmer** and if you wants
to help a nice project, this is your opportunity.

My name is Eriberto and **I am not a Perl developer**. I imported txt2html
from its old repositories[1][2] to GitHub (the original developer is
inactive[3]). After this, I applied all patches found in Debian project and
other places for this program. All my work was registered in ChangeLog
file (version 2.53 and later releases). I also maintain txt2html packaged in
Debian[4].

If you are interested to help txt2html, read the [CONTRIBUTING.md](CONTRIBUTING.md) file.

[1] http://txt2html.sourceforge.net
[2] https://metacpan.org/release/txt2html
[3] Kathryn Andersen (RUBYKAT) told me in a private email message that is
    inactive because a personal problem. So, txt2html needs help!
[4] https://tracker.debian.org/pkg/txt2html


--------------------
2. WHAT IS TXT2HTML?
--------------------

txt2html is a Perl program that converts plain text to HTML, using
HTML::TextToHTML Perl module.

It supports headings, lists, simple character markup, and hyperlinking, and
is highly customizable. It recognizes some of the apparent structure of the
source document (mostly whitespace and typographic layout), and attempts to
mark that structure explicitly using HTML.

The purpose for this tool is to provide an easier way of converting existing
text documents to HTML format, giving something nicer than just whapping the
text into a big PRE block. txt2html can also be used to aid in writing new
HTML documents, but there are probably better ways of doing that.


------------------------
3. WHAT IS TXT2HTML NOT?
------------------------

txt2html is not a program to convert wordprocessor files or other marked-up
document formats. It is also not a program to convert HTML to text. Most HTML
browsers do that.

If you need to convert something other than plain text to HTML, or you need to
convert from HTML, you should look for a more appropriate tool.

txt2html is not a program for automatically generating a table-of-contents from
a file. If you want that, then use txt2html to generate a HTML file, and then
use htmltoc or hypertoc on the HTML file.


-------------------------
4. HOW TO INSTALL AND USE
-------------------------

Please, read the README.txt2html file and generated manpages txt2html(1) and
HTML::TextToHTML(3).
txt2html-2.53/README.txt2html000066400000000000000000001300641352116237600157100ustar00rootroot00000000000000NAME
    HTML::TextToHTML - convert plain text file to HTML

VERSION
    version 2.53

SYNOPSIS
      From the command line:

        txt2html I

      From Scripts:

        use HTML::TextToHTML;
 
        # create a new object
        my $conv = new HTML::TextToHTML();

        # convert a file
        $conv->txt2html(infile=>[$text_file],
                         outfile=>$html_file,
                         title=>"Wonderful Things",
                         mail=>1,
          ]);

        # reset arguments
        $conv->args(infile=>[], mail=>0);

        # convert a string
        $newstring = $conv->process_chunk($mystring)

DESCRIPTION
    HTML::TextToHTML converts plain text files to HTML. The txt2html script
    uses this module to do the same from the command-line.

    It supports headings, tables, lists, simple character markup, and
    hyperlinking, and is highly customizable. It recognizes some of the
    apparent structure of the source document (mostly whitespace and
    typographic layout), and attempts to mark that structure explicitly
    using HTML. The purpose for this tool is to provide an easier way of
    converting existing text documents to HTML format, giving something
    nicer than just whapping the text into a big PRE block.

  History
    The original txt2html script was written by Seth Golub (see
    http://www.aigeek.com/txt2html/), and converted to a perl module by
    Kathryn Andersen (see http://www.katspace.com/tools/text_to_html/) and
    made into a sourceforge project by Sun Tong (see
    http://sourceforge.net/projects/txt2html/). Earlier versions of the
    HTML::TextToHTML module called the included script texthyper so as not
    to clash with the original txt2html script, but now the projects have
    all been merged. UPDATING: currently, the project is available on GitHub
    at https://github.com/resurrecting-open-source-projects/txt2html

OPTIONS
    All arguments can be set when the object is created, and further options
    can be set when calling the actual txt2html method. Arguments to methods
    can take a hash of arguments.

    Note that all option-names must match exactly -- no abbreviations are
    allowed. The argument-keys are expected to have values matching those
    required for that argument -- whether that be a boolean, a string, a
    reference to an array or a reference to a hash. These will replace any
    value for that argument that might have been there before.

    append_file
            append_file=>I

        If you want something appended by default, put the filename here.
        The appended text will not be processed at all, so make sure it's
        plain text or correct HTML. i.e. do not have things like: Mary
        Andersen  but instead, have: Mary Andersen
        <kitty@example.com>

        (default: nothing)

    append_head
            append_head=>I

        If you want something appended to the head by default, put the
        filename here. The appended text will not be processed at all, so
        make sure it's plain text or correct HTML. i.e. do not have things
        like: Mary Andersen  but instead, have: Mary
        Andersen <kitty@example.com>

        (default: nothing)

    body_deco
            body_deco=>I

        Body decoration string: a string to be added to the BODY tag so that
        one can set attributes to the BODY (such as class, style, bgcolor
        etc) For example, "class='withimage'".

    bold_delimiter
            bold_delimiter=>I

        This defines what character (or string) is taken to be the delimiter
        of text which is to be interpreted as bold (that is, to be given a
        STRONG tag). If this is empty, then no bolding of text will be done.
        (default: #)

    bullets
            bullets=>I

        This defines what single characters are taken to be "bullet"
        characters for unordered lists. Note that because this is used as a
        character class, if you use '-' it must come first.
        (default:-=o*\267)

    bullets_ordered
            bullets_ordered=>I

        This defines what single characters are taken to be "bullet"
        placeholder characters for ordered lists. Ordered lists are normally
        marked by a number or letter followed by '.' or ')' or ']' or ':'.
        If an ordered bullet is used, then it simply indicates that this is
        an ordered list, without giving explicit numbers.

        Note that because this is used as a character class, if you use '-'
        it must come first. (default:nothing)

    caps_tag
            caps_tag=>I

        Tag to put around all-caps lines (default: STRONG) If an empty tag
        is given, then no tag will be put around all-caps lines.

    custom_heading_regexp
            custom_heading_regexp=>\@custom_headings

        Add patterns for headings. Header levels are assigned by regexp in
        the order seen in the input text. When a line matches a custom
        header regexp, it is tagged as a header. If it's the first time that
        particular regexp has matched, the next available header level is
        associated with it and applied to the line. Any later matches of
        that regexp will use the same header level. Therefore, if you want
        to match numbered header lines, you could use something like this:

            my @custom_headings = ('^ *\d+\. \w+',
                                   '^ *\d+\.\d+\. \w+',
                                   '^ *\d+\.\d+\.\d+\. \w+');

            ...
                custom_heading_regexp=>\@custom_headings,
            ...

        Then lines like

                        " 1. Examples "
                        " 1.1. Things"
                    and " 4.2.5. Cold Fusion"

        Would be marked as H1, H2, and H3 (assuming they were found in that
        order, and that no other header styles were encountered). If you
        prefer that the first one specified always be H1, the second always
        be H2, the third H3, etc, then use the "explicit_headings" option.

        This expects a reference to an array of strings.

        (default: none)

    default_link_dict
            default_link_dict=>I

        The name of the default "user" link dictionary. (default:
        "$ENV{'HOME'}/.txt2html.dict" -- this is the same as for the
        txt2html script. If there is no $ENV{HOME} then it is just
        '.txt2html.dict')

    demoronize
            demoronize=>1

        Convert Microsoft-generated character codes that are non-ISO codes
        into something more reasonable. (default:true)

    doctype
            doctype=>I

        This gets put in the DOCTYPE field at the top of the document,
        unless it's empty.

        Default : '-//W3C//DTD HTML 4.01//EN"
        "http://www.w3.org/TR/html4/strict.dtd'

        If xhtml is true, the contents of this is ignored, unless it's
        empty, in which case no DOCTYPE declaration is output.

    eight_bit_clean
            eight_bit_clean=>1

        If false, convert Latin-1 characters to HTML entities. If true, this
        conversion is disabled; also "demoronize" is set to false, since
        this also changes 8-bit characters. (default: false)

    escape_HTML_chars
            escape_HTML_chars=>1

        turn & < > into & > < (default: true)

    explicit_headings
            explicit_headings=>1

        Don't try to find any headings except the ones specified in the
        --custom_heading_regexp option. Also, the custom headings will not
        be assigned levels in the order they are encountered in the
        document, but in the order they are specified on the
        custom_heading_regexp option. (default: false)

    extract
            extract=>1

        Extract Mode; don't put HTML headers or footers on the result, just
        the plain HTML (thus making the result suitable for inserting into
        another document (or as part of the output of a CGI script).
        (default: false)

    hrule_min
            hrule_min=>I

        Min number of ---s for an HRule. (default: 4)

    indent_width
            indent_width=>I

        Indents this many spaces for each level of a list. (default: 2)

    indent_par_break
            indent_par_break=>1

        Treat paragraphs marked solely by indents as breaks with indents.
        That is, instead of taking a three-space indent as a new paragraph,
        put in a 
     and three non-breaking spaces instead. (see also
        --preserve_indent) (default: false)

    infile
            infile=>\@my_files
            infile=>['chapter1.txt', 'chapter2.txt']

        The name of the input file(s). This expects a reference to an array
        of filenames.

        The special filename '-' designates STDIN.

        See also "inhandle" and "instring".

        (default:-)

    inhandle
            inhandle=>\@my_handles
            inhandle=>[\*MYINHANDLE, \*STDIN]

        An array of input filehandles; use this instead of "infile" or
        "instring" to use a filehandle or filehandles as input.

    instring
            instring=>\@my_strings
            instring=>[$string1, $string2]

        An array of input strings; use this instead of "infile" or
        "inhandle" to use a string or strings as input.

    italic_delimiter
            italic_delimiter=>I

        This defines what character (or string) is taken to be the delimiter
        of text which is to be interpreted as italic (that is, to be given a
        EM tag). If this is empty, no italicising of text will be done.
        (default: *)

    underline_delimiter
            underline_delimiter=>I

        This defines what character (or string) is taken to be the delimiter
        of text which is to be interpreted as underlined (that is, to be
        given a U tag). If this is empty, no underlining of text will be
        done. (default: _)

    links_dictionaries
            links_dictionaries=>\@my_link_dicts
            links_dictionaries=>['url_links.dict', 'format_links.dict']

        File(s) to use as a link-dictionary. There can be more than one of
        these. These are in addition to the Global Link Dictionary and the
        User Link Dictionary. This expects a reference to an array of
        filenames.

    link_only
            link_only=>1

        Do no escaping or marking up at all, except for processing the links
        dictionary file and applying it. This is useful if you want to use
        the linking feature on an HTML document. If the HTML is a complete
        document (includes HTML,HEAD,BODY tags, etc) then you'll probably
        want to use the --extract option also. (default: false)

    lower_case_tags
             lower_case_tags=>1

        Force all tags to be in lower-case.

    mailmode
            mailmode=>1

        Deal with mail headers & quoted text. The mail header paragraph is
        given the class 'mail_header', and mail-quoted text is given the
        class 'quote_mail'. (default: false)

    make_anchors
            make_anchors=>0

        Should we try to make anchors in headings? (default: true)

    make_links
            make_links=>0

        Should we try to build links? If this is false, then the links
        dictionaries are not consulted and only structural text-to-HTML
        conversion is done. (default: true)

    make_tables
            make_tables=>1

        Should we try to build tables? If true, spots tables and marks them
        up appropriately. See "Input File Format" for information on how
        tables should be formatted.

        This overrides the detection of lists; if something looks like a
        table, it is taken as a table, and list-checking is not done for
        that paragraph.

        (default: false)

    min_caps_length
            min_caps_length=>I

        min sequential CAPS for an all-caps line (default: 3)

    outfile
            outfile=>I

        The name of the output file. If it is "-" then the output goes to
        Standard Output. (default: - )

    outhandle
        The output filehandle; if this is given then the output goes to this
        filehandle instead of to the file given in "outfile".

    par_indent
            par_indent=>I

        Minimum number of spaces indented in first lines of paragraphs. Only
        used when there's no blank line preceding the new paragraph.
        (default: 2)

    preformat_trigger_lines
            preformat_trigger_lines=>I

        How many lines of preformatted-looking text are needed to switch to
        
     <= 0 : Preformat entire document 1 : one line triggers >= 2 :
        two lines trigger

        (default: 2)

    endpreformat_trigger_lines
            endpreformat_trigger_lines=>I

        How many lines of unpreformatted-looking text are needed to switch
        from 
     <= 0 : Never preformat within document 1 : one line
        triggers >= 2 : two lines trigger (default: 2)

        NOTE for preformat_trigger_lines and endpreformat_trigger_lines: A
        zero takes precedence. If one is zero, the other is ignored. If both
        are zero, entire document is preformatted.

    preformat_start_marker
            preformat_start_marker=>I

        What flags the start of a preformatted section if
        --use_preformat_marker is true.

        (default: "^(:?(:?<)|<)PRE(:?(:?>)|>)\$")

    preformat_end_marker
            preformat_end_marker=>I

        What flags the end of a preformatted section if
        --use_preformat_marker is true.

        (default: "^(:?(:?<)|<)/PRE(:?(:?>)|>)\$")

    preformat_whitespace_min
            preformat_whitespace_min=>I

        Minimum number of consecutive whitespace characters to trigger
        normal preformatting. NOTE: Tabs are expanded to spaces before this
        check is made. That means if tab_width is 8 and this is 5, then one
        tab may be expanded to 8 spaces, which is enough to trigger
        preformatting. (default: 5)

    prepend_file
            prepend_file=>I

        If you want something prepended to the processed body text, put the
        filename here. The prepended text will not be processed at all, so
        make sure it's plain text or correct HTML.

        (default: nothing)

    preserve_indent
            preserve_indent=>1

        Preserve the first-line indentation of paragraphs marked with
        indents by replacing the spaces of the first line with non-breaking
        spaces. (default: false)

    short_line_length
            short_line_length=>I

        Lines this short (or shorter) must be intentionally broken and are
        kept that short. (default: 40)

    style_url
            style_url=>I

        This gives the URL of a stylesheet; a LINK tag will be added to the
        output.

    tab_width
            tab_width=>I

        How many spaces equal a tab? (default: 8)

    table_type
            table_type=>{ ALIGN=>0, PGSQL=>0, BORDER=>1, DELIM=>0 }

        This determines which types of tables will be recognised when
        "make_tables" is true. The possible types are ALIGN, PGSQL, BORDER
        and DELIM. (default: all types are true)

    title
            title=>I

        You can specify a title. Otherwise it will use a blank one.
        (default: nothing)

    titlefirst
            titlefirst=>1

        Use the first non-blank line as the title. (See also "title")

    underline_length_tolerance
            underline_length_tolerance=>I<n>

        How much longer or shorter can underlines be and still be
        underlines? (default: 1)

    underline_offset_tolerance
            underline_offset_tolerance=>I<n>

        How far offset can underlines be and still be underlines? (default:
        1)

    unhyphenation
            unhyphenation=>0

        Enables unhyphenation of text. (default: true)

    use_mosaic_header
            use_mosaic_header=>1

        Use this option if you want to force the heading styles to match
        what Mosaic outputs. (Underlined with "***"s is H1, with "==="s is
        H2, with "+++" is H3, with "---" is H4, with "~~~" is H5 and with
        "..." is H6) This was the behavior of txt2html up to version 1.10.
        (default: false)

    use_preformat_marker
            use_preformat_marker=>1

        Turn on preformatting when encountering "<PRE>" on a line by itself,
        and turn it off when there's a line containing only "</PRE>". When
        such preformatted text is detected, the PRE tag will be given the
        class 'quote_explicit'. (default: off)

    xhtml
            xhtml=>1

        Try to make the output conform to the XHTML standard, including
        closing all open tags and marking empty tags correctly. This turns
        on --lower_case_tags and overrides the --doctype option. Note that
        if you add a header or a footer file, it is up to you to make it
        conform; the header/footer isn't touched by this. Likewise, if you
        make link-dictionary entries that break XHTML, then this won't fix
        them, except to the degree of putting all tags into lower-case.

        (default: true)

DEBUGGING
    There are global variables for setting types and levels of debugging.
    These should only be used by developers.

    $HTML::TextToHTML::Debug
        $HTML::TextToHTML::Debug = 1;

        Enable copious debugging output. (default: false)

    $HTML::TextToHTML::DictDebug
            $HTML::TextToHTML::DictDebug = I<n>;

        Debug mode for link dictionaries. Bitwise-Or what you want to see:

                  1: The parsing of the dictionary
                  2: The code that will make the links
                  4: When each rule matches something
                  8: When each tag is created

        (default: 0)

METHODS
  new
        $conv = new HTML::TextToHTML()

        $conv = new HTML::TextToHTML(titlefirst=>1,
            ...
        );

    Create a new object with new. If arguments are given, these arguments
    will be used in invocations of other methods.

    See "OPTIONS" for the possible values of the arguments.

  args
        $conv->args(short_line_length=>60,
            titlefirst=>1,
            ....
        );

    Updates the current arguments/options of the HTML::TextToHTML object.
    Takes hash of arguments, which will be used in invocations of other
    methods. See "OPTIONS" for the possible values of the arguments.

  process_chunk
    $newstring = $conv->process_chunk($mystring);

    Convert a string to a HTML fragment. This assumes that this string is at
    the least, a single paragraph, but it can contain more than that. This
    returns the processed string. If you want to pass arguments to alter the
    behaviour of this conversion, you need to do that earlier, either when
    you create the object, or with the "args" method.

        $newstring = $conv->process_chunk($mystring,
                                close_tags=>0);

    If there are open tags (such as lists) in the input string,
    process_chunk will automatically close them, unless you specify not to,
    with the close_tags option.

        $newstring = $conv->process_chunk($mystring,
                                is_fragment=>1);

    If you want this string to be treated as a fragment, and not assumed to
    be a paragraph, set is_fragment to true. If there is more than one
    paragraph in the string (ie it contains blank lines) then this option
    will be ignored.

  process_para
    $newstring = $conv->process_para($mystring);

    Convert a string to a HTML fragment. This assumes that this string is at
    the most a single paragraph, with no blank lines in it. If you don't
    know whether your string will contain blank lines or not, use the
    "process_chunk" method instead.

    This returns the processed string. If you want to pass arguments to
    alter the behaviour of this conversion, you need to do that earlier,
    either when you create the object, or with the "args" method.

        $newstring = $conv->process_para($mystring,
                                close_tags=>0);

    If there are open tags (such as lists) in the input string, process_para
    will automatically close them, unless you specify not to, with the
    close_tags option.

        $newstring = $conv->process_para($mystring,
                                is_fragment=>1);

    If you want this string to be treated as a fragment, and not assumed to
    be a paragraph, set is_fragment to true.

  txt2html
        $conv->txt2html(%args);

    Convert a text file to HTML. Takes a hash of arguments. See "OPTIONS"
    for the possible values of the arguments. Arguments which have already
    been set with new or args will remain as they are, unless they are
    overridden.

PRIVATE METHODS
    These are methods used internally, only of interest to developers.

  init_our_data
    $self->init_our_data();

    Initializes the internal object data.

  deal_with_options
    $self->deal_with_options();

    do extra processing related to particular options

  escape
    $newtext = escape($text);

    Escape & < and >

  demoronize_char
    $newtext = demoronize_char($text);

    Convert Microsoft character entities into characters.

    Added by Alan Jackson, alan at ajackson dot org, and based on the
    demoronize script by John Walker, http://www.fourmilab.ch/

  demoronize_code
    $newtext = demoronize_code($text);

    convert Microsoft character entities into HTML code

  get_tag
    $tag = $self->get_tag($in_tag);

    $tag = $self->get_tag($in_tag, tag_type=>TAG_START, inside_tag=>'');

    output the tag wanted (add the <> and the / if necessary) - output in
    lower or upper case - do tag-related processing options:
    tag_type=>TAG_START | tag_type=>TAG_END | tag_type=>TAG_EMPTY (default
    start) inside_tag=>string (default empty)

  close_tag
    $tag = $self->close_tag($in_tag);

    close the open tag

  hrule
       $self->hrule(para_lines_ref=>$para_lines,
                 para_action_ref=>$para_action,
                 ind=>0);

    Deal with horizontal rules.

  shortline
        $self->shortline(line_ref=>$line_ref,
                         line_action_ref=>$line_action_ref,
                         prev_ref=>$prev_ref,
                         prev_action_ref=>$prev_action_ref,
                         prev_line_len=>$prev_line_len);

    Deal with short lines.

  is_mailheader
        if ($self->is_mailheader(rows_ref=>$rows_ref))
        {
            ...
        }

    Is this a mailheader line?

  mailheader
        $self->mailheader(rows_ref=>$rows_ref);

    Deal with a mailheader.

  mailquote
        $self->mailquote(line_ref=>$line_ref,
                         line_action_ref=>$line_action_ref,
                         prev_ref=>$prev_ref,
                         prev_action_ref=>$prev_action_ref,
                         next_ref=>$next_ref);

    Deal with quoted mail.

  subtract_modes
        $newvector = subtract_modes($vector, $mask);

    Subtracts modes listed in $mask from $vector.

  paragraph
        $self->paragraph(line_ref=>$line_ref,
                         line_action_ref=>$line_action_ref,
                         prev_ref=>$prev_ref,
                         prev_action_ref=>$prev_action_ref,
                         line_indent=>$line_indent,
                         prev_indent=>$prev_indent,
                         is_fragment=>$is_fragment,
                         ind=>$ind);

    Detect paragraph indentation.

  listprefix
        ($prefix, $number, $rawprefix, $term) = $self->listprefix($line);

    Detect and parse a list item.

  startlist
        $self->startlist(prefix=>$prefix,
                         number=>0,
                         rawprefix=>$rawprefix,
                         term=>$term,
                         para_lines_ref=>$para_lines_ref,
                         para_action_ref=>$para_action_ref,
                         ind=>0,
                         prev_ref=>$prev_ref,
                         total_prefix=>$total_prefix);

    Start a list.

  endlist
        $self->endlist(num_lists=>0,
            prev_ref=>$prev_ref,
            line_action_ref=>$line_action_ref);

    End N lists

  continuelist
        $self->continuelist(para_lines_ref=>$para_lines_ref,
                            para_action_ref=>$para_action_ref,
                            ind=>0,
                            term=>$term);

    Continue a list.

  liststuff
        $self->liststuff(para_lines_ref=>$para_lines_ref,
                         para_action_ref=>$para_action_ref,
                         para_line_indent_ref=>$para_line_indent_ref,
                         ind=>0,
                         prev_ref=>$prev_ref);

    Process a list (higher-level method).

  get_table_type
        $table_type = $self->get_table_type(rows_ref=>$rows_ref,
                                            para_len=>0);

    Figure out the table type of this table, if any

  is_aligned_table
        if ($self->is_aligned_table(rows_ref=>$rows_ref, para_len=>0))
        {
            ...
        }

    Check if the given paragraph-array is an aligned table

  is_pgsql_table
        if ($self->is_pgsql_table(rows_ref=>$rows_ref, para_len=>0))
        {
            ...
        }

    Check if the given paragraph-array is a Postgresql table (the ascii
    format produced by Postgresql)

    A PGSQL table can start with an optional table-caption,

        then it has a row of column headings separated by |
        then it has a row of ------+-----
        then it has one or more rows of column values separated by |
        then it has a row-count (N rows)

  is_border_table
        if ($self->is_border_table(rows_ref=>$rows_ref, para_len=>0))
        {
            ...
        }

    Check if the given paragraph-array is a Border table.

    A BORDER table can start with an optional table-caption,

        then it has a row of +------+-----+
        then it has a row of column headings separated by |
        then it has a row of +------+-----+
        then it has one or more rows of column values separated by |
        then it has a row of +------+-----+

  is_delim_table
        if ($self->is_delim_table(rows_ref=>$rows_ref, para_len=>0))
        {
            ...
        }

    Check if the given paragraph-array is a Delimited table.

    A DELIM table can start with an optional table-caption, then it has at
    least two rows which start and end and are punctuated by a
    non-alphanumeric delimiter.

        | val1 | val2 |
        | val3 | val4 |

  tablestuff
        $self->tablestuff(table_type=>0,
                          rows_ref=>$rows_ref,
                          para_len=>0);

    Process a table.

  make_aligned_table
        $self->make_aligned_table(rows_ref=>$rows_ref,
                                  para_len=>0);

    Make an Aligned table.

  make_pgsql_table
        $self->make_pgsql_table(rows_ref=>$rows_ref,
                                  para_len=>0);

    Make a PGSQL table.

  make_border_table
        $self->make_border_table(rows_ref=>$rows_ref,
                                 para_len=>0);

    Make a BORDER table.

  make_delim_table
        $self->make_delim_table(rows_ref=>$rows_ref,
                                para_len=>0);

    Make a Delimited table.

  is_preformatted
        if ($self->is_preformatted($line))
        {
            ...
        }

    Returns true if the passed string is considered to be preformatted.

  split_end_explicit_preformat
        $front = $self->split_end_explicit_preformat(para_ref=>$para_ref);

    Modifies the given string, and returns the front preformatted part.

  endpreformat
        $self->endpreformat(para_lines_ref=>$para_lines_ref,
                            para_action_ref=>$para_action_ref,
                            ind=>0,
                            prev_ref=>$prev_ref);

    End a preformatted section.

  preformat
        $self->preformat(mode_ref=>$mode_ref,
                         line_ref=>$line_ref,
                         line_action_ref=>$line_action_ref,
                         prev_ref=>$prev_ref,
                         next_ref=>$next_ref,
                         prev_action_ref);

    Detect and process a preformatted section.

  make_new_anchor
        $anchor = $self->make_new_anchor($heading_level);

    Make a new anchor.

  anchor_mail
        $self->anchor_mail($line_ref);

    Make an anchor for a mail section.

  anchor_heading
        $self->anchor_heading($heading_level, $line_ref);

    Make an anchor for a heading.

  heading_level
        $self->heading_level($style);

    Add a new heading style if this is a new heading style.

  is_ul_list_line
        if ($self->is_ul_list_line($line))
        {
            ...
        }

    Tests if this line starts a UL list item.

  is_heading
        if ($self->is_heading(line_ref=>$line_ref, next_ref=>$next_ref))
        {
            ...
        }

    Tests if this line is a heading. Needs to take account of the next line,
    because a standard heading is defined by "underlining" the text of the
    heading.

  heading
        $self->heading(line_ref=>$line_ref,
            next_ref=>$next_ref);

    Make a heading. Assumes is_heading is true.

  is_custom_heading
        if ($self->is_custom_heading($line))
        {
            ...
        }

    Check if the given line matches a custom heading.

  custom_heading
        $self->custom_heading(line_ref=>$line_ref);

    Make a custom heading. Assumes is_custom_heading is true.

  unhyphenate_para
        $self->unhyphenate_para($para_ref);

    Join up hyphenated words that are split across lines.

  tagline
        $self->tagline($tag, $line_ref);

    Put the given tag around the given line.

  iscaps
        if ($self->iscaps($line))
        {
            ...
        }

    Check if a line is all capitals.

  caps
        $self->caps(line_ref=>$line_ref,
                    line_action_ref=>$line_action_ref);

    Detect and deal with an all-caps line.

  do_delim
        $self->do_delim(line_ref=>$line_ref,
                        line_action_ref=>$line_action_ref,
                        delim=>'*',
                        tag=>'STRONG');

    Deal with a line which has words delimited by the given delimiter; this
    is used to deal with italics, bold and underline formatting.

  glob2regexp
        $regexp = glob2regexp($glob);

    Convert very simple globs to regexps

  add_regexp_to_links_table
        $self->add_regexp_to_links_table(label=>$label,
                                         pattern=>$pattern,
                                         url=>$url,
                                         switches=>$switches);

    Add the given regexp "link definition" to the links table.

  add_literal_to_links_table
        $self->add_literal_to_links_table(label=>$label,
                                          pattern=>$pattern,
                                          url=>$url,
                                          switches=>$switches);

    Add the given literal "link definition" to the links table.

  add_glob_to_links_table
        $self->add_glob_to_links_table(label=>$label,
                                       pattern=>$pattern,
                                       url=>$url,
                                       switches=>$switches);

    Add the given glob "link definition" to the links table.

  parse_dict
        $self->parse_dict($dictfile, $dict);

    Parse the dictionary file. (see also load_dictionary_links, for things
    that were stripped)

  setup_dict_checking
        $self->setup_dict_checking();

    Set up the dictionary checking.

  in_link_context
        if ($self->in_link_context($match, $before))
        {
            ...
        }

    Check if we are inside a link (<a ...>); certain kinds of substitution
    are not allowed here.

  apply_links
        $self->apply_links(para_ref=>$para_ref,
                           para_action_ref=>$para_action_ref);

    Apply links and formatting to this paragraph.

  check_dictionary_links
        $self->check_dictionary_links(line_ref=>$line_ref,
                                      line_action_ref=>$line_action_ref);

    Check (and alter if need be) the bits in this line matching the patterns
    in the link dictionary.

  load_dictionary_links
        $self->load_dictionary_links();

    Load the dictionary links.

  do_file_start
        $self->do_file_start($outhandle, $para);

    Extra stuff needed for the beginning: HTML headers, and prepending a
    file if desired.

  do_init_call
        $self->do_init_call();

    Certain things, like reading link dictionaries, need to be done only
    once.

FILE FORMATS
    There are two files which are used which can affect the outcome of the
    conversion. One is the link dictionary, which contains patterns (of how
    to recognise http links and other things) and how to convert them. The
    other is, naturally, the format of the input file itself.

  Link Dictionary
    A link dictionary file contains patterns to match, and what to convert
    them to. It is called a "link" dictionary because it was intended to be
    something which defined what a href link was, but it can be used for
    more than that. However, if you wish to define your own links, it is
    strongly advised to read up on regular expressions (regexes) because
    this relies heavily on them.

    The file consists of comments (which are lines starting with #) and
    blank lines, and link entries. Each entry consists of a regular
    expression, a -> separator (with optional flags), and a link "result".

    In the simplest case, with no flags, the regular expression defines the
    pattern to look for, and the result says what part of the regular
    expression is the actual link, and the link which is generated has the
    href as the link, and the whole matched pattern as the visible part of
    the link. The first character of the regular expression is taken to be
    the separator for the regex, so one could either use the traditional /
    separator, or something else such as | (which can be helpful with URLs
    which are full of / characters).

    So, for example, an ftp URL might be defined as:

        |ftp:[\w/\.:+\-]+|      -> $&

    This takes the whole pattern as the href, and the resultant link has the
    same thing in the href as in the contents of the anchor.

    But sometimes the href isn't the whole pattern.

        /<URL:\s*(\S+?)\s*>/ --> $1

    With the above regex, a () grouping marks the first subexpression, which
    is represented as $1 (rather than $& the whole expression). This entry
    matches a URL which was marked explicitly as a URL with the pattern
    <URL:foo> (note the < is shown as the entity, not the actual
    character. This is because by the time the links dictionary is checked,
    all such things have already been converted to their HTML entity forms,
    unless, of course, the escape_HTML_chars option was turned off) This
    would give us a link in the form <A HREF="foo"><URL:foo></A>

    The h flag

    However, if we want more control over the way the link is constructed,
    we can construct it ourself. If one gives the h flag, then the "result"
    part of the entry is taken not to contain the href part of the link, but
    the whole link.

    For example, the entry:

        /<URL:\s*(\S+?)\s*>/ -h-> <A HREF="$1">$1</A>

    will take <URL:foo> and give us <A HREF="foo">foo</A>

    However, this is a very powerful mechanism, because it can be used to
    construct custom tags which aren't links at all. For example, to flag
    *italicised words* the following entry will surround the words with EM
    tags.

        /\B\*([a-z][a-z -]*[a-z])\*\B/ -hi-> <EM>$1</EM>

    The i flag

    This turns on ignore case in the pattern matching.

    The e flag

    This turns on execute in the pattern substitution. This really only
    makes sense if h is turned on too. In that case, the "result" part of
    the entry is taken as perl code to be executed, and the result of that
    code is what replaces the pattern.

    The o flag

    This marks the entry as a once-only link. This will convert the first
    instance of a matching pattern, and ignore any others further on.

    For example, the following pattern will take the first mention of
    HTML::TextToHTML and convert it to a link to the module's home page.

        "HTML::TextToHTML"  -io-> http://www.katspace.com/tools/text_to_html/

  Input File Format
    For the most part, this module tries to use intuitive conventions for
    determining the structure of the text input. Unordered lists are marked
    by bullets; ordered lists are marked by numbers or letters; in either
    case, an increase in indentation marks a sub-list contained in the outer
    list.

    Headers (apart from custom headers) are distinguished by "underlines"
    underneath them; headers in all-capitals are distinguished from those in
    mixed case. All headers, both normal and custom headers, are expected to
    start at the first line in a "paragraph".

    In other words, the following is a header:

        I am Head Man
        -------------

    But the following does not have a header:

        I am not a head Man, man
        I am Head Man
        -------------

    Tables require a more rigid convention. A table must be marked as a
    separate paragraph, that is, it must be surrounded by blank lines.
    Tables come in different types. For a table to be parsed, its
    --table_type option must be on, and the --make_tables option must be
    true.

    ALIGN Table Type

    Columns must be separated by two or more spaces (this prevents
    accidental incorrect recognition of a paragraph where interword spaces
    happen to line up). If there are two or more rows in a paragraph and all
    rows share the same set of (two or more) columns, the paragraph is
    assumed to be a table. For example

        -e  File exists.
        -z  File has zero size.
        -s  File has nonzero size (returns size).

    becomes

        <table>
        <tr><td>-e</td><td>File exists.</td></tr>
        <tr><td>-z</td><td>File has zero size.</td></tr>
        <tr><td>-s</td><td>File has nonzero size (returns size).</td></tr>
        </table>

    This guesses for each column whether it is intended to be left, centre
    or right aligned.

    BORDER Table Type

    This table type has nice borders around it, and will be rendered with a
    border, like so:

        +---------+---------+
        | Column1 | Column2 |
        +---------+---------+
        | val1    | val2    |
        | val3    | val3    |
        +---------+---------+

    The above becomes

        <table border="1">
        <thead><tr><th>Column1</th><th>Column2</th></tr></thead>
        <tbody>
        <tr><td>val1</td><td>val2</td></tr>
        <tr><td>val3</td><td>val3</td></tr>
        </tbody>
        </table>

    It can also have an optional caption at the start.

             My Caption
        +---------+---------+
        | Column1 | Column2 |
        +---------+---------+
        | val1    | val2    |
        | val3    | val3    |
        +---------+---------+

    PGSQL Table Type

    This format of table is what one gets from the output of a Postgresql
    query.

         Column1 | Column2
        ---------+---------
         val1    | val2
         val3    | val3
        (2 rows)

    This can also have an optional caption at the start. This table is also
    rendered with a border and table-headers like the BORDER type.

    DELIM Table Type

    This table type is delimited by non-alphanumeric characters, and has to
    have at least two rows and two columns before it's recognised as a
    table.

    This one is delimited by the '| character:

        | val1  | val2  |
        | val3  | val3  |

    But one can use almost any suitable character such as : # $ % + and so
    on. This is clever enough to figure out what you are using as the
    delimiter if you have your data set up like a table. Note that the line
    has to both begin and end with the delimiter, as well as using it to
    separate values.

    This can also have an optional caption at the start.

EXAMPLES
        use HTML::TextToHTML;

  Create a new object
        my $conv = new HTML::TextToHTML();

        my $conv = new HTML::TextToHTML(title=>"Wonderful Things",
                                default_link_dict=>$my_link_file,
          );

  Add further arguments
        $conv->args(short_line_length=>60,
                   preformat_trigger_lines=>4,
                   caps_tag=>"strong",
          );

  Convert a file
        $conv->txt2html(infile=>[$text_file],
                         outfile=>$html_file,
                         title=>"Wonderful Things",
                         mail=>1
          );

  Make a pipleline
        open(IN, "ls |") or die "could not open!";
        $conv->txt2html(inhandle=>[\*IN],
                         outfile=>'-',
          );

NOTES
    *   If the underline used to mark a header is off by more than 1, then
        that part of the text will not be picked up as a header unless you
        change the value of --underline_length_tolerance and/or
        --underline_offset_tolerance. People tend to forget this.

REQUIRES
    HTML::TextToHTML requires Perl 5.8.1 or later.

    For installation, it needs:

        Module::Build

    The txt2html script needs:

        Getopt::Long
        Getopt::ArgvFile
        Pod::Usage
        File::Basename

    For testing, it also needs:

        Test::More

    For debugging, it also needs:

        YAML::Syck

INSTALLATION
    Make sure you have the dependencies installed first! (see REQUIRES
    above)

    Some of those modules come standard with more recent versions of perl,
    but I thought I'd mention them anyway, just in case you may not have
    them.

    If you don't know how to install these, try using the CPAN module, an
    easy way of auto-installing modules from the Comprehensive Perl Archive
    Network, where the above modules reside. Do "perldoc perlmodinstall" or
    "perldoc CPAN" for more information.

    To install this module type the following:

       perl Build.PL
       ./Build
       ./Build test
       ./Build install

    Or, if you're on a platform (like DOS or Windows) that doesn't like the
    "./" notation, you can do this:

       perl Build.PL
       perl Build
       perl Build test
       perl Build install

    In order to install somewhere other than the default, such as in a
    directory under your home directory, like "/home/fred/perl" go

       perl Build.PL --install_base /home/fred/perl

    as the first step instead.

    This will install the files underneath /home/fred/perl.

    You will then need to make sure that you alter the PERL5LIB variable to
    find the modules, and the PATH variable to find the script.

    Therefore you will need to change: your path, to include
    /home/fred/perl/script (where the script will be)

            PATH=/home/fred/perl/script:${PATH}

    the PERL5LIB variable to add /home/fred/perl/lib

            PERL5LIB=/home/fred/perl/lib:${PERL5LIB}

    Note that the system links dictionary will be installed as
    "/home/fred/perl/share/txt2html/txt2html.dict"

    If you want to install in a temporary install directory (such as if you
    are building a package) then instead of going

       perl Build install

    go

       perl Build install destdir=/my/temp/dir

    and it will be installed there, with a directory structure under
    /my/temp/dir the same as it would be if it were installed plain. Note
    that this is NOT the same as setting --install_base, because certain
    things are done at build-time which use the install_base info.

    See "perldoc perlrun" for more information on PERL5LIB, and see "perldoc
    Module::Build" for more information on installation options.

BUGS
    Please, send to
    https://github.com/resurrecting-open-source-projects/txt2html/issues

SEE ALSO
    perl txt2html.

AUTHOR
        Kathryn Andersen (RUBYKAT)
        perlkat AT katspace dot com
        http//www.katspace.com/

    based on txt2html by Seth Golub

    Current homepage is
    https://github.com/resurrecting-open-source-projects/txt2html

COPYRIGHT AND LICENCE
    Original txt2html script copyright (c) 1994-2000 Seth Golub <seth AT
    aigeek.com>

    Copyright (c) 2002-2005 by Kathryn Andersen

    Copyright (c) 2018-2019 Joao Eriberto Mota Filho

    This program is free software; you can redistribute it and/or modify it
    under the same terms as Perl itself.

����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/TODO����������������������������������������������������������������������������������0000664�0000000�0000000�00000002131�13521162376�0013724�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������TODO list for txt2html
======================
  5. try to make this more thread-safe
    Added:19/01/07, 09:29  Priority: high

  6. add in an "obfustcate email addresses" facility
    Added:08/11/04, 15:19  Priority: medium

  7. convert (c) (r) and (tm) to the correct entities (add to links)
    Added:08/11/04, 15:20  Priority: medium

  8. add optional "enhanced" definition lists detection, which does Term:
    Defintion
    Added:08/11/04, 15:20  Priority: medium

  9. recognise and reproduce different Ordered List styles.
    Added:08/11/04, 15:20  Priority: medium

 10. links-per-section
    Added:08/11/04, 15:21  Priority: medium

 11. tables with multi-line cells
    Added:08/11/04, 15:21  Priority: medium

 12. option to add section-numbers to headers (not just header anchors)
    Added:08/11/04, 15:22  Priority: medium

      1. allow starting section number to be user-defined
        Added:08/11/04, 15:22  Priority: medium

 13. make this more efficient
    Added:23/01/05, 14:42  Priority: medium

 14. make a proper CGI script as an example
    Added:17/05/05, 22:09  Priority: medium

���������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/doc/����������������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0014004�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/doc/UPDATE-CHECK����������������������������������������������������������������������0000664�0000000�0000000�00000000226�13521162376�0015524�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������When updating, change the following files (if needed):

- ChangeLog
- Change version in all needed files (use rpl)
- Update MANIFEST
- Test in Debian
��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/lib/����������������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0014005�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/lib/HTML/�����������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0014551�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/lib/HTML/TextToHTML.pm����������������������������������������������������������������0000664�0000000�0000000�00000471264�13521162376�0017041�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������package HTML::TextToHTML;
{
  $HTML::TextToHTML::VERSION = '2.53';
}
use 5.8.1;
use strict;
#------------------------------------------------------------------------

=head1 NAME

HTML::TextToHTML - convert plain text file to HTML.

=head1 VERSION

version 2.53

=head1 SYNOPSIS

  From the command line:

    txt2html I<arguments>

  From Scripts:

    use HTML::TextToHTML;
 
    # create a new object
    my $conv = new HTML::TextToHTML();

    # convert a file
    $conv->txt2html(infile=>[$text_file],
                     outfile=>$html_file,
		     title=>"Wonderful Things",
		     mail=>1,
      ]);

    # reset arguments
    $conv->args(infile=>[], mail=>0);

    # convert a string
    $newstring = $conv->process_chunk($mystring)

=head1 DESCRIPTION

HTML::TextToHTML converts plain text files to HTML. The txt2html script
uses this module to do the same from the command-line.

It supports headings, tables, lists, simple character markup, and
hyperlinking, and is highly customizable. It recognizes some of the
apparent structure of the source document (mostly whitespace and
typographic layout), and attempts to mark that structure explicitly
using HTML. The purpose for this tool is to provide an easier way of
converting existing text documents to HTML format, giving something nicer
than just whapping the text into a big PRE block.

=head2 History

The original txt2html script was written by Seth Golub (see
http://www.aigeek.com/txt2html/), and converted to a perl module by
Kathryn Andersen (see http://www.katspace.com/tools/text_to_html/) and
made into a sourceforge project by Sun Tong (see
http://sourceforge.net/projects/txt2html/).  Earlier versions of the
HTML::TextToHTML module called the included script texthyper so as not
to clash with the original txt2html script, but now the projects have
all been merged. UPDATING: currently, the project is available on GitHub
at https://github.com/resurrecting-open-source-projects/txt2html

=head1 OPTIONS

All arguments can be set when the object is created, and further options
can be set when calling the actual txt2html method. Arguments
to methods can take a hash of arguments.

Note that all option-names must match exactly -- no abbreviations are
allowed.  The argument-keys are expected to have values matching those
required for that argument -- whether that be a boolean, a string, a
reference to an array or a reference to a hash.  These will replace any
value for that argument that might have been there before.

=over

=item append_file

    append_file=>I<filename>

If you want something appended by default, put the filename here.
The appended text will not be processed at all, so make sure it's
plain text or correct HTML.  i.e. do not have things like:
    Mary Andersen E<lt>kitty@example.comE<gt>
but instead, have:
    Mary Andersen <kitty@example.com>

(default: nothing)

=item append_head

    append_head=>I<filename>

If you want something appended to the head by default, put the filename here.
The appended text will not be processed at all, so make sure it's
plain text or correct HTML.  i.e. do not have things like:
    Mary Andersen E<lt>kitty@example.comE<gt>
but instead, have:
    Mary Andersen <kitty@example.com>

(default: nothing)

=item body_deco

    body_deco=>I<string>

Body decoration string: a string to be added to the BODY tag so that
one can set attributes to the BODY (such as class, style, bgcolor etc)
For example, "class='withimage'".

=item bold_delimiter

    bold_delimiter=>I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as bold (that is, to be given a STRONG
tag).  If this is empty, then no bolding of text will be done.
(default: #)

=item bullets

    bullets=>I<string>

This defines what single characters are taken to be "bullet" characters
for unordered lists.  Note that because this is used as a character
class, if you use '-' it must come first.
(default:-=o*\267)

=item bullets_ordered

    bullets_ordered=>I<string>

This defines what single characters are taken to be "bullet" placeholder
characters for ordered lists.  Ordered lists are normally marked by
a number or letter followed by '.' or ')' or ']' or ':'.  If an ordered
bullet is used, then it simply indicates that this is an ordered list,
without giving explicit numbers.

Note that because this is used as a character class, if you use '-' it
must come first.
(default:nothing)

=item caps_tag

    caps_tag=>I<tag>

Tag to put around all-caps lines
(default: STRONG)
If an empty tag is given, then no tag will be put around all-caps lines.

=item custom_heading_regexp

    custom_heading_regexp=>\@custom_headings

Add patterns for headings.  Header levels are assigned by regexp in the
order seen in the input text. When a line matches a custom header
regexp, it is tagged as a header.  If it's the first time that
particular regexp has matched, the next available header level is
associated with it and applied to the line.  Any later matches of that
regexp will use the same header level.  Therefore, if you want to match
numbered header lines, you could use something like this:

    my @custom_headings = ('^ *\d+\. \w+',
			   '^ *\d+\.\d+\. \w+',
			   '^ *\d+\.\d+\.\d+\. \w+');

    ...
	custom_heading_regexp=>\@custom_headings,
    ...

Then lines like

                " 1. Examples "
                " 1.1. Things"
            and " 4.2.5. Cold Fusion"

Would be marked as H1, H2, and H3 (assuming they were found in that
order, and that no other header styles were encountered).
If you prefer that the first one specified always be H1, the second
always be H2, the third H3, etc, then use the "explicit_headings"
option.

This expects a reference to an array of strings.

(default: none)

=item default_link_dict

    default_link_dict=>I<filename>

The name of the default "user" link dictionary.
(default: "$ENV{'HOME'}/.txt2html.dict" -- this is the same as for
the txt2html script.  If there is no $ENV{HOME} then it is just '.txt2html.dict')

=item demoronize

    demoronize=>1

Convert Microsoft-generated character codes that are non-ISO codes into
something more reasonable.
(default:true)

=item doctype

    doctype=>I<doctype>

This gets put in the DOCTYPE field at the top of the document, unless it's
empty.

Default :
'-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd'

If B<xhtml> is true, the contents of this is ignored, unless it's
empty, in which case no DOCTYPE declaration is output.

=item eight_bit_clean

    eight_bit_clean=>1

If false, convert Latin-1 characters to HTML entities.
If true, this conversion is disabled; also "demoronize" is set to
false, since this also changes 8-bit characters.
(default: false)

=item escape_HTML_chars

    escape_HTML_chars=>1

turn & E<lt> E<gt> into & > <
(default: true)

=item explicit_headings

    explicit_headings=>1

Don't try to find any headings except the ones specified in the
--custom_heading_regexp option.
Also, the custom headings will not be assigned levels in the order they
are encountered in the document, but in the order they are specified on
the custom_heading_regexp option.
(default: false)

=item extract

    extract=>1

Extract Mode; don't put HTML headers or footers on the result, just
the plain HTML (thus making the result suitable for inserting into
another document (or as part of the output of a CGI script).
(default: false)

=item hrule_min

    hrule_min=>I<n>

Min number of ---s for an HRule.
(default: 4)

=item indent_width

    indent_width=>I<n>

Indents this many spaces for each level of a list.
(default: 2)

=item indent_par_break

    indent_par_break=>1

Treat paragraphs marked solely by indents as breaks with indents.
That is, instead of taking a three-space indent as a new paragraph,
put in a <BR> and three non-breaking spaces instead.
(see also --preserve_indent)
(default: false)

=item infile

    infile=>\@my_files
    infile=>['chapter1.txt', 'chapter2.txt']

The name of the input file(s).  
This expects a reference to an array of filenames.

The special filename '-' designates STDIN.

See also L</inhandle> and L</instring>.

(default:-)

=item inhandle

    inhandle=>\@my_handles
    inhandle=>[\*MYINHANDLE, \*STDIN]

An array of input filehandles; use this instead of
L</infile> or L</instring> to use a filehandle or filehandles
as input.

=item instring

    instring=>\@my_strings
    instring=>[$string1, $string2]

An array of input strings; use this instead of
L</infile> or L</inhandle> to use a string or strings
as input.

=item italic_delimiter

    italic_delimiter=>I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as italic (that is, to be given a EM
tag).  If this is empty, no italicising of text will be done.
(default: *)

=item underline_delimiter

    underline_delimiter=>I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as underlined (that is, to be given a U
tag).  If this is empty, no underlining of text will be done.
(default: _)

=item links_dictionaries

    links_dictionaries=>\@my_link_dicts
    links_dictionaries=>['url_links.dict', 'format_links.dict']

File(s) to use as a link-dictionary.  There can be more than one of
these.  These are in addition to the Global Link Dictionary and the User
Link Dictionary.  This expects a reference to an array of filenames.

=item link_only

    link_only=>1

Do no escaping or marking up at all, except for processing the links
dictionary file and applying it.  This is useful if you want to use
the linking feature on an HTML document.  If the HTML is a
complete document (includes HTML,HEAD,BODY tags, etc) then you'll
probably want to use the --extract option also.
(default: false)

=item lower_case_tags

     lower_case_tags=>1

Force all tags to be in lower-case.

=item mailmode

    mailmode=>1

Deal with mail headers & quoted text.  The mail header paragraph is
given the class 'mail_header', and mail-quoted text is given the class
'quote_mail'.
(default: false)

=item make_anchors

    make_anchors=>0

Should we try to make anchors in headings?
(default: true)

=item make_links

    make_links=>0

Should we try to build links?  If this is false, then the links
dictionaries are not consulted and only structural text-to-HTML
conversion is done.  (default: true)

=item make_tables

    make_tables=>1

Should we try to build tables?  If true, spots tables and marks them up
appropriately.  See L</Input File Format> for information on how tables
should be formatted.

This overrides the detection of lists; if something looks like a table,
it is taken as a table, and list-checking is not done for that
paragraph.

(default: false)

=item min_caps_length

    min_caps_length=>I<n>

min sequential CAPS for an all-caps line
(default: 3)

=item outfile

    outfile=>I<filename>

The name of the output file.  If it is "-" then the output goes
to Standard Output.
(default: - )

=item outhandle

The output filehandle; if this is given then the output goes
to this filehandle instead of to the file given in L</outfile>.

=item par_indent

    par_indent=>I<n>

Minimum number of spaces indented in first lines of paragraphs.
  Only used when there's no blank line
preceding the new paragraph.
(default: 2)

=item preformat_trigger_lines

    preformat_trigger_lines=>I<n>

How many lines of preformatted-looking text are needed to switch to <PRE>
          <= 0 : Preformat entire document
             1 : one line triggers
          >= 2 : two lines trigger

(default: 2)

=item endpreformat_trigger_lines

    endpreformat_trigger_lines=>I<n>

How many lines of unpreformatted-looking text are needed to switch from <PRE>
           <= 0 : Never preformat within document
              1 : one line triggers
           >= 2 : two lines trigger
(default: 2)

NOTE for preformat_trigger_lines and endpreformat_trigger_lines:
A zero takes precedence.  If one is zero, the other is ignored.
If both are zero, entire document is preformatted.

=item preformat_start_marker

    preformat_start_marker=>I<regexp>

What flags the start of a preformatted section if --use_preformat_marker
is true.

(default: "^(:?(:?<)|<)PRE(:?(:?>)|>)\$")

=item preformat_end_marker

    preformat_end_marker=>I<regexp>

What flags the end of a preformatted section if --use_preformat_marker
is true.

(default: "^(:?(:?<)|<)/PRE(:?(:?>)|>)\$")

=item preformat_whitespace_min

    preformat_whitespace_min=>I<n>

Minimum number of consecutive whitespace characters to trigger
normal preformatting. 
NOTE: Tabs are expanded to spaces before this check is made.
That means if B<tab_width> is 8 and this is 5, then one tab may be
expanded to 8 spaces, which is enough to trigger preformatting.
(default: 5)

=item prepend_file

    prepend_file=>I<filename>

If you want something prepended to the processed body text, put the
filename here.  The prepended text will not be processed at all, so make
sure it's plain text or correct HTML.

(default: nothing)

=item preserve_indent

    preserve_indent=>1

Preserve the first-line indentation of paragraphs marked with indents
by replacing the spaces of the first line with non-breaking spaces.
(default: false)

=item short_line_length

    short_line_length=>I<n>

Lines this short (or shorter) must be intentionally broken and are kept
that short.
(default: 40)

=item style_url

    style_url=>I<url>

This gives the URL of a stylesheet; a LINK tag will be added to the
output.

=item tab_width

    tab_width=>I<n>

How many spaces equal a tab?
(default: 8)

=item table_type
    
    table_type=>{ ALIGN=>0, PGSQL=>0, BORDER=>1, DELIM=>0 }

This determines which types of tables will be recognised when "make_tables"
is true.  The possible types are ALIGN, PGSQL, BORDER and DELIM.
(default: all types are true)

=item title

    title=>I<title>

You can specify a title.  Otherwise it will use a blank one.
(default: nothing)

=item titlefirst

    titlefirst=>1

Use the first non-blank line as the title. (See also "title")

=item underline_length_tolerance

    underline_length_tolerance=>I<n>

How much longer or shorter can underlines be and still be underlines?
(default: 1)

=item underline_offset_tolerance

    underline_offset_tolerance=>I<n>

How far offset can underlines be and still be underlines?
(default: 1)

=item unhyphenation

    unhyphenation=>0

Enables unhyphenation of text.
(default: true)

=item use_mosaic_header

    use_mosaic_header=>1

Use this option if you want to force the heading styles to match what Mosaic
outputs.  (Underlined with "***"s is H1,
with "==="s is H2, with "+++" is H3, with "---" is H4, with "~~~" is H5
and with "..." is H6)
This was the behavior of txt2html up to version 1.10.
(default: false)

=item use_preformat_marker

    use_preformat_marker=>1

Turn on preformatting when encountering "<PRE>" on a line by itself, and turn
it off when there's a line containing only "</PRE>".
When such preformatted text is detected, the PRE tag will be given the
class 'quote_explicit'.
(default: off)

=item xhtml

    xhtml=>1

Try to make the output conform to the XHTML standard, including
closing all open tags and marking empty tags correctly.  This
turns on --lower_case_tags and overrides the --doctype option.
Note that if you add a header or a footer file, it is up to you
to make it conform; the header/footer isn't touched by this.
Likewise, if you make link-dictionary entries that break XHTML,
then this won't fix them, except to the degree of putting all tags
into lower-case.

(default: true)

=back

=head1 DEBUGGING

There are global variables for setting types and levels
of debugging.  These should only be used by developers.

=over

=item $HTML::TextToHTML::Debug

$HTML::TextToHTML::Debug = 1;
    
Enable copious debugging output.
(default: false)

=item $HTML::TextToHTML::DictDebug

    $HTML::TextToHTML::DictDebug = I<n>;

Debug mode for link dictionaries. Bitwise-Or what you want to see:

          1: The parsing of the dictionary
          2: The code that will make the links
          4: When each rule matches something
          8: When each tag is created

(default: 0)

=back

=cut

our $Debug = 0;
our $DictDebug = 0;

=head1 METHODS

=cut

#------------------------------------------------------------------------
use YAML::Syck;

our $PROG = 'HTML::TextToHTML';

#------------------------------------------------------------------------

########################################
# Definitions  (Don't change these)
#

# These are just constants I use for making bit vectors to keep track
# of what modes I'm in and what actions I've taken on the current and
# previous lines.

our $NONE         = 0;
our $LIST         = 1;
our $HRULE        = 2;
our $PAR          = 4;
our $PRE          = 8;
our $END          = 16;
our $BREAK        = 32;
our $HEADER       = 64;
our $MAILHEADER   = 128;
our $MAILQUOTE    = 256;
our $CAPS         = 512;
our $LINK         = 1024;
our $PRE_EXPLICIT = 2048;
our $TABLE        = 4096;
our $IND_BREAK    = 8192;
our $LIST_START   = 16384;
our $LIST_ITEM    = 32768;

# Constants for Link-processing
# bit-vectors for what to do with a particular link-dictionary entry
our $LINK_NOCASE    = 1;
our $LINK_EVAL      = 2;
our $LINK_HTML      = 4;
our $LINK_ONCE      = 8;
our $LINK_SECT_ONCE = 16;

# Constants for Ordered Lists and Unordered Lists.
# And Definition Lists.
# I use this in the list stack to keep track of what's what.

our $OL = 1;
our $UL = 2;
our $DL = 3;

# Constants for table types
our $TAB_ALIGN  = 1;
our $TAB_PGSQL  = 2;
our $TAB_BORDER = 3;
our $TAB_DELIM  = 4;

# Constants for tags
use constant {
    TAG_START	=> 1,
    TAG_END	=> 2,
    TAG_EMPTY	=> 3,
};

# Character entity names
# characters to replace with entities
our %char_entities = (
    "\241", "¡",  "\242", "¢",   "\243", "£",
    "\244", "¤", "\245", "¥",    "\246", "¦",
    "\247", "§",   "\250", "¨",    "\251", "©",
    "\252", "ª",   "\253", "«",  "\254", "¬",
    "\255", "­",    "\256", "®",    "\257", "&hibar;",
    "\260", "°",    "\261", "±", "\262", "²",
    "\263", "³",   "\264", "´",  "\265", "µ",
    "\266", "¶",   "\270", "¸",  "\271", "¹",
    "\272", "º",   "\273", "»",  "\274", "¼",
    "\275", "½", "\276", "¾", "\277", "¿",
    "\300", "À", "\301", "Á", "\302", "Â",
    "\303", "Ã", "\304", "Ä",   "\305", "Å",
    "\306", "Æ",  "\307", "Ç", "\310", "È",
    "\311", "É", "\312", "Ê",  "\313", "Ë",
    "\314", "Ì", "\315", "Í", "\316", "Î",
    "\317", "Ï",   "\320", "Ð",    "\321", "Ñ",
    "\322", "Ò", "\323", "Ó", "\324", "Ô",
    "\325", "Õ", "\326", "Ö",   "\327", "×",
    "\330", "Ø", "\331", "Ù", "\332", "Ú",
    "\333", "Û",  "\334", "Ü",   "\335", "Ý",
    "\336", "Þ",  "\337", "ß",  "\340", "à",
    "\341", "á", "\342", "â",  "\343", "ã",
    "\344", "ä",   "\345", "å",  "\346", "æ",
    "\347", "ç", "\350", "è", "\351", "é",
    "\352", "ê",  "\353", "ë",   "\354", "ì",
    "\355", "í", "\356", "î",  "\357", "ï",
    "\360", "ð",    "\361", "ñ", "\362", "ò",
    "\363", "ó", "\364", "ô",  "\365", "õ",
    "\366", "ö",   "\367", "÷", "\370", "ø",
    "\371", "ù", "\372", "ú", "\373", "û",
    "\374", "ü",   "\375", "ý", "\376", "þ",
    "\377", "ÿ",   "\267", "·",
);

# alignments for tables
our @alignments    = ('', '', ' ALIGN="RIGHT"', ' ALIGN="CENTER"');
our @lc_alignments = ('', '', ' align="right"', ' align="center"');
our @xhtml_alignments =
  ('', '', ' style="text-align: right;"', ' style="text-align: center;"');

#---------------------------------------------------------------#
# Object interface
#---------------------------------------------------------------#

=head2 new

    $conv = new HTML::TextToHTML()

    $conv = new HTML::TextToHTML(titlefirst=>1,
	...
    );

Create a new object with new. If arguments are given, these arguments
will be used in invocations of other methods.

See L</OPTIONS> for the possible values of the arguments.

=cut

sub new
{
    my $invocant = shift;
    my $self     = {};

    my $class = ref($invocant) || $invocant;    # Object or class name
    init_our_data($self);

    # bless self
    bless($self, $class);

    $self->args(@_);

    return $self;
}    # new

=head2 args

    $conv->args(short_line_length=>60,
	titlefirst=>1,
	....
    );

Updates the current arguments/options of the HTML::TextToHTML object.
Takes hash of arguments, which will be used in invocations of other
methods.
See L</OPTIONS> for the possible values of the arguments.

=cut

sub args
{
    my $self      = shift;
    my %args = @_;

    if (%args)
    {
        if ($Debug)
        {
            print STDERR "========args(hash)========\n";
            print STDERR Dump(%args);
        }
	my $arg;
	my $val;
	while (($arg, $val) = each %args)
        {
            if (defined $val)
            {
                if ($arg =~ /^-/)
                {
                    $arg =~ s/^-//;    # get rid of first dash
                    $arg =~ s/^-//;    # get rid of possible second dash
                }
                if ($Debug)
                {
                    print STDERR "--", $arg;
                }
                $self->{$arg} = $val;
                if ($Debug)
                {
                    print STDERR " ", $val, "\n";
                }
            }
        }
    }
    $self->deal_with_options();
    if ($Debug)
    {
        print STDERR Dump($self);
    }

    return 1;
}    # args

=head2 process_chunk

$newstring = $conv->process_chunk($mystring);

Convert a string to a HTML fragment.  This assumes that this string is
at the least, a single paragraph, but it can contain more than that.
This returns the processed string.  If you want to pass arguments to
alter the behaviour of this conversion, you need to do that earlier,
either when you create the object, or with the L</args> method.

    $newstring = $conv->process_chunk($mystring,
			    close_tags=>0);

If there are open tags (such as lists) in the input string,
process_chunk will automatically close them, unless you specify not
to, with the close_tags option.

    $newstring = $conv->process_chunk($mystring,
			    is_fragment=>1);

If you want this string to be treated as a fragment, and not assumed to
be a paragraph, set is_fragment to true.  If there is more than one
paragraph in the string (ie it contains blank lines) then this option
will be ignored.

=cut

sub process_chunk ($$;%)
{
    my $self  = shift;
    my $chunk = shift;
    my %args  = (
        close_tags  => 1,
        is_fragment => 0,
        @_
    );

    my $ret_str = '';
    my @paras   = split(/\r?\n\r?\n/, $chunk);
    my $ind     = 0;
    if (@paras == 1)    # just one paragraph
    {
        $ret_str .= $self->process_para(
            $chunk,
            close_tags  => $args{close_tags},
            is_fragment => $args{is_fragment}
        );
    }
    else
    {
        my $ind = 0;
        foreach my $para (@paras)
        {
            # if the paragraph doesn't end with a newline, add one
            $para .= "\n" if ($para !~ /\n$/);
            if ($ind == @paras - 1)    # last one
            {
                $ret_str .= $self->process_para(
                    $para,
                    close_tags  => $args{close_tags},
                    is_fragment => 0
                );
            }
            else
            {
                $ret_str .= $self->process_para(
                    $para,
                    close_tags  => 0,
                    is_fragment => 0
                );
            }
            $ind++;
        }
    }
    $ret_str;
}    # process_chunk

=head2 process_para

$newstring = $conv->process_para($mystring);

Convert a string to a HTML fragment.  This assumes that this string is
at the most a single paragraph, with no blank lines in it.  If you don't
know whether your string will contain blank lines or not, use the
L</process_chunk> method instead.

This returns the processed string.  If you want to pass arguments to
alter the behaviour of this conversion, you need to do that earlier,
either when you create the object, or with the L</args> method.

    $newstring = $conv->process_para($mystring,
			    close_tags=>0);

If there are open tags (such as lists) in the input string, process_para
will automatically close them, unless you specify not to, with the
close_tags option.

    $newstring = $conv->process_para($mystring,
			    is_fragment=>1);

If you want this string to be treated as a fragment, and not assumed to be
a paragraph, set is_fragment to true.

=cut

sub process_para ($$;%)
{
    my $self = shift;
    my $para = shift;
    my %args = (
        close_tags  => 1,
        is_fragment => 0,
        @_
    );

    # if this is an external call, do certain initializations
    $self->do_init_call();

    my $para_action = $NONE;

    # tables and mailheaders don't carry over from one para to the next
    if ($self->{__mode} & $TABLE)
    {
        $self->{__mode} ^= $TABLE;
    }
    if ($self->{__mode} & $MAILHEADER)
    {
        $self->{__mode} ^= $MAILHEADER;
    }

    # convert Microsoft character codes into sensible characters
    if ($self->{demoronize})
    {
        demoronize_char($para);
    }

    # if we are not just linking, we are discerning structure
    if (!$self->{link_only})
    {

        # Chop trailing whitespace and DOS CRs
        $para =~ s/[ \011]*\015$//;
        # Chop leading whitespace and DOS CRs
        $para =~ s/^[ \011]*\015//;
        $para =~ s/\r//g;             # remove any stray carriage returns

        my @done_lines = ();          # lines which have been processed

        # The PRE_EXPLICIT structure can carry over from one
        # paragraph to the next, but it is ended with the
        # explicit end-tag designated for it.
        # Therefore we can shortcut for this by checking
        # for the end of the PRE_EXPLICIT and chomping off
        # the preformatted string part of this para before
        # we have to split it into lines.
        # Note that after this check, we could *still* be
        # in PRE_EXPLICIT mode.
        if ($self->{__mode} & $PRE_EXPLICIT)
        {
            my $pre_str =
              $self->split_end_explicit_preformat(para_ref => \$para);
            if ($pre_str)
            {
                push @done_lines, $pre_str;
            }
        }

        if (defined $para && $para ne "")
        {
            #
            # Now we split the paragraph into lines
            #
            my $para_len         = length($para);
            my @para_lines       = split(/^/, $para);
            my @para_line_len    = ();
            my @para_line_indent = ();
            my @para_line_action = ();
            my $i                = 0;
            foreach my $line (@para_lines)
            {
                # Change all tabs to spaces
                while ($line =~ /\011/)
                {
                    my $tw = $self->{tab_width};
                    $line =~ s/\011/" " x ($tw - (length($`) % $tw))/e;
                }
                push @para_line_len, length($line);
                if ($line =~ /^\s*$/)
                {
                    # if the line is blank, use the previous indent
                    # if there is one
                    push @para_line_indent,
                      ($i == 0 ? 0 : $para_line_indent[$i - 1]);
                }
                else
                {
                    # count the number of leading spaces
                    my ($ws) = $line =~ /^( *)[^ ]/;
                    push @para_line_indent, length($ws);
                }
                push @para_line_action, $NONE;
                $i++;
            }

            # There are two more structures which carry over from one
            # paragraph to the next: LIST, PRE
            # There are also certain things which will immediately end
            # multi-paragraph LIST and PRE, if found at the start
            # of a paragraph:
            # A list will be ended by
            # TABLE, MAILHEADER, HEADER, custom-header
            # A PRE will be ended by
            # TABLE, MAILHEADER and non-pre text

            my $is_table         = 0;
            my $table_type       = 0;
            my $is_mailheader    = 0;
            my $is_header        = 0;
            my $is_custom_header = 0;
            if (@{$self->{custom_heading_regexp}})
            {
                $is_custom_header =
                  $self->is_custom_heading(line => $para_lines[0]);
            }
            if (   $self->{make_tables}
                && @para_lines > 1)
            {
                $table_type = $self->get_table_type(
                    rows_ref => \@para_lines,
                    para_len => $para_len
                );
                $is_table = ($table_type != 0);
            }
            if (   !$self->{explicit_headings}
                && @para_lines > 1
                && !$is_table)
            {
                $is_header = $self->is_heading(
                    line_ref => \$para_lines[0],
                    next_ref => \$para_lines[1]
                );
            }
            # Note that it is concievable that someone has
            # partially disabled mailmode by making a custom header
            # which matches the start of mail.
            # This is stupid, but allowable, so we check.
            if (   $self->{mailmode}
                && !$is_table
                && !$is_custom_header)
            {
                $is_mailheader = $self->is_mailheader(rows_ref => \@para_lines);
            }

            # end the list if we can end it
            if (
                ($self->{__mode} & $LIST)
                && (   $is_table
                    || $is_mailheader
                    || $is_header
                    || $is_custom_header)
              )
            {
                my $list_end = '';
                my $action   = 0;
                $self->endlist(
                    num_lists       => $self->{__listnum},
                    prev_ref        => \$list_end,
                    line_action_ref => \$action
                );
                push @done_lines, $list_end;
                $self->{__prev_para_action} |= $END;
            }

            # end the PRE if we can end it
            if (
                   ($self->{__mode} & $PRE)
                && !($self->{__mode} & $PRE_EXPLICIT)
                && (   $is_table
                    || $is_mailheader
                    || !$self->is_preformatted($para_lines[0]))
                && ($self->{preformat_trigger_lines} != 0)
              )
            {
                my $pre_end = '';
                my $tag     = $self->close_tag('pre');
                $pre_end = "${tag}\n";
                $self->{__mode} ^= ($PRE & $self->{__mode});
                push @done_lines, $pre_end;
                $self->{__prev_para_action} |= $END;
            }

            # The PRE and PRE_EXPLICIT structure can carry over
            # from one paragraph to the next, but because we don't
            # want trailing newlines, such newlines would have been
            # gotten rid of in the previous call.  However, with
            # a preformatted text, we do want the blank lines in it
            # to be preserved, so let's add a blank line in here.
            if ($self->{__mode} & $PRE)
            {
                push @done_lines, "\n";
            }

            # Now, we do certain things which are only found at the
            # start of a paragraph:
            # HEADER, custom-header, TABLE and MAILHEADER
            # These could concievably eat the rest of the paragraph.

            if ($is_custom_header)
            {
                # custom header eats the first line
                my $header = shift @para_lines;
                shift @para_line_len;
                shift @para_line_indent;
                shift @para_line_action;
                $self->custom_heading(line_ref => \$header);
                push @done_lines, $header;
                $self->{__prev_para_action} |= $HEADER;
            }
            elsif ($is_header)
            {
                # normal header eats the first two lines
                my $header = shift @para_lines;
                shift @para_line_len;
                shift @para_line_indent;
                shift @para_line_action;
                my $underline = shift @para_lines;
                shift @para_line_len;
                shift @para_line_indent;
                shift @para_line_action;
                $self->heading(
                    line_ref => \$header,
                    next_ref => \$underline
                );
                push @done_lines, $header;
                $self->{__prev_para_action} |= $HEADER;
            }

            # do the table stuff on the array of lines
            if ($self->{make_tables} && $is_table)
            {
                if (
                    $self->tablestuff(
                        table_type => $table_type,
                        rows_ref   => \@para_lines,
                        para_len   => $para_len
                    )
                  )
                {
                    # this has used up all the lines
                    push @done_lines, @para_lines;
                    @para_lines = ();
                }
            }

            # check of this para is a mail-header
            if (   $is_mailheader
                && !($self->{__mode} & $TABLE)
                && @para_lines)
            {
                $self->mailheader(rows_ref => \@para_lines);
                # this has used up all the lines
                push @done_lines, @para_lines;
                @para_lines = ();
            }

            #
            # Now go through the paragraph lines one at a time
            # Note that we won't have TABLE, MAILHEADER, HEADER modes
            # because they would have eaten the lines
            #
            my $prev        = '';
            my $prev_action = $self->{__prev_para_action};
            for (my $i = 0; $i < @para_lines; $i++)
            {
                my $prev_ref;
                my $prev_action_ref;
                my $prev_line_indent;
                my $prev_line_len;
                if ($i == 0)
                {
                    $prev_ref         = \$prev;
                    $prev_action_ref  = \$prev_action;
                    $prev_line_indent = 0;
                    $prev_line_len    = 0;
                }
                else
                {
                    $prev_ref         = \$para_lines[$i - 1];
                    $prev_action_ref  = \$para_line_action[$i - 1];
                    $prev_line_indent = $para_line_indent[$i - 1];
                    $prev_line_len    = $para_line_len[$i - 1];
                }
                my $next_ref;
                if ($i == $#para_lines)
                {
                    $next_ref = undef;
                }
                else
                {
                    $next_ref = \$para_lines[$i + 1];
                }

                $para_lines[$i] = escape($para_lines[$i])
                  if ($self->{escape_HTML_chars});

                if ($self->{mailmode}
                    && !($self->{__mode} & ($PRE_EXPLICIT)))
                {
                    $self->mailquote(
                        line_ref        => \$para_lines[$i],
                        line_action_ref => \$para_line_action[$i],
                        prev_ref        => $prev_ref,
                        prev_action_ref => $prev_action_ref,
                        next_ref        => $next_ref
                    );
                }

                if (   ($self->{__mode} & $PRE)
                    && ($self->{preformat_trigger_lines} != 0))
                {
                    $self->endpreformat(
                        para_lines_ref  => \@para_lines,
                        para_action_ref => \@para_line_action,
                        ind             => $i,
                        prev_ref        => $prev_ref
                    );
                }

                if (!($self->{__mode} & $PRE))
                {
                    $self->hrule(
                        para_lines_ref  => \@para_lines,
                        para_action_ref => \@para_line_action,
                        ind             => $i
                    );
                }
                if (!($self->{__mode} & ($PRE))
                    && ($para_lines[$i] !~ /^\s*$/))
                {
                    $self->liststuff(
                        para_lines_ref       => \@para_lines,
                        para_action_ref      => \@para_line_action,
                        para_line_indent_ref => \@para_line_indent,
                        ind                  => $i,
                        prev_ref             => $prev_ref
                    );
                }
                if (   !($para_line_action[$i] & ($HEADER | $LIST))
                    && !($self->{__mode} & ($LIST | $PRE))
                    && $self->{__preformat_enabled})
                {
                    $self->preformat(
                        mode_ref        => \$self->{__mode},
                        line_ref        => \$para_lines[$i],
                        line_action_ref => \$para_line_action[$i],
                        prev_ref        => $prev_ref,
                        next_ref        => $next_ref,
                        prev_action_ref => $prev_action_ref
                    );
                }
                if (!($self->{__mode} & ($PRE)))
                {
                    $self->paragraph(
                        line_ref        => \$para_lines[$i],
                        line_action_ref => \$para_line_action[$i],
                        prev_ref        => $prev_ref,
                        prev_action_ref => $prev_action_ref,
                        line_indent     => $para_line_indent[$i],
                        prev_indent     => $prev_line_indent,
                        is_fragment     => $args{is_fragment},
                        ind             => $i,
                    );
                }
                if (!($self->{__mode} & ($PRE | $LIST)))
                {
                    $self->shortline(
                        line_ref        => \$para_lines[$i],
                        line_action_ref => \$para_line_action[$i],
                        prev_ref        => $prev_ref,
                        prev_action_ref => $prev_action_ref,
                        prev_line_len   => $prev_line_len
                    );
                }
                if (!($self->{__mode} & ($PRE)))
                {
                    $self->caps(
                        line_ref        => \$para_lines[$i],
                        line_action_ref => \$para_line_action[$i]
                    );
                }

                # put the "prev" line in front of the first line
                $para_lines[$i] = $prev . $para_lines[$i]
                  if ($i == 0 && ($prev !~ /^\s*$/));
            }

            # para action is the action of the last line of the para
            $para_action = $para_line_action[$#para_line_action];
            $para_action = $NONE if (!defined $para_action);

            # push them on the done lines
            push @done_lines, @para_lines;
            @para_lines = ();

        }
        # now put the para back together as one string
        $para = join('', @done_lines);

        # if this is a paragraph, and we are in XHTML mode,
        # close an open paragraph.
        if ($self->{xhtml})
        {
            my $open_tag = @{$self->{__tags}}[$#{$self->{__tags}}];
            if (defined $open_tag && $open_tag eq 'p')
            {
                $para .= $self->close_tag('p');
            }
        }

        if (
            $self->{unhyphenation}

            # ends in hyphen & next line starts w/letters
            && ($para =~ /[^\W\d_]\-\n\s*[^\W\d_]/s) && !(
                $self->{__mode} &
                ($PRE | $HEADER | $MAILHEADER | $TABLE | $BREAK)
            )
          )
        {
            $self->unhyphenate_para(\$para);
        }
        # chop trailing newlines for continuing lists and PRE
        if (   $self->{__mode} & $LIST
            || $self->{__mode} & $PRE)
        {
            $para =~ s/\n$//g;
        }
    }

    # apply links and bold/italic/underline formatting
    if ($para !~ /^\s*$/)
    {
        $self->apply_links(
            para_ref        => \$para,
            para_action_ref => \$para_action
        );
    }

    # close any open lists if required to
    if (   $args{close_tags}
        && $self->{__mode} & $LIST)    # End all lists
    {
        $self->endlist(
            num_lists       => $self->{__listnum},
            prev_ref        => \$para,
            line_action_ref => \$para_action
        );
    }
    # close any open tags
    if ($args{close_tags} && $self->{xhtml})
    {
        while (@{$self->{__tags}})
        {
            $para .= $self->close_tag('');
        }
    }

    # convert remaining Microsoft character codes into sensible HTML
    if ($self->{demoronize} && !$self->{eight_bit_clean})
    {
        $para = demoronize_code($para);
    }
    # All the matching and formatting is done.  Now we can
    # replace non-ASCII characters with character entities.
    if (!$self->{eight_bit_clean})
    {
        my @chars = split(//, $para);
        foreach $_ (@chars)
        {
            $_ = $char_entities{$_} if defined($char_entities{$_});
        }
        $para = join('', @chars);
    }

    $self->{__prev_para_action} = $para_action;

    return $para;
}    # process_para

=head2 txt2html

    $conv->txt2html(%args);

Convert a text file to HTML.  Takes a hash of arguments.  See
L</OPTIONS> for the possible values of the arguments.  Arguments which
have already been set with B<new> or B<args> will remain as they are,
unless they are overridden.

=cut

sub txt2html ($;$)
{
    my $self = shift;

    if (@_)
    {
        $self->args(@_);
    }

    $self->do_init_call();

    my $outhandle;
    my $outhandle_needs_closing;

    # set up the output
    if ($self->{outhandle})
    {
        $outhandle               = $self->{outhandle};
        $outhandle_needs_closing = 1;
    }
    elsif ($self->{outfile} eq "-")
    {
        $outhandle               = *STDOUT;
        $outhandle_needs_closing = 0;
    }
    else
    {
        open($outhandle, "> " . $self->{outfile})
          || die "Error: unable to open ", $self->{outfile}, ": $!\n";
        $outhandle_needs_closing = 1;
    }

    # slurp up a paragraph at a time, a file at a time
    local $/ = "";
    my $para        = '';
    my $count       = 0;
    my $print_count = 0;
    my @sources     = ();
    my $source_type;
    if ($self->{infile} and @{$self->{infile}})
    {
        @sources     = @{$self->{infile}};
        $source_type = 'file';
    }
    elsif ($self->{inhandle} and @{$self->{inhandle}})
    {
        @sources     = @{$self->{inhandle}};
        $source_type = 'filehandle';
    }
    elsif ($self->{instring} and @{$self->{instring}})
    {
        @sources     = @{$self->{instring}};
        $source_type = 'string';
    }
    my $inhandle;
    my $inhandle_needs_closing = 0;
    foreach my $source (@sources)
    {
        $inhandle = undef;
        if ($source_type eq 'file')
        {
            if (!$source or $source eq '-')
            {
                $inhandle               = *STDIN;
                $inhandle_needs_closing = 0;
            }
            else
            {
                if (-f $source && open($inhandle, $source))
                {
                    $inhandle_needs_closing = 1;
                }
                else    # error
                {
                    warn "Could not open $source\n";
                    next;
                }
            }
        }
        elsif ($source_type eq 'filehandle')
        {
            $inhandle               = $source;
            $inhandle_needs_closing = 1;
        }
        if ($source_type eq 'string')
        {
            # process the string
            $para = $_;
            $para =~ s/\n$//;    # trim the endline
            if ($count == 0)
            {
                $self->do_file_start($outhandle, $para);
            }
            $self->{__done_with_sect_link} = [];
            $para = $self->process_chunk($para, close_tags => 0);
            print $outhandle $para, "\n";
            $print_count++;
            $count++;
        }
        else                     # file or filehandle
        {
            while (<$inhandle>)
            {
                $para = $_;
                $para =~ s/\n$//;    # trim the endline
                if ($count == 0)
                {
                    $self->do_file_start($outhandle, $para);
                }
                $self->{__done_with_sect_link} = [];
                $para = $self->process_chunk($para, close_tags => 0);
                print $outhandle $para, "\n";
                $print_count++;
                $count++;
            }
            if ($inhandle_needs_closing)
            {
                close($inhandle);
            }
        }
    }    # for each file

    $self->{__prev} = "";
    if ($self->{__mode} & $LIST)    # End all lists
    {
        $self->endlist(
            num_lists       => $self->{__listnum},
            prev_ref        => \$self->{__prev},
            line_action_ref => \$self->{__line_action}
        );
    }
    print $outhandle $self->{__prev};

    # end open preformats
    if ($self->{__mode} & $PRE)
    {
        my $tag = $self->close_tag('pre');
        print $outhandle $tag;
    }

    # close all open tags
    if (   $self->{xhtml}
        && !$self->{extract}
        && @{$self->{__tags}})
    {
        if ($DictDebug & 8)
        {
            print STDERR "closing all tags at end\n";
        }
        # close any open tags (until we get to the body)
        my $open_tag = @{$self->{__tags}}[$#{$self->{__tags}}];
        while (@{$self->{__tags}}
            && $open_tag ne 'body'
            && $open_tag ne 'html')
        {
            print $outhandle $self->close_tag('');
            $open_tag = @{$self->{__tags}}[$#{$self->{__tags}}];
        }
        print $outhandle "\n";
    }

    if ($self->{append_file})
    {
        if (-r $self->{append_file})
        {
            open(APPEND, $self->{append_file});
            while (<APPEND>)
            {
                print $outhandle $_;
                $print_count++;
            }
            close(APPEND);
        }
        else
        {
            print STDERR "Can't find or read file ", $self->{append_file},
              " to append.\n";
        }
    }

    # print the closing tags (if we have printed stuff at all)
    if ($print_count && !$self->{extract})
    {
        print $outhandle $self->close_tag('body'), "\n";
        print $outhandle $self->close_tag('html'), "\n";
    }
    if ($outhandle_needs_closing)
    {
        close($outhandle);
    }
    return 1;
}

=head1 PRIVATE METHODS

These are methods used internally, only of interest to developers.

=cut

#---------------------------------------------------------------#
# Init-related subroutines

=head2 init_our_data

$self->init_our_data();

Initializes the internal object data.

=cut
sub init_our_data ($)
{
    my $self = shift;

    #
    # All the options, in alphabetical order
    #
    $self->{append_file}           = '';
    $self->{append_head}           = '';
    $self->{body_deco}             = '';
    $self->{bullets}               = '-=o*\267';
    $self->{bullets_ordered}       = '';
    $self->{bold_delimiter}        = '#';
    $self->{caps_tag}              = 'STRONG';
    $self->{custom_heading_regexp} = [];
    $self->{default_link_dict}     =
      ($ENV{HOME} ? "$ENV{HOME}/.txt2html.dict" : '.txt2html.dict');
    $self->{doctype}                    = '-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd';
    $self->{demoronize}                 = 1;
    $self->{eight_bit_clean}            = 0;
    $self->{escape_HTML_chars}          = 1;
    $self->{explicit_headings}          = 0;
    $self->{extract}                    = 0;
    $self->{hrule_min}                  = 4;
    $self->{indent_width}               = 2;
    $self->{indent_par_break}           = 0;
    $self->{infile}                     = [];
    $self->{inhandle}                   = [];
    $self->{instring}                   = [];
    $self->{italic_delimiter}           = '*';
    $self->{links_dictionaries}         = [];
    $self->{link_only}                  = 0;
    $self->{lower_case_tags}            = 0;
    $self->{mailmode}                   = 0;
    $self->{make_anchors}               = 1;
    $self->{make_links}                 = 1;
    $self->{make_tables}                = 0;
    $self->{min_caps_length}            = 3;
    $self->{outfile}                    = '-';
    $self->{par_indent}                 = 2;
    $self->{preformat_trigger_lines}    = 2;
    $self->{endpreformat_trigger_lines} = 2;
    $self->{preformat_start_marker}     = "^(:?(:?<)|<)PRE(:?(:?>)|>)\$";
    $self->{preformat_end_marker}       = "^(:?(:?<)|<)/PRE(:?(:?>)|>)\$";
    $self->{preformat_whitespace_min}   = 5;
    $self->{prepend_file}               = '';
    $self->{preserve_indent}            = 0;
    $self->{short_line_length}          = 40;
    $self->{style_url}                  = '';
    $self->{tab_width}                  = 8;
    $self->{table_type}                 = {
        ALIGN  => 1,
        PGSQL  => 1,
        BORDER => 1,
        DELIM  => 1,
    };
    $self->{title}                      = '';
    $self->{titlefirst}                 = 0;
    $self->{underline_delimiter}        = '_';
    $self->{underline_length_tolerance} = 1;
    $self->{underline_offset_tolerance} = 1;
    $self->{unhyphenation}              = 1;
    $self->{use_mosaic_header}          = 0;
    $self->{use_preformat_marker}       = 0;
    $self->{xhtml}                      = 1;

    # accumulation variables
    $self->{__file}               = "";    # Current file being processed
    $self->{__heading_styles}     = {};
    $self->{__num_heading_styles} = 0;
    $self->{__links_table}        = {};
    $self->{__links_table_order}  = [];
    $self->{__links_table_patterns} = {};
    $self->{__search_patterns}    = [];
    $self->{__repl_code}          = [];
    $self->{__prev_para_action}   = 0;
    $self->{__non_header_anchor}  = 0;
    $self->{__mode}               = 0;
    $self->{__listnum}            = 0;
    $self->{__list_nice_indent}   = "";
    $self->{__list_indent}        = [];

    $self->{__call_init_done} = 0;

    #
    # The global links data
    #
    my $system_dict = <<'EOT';
#
# Global links dictionary file for HTML::TextToHTML
# http://www.katspace.com/tools/text_to_html
# http://txt2html.sourceforge.net/
# based on links dictionary for Seth Golub's txt2html
# http://www.aigeek.com/txt2html/
#
# This dictionary contains some patterns for converting obvious URLs,
# ftp sites, hostnames, email addresses and the like to hrefs.
#
# Original adapted from the html.pl package by Oscar Nierstrasz in
# the Software Archive of the Software Composition Group
# http://iamwww.unibe.ch/~scg/Src/
#

# Some people even like to mark the URL label explicitly <URL:foo:label>
/<URL:([-\w\.\/:~_\@]+):([a-zA-Z0-9'() ]+)>/ -h-> <A HREF="$1">$2</A>

# Some people like to mark URLs explicitly <URL:foo>
/<URL:\s*(\S+?)\s*>/ -h-> <A HREF="$1">$1</A>

#  <http://site>
/<(http:\S+?)\s*>/ -h-> <<A HREF="$1">$1</A>>

# Urls: <service>:<rest-of-url>

|snews:[\w\.]+|        -> $&
|news:[\w\.]+|         -> $&
|nntp:[\w/\.:+\-]+|    -> $&
|http:[\w/\.:\@+\-~\%#?=&;,]+[\w/]|  -> $&
|shttp:[\w/\.:+\-~\%#?=&;,]+| -> $&
|https:[\w/\.:+\-~\%#?=&;,]+| -> $&
|file:[\w/\.:+\-]+|     -> $&
|ftp:[\w/\.:+\-]+|      -> $&
|wais:[\w/\.:+\-]+|     -> $&
|gopher:[\w/\.:+\-]+|   -> $&
|telnet:[\w/\@\.:+\-]+|   -> $&


# catch some newsgroups to avoid confusion with sites:
|([^\w\-/\.:\@>])(alt\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(bionet\.[\w\.+\-]+[\w+\-]+)| -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(bit\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(biz\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(clari\.[\w\.+\-]+[\w+\-]+)|  -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(comp\.[\w\.+\-]+[\w+\-]+)|   -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(gnu\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(humanities\.[\w\.+\-]+[\w+\-]+)| 
          -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(k12\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(misc\.[\w\.+\-]+[\w+\-]+)|   -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(news\.[\w\.+\-]+[\w+\-]+)|   -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(rec\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(soc\.[\w\.+\-]+[\w+\-]+)|    -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(talk\.[\w\.+\-]+[\w+\-]+)|   -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(us\.[\w\.+\-]+[\w+\-]+)|     -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(ch\.[\w\.+\-]+[\w+\-]+)|     -h-> $1<A HREF="news:$2">$2</A>
|([^\w\-/\.:\@>])(de\.[\w\.+\-]+[\w+\-]+)|     -h-> $1<A HREF="news:$2">$2</A>

# FTP locations (with directory):
# anonymous@<site>:<path>
|(anonymous\@)([[:alpha:]][\w\.+\-]+\.[[:alpha:]]{2,}):(\s*)([\w\d+\-/\.]+)|
  -h-> $1<A HREF="ftp://$2/$4">$2:$4</A>$3

# ftp@<site>:<path>
|(ftp\@)([[:alpha:]][\w\.+\-]+\.[[:alpha:]]{2,}):(\s*)([\w\d+\-/\.]+)|
  -h-> $1<A HREF="ftp://$2/$4">$2:$4</A>$3

# Email address
|[[:alnum:]_\+\-\.]+\@([[:alnum:]][\w\.+\-]+\.[[:alpha:]]{2,})|
  -> mailto:$&

# <site>:<path>
|([^\w\-/\.:\@>])([[:alpha:]][\w\.+\-]+\.[[:alpha:]]{2,}):(\s*)([\w\d+\-/\.]+)|
  -h-> $1<A HREF="ftp://$2/$4">$2:$4</A>$3

# NB: don't confuse an http server with a port number for
# an FTP location!
# internet number version: <internet-num>:<path>
|([^\w\-/\.:\@])(\d{2,}\.\d{2,}\.\d+\.\d+):([\w\d+\-/\.]+)|
  -h-> $1<A HREF="ftp://$2/$3">$2:$3</A>

# telnet <site> <port>
|telnet ([[:alpha:]][\w+\-]+(\.[\w\.+\-]+)+\.[[:alpha:]]{2,})\s+(\d{2,4})|
  -h-> telnet <A HREF="telnet://$1:$3/">$1 $3</A>

# ftp <site>
|ftp ([[:alpha:]][\w+\-]+(\.[\w\.+\-]+)+\.[[:alpha:]]{2,})|
  -h-> ftp <A HREF="ftp://$1/">$1</A>

# host with "ftp" in the machine name
|\b([[:alpha:]][\w])*ftp[\w]*(\.[\w+\-]+){2,}| -h-> ftp <A HREF="ftp://$&/">$&</A>

# ftp.foo.net/blah/
|ftp(\.[\w\@:-]+)+/\S+| -> ftp://$&

# www.thehouse.org/txt2html/
|www(\.[\w\@:-]+)+/\S+| -> http://$&

# host with "www" in the machine name
|\b([[:alpha:]][\w])*www[\w]*(\.[\w+\-]+){2,}| -> http://$&/

# <site> <port>
|([[:alpha:]][\w+\-]+\.[\w+\-]+\.[[:alpha:]]{2,})\s+(\d{2,4})|
  -h-> <A HREF="telnet://$1:$2/">$1 $2</A>

# just internet numbers with port:
|([^\w\-/\.:\@])(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\s+(\d{1,4})|
  -h-> $1<A HREF="telnet://$2:$3">$2 $3</A>

# just internet numbers:
|([^\w\-/\.:\@])(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})|
  -h-> $1<A HREF="telnet://$2">$2</A>

# RFCs
/RFC ?(\d+)/ -i-> http://www.cis.ohio-state.edu/rfc/rfc$1.txt

# Mark _underlined stuff_ as <U>underlined stuff</U>
# Don't mistake variable names for underlines, and
# take account of possible trailing punctuation
#/([ \t\n])_([[:alpha:]][[:alnum:]\s-]*[[:alpha:]])_([\s\.;:,\!\?])/ -h-> $1<U>$2</U>$3

# Seth and his amazing conversion program    :-)

"Seth Golub"  -o-> http://www.aigeek.com/
"txt2html"    -o-> https://github.com/resurrecting-open-source-projects/txt2html

# Kathryn and her amazing modules 8-)
"Kathryn Andersen"  -o-> http://www.katspace.com/
"HTML::TextToHTML"  -o-> http://www.katspace.com/tools/text_to_html/
"hypertoc"          -o-> http://www.katspace.com/tools/hypertoc/
"HTML::GenToc"      -o-> http://www.katspace.com/tools/hypertoc/

# End of global dictionary
EOT

    # pre-parse the above data by removing unwanted lines
    # skip lines that start with '#'
    $system_dict =~ s/^\#.*$//mg;
    # skip lines that end with unescaped ':'
    $system_dict =~ s/^.*[^\\]:\s*$//mg;

    $self->{__global_links_data} = $system_dict;

}    # init_our_data

#---------------------------------------------------------------#
# txt2html-related subroutines

=head2 deal_with_options

$self->deal_with_options();

do extra processing related to particular options

=cut
sub deal_with_options ($)
{
    my $self = shift;

    if (!$self->{make_links})
    {
        $self->{'links_dictionaries'} = 0;
    }
    if ($self->{append_file})
    {
        if (!-r $self->{append_file})
        {
            print STDERR "Can't find or read ", $self->{append_file}, "\n";
            $self->{append_file} = '';
        }
    }
    if ($self->{prepend_file})
    {
        if (!-r $self->{prepend_file})
        {
            print STDERR "Can't find or read ", $self->{prepend_file}, "\n";
            $self->{'prepend_file'} = '';
        }
    }
    if ($self->{append_head})
    {
        if (!-r $self->{append_head})
        {
            print STDERR "Can't find or read ", $self->{append_head}, "\n";
            $self->{'append_head'} = '';
        }
    }

    if (!$self->{outfile})
    {
        $self->{'outfile'} = "-";
    }

    $self->{'preformat_trigger_lines'} = 0
      if ($self->{preformat_trigger_lines} < 0);
    $self->{'preformat_trigger_lines'} = 2
      if ($self->{preformat_trigger_lines} > 2);

    $self->{'endpreformat_trigger_lines'} = 1
      if ($self->{preformat_trigger_lines} == 0);
    $self->{'endpreformat_trigger_lines'} = 0
      if ($self->{endpreformat_trigger_lines} < 0);
    $self->{'endpreformat_trigger_lines'} = 2
      if ($self->{endpreformat_trigger_lines} > 2);

    $self->{__preformat_enabled} =
      (($self->{endpreformat_trigger_lines} != 0)
          || $self->{use_preformat_marker});

    if ($self->{use_mosaic_header})
    {
        my $num_heading_styles = 0;
        my %heading_styles     = ();
        $heading_styles{"*"}          = ++$num_heading_styles;
        $heading_styles{"="}          = ++$num_heading_styles;
        $heading_styles{"+"}          = ++$num_heading_styles;
        $heading_styles{"-"}          = ++$num_heading_styles;
        $heading_styles{"~"}          = ++$num_heading_styles;
        $heading_styles{"."}          = ++$num_heading_styles;
        $self->{__heading_styles}     = \%heading_styles;
        $self->{__num_heading_styles} = $num_heading_styles;
    }
    # XHTML implies lower case
    $self->{'lower_case_tags'} = 1 if ($self->{xhtml});
}

=head2 escape

$newtext = escape($text);

Escape & < and >

=cut
sub escape ($)
{
    my ($text) = @_;
    $text =~ s/&/&/g;
    $text =~ s/>/>/g;
    $text =~ s/</</g;
    return $text;
}

=head2 demoronize_char

$newtext = demoronize_char($text);

Convert Microsoft character entities into characters.

Added by Alan Jackson, alan at ajackson dot org, and based
on the demoronize script by John Walker, http://www.fourmilab.ch/

=cut
sub demoronize_char($)
{
    my $s = shift;
    #   Map strategically incompatible non-ISO characters in the
    #   range 0x82 -- 0x9F into plausible substitutes where
    #   possible.

    $s =~ s/\x82/,/g;
    $s =~ s/\x84/,,/g;
    $s =~ s/\x85/.../g;

    $s =~ s/\x88/^/g;

    $s =~ s/\x8B/</g;
    $s =~ s/\x8C/Oe/g;

    $s =~ s/\x91/`/g;
    $s =~ s/\x92/'/g;
    $s =~ s/\x93/"/g;
    $s =~ s/\x94/"/g;
    $s =~ s/\x95/*/g;
    $s =~ s/\x96/-/g;
    $s =~ s/\x97/--/g;

    $s =~ s/\x9B/>/g;
    $s =~ s/\x9C/oe/g;

    return $s;
}

=head2 demoronize_code

$newtext = demoronize_code($text);

convert Microsoft character entities into HTML code

=cut
sub demoronize_code($)
{
    my $s = shift;
    #   Map strategically incompatible non-ISO characters in the
    #   range 0x82 -- 0x9F into plausible substitutes where
    #   possible.

    $s =~ s-\x83-<em>f</em>-g;

    $s =~ s-\x98-<sup>~</sup>-g;
    $s =~ s-\x99-<sup>TM</sup>-g;

    return $s;
}

=head2 get_tag

$tag = $self->get_tag($in_tag);

$tag = $self->get_tag($in_tag,
	tag_type=>TAG_START,
	inside_tag=>'');

output the tag wanted (add the <> and the / if necessary)
- output in lower or upper case
- do tag-related processing
options:
  tag_type=>TAG_START | tag_type=>TAG_END | tag_type=>TAG_EMPTY
  (default start)
  inside_tag=>string (default empty)

=cut
sub get_tag ($$;%)
{
    my $self   = shift;
    my $in_tag = shift;
    my %args   = (
        tag_type   => TAG_START,
        inside_tag => '',
        @_
    );
    my $inside_tag = $args{inside_tag};

    my $open_tag = @{$self->{__tags}}[$#{$self->{__tags}}];
    if (!defined $open_tag)
    {
        $open_tag = '';
    }
    # close any open tags that need closing
    # Note that we only have to check for the structural tags we make,
    # not every possible HTML tag
    my $tag_prefix = '';
    if ($self->{xhtml})
    {
        if (    $open_tag eq 'p'
            and $in_tag eq 'p'
            and $args{tag_type} != TAG_END)
        {
            $tag_prefix = $self->close_tag('p');
        }
        elsif ( $open_tag eq 'p'
            and $in_tag =~ /^(hr|ul|ol|dl|pre|table|h)/)
        {
            $tag_prefix = $self->close_tag('p');
        }
        elsif ( $open_tag eq 'li'
            and $in_tag eq 'li'
            and $args{tag_type} != TAG_END)
        {
            # close a LI before the next LI
            $tag_prefix = $self->close_tag('li');
        }
        elsif ( $open_tag eq 'li'
            and $in_tag =~ /^(ul|ol)$/
            and $args{tag_type} == TAG_END)
        {
            # close the LI before the list closes
            $tag_prefix = $self->close_tag('li');
        }
        elsif ( $open_tag eq 'dt'
            and $in_tag eq 'dd'
            and $args{tag_type} != TAG_END)
        {
            # close a DT before the next DD
            $tag_prefix = $self->close_tag('dt');
        }
        elsif ( $open_tag eq 'dd'
            and $in_tag eq 'dt'
            and $args{tag_type} != TAG_END)
        {
            # close a DD before the next DT
            $tag_prefix = $self->close_tag('dd');
        }
        elsif ( $open_tag eq 'dd'
            and $in_tag         eq 'dl'
            and $args{tag_type} == TAG_END)
        {
            # close the DD before the list closes
            $tag_prefix = $self->close_tag('dd');
        }
    }

    my $out_tag = $in_tag;
    if ($args{tag_type} == TAG_END)
    {
        $out_tag = $self->close_tag($in_tag);
    }
    else
    {
        if ($self->{lower_case_tags})
        {
            $out_tag =~ tr/A-Z/a-z/;
        }
        else    # upper case
        {
            $out_tag =~ tr/a-z/A-Z/;
        }
        if ($args{tag_type} == TAG_EMPTY)
        {
            if ($self->{xhtml})
            {
                $out_tag = "<${out_tag}${inside_tag}/>";
            }
            else
            {
                $out_tag = "<${out_tag}${inside_tag}>";
            }
        }
        else
        {
            push @{$self->{__tags}}, $in_tag;
            $out_tag = "<${out_tag}${inside_tag}>";
        }
    }
    $out_tag = $tag_prefix . $out_tag if $tag_prefix;
    if ($DictDebug & 8)
    {
        print STDERR
          "open_tag = '${open_tag}', in_tag = '${in_tag}', tag_type = ",
          $args{tag_type},
          ", inside_tag = '${inside_tag}', out_tag = '$out_tag'\n";
    }

    return $out_tag;
}    # get_tag

=head2 close_tag

$tag = $self->close_tag($in_tag);

close the open tag

=cut
sub close_tag ($$)
{
    my $self   = shift;
    my $in_tag = shift;

    my $open_tag = pop @{$self->{__tags}};
    $in_tag ||= $open_tag;
    # put the open tag back on the stack if the in-tag is not the same
    if (defined $open_tag && $open_tag ne $in_tag)
    {
        push @{$self->{__tags}}, $open_tag;
    }
    my $out_tag = $in_tag;
    if ($self->{lower_case_tags})
    {
        $out_tag =~ tr/A-Z/a-z/;
    }
    else    # upper case
    {
        $out_tag =~ tr/a-z/A-Z/;
    }
    $out_tag = "<\/${out_tag}>";
    if ($DictDebug & 8)
    {
        print STDERR
"close_tag: open_tag = '${open_tag}', in_tag = '${in_tag}', out_tag = '$out_tag'\n";
    }

    return $out_tag;
}

=head2 hrule

   $self->hrule(para_lines_ref=>$para_lines,
	     para_action_ref=>$para_action,
	     ind=>0);

Deal with horizontal rules.

=cut
sub hrule ($%)
{
    my $self = shift;
    my %args = (
        para_lines_ref  => undef,
        para_action_ref => undef,
        ind             => 0,
        @_
    );
    my $para_lines_ref  = $args{para_lines_ref};
    my $para_action_ref = $args{para_action_ref};
    my $ind             = $args{ind};

    my $hrmin = $self->{hrule_min};
    if ($para_lines_ref->[$ind] =~ /^\s*([-_~=\*]\s*){$hrmin,}$/)
    {
        my $tag = $self->get_tag("hr", tag_type => TAG_EMPTY);
        $para_lines_ref->[$ind] = "$tag\n";
        $para_action_ref->[$ind] |= $HRULE;
    }
    elsif ($para_lines_ref->[$ind] =~ /\014/)
    {
        # Linefeeds become horizontal rules
        $para_action_ref->[$ind] |= $HRULE;
        my $tag = $self->get_tag("hr", tag_type => TAG_EMPTY);
        $para_lines_ref->[$ind] =~ s/\014/\n${tag}\n/g;
    }
}

=head2 shortline

    $self->shortline(line_ref=>$line_ref,
		     line_action_ref=>$line_action_ref,
		     prev_ref=>$prev_ref,
		     prev_action_ref=>$prev_action_ref,
		     prev_line_len=>$prev_line_len);

Deal with short lines.

=cut
sub shortline ($%)
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        prev_ref        => undef,
        prev_action_ref => undef,
        prev_line_len   => 0,
        @_
    );
    my $mode_ref        = $args{mode_ref};
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};
    my $prev_ref        = $args{prev_ref};
    my $prev_action_ref = $args{prev_action_ref};
    my $prev_line_len   = $args{prev_line_len};

    # Short lines should be broken even on list item lines iff the
    # following line is more text.  I haven't figured out how to do
    # that yet.  For now, I'll just not break on short lines in lists.
    # (sorry)

    my $tag = $self->get_tag('br', tag_type => TAG_EMPTY);
    if (
           ${$line_ref} !~ /^\s*$/
        && ${$prev_ref} !~ /^\s*$/
        && ($prev_line_len < $self->{short_line_length})
        && !(
            ${$line_action_ref} &
            ($END | $HEADER | $HRULE | $LIST | $IND_BREAK | $PAR)
        )
        && !(${$prev_action_ref} & ($HEADER | $HRULE | $BREAK | $IND_BREAK))
      )
    {
        ${$prev_ref} .= $tag . chop(${$prev_ref});
        ${$prev_action_ref} |= $BREAK;
    }
}

=head2 is_mailheader

    if ($self->is_mailheader(rows_ref=>$rows_ref))
    {
	...
    }

Is this a mailheader line?

=cut
sub is_mailheader ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        @_
    );
    my $rows_ref = $args{rows_ref};

    # a mail header is assumed to be the whole
    # paragraph which starts with a From , From: or Newsgroups: line

    if ($rows_ref->[0] =~ /^(From:?)|(Newsgroups:) /)
    {
        return 1;
    }
    return 0;

}    # is_mailheader

=head2 mailheader

    $self->mailheader(rows_ref=>$rows_ref);

Deal with a mailheader.

=cut
sub mailheader ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        @_
    );
    my $rows_ref = $args{rows_ref};

    # a mail header is assumed to be the whole
    # paragraph which starts with a From: or Newsgroups: line
    my $tag  = '';
    my @rows = @{$rows_ref};

    if ($self->is_mailheader(%args))
    {
        $self->{__mode} |= $MAILHEADER;
        if ($self->{escape_HTML_chars})
        {
            $rows[0] = escape($rows[0]);
        }
        $self->anchor_mail(\$rows[0]);
        chomp ${rows}[0];
        $tag = $self->get_tag('p', inside_tag => " class='mail_header'");
        my $tag2 = $self->get_tag('br', tag_type => TAG_EMPTY);
        $rows[0] =
          join('', "<!-- New Message -->\n", $tag, $rows[0], $tag2, "\n");
        # now put breaks on the rest of the paragraph
        # apart from the last line
        for (my $rn = 1; $rn < @rows; $rn++)
        {
            if ($self->{escape_HTML_chars})
            {
                $rows[$rn] = escape($rows[$rn]);
            }
            if ($rn != (@rows - 1))
            {
                $tag = $self->get_tag('br', tag_type => TAG_EMPTY);
                chomp $rows[$rn];
                $rows[$rn] =~ s/$/${tag}\n/;
            }
        }
    }
    @{$rows_ref} = @rows;

}    # mailheader

=head2 mailquote

    $self->mailquote(line_ref=>$line_ref,
		     line_action_ref=>$line_action_ref,
		     prev_ref=>$prev_ref,
		     prev_action_ref=>$prev_action_ref,
		     next_ref=>$next_ref);

Deal with quoted mail.

=cut
sub mailquote ($%)
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        prev_ref        => undef,
        prev_action_ref => undef,
        next_ref        => undef,
        @_
    );
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};
    my $prev_ref        = $args{prev_ref};
    my $prev_action_ref = $args{prev_action_ref};
    my $next_ref        = $args{next_ref};

    my $tag = '';
    if (
        (
            (${$line_ref} =~ /^\w*>/)    # Handle "FF> Werewolves."
            || (${$line_ref} =~ /^[\|:]/)
        )                                  # Handle "[|:] There wolves."
        && defined($next_ref) && (${$next_ref} !~ /^\s*$/)
      )
    {
        $tag = $self->get_tag('br', tag_type => TAG_EMPTY);
        ${$line_ref} =~ s/$/${tag}/;
        ${$line_action_ref} |= ($BREAK | $MAILQUOTE);
        if (!(${$prev_action_ref} & ($BREAK | $MAILQUOTE)))
        {
            $tag = $self->get_tag('p', inside_tag => " class='quote_mail'");
            ${$prev_ref} .= $tag;
            ${$line_action_ref} |= $PAR;
        }
    }
}

=head2 subtract_modes
    
    $newvector = subtract_modes($vector, $mask);

Subtracts modes listed in $mask from $vector.

=cut
sub subtract_modes ($$)
{
    my ($vector, $mask) = @_;
    return ($vector | $mask) - $mask;
}

=head2 paragraph

    $self->paragraph(line_ref=>$line_ref,
		     line_action_ref=>$line_action_ref,
		     prev_ref=>$prev_ref,
		     prev_action_ref=>$prev_action_ref,
		     line_indent=>$line_indent,
		     prev_indent=>$prev_indent,
		     is_fragment=>$is_fragment,
		     ind=>$ind);

Detect paragraph indentation.

=cut
sub paragraph ($%)
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        prev_ref        => undef,
        prev_action_ref => undef,
        line_indent     => 0,
        prev_indent     => 0,
        is_fragment     => 0,
        ind             => 0,
        @_
    );
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};
    my $prev_ref        = $args{prev_ref};
    my $prev_action_ref = $args{prev_action_ref};
    my $line_indent     = $args{line_indent};
    my $prev_indent     = $args{prev_indent};
    my $is_fragment     = $args{is_fragment};
    my $line_no         = $args{ind};

    my $tag = '';
    if (
        ${$line_ref} !~ /^\s*$/
        && !subtract_modes(
            ${$line_action_ref}, $END | $MAILQUOTE | $CAPS | $BREAK
        )
        && (   ${$prev_ref} =~ /^\s*$/
            || (${$line_action_ref} & $END)
            || ($line_indent > $prev_indent + $self->{par_indent}))
        && !($is_fragment && $line_no == 0)
      )
    {

        if (   $self->{indent_par_break}
            && ${$prev_ref} !~ /^\s*$/
            && !(${$line_action_ref} & $END)
            && ($line_indent > $prev_indent + $self->{par_indent}))
        {
            $tag = $self->get_tag('br', tag_type => TAG_EMPTY);
            ${$prev_ref} .= $tag;
            ${$prev_ref} .= " " x $line_indent;
            ${$line_ref} =~ s/^ {$line_indent}//;
            ${$prev_action_ref} |= $BREAK;
            ${$line_action_ref} |= $IND_BREAK;
        }
        elsif ($self->{preserve_indent})
        {
            $tag = $self->get_tag('p');
            ${$prev_ref} .= $tag;
            ${$prev_ref} .= " " x $line_indent;
            ${$line_ref} =~ s/^ {$line_indent}//;
            ${$line_action_ref} |= $PAR;
        }
        else
        {
            $tag = $self->get_tag('p');
            ${$prev_ref} .= $tag;
            ${$line_action_ref} |= $PAR;
        }
    }
    # detect also a continuing indentation at the same level
    elsif ($self->{indent_par_break}
        && !($self->{__mode} & ($PRE | $TABLE | $LIST))
        && ${$prev_ref} !~ /^\s*$/
        && !(${$line_action_ref} & $END)
        && (${$prev_action_ref} & ($IND_BREAK | $PAR))
        && !subtract_modes(${$line_action_ref}, $END | $MAILQUOTE | $CAPS)
        && ($line_indent > $self->{par_indent})
        && ($line_indent == $prev_indent))
    {
        $tag = $self->get_tag('br', tag_type => TAG_EMPTY);
        ${$prev_ref} .= $tag;
        ${$prev_ref} .= " " x $line_indent;
        ${$line_ref} =~ s/^ {$line_indent}//;
        ${$prev_action_ref} |= $BREAK;
        ${$line_action_ref} |= $IND_BREAK;
    }
}

=head2 listprefix

    ($prefix, $number, $rawprefix, $term) = $self->listprefix($line);

Detect and parse a list item.

=cut
sub listprefix ($$)
{
    my $self = shift;
    my $line = shift;

    my ($prefix, $number, $rawprefix, $term);

    my $bullets         = $self->{bullets};
    my $bullets_ordered = $self->{bullets_ordered};
    my $number_match    = '(\d+|[^\W\d])';
    if ($bullets_ordered)
    {
        $number_match = '(\d+|[[:alpha:]]|[' . "${bullets_ordered}])";
    }
    $self->{__number_match} = $number_match;
    my $term_match = '(\w\w+)';
    $self->{__term_match} = $term_match;
    return (0, 0, 0, 0)
      if ( !($line =~ /^\s*[${bullets}]\s+\S/)
        && !($line =~ /^\s*${number_match}[\.\)\]:]\s+\S/)
        && !($line =~ /^\s*${term_match}:$/));

    ($term)   = $line =~ /^\s*${term_match}:$/;
    ($number) = $line =~ /^\s*${number_match}\S\s+\S/;
    $number = 0 unless defined($number);
    if (   $bullets_ordered
        && $number =~ /[${bullets_ordered}]/)
    {
        $number = 1;
    }

    # That slippery exception of "o" as a bullet
    # (This ought to be determined using the context of what lists
    #  we have in progress, but this will probably work well enough.)
    if ($bullets =~ /o/ && $line =~ /^\s*o\s/)
    {
        $number = 0;
    }

    if ($term)
    {
        ($rawprefix) = $line =~ /^(\s*${term_match}.)$/;
        $prefix = $rawprefix;
        $prefix =~ s/${term_match}//;    # Take the term out
    }
    elsif ($number)
    {
        ($rawprefix) = $line =~ /^(\s*${number_match}.)/;
        $prefix = $rawprefix;
        $prefix =~ s/${number_match}//;    # Take the number out
    }
    else
    {
        ($rawprefix) = $line =~ /^(\s*[${bullets}].)/;
        $prefix = $rawprefix;
    }
    ($prefix, $number, $rawprefix, $term);
}    # listprefix

=head2 startlist

    $self->startlist(prefix=>$prefix,
		     number=>0,
		     rawprefix=>$rawprefix,
		     term=>$term,
		     para_lines_ref=>$para_lines_ref,
		     para_action_ref=>$para_action_ref,
		     ind=>0,
		     prev_ref=>$prev_ref,
		     total_prefix=>$total_prefix);

Start a list.

=cut
sub startlist ($%)
{
    my $self = shift;
    my %args = (
        prefix          => '',
        number          => 0,
        rawprefix       => '',
        term            => '',
        para_lines_ref  => undef,
        para_action_ref => undef,
        ind             => 0,
        prev_ref        => undef,
        total_prefix    => '',
        @_
    );
    my $prefix          = $args{prefix};
    my $number          = $args{number};
    my $rawprefix       = $args{rawprefix};
    my $term            = $args{term};
    my $para_lines_ref  = $args{para_lines_ref};
    my $para_action_ref = $args{para_action_ref};
    my $ind             = $args{ind};
    my $prev_ref        = $args{prev_ref};

    my $tag = '';
    $self->{__listprefix}->[$self->{__listnum}] = $prefix;
    if ($number)
    {

        # It doesn't start with 1,a,A.  Let's not screw with it.
        if (($number ne "1") && ($number ne "a") && ($number ne "A"))
        {
            return 0;
        }
        $tag = $self->get_tag('ol');
        ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
        $self->{__list}->[$self->{__listnum}] = $OL;
    }
    elsif ($term)
    {
        $tag = $self->get_tag('dl');
        ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
        $self->{__list}->[$self->{__listnum}] = $DL;
    }
    else
    {
        $tag = $self->get_tag('ul');
        ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
        $self->{__list}->[$self->{__listnum}] = $UL;
    }

    $self->{__list_indent}->[$self->{__listnum}] = length($args{total_prefix});
    $self->{__listnum}++;
    $self->{__list_nice_indent} =
      " " x $self->{__listnum} x $self->{indent_width};
    $para_action_ref->[$ind] |= $LIST;
    $para_action_ref->[$ind] |= $LIST_START;
    $self->{__mode}          |= $LIST;
    1;
}    # startlist

=head2 endlist

    $self->endlist(num_lists=>0,
	prev_ref=>$prev_ref,
	line_action_ref=>$line_action_ref);

End N lists

=cut
sub endlist ($%)
{
    my $self = shift;
    my %args = (
        num_lists       => 0,
        prev_ref        => undef,
        line_action_ref => undef,
        @_
    );
    my $n               = $args{num_lists};
    my $prev_ref        = $args{prev_ref};
    my $line_action_ref = $args{line_action_ref};

    my $tag = '';
    for (; $n > 0; $n--, $self->{__listnum}--)
    {
        $self->{__list_nice_indent} =
          " " x ($self->{__listnum} - 1) x $self->{indent_width};
        if ($self->{__list}->[$self->{__listnum} - 1] == $UL)
        {
            $tag = $self->get_tag('ul', tag_type => TAG_END);
            ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
            pop @{$self->{__list_indent}};
        }
        elsif ($self->{__list}->[$self->{__listnum} - 1] == $OL)
        {
            $tag = $self->get_tag('ol', tag_type => TAG_END);
            ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
            pop @{$self->{__list_indent}};
        }
        elsif ($self->{__list}->[$self->{__listnum} - 1] == $DL)
        {
            $tag = $self->get_tag('dl', tag_type => TAG_END);
            ${$prev_ref} .= join('', $self->{__list_nice_indent}, $tag, "\n");
            pop @{$self->{__list_indent}};
        }
        else
        {
            print STDERR "Encountered list of unknown type\n";
        }
    }
    ${$line_action_ref} |= $END;
    $self->{__mode} ^= $LIST if (!$self->{__listnum});
}    # endlist

=head2 continuelist

    $self->continuelist(para_lines_ref=>$para_lines_ref,
			para_action_ref=>$para_action_ref,
			ind=>0,
			term=>$term);

Continue a list.

=cut
sub continuelist ($%)
{
    my $self = shift;
    my %args = (
        para_lines_ref  => undef,
        para_action_ref => undef,
        ind             => 0,
        term            => '',
        @_
    );
    my $para_lines_ref  = $args{para_lines_ref};
    my $para_action_ref = $args{para_action_ref};
    my $ind             = $args{ind};
    my $term            = $args{term};

    my $list_indent = $self->{__list_nice_indent};
    my $bullets     = $self->{bullets};
    my $num_match   = $self->{__number_match};
    my $term_match  = $self->{__term_match};
    my $tag         = '';
    if (   $self->{__list}->[$self->{__listnum} - 1] == $UL
        && $para_lines_ref->[$ind] =~ /^\s*[${bullets}]\s*/)
    {
        $tag = $self->get_tag('li');
        $para_lines_ref->[$ind] =~ s/^\s*[${bullets}]\s*/${list_indent}${tag}/;
        $para_action_ref->[$ind] |= $LIST_ITEM;
    }
    if ($self->{__list}->[$self->{__listnum} - 1] == $OL)
    {
        $tag = $self->get_tag('li');
        $para_lines_ref->[$ind] =~ s/^\s*${num_match}.\s*/${list_indent}${tag}/;
        $para_action_ref->[$ind] |= $LIST_ITEM;
    }
    if (   $self->{__list}->[$self->{__listnum} - 1] == $DL
        && $term)
    {
        $tag = $self->get_tag('dt');
        my $tag2 = $self->get_tag('dt', tag_type => TAG_END);
        $term =~ s/_/ /g;    # underscores are now spaces in the term
        $para_lines_ref->[$ind] =~
          s/^\s*${term_match}.$/${list_indent}${tag}${term}${tag2}/;
        $tag = $self->get_tag('dd');
        $para_lines_ref->[$ind] .= ${tag};
        $para_action_ref->[$ind] |= $LIST_ITEM;
    }
    $para_action_ref->[$ind] |= $LIST;
}    # continuelist

=head2 liststuff

    $self->liststuff(para_lines_ref=>$para_lines_ref,
		     para_action_ref=>$para_action_ref,
		     para_line_indent_ref=>$para_line_indent_ref,
		     ind=>0,
		     prev_ref=>$prev_ref);

Process a list (higher-level method).

=cut
sub liststuff ($%)
{
    my $self = shift;
    my %args = (
        para_lines_ref       => undef,
        para_action_ref      => undef,
        para_line_indent_ref => undef,
        ind                  => 0,
        prev_ref             => undef,
        @_
    );
    my $para_lines_ref       = $args{para_lines_ref};
    my $para_action_ref      = $args{para_action_ref};
    my $para_line_indent_ref = $args{para_line_indent_ref};
    my $ind                  = $args{ind};
    my $prev_ref             = $args{prev_ref};

    my $i;

    my ($prefix, $number, $rawprefix, $term) =
      $self->listprefix($para_lines_ref->[$ind]);

    if (!$prefix)
    {
        # if the previous line is not blank
        if ($ind > 0 && $para_lines_ref->[$ind - 1] !~ /^\s*$/)
        {
            # inside a list item
            return;
        }
        # This might be a new paragraph within an existing list item;
        # It will be the first line, and have the same indentation
        # as the list's indentation.
        if (   $ind == 0
            && $self->{__listnum}
            && $para_line_indent_ref->[$ind] ==
            $self->{__list_indent}->[$self->{__listnum} - 1])
        {
            # start a paragraph
            my $tag = $self->get_tag('p');
            ${$prev_ref} .= $tag;
            $para_action_ref->[$ind] |= $PAR;
            return;
        }
        # This ain't no list.  We'll want to end all of them.
        if ($self->{__listnum})
        {
            $self->endlist(
                num_lists       => $self->{__listnum},
                prev_ref        => $prev_ref,
                line_action_ref => \$para_action_ref->[$ind]
            );
        }
        return;
    }

    # If numbers with more than one digit grow to the left instead of
    # to the right, the prefix will shrink and we'll fail to match the
    # right list.  We need to account for this.
    my $prefix_alternate;
    if (length("" . $number) > 1)
    {
        $prefix_alternate = (" " x (length("" . $number) - 1)) . $prefix;
    }

    # Maybe we're going back up to a previous list
    for (
        $i = $self->{__listnum} - 1;
        ($i >= 0) && ($prefix ne $self->{__listprefix}->[$i]);
        $i--
      )
    {
        if (length("" . $number) > 1)
        {
            last if $prefix_alternate eq $self->{__listprefix}->[$i];
        }
    }

    my $islist;

    # Measure the indent from where the text starts, not where the
    # prefix starts.  This won't screw anything up, and if we don't do
    # it, the next line might appear to be indented relative to this
    # line, and get tagged as a new paragraph.
    my $bullets         = $self->{bullets};
    my $bullets_ordered = $self->{bullets_ordered};
    my $term_match      = $self->{__term_match};
    my ($total_prefix)  =
      $para_lines_ref->[$ind] =~ /^(\s*[${bullets}${bullets_ordered}\w]+.\s*)/;
    # a DL indent starts from the edge of the term, plus indent_width
    if ($term)
    {
        ($total_prefix) = $para_lines_ref->[$ind] =~ /^(\s*)${term_match}.$/;
        $total_prefix .= " " x $self->{indent_width};
    }

    # Of course, we only use it if it really turns out to be a list.

    $islist = 1;
    $i++;
    if (($i > 0) && ($i != $self->{__listnum}))
    {
        $self->endlist(
            num_lists       => $self->{__listnum} - $i,
            prev_ref        => $prev_ref,
            line_action_ref => \$para_action_ref->[$ind]
        );
        $islist = 0;
    }
    elsif (!$self->{__listnum} || ($i != $self->{__listnum}))
    {
        if (
               ($para_line_indent_ref->[$ind] > 0)
            || $ind == 0
            || ($ind > 0 && ($para_lines_ref->[$ind - 1] =~ /^\s*$/))
            || (   $ind > 0
                && $para_action_ref->[$ind - 1] & ($BREAK | $HEADER | $CAPS))
          )
        {
            $islist = $self->startlist(
                prefix          => $prefix,
                number          => $number,
                rawprefix       => $rawprefix,
                term            => $term,
                para_lines_ref  => $para_lines_ref,
                para_action_ref => $para_action_ref,
                ind             => $ind,
                prev_ref        => $prev_ref,
                total_prefix    => $total_prefix
            );
        }
        else
        {

            # We have something like this: "- foo" which usually
            # turns out not to be a list.
            return;
        }
    }

    $self->continuelist(
        para_lines_ref  => $para_lines_ref,
        para_action_ref => $para_action_ref,
        ind             => $ind,
        term            => $term
      )
      if ($self->{__mode} & $LIST);
    $para_line_indent_ref->[$ind] = length($total_prefix) if $islist;
}    # liststuff

=head2 get_table_type

    $table_type = $self->get_table_type(rows_ref=>$rows_ref,
					para_len=>0);

Figure out the table type of this table, if any

=cut
sub get_table_type ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $table_type = 0;
    if (   $self->{table_type}->{DELIM}
        && $self->is_delim_table(%args))
    {
        $table_type = $TAB_DELIM;
    }
    elsif ($self->{table_type}->{ALIGN}
        && $self->is_aligned_table(%args))
    {
        $table_type = $TAB_ALIGN;
    }
    elsif ($self->{table_type}->{PGSQL}
        && $self->is_pgsql_table(%args))
    {
        $table_type = $TAB_PGSQL;
    }
    elsif ($self->{table_type}->{BORDER}
        && $self->is_border_table(%args))
    {
        $table_type = $TAB_BORDER;
    }

    return $table_type;
}

=head2 is_aligned_table

    if ($self->is_aligned_table(rows_ref=>$rows_ref, para_len=>0))
    {
	...
    }

Check if the given paragraph-array is an aligned table

=cut
sub is_aligned_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # TABLES: spot and mark up tables.  We combine the lines of the
    # paragraph using the string bitwise or (|) operator, the result
    # being in $spaces.  A character in $spaces is a space only if
    # there was a space at that position in every line of the
    # paragraph.  $space can be used to search for contiguous spaces
    # that occur on all lines of the paragraph.  If this results in at
    # least two columns, the paragraph is identified as a table.

    # Note that this sub must be called before checking for preformatted
    # lines because a table may well have whitespace to the left, in
    # which case it must not be incorrectly recognised as a preformat.
    my @rows = @{$rows_ref};
    my @starts;
    my $spaces = '';
    my $max    = 0;
    my $min    = $para_len;
    foreach my $row (@rows)
    {
        ($spaces |= $row) =~ tr/ /\xff/c;
        $min = length $row if length $row < $min;
        $max = length $row if $max < length $row;
    }
    $spaces = substr $spaces, 0, $min;
    push(@starts, 0) unless $spaces =~ /^ /;
    while ($spaces =~ /((?:^| ) +)(?=[^ ])/g)
    {
        push @starts, pos($spaces);
    }

    if (2 <= @rows and 2 <= @starts)
    {
        return 1;
    }
    else
    {
        return 0;
    }
}

=head2 is_pgsql_table

    if ($self->is_pgsql_table(rows_ref=>$rows_ref, para_len=>0))
    {
	...
    }

Check if the given paragraph-array is a Postgresql table
(the ascii format produced by Postgresql)

A PGSQL table can start with an optional table-caption,

    then it has a row of column headings separated by |
    then it has a row of ------+-----
    then it has one or more rows of column values separated by |
    then it has a row-count (N rows)

=cut
sub is_pgsql_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # A PGSQL table must have at least 4 rows (see above).
    if (@{$rows_ref} < 4)
    {
        return 0;
    }

    my @rows = @{$rows_ref};
    if ($rows[0] !~ /\|/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        shift @rows;
    }
    if (@rows < 4)
    {
        return 0;
    }
    if ($rows[0] !~ /^\s*\w+\s+\|\s+/)                # Colname |
    {
        return 0;
    }
    if ($rows[1] !~ /^\s*[-]+[+][-]+/)                # ----+----
    {
        return 0;
    }
    if ($rows[2] !~ /^\s*[^|]*\s+\|\s+/)              # value |
    {
        return 0;
    }
    # check the last row for rowcount
    if ($rows[$#rows] !~ /\(\d+\s+rows\)/)
    {
        return 0;
    }

    return 1;
}

=head2 is_border_table

    if ($self->is_border_table(rows_ref=>$rows_ref, para_len=>0))
    {
	...
    }

Check if the given paragraph-array is a Border table.

A BORDER table can start with an optional table-caption,

    then it has a row of +------+-----+
    then it has a row of column headings separated by |
    then it has a row of +------+-----+
    then it has one or more rows of column values separated by |
    then it has a row of +------+-----+

=cut
sub is_border_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # A BORDER table must have at least 5 rows (see above)
    # And note that it could be indented with spaces
    if (@{$rows_ref} < 5)
    {
        return 0;
    }

    my @rows = @{$rows_ref};
    if ($rows[0] !~ /\|/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        shift @rows;
    }
    if (@rows < 5)
    {
        return 0;
    }
    if ($rows[0] !~ /^\s*[+][-]+[+][-]+[+][-+]*$/)    # +----+----+
    {
        return 0;
    }
    if ($rows[1] !~ /^\s*\|\s*\w+\s+\|\s+.*\|$/)      # | Colname |
    {
        return 0;
    }
    if ($rows[2] !~ /^\s*[+][-]+[+][-]+[+][-+]*$/)    # +----+----+
    {
        return 0;
    }
    if ($rows[3] !~ /^\s*\|\s*[^|]*\s+\|\s+.*\|$/)    # | value |
    {
        return 0;
    }
    # check the last row for +------+------+
    if ($rows[$#rows] !~ /^\s*[+][-]+[+][-]+[+][-+]*$/)    # +----+----+
    {
        return 0;
    }

    return 1;
}    # is_border_table

=head2 is_delim_table

    if ($self->is_delim_table(rows_ref=>$rows_ref, para_len=>0))
    {
	...
    }

Check if the given paragraph-array is a Delimited table.

A DELIM table can start with an optional table-caption,
then it has at least two rows which start and end and are
punctuated by a non-alphanumeric delimiter.

    | val1 | val2 |
    | val3 | val4 |

=cut
sub is_delim_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    #
    # And note that it could be indented with spaces
    if (@{$rows_ref} < 2)
    {
        return 0;
    }

    my @rows = @{$rows_ref};
    if ($rows[0] !~ /[^\w\s]/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        shift @rows;
    }
    if (@rows < 2)
    {
        return 0;
    }
    # figure out if the row starts with a possible delimiter
    my $delim = '';
    if ($rows[0] =~ /^\s*([^[:alnum:]])/)
    {
        $delim = $1;
        # have to get rid of ^ and [] and \
        $delim =~ s/\^//g;
        $delim =~ s/\[//g;
        $delim =~ s/\]//g;
        $delim =~ s/\\//g;
        if (!$delim)    # no delimiter after all
        {
            return 0;
        }
    }
    else
    {
        return 0;
    }
    # There needs to be at least three delimiters in the row
    my @all_delims = ($rows[0] =~ /[${delim}]/g);
    my $total_num_delims = @all_delims;
    if ($total_num_delims < 3)
    {
        return 0;
    }
    # All rows must start and end with the delimiter
    # and have $total_num_delims number of them
    foreach my $row (@rows)
    {
        if ($row !~ /^\s*[${delim}]/)
        {
            return 0;
        }
        if ($row !~ /[${delim}]\s*$/)
        {
            return 0;
        }
        @all_delims = ($row =~ /[${delim}]/g);
        if (@all_delims != $total_num_delims)
        {
            return 0;
        }
    }

    return 1;
}    # is_delim_table

=head2 tablestuff

    $self->tablestuff(table_type=>0,
		      rows_ref=>$rows_ref,
		      para_len=>0);

Process a table.

=cut
sub tablestuff ($%)
{
    my $self = shift;
    my %args = (
        table_type => 0,
        rows_ref   => undef,
        para_len   => 0,
        @_
    );
    my $table_type = $args{table_type};
    if ($table_type eq $TAB_ALIGN)
    {
        return $self->make_aligned_table(%args);
    }
    if ($table_type eq $TAB_PGSQL)
    {
        return $self->make_pgsql_table(%args);
    }
    if ($table_type eq $TAB_BORDER)
    {
        return $self->make_border_table(%args);
    }
    if ($table_type eq $TAB_DELIM)
    {
        return $self->make_delim_table(%args);
    }
}    # tablestuff

=head2 make_aligned_table

    $self->make_aligned_table(rows_ref=>$rows_ref,
			      para_len=>0);

Make an Aligned table.

=cut
sub make_aligned_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # TABLES: spot and mark up tables.  We combine the lines of the
    # paragraph using the string bitwise or (|) operator, the result
    # being in $spaces.  A character in $spaces is a space only if
    # there was a space at that position in every line of the
    # paragraph.  $space can be used to search for contiguous spaces
    # that occur on all lines of the paragraph.  If this results in at
    # least two columns, the paragraph is identified as a table.

    # Note that this sub must be called before checking for preformatted
    # lines because a table may well have whitespace to the left, in
    # which case it must not be incorrectly recognised as a preformat.
    my @rows = @{$rows_ref};
    my @starts;
    my @ends;
    my $spaces;
    my $max = 0;
    my $min = $para_len;
    foreach my $row (@rows)
    {
        ($spaces |= $row) =~ tr/ /\xff/c;
        $min = length $row if length $row < $min;
        $max = length $row if $max < length $row;
    }
    $spaces = substr $spaces, 0, $min;
    push(@starts, 0) unless $spaces =~ /^ /;
    while ($spaces =~ /((?:^| ) +)(?=[^ ])/g)
    {
        push @ends,   pos($spaces) - length $1;
        push @starts, pos($spaces);
    }
    shift(@ends) if $spaces =~ /^ /;
    push(@ends, $max);

    # Two or more rows and two or more columns indicate a table.
    if (2 <= @rows and 2 <= @starts)
    {
        $self->{__mode} |= $TABLE;

        # For each column, guess whether it should be left, centre or
        # right aligned by examining all cells in that column for space
        # to the left or the right.  A simple majority among those cells
        # that actually have space to one side or another decides (if no
        # alignment gets a majority, left alignment wins by default).
        my @align;
        my $cell = '';
        foreach my $col (0 .. $#starts)
        {
            my @count = (0, 0, 0, 0);
            foreach my $row (@rows)
            {
                my $width = $ends[$col] - $starts[$col];
                $cell = substr $row, $starts[$col], $width;
                ++$count[($cell =~ /^ / ? 2 : 0) +
                  ($cell =~ / $/ || length($cell) < $width ? 1 : 0)];
            }
            $align[$col] = 0;
            my $population = $count[1] + $count[2] + $count[3];
            foreach (1 .. 3)
            {
                if ($count[$_] * 2 > $population)
                {
                    $align[$col] = $_;
                    last;
                }
            }
        }

        foreach my $row (@rows)
        {
            $row = join '', $self->get_tag('tr'), (
                map {
                    $cell = substr $row, $starts[$_], $ends[$_] - $starts[$_];
                    $cell =~ s/^ +//;
                    $cell =~ s/ +$//;

                    if ($self->{escape_HTML_chars})
                    {
                        $cell = escape($cell);
                    }

                    (
                        $self->get_tag(
                            'td',
                            inside_tag => (
                                $self->{xhtml} ? $xhtml_alignments[$align[$_]]
                                : (
                                      $self->{lower_case_tags}
                                    ? $lc_alignments[$align[$_]]
                                    : $alignments[$align[$_]]
                                )
                            )
                        ),
                        $cell,
                        $self->close_tag('td')
                    );
                  } 0 .. $#starts
              ),
              $self->close_tag('tr');
        }

        # put the <TABLE> around the rows
        my $tag;
        if ($self->{xhtml})
        {
            $tag = $self->get_tag('table', inside_tag => ' summary=""');
        }
        else
        {
            $tag = $self->get_tag('table');
        }
        $rows[0] = join("\n", $tag, $rows[0]);
        $tag = $self->close_tag('table', tag_type => TAG_END);
        $rows[$#rows] .= "\n${tag}";
        @{$rows_ref} = @rows;
        return 1;
    }
    else
    {
        return 0;
    }
}    # make_aligned_table

=head2 make_pgsql_table

    $self->make_pgsql_table(rows_ref=>$rows_ref,
			      para_len=>0);

Make a PGSQL table.

=cut
sub make_pgsql_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # a PGSQL table can start with an optional table-caption,
    # then it has a row of column headings separated by |
    # then it has a row of ------+-----
    # then it has one or more rows of column values separated by |
    # then it has a row-count (N rows)
    # Thus it must have at least 4 rows.
    my @rows    = @{$rows_ref};
    my $caption = '';
    if ($rows[0] !~ /\|/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        $caption = shift @rows;
    }
    my @headings = split(/\s+\|\s+/, shift @rows);
    # skip the ----+--- line
    shift @rows;
    # grab the N rows line
    my $n_rows = pop @rows;

    # now start making the table
    my @tab_lines = ();
    my $tag;
    my $tag2;
    if ($self->{xhtml})
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1" summary=""');
    }
    else
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1"');
    }
    push @tab_lines, "$tag\n";
    if ($caption)
    {
        $caption =~ s/^\s+//;
        $caption =~ s/\s+$//;
        $tag     = $self->get_tag('caption');
        $tag2    = $self->close_tag('caption');
        $caption = join('', $tag, $caption, $tag2, "\n");
        push @tab_lines, $caption;
    }
    # table header
    my $thead = '';
    $tag = $self->get_tag('thead');
    $thead .= $tag;
    $tag = $self->get_tag('tr');
    $thead .= $tag;
    foreach my $col (@headings)
    {
        $col =~ s/^\s+//;
        $col =~ s/\s+$//;
        $tag  = $self->get_tag('th');
        $tag2 = $self->close_tag('th');
        $thead .= join('', $tag, $col, $tag2);
    }
    $tag = $self->close_tag('tr');
    $thead .= $tag;
    $tag = $self->close_tag('thead');
    $thead .= $tag;
    push @tab_lines, "${thead}\n";
    $tag = $self->get_tag('tbody');
    push @tab_lines, "$tag\n";

    # each row
    foreach my $row (@rows)
    {
        my $this_row = '';
        $tag = $self->get_tag('tr');
        $this_row .= $tag;
        my @cols = split(/\|/, $row);
        foreach my $cell (@cols)
        {
            $cell =~ s/^\s+//;
            $cell =~ s/\s+$//;
            if ($self->{escape_HTML_chars})
            {
                $cell = escape($cell);
            }
            if (!$cell)
            {
                $cell = ' ';
            }
            $tag  = $self->get_tag('td');
            $tag2 = $self->close_tag('td');
            $this_row .= join('', $tag, $cell, $tag2);
        }
        $tag = $self->close_tag('tr');
        $this_row .= $tag;
        push @tab_lines, "${this_row}\n";
    }

    # end the table
    $tag = $self->close_tag('tbody');
    push @tab_lines, "$tag\n";
    $tag = $self->get_tag('table', tag_type => TAG_END);
    push @tab_lines, "$tag\n";

    # and add the N rows line
    $tag = $self->get_tag('p');
    push @tab_lines, "${tag}${n_rows}\n";
    if ($self->{xhtml})
    {
        $tag = $self->get_tag('p', tag_type => TAG_END);
        $tab_lines[$#tab_lines] =~ s/\n/${tag}\n/;
    }

    # replace the rows
    @{$rows_ref} = @tab_lines;
}    # make_pgsql_table

=head2 make_border_table

    $self->make_border_table(rows_ref=>$rows_ref,
			     para_len=>0);

Make a BORDER table.

=cut
sub make_border_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # a BORDER table can start with an optional table-caption,
    # then it has a row of +------+-----+
    # then it has a row of column headings separated by |
    # then it has a row of +------+-----+
    # then it has one or more rows of column values separated by |
    # then it has a row of +------+-----+
    my @rows    = @{$rows_ref};
    my $caption = '';
    if ($rows[0] !~ /\|/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        $caption = shift @rows;
    }
    # skip the +----+---+ line
    shift @rows;
    # get the head row and cut off the start and end |
    my $head_row = shift @rows;
    $head_row =~ s/^\s*\|//;
    $head_row =~ s/\|$//;
    my @headings = split(/\s+\|\s+/, $head_row);
    # skip the +----+---+ line
    shift @rows;
    # skip the last +----+---+ line
    pop @rows;

    # now start making the table
    my @tab_lines = ();
    my $tag;
    if ($self->{xhtml})
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1" summary=""');
    }
    else
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1"');
    }
    push @tab_lines, "$tag\n";
    if ($caption)
    {
        $caption =~ s/^\s+//;
        $caption =~ s/\s+$//;
        $tag     = $self->get_tag('caption');
        $caption = $tag . $caption;
        $tag     = $self->close_tag('caption');
        $caption .= $tag;
        push @tab_lines, "$caption\n";
    }
    # table header
    my $thead = '';
    $tag = $self->get_tag('thead');
    $thead .= $tag;
    $tag = $self->get_tag('tr');
    $thead .= $tag;
    foreach my $col (@headings)
    {
        $col =~ s/^\s+//;
        $col =~ s/\s+$//;
        $tag = $self->get_tag('th');
        $thead .= $tag;
        $thead .= $col;
        $tag = $self->close_tag('th');
        $thead .= $tag;
    }
    $tag = $self->close_tag('tr');
    $thead .= $tag;
    $tag = $self->close_tag('thead');
    $thead .= $tag;
    push @tab_lines, "${thead}\n";
    $tag = $self->get_tag('tbody');
    push @tab_lines, "$tag\n";

    # each row
    foreach my $row (@rows)
    {
        # cut off the start and end |
        $row =~ s/^\s*\|//;
        $row =~ s/\|$//;
        my $this_row = '';
        $tag = $self->get_tag('tr');
        $this_row .= $tag;
        my @cols = split(/\|/, $row);
        foreach my $cell (@cols)
        {
            $cell =~ s/^\s+//;
            $cell =~ s/\s+$//;
            if ($self->{escape_HTML_chars})
            {
                $cell = escape($cell);
            }
            if (!$cell)
            {
                $cell = ' ';
            }
            $tag = $self->get_tag('td');
            $this_row .= $tag;
            $this_row .= $cell;
            $tag = $self->close_tag('td');
            $this_row .= $tag;
        }
        $tag = $self->close_tag('tr');
        $this_row .= $tag;
        push @tab_lines, "${this_row}\n";
    }

    # end the table
    $tag = $self->close_tag('tbody');
    push @tab_lines, "$tag\n";
    $tag = $self->get_tag('table', tag_type => TAG_END);
    push @tab_lines, "$tag\n";

    # replace the rows
    @{$rows_ref} = @tab_lines;
}    # make_border_table

=head2 make_delim_table

    $self->make_delim_table(rows_ref=>$rows_ref,
			    para_len=>0);

Make a Delimited table.

=cut
sub make_delim_table ($%)
{
    my $self = shift;
    my %args = (
        rows_ref => undef,
        para_len => 0,
        @_
    );
    my $rows_ref = $args{rows_ref};
    my $para_len = $args{para_len};

    # a DELIM table can start with an optional table-caption,
    # then it has at least two rows which start and end and are
    # punctuated by a non-alphanumeric delimiter.
    # A DELIM table has no table-header.
    my @rows    = @{$rows_ref};
    my $caption = '';
    if ($rows[0] !~ /\|/ && $rows[0] =~ /^\s*\w+/)    # possible caption
    {
        $caption = shift @rows;
    }
    # figure out the delimiter
    my $delim = '';
    if ($rows[0] =~ /^\s*([^[:alnum:]])/)
    {
        $delim = $1;
    }
    else
    {
        return 0;
    }

    # now start making the table
    my @tab_lines = ();
    my $tag;
    if ($self->{xhtml})
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1" summary=""');
    }
    else
    {
        $tag = $self->get_tag('table', inside_tag => ' border="1"');
    }
    push @tab_lines, "$tag\n";
    if ($caption)
    {
        $caption =~ s/^\s+//;
        $caption =~ s/\s+$//;
        $tag     = $self->get_tag('caption');
        $caption = $tag . $caption;
        $tag     = $self->close_tag('caption');
        $caption .= $tag;
        push @tab_lines, "$caption\n";
    }

    # each row
    foreach my $row (@rows)
    {
        # cut off the start and end delimiter
        $row =~ s/^\s*[${delim}]//;
        $row =~ s/[${delim}]$//;
        my $this_row = '';
        $tag = $self->get_tag('tr');
        $this_row .= $tag;
        my @cols = split(/[${delim}]/, $row);
        foreach my $cell (@cols)
        {
            $cell =~ s/^\s+//;
            $cell =~ s/\s+$//;
            if ($self->{escape_HTML_chars})
            {
                $cell = escape($cell);
            }
            if (!$cell)
            {
                $cell = ' ';
            }
            $tag = $self->get_tag('td');
            $this_row .= $tag;
            $this_row .= $cell;
            $tag = $self->close_tag('td');
            $this_row .= $tag;
        }
        $tag = $self->close_tag('tr');
        $this_row .= $tag;
        push @tab_lines, "${this_row}\n";
    }

    # end the table
    $tag = $self->get_tag('table', tag_type => TAG_END);
    push @tab_lines, "$tag\n";

    # replace the rows
    @{$rows_ref} = @tab_lines;
}    # make_delim_table

=head2 is_preformatted

    if ($self->is_preformatted($line))
    {
	...
    }

Returns true if the passed string is considered to be preformatted.

=cut
sub is_preformatted ($$)
{
    my $self = shift;
    my $line = shift;

    my $pre_white_min = $self->{preformat_whitespace_min};
    my $result        = (
        ($line =~ /\s{$pre_white_min,}\S+/o)    # whitespaces
          || ($line =~ /\.{$pre_white_min,}\S+/o)
    );                                          # dots
    return $result;
}

=head2 split_end_explicit_preformat

    $front = $self->split_end_explicit_preformat(para_ref=>$para_ref);

Modifies the given string, and returns the front preformatted part.

=cut
sub split_end_explicit_preformat ($%)
{
    my $self = shift;
    my %args = (
        para_ref => undef,
        @_
    );
    my $para_ref = $args{para_ref};

    my $tag      = '';
    my $pre_str  = '';
    my $post_str = '';
    if ($self->{__mode} & $PRE_EXPLICIT)
    {
        my $pe_mark = $self->{preformat_end_marker};
        if (${para_ref} =~ /$pe_mark/io)
        {
            ($pre_str, $post_str) = split(/$pe_mark/, ${$para_ref}, 2);
            if ($self->{escape_HTML_chars})
            {
                $pre_str = escape($pre_str);
            }
            $tag = $self->close_tag('pre');
            $pre_str .= "${tag}\n";
            $self->{__mode} ^= (($PRE | $PRE_EXPLICIT) & $self->{__mode});
        }
        else    # no end -- the whole thing is preformatted
        {
            $pre_str = ${$para_ref};
            if ($self->{escape_HTML_chars})
            {
                $pre_str = escape($pre_str);
            }
            ${$para_ref} = '';
        }
    }
    return $pre_str;
}    # split_end_explicit_preformat

=head2 endpreformat

    $self->endpreformat(para_lines_ref=>$para_lines_ref,
			para_action_ref=>$para_action_ref,
			ind=>0,
			prev_ref=>$prev_ref);

End a preformatted section.

=cut
sub endpreformat ($%)
{
    my $self = shift;
    my %args = (
        para_lines_ref  => undef,
        para_action_ref => undef,
        ind             => 0,
        prev_ref        => undef,
        @_
    );
    my $para_lines_ref  = $args{para_lines_ref};
    my $para_action_ref = $args{para_action_ref};
    my $ind             = $args{ind};
    my $prev_ref        = $args{prev_ref};

    my $tag = '';
    if ($self->{__mode} & $PRE_EXPLICIT)
    {
        my $pe_mark = $self->{preformat_end_marker};
        if ($para_lines_ref->[$ind] =~ /$pe_mark/io)
        {
            if ($ind == 0)
            {
                $tag = $self->close_tag('pre');
                $para_lines_ref->[$ind] = "${tag}\n";
            }
            else
            {
                $tag = $self->close_tag('pre');
                $para_lines_ref->[$ind - 1] .= "${tag}\n";
                $para_lines_ref->[$ind] = "";
            }
            $self->{__mode} ^= (($PRE | $PRE_EXPLICIT) & $self->{__mode});
            $para_action_ref->[$ind] |= $END;
        }
        return;
    }

    if (
        !$self->is_preformatted($para_lines_ref->[$ind])
        && (
            $self->{endpreformat_trigger_lines} == 1
            || ($ind + 1 < @{$para_lines_ref}
                && !$self->is_preformatted($para_lines_ref->[$ind + 1]))
            || $ind + 1 >= @{$para_lines_ref}    # last line of para
        )
      )
    {
        if ($ind == 0)
        {
            $tag = $self->close_tag('pre');
            ${$prev_ref} = "${tag}\n";
        }
        else
        {
            $tag = $self->close_tag('pre');
            $para_lines_ref->[$ind - 1] .= "${tag}\n";
        }
        $self->{__mode} ^= ($PRE & $self->{__mode});
        $para_action_ref->[$ind] |= $END;
    }
}    # endpreformat

=head2 preformat

    $self->preformat(mode_ref=>$mode_ref,
		     line_ref=>$line_ref,
		     line_action_ref=>$line_action_ref,
		     prev_ref=>$prev_ref,
		     next_ref=>$next_ref,
		     prev_action_ref);

Detect and process a preformatted section.

=cut
sub preformat ($%)
{
    my $self = shift;
    my %args = (
        mode_ref        => undef,
        line_ref        => undef,
        line_action_ref => undef,
        prev_ref        => undef,
        next_ref        => undef,
        prev_action_ref => undef,
        @_
    );
    my $mode_ref        = $args{mode_ref};
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};
    my $prev_ref        = $args{prev_ref};
    my $next_ref        = $args{next_ref};
    my $prev_action_ref = $args{prev_action_ref};

    my $tag = '';
    if ($self->{use_preformat_marker})
    {
        my $pstart = $self->{preformat_start_marker};
        if (${$line_ref} =~ /$pstart/io)
        {
            if (${$prev_ref} =~ s/<p>$//)
            {
                pop @{$self->{__tags}};
            }
            $tag =
              $self->get_tag('pre', inside_tag => " class='quote_explicit'");
            ${$line_ref} = "${tag}\n";
            ${$mode_ref}        |= $PRE | $PRE_EXPLICIT;
            ${$line_action_ref} |= $PRE;
            return;
        }
    }

    if (
           !(${$line_action_ref} & $MAILQUOTE)
        && !(${$prev_action_ref} & $MAILQUOTE)
        && (
            $self->{preformat_trigger_lines} == 0
            || (
                $self->is_preformatted(${$line_ref})
                && (
                    $self->{preformat_trigger_lines} == 1
                    || (defined $next_ref
                        && $self->is_preformatted(${$next_ref}))
                )
            )
        )
      )
    {
        if (${$prev_ref} =~ s/<p>$//)
        {
            pop @{$self->{__tags}};
        }
        $tag = $self->get_tag('pre');
        ${$line_ref} =~ s/^/${tag}\n/;
        ${$mode_ref}        |= $PRE;
        ${$line_action_ref} |= $PRE;
    }
}    # preformat

=head2 make_new_anchor

    $anchor = $self->make_new_anchor($heading_level);

Make a new anchor.

=cut
sub make_new_anchor ($$)
{
    my $self          = shift;
    my $heading_level = shift;

    my ($anchor, $i);

    return sprintf("%d", $self->{__non_header_anchor}++) if (!$heading_level);

    $anchor = "section";
    $self->{__heading_count}->[$heading_level - 1]++;

    # Reset lower order counters
    for ($i = @{$self->{__heading_count}}; $i > $heading_level; $i--)
    {
        $self->{__heading_count}->[$i - 1] = 0;
    }

    for ($i = 0; $i < $heading_level; $i++)
    {
        $self->{__heading_count}->[$i] = 1
          if !$self->{__heading_count}->[$i];    # In case they skip any
        $anchor .= sprintf("_%d", $self->{__heading_count}->[$i]);
    }
    chomp($anchor);
    $anchor;
}    # make_new_anchor

=head2 anchor_mail

    $self->anchor_mail($line_ref);

Make an anchor for a mail section.

=cut
sub anchor_mail ($$)
{
    my $self     = shift;
    my $line_ref = shift;

    if ($self->{make_anchors})
    {
        my ($anchor) = $self->make_new_anchor(0);
        if ($self->{lower_case_tags})
        {
            ${$line_ref} =~ s/([^ ]*)/<a name="$anchor">$1<\/a>/;
        }
        else
        {
            ${$line_ref} =~ s/([^ ]*)/<A NAME="$anchor">$1<\/A>/;
        }
    }
}    # anchor_mail

=head2 anchor_heading

    $self->anchor_heading($heading_level, $line_ref);

Make an anchor for a heading.

=cut
sub anchor_heading ($$$)
{
    my $self     = shift;
    my $level    = shift;
    my $line_ref = shift;

    if ($DictDebug & 8)
    {
        print STDERR "anchor_heading: ", ${$line_ref}, "\n";
    }
    if ($self->{make_anchors})
    {
        my ($anchor) = $self->make_new_anchor($level);
        if ($self->{lower_case_tags})
        {
            ${$line_ref} =~ s/(<h.>)(.*)(<\/h.>)/$1<a name="$anchor">$2<\/a>$3/;
        }
        else
        {
            ${$line_ref} =~ s/(<H.>)(.*)(<\/H.>)/$1<A NAME="$anchor">$2<\/A>$3/;
        }
    }
    if ($DictDebug & 8)
    {
        print STDERR "anchor_heading(after): ", ${$line_ref}, "\n";
    }
}    # anchor_heading

=head2 heading_level

    $self->heading_level($style);

Add a new heading style if this is a new heading style.

=cut
sub heading_level ($$)
{
    my $self = shift;

    my ($style) = @_;
    $self->{__heading_styles}->{$style} = ++$self->{__num_heading_styles}
      if !$self->{__heading_styles}->{$style};
    $self->{__heading_styles}->{$style};
}    # heading_level

=head2 is_ul_list_line

    if ($self->is_ul_list_line($line))
    {
	...
    }

Tests if this line starts a UL list item.

=cut
sub is_ul_list_line ($%)
{
    my $self = shift;
    my %args = (
        line => undef,
        @_
    );
    my $line = $args{line};

    my ($prefix, $number, $rawprefix, $term) = $self->listprefix($line);
    if ($prefix && !$number)
    {
        return 1;
    }
    return 0;
}

=head2 is_heading

    if ($self->is_heading(line_ref=>$line_ref, next_ref=>$next_ref))
    {
	...
    }

Tests if this line is a heading.  Needs to take account of the
next line, because a standard heading is defined by "underlining"
the text of the heading.

=cut
sub is_heading ($%)
{
    my $self = shift;
    my %args = (
        line_ref => undef,
        next_ref => undef,
        @_
    );
    my $line_ref = $args{line_ref};
    my $next_ref = $args{next_ref};

    if (   ${$line_ref} !~ /^\s*$/
        && !$self->is_ul_list_line(line => ${$line_ref})
        && defined $next_ref
        && ${$next_ref} =~ /^\s*[-=*.~+]+\s*$/)
    {
        my ($hoffset, $heading) = ${$line_ref} =~ /^(\s*)(.+)$/;
        $hoffset = "" unless defined($hoffset);
        $heading = "" unless defined($heading);
        # Unescape chars so we get an accurate length
        $heading =~ s/&[^;]+;/X/g;
        my ($uoffset, $underline) = ${$next_ref} =~ /^(\s*)(\S+)\s*$/;
        $uoffset   = "" unless defined($uoffset);
        $underline = "" unless defined($underline);
        my ($lendiff, $offsetdiff);
        $lendiff = length($heading) - length($underline);
        $lendiff *= -1 if $lendiff < 0;

        $offsetdiff = length($hoffset) - length($uoffset);
        $offsetdiff *= -1 if $offsetdiff < 0;
        if (   ($lendiff <= $self->{underline_length_tolerance})
            || ($offsetdiff <= $self->{underline_offset_tolerance}))
        {
            return 1;
        }
    }

    return 0;

}    # is_heading

=head2 heading
    
    $self->heading(line_ref=>$line_ref,
	next_ref=>$next_ref);

Make a heading.
Assumes is_heading is true.

=cut
sub heading ($%)
{
    my $self = shift;
    my %args = (
        line_ref => undef,
        next_ref => undef,
        @_
    );
    my $line_ref = $args{line_ref};
    my $next_ref = $args{next_ref};

    my ($hoffset, $heading) = ${$line_ref} =~ /^(\s*)(.+)$/;
    $hoffset = "" unless defined($hoffset);
    $heading = "" unless defined($heading);
    $heading =~ s/&[^;]+;/X/g;    # Unescape chars so we get an accurate length
    my ($uoffset, $underline) = ${$next_ref} =~ /^(\s*)(\S+)\s*$/;
    $uoffset   = "" unless defined($uoffset);
    $underline = "" unless defined($underline);

    $underline = substr($underline, 0, 1);

    # Call it a different style if the heading is in all caps.
    $underline .= "C" if $self->iscaps(${$line_ref});
    ${$next_ref} = " ";           # Eat the underline
    $self->{__heading_level} = $self->heading_level($underline);
    if ($self->{escape_HTML_chars})
    {
        ${$line_ref} = escape(${$line_ref});
    }
    $self->tagline("H" . $self->{__heading_level}, $line_ref);
    $self->anchor_heading($self->{__heading_level}, $line_ref);
}    # heading

=head2 is_custom_heading

    if ($self->is_custom_heading($line))
    {
	...
    }

Check if the given line matches a custom heading.

=cut
sub is_custom_heading ($%)
{
    my $self = shift;
    my %args = (
        line => undef,
        @_
    );
    my $line = $args{line};

    foreach my $reg (@{$self->{custom_heading_regexp}})
    {
        return 1 if ($line =~ /$reg/);
    }
    return 0;
}    # is_custom_heading

=head2 custom_heading

    $self->custom_heading(line_ref=>$line_ref);

Make a custom heading.  Assumes is_custom_heading is true.

=cut
sub custom_heading ($%)
{
    my $self = shift;
    my %args = (
        line_ref => undef,
        @_
    );
    my $line_ref = $args{line_ref};

    my $level;
    my $i = 0;
    foreach my $reg (@{$self->{custom_heading_regexp}})
    {
        if (${$line_ref} =~ /$reg/)
        {
            if ($self->{explicit_headings})
            {
                $level = $i + 1;
            }
            else
            {
                $level = $self->heading_level("Cust" . $i);
            }
            if ($self->{escape_HTML_chars})
            {
                ${$line_ref} = escape(${$line_ref});
            }
            $self->tagline("H" . $level, $line_ref);
            $self->anchor_heading($level, $line_ref);
            last;
        }
        $i++;
    }
}    # custom_heading

=head2 unhyphenate_para

    $self->unhyphenate_para($para_ref);

Join up hyphenated words that are split across lines.

=cut
sub unhyphenate_para ($$)
{
    my $self     = shift;
    my $para_ref = shift;

    # Treating this whole paragraph as one string, look for
    # 1 - whitespace
    # 2 - a word (ending in a hyphen, followed by a newline)
    # 3 - whitespace (starting on the next line)
    # 4 - a word with its punctuation
    # Substitute this with
    # 1-whitespace 2-word 4-word newline 3-whitespace
    # We preserve the 3-whitespace because we don't want to mess up
    # our existing indentation.
    ${$para_ref} =~
      /(\s*)([^\W\d_]*)\-\n(\s*)([^\W\d_]+[\)\}\]\.,:;\'\"\>]*\s*)/s;
    ${$para_ref} =~
s/(\s*)([^\W\d_]*)\-\n(\s*)([^\W\d_]+[\)\}\]\.,:;\'\"\>]*\s*)/$1$2$4\n$3/gs;
}    # unhyphenate_para

=head2 tagline

    $self->tagline($tag, $line_ref);

Put the given tag around the given line.

=cut
sub tagline ($$$)
{
    my $self     = shift;
    my $tag      = shift;
    my $line_ref = shift;

    chomp ${$line_ref};    # Drop newline
    my $tag1 = $self->get_tag($tag);
    my $tag2 = $self->close_tag($tag);
    ${$line_ref} =~ s/^\s*(.*)$/${tag1}$1${tag2}\n/;
}    # tagline

=head2 iscaps

    if ($self->iscaps($line))
    {
	...
    }

Check if a line is all capitals.

=cut
sub iscaps
{
    my $self = shift;
    local ($_) = @_;

    my $min_caps_len = $self->{min_caps_length};

    /^[^[:lower:]<]*[[:upper:]]{$min_caps_len,}[^[:lower:]<]*$/;
}    # iscaps

=head2 caps

    $self->caps(line_ref=>$line_ref,
		line_action_ref=>$line_action_ref);

Detect and deal with an all-caps line.

=cut
sub caps
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        @_
    );
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};

    if (   $self->{caps_tag}
        && $self->iscaps(${$line_ref}))
    {
        $self->tagline($self->{caps_tag}, $line_ref);
        ${$line_action_ref} |= $CAPS;
    }
}    # caps

=head2 do_delim

    $self->do_delim(line_ref=>$line_ref,
		    line_action_ref=>$line_action_ref,
		    delim=>'*',
		    tag=>'STRONG');

Deal with a line which has words delimited by the given delimiter;
this is used to deal with italics, bold and underline formatting.

=cut
sub do_delim
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        delim           => '*',
        tag             => 'STRONG',
        @_
    );
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};
    my $delim           = $args{delim};
    my $tag             = $args{tag};

    if ($delim eq '#')  
    {
        if (${$line_ref} =~ m/\B#([[:alpha:]])#\B/s)
	{
	    ${$line_ref} =~ s/\B#([[:alpha:]])#\B/<${tag}>$1<\/${tag}>/gs;
	}
	# special treatment of # for the #num case and the #link case
	if (${$line_ref} !~ m/<[aA]/)
	{
	    ${$line_ref} =~
s/#([^\d#](?![^#]*(?:<li>|<LI>|<P>|<p>))[^#]*[^# \t\n])#/<${tag}>$1<\/${tag}>/gs;
	}
	else
	{
	    my $line_with_links = '';
	    my $linkme = '';
	    my $unmatched = ${$line_ref};
	    while ($unmatched =~ 
		   m/#([^\d#](?![^#]*(?:<li>|<LI>|<P>|<p>))[^#]*[^# \t\n])#/s)
	    {
		$line_with_links .= $`;
		$linkme = $&;
		$unmatched = $';
		if (!$self->in_link_context($linkme, $line_with_links))
		{
		    $linkme =~
			s/#([^\d#](?![^#]*(?:<li>|<LI>|<P>|<p>))[^#]*[^# \t\n])#/<${tag}>$1<\/${tag}>/gs;
		}
		$line_with_links .= $linkme;
	    }
	    ${$line_ref} = $line_with_links . $unmatched;
	}
    }
    elsif ($delim eq '^')
    {
        ${$line_ref} =~
s/\^((?![^^]*(?:<li>|<LI>|<p>|<P>))(\w|["'<>])[^^]*)\^/<${tag}>$1<\/${tag}>/gs;
        ${$line_ref} =~ s/\B\^([[:alpha:]])\^\B/<${tag}>$1<\/${tag}>/gs;
    }
    elsif ($delim eq '_')
    {
        if (${$line_ref} =~ m/\B_([[:alpha:]])_\B/s)
	{
	    ${$line_ref} =~ s/\B_([[:alpha:]])_\B/<${tag}>$1<\/${tag}>/gs;
	    ${$line_ref} =~
		s#(?<![_[:alnum:]])_([^_]+?[[:alnum:]"'\.\?\&;:<>])_#<${tag}>$1</${tag}>#gs;
	}
	else
	{
	    # make sure we don't wallop links that have underscores
	    # need to make sure that _ delimiters are not mistaken for
	    # a_variable_name
	    my $line_with_links = '';
	    my $linkme = '';
	    my $unmatched = ${$line_ref};
	    while ($unmatched =~ 
			m#(?<![_[:alnum:]])_([^_]+?[[:alnum:]"'\.\?\&;:<>])_#s)
	    {
		$line_with_links .= $`;
		$linkme = $&;
		$unmatched = $';
		if (!$self->in_link_context($linkme, $line_with_links))
		{
		    $linkme =~
			s#(?<![_[:alnum:]])_([^_]+?[[:alnum:]"'\.\?\&;:<>])_#<${tag}>$1</${tag}>#gs;
		}
		$line_with_links .= $linkme;
	    }
	    ${$line_ref} = $line_with_links . $unmatched;
	}
    }
    elsif (length($delim) eq 1)    # one-character, general
    {
        if (${$line_ref} =~ m/\B[${delim}]([[:alpha:]])[${delim}]\B/s)
	{
	    ${$line_ref} =~ s/\B[${delim}]([[:alpha:]])[${delim}]\B/<${tag}>$1<\/${tag}>/gs;
	}
        ${$line_ref} =~
	    s#(?<![${delim}])[${delim}]([^${delim}]+?[[:alnum:][:punct:]\&<>])[${delim}]#<${tag}>$1</${tag}>#gs;
    }
    else
    {
        ${$line_ref} =~
s/(?<!${delim})${delim}((\w|["'])(\w|[-\s[:punct:]])*[^\s])${delim}/<${tag}>$1<\/${tag}>/gs;
        ${$line_ref} =~ s/${delim}]([[:alpha:]])${delim}/<${tag}>$1<\/${tag}>/gs;
    }
}    # do_delim

=head2 glob2regexp

    $regexp = glob2regexp($glob);

Convert very simple globs to regexps

=cut
sub glob2regexp
{
    my ($glob) = @_;

    # Escape funky chars
    $glob =~ s/[^\w\[\]\*\?\|\\]/\\$&/g;
    my ($regexp, $i, $len, $escaped) = ("", 0, length($glob), 0);

    for (; $i < $len; $i++)
    {
        my $char = substr($glob, $i, 1);
        if ($escaped)
        {
            $escaped = 0;
            $regexp .= $char;
            next;
        }
        if ($char eq "\\")
        {
            $escaped = 1;
            next;
            $regexp .= $char;
        }
        if ($char eq "?")
        {
            $regexp .= ".";
            next;
        }
        if ($char eq "*")
        {
            $regexp .= ".*";
            next;
        }
        $regexp .= $char;    # Normal character
    }
    join('', "\\b", $regexp, "\\b");
}    # glob2regexp

=head2 add_regexp_to_links_table

    $self->add_regexp_to_links_table(label=>$label,
				     pattern=>$pattern,
				     url=>$url,
				     switches=>$switches);

Add the given regexp "link definition" to the links table.

=cut
sub add_regexp_to_links_table ($%)
{
    my $self = shift;
    my %args = (
        label => undef,
        pattern => undef,
        url => undef,
        switches => undef,
        @_
    );
    my $label = $args{label};
    my $pattern = $args{pattern};
    my $URL = $args{url};
    my $switches = $args{switches};

    # No sense adding a second one if it's already in there.
    # It would never get used.
    if (!$self->{__links_table}->{$label})
    {

        # Keep track of the order they were added so we can
        # look for matches in the same order
        push(@{$self->{__links_table_order}}, ($label));

	$self->{__links_table_patterns}->{$label} = $pattern;
        $self->{__links_table}->{$label}        = $URL;      # Put it in The Table
        $self->{__links_switch_table}->{$label} = $switches;
        my $ind = @{$self->{__links_table_order}} - 1;
        print STDERR " (", $ind,
          ")\tLABEL: $label \tPATTERN: $pattern\n\tVALUE: $URL\n\tSWITCHES: $switches\n\n"
          if ($DictDebug & 1);
    }
    else
    {
        if ($DictDebug & 1)
        {
            print STDERR " Skipping entry.  Key already in table.\n";
            print STDERR "\tLABEL: $label \tPATTERN: $pattern\n\tVALUE: $URL\n\n";
        }
    }
}    # add_regexp_to_links_table

=head2 add_literal_to_links_table

    $self->add_literal_to_links_table(label=>$label,
				      pattern=>$pattern,
				      url=>$url,
				      switches=>$switches);

Add the given literal "link definition" to the links table.

=cut
sub add_literal_to_links_table ($%)
{
    my $self = shift;
    my %args = (
        label => undef,
        pattern => undef,
        url => undef,
        switches => undef,
        @_
    );
    my $label = $args{label};
    my $pattern = $args{pattern};
    my $URL = $args{url};
    my $switches = $args{switches};

    $pattern =~ s/(\W)/\\$1/g;    # Escape non-alphanumeric chars
    $pattern = "\\b$pattern\\b";      # Make a regexp out of it
    $self->add_regexp_to_links_table(label=>$label, pattern=>$pattern, url=>$URL, switches=>$switches);
}    # add_literal_to_links_table

=head2 add_glob_to_links_table

    $self->add_glob_to_links_table(label=>$label,
				   pattern=>$pattern,
				   url=>$url,
				   switches=>$switches);

Add the given glob "link definition" to the links table.

=cut
sub add_glob_to_links_table ($%)
{
    my $self = shift;
    my %args = (
        label => undef,
        pattern => undef,
        url => undef,
        switches => undef,
        @_
    );
    my $label = $args{label};
    my $pattern = $args{pattern};
    my $URL = $args{url};
    my $switches = $args{switches};

    $self->add_regexp_to_links_table(pattern=>glob2regexp($pattern),
	label=>$label,
	url=>$URL, switches=>$switches);
}    # add_glob_to_links_table

=head2 parse_dict
    
    $self->parse_dict($dictfile, $dict);

Parse the dictionary file.
(see also load_dictionary_links, for things that were stripped)

=cut
sub parse_dict ($$$)
{
    my $self = shift;

    my ($dictfile, $dict) = @_;

    print STDERR "Parsing dictionary file $dictfile\n"
      if ($DictDebug & 1);

    if ($dict =~ /->\s*->/)
    {
        my $message = "Two consecutive '->'s found in $dictfile\n";
        my $near;

        # Print out any useful context so they can find it.
        ($near) = $dict =~ /([\S ]*\s*->\s*->\s*\S*)/;
        $message .= "\n$near\n" if $near =~ /\S/;
        die $message;
    }

    my ($key, $URL, $switches, $options);
    while ($dict =~ /\s*(.+)\s+\-+([iehos]+\-+)?\>\s*(.*\S+)\s*\n/ig)
    {
        $key      = $1;
        $options  = $2;
        $options  = "" unless defined($options);
        $URL      = $3;
        $switches = 0;
        # Case insensitivity
        $switches += $LINK_NOCASE if $options =~ /i/i;
        # Evaluate as Perl code
        $switches += $LINK_EVAL if $options =~ /e/i;
        # provides HTML, not just URL
        $switches += $LINK_HTML if $options =~ /h/i;
        # Only do this link once
        $switches += $LINK_ONCE if $options =~ /o/i;
        # Only do this link once per section
        $switches += $LINK_SECT_ONCE if $options =~ /s/i;

        $key =~ s/\s*$//;    # Chop trailing whitespace

        if ($key =~ m|^/|)   # Regexp
        {
            $key = substr($key, 1);
            $key =~ s|/$||;    # Allow them to forget the closing /
            $self->add_regexp_to_links_table(pattern=>$key, label=>$key, url=>$URL, switches=>$switches);
        }
        elsif ($key =~ /^\|/)    # alternate regexp format
        {
            $key = substr($key, 1);
            $key =~ s/\|$//;      # Allow them to forget the closing |
            $key =~ s|/|\\/|g;    # Escape all slashes
            $self->add_regexp_to_links_table(pattern=>$key, label=>$key, url=>$URL, switches=>$switches);
        }
        elsif ($key =~ /\"/)
        {
            $key = substr($key, 1);
            $key =~ s/\"$//;      # Allow them to forget the closing "
            $self->add_literal_to_links_table(pattern=>$key, label=>$key, url=>$URL, switches=>$switches);
        }
        else
        {
            $self->add_glob_to_links_table(pattern=>$key, label=>$key, url=>$URL, switches=>$switches);
        }
    }

}    # parse_dict

=head2 setup_dict_checking

    $self->setup_dict_checking();

Set up the dictionary checking.

=cut
sub setup_dict_checking ($)
{
    my $self = shift;

    # now create the replace funcs and precomile the regexes
    my ($URL, $switches, $pattern, $options, $tag1, $tag2);
    my ($href, $r_sw);
    my @subs;
    my $i = 0;
    foreach my $label (@{$self->{__links_table_order}})
    {
        $switches = $self->{__links_switch_table}->{$label};
        $pattern = $self->{__links_table_patterns}->{$label};

        $href = $self->{__links_table}->{$label};

        if (!($switches & $LINK_HTML))
        {
            $href =~ s#/#\\/#g;
            $href = (
                $self->{lower_case_tags}
                ? join('', '<a href="', $href, '">$&<\\/a>')
                : join('', '<A HREF="', $href, '">$&<\\/A>')
            );
        }
        else
        {
            # change the uppercase tags to lower case
            if ($self->{lower_case_tags})
            {
                $href =~ s#(</)([A-Z]*)(>)#${1}\L${2}${3}#g;
                $href =~ s/(<)([A-Z]*)(>)/${1}\L${2}${3}/g;
                # and the anchors
                $href =~ s/(<)(A\s*HREF)([^>]*>)/$1\L$2$3/g;
            }
            $href =~ s#/#\\/#g;
        }

        $r_sw = "s";    # Options for replacing
        $r_sw .= "i" if ($switches & $LINK_NOCASE);
        $r_sw .= "e" if ($switches & $LINK_EVAL);

        # Generate code for replacements.
        # Create an anonymous subroutine for each replacement,
        # and store its reference in an array.
        # We need to do an "eval" to create these because we need to
        # be able to treat the *contents* of the $href variable
        # as if it were perl code, because sometimes the $href
        # contains things which need to be evaluated, such as $& or $1,
        # not just those cases where we have a "e" switch.
        my $code = <<EOT;
\$self->{__repl_code}->[$i] =
sub {
my \$al = shift;
\$al =~ s/$pattern/$href/$r_sw;
return \$al;
};
EOT
        print STDERR $code if ($DictDebug & 2);
        push @subs, $code;

        # compile searching pattern
        if ($switches & $LINK_NOCASE)    # i
        {
            $self->{__search_patterns}->[$i] = qr/$pattern/si;
        }
        else
        {
            $self->{__search_patterns}->[$i] = qr/$pattern/s;
        }
        $i++;
    }
    # now eval the replacements code string
    my $codes = join('', @subs);
    eval "$codes";
}    # setup_dict_checking

=head2 in_link_context

    if ($self->in_link_context($match, $before))
    {
	...
    }

Check if we are inside a link (<a ...>); certain kinds of substitution are
not allowed here.

=cut
sub in_link_context ($$$)
{
    my $self = shift;
    my ($match, $before) = @_;
    return 1 if $match =~ m@</?A>@i;    # No links allowed inside match

    my ($final_open, $final_close);
    if ($self->{lower_case_tags})
    {
        $final_open  = rindex($before, "<a ") - $[;
        $final_close = rindex($before, "</a>") - $[;
    }
    else
    {
        $final_open  = rindex($before, "<A ") - $[;
        $final_close = rindex($before, "</A>") - $[;
    }

    return 1 if ($final_open >= 0)    # Link opened
      && (
        ($final_close < 0)            # and not closed    or
        || ($final_open > $final_close)
      );                              # one opened after last close

    # Now check to see if we're inside a tag, matching a tag name,
    # or attribute name or value
    $final_open  = rindex($before, "<") - $[;
    $final_close = rindex($before, ">") - $[;
    ($final_open >= 0)                # Tag opened
      && (
        ($final_close < 0)            # and not closed    or
        || ($final_open > $final_close)
      );                              # one opened after last close
}    # in_link_context

=head2 apply_links

    $self->apply_links(para_ref=>$para_ref,
		       para_action_ref=>$para_action_ref);

Apply links and formatting to this paragraph.

=cut
sub apply_links ($%)
{
    my $self = shift;
    my %args = (
        para_ref        => undef,
        para_action_ref => undef,
        @_
    );
    my $para_ref        = $args{para_ref};
    my $para_action_ref = $args{para_action_ref};

    if ($self->{make_links}
        && @{$self->{__links_table_order}})
    {
        $self->check_dictionary_links(
            line_ref        => $para_ref,
            line_action_ref => $para_action_ref
        );
    }
    if ($self->{bold_delimiter})
    {
        my $tag = ($self->{lower_case_tags} ? 'strong' : 'STRONG');
        $self->do_delim(
            line_ref        => $para_ref,
            line_action_ref => $para_action_ref,
            delim           => $self->{bold_delimiter},
            tag             => $tag
        );
    }
    if ($self->{italic_delimiter})
    {
        my $tag = ($self->{lower_case_tags} ? 'em' : 'EM');
        $self->do_delim(
            line_ref        => $para_ref,
            line_action_ref => $para_action_ref,
            delim           => $self->{italic_delimiter},
            tag             => $tag
        );
    }
    if ($self->{underline_delimiter})
    {
        my $tag = ($self->{lower_case_tags} ? 'u' : 'U');
        $self->do_delim(
            line_ref        => $para_ref,
            line_action_ref => $para_action_ref,
            delim           => $self->{underline_delimiter},
            tag             => $tag
        );
    }

}    # apply_links

=head2 check_dictionary_links

    $self->check_dictionary_links(line_ref=>$line_ref,
				  line_action_ref=>$line_action_ref);

Check (and alter if need be) the bits in this line matching
the patterns in the link dictionary.

=cut
sub check_dictionary_links ($%)
{
    my $self = shift;
    my %args = (
        line_ref        => undef,
        line_action_ref => undef,
        @_
    );
    my $line_ref        = $args{line_ref};
    my $line_action_ref = $args{line_action_ref};

    my ($switches, $pattern, $options, $repl_func);
    my ($linkme, $line_with_links);

    # for each pattern, check and alter the line
    my $i = 0;
    foreach my $label (@{$self->{__links_table_order}})
    {
        $switches = $self->{__links_switch_table}->{$label};
        $pattern = $self->{__links_table_patterns}->{$label};

        # check the pattern
        if ($switches & $LINK_ONCE)    # Do link only once
        {
            $line_with_links = '';
            if (!$self->{__done_with_link}->[$i]
                && ${$line_ref} =~ $self->{__search_patterns}->[$i])
            {
                $self->{__done_with_link}->[$i] = 1;
                $line_with_links .= $`;
                $linkme = $&;

                ${$line_ref} = $';
                if (!$self->in_link_context($linkme, $line_with_links))
                {
                    print STDERR "Link rule $i matches $linkme\n"
                      if ($DictDebug & 4);

                    # call the special subroutine already created to do
                    # this replacement
                    $repl_func = $self->{__repl_code}->[$i];
                    $linkme    = &$repl_func($linkme);
                }
                $line_with_links .= $linkme;
            }
            ${$line_ref} = $line_with_links . ${$line_ref};
        }
        elsif ($switches & $LINK_SECT_ONCE)    # Do link only once per section
        {
            $line_with_links = '';
            if (!$self->{__done_with_sect_link}->[$i]
                && ${$line_ref} =~ $self->{__search_patterns}->[$i])
            {
                $self->{__done_with_sect_link}->[$i] = 1;
                $line_with_links .= $`;
                $linkme = $&;

                ${$line_ref} = $';
                if (!$self->in_link_context($linkme, $line_with_links))
                {
                    print STDERR "Link rule $i matches $linkme\n"
                      if ($DictDebug & 4);

                    # call the special subroutine already created to do
                    # this replacement
                    $repl_func = $self->{__repl_code}->[$i];
                    $linkme    = &$repl_func($linkme);
                }
                $line_with_links .= $linkme;
            }
            ${$line_ref} = $line_with_links . ${$line_ref};
        }
        else
        {
            $line_with_links = '';
            while (${$line_ref} =~ $self->{__search_patterns}->[$i])
            {
                $line_with_links .= $`;
                $linkme = $&;

                ${$line_ref} = $';
                if (!$self->in_link_context($linkme, $line_with_links))
                {
                    print STDERR "Link rule $i matches $linkme\n"
                      if ($DictDebug & 4);

                    # call the special subroutine already created to do
                    # this replacement
                    $repl_func = $self->{__repl_code}->[$i];
                    $linkme    = &$repl_func($linkme);
                }
                $line_with_links .= $linkme;
            }
            ${$line_ref} = $line_with_links . ${$line_ref};
        }
        $i++;
    }
    ${$line_action_ref} |= $LINK;
}    # check_dictionary_links

=head2 load_dictionary_links

    $self->load_dictionary_links();

Load the dictionary links.

=cut
sub load_dictionary_links ($)
{
    my $self = shift;

    @{$self->{__links_table_order}} = ();
    %{$self->{__links_table}}       = ();

    my $dict;
    foreach $dict (@{$self->{links_dictionaries}})
    {
        next unless $dict;
        open(DICT, "$dict") || die "Can't open Dictionary file $dict\n";

        my @lines = ();
        while (<DICT>)
        {
            # skip lines that start with '#'
            next if /^\#/;
            # skip lines that end with unescaped ':'
            next if /^.*[^\\]:\s*$/;
            push @lines, $_;
        }
        close(DICT);
        my $contents = join('', @lines);
        $self->parse_dict($dict, $contents);
    }
    # last of all, do the system dictionary, already read in from DATA
    if ($self->{__global_links_data})
    {
        $self->parse_dict("DATA", $self->{__global_links_data});
    }

    $self->setup_dict_checking();
}    # load_dictionary_links

=head2 do_file_start

    $self->do_file_start($outhandle, $para);

Extra stuff needed for the beginning:
HTML headers, and prepending a file if desired.

=cut
sub do_file_start ($$$)
{
    my $self      = shift;
    my $outhandle = shift;
    my $para      = shift;

    if (!$self->{extract})
    {
        my @para_lines = split(/\n/, $para);
        my $first_line = $para_lines[0];

        if ($self->{doctype})
        {
            if ($self->{xhtml})
            {
                print $outhandle
'<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"',
                  "\n";
                print $outhandle
		  '"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">',
                  "\n";
		print $outhandle $self->get_tag('html',
		    inside_tag => ' xmlns="http://www.w3.org/1999/xhtml"'), "\n";
            }
            else
            {
                print $outhandle '<!DOCTYPE HTML PUBLIC "', $self->{doctype},
                  "\">\n";
		print $outhandle $self->get_tag('html'), "\n";
            }
        }
        print $outhandle $self->get_tag('head'), "\n";

        # if --titlefirst is set and --title isn't, use the first line
        # as the title.
        if ($self->{titlefirst} && !$self->{title})
        {
            my ($tit) = $first_line =~ /^ *(.*)/;    # grab first line
            $tit =~ s/ *$//;                         # strip trailing whitespace
            $tit = escape($tit) if $self->{escape_HTML_chars};
            $self->{'title'} = $tit;
        }
        if (!$self->{title})
        {
            $self->{'title'} = "";
        }
        print $outhandle $self->get_tag('title'), $self->{title},
          $self->close_tag('title'), "\n";

        if ($self->{append_head})
        {
            open(APPEND, $self->{append_head})
              || die "Failed to open ", $self->{append_head}, "\n";
            while (<APPEND>)
            {
                print $outhandle $_;
            }
            close(APPEND);
        }

        if ($self->{lower_case_tags})
        {
            print $outhandle $self->get_tag(
                'meta',
                tag_type   => TAG_EMPTY,
                inside_tag => " name=\"generator\" content=\"$PROG v$HTML::TextToHTML::VERSION\""
              ),
              "\n";
        }
        else
        {
            print $outhandle $self->get_tag(
                'meta',
                tag_type   => TAG_EMPTY,
                inside_tag => " NAME=\"generator\" CONTENT=\"$PROG v$HTML::TextToHTML::VERSION\""
              ),
              "\n";
        }
        if ($self->{style_url})
        {
            my $style_url = $self->{style_url};
            if ($self->{lower_case_tags})
            {
                print $outhandle $self->get_tag(
                    'link',
                    tag_type   => TAG_EMPTY,
                    inside_tag =>
" rel=\"stylesheet\" type=\"text/css\" href=\"$style_url\""
                  ),
                  "\n";
            }
            else
            {
                print $outhandle $self->get_tag(
                    'link',
                    tag_type   => TAG_EMPTY,
                    inside_tag =>
" REL=\"stylesheet\" TYPE=\"text/css\" HREF=\"$style_url\""
                  ),
                  "\n";
            }
        }
        print $outhandle $self->close_tag('head'), "\n";
        if ($self->{body_deco})
        {
            print $outhandle $self->get_tag('body',
                inside_tag => $self->{body_deco}), "\n";
        }
        else
        {
            print $outhandle $self->get_tag('body'), "\n";
        }
    }

    if ($self->{prepend_file})
    {
        if (-r $self->{prepend_file})
        {
            open(PREPEND, $self->{prepend_file});
            while (<PREPEND>)
            {
                print $outhandle $_;
            }
            close(PREPEND);
        }
        else
        {
            print STDERR "Can't find or read file ", $self->{prepend_file},
              " to prepend.\n";
        }
    }
}    # do_file_start

=head2 do_init_call

    $self->do_init_call();

Certain things, like reading link dictionaries, need to be done only
once.

=cut
sub do_init_call ($)
{
    my $self = shift;

    if (!$self->{__call_init_done})
    {
        push(@{$self->{links_dictionaries}}, ($self->{default_link_dict}))
          if ($self->{make_links} && (-f $self->{default_link_dict}));
	if ($self->{links_dictionaries})
	{
	    # only put into the links dictionaries files which are readable
	    my @dict_files = @{$self->{links_dictionaries}};
	    $self->args(links_dictionaries => []);

	    foreach my $ld (@dict_files)
	    {
		if (-r $ld)
		{
		    $self->{'make_links'} = 1;
		    $self->args(['--links_dictionaries', $ld]);
		}
		else
		{
		    print STDERR "Can't find or read link-file $ld\n";
		}
	    }
	}
        if ($self->{make_links})
        {
            $self->load_dictionary_links();
        }

        # various initializations
        $self->{__non_header_anchor} = 0;
        $self->{__mode}              = 0;
        $self->{__listnum}           = 0;
        $self->{__list_nice_indent}  = '';
        $self->{__list_indent}       = [];
        $self->{__tags}              = [];

        $self->{__call_init_done} = 1;
    }
}    # do_init_call

=head1 FILE FORMATS

There are two files which are used which can affect the outcome of the
conversion.  One is the link dictionary, which contains patterns (of how
to recognise http links and other things) and how to convert them. The
other is, naturally, the format of the input file itself.

=head2 Link Dictionary

A link dictionary file contains patterns to match, and what to convert
them to.  It is called a "link" dictionary because it was intended to be
something which defined what a href link was, but it can be used for
more than that.  However, if you wish to define your own links, it is
strongly advised to read up on regular expressions (regexes) because
this relies heavily on them.

The file consists of comments (which are lines starting with #)
and blank lines, and link entries.
Each entry consists of a regular expression, a -> separator (with
optional flags), and a link "result".

In the simplest case, with no flags, the regular expression
defines the pattern to look for, and the result says what part
of the regular expression is the actual link, and the link which
is generated has the href as the link, and the whole matched pattern
as the visible part of the link.  The first character of the regular
expression is taken to be the separator for the regex, so one
could either use the traditional / separator, or something else
such as | (which can be helpful with URLs which are full of / characters).

So, for example, an ftp URL might be defined as:

    |ftp:[\w/\.:+\-]+|      -> $&

This takes the whole pattern as the href, and the resultant link
has the same thing in the href as in the contents of the anchor.

But sometimes the href isn't the whole pattern.

    /<URL:\s*(\S+?)\s*>/ --> $1

With the above regex, a () grouping marks the first subexpression,
which is represented as $1 (rather than $& the whole expression).
This entry matches a URL which was marked explicitly as a URL
with the pattern <URL:foo>  (note the < is shown as the
entity, not the actual character.  This is because by the
time the links dictionary is checked, all such things have
already been converted to their HTML entity forms, unless, of course,
the escape_HTML_chars option was turned off)
This would give us a link in the form
<A HREF="foo"><URL:foo></A>

B<The h flag>

However, if we want more control over the way the link is constructed,
we can construct it ourself.  If one gives the h flag, then the
"result" part of the entry is taken not to contain the href part of
the link, but the whole link.

For example, the entry:

    /<URL:\s*(\S+?)\s*>/ -h-> <A HREF="$1">$1</A>

will take <URL:foo> and give us <A HREF="foo">foo</A>

However, this is a very powerful mechanism, because it
can be used to construct custom tags which aren't links at all.
For example, to flag *italicised words* the following
entry will surround the words with EM tags.

    /\B\*([a-z][a-z -]*[a-z])\*\B/ -hi-> <EM>$1</EM>

B<The i flag>

This turns on ignore case in the pattern matching.

B<The e flag>

This turns on execute in the pattern substitution.  This really
only makes sense if h is turned on too.  In that case, the "result"
part of the entry is taken as perl code to be executed, and the
result of that code is what replaces the pattern.

B<The o flag>

This marks the entry as a once-only link.  This will convert the
first instance of a matching pattern, and ignore any others
further on.

For example, the following pattern will take the first mention
of HTML::TextToHTML and convert it to a link to the module's home page.

    "HTML::TextToHTML"  -io-> http://www.katspace.com/tools/text_to_html/

=head2 Input File Format

For the most part, this module tries to use intuitive conventions for
determining the structure of the text input.  Unordered lists are
marked by bullets; ordered lists are marked by numbers or letters;
in either case, an increase in indentation marks a sub-list contained
in the outer list.

Headers (apart from custom headers) are distinguished by "underlines"
underneath them; headers in all-capitals are distinguished from
those in mixed case.  All headers, both normal and custom headers,
are expected to start at the first line in a "paragraph".

In other words, the following is a header:

    I am Head Man
    -------------

But the following does not have a header:

    I am not a head Man, man
    I am Head Man
    -------------

Tables require a more rigid convention.  A table must be marked as a
separate paragraph, that is, it must be surrounded by blank lines.
Tables come in different types.  For a table to be parsed, its
--table_type option must be on, and the --make_tables option must be true.

B<ALIGN Table Type>

Columns must be separated by two or more spaces (this prevents
accidental incorrect recognition of a paragraph where interword spaces
happen to line up).  If there are two or more rows in a paragraph and
all rows share the same set of (two or more) columns, the paragraph is
assumed to be a table.  For example

    -e  File exists.
    -z  File has zero size.
    -s  File has nonzero size (returns size).

becomes

    <table>
    <tr><td>-e</td><td>File exists.</td></tr>
    <tr><td>-z</td><td>File has zero size.</td></tr>
    <tr><td>-s</td><td>File has nonzero size (returns size).</td></tr>
    </table>

This guesses for each column whether it is intended to be left,
centre or right aligned.

B<BORDER Table Type>

This table type has nice borders around it, and will be rendered
with a border, like so:

    +---------+---------+
    | Column1 | Column2 |
    +---------+---------+
    | val1    | val2    |
    | val3    | val3    |
    +---------+---------+

The above becomes

    <table border="1">
    <thead><tr><th>Column1</th><th>Column2</th></tr></thead>
    <tbody>
    <tr><td>val1</td><td>val2</td></tr>
    <tr><td>val3</td><td>val3</td></tr>
    </tbody>
    </table>

It can also have an optional caption at the start.

         My Caption
    +---------+---------+
    | Column1 | Column2 |
    +---------+---------+
    | val1    | val2    |
    | val3    | val3    |
    +---------+---------+

B<PGSQL Table Type>

This format of table is what one gets from the output of a Postgresql
query.

     Column1 | Column2
    ---------+---------
     val1    | val2
     val3    | val3
    (2 rows)

This can also have an optional caption at the start.
This table is also rendered with a border and table-headers like
the BORDER type.

B<DELIM Table Type>

This table type is delimited by non-alphanumeric characters, and has to
have at least two rows and two columns before it's recognised as a table.

This one is delimited by the '| character:

    | val1  | val2  |
    | val3  | val3  |

But one can use almost any suitable character such as : # $ % + and so on.
This is clever enough to figure out what you are using as the delimiter
if you have your data set up like a table.  Note that the line has to
both begin and end with the delimiter, as well as using it to separate
values.

This can also have an optional caption at the start.

=head1 EXAMPLES

    use HTML::TextToHTML;
 
=head2 Create a new object

    my $conv = new HTML::TextToHTML();

    my $conv = new HTML::TextToHTML(title=>"Wonderful Things",
			    default_link_dict=>$my_link_file,
      );

=head2 Add further arguments

    $conv->args(short_line_length=>60,
	       preformat_trigger_lines=>4,
	       caps_tag=>"strong",
      );

=head2 Convert a file

    $conv->txt2html(infile=>[$text_file],
                     outfile=>$html_file,
		     title=>"Wonderful Things",
		     mail=>1
      );

=head2 Make a pipleline

    open(IN, "ls |") or die "could not open!";
    $conv->txt2html(inhandle=>[\*IN],
                     outfile=>'-',
      );

=head1 NOTES

=over

=item *

If the underline used to mark a header is off by more than 1, then 
that part of the text will not be picked up as a header unless you
change the value of --underline_length_tolerance and/or
--underline_offset_tolerance.  People tend to forget this.

=back

=head1 REQUIRES

HTML::TextToHTML requires Perl 5.8.1 or later.

For installation, it needs:

    Module::Build

The txt2html script needs:

    Getopt::Long
    Getopt::ArgvFile
    Pod::Usage
    File::Basename

For testing, it also needs:

    Test::More

For debugging, it also needs:

    YAML::Syck

=head1 INSTALLATION

Make sure you have the dependencies installed first!
(see REQUIRES above)

Some of those modules come standard with more recent versions of perl,
but I thought I'd mention them anyway, just in case you may not have
them.

If you don't know how to install these, try using the CPAN module, an
easy way of auto-installing modules from the Comprehensive Perl Archive
Network, where the above modules reside.
Do "perldoc perlmodinstall" or "perldoc CPAN" for more information.

To install this module type the following:

   perl Build.PL
   ./Build
   ./Build test
   ./Build install

Or, if you're on a platform (like DOS or Windows) that doesn't like the
"./" notation, you can do this:

   perl Build.PL
   perl Build
   perl Build test
   perl Build install

In order to install somewhere other than the default, such as
in a directory under your home directory, like "/home/fred/perl"
go

   perl Build.PL --install_base /home/fred/perl

as the first step instead.

This will install the files underneath /home/fred/perl.

You will then need to make sure that you alter the PERL5LIB variable to
find the modules, and the PATH variable to find the script.

Therefore you will need to change:
your path, to include /home/fred/perl/script (where the script will be)

	PATH=/home/fred/perl/script:${PATH}

the PERL5LIB variable to add /home/fred/perl/lib

	PERL5LIB=/home/fred/perl/lib:${PERL5LIB}

Note that the system links dictionary will be installed as
"/home/fred/perl/share/txt2html/txt2html.dict"

If you want to install in a temporary install directory (such as
if you are building a package) then instead of going

   perl Build install

go

   perl Build install destdir=/my/temp/dir

and it will be installed there, with a directory structure under
/my/temp/dir the same as it would be if it were installed plain.
Note that this is NOT the same as setting --install_base, because
certain things are done at build-time which use the install_base info.

See "perldoc perlrun" for more information on PERL5LIB, and
see "perldoc Module::Build" for more information on
installation options.

=head1 BUGS

Please, send to
https://github.com/resurrecting-open-source-projects/txt2html/issues

=head1 SEE ALSO

perl
L<txt2html>.

=head1 AUTHOR

    Kathryn Andersen (RUBYKAT)
    perlkat AT katspace dot com
    http//www.katspace.com/

based on txt2html by Seth Golub

=head1 COPYRIGHT AND LICENCE

Original txt2html script copyright (c) 1994-2000 Seth Golub <seth AT aigeek.com>

Copyright (c) 2002-2005 by Kathryn Andersen

Copyright (c) 2018-2019 Joao Eriberto Mota Filho

This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.

=cut

#------------------------------------------------------------------------
1;
��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/scripts/������������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0014726�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/scripts/txt2html����������������������������������������������������������������������0000664�0000000�0000000�00000067476�13521162376�0016463�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!/usr/bin/perl
use 5.006_001;
use strict;
##---------------------------------------------------------------------------##

=head1 NAME

txt2html - convert plain text file to HTML

=head1 VERSION

version 2.53

=head1 SYNOPSIS

txt2html --help | --manpage

txt2html [ --append_file I<filename> ] [ --append_head I<filename> ]
    [ --body_deco I<string> ] [ --bold_delimiter I<string> ]
    [ --bullets I<string> ] [ --bullets_ordered I<string> ] [ --caps_tag I<tag> ]
    { --custom_heading_regexp I<regexp> } [ --debug ] [ --demoronize ]
    [ --default_link_dict I<filename> ] [ --dict_debug I<n> ]
    [ --doctype I<doctype> ] [ --eight_bit_clean ] [ --escape_HTML_chars ]
    [ --explicit_headings ] [ --extract ] [ --hrule_min I<n> ]
    [ --indent_width I<n> ] [ --indent_par_break ]
    { --infile I<filename> | --instring I<string> }
    [ --italic_delimiter I<string> ] { --links_dictionaries I<filename> }
    [ --link_only ] [ --lower_case_tags ] [ --mailmode ]
    [ --make_anchors ] [ --make_tables ] [ --min_caps_length I<n> ]
    [ --outfile I<filename> ] [ --par_indent I<n> ]
    [ --preformat_trigger_lines I<n> ] [ --endpreformat_trigger_lines I<n> ]
    [ --preformat_start_marker I<regexp> ] [ --preformat_end_marker I<regexp> ]
    [ --preformat_whitespace_min I<n> ] [ --prepend_file I<filename> ]
    [ --preserve_indent ] [ --short_line_length I<n> ]
    [ --style_url I<stylesheet_url> ] [ --tab_width I<n> ]
    [ --table_type I<type>=0/1 ] [ --title I<title> ] [ --titlefirst ]
    [ --underline_delimiter I<string> ] [ --underline_length_tolerance I<n> ]
    [ --underline_offset_tolerance I<n> ] [ --unhyphenation ]
    [ --use_mosaic_header ] [ --use_preformat_marker ] [ --xhtml ] [file ...]

=head1 DESCRIPTION

txt2html converts plain text files to HTML.

It supports headings, tables, lists, simple character markup, and
hyperlinking, and is highly customizable. It recognizes some of the
apparent structure of the source document (mostly whitespace and
typographic layout), and attempts to mark that structure explicitly
using HTML. The purpose for this tool is to provide an easier way of
converting existing text documents to HTML format.

One can use txt2html as a filter, outputting the result to STDOUT,
or to a given file.

One can define options in a config file as well as on the command-line.

=head1 OPTIONS

Option names can be abbreviated to the shortest unique name for that option.
Options can start with "--" or "-". Boolean options can be negated
by preceding them with "no"; options with hash or array values
can be added to by giving the option again for each value.

See L<Getopt::Long> for more information.

If the Getopt::ArgvFile module is installed, then groups of options can
be read from a file or files designated by the @ character preceding
the name.  For example:

    txt2html @poem_options --outfile poem_glory.html  poem_glory.txt

See L<Options Files> for more information.

Help options:

=over

=item --help

Display short help and exit.

=item --manpage

Display full documentation and exit.
This requires perldoc to be installed.

=back

General options:

=over

=item --append_file I<filename> | --append I<filename> | --append_body I<filename>

If you want something appended by default, put the filename here.
The appended text will not be processed at all, so make sure it's
plain text or decent HTML.  i.e. do not have things like:
    Mary Andersen E<lt>kitty@example.comE<gt>
but instead, have:
    Mary Andersen <kitty@example.com>

(default: nothing)

=item --append_head I<filename> | -ah I<filename>

If you want something appended to the head by default, put the filename here.
The appended text will not be processed at all, so make sure it's
plain text or decent HTML.  i.e. do not have things like:
    Mary Andersen E<lt>kitty@example.comE<gt>
but instead, have:
    Mary Andersen <kitty@example.com>

(default: nothing)

=item --body_deco I<string>

Body decoration string: a string to be added to the BODY tag so that
one can set attributes to the BODY (such as class, style, bgcolor etc)
For example, "class='withimage'".

=item --bold_delimiter I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as bold (that is, to be given a STRONG
tag).  If this is empty, then no bolding of text will be done.
(default: #)

=item --bullets I<string>

This defines what single characters are taken to be "bullet" characters
for unordered lists.  Note that because this is used as a character
class, if you use '-' it must come first.
(default:-=o*\267)

=item --bullets_ordered I<string>

This defines what single characters are taken to be "bullet" placeholder
characters for ordered lists.  Ordered lists are normally marked by
a number or letter followed by '.' or ')' or ']' or ':'.  If an ordered
bullet is used, then it simply indicates that this is an ordered list,
without giving explicit numbers.

Note that because this is used as a character class, if you use '-' it
must come first.
(default:nothing)

=item --caps_tag I<tag> | --capstag I<tag> | -ct I<tag>

Tag to put around all-caps lines
(default: STRONG)
If an empty tag is given, then no tag will be put around all-caps lines.

=item --custom_heading_regexp I<regexp> | --heading I<regexp> | -H I<regexp>

Add a regexp for headings.  Header levels are assigned by regexp
in order seen When a line matches a custom header regexp, it is tagged as
a header.  If it's the first time that particular regexp has matched,
the next available header level is associated with it and applied to
the line.  Any later matches of that regexp will use the same header level.
Therefore, if you want to match numbered header lines, you could use
something like this:

    -H '^ *\d+\. \w+' -H '^ *\d+\.\d+\. \w+' -H '^ *\d+\.\d+\.\d+\. \w+'

Then lines like

                " 1. Examples "
                " 1.1. Things"
            and " 4.2.5. Cold Fusion"

Would be marked as H1, H2, and H3 (assuming they were found in that
order, and that no other header styles were encountered).
If you prefer that the first one specified always be H1, the second
always be H2, the third H3, etc, then use the -EH/--explicit-headings
option.

This is a multi-valued option.

(default: none)

=item --debug

Enable copious script debugging output (don't bother, this is for the
developer)

=item --default_link_dict I<filename>

The name of the default "user" link dictionary.
(default: "$ENV{'HOME'}/.txt2html.dict")

=item --demoronize

Convert Microsoft-generated character codes that are non-ISO codes into
something more reasonable.
(default:true)

=item --dict_debug I<n> | -db I<n>

Debug mode for link dictionaries Bitwise-Or what you want to see:
          1: The parsing of the dictionary
          2: The code that will make the links
          4: When each rule matches something
          8: When each tag is created

(default: 0)

=item --doctype I<doctype> | --dt I<doctype>

This gets put in the DOCTYPE field at the top of the document, unless it's
empty.

Default :
'-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd'

If --xhtml is true, the contents of this is ignored, unless it's
empty, in which case no DOCTYPE declaration is output.

=item --eight_bit_clean | -8

If false, convert Latin-1 characters to HTML entities.
If true, this conversion is disabled.
(default: false)

=item --escape_HTML_chars | --escapechars | -ec

turn & E<lt> E<gt> into & > <
(default: true)

=item --explicit_headings | -EH

Don't try to find any headings except the ones specified in the
--custom_heading_regexp option.
Also, the custom headings will not be assigned levels in the order they
are encountered in the document, but in the order they are specified on
the command line.
(default: false)

=item --extract

Extract Mode; don't put HTML headers or footers on the result, just
the plain HTML (thus making the result suitable for inserting into
another document (or as part of the output of a CGI script).
(default: false)

=item --hrule_min I<n> | --hrule I<n> | -r I<n>

Min number of ---s for an HRule.
(default: 4)

=item --indent_width I<n> | --indent I<n> | -iw I<n>

Indents this many spaces for each level of a list.
(default: 2)

=item --indent_par_break | -ipb

Treat paragraphs marked solely by indents as breaks with indents.
That is, instead of taking a three-space indent as a new paragraph,
put in a <BR> and three non-breaking spaces instead.
(see also --preserve_indent)
(default: false)

=item --infile I<filename>

The name of the input file.
This is a cumulative list argument.  If you want to process more than
one file, just add another --infile I<file> to the list of arguments.
Or else just add the filename without the option, after all the options.
Note that the special file name of '-' means standard input.

(default:-)

=item --instring I<string>

An input string.  One can either have input files or input strings,
not both.  If you want to process more than one string, just add
another --instring I<string> to the list of arguments.

=item --italic_delimiter I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as italic (that is, to be given a EM
tag).  If this is empty, no italicising of text will be done.
(default: *)

=item --links_dictionaries I<filename> | --link I<filename> | -l I<filename>

File to use as a link-dictionary.  There can be more than one of these.
These are in addition to the System Link Dictionary and the User Link
Dictionary.

=item --link_only | --linkonly | -LO

Do no escaping or marking up at all, except for processing the links
dictionary file and applying it.  This is useful if you want to use
the linking feature on an HTML document.  If the HTML is a
complete document (includes HTML,HEAD,BODY tags, etc) then you'll
probably want to use the --extract option also.
(default: false)

=item --lower_case_tags

Force all the tags to be in lower-case.

=item --mailmode | -m

Deal with mail headers & quoted text.  The mail header paragraph is
given the class 'mail_header', and mail-quoted text is given the class
'quote_mail'.
(default: false)

=item --make_anchors | --anchors

Should we try to make anchors in headings?
(default: true)

=item --make_links

Should we try to build links?  If this is false, then the links
dictionaries are not consulted and only structural text-to-HTML
conversion is done.
(default: true)

=item --make_tables | --tables

Should we try to build tables?  If true, spots tables and marks them up
appropriately.  See L<Input File Format> for information on how tables
should be formatted.

This overrides the detection of lists; if something looks like a table,
it is taken as a table, and list-checking is not done for that
paragraph.

(default: false)

=item --min_caps_length I<n> | --caps I<n> | -c I<n>

min sequential CAPS for an all-caps line
(default: 3)

=item --outfile I<filename>

The name of the output file.  If it is "-" then the output goes
to Standard Output.
(default: - )

=item --par_indent I<n>

Minimum number of spaces indented in first lines of paragraphs.
  Only used when there's no blank line
preceding the new paragraph.
(default: 2)

=item --preformat_trigger_lines I<n> | --prebegin I<n> | -pb I<n>

How many lines of preformatted-looking text are needed to switch to <PRE>
          <= 0 : Preformat entire document
             1 : one line triggers
          >= 2 : two lines trigger

(default: 2)

=item --endpreformat_trigger_lines I<n> | --preend I<n> | -pe I<n>

How many lines of unpreformatted-looking text are needed to switch from <PRE>
           <= 0 : Never preformat within document
              1 : one line triggers
           >= 2 : two lines trigger
(default: 2)

NOTE for --prebegin and --preend:
A zero takes precedence.  If one is zero, the other is ignored.
If both are zero, entire document is preformatted.

=item --preformat_start_marker I<regexp>

What flags the start of a preformatted section if --use_preformat_marker
is true.

(default: "^(:?(:?<)|<)PRE(:?(:?>)|>)\$")

=item --preformat_end_marker I<regexp>

What flags the end of a preformatted section if --use_preformat_marker
is true.

(default: "^(:?(:?<)|<)/PRE(:?(:?>)|>)\$")

=item --preformat_whitespace_min I<n> | --prewhite I<n> | -p I<n>

Minimum number of consecutive whitespace characters to trigger
normal preformatting. 
NOTE: Tabs are expanded to spaces before this check is made.
That means if B<tab_width> is 8 and this is 5, then one tab may be
expanded to 8 spaces, which is enough to trigger preformatting.
(default: 5)

=item --prepend_file I<filename> | --prepend_body I<filename> | --pp I<filename>

If you want something prepended to the processed body text, put the
filename here.  The prepended text will not be processed at all, so make
sure it's plain text or decent HTML.

(default: nothing)

=item --preserve_indent | -pi

Preserve the first-line indentation of paragraphs marked with indents
by replacing the spaces of the first line with non-breaking spaces.
(default: false)

=item --short_line_length I<n> | --shortline I<n> | -s I<n>

Lines this short (or shorter) must be intentionally broken and are kept
that short.
(default: 40)

=item --style_url I<stylesheet_url>

This gives the URL of a stylesheet; a LINK tag will be added to the
output.

=item --tab_width I<n> | --tabwidth I<n> | -tw I<n>

How many spaces equal a tab?
(default: 8)

=item --table_type I<type>=0/1
    
    --table_type ALIGN=1 --table_type BORDER=0

This determines which types of tables will be recognised when "make_tables"
is true.  The possible types are ALIGN, PGSQL, BORDER and DELIM.
(default: all types are true)

=item --title I<title> | -t I<title>

You can specify a title.  Otherwise it will use a blank one.
(default: nothing)

=item --titlefirst | -tf

Use the first non-blank line as the title.

=item --underline_delimiter I<string>

This defines what character (or string) is taken to be the delimiter of
text which is to be interpreted as underlined (that is, to be given a <U>
tag).  If this is empty, then no underlining of text will be done.
This is NOT the same as the following "underline" options, which are
about underlining of "header" sections.
(default: _)

=item --underline_length_tolerance I<n> | --ulength I<n> | -ul I<n>

How much longer or shorter can header underlines be and still be header
underlines?
(default: 1)

=item --underline_offset_tolerance I<n> | --uoffset I<n> | -uo I<n>

How far offset can header underlines be and still be header underlines?
(default: 1)

=item --unhyphenation | --unhypnenate | -u

Enables unhyphenation of text.
(default: true)

=item --use_mosaic_header | --mosaic | -mh

Use this option if you want to force the heading styles to match what Mosaic
outputs.  (Underlined with "***"s is H1,
with "==="s is H2, with "+++" is H3, with "---" is H4, with "~~~" is H5
and with "..." is H6)
This was the behavior of txt2html up to version 1.10.
(default: false)

=item --use_preformat_marker | --preformat_marker | -pm

Turn on preformatting when encountering "<PRE>" on a line by itself, and turn
it off when there's a line containing only "</PRE>".
When such preformatted text is detected, the PRE tag will be given the
class 'quote_explicit'.
(default: off)

=item --xhtml

Try to make the output conform to the XHTML standard, including
closing all open tags and marking empty tags correctly.  This
turns on --lower_case_tags and overrides the --doctype option.
Note that if you add a header or a footer file, it is up to you
to make it conform; the header/footer isn't touched by this.
Likewise, if you make link-dictionary entries that break XHTML,
then this won't fix them, except to the degree of putting all tags
into lower-case.

(default: true)

=back

=head1 FILE FORMATS

=head2 Options Files

Options can be given in files as well as on the command-line by
flagging an option file with @I<filename> in the command-line.
Also, the files ~/.txt2htmlrc and ./.txt2htmlrc are checked for options.

The format is as follows:
Lines starting with # are comments.  Lines enclosed in PoD markers are
also comments.  Blank lines are ignored.  The options themselves
should be given the way they would be on the command line, that is,
the option name (I<including> the --) followed by its value (if any).

For example:

    # set link dictionaries
    --default_link_dict /home/kat/.TextToHTML.dict

    # set options for poetry
    --titlefirst
    --short_line_length 60

See L<Getopt::ArgvFile> for more information.

=head2 Link Dictionary

A link dictionary file contains patterns to match, and what to convert
them to.  It is called a "link" dictionary because it was intended to be
something which defined what a href link was, but it can be used for
more than that.  However, if you wish to define your own links, it is
strongly advised to read up on regular expressions (regexes) because
this relies heavily on them.

The file consists of comments (which are lines starting with #)
and blank lines, and link entries.
Each entry consists of a regular expression, a -> separator (with
optional flags), and a link "result".

In the simplest case, with no flags, the regular expression
defines the pattern to look for, and the result says what part
of the regular expression is the actual link, and the link which
is generated has the href as the link, and the whole matched pattern
as the visible part of the link.  The first character of the regular
expression is taken to be the separator for the regex, so one
could either use the traditional / separator, or something else
such as | (which can be helpful with URLs which are full of / characters).

So, for example, an ftp URL might be defined as:

    |ftp:[\w/\.:+\-]+|      -> $&

This takes the whole pattern as the href, and the resultant link
has the same thing in the href as in the contents of the anchor.

But sometimes the href isn't the whole pattern.

    /<URL:\s*(\S+?)\s*>/ --> $1

With the above regex, a () grouping marks the first subexpression,
which is represented as $1 (rather than $& the whole expression).
This entry matches a URL which was marked explicitly as a URL
with the pattern <URL:foo>  (note the < is shown as the
entity, not the actual character.  This is because by the
time the links dictionary is checked, all such things have
already been converted to their HTML entity forms)
This would give us a link in the form
<A HREF="foo"><URL:foo></A>

B<The h flag>

However, if we want more control over the way the link is constructed,
we can construct it ourself.  If one gives the h flag, then the
"result" part of the entry is taken not to contain the href part of
the link, but the whole link.

For example, the entry:

    /<URL:\s*(\S+?)\s*>/ -h-> <A HREF="$1">$1</A>

will take <URL:foo> and give us <A HREF="foo">foo</A>

However, this is a very powerful mechanism, because it
can be used to construct custom tags which aren't links at all.
For example, to flag *italicised words* the following
entry will surround the words with EM tags.

    /\B\*([a-z][a-z -]*[a-z])\*\B/ -hi-> <EM>$1</EM>

B<The i flag>

This turns on ignore case in the pattern matching.

B<The e flag>

This turns on execute in the pattern substitution.  This really
only makes sense if h is turned on too.  In that case, the "result"
part of the entry is taken as perl code to be executed, and the
result of that code is what replaces the pattern.

B<The o flag>

This marks the entry as a once-only link.  This will convert the
first instance of a matching pattern, and ignore any others
further on.

For example, the following pattern will take the first mention
of HTML::TextToHTML and convert it to a link to the module's home page.

    "HTML::TextToHTML"  -io-> http://www.example.com/tools/text_to_html/

=head2 Input File Format

For the most part, this module tries to use intuitive conventions for
determining the structure of the text input.  Unordered lists are
marked by bullets; ordered lists are marked by numbers or letters;
in either case, an increase in indentation marks a sub-list contained
in the outer list.

Headers (apart from custom headers) are distinguished by "underlines"
underneath them; headers in all-capitals are distinguished from
those in mixed case.  All headers, both normal and custom headers,
are expected to start at the first line in a "paragraph".

Tables require a more rigid convention.  A table must be marked as a
separate paragraph, that is, it must be surrounded by blank lines.
Tables come in different types.  For a table to be parsed, its
--table_type option must be on, and the --make_tables option must be true.

B<ALIGN Table Type>

Columns must be separated by two or more spaces (this prevents
accidental incorrect recognition of a paragraph where interword spaces
happen to line up).  If there are two or more rows in a paragraph and
all rows share the same set of (two or more) columns, the paragraph is
assumed to be a table.  For example

    -e  File exists.
    -z  File has zero size.
    -s  File has nonzero size (returns size).

becomes

    <table>
    <tr><td>-e</td><td>File exists.</td></tr>
    <tr><td>-z</td><td>File has zero size.</td></tr>
    <tr><td>-s</td><td>File has nonzero size (returns size).</td></tr>
    </table>

This guesses for each column whether it is intended to be left,
centre or right aligned.

B<BORDER Table Type>

This table type has nice borders around it, and will be rendered
with a border, like so:

    +---------+---------+
    | Column1 | Column2 |
    +---------+---------+
    | val1    | val2    |
    | val3    | val3    |
    +---------+---------+

The above becomes

    <table border="1">
    <thead><tr><th>Column1</th><th>Column2</th></tr></thead>
    <tbody>
    <tr><td>val1</td><td>val2</td></tr>
    <tr><td>val3</td><td>val3</td></tr>
    </tbody>
    </table>

It can also have an optional caption at the start.

         My Caption
    +---------+---------+
    | Column1 | Column2 |
    +---------+---------+
    | val1    | val2    |
    | val3    | val3    |
    +---------+---------+

B<PGSQL Table Type>

This format of table is what one gets from the output of a Postgresql
query.

     Column1 | Column2
    ---------+---------
     val1    | val2
     val3    | val3
    (2 rows)

This can also have an optional caption at the start.
This table is also rendered with a border and table-headers like
the BORDER type.

B<DELIM Table Type>

This table type is delimited by non-alphanumeric characters, and has to
have at least two rows and two columns before it's recognised as a table.

This one is delimited by the '| character:

    | val1  | val2  |
    | val3  | val3  |

But one can use almost any suitable character such as : # $ % + and so on.
This is clever enough to figure out what you are using as the delimiter
if you have your data set up like a table.  Note that the line has to
both begin and end with the delimiter, as well as using it to separate
values.

This can also have an optional caption at the start.

=head1 EXAMPLES

B<Convert one file to HTML>

    txt2html --infile thing.txt --outfile thing.html

This will create a HTML file called C<thing.html> from the plain
text file C<thing.txt>.

=head1 BUGS

Tell me about them.

=head1 PREREQUISITES

    Pod::Usage
    HTML::TextToHTML
    Getopt::Long
    Getopt::ArgvFile
    File::Basename
    YAML::Syck
    perldoc

=head1 SCRIPT CATEGORIES

Web

=head1 ENVIRONMENT

=over

=item HOME

txt2html looks in the HOME directory for config files.

=back

=head1 FILES

These files are only read if the Getopt::ArgvFile module is
available on the system.

=over

=item C<~/.txt2htmlrc>

User configuration file.

=item C<.txt2htmlrc>

Configuration file in the current working directory; overrides
options in C<~/.txt2htmlrc> and is overridden by command-line options.

=back

=head1 SEE ALSO

perl(1)
htmltoc(1)
HTML::TextToHTML
Getopt::Long
Getopt::ArgvFile

=head1 AUTHOR

    Kathryn Andersen (RUBYKAT)
    perlkat AT katspace dot com
    http//www.katspace.com/

based on txt2html by Seth Golub

Current homepage is https://github.com/resurrecting-open-source-projects/txt2html

=head1 COPYRIGHT

Original txt2html script Copyright (c) 1994-2000 Seth Golub seth AT aigeek.com

Copyright (c) 2002-2005 Kathryn Andersen

Copyright (c) 2018-2019 Joao Eriberto Mota Filho

This program is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.

=cut

#################################################################
# Includes
use Pod::Usage;
use Getopt::Long;
use File::Basename;
use HTML::TextToHTML;

#################################################################
# Subroutines

sub init_data ($) {
    my $data_ref = shift;

    my %args = ();
    $args{manpage} = 0;
    $args{debug} = 0;
    $args{version} = 0;
    $args{quiet} = 0;
    $args{help} = 0;
    $args{infile} = [];
    $args{instring} = [];

    $data_ref->{args} = \%args;
}

sub process_args ($) {
    my $data_ref = shift;
    my $args_ref = $data_ref->{args};

    my $ok = 1;

    # check the rc file if we can
    if (eval("require Getopt::ArgvFile")) {
	no strict;
	my $bn = basename($0, '');
	my $rc_name = ".${bn}rc";
	Getopt::ArgvFile::argvFile(
	    startupFilename=>$rc_name,
	    home=>1,
	    current=>1);
    }
    $ok = GetOptions($args_ref,
	'help',
	'manpage|man_help',
	'debug',
	'version',
	'verbose!',
	'append_file|append_body|ab=s',
	'append_head|ah=s',
	'body_deco=s',
	'bold_delimiter=s',
	'bullets=s',
	'bullets_ordered=s',
	'caps_tag|capstag|ct=s',
	'custom_heading_regexp|heading|H=s@',
	'default_link_dict|dict=s',
	'demoronize!',
	'dict_debug|db=n',
	'doctype|dt=s',
	'eight_bit_clean|8!',
	'escape_HTML_chars|escapechars|ec!',
	'explicit_headings|EH!',
	'extract!',
	'hrule_min|r=n',
	'indent_width|iw=n',
	'indent_par_break|ipb!',
	'infile=s@',
	'instring=s@',
	'italic_delimiter=s',
	'links_dictionaries|link|l=s@',
	'link_only|linkonly|LO!',
	'lower_case_tags|lc_tags|LC!',
	'mailmode|m!',
	'make_anchors|anchors!',
	'make_links!',
	'make_tables|tables!',
	'min_caps_length|caps|c=n',
	'outfile|out|o=s',
	'par_indent=n',
	'preformat_trigger_lines|prebegin|pb=n',
	'endpreformat_trigger_lines|preend|pe=n',
	'preformat_start_marker=s',
	'preformat_end_marker=s',
	'preformat_whitespace_min|prewhite|p=n',
	'prepend_file|prepend_body|pp=s',
	'preserve_indent|pi!',
	'short_line_length|shortline|s=n',
	'style_url=s',
	'tab_width|tabwidth|tw=n',
	'table_type=n%',
	'title|t=s',
	'titlefirst|tf!',
	'underline_delimiter=s',
	'underline_length_tolerance|ulength|ul=n',
	'underline_offset_tolerance|uoffset|uo=n',
	'unhyphenation|unhyphenate!',
	'utf8',
	'use_mosaic_header|mosaic|mh!',
	'use_preformat_marker|preformat_marker|pm!',
	'xhtml!',
    );
    if (!$ok)
    {
	pod2usage({ -message => "$0",
		    -exitval => 1,
		    -verbose => 0,
	    });
    }

    if ($args_ref->{'version'})
    {
	print STDERR "$0 version: $HTML::TextToHTML::VERSION\n";
	exit 0;
    }
    if ($args_ref->{'manpage'})
    {
	pod2usage({ -message => "$0 version $HTML::TextToHTML::VERSION",
		    -exitval => 0,
		    -verbose => 2,
	    });
    }
    if ($args_ref->{'help'})
    {
	pod2usage({ -message => "$0 version $HTML::TextToHTML::VERSION",
		    -exitval => 0,
		    -verbose => 1,
	    });
    }
    # transfer script-only things to the data-ref
    undef $args_ref->{help};
    undef $args_ref->{manpage};
    undef $args_ref->{version};
    # make the object
    my $doc = HTML::TextToHTML->new(%{$args_ref});
    $data_ref->{doc} = $doc;
}

#################################################################
# Main

MAIN: {
    my %data = ();
    my $result = 0;
    init_data(\%data);
    process_args(\%data);

    # now the remainder must be input-files
    # Push the infiles onto the infile array,
    # because there might already have been infiles added with --infile.
    foreach my $df (@ARGV)
    {
	if ($data{doc}->{debug}) {
	    print STDERR "--infile $df\n";
	}
	push @{$data{doc}->{infile}}, $df;
    }
    # if we have no infile, and no instring
    # assume stdin, and mark that with '-'
    if (!@{$data{doc}->{infile}} and !@{$data{doc}->{instring}})
    {
	if ($data{doc}->{debug}) {
	    print STDERR "using STDIN\n";
	}
	push @{$data{doc}->{infile}}, '-';
    }

    $data{doc}->txt2html();
}

# vim: sw=4 sts=4 ai
��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/������������������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0013502�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/00-compile.t������������������������������������������������������������������������0000664�0000000�0000000�00000003126�13521162376�0015536�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

use strict;
use warnings;

use Test::More;



use File::Find;
use File::Temp qw{ tempdir };

my @modules;
find(
  sub {
    return if $File::Find::name !~ /\.pm\z/;
    my $found = $File::Find::name;
    $found =~ s{^lib/}{};
    $found =~ s{[/\\]}{::}g;
    $found =~ s/\.pm$//;
    # nothing to skip
    push @modules, $found;
  },
  'lib',
);

sub _find_scripts {
    my $dir = shift @_;

    my @found_scripts = ();
    find(
      sub {
        return unless -f;
        my $found = $File::Find::name;
        # nothing to skip
        open my $FH, '<', $_ or do {
          note( "Unable to open $found in ( $! ), skipping" );
          return;
        };
        my $shebang = <$FH>;
        return unless $shebang =~ /^#!.*?\bperl\b\s*$/;
        push @found_scripts, $found;
      },
      $dir,
    );

    return @found_scripts;
}

my @scripts;
do { push @scripts, _find_scripts($_) if -d $_ }
    for qw{ bin script scripts };

my $plan = scalar(@modules) + scalar(@scripts);
$plan ? (plan tests => $plan) : (plan skip_all => "no tests to run");

{
    # fake home for cpan-testers
    # no fake requested ## local $ENV{HOME} = tempdir( CLEANUP => 1 );

    like( qx{ $^X -Ilib -e "require $_; print '$_ ok'" }, qr/^\s*$_ ok/s, "$_ loaded ok" )
        for sort @modules;

    SKIP: {
        eval "use Test::Script 1.05; 1;";
        skip "Test::Script needed to test script compilation", scalar(@scripts) if $@;
        foreach my $file ( @scripts ) {
            my $script = $file;
            $script =~ s!.*/!!;
            script_compiles( $file, "$script script compiles" );
        }
    }

}
������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/10para.t����������������������������������������������������������������������������0000664�0000000�0000000�00000010044�13521162376�0014752�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#########################

use Test::More tests => 18;
use HTML::TextToHTML;
ok(1); # If we made it this far, we are ok.

# Insert your test code below, the Test module is use()ed here so read
# its man page ( perldoc Test ) for help writing this test script.

my $conv = new HTML::TextToHTML();
ok( defined $conv, 'new() returned something' );
ok( $conv->isa('HTML::TextToHTML'), "  and it's the right class" );

$conv->args(
	system_link_dict=>'txt2html.dict',
	default_link_dict=>'',
	);

#
# test the process_para method alone
#
$test_str = "Matty had a little truck
he drove it round and round
and everywhere that Matty went
the truck was *always* found.
";

$ok_str = "<p>Matty had a little truck<br/>
he drove it round and round<br/>
and everywhere that Matty went<br/>
the truck was <em>always</em> found.
</p>";

$out_str = $conv->process_para($test_str);
ok($out_str, 'converted sample string');

# compare the result
is($out_str, $ok_str, 'compare converted string with OK string');

#
# test the process_chunk method with an ordered list
#
$test_str = "Here is my list:

1. Spam
2. Jam
3. Ham
4. Pickles
";

$ok_str = "<p>Here is my list:
</p><ol>
  <li>Spam
  </li><li>Jam
  </li><li>Ham
  </li><li>Pickles</li></ol>
";

$out_str = $conv->process_chunk($test_str);
ok($out_str, 'converted sample string with list');

# compare the result
is($out_str, $ok_str, 'compare converted list string with OK list string');

#
# test the process_chunk method with an empty string
#
$test_str = "";

$ok_str = "";

$out_str = $conv->process_chunk($test_str);
# note we do not do an ok on this because it should be empty

# compare the result
is($out_str, $ok_str, 'compare converted empty string with OK empty string');

#
# test with is_fragment
#
$test_str = "Matty had a little truck
he drove it round and round
and everywhere that Matty went
the truck was *always* found.
";

$ok_str = "Matty had a little truck<br/>
he drove it round and round<br/>
and everywhere that Matty went<br/>
the truck was <em>always</em> found.
";

$out_str = $conv->process_chunk($test_str, is_fragment=>1);
ok($out_str, 'converted sample string');

# compare the result
is($out_str, $ok_str, 'compare converted string with OK string');

#
# test the process_para method with a URL
#
$test_str = "I like to look at http://www.example.com a lot";

$ok_str = 'I like to look at <a href="http://www.example.com">http://www.example.com</a> a lot';

$out_str = $conv->process_para($test_str, is_fragment=>1);
ok($out_str, 'converted sample string with URL');

# compare the result
is($out_str, $ok_str, 'compare converted URL string with OK URL string');

#
# test process_chunk with caps_tag turned off
#
$test_str = "We have a line alone
FULL OF CAPS AND FURY
";

$ok_str = "We have a line alone<br/>
FULL OF CAPS AND FURY
";

$conv->args(caps_tag=>'');
$out_str = $conv->process_chunk($test_str, is_fragment=>1);
ok($out_str, 'converted sample string with CAPS');

# compare the result
is($out_str, $ok_str, 'compare converted CAPS string with OK CAPS string');

$conv->args(caps_tag=>'STRONG'); # restore caps to default

#
# Test with different italic/bold delimiters
#
$test_str = "I am ^bold^,
You are --really krazy--.
-----------------
";

$ok_str = "I am <strong>bold</strong>,<br/>
You are <em>really krazy</em>.
<hr/>
";

$conv->args(bold_delimiter=>'^',
	italic_delimiter=>'--');
$out_str = $conv->process_chunk($test_str, is_fragment=>1);
ok($out_str, 'converted sample string with delimiters');

# compare the result
is($out_str, $ok_str, 'compare converted delimiter string with OK delimiter string');

# 
# test with no bolding or italic at all
$test_str = "I am ^bold^,
You are --really krazy--.
-----------------
";

$ok_str = "I am ^bold^,<br/>
You are --really krazy--.
<hr/>
";

$conv->args(bold_delimiter=>'',
	italic_delimiter=>'');
$out_str = $conv->process_chunk($test_str, is_fragment=>1);
ok($out_str, 'converted sample string with no bold');

# compare the result
is($out_str, $ok_str, 'compare converted no-bold string with OK no-bold string');

# restore default
$conv->args(bold_delimiter=>'#',
	italic_delimiter=>'*');
��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/20tfiles.t��������������������������������������������������������������������������0000664�0000000�0000000�00000032167�13521162376�0015330�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������# miscelaneous tests in separate files

#########################

use Test::More tests => 50;
use HTML::TextToHTML;

#########################

# compare two files
sub compare {
    my $file1 = shift;
    my $file2 = shift;

    if (!open(F1, $file1))
    {
    	print "error - $file1 did not open\n";
	return 0;
    }
    if (!open(F2, $file2))
    {
    	print "error - $file2 did not open\n";
	return 0;
    }

    my $res = 1;
    my $count = 0;
    while (<F1>)
    {
	$count++;
	my $comp1 = $_;
	# remove newline/carriage return (in case these aren't both Unix)
	$comp1 =~ s/\n//;
	$comp1 =~ s/\r//;

	my $comp2 = <F2>;

	# check if F2 has less lines than F1
	if (!defined $comp2)
	{
	    print "error - line $count does not exist in $file2\n  $file1 : $comp1\n";
	    close(F1);
	    close(F2);
	    return 0;
	}

	# remove newline/carriage return
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	if ($comp1 ne $comp2)
	{
	    print "error - line $count not equal\n  $file1 : $comp1\n  $file2 : $comp2\n";
	    close(F1);
	    close(F2);
	    return 0;
	}
    }
    close(F1);

    # check if F2 has more lines than F1
    if (defined($comp2 = <F2>))
    {
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	print "error - extra line in $file2 : '$comp2'\n";
	$res = 0;
    }

    close(F2);

    return $res;
}

#-----------------------------------------------------------------

my $conv = new HTML::TextToHTML();

#
# Custom headers 1
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/custom-headers.txt"],
outfile=>"custom-headers.html",
custom_heading_regexp=>['^\d+\. +\w+', '^\d+\.\d+\. +\w+', '^\d+\.\d+\.\d+\. +\w+'],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted custom-headers.txt');

# compare the files
$result = compare('tfiles/good_custom-headers.html', 'custom-headers.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('custom-headers.html');
}

#
# Custom headers 2
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/custom-headers2.txt"],
outfile=>"custom-headers2.html",
custom_heading_regexp=>['^What: '],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted custom-headers2.txt');

# compare the files
$result = compare('tfiles/good_custom-headers2.html', 'custom-headers2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('custom-headers2.html');
}

#
# hyphens
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/hyphens.txt"],
outfile=>"hyphens.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted hyphens.txt');

# compare the files
$result = compare('tfiles/good_hyphens.html', 'hyphens.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('hyphens.html');
}

#
# links
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/links.txt"],
outfile=>"links.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted links.txt');

# compare the files
$result = compare('tfiles/good_links.html', 'links.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('links.html');
}

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/links2.txt"],
outfile=>"links2.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted links2.txt');

# compare the files
$result = compare('tfiles/good_links2.html', 'links2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('links2.html');
}

#
# Lists
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/list.txt"],
outfile=>"list.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list.txt');

# compare the files
$result = compare('tfiles/good_list.html', 'list.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list.html');
}

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>["tfiles/list-2.txt"],
outfile=>"list-2.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-2.txt');

# compare the files
$result = compare('tfiles/good_list-2.html', 'list-2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-2.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
xhtml=>1,
infile=>["tfiles/list-3.txt"],
outfile=>"list-3.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-3.txt');

# compare the files
$result = compare('tfiles/good_list-3.html', 'list-3.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-3.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>1,
infile=>["tfiles/list-4.txt"],
outfile=>"list-4.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-4.txt');

# compare the files
$result = compare('tfiles/good_list-4.html', 'list-4.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-4.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>1,
infile=>["tfiles/list-5.txt"],
outfile=>"list-5.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-5.txt');

# compare the files
$result = compare('tfiles/good_list-5.html', 'list-5.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-5.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
bullets=>'-=o+*',
bullets_ordered=>'#',
extract=>0,
xhtml=>1,
infile=>["tfiles/list-custom.txt"],
outfile=>"list-custom.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-custom.txt');

# compare the files
$result = compare('tfiles/good_list-custom.html', 'list-custom.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-custom.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>1,
infile=>["tfiles/list-advanced.txt"],
outfile=>"list-advanced.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-advanced.txt');

# compare the files
$result = compare('tfiles/good_list-advanced.html', 'list-advanced.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-advanced.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>1,
infile=>["tfiles/list-styles.txt"],
outfile=>"list-styles.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted list-styles.txt');

# compare the files
$result = compare('tfiles/good_list-styles.html', 'list-styles.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('list-styles.html');
}

#
# news
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
mailmode=>1,
infile=>["tfiles/news.txt"],
outfile=>"news.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted news.txt');

# compare the files
$result = compare('tfiles/good_news.html', 'news.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('news.html');
}

#
# pre
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
use_preformat_marker=>1,
infile=>["tfiles/pre.txt"],
outfile=>"pre.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted pre.txt');

# compare the files
$result = compare('tfiles/good_pre.html', 'pre.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('pre.html');
}

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
use_preformat_marker=>0,
infile=>["tfiles/pre2.txt"],
outfile=>"pre2.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted pre2.txt');

# compare the files
$result = compare('tfiles/good_pre2.html', 'pre2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('pre2.html');
}

#
# Tables
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
make_tables=>1,
infile=>["tfiles/table-align.txt"],
outfile=>"table-align.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted table-align.txt');

# compare the files
$result = compare('tfiles/good_table-align.html', 'table-align.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('table-align.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
make_tables=>1,
infile=>["tfiles/table-pgsql.txt"],
outfile=>"table-pgsql.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted table-pgsql.txt');

# compare the files
$result = compare('tfiles/good_table-pgsql.html', 'table-pgsql.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('table-pgsql.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
make_tables=>1,
xhtml=>1,
infile=>["tfiles/table-pgsql2.txt"],
outfile=>"table-pgsql2.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted table-pgsql2.txt');

# compare the files
$result = compare('tfiles/good_table-pgsql2.html', 'table-pgsql2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('table-pgsql2.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
make_tables=>1,
infile=>["tfiles/table-border.txt"],
outfile=>"table-border.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted table-border.txt');

# compare the files
$result = compare('tfiles/good_table-border.html', 'table-border.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('table-border.html');
}

$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
make_tables=>1,
xhtml=>1,
infile=>["tfiles/table-delim.txt"],
outfile=>"table-delim.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted table-delim.txt');

# compare the files
$result = compare('tfiles/good_table-delim.html', 'table-delim.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('table-delim.html');
}

#
# an EMPTY file (non-extracted)
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>0,
infile=>["tfiles/empty.txt"],
outfile=>"empty1.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted empty.txt (default)');

# compare the files
$result = compare('tfiles/good_empty.html', 'empty1.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('empty1.html');
}

#
# an EMPTY file (non-extracted) (xhtml)
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>0,
xhtml=>1,
infile=>["tfiles/empty.txt"],
outfile=>"empty2.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted empty.txt (xhtml)');

# compare the files
$result = compare('tfiles/good_empty.html', 'empty2.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('empty2.html');
}

#
# an EMPTY file (extracted)
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
xhtml=>0,
infile=>["tfiles/empty.txt"],
outfile=>"empty3.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted empty.txt (extract)');

# compare the files
$result = compare('tfiles/good_empty.html', 'empty3.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('empty3.html');
}

#
# an EMPTY file (extracted) (xhtml)
#
$conv = undef;
$conv = new HTML::TextToHTML();

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
xhtml=>1,
infile=>["tfiles/empty.txt"],
outfile=>"empty4.html",
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted empty.txt (extract) (xhtml)');

# compare the files
$result = compare('tfiles/good_empty.html', 'empty4.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('empty4.html');
}

���������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/25handles.t�������������������������������������������������������������������������0000664�0000000�0000000�00000006124�13521162376�0015457�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������# miscelaneous tests for filehandles

#########################

use Test::More tests => 6;
use HTML::TextToHTML;

#########################

# compare two files
sub compare {
    my $file1 = shift;
    my $file2 = shift;

    if (!open(F1, $file1))
    {
    	print "error - $file1 did not open\n";
	return 0;
    }
    if (!open(F2, $file2))
    {
    	print "error - $file2 did not open\n";
	return 0;
    }

    my $res = 1;
    my $count = 0;
    while (<F1>)
    {
	$count++;
	my $comp1 = $_;
	# remove newline/carriage return (in case these aren't both Unix)
	$comp1 =~ s/\n//;
	$comp1 =~ s/\r//;

	my $comp2 = <F2>;

	# check if F2 has less lines than F1
	if (!defined $comp2)
	{
	    print "error - line $count does not exist in $file2\n  $file1 : $comp1\n";
	    close(F1);
	    close(F2);
	    return 0;
	}

	# remove newline/carriage return
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	if ($comp1 ne $comp2)
	{
	    print "error - line $count not equal\n  $file1 : $comp1\n  $file2 : $comp2\n";
	    close(F1);
	    close(F2);
	    return 0;
	}
    }
    close(F1);

    # check if F2 has more lines than F1
    if (defined($comp2 = <F2>))
    {
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	print "error - extra line in $file2 : '$comp2'\n";
	$res = 0;
    }

    close(F2);

    return $res;
}

#-----------------------------------------------------------------

my $conv = new HTML::TextToHTML();

#
# FILEHANDLE
#

open (IN, "tfiles/hyphens.txt")
or die "could not open tfiles/hyphens.txt";

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
inhandle=>[\*IN],
outfile=>"fh_hyphens.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted (FH) hyphens.txt');

# compare the files
$result = compare('tfiles/good_hyphens.html', 'fh_hyphens.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('fh_hyphens.html');
}

#
# filehandle variable
#
$conv = undef;
$conv = new HTML::TextToHTML();

my $fh;
open ($fh, "tfiles/hyphens.txt")
or die "could not open tfiles/hyphens.txt";

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
inhandle=>[$fh],
outfile=>"fh2_hyphens.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted (FH 2) hyphens.txt');

# compare the files
$result = compare('tfiles/good_hyphens.html', 'fh2_hyphens.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('fh2_hyphens.html');
}

#
# Output filehandle
#
$conv = undef;
$conv = new HTML::TextToHTML();

my $ofh;
open ($ofh, ">", "fh3_hyphens.html")
or die "could not open fh3_hyphens.html for writing";

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
extract=>1,
infile=>['tfiles/hyphens.txt'],
outhandle=>$ofh,
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted (FH 3) hyphens.txt');

# compare the files
$result = compare('tfiles/good_hyphens.html', 'fh3_hyphens.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('fh3_hyphens.html');
}

��������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/30sample.t��������������������������������������������������������������������������0000664�0000000�0000000�00000004174�13521162376�0015321�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������# Before `make install' is performed this script should be runnable with
# `make test'. After `make install' it should work as `perl test.pl'

#########################

# change 'tests => 1' to 'tests => last_test_to_print';

use Test::More tests => 5;
use HTML::TextToHTML;
ok(1); # If we made it this far, we're ok.

#########################

# compare two files
sub compare {
    my $file1 = shift;
    my $file2 = shift;

    open(F1, $file1) || return 0;
    open(F2, $file2) || return 0;

    my $res = 1;
    my $count = 0;
    while (<F1>)
    {
	$count++;
	my $comp1 = $_;
	# remove newline/carriage return (in case these aren't both Unix)
	$comp1 =~ s/\n//;
	$comp1 =~ s/\r//;

	my $comp2 = <F2>;

	# check if F2 has less lines than F1
	if (!defined $comp2)
	{
	    print "error - line $count does not exist in $file2\n  $file1 : $comp1\n";
	    close(F1);
	    close(F2);
	    return 0;
	}

	# remove newline/carriage return
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	if ($comp1 ne $comp2)
	{
	    print "error - line $count not equal\n  $file1 : $comp1\n  $file2 : $comp2\n";
	    close(F1);
	    close(F2);
	    return 0;
	}
    }
    close(F1);

    # check if F2 has more lines than F1
    if (defined($comp2 = <F2>))
    {
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	print "error - extra line in $file2 : '$comp2'\n";
	$res = 0;
    }

    close(F2);

    return $res;
}

# Insert your test code below, the Test module is use()ed here so read
# its man page ( perldoc Test ) for help writing this test script.

my $conv = new HTML::TextToHTML(xhtml=>0);
ok( defined $conv, 'new() returned something' );
ok( $conv->isa('HTML::TextToHTML'), "  and it's the right class" );

$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
infile=>["tfiles/sample.txt"],
outfile=>"sample.html",
append_file=>"tfiles/sample.foot",
titlefirst=>1, mailmode=>1,
custom_heading_regexp=>['^ *--[\w\s]+-- *$'],
make_tables=>1,
);
ok($result, 'converted sample.txt');

# compare the files
$result = compare('tfiles/good_sample.html', 'sample.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('sample.html');
}

����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/50xsample.t�������������������������������������������������������������������������0000664�0000000�0000000�00000004474�13521162376�0015516�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������# Before `make install' is performed this script should be runnable with
# `make test'. After `make install' it should work as `perl test.pl'

#########################

# change 'tests => 1' to 'tests => last_test_to_print';

use Test::More tests => 5;
use HTML::TextToHTML;
ok(1); # If we made it this far, we're ok.

#########################

# compare two files
sub compare {
    my $file1 = shift;
    my $file2 = shift;

    open(F1, $file1) || return 0;
    open(F2, $file2) || return 0;

    my $res = 1;
    my $count = 0;
    while (<F1>)
    {
	$count++;
	my $comp1 = $_;
	# remove newline/carriage return (in case these aren't both Unix)
	$comp1 =~ s/\n//;
	$comp1 =~ s/\r//;

	my $comp2 = <F2>;

	# check if F2 has less lines than F1
	if (!defined $comp2)
	{
	    print "error - line $count does not exist in $file2\n  $file1 : $comp1\n";
	    close(F1);
	    close(F2);
	    return 0;
	}

	# remove newline/carriage return
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	if ($comp1 ne $comp2)
	{
	    print "error - line $count not equal\n  $file1 : $comp1\n  $file2 : $comp2\n";
	    close(F1);
	    close(F2);
	    return 0;
	}
    }
    close(F1);

    # check if F2 has more lines than F1
    if (defined($comp2 = <F2>))
    {
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	print "error - extra line in $file2 : '$comp2'\n";
	$res = 0;
    }

    close(F2);

    return $res;
}

# Insert your test code below, the Test module is use()ed here so read
# its man page ( perldoc Test ) for help writing this test script.

my $conv = new HTML::TextToHTML();
ok( defined $conv, 'new() returned something' );
ok( $conv->isa('HTML::TextToHTML'), "  and it's the right class" );

my %args = ();
$args{system_link_dict} = "txt2html.dict";
$args{default_link_dict} = "";
$args{infile} = ["tfiles/sample.txt"];
$args{append_file} = "tfiles/sample.foot2";
$args{titlefirst} = 1;
$args{mailmode} = 1;
$args{custom_heading_regexp} = ['^ *--[\w\s]+-- *$'];
$args{make_tables} = 1;
$args{make_anchors} = 1;
$args{xhtml} = 1; 
$args{outfile} =  "xhtml_sample.html";
$result = $conv->txt2html(%args);
ok($result, 'converted xhtml sample.txt');

# compare the files
$result = compare('tfiles/good_xhtml_sample.html', 'xhtml_sample.html');
ok($result, 'test file xhtml_sample.html matches original good_xhtml_sample.html exactly');

if ($result) {
    unlink('xhtml_sample.html');
}
����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/70bugs.t����������������������������������������������������������������������������0000664�0000000�0000000�00000012442�13521162376�0015001�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������# files which have triggered bugs

#########################

use Test::More tests => 16;
use HTML::TextToHTML;

#########################

# compare two files
sub compare {
    my $file1 = shift;
    my $file2 = shift;

    if (!open(F1, $file1))
    {
    	print "error - $file1 did not open\n";
	return 0;
    }
    if (!open(F2, $file2))
    {
    	print "error - $file2 did not open\n";
	return 0;
    }

    my $res = 1;
    my $count = 0;
    while (<F1>)
    {
	$count++;
	my $comp1 = $_;
	# remove newline/carriage return (in case these are not both Unix)
	$comp1 =~ s/\n//;
	$comp1 =~ s/\r//;

	my $comp2 = <F2>;

	# check if F2 has less lines than F1
	if (!defined $comp2)
	{
	    print "error - line $count does not exist in $file2\n  $file1 : $comp1\n";
	    close(F1);
	    close(F2);
	    return 0;
	}

	# remove newline/carriage return
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	if ($comp1 ne $comp2)
	{
	    print "error - line $count not equal\n  $file1 : $comp1\n  $file2 : $comp2\n";
	    close(F1);
	    close(F2);
	    return 0;
	}
    }
    close(F1);

    # check if F2 has more lines than F1
    if (defined($comp2 = <F2>))
    {
	$comp2 =~ s/\n//;
	$comp2 =~ s/\r//;
	print "error - extra line in $file2 : '$comp2'\n";
	$res = 0;
    }

    close(F2);

    return $res;
}

#-----------------------------------------------------------------

my $conv = new HTML::TextToHTML();

#
# bugs : make_tables
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_tables=>1,
infile=>["tfiles/robo.txt"],
outfile=>"robo.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted robo.txt');

# compare the files
$result = compare('tfiles/good_robo.html', 'robo.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('robo.html');
}

#
# bugs : list with bold chars
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_tables=>0,
infile=>["tfiles/mixed.txt"],
outfile=>"mixed.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted mixed.txt');

# compare the files
$result = compare('tfiles/good_mixed.html', 'mixed.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('mixed.html');
}

#
# bugs : dos file on unix platform not detecting headings
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_tables=>0,
infile=>["tfiles/heading1.txt"],
outfile=>"heading1.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted heading1.txt');

# compare the files
$result = compare('tfiles/good_heading1.html', 'heading1.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('heading1.html');
}

#
# bugs : link with # in it being replaced by <STRONG> tags
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_tables=>0,
infile=>["tfiles/links3.txt"],
outfile=>"links3.html",
custom_heading_regexp=>[],
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted links3.txt');

# compare the files
$result = compare('tfiles/good_links3.html', 'links3.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('links3.html');
}

$conv = new HTML::TextToHTML();
#
# bugs : file with umlauts not doing italics and unterlines correctly
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_tables=>0,
infile=>["tfiles/umlauttest.txt"],
outfile=>"umlauttest.html",
custom_heading_regexp=>[],
xhtml=>1,
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted umlauttest.txt');

# compare the files
$result = compare('tfiles/good_umlauttest.html', 'umlauttest.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('umlauttest.html');
}

#
# bugs : UTF-8 characters are being wrongly zapped
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_anchors=>0,
infile=>["tfiles/utf8.txt"],
outfile=>"utf8.html",
custom_heading_regexp=>[],
xhtml=>1,
extract=>1,
eight_bit_clean=>1,
#debug=>1,
#dict_debug=>15,
);
ok($result, 'converted utf8.txt');

# compare the files
$result = compare('tfiles/good_utf8.html', 'utf8.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('utf8.html');
}

#
# bugs : italics with punctuation characters , and ! not converted
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_anchors=>0,
infile=>["tfiles/punct.txt"],
outfile=>"punct.html",
custom_heading_regexp=>[],
extract=>1,
eight_bit_clean=>1,
);
ok($result, 'converted punct.txt');

# compare the files
$result = compare('tfiles/good_punct.html', 'punct.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('punct.html');
}

#
# bugs : links with underscores
#
$result = $conv->txt2html(
system_link_dict=>"txt2html.dict",
default_link_dict=>"",
make_anchors=>0,
infile=>["tfiles/links4.txt"],
outfile=>"links4.html",
custom_heading_regexp=>[],
extract=>1,
eight_bit_clean=>1,
);
ok($result, 'converted links4.txt');

# compare the files
$result = compare('tfiles/good_links4.html', 'links4.html');
ok($result, 'test file matches original example exactly');
if ($result) {
    unlink('links4.html');
}

������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/release-distmeta.t������������������������������������������������������������������0000664�0000000�0000000�00000000455�13521162376�0017123�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

BEGIN {
  unless ($ENV{RELEASE_TESTING}) {
    require Test::More;
    Test::More::plan(skip_all => 'these tests are for release candidate testing');
  }
}


use Test::More;

eval "use Test::CPAN::Meta";
plan skip_all => "Test::CPAN::Meta required for testing META.yml" if $@;
meta_yaml_ok();
�������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/release-has-version.t���������������������������������������������������������������0000664�0000000�0000000�00000000473�13521162376�0017547�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

BEGIN {
  unless ($ENV{RELEASE_TESTING}) {
    require Test::More;
    Test::More::plan(skip_all => 'these tests are for release candidate testing');
  }
}


use Test::More;

eval "use Test::HasVersion";
plan skip_all => "Test::HasVersion required for testing version numbers"
  if $@;
all_pm_version_ok();
�����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/release-pod-coverage.t��������������������������������������������������������������0000664�0000000�0000000�00000000765�13521162376�0017670�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

BEGIN {
  unless ($ENV{RELEASE_TESTING}) {
    require Test::More;
    Test::More::plan(skip_all => 'these tests are for release candidate testing');
  }
}


use Test::More;

eval "use Test::Pod::Coverage 1.08";
plan skip_all => "Test::Pod::Coverage 1.08 required for testing POD coverage"
  if $@;

eval "use Pod::Coverage::TrustPod";
plan skip_all => "Pod::Coverage::TrustPod required for testing POD coverage"
  if $@;

all_pod_coverage_ok({ coverage_class => 'Pod::Coverage::TrustPod' });
�����������txt2html-2.53/t/release-pod-syntax.t����������������������������������������������������������������0000664�0000000�0000000�00000000450�13521162376�0017412�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

BEGIN {
  unless ($ENV{RELEASE_TESTING}) {
    require Test::More;
    Test::More::plan(skip_all => 'these tests are for release candidate testing');
  }
}

use Test::More;

eval "use Test::Pod 1.41";
plan skip_all => "Test::Pod 1.41 required for testing POD" if $@;

all_pod_files_ok();
������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/t/release-portability.t���������������������������������������������������������������0000664�0000000�0000000�00000000534�13521162376�0017651�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������#!perl

BEGIN {
  unless ($ENV{RELEASE_TESTING}) {
    require Test::More;
    Test::More::plan(skip_all => 'these tests are for release candidate testing');
  }
}


use strict;
use warnings;

use Test::More;

eval 'use Test::Portability::Files';
plan skip_all => 'Test::Portability::Files required for testing portability'
    if $@;
run_tests();
��������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/�������������������������������������������������������������������������������0000775�0000000�0000000�00000000000�13521162376�0014525�5����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/custom-headers.txt�������������������������������������������������������������0000664�0000000�0000000�00000001423�13521162376�0020211�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������1.  INTRODUCTION

1.1.  SCOPE

     This standard specifies a syntax for text messages that  are
sent  among  computer  users, within the framework of "electronic
mail".  The standard supersedes  the  one  specified  in  ARPANET
Request  for Comments #733, "Standard for the Format of ARPA Net-
work Text Messages".

1.2.  COMMUNICATION FRAMEWORK

     Messages consist of lines of text.   No  special  provisions
are  made for encoding drawings, facsimile, speech, or structured
text.  No significant consideration has been given  to  questions
of  data  compression  or to transmission and storage efficiency,
and the standard tends to be free with the number  of  bits  con-
sumed.   For  example,  field  names  are specified as free text,
rather than special terse codes.

2. BLAH

���������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/custom-headers2.txt������������������������������������������������������������0000664�0000000�0000000�00000000064�13521162376�0020273�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������What: A Bargain

What: A Nuisance

What: Am I Doing
����������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/empty.txt����������������������������������������������������������������������0000664�0000000�0000000�00000000000�13521162376�0016412�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/good_custom-headers.html�������������������������������������������������������0000664�0000000�0000000�00000001647�13521162376�0021356�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������<h1><a name="section_1">1.  INTRODUCTION</a></h1>

<h2><a name="section_1_1">1.1.  SCOPE</a></h2>

<p>     This standard specifies a syntax for text messages that  are
sent  among  computer  users, within the framework of "electronic
mail".  The standard supersedes  the  one  specified  in  ARPANET
Request  for Comments #733, "Standard for the Format of ARPA Network 
Text Messages".
</p>
<h2><a name="section_1_2">1.2.  COMMUNICATION FRAMEWORK</a></h2>

<p>     Messages consist of lines of text.   No  special  provisions
are  made for encoding drawings, facsimile, speech, or structured
text.  No significant consideration has been given  to  questions
of  data  compression  or to transmission and storage efficiency,
and the standard tends to be free with the number  of  bits  consumed.   
For  example,  field  names  are specified as free text,
rather than special terse codes.
</p>
<h1><a name="section_2">2. BLAH</a></h1>

�����������������������������������������������������������������������������������������txt2html-2.53/tfiles/good_custom-headers2.html������������������������������������������������������0000664�0000000�0000000�00000000230�13521162376�0021423�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������<h1><a name="section_3">What: A Bargain</a></h1>

<h1><a name="section_4">What: A Nuisance</a></h1>

<h1><a name="section_5">What: Am I Doing</a></h1>

������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/good_empty.html����������������������������������������������������������������0000664�0000000�0000000�00000000000�13521162376�0017547�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������txt2html-2.53/tfiles/good_heading1.html�������������������������������������������������������������0000664�0000000�0000000�00000050172�13521162376�0020110�0����������������������������������������������������������������������������������������������������ustar�00root����������������������������root����������������������������0000000�0000000������������������������������������������������������������������������������������������������������������������������������������������������������������������������<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>




    Doctor Who New Adventures
    

    The Left-Handed Hummingbird by Kate Orman
    

    (an attempt at a spoiler-free review by Kathryn Andersen)

    This novel is right up there with Love & War in the best NA
category, I think.   Why?  Hmmm.  Many of the NA's are "okay".
They have nothing wrong with them.  But to be an outstanding story,
it needs something extra; some character insight or development
which changes the relationship of the major characters, an original
plot/twist/adversary, an excellent turn of phrase - and LHH had
all of these.  Here, the Doctor is put in a position he has
never been in before, hoist on his own petard, a victim of his
own way of doing things, caught in a trap that travels with him.

    (I am reminded of the Blake's 7 quote:
    
"When you know an enemy's strengths, and can use them against them,
they become weaknesses."
    
-- Servalan, to Travis  (Blake's 7: Weapon [B3])
)

    There are some good insights about him and Ace, wondering
if they are more alike than they like to admit...
And finally, those turning phrases, made me want to write again.
It's not often you get some lovely stuff you'd like to quote -
my quotes file has many gems from "Transit", but hardly anything
from the other NA's.  This one doesn't have as many quotable
jewels, but a number of places that made you sit up and take
notice.  My favourite is:
    
"Ashes to nothing.  Dust to nothing.  Live fast, die young, and
leave a beautiful empty space where you used to be." (p220)

    

    This story stood out because, as I said above, this is the first time
that the Doctor has been a victim.  There have been times when
he has been helpless to help others. There have been times when
he has been at the losing end, but he has been in control, able to
play for time.  There has even been the time, with the Timewyrm,
where half the time he hasn't been in control, but he has always
been playing his game, fencing with the enemy.  This time he couldn't
fence at all.  The quote from Nietzsche at the start is doubly
fitting now that I know what happened.  Because that's what happened.
He gazed into the Abyss, and became a monster.  This is a good
follow-on from The Dimension Riders, because the stakes have upped.
In The Dimension Riders, for the first time, the Doctor's clever
plan didn't work, and someone else's clever plan did.  He was
helped by someone else.  And in The Left-Handed Hummingbird,
the Doctor was up against something too big for him to handle;
he hardly had a plan at all (no great plan involves suicide...),
and that didn't work either.
    
The Doctor is so used to being more capable than everyone else
he meets, is he incapable of accepting help from others?  I mean
real help, not directed assistance to fight the enemy.  He got
into this trouble because he went looking for it.

    Sid & Nancy scale: a thunderstorm wrapped in blue

    

    First Frontier
    

    an attempt at a spoiler-free review by Kathryn Andersen

    So, here's the latest NA to pass through my hands.  I'm wondering if
the inverse-cover-rule applies to this one: the cover is great, the book
isn't.  But actually, the book was okay, even if not terrific.  I can
understand why the author said he did it for fun.  Strangely enough, it
picked up in the latter half of the book - or else I merely changed my
mood and decided I wanted to read it.

    The Ace characterisation harked back to the earlier Ace - or perhaps I
was reminded of her because this was, in its own way, a sequel to
"Survival", and that part of it it did well.  I tip my hat to the author
that I did not suspect who Kreer really was until it was revealed, even
though enough clues were left around for someone more astute than I to
figure it out, maybe.  If I were more up with UFO-ology, I might also
tip my hat to the author about his UFO research, but I don't know enough
to know if he did it well.

    Benny doesn't seem to have much to do, and the Doctor doesn't feature as
much as he might - there seems to be an abundance of supporting
characters being suspicious of each other, following orders, or being
victims.

    It was readable, but I'm keeping it for the cover.  8-)

    Sid & Nancy scale: a model kit of a flying saucer

    

    Falls The Shadow
    

    reviewed by Kathryn Andersen

    Well, I finally read this one, months after I got it.

    I can see why someone compared this with "Strange England", though in
one sense, "Strange England" was more vividly horrible.  There was more
horror in those singing insects than there was in the two villains.  Yet
another NA with a surreal landscape.  I wonder if it's a requirement.
No, I don't dislike surreal landscapes, it's just that you start to
get weary of them when they happen a lot.  Which NA's didn't have a
surreal landscape in there somewhere?

    Am I becoming jaded, or are the NAs all running into each other in
ordinariness?

    Okay spoiler warning time.  Discussion time.


    

The cover didn't help.  Hard to think of Gabriel and Tanith as perfect
in beauty when the pictures of them on the cover weren't very beautiful
at all.  Gabriel and Tanith were just violent.  Continuously and
sadistically violent.

    But the most interesting question, and here's for the discussion time:
who is the grey man?  I mean the author seems to be proposing a change
in the metaphysical nature of the Whoniverse, but there are several
things that don't make sense about it.

      
  
    • Grey.  With white as Good and Black as Evil, Grey seems to style
himself as Doubt.  But on the other hand, he seems to style himself as
Chaos.  Now, I agree that Order and Chaos are neither good nor evil
(since things like Nazi dictatorships can be very evil and very
orderly).  But...  aw, I think part of my problem here is that I
disagree with the standing metaphysical order of the Whoniverse with the
Black and White Guardians being equal and opposite, so trying to slot
a Grey Guardian in there is adding to my confusion.  But still, I don't
really understand what he's supposed to stand for.  Doubt?  (and how
would doubt apply to Evil?) Chaos?  (and doesn't Evil want to create
chaos as well as order?) Freedom?  (but doesn't Good want to create
freedom?)  
    • His people.  Who are his people?  Are the Black Guardian and the White
Guardian of his people, or something else?  And if they are, then who
are the rest, or are there only three of them?  Who are they?
    

    I think I had some more questions, but I can't remember what they were.

    Kathryn Andersen
    
(now I can read Set Piece!  Yay!)

    Later, on Thu, 30 Mar 1995...

    Ah, I remember now.  The other query/problem I had with "Falls the Shadow".
And it was the most important one too.

    Whoniversal metaphysics warning

    Falls The Shadow spoiler warning

    Okay, so Gabriel and Tanith were born out of the pain of the universe, a
wounding of the universe, the pain of destroyed potential futures, such as
the one that Jane Page came from.  And the Doctor felt guilty because such
pain was caused by him and other time travellers.  Am I right, or did I
completely miss what was happening?

    Because, if that's the case, however poetically appealing it is, it doesn't
make any sense.  Because time travel isn't the only thing that destroys
potential futures.  If time travel was never invented, millions of
potential futures are destroyed every second, every time someone makes a
decision.  Is the author trying to tell me that the natural order of the
universe (that is, a universe supposing time travel had never been
invented, an untampered-with universe) causes a wounding of the universe?
Where is the logic in that, the design?

    I am assuming that the Darvil-Evans structure of the Whoniverse is the one
that needs to be used: the one which sets the Doctor's Gallifrey way way
back in (to us) the past, which is actually the Present.  And the nature of
time travel is such that it is impossible to travel into the Past, into a
point before the Present (thus nobody goes back in time to have a chat to
Rassillon etc), but it is possible to travel into the future, but the act
of travelling into the future and observing and participating in it, makes
that future certain (or almost certain) to occur.  It crystalizes it, so to
speak. That there is only one universe; parallel universes take a great
deal of energy to create and they are only temporary.  It is not impossible
to change history, but it is difficult, destructive, and a very Bad Thing.

    So, in all this, why is there pain at the wiping out of possible futures?
It's not as if they had a right to exist: there can be only one
history-of-the-universe in the end.  What exists, exists.  What might have
existed does not exist, and should not exist.

    Is it because these potential futures were wiped out "sooner" than they
might have been?  Because the actions/decisions that wiped them out
happened before the Present moment actually arrived there?  But what does
"before" mean in that context?  We're talking about meta-time here,
and that's so hairy I think I'll leave it.

    (sigh)

    Sid & Nancy scale: a Ken Done painting

    

    Set Piece by Kate Orman
    

    Date - June 5th 1995

    reviewed by Kathryn Andersen

    The obvious book to compare "Set Piece" to would be the previous
excursion of Kate Orman into the realms of the New Adventures - "The
Left-Handed Hummingbird" (otherwise known in fannish shorthand as
"Hummer").  Oddly enough, I think "Set Piece" was both better and not as
good as Hummer.  Better, because I can think of not a thing to point to
that was a problem (on the other hand, maybe I just wasn't looking
carefully enough?).  Not as good simply because it wasn't the same kind
of rollercoaster ride that Hummer was, not as much of the sheer
angstiness that was in Hummer.  Not the same psychological torture -
here I was more worried about Ace than the Doctor.  But maybe that's
just that it's a different book.  And it would be only half a point
difference anyway.  I did really like Set Piece.  Action and
characterisation in even amounts, a few surprises, and a few
not-surprises.  8.5 or 9 out of 10.

    This story is really Ace's story, not really surprising since this is
the book in which she is written out of the series.  The Doctor and
Benny have their parts to play, but Ace is the emotional heart of the
tale.  The three time travellers are cast adrift through history when a
rescue attempt goes awry, and the three have to survive in different
eras while something living in a crack in space-time preys on people
from the past, present and future.

    Here, Ace is all alone, in the alien (to her) culture of Ancient Egypt,
with only her own resources to fall back on, surviving and waiting,
waiting, waiting for the Doctor to turn up and tell her the sneaky plan
he had been preparing all this while.  But the last time she saw the
Doctor, "Benny was stooped over the Doctor, frantically trying to get a
response out of him.  Blood was trickling from his mouth and nose,
sluggishly.  His eyes had flicked shut.  Ace wished she could tell Benny
that the Doctor was dead."  Isolated, despairing, Ace is in danger of
losing her soul, of making the worst mistake in her life...

    Again, Kate Orman has sprinkled the work with sharp pieces of prose:
"Suddenly the Doctor did not walk up and say hello." (p50) about Ace's
loneliness.  "When you're short of everything except the enemy, you know
you're in combat." (p138) was another good example.  And touches of
humour here and there.  One might make a complaint, though, that the
Whoniverse is becoming cluttered with metaphysical constructs; previous
New Adventures have dream-encounters with Death and Time - here we meet
Pain, with the Doctor as Time's butterfly.  I guess that depends on how
much one enjoys symbolism.  There are some very good character moments -
for Ace and the Doctor particularly.  Ace faces herself, and the Doctor
wins by losing.

    The plot as a whole comes together piece by piece, jumping about from
time and place (with a flashback and a red herring or two to stop it
from being too straightforward), becoming clearer as it goes along, and
tieing itself together very satisfactorily.  No megalomaniacs, no 'fixed
up in the last five minutes with the wave of a gizmo', and not even a
'I've been subtly planning this behind the scenes for months' which
tends to happen with the 7th Doctor.

    The way in which Ace departs the series had me cheering.  I couldn't
have asked for a better way for her to go.  And I'd better not say any
more about that for fear of letting slip hints about what happens.

    If you are reading the New Adventures at all, there are no excuses for
not reading this one, except perhaps putting it off until you've read
all the previous ones by Paul Cornell, Ben Aaronovich and Kate Orman.

    Sid & Nancy scale: chocolate cake with ice cream

    

    Sky Pirates by Dave Stone
    

    note on rec.arts.drwho on Thu Aug 17 1995 from kat

    I only have two things to say about this NA:
1. I expect that persons will have similar attitudes towards this as they
had about The Highest Science.
    
2. It made me laugh.

    Kathryn Andersen

    (who hasn't read radw for months...)

    Sid & Nancy scale: Mystery Science Theatre 3000

    

    The Room With No Doors by Kate Orman
    

    a rambling rave by Kathryn Andersen

    Whee!  She did it again!  So I couldn't put it down, what's the
surprise in that?

    First warning - ignore the back cover blurb.  It's misleading.  It
tells you too much about the wrong things.

    Okay, what did we get?

    The Zen - that was cool.

    An angst-guilty Chris - of course since I haven't read an NA since...
too long - I don't know what he was referring back to, except that it's
presumably spoiled a previous NA, probably the one just before,
"Eternity Weeps", yes?

    Fanboy-Joel returns!  And drops in a few fannish references, B5
included...  Not to mention references back to "Return of the Living
Dad" and "Sleepy".  Probably other ones that I missed, too.

    And the Doctor... his torture is on the inside, this time.  Sort of.

    Plus assorted "demons", legends, fighting, and codes of honour.  And how
many ways can one pronounce "Chris"?

    And I love it how it all came together.  Practically driving us nuts
with not knowing what this ruddy pod is!  Even though every man and
his dog is fighting over it... typical, neh.  And of course, driving
us nuts wondering what the Room With No Doors is too.  And What Does It
All Mean?  Read the book, and find out.

    Can a house stand, if it is divided among itself?  Can a Doctor stand,
if he is not at peace?  This does a bit of foreshadowing about the 8th
Doctor's genesis, which is cool too.  Hmmm, can you call it
foreshadowing if we all know what it is referring to already?

    This is a happening book - and not a happening book.  The universe is
not at stake, but that just brings it down to a level we can
comprehend.  People.  There's certainly a lot of running around.  And a
lot of thinking, too.

    Oh, look, I don't know how it compares with her others, I just enjoyed
it.  I liked it better than Sleepy, but then that was the one of
Kate's that I liked the least.

    Oh, and now that R.J. Anderson's "Sacrifice" is now officially
quoted in an NA, I'll just have to mention that you'd better go off
and read all of
    
<http://www.pobox.com/~rebeccaj/:R.J. Anderson>'s
11th Doctor stories, too.
    
(Two of which appeared in
    
<http://www.katspace.com/enarrare/e09.html:Enarrare 9>).

    

    So Vile A Sin by Ben Aaronvich and Kate Orman
    

    reviewed by Kathryn Andersen

    They did it again!  Another one of those "Huh, what the hell is going
on?" books, from the now-team of Ben Aaronvich and Kate Orman, where it
does all make sense in the end.  And here, when we thought everything
was fine, we knew it couldn't be, because the book wasn't over yet.
And again, got to a point where one was thinking, "How on earth are they
going to get out of this?" and they did anyway.  Surely it must be hard
to think of yet more universe-threatening threats, and yet they did it.
And very sensibly, they put the body on page one.  Since everybody knew
she was dead already, might as well take advantage of that, and still
manage to leave us in suspense.

    And of course, the in-jokes and past-adventures references - noticed
the Tara reference - sneaky!  And Kate(?) put in more "guns and frocks"
jokes, um, in-jokes. I dunno, I can't see a reference to guns and frocks
in Kate's books any more without smiling.

    But the title still looks like an anagram to me.

    A silver-dusted Rubic's Cube that someone does for you, on the Sid &
Nancy scale.

    

    Lungbarrow by Marc Platt
    

    reviewed by Kathryn Andersen

    Well, I had gotten the impression from comments by other people that I
would find this one confusing, that it would raise more questions than
it answered, but I don't think so.  It answered quite a few questions,
or, strictly speaking, dropped the broadest of hints, hints which
followed up the intriguing hints about the Doctor's past which had
been dropped in COLD FUSION.  Tied up quite a few loose ends, really.
It even explained the return of the sonic screwdriver!  In atmosphere, it
reminded me somewhat of STRANGE ENGLAND, but more, really, of GHOST LIGHT.

    After I read this, I realized something about many of the New Adventures.
Much of the TV Who was dedicated to de-mystifying things.  Gods are just
aliens, faith as a weapon against haemeovores, human culture as a result
of alien interference, and so on.  But the New Adventures are bringing the
Mystery back - and I don't just mean making the Doctor more mysterious,
Leela's comment in LUNGBARROW about the Doctor notwithstanding.  All the
bits about Death and Time and Pain, the "gods" of Gallifrey, are bringing
back the Otherness (and I don't mean the Other!), bringing the Mythic into
Doctor Who.  And I like it.

    Sid & Nancy scale: a giant's house

    

    The Dying Days by Lance Parkin
    

    reviewed by Kathryn Andersen

    Here we are - the first of the New Adventures to feature the 8th
Doctor instead of the seventh; the end of an era, and the beginning of
a new one; ushered in by another on of the NA authors that I admire.

    Whee!  This one was more slow-moving than the others I had read in my
recent Who-thon.  It was also more straightforward.  I was tempted to
complain that there wasn't enough of the Doctor and too much of Benny
(if one could really have too much of a well-written Benny), that I
didn't get to see the 8th Doctor shine in his own unique Doctorish way,
but I was wrong.  It just took a while, that's all.  I kept on looking
at the cover to remind myself of him.  I'm looking forward to the
BBCNA's simply because I want more 8th Doctor.  But don't let me give
you the impression that the Doctor and Benny are the only decent
characters there.  The Brigadier's there as well, and gets in his own
thoughtful moments.  Plus other supporting decent characters;
particularly the little bits with Doug and Oswald.  (grin) I have a
suspicion that there are some in-jokes there that I missed.  Oh well,
didn't stop me from enjoying it.  Particularly the end.

    Sid & Nancy scale: roast beef


    



txt2html-2.53/tfiles/good_hyphens.html000066400000000000000000000001171352116237600201000ustar00rootroot00000000000000
    Blah blah blah blah blah blah.  This paragraph has a hyphenated 
word.

    
txt2html-2.53/tfiles/good_links.html000066400000000000000000000002731352116237600175450ustar00rootroot00000000000000
    This is a test of txt2html.

    

    testing txt2html in a header
    


    nu?

    
txt2html-2.53/tfiles/good_links2.html000066400000000000000000000040001352116237600176170ustar00rootroot00000000000000
    This is a test file with some bizzare lines

    

    These get converted:

    

    I'm going to ftp ftp.howdy.com     yay!!
I'm going to ftp abbaftp.howdy.com     yay!!
I'm going to ftp ftpabba.howdy.com     yay!!
I'm going to ftp abftpba.howdy.com     yay!!
I'm going to ftp a_ftp_a.howdy.com     yay!!
I'm going to ***ftp a_ftp_a.howdy.com***     yay!!

    

    These are correctly not converted:

    

    I'm going to 9bftpba.howdy.com     yay!!
I'm going to -bftpba.howdy.com     yay!!
I'm going to ***-bftpba.howdy.com***     yay!!

    

    These test beginning and end of line conversions:

    

    ftp ftp.howdy.com     yay!!
    
I'm going to ftp ftp.howdy.com
    
ftp ftp.howdy.com

    

    The same jazz but with www in the name:
 

    These get converted:

    

    I'm going to www.howdy.com     yay!!
I'm going to abbawww.howdy.com     yay!!
I'm going to wwwabba.howdy.com     yay!!
I'm going to abwwwba.howdy.com     yay!!
I'm going to a_www_a.howdy.com     yay!!
I'm going to ***a_www_a.howdy.com***     yay!!

    

    These are correctly not converted:

    

    I'm going to 9bwwwba.howdy.com     yay!!
I'm going to -bwwwba.howdy.com     yay!!
I'm going to ***-bwwwba.howdy.com***     yay!!

    

    These test beginning and end of line conversions:

    

    www.howdy.com     yay!!
    
I'm going to www.howdy.com
    
www.howdy.com

    
txt2html-2.53/tfiles/good_links3.html000066400000000000000000000011511352116237600176240ustar00rootroot00000000000000







    This is a link with a sub-anchor in it.

    

    (http://www.steelypips.org/nethack/id_faq.html#general)

    

    This should not be bolded.

    

    But this should be.  And <http://www.example.com> should
be linked.
    



txt2html-2.53/tfiles/good_links4.html000066400000000000000000000003701352116237600176270ustar00rootroot00000000000000
    This is to test links with underscores in them.

    

    http://rapidshare.com/files/78582195/Futurama_-_S05E01_-_Crimes_Of_The_Hot.part1.rar

    
txt2html-2.53/tfiles/good_list-2.html000066400000000000000000000017101352116237600175340ustar00rootroot00000000000000
    Simple Unordered
    


    This is just an unordered list.

    

      
  
    • Background to building a jump start/install server.
  
    • Extra setup required for district servers (Modem Ports)
  
    • Extra setup required for district servers (External Modems)

    

    Simple Ordered
    


    This is just an ordered list.

    

      
  
    1. First
  
    2. Second
  
    3. Third

    

    Mixed Lists
    


    This list is mixed.  Each ordered item contains an unordered list.

    

      
  
    1. Bureau Server
  
        
    
      • Sun Sparcstation 20
    
      • Dual processor upgrade
  
      
  
    2. Bureau Contingency Server
  
        
    
      • Sun Sparcstation 20
    
      • Dual processor upgrade
  
      
  
    3. PC access Server (read only)
  
        
    
      • Sun Sparcstation 5/110Mhz
    
      • 96Meg of RAM
    
      • 4 X SCSI SBUS cards
  
      

    
txt2html-2.53/tfiles/good_list-3.html000066400000000000000000000006041352116237600175360ustar00rootroot00000000000000
    some random text here.

    

      
  
    • part 1
  
        
    
      1. blah
    
      2. blah blah...
  
      

    

    some random text here.

    

      
  
    • part 2
  
        
    
      1. blah
    
      2. blah blah...
  
      

    

    some random text here.

    

      
  
    • part 3
  
        
    
      1. blah
    
      2. blah blah...
  
      

    

    some random text here.

    
txt2html-2.53/tfiles/good_list-4.html000066400000000000000000000026201352116237600175370ustar00rootroot00000000000000







    Header
    


      
  
    • Item 1: works but looks ugly in text

            This is list item 1 which I will pad with asdashjk kjashdkajsh
   kjhaskjahs kajshkajsdh kajshkajshd

            This is another paragraph of list item 1 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

      
  
    • Item 2: doesn't work but is readable as text

    

         This is list item 2 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

    

          This is another paragraph of list item 2 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

    

      
  
    • Item 3: does work and is readable as text

        This is list item 3 which I will pad with
  asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

      

        This is another paragraph of list item 3 which I will pad with
  asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

      
  
    • Item 4:

        This item explains the 2 test cases below:

      
  
        
    
      1. This is case 1
    
      2. This is case 2
  
      
  
    • Item 5: does indent to the previous level

    



txt2html-2.53/tfiles/good_list-5.html000066400000000000000000000026261352116237600175460ustar00rootroot00000000000000







    Definition Lists
    


    A definition list comprises the following:

    

    
  
    Term
    

      The term part of a DL item is a word on a line by itself, ending
with a colon.
  
    Definition
    

      The definition part of a DL item is at least one paragraph following
the term.

      If one has more than one paragraph in the definition, the first line of
the next paragraph needs to be indented two spaces from where the term
starts, otherwise we don't know that it belongs to the definition.

    

    

    This is a new, separate paragraph.

    

    Mixed Lists
    


    
  
    Yadda Yadda
    

      
      
    
    1. a meaningless term
    
    2. something which Fred Flinstone says
    
    3. something with lawn in it
  
    

    

    Just to be clear, this is a paragraph.

    

      
  
    • Here's some unordered things.
  
      
    
      Unordered
      

          Something without order.
  
      
  
    • Item 2 in the unordered list.
  
      
    
      Ordered
      

          Something with order.
  
      
  
    • This should be item 3 in the unordered list.

    



txt2html-2.53/tfiles/good_list-advanced.html000066400000000000000000000055551352116237600211530ustar00rootroot00000000000000






 

    For Grand Falls E1 events (loss of service for a long time) huge
LOG files (200-300 thousand of lines) is a very typical and
complicating characteristics. Many process (SWERRs, TRAPs, INFOs,
etc) run in parallel and it is very important to understand what
caused what. I want to suggest some tips that can make easier
analysis of such log files.
 

      
  
    1. First of all learn ALL logs AT THE BEGINNING of the event.
   It is very important to understand what process began first.
   You should understand the meaning of EVERY log here.
 
  
    2. Unix tool awk could be very useful for logs files processing.
   Here are some simplest examples of its using.
 
  
        
    
      1. Cutting all logs of some definite type:
  
      

    

                   awk '/PM189/,length < 2' inp_file > out_file
                       ^           ^
                       |           |
      Where:    Pattern in the   End condition
              first line of log  of log (empty string)

    
 

     b) Cutting all lines BEFORE lines with some pattern:
 

        awk '/INV CLASS/{print str;next}{str=$0}' inp_file > out_file

                  ^          ^       ^      ^
       Where: |          |       |      |
              |     Output prev  |    Save full line
           Pattern     line    Go to
                              next line

    
 

     c) Cutting all lines TWO lines BEFORE lines with some pattern:
 

    awk '/cp 35/{print str1;next}{str1=str;str=$0}' inp_file > out_file
 

     d) Prepare exec for site in the form: QDN dn

                                           QDN dn
                                       . . .

    
 

     awk '/  DN /{print "QDN " $8}' inp_file | sort | uniq > out_file

              ^                 ^
 Where:   |                 |
          |           Field number in line

    

       Selection pattern  that contains dn
 

    3. If you need to answer question like that:
 

       "What dn's that appear in logs of type A appear in logs of type B
   too ?" (For example, how many dn's that appear in AUDT203 logs
   appear in logs of TPTSWER cp 35 - inter integrity lost ?)
 

       you could use the next procedure:
 

      
  
    1. Use 2a) for cutting all AUDT203 logs into one file and cp 35
       logs into another.
 
  
    2. Use 2d) for producing of sorted list of dn's from these two
       new files.
 
  
    3. Use tool comm in the form:
 

    

             comm dn_list1_file dn_list2_file > out_file
 

           and in the out_file you will see three columns - in the
       third one common dn's will appear.

    


txt2html-2.53/tfiles/good_list-custom.html000066400000000000000000000012051352116237600207040ustar00rootroot00000000000000







    Testing Different Bullets
    


      
  
    1. Is this an ordered list item?
  
    2. Because somebody did something.
  
    3. And added another!

    

    And then we'll have an unordered list.

    

      
  
    • with a pluss
  
    • as the new bullet, man.
  
        
    
      • and another indent, why not?
  
      
  
    • bask up

    



txt2html-2.53/tfiles/good_list-styles.html000066400000000000000000000060221352116237600207170ustar00rootroot00000000000000







    STRATEGISKA BESLUTSSTÖDSSYSTEM
    


    Syfte
    

    Syftet med detta examensarbete är att studera vilka behov av beslutsunderlag som finns samt att i detta sammanhang undersöka vilka krav man bör ställa på informationssystem för beslutsstöd.

    

    Avgränsningar
    

    Vi kommer endast att rikta in oss på stödet för företags strategiska beslut i samband med expansion på främmande länders marknader. Vi avser endast att studera dessa behov och krav ur beslutsfattarens synvinkel.

    

    Innehåll
    


      
  
    • Människan
  
        
    
      • Beslutsprocessen
    
      • Perception
    
          
      
        • Läshastighet
    
        
    
      • Hur tolkas informationen
    
      • Parametermängd
  
      
  
    • Organisationen
  
        
    
      • Informationsflödet
    
      • Förändringar
  
      
  
    • Marknaden
  
        
    
      • Hur ser dagens informationssystem ut?
    
      • Effektivitet
    
      • Dagens tillvägagångssätt
  
      
  
    • Tekniken
  
        
    
      • Medium för spridning
    
      • Statisk respektive dynamisk information
    
      • Databaser
    
      • Säkerhet
    
          
      
        • Affärshemligheter
    
        
    
      • Agenter (robotar)
  
      

    

    Bakgrund
    

    I dagens samhälle av allt intensivare produktion av information och även behov av information måste beslutsfattarna allt snabbare fatta viktiga beslut. Med marknadernas utveckling mot allt snabbare faktorrörelser på det internationella planet måste även de strategiska besluten ofta fattas mycket snabbt. Man måste trots detta skaffa sig ett adekvat beslutsunderlag, vilket naturligtvis tar en viss tid, tid som man kanske inte har!

    

    Beslutsfattare behöver alltså hjälp från automatiserade verktyg. Frågor man ställs inför i detta sammanhang är bl.a. hur bör beslutsunderlagen utformas och vilka krav bör ställas på informationssystemen som förser beslutsfattarna med beslutsunderlagen.

    

    Tillvägagångssätt
    

    Kvalitativ undersökning genom intervjuer med företags beslutsfattare på olika nivåer, främst ansvariga för internationella marknader.
Kvantitativ studie genom att undersöka vidtagna åtgärder vi olika företags etableringar utomlands, samt försöka relatera dessa till de uppnådda resultaten och sedan jämföra med hemmamarknaden.
    



txt2html-2.53/tfiles/good_list.html000066400000000000000000000000601352116237600173720ustar00rootroot00000000000000
      
  
    • foo

      
 blah blah blah

    
txt2html-2.53/tfiles/good_mixed.html000066400000000000000000000012211352116237600175250ustar00rootroot00000000000000







    This is an example of mixed input, with a list with what shouldn't be bold.

    

      
  
    • The '#' character can be used to introduce comment lines. Comments and
   lines that are empty or contain only whitespace are ignored.
  
    • Pipe characters and newlines within fields and '#' at the begin of the
   first field of an entry must be escaped with a backslash ('\').

    



txt2html-2.53/tfiles/good_news.html000066400000000000000000000346411352116237600174070ustar00rootroot00000000000000








    From: force10ten@some.where.com (Force10Ten)
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 14 Jan 1996 02:03:01 -0500
    
Reply-To: force10ten@some.where.com (Force10Ten)

    

    Because I'm looking for binoculars for use at the Olympic Games, I just
spent quite a bit of time talking about this very subject with Jim
Dougherty, Dave Myers, Jay Barrs and Dick Tone, all of whom have the
opinion that the really good binoculars show their stuff in twilight.  
Myers told me this story at the Bowhunting Trade Show.

    

    He and his buddies were sheep hunting.   There were 5 or 6 guys.  One of
them told the others "there's a sheep in this hollow" several hundred
yards off.  It was dusk.   Nobody but this guy could see the sheep. 
Everybody had binoculars in the 100-300 dollar price range.  Except this
guy who had a set of Zeiss 10 x 50's.   As he passed the glasses around
every one of these guys could see the sheep perfectly clearly.   Nobody
could see it with the cheaper glasses.   

    

    I chose a pair of Leica 10 x 42's for my task at the Olympics, which will
be to do TV and venue play by play coverage of archery.  I need to be able
to call the arrows in the head-to-head instantly.   These glasses are
perfect for the job, which will really involve several weeks of looking
through binoculars this year, what with test tournaments and my own
shooting.

    

    My "A" list after shopping around is in the 700 to 1600 dollar price range
as follows:

    

      
  
    1. Leica 10 x 42
  
    2. Bausch & Lomb Elite 10 x 42
  
    3. Zeiss 10 x 42
  
    4. Svarovski
  
    5. Docter Optik

    

    george t.

    


    From: bowbuff@some.where.com (Bowbuff)
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 16 Jan 1996 06:37:05 -0500

    

    Randy, just reread your question and it may be that the answers you
received didn't answer your question about 8 vs 10 power in low light. 
Considering magnification alone the higher the power the worse it is
likely to be in very low light.  More important is the "exit pupil" of the
binocs:   The second number divided by the first.  
For example a 10x50 binoc has an exit pupil of 5, the same as a 7x35 or
8x40.  This is the measure of light gathering ability of the unit. 
Ignoring power, quality of the optical elements, and lens coatings, an
e.p. of 5 is the optimum.  At least, I read somewhere that this is the
maximum the human eye can process.   All I know is that a top quality pair
of 10x50, 8x40, or 7x35 glasses will pick up more light at dark than you
can see with your naked eyes.  Seriously, I was watching two bull elk
fighting at dark in Rocky Mtn Nat'l Park and it became too dark to see
them although they were in the open only 75 yards away.  With my
Swarovskis I could watch them for about another half hour when I got tired
and gave up.  The higher the e.p. the larger the binocs are physically, of
course, as this means a bigger diameter exit lens and focal length as
well.

    

    The lower the e.p., the worse your binocs will let you down in low light. 
This is why all the compacts are only useful during good light.  The
finest 8x24s or 10x25s will fit in your shirt pocket really neat....and
you'll soon be leaving them there unless it is the middle of the day...or
unless you really don't need to see very much.  

    

    Optics and coatings are no less important for extended use, especially at
very long ranges in the daylight.  Unfortunately you cant sort this out by
looking through them in a store or looking down the street in front of a
store.  The best way is to take them-and all the others you can beg, bum,
or borrow out to the tallest mountain you know and compare them for hours,
especially as it gets dark.  The next best way is to follow the advice of
the Rocky Mountain Bighorn Society:  figure out what is the maximum you
can spend on the finest optics - and then spend 25% more!

    

    Good Luck!

    


    From: abqkelly@some.where.netcom.com(John Kelly )
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Warsaw Pact Binocs
    
Date: 16 Jan 1996 16:52:11 GMT

    

    >Optics and coatings are no less important for extended use, especially
    
at

    >very long ranges in the daylight.  Unfortunately you cant sort this
    
out by

    >looking through them in a store or looking down the street in front of
    
a
    
>store.  

    

    I had an opportunity to compare Leica, Swarkkkovyjowskiiskiskzsky,
Zeiss, and "Warsaw Pact" 8X50s last year at a Rockey Mt Elk Camp event.
You CAN make certain interesting and useful appraisals in that sort of
situation. For example, you can evaluate color and contrast. You can
look right into backlit areas, right at objects next to bright lights
in the trade show ceiling, and judge internal refraction, contrast, and
glare. IMHO the Leicas "looked" prettiest overall, I'd have loved a
pair, were I a successful cocaine dealer or Phil Gramm. 

    

    But a bowhunting pal bought WARSAW PACT "cheapies" ($500..widely
advertised in hunting magazines) there, since they were MUCH brighter
(apparently the equivalent of maybe two f-stops) and more contrasty
than ANY of the others (not to mention, ahem, AFFORDABLE). They were
VASTLY SUPERIOR in those respects. 

    

    In the woods I later found you can look into deep shadows and they are
lit as if they were video amplified. You can look directly into scenes
involving the setting sun and still see clearly, FAR better than with
the naked eye. 

    

    There IS one BIG drawback: everything is a sickly greenish orange or
yellow. The damned things are color blind. Otherwise they are
exceptional at picking out shapes, movement etc under extremely
difficult lighting conditions. That is exactly what they were designed
for, of course, being military equipment, not bird watching equipment.
NOTHING looks pretty through them. Is that a sacrifice that makes
sense? Hmmm. Maybe that depends on your reasons for hunting. 

    

    I've got Pentax and Nikon, under $200ea, and they have to fill the bill
for now. I'm waiting for money from heaven. Maybe I'll go for better
Nikons.

    

    JK

    


    From: Perry Ratcliff <ratcliff@some.where.trw.com>
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: Sun, 14 Jan 96 07:36:28 PDT

    

    > I plan on purchasing a new pair of binoculars next hunting season and 
    
> would like some help.  Let me know what you like or dislike.  Also can 
    
> anyone tell what difference I might expect between an 8X and 10X 
    
> binocular.  How does light conditions affect either one?
    
> 
    
I also have Swarovskis 10x50 but haven't used them for a couple of 
years because they are so heavy.  I'm now using Pentax 12x42 
binoculars and am extremely pleased with them.  They are very light
for the size and have good light gathering capabilities.  They are
nitrogen filled and have never fogged up on me.  I believe they cost
me around $300 and feel that they are an outstanding value.

    

    If you are on a more modest budget there are some very good 
compact binoculars in the $150 range.  Make sure that they are
nitrogen filled to prevent fogging in the rain.  If you wear
glasses make certain that the binoculars have a long eye relief
or you will lose a lot of light through the binoculars.

    

    Good Luck,

    

    Perry

    


    From: ap941@some.where.ysu.edu (Mark W. Thurm)
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 16 Jan 1996 17:07:13 GMT
    
Reply-To: ap941@some.where.ysu.edu (Mark W. Thurm)

    

    >I plan on purchasing a new pair of binoculars next hunting season and 
    
>would like some help.  Let me know what you like or dislike.  Also can 
    
>anyone tell what difference I might expect between an 8X and 10X 
    
>binocular.  How does light conditions affect either one?

    
 

     I have a pair of Cabellas compacts, 8 power, nitrogen filled, long
eye relief. For the money ($100) they're a good deal (IMHO). I've
looked at Ziess, Swarvoski. Brunton, etc. and they were excellent
but with my constrants (married with children) my wife wouldn't
authorize er... I couldn't justfy the 6-10 times price diferential.

    

     A 10 power compact will not gather much light and will be harder to hold
steady. I hunt in the west and the 8x has worked well fo me.

    

    MT

    

    -- 
   

                It's not the bible that's filled with contradictions,
                 It's our brains that are filled with them.
                             J. Vernon McGee

    


    Newsgroups: alt.archery
    
From: jwf20@some.where.ccc.amdahl.com (Jim Flenniken)
    
Subject: Re: Binocular Purchase - Advice
    
Date: Tue, 16 Jan 1996 18:14:09 GMT

    

    Randy Ross <randyr@some.where.com> wrote:

    

    >I plan on purchasing a new pair of binoculars next hunting season and 
    
>would like some help.  Let me know what you like or dislike.  Also can 
    
>anyone tell what difference I might expect between an 8X and 10X 
    
>binocular.  How does light conditions affect either one?

    

    >Thanks.

    

    >Randy

    

    Bushnell makes a pair of 'glasses on' binoculars that are excellent
for those of us that wear glasses. the long eye-relief is a blessing
when scanning a field while wearing glasses and the price is about
$125. 

    


    From: Alex Hoover <alexh>
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 16 Jan 1996 22:17:34 GMT

    

    I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

    

    In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

    

    There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

    

    Regards,
    
alex.hoover@some.where.com
    
Denver, CO

    


    From: Alex Hoover <alexh>
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 16 Jan 1996 22:18:10 GMT

    

    I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

    

    In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

    

    There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

    

    Regards,
    
alex.hoover@some.where.com
    
Denver, CO

    


    From: Alex Hoover <alexh>
    
Newsgroups: alt.archery
    
Subject: Re: Binocular Purchase - Advice
    
Date: 16 Jan 1996 22:18:19 GMT

    

    I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

    

    In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

    

    There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

    

    Regards,
    
alex.hoover@some.where.com
    
Denver, CO

    

    The following should be treated as mail quote, not as pre-formatted

    

    > 1      more
    
> 2      more
    
> 3      more
    
> 4      more
    
> 5      more

    

    Back to normal again. more and more, make it a long line, not a short one. 

    

    > 1      more and more, make it a long line, not a short one. 
    
> 2      more and more, make it a long line, not a short one. 
    
> 3      more and more, make it a long line, not a short one. 

    



txt2html-2.53/tfiles/good_pre.html000066400000000000000000000011111352116237600172030ustar00rootroot00000000000000
    ## Test on pre-in-list

    

    txt2html.pl -p 7 -pb 1

    

    Here is an example bad file:

    

      
  
    1. text (should be translated as <LI>) (there should be no </OL> tag
at this point)

             preformatted text..
       ... and more 
     
  
    2. this should be translated as <LI>

    

    ## Test on mail_quote-in-pre_explicit

    

    Here is the actuall file content. 
Maybe more lines.
> 1      more
> 2      more

    

txt2html-2.53/tfiles/good_pre2.html000066400000000000000000000002151352116237600172710ustar00rootroot00000000000000
    This is a text file.

    

            The text file ends with a block of preformatted text.
        This is the end of the file.

    
txt2html-2.53/tfiles/good_punct.html000066400000000000000000000016021352116237600175530ustar00rootroot00000000000000
    Why do I keep on having these bright ideas? Miles wondered as he
crawled through the service tunnel.  It gave him uncomfortable
flashbacks to the time he'd crawled through the ducting on Aslund
station.  Though at least this time he didn't have Gregor to worry
about.  No, just lizard things, and the Doctor.  Now there was an
unknown quantity.  Sharp, yes, and knew too much about the wrong things,
but... You are supposed to be a good judge of character, Miles, he
thought to himself.  It's a bit late to be second-guessing now.

    

    Miles sat up straighter in the chair and checked the settings again.
The earbud in his ear had warmed to body-temperature, but it was still a
hard lump.  Part of him was gibbering Aliens!  You're going to be
talking to aliens! while another part of him was just getting
impatient, waiting for the Doctor to return.

    
txt2html-2.53/tfiles/good_robo.html000066400000000000000000000036321352116237600173700ustar00rootroot00000000000000







    Type:     cmu.cs.robotics
    
Topic:    Robotics Seminar, Prof. John Canny, Friday Oct 11, 3:30, Adamson Wing, Baker Hall
Dates:    11-Oct-91
    
Time:     3:30
    
Place:    Adamson Wing, Baker Hall
    
PostedBy: me on 11-Oct-91 at 01:39 from H.GP.CS.CMU.EDU (Michael Erdmann)
Abstract: 

    

    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

             ***** Friendly Reminder:  Robotics Seminar Today!! *****
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

    

    

    Date:11-Oct-91

    Time:3:30 (Refreshments at 3:15)

    Place:Adamson Wing, Baker Hall

    

    

                                RISC-Robotics

    

                                  John Canny
                            U.C. Berkeley

    

       RISC in a robotics context stands for Reduced Intricacy in Sensing and
   Control.  But it shares the same philosophy as RISC computer design.
   The idea is to replace complicated manipulation and sensing steps with
   combinations of simple ones.  Industrial robotics research has focussed
   on anthropomorphism in the hope that once robots become sufficiently
   human-like, they will be able to solve all the tasks that they are
   currently incapable of doing.  This approach is seductive and has led
   researchers further and further away from the real problems that
   hinder the proliferation of robots in manufacturing.  The enthusiasm
   for robotics in industry which reached a peak in the mid 80's has all
   but disappeared after a protracted lack of progress on these problems.
    



txt2html-2.53/tfiles/good_sample.html000066400000000000000000000276021352116237600177130ustar00rootroot00000000000000


txt2html/HTML::TextToHTML Sample Conversion




    txt2html/HTML::TextToHTML Sample Conversion


    This sample is based hugely on the original sample.txt produced
by Seth Golub for txt2html.


    I used the following options to convert this document:


         -titlefirst -mailmode -make_tables
     --custom_heading_regexp '^ *--[\w\s]+-- *$'
     --system_link_dict txt2html.dict
     --append_body sample.foot --infile sample.txt --outfile sample.html

    

    This has either been done at the command line with:


            perl -MHTML::TextToHTML -e run_txt2html -- options


    or using the script


            txt2html options


    or from a (test) perl script with:
        

            use HTML::TextToHTML;
        my $conv = new HTML::TextToHTML();
        $conv->txt2html([options]);

    

    



    From bozo@clown.wustl.edu
    
Return-Path: <bozo@clown.wustl.edu>
    
Message-Id: <9405102200.AA04736@clown.wustl.edu>
    
Content-Length: 1070
    
From: bozo@clown.wustl.edu (Bozo the Clown)
    
To: kitty@example.com (Kathryn Andersen)
    
Subject: Re: HTML::TextToHTML
    
Date: Sun, 12 May 2002 10:01:10 -0500


    Bozo wrote:

    BtC> Can you post an example text file with its html'ed output?
    
BtC> That would provide a much better first glance at what it does
    
BtC> without having to look through and see what the perl code does.


    Good idea.  I'll write something up.


    


    The header lines were kept separate because they looked like mail
headers and I have mailmode on.  The same thing applies to Bozo's
quoted text.  Mailmode doesn't screw things up very often, but since
most people are usually converting non-mail, it's off by default.


    Paragraphs are handled ok.  In fact, this one is here just to
demonstrate that.


    THIS LINE IS VERY IMPORTANT!
    
(Ok, it wasn't that important)


    EXAMPLE HEADER
    


    Since this is the first header noticed (all caps, underlined with an
"="), it will be a level 1 header.  It gets an anchor named
"section_1".


    Another example
    

    This is the second type of header (not all caps, underlined with "=").
It gets an anchor named "section_1_1".


    Yet another example
    


    This header was in the same style, so it was assigned the same header
tag.  Note the anchor names in the HTML. (You probably can't see them
in your current document view.)  Its anchor is named "section_1_2". 
Get the picture?


    -- This is a custom header --
    


    You can define your own custom header patterns if you know what your
documents look like.


    Features of HTML::TextToHTML
    


      
  
    • Handles different kinds of lists
  
        
    
      1. Bulleted
    
      2. Numbered
    
          
      
        • You can nest them as far as you want.
      
        • It's pretty decent about figuring out which level of list it
        is supposed to be on.
      
            
        
          • You don't need to change bullet markers to start a new list.
      
          
    
        
    
      3. Lettered
    
          
      
        1. Finally handles lettered lists
      
        2. Upper and lower case both work
      
            
        
          1. Here's an example
        
          2. I've been meaning to add this for some time.
      
          
      
        3. HTML without CSS can't specify how ordered lists should be
        indicated, so it will be a numbered list in most browsers.
    
        
    
      4. Definition lists (see below)
  
      
  
    • Doesn't screw up mail-ish things
  
    • Spots preformated text

    

                     It just needs to have enough whitespace in the line.
        Surrounding blank lines aren't necessary.  If it sees enough
        whitespace in a line, it preformats it.  How much is enough?
        Set it yourself at command line if you want.

    

      
  
    • You can append a file automatically to all converted files.  This
   is handy for adding signatures to your documents.
  
    • Deals with paragraphs decently.

         Looks for short lines in the middle of paragraphs and keeps them
   short with the use of breaks (<BR>).  How short the lines need to
   be is configurable.

         Unhyphenates split words that are in the middle of paragraphs.  
   Let me know if trailing punctuation isn't handled "properly".  
   It should be.

         One can also have multi-paragraph list items, like this one.
  
    • Puts anchors at all headers and, if you're using the mail header
   features, at the beginning of each mail message.  The anchor names
   for headings are based on guessed section numbers.  
  
        
    
      • You can turn off this option too, if you don't like it.
  
      
  
    • Groks Mosaic-style "formatted text" headers (like the one below)
  
    • Can hyperlink things according to a dictionary file.
   The sample dictionary handles URLs like http://www.aigeek.com/ and
   <http://www.katspace.com/> and also shows how to do simpler
   things such as linking the word txt2html the first time it appeared.
  
    • One can also use the link-dictionary to define custom tags, for
   example using the star character to indicate italics.
  
    • Recognises and parses tables of different types:
  
        
    
      • DELIM: A table determined by delimiters.
    
      • ALIGN: No need for fancy delimiters, this figures out
     a table by looking at the layout, the spacing of the cells.
    
      • BORDER: has a nice border around the table
    
      • PGSQL: the same format as Postgresql query results.
  
      
  
    • Also with XHTML!  Turn on the --xhtml option and it will ensure that
   all paragraphs and list items have end-tags, all tags are in
   lower-case, and the doctype is for XHTML.

    

    Example of short lines
    


    We're the knights of the round table
    
We dance whene'er we're able
    
We do routines and chorus scenes
    
With footwork impeccable.
    
We dine well here in Camelot
    
We eat ham and jam and spam a lot.


    Example of varied formatting
    


    If I want to emphasize something, then I'd use stars to wrap
around the words, even if there were more than one, that's
what I'd do.  But I could also underline words, so long as
the darn thing was not a_variable_name, in which case I wouldn't
want to lose the underscores in something which thought it was
underlining.  Though we might want to underline more than one word
in a sentence.  Especially if it is The Title Of A Book.
For another kind of emphasis, let's go and put something in bold.

       But it doesn't even need to be that simple. Something which is really
exciting is coping with italics and similar things spread across
multiple lines.


    Example of Long Preformatting
    


    (extract from Let It Rain by Kristen Hall)


            I have given, I have given and got none
        Still I'm driven by something I can't explain
        It's not a cross, it is a choice
        I cannot help but hear his voice
        I only wish that I could listen without shame

        Let it rain, let it rain, on me
        Let it rain, oh let it rain,
        Let it rain, on me

        I have been a witness to the perfect crime
        Wipe the grin off of my face to hide the pain
        It isn't worth the tears you cry
        To have a perfect alibi
        Now I'm beaten at the hands of my own game

        Let it rain, let it rain, on me
        Let it rain, oh let it rain,
        Let it rain, on me

    

    Definition Lists
    


    A definition list comprises the following:


    
  
    Term
    

      The term part of a DL item is a word on a line by itself, ending
with a colon.
  
    Definition
    

    The definition part of a DL item is at least one paragraph following
the term.

      If one has more than one paragraph in the definition, the first line of
the next paragraph needs to be indented two spaces from where the term
starts, otherwise we don't know that it belongs to the definition.

    

    Examples of Tables
    


    ALIGN
    


    Here is a simple ALIGN table:


    

    -eFile exists.

    -zFile has zero size.

    -sFile has nonzero size (returns size).

    

    

    Here are some of the conditions of ALIGN tables:


    

    Context:A table needs to be surrounded by blank lines.

    Length:A table must contain at least two rows.

    Width:A table must contain at least two columns.

    Spacing:There needs to be at least two spaces between the columns,

    otherwise there might be some random paragraph which

    could have inter-word spacing that lined up by accident.

    Cell Size:If you have more than one line (as just above) then

    you will simply get empty cells where the other column is empty.

    Alignment:Alignment of cells is attempted to be preserved.

    

    

    BORDER
    


    This is a table with a border.


    

    FoodQty
    


    Bread1
    

    Milk1
    

    Oranges3
    

    Apples6
    
    

    


    PGSQL
    


    This is the same table like Postgresql would make it.


    

    FoodQty
    


    Bread1
    

    Milk1
    

    Oranges3
    

    Apples6
    
    

    

            (4 rows)



    DELIM
    


    A delimited table needs to have its delimiters at the start and end,
just to be sure that this is a table.


    

    FredNurk58
    

    GeorgeWashington62
    

    MaryQuant35
    

    


    And one can have almost any delimiter one wishes.


    

    Darcy, Fitzwilliamhero
    

    Bennet, Elizabethheroine
    

    Wickham, Georgevillain
    

    


    THINGS TO DO
    


    There are some things which this module doesn't handle yet which
I would like to implement.


      
  
    1. I would like to be able to preserve lettered lists, that is:
  
        
    
      1. recognise that they are letters and not numbers (which it already
      does)
    
      2. display the correct OL properties with CSS so as to preserve
      that information.
  
      

    

    


    The footer is everything from the end of this sentence to the
</BODY> tag.


    

    
KatSpace

    


txt2html-2.53/tfiles/good_table-align.html000066400000000000000000000012431352116237600206020ustar00rootroot00000000000000
    This is for testing a table which is regognised by its alignment.

    

    

    FruitVegetable

    BananaCarrot

    AppleCelery

    

    

    The following is not a table because there aren't enough spaces between
items.

    

    Fred Nurk    ate
    
Mary Norton  slept
    
Hugh Jackman snarled

    

    But this one is.

    

    

    FredNurkate

    MaryNortonslept

    HughJackmansnarled
    

    
txt2html-2.53/tfiles/good_table-border.html000066400000000000000000000037341352116237600207740ustar00rootroot00000000000000
    

    SchemaNameTypeOwner
    


    publicactor_episodesviewkat
    

    publicactorstablekat
    

    publiccopyableviewkat
    

    publicepisode_recordingviewkat
    

    publicepisodestablekat
    

    publicepisodes_title_id_seqsequencekat
    

    publicpal_recordingsviewkat
    

    publicrecordingstablekat
    

    publicsorted_epsviewkat
    

    publictapestablekat
    

    publicunrecordedviewkat
    

    publicwantingviewkat
    
    

    


    And the same table could be indented.

    

    

    SchemaNameTypeOwner
    


    publicactor_episodesviewkat
    

    publicactorstablekat
    

    publiccopyableviewkat
    

    publicepisode_recordingviewkat
    

    publicepisodestablekat
    

    publicepisodes_title_id_seqsequencekat
    

    publicpal_recordingsviewkat
    

    publicrecordingstablekat
    

    publicsorted_epsviewkat
    

    publictapestablekat
    

    publicunrecordedviewkat
    

    publicwantingviewkat
    
    

    

txt2html-2.53/tfiles/good_table-delim.html000066400000000000000000000032311352116237600206010ustar00rootroot00000000000000
    Delimited Table
    


    This one was a border table from which I removed the divider lines.

    

    

    SchemaNameTypeOwner
    

    publicactor_episodesviewkat
    

    publicactorstablekat
    

    publiccopyableviewkat
    

    publicepisode_recordingviewkat
    

    publicepisodestablekat
    

    publicepisodes_title_id_seqsequencekat
    

    publicpal_recordingsviewkat
    

    publicrecordingstablekat
    

    publicsorted_epsviewkat
    

    publictapestablekat
    

    publicunrecordedviewkat
    

    publicwantingviewkat
    

    


    And this is a homegrown one.

    

    

    FredNurklives
    

    KerrAvonis wonderfule
    

     Servalanhas no first name
    

    


    And the next one has a caption, and a possibly tricky delimiter.

    

    
Actors

    PaulDarrow
    

    JackiePierce
    

    


    Note that a CSV table doesn't work for delimiter stuff,
because it isn't bounded by commas.

    

    Fred,Nurk
    
Joe,Schmoe
    
txt2html-2.53/tfiles/good_table-pgsql.html000066400000000000000000000020161352116237600206350ustar00rootroot00000000000000
    
List of relations

    SchemaNameTypeOwner
    


    publicactor_episodesviewkat
    

    publicactorstablekat
    

    publiccopyableviewkat
    

    publicepisode_recordingviewkat
    

    publicepisodestablekat
    

    publicepisodes_title_id_seqsequencekat
    

    publicpal_recordingsviewkat
    

    publicrecordingstablekat
    

    publicsorted_epsviewkat
    

    publictapestablekat
    

    publicunrecordedviewkat
    

    publicwantingviewkat
    
    

    

    (12 rows)
    


txt2html-2.53/tfiles/good_table-pgsql2.html000066400000000000000000000457561352116237600207410ustar00rootroot00000000000000
    

    titlesub_titletitle_idcategoryseries_titleepisode_positionseasonseason_positionepisode_codewanting
    


    Gathering, The 687SERIESHighlander111  
    

    Innocent Man 689SERIESHighlander212  
    

    Road Not Taken 694SERIESHighlander313  
    

    Bad Day In Building A 677SERIESHighlander414  
    

    Free Fall 686SERIESHighlander515  
    

    Deadly Medicine 680SERIESHighlander616  
    

    Mountain Men 691SERIESHighlander717  
    

    Revenge Is Sweet 693SERIESHighlander818  
    

    Sea Witch, The 696SERIESHighlander919  
    

    Eye Witness 681SERIESHighlander10110  
    

    Family Tree 683SERIESHighlander11111  
    

    See No Evil 697SERIESHighlander12112  
    

    Band of Brothers 678SERIESHighlander13113  
    

    For Evil's Sake 684SERIESHighlander14114  
    

    For Tomorrow We Die 685SERIESHighlander15115  
    

    Beast Below, The 679SERIESHighlander16116  
    

    Saving Grace 695SERIESHighlander17117  
    

    Lady and the Tiger, The 690SERIESHighlander18118  
    

    Avenging Angel 676SERIESHighlander19119  
    

    Eye of the Beholder 682SERIESHighlander20120  
    

    Nowhere To Run 692SERIESHighlander21121  
    

    Hunters, The 688SERIESHighlander22122  
    

    Watchers, The 698SERIESHighlander2321  
    

    Studies in Light 2820SERIESHighlander2422  
    

    Turnabout 2821SERIESHighlander2523  
    

    Darkness, The 2822SERIESHighlander2624  
    

    Eye For An Eye 2823SERIESHighlander2725  
    

    Zone, The 2824SERIESHighlander2826  
    

    Return of Amanda, The 2825SERIESHighlander2927  
    

    Revenge of The Sword 2826SERIESHighlander3028  
    

    Run For Your Life 2827SERIESHighlander3129  
    

    Epitaph For Tommy 2828SERIESHighlander32210  
    

    Bless The Child 2829SERIESHighlander33211  
    

    Fighter, The 2830SERIESHighlander34212  
    

    Under Color of Authority 2831SERIESHighlander35213  
    

    Unholy Alliance (1) 2832SERIESHighlander36214  
    

    Unholy Alliance (2) 2833SERIESHighlander37215  
    

    Vampire, The 2834SERIESHighlander38216  
    

    Warmonger 2835SERIESHighlander39217  
    

    Pharaoh's Daughter 2836SERIESHighlander40218  
    

    Legacy 2837SERIESHighlander41219  
    

    Prodigal Son 2838SERIESHighlander42220  
    

    Counterfeit (1) 2839SERIESHighlander43221  
    

    Counterfiet (2) 2840SERIESHighlander44222  
    

    Samurai, The 2875SERIESHighlander4531  
    

    Line of Fire 2876SERIESHighlander4632  
    

    Revolutionary, The 2877SERIESHighlander4733  
    

    Cross of St. Antoine 2878SERIESHighlander4834  
    

    Rite of Passage 2879SERIESHighlander4935  
    

    Courage 2880SERIESHighlander5036  
    

    Lamb, The 2881SERIESHighlander5137  
    

    Obsession 2882SERIESHighlander5238  
    

    Shadows 2883SERIESHighlander5339  
    

    BlackmailSwords, Lies & Videotape2884SERIESHighlander54310  
    

    Vendetta 2885SERIESHighlander55311  
    

    They Also Serve 2886SERIESHighlander56312  
    

    Blind Faith 2887SERIESHighlander57313  
    

    Song of the Executioner 3002SERIESHighlander58314  
    

    Star Crossed 3003SERIESHighlander59315  
    

    Methos 3004SERIESHighlander60316  
    

    Take Back the Night 3005SERIESHighlander61317  
    

    Testimony 3006SERIESHighlander62318  
    

    Mortal Sins 3007SERIESHighlander63319  
    

    Reasonable Doubt 3163SERIESHighlander 320  
    

    Finale 3164SERIESHighlander 321  
    

    Finale II 3165SERIESHighlander 322  
    

    Homeland 3166SERIESHighlander 41  
    

    Brothers In Arms 3167SERIESHighlander 42  
    

    Innocent, The 3168SERIESHighlander 43  
    

    Leader of the Pack 3169SERIESHighlander 44  
    

    Double Eagle 3170SERIESHighlander 45  
    

    Reunion 3171SERIESHighlander 46  
    

    Colonel, The 3172SERIESHighlander 47  
    

    Reluctant Heroes 3173SERIESHighlander 48  
    

    Wrath of Kali, The 3174SERIESHighlander 49  
    

    Chivalry 3175SERIESHighlander 410  
    

    Timeless 3176SERIESHighlander 411  
    

    Blitz, The 3177SERIESHighlander 412  
    

    Something WickedHakoya3261SERIESHighlander 413  
    

    DeliveranceLeap of Faith3262SERIESHighlander 414  
    

    Promises 3180SERIESHighlander 415  
    

    Methuselah's Gift 3426SERIESHighlander 416  
    

    Immortal Cimoli, The 3263SERIESHighlander 417  
    

    Through a Glass Darkly 3427SERIESHighlander 418  
    

    Double Jeopardy 3453SERIESHighlander 419  
    

    Till Death 3428SERIESHighlander 420  
    

    Judgement Day 3429SERIESHighlander 421  
    

    One Minute To Midnight 3430SERIESHighlander 422  
    

    Prophecy 3454SERIESHighlander 51  
    

    End of Innocence, The 3455SERIESHighlander 52  
    

    Manhunt 3456SERIESHighlander 53  
    

    Glory Days 3457SERIESHighlander 54  
    

    Dramatic Licence 3458SERIESHighlander 55  
    

    Money's No Object 3459SERIESHighlander 56  
    

    Haunted 3460SERIESHighlander 57  
    

    Little Tin God 3461SERIESHighlander 58  
    

    Messenger, The 3462SERIESHighlander 59  
    

    Valkyrie, The 3463SERIESHighlander 510  
    

    Comes A Horseman 3464SERIESHighlander 511  
    

    Revelations 6:8 3465SERIESHighlander 512  
    

    Ransom of Richard Redstone, The 3466SERIESHighlander 513  
    

    Duende 3467SERIESHighlander 514  
    

    Stone of Scone, The 3468SERIESHighlander 515  
    

    Forgive Us Our Trespasses 3469SERIESHighlander 516  
    

    Modern Prometheus, The 3470SERIESHighlander 517  
    

    Archangel 3471SERIESHighlander 518  
    

    Avatar 3624SERIESHighlander 61  
    

    Armageddon 3625SERIESHighlander 62  
    

    Sins of the Father 3626SERIESHighlander 63  
    

    Diplomatic Immunity 3888SERIESHighlander 64  
    

    Patient Number 7 3889SERIESHighlander 65  
    

    Black Tower 3936SERIESHighlander 66  
    

    Unusual Suspects 3904SERIESHighlander 67  
    

    Justice 3905SERIESHighlander 68  
    

    Deadly Exposure 3906SERIESHighlander 69  
    

    Two of Hearts 3937SERIESHighlander 610  
    

    Indiscretions 3938SERIESHighlander 611  
    

    To Be 3939SERIESHighlander 612  
    

    Not To Be 3940SERIESHighlander 613  
    

    Highlander 3105MOVIEHighlander     
    

    bloopers 3523SERIESHighlander     
    
    

    

    (121 rows)
    


txt2html-2.53/tfiles/good_umlauttest.html000066400000000000000000000011561352116237600206350ustar00rootroot00000000000000







    Es geht darum, sie zu verändern zu ändern zu Ändern.
Es geht darum, sie zu verändern zu ändern zu Ändern.
Es geht darum, sie zu verändern zu ändern zu Ändern.

    

    ÄNDERN

    



txt2html-2.53/tfiles/good_utf8.html000066400000000000000000000001471352116237600173130ustar00rootroot00000000000000
    Some UTF-8 characters
    


    $ echo 門牌號碼規劃

    

    Perhaps just tip of iceberg.

    
txt2html-2.53/tfiles/good_xhtml_sample.html000066400000000000000000000307031352116237600211230ustar00rootroot00000000000000


txt2html/HTML::TextToHTML Sample Conversion




    txt2html/HTML::TextToHTML Sample Conversion

    

    This sample is based hugely on the original sample.txt produced
by Seth Golub for txt2html.

    

    I used the following options to convert this document:

    

         -titlefirst -mailmode -make_tables
     --custom_heading_regexp '^ *--[\w\s]+-- *$'
     --system_link_dict txt2html.dict
     --append_body sample.foot --infile sample.txt --outfile sample.html

    

    This has either been done at the command line with:

    

            perl -MHTML::TextToHTML -e run_txt2html -- options

    

    or using the script

    

            txt2html options

    

    or from a (test) perl script with:
        

            use HTML::TextToHTML;
        my $conv = new HTML::TextToHTML();
        $conv->txt2html([options]);

    

    



    From bozo@clown.wustl.edu
    
Return-Path: <bozo@clown.wustl.edu>
    
Message-Id: <9405102200.AA04736@clown.wustl.edu>
    
Content-Length: 1070
    
From: bozo@clown.wustl.edu (Bozo the Clown)
    
To: kitty@example.com (Kathryn Andersen)
    
Subject: Re: HTML::TextToHTML
    
Date: Sun, 12 May 2002 10:01:10 -0500

    

    Bozo wrote:

    BtC> Can you post an example text file with its html'ed output?
    
BtC> That would provide a much better first glance at what it does
    
BtC> without having to look through and see what the perl code does.

    

    Good idea.  I'll write something up.

    

    


    The header lines were kept separate because they looked like mail
headers and I have mailmode on.  The same thing applies to Bozo's
quoted text.  Mailmode doesn't screw things up very often, but since
most people are usually converting non-mail, it's off by default.

    

    Paragraphs are handled ok.  In fact, this one is here just to
demonstrate that.

    

    THIS LINE IS VERY IMPORTANT!
    
(Ok, it wasn't that important)

    

    EXAMPLE HEADER
    


    Since this is the first header noticed (all caps, underlined with an
"="), it will be a level 1 header.  It gets an anchor named
"section_1".

    

    Another example
    

    This is the second type of header (not all caps, underlined with "=").
It gets an anchor named "section_1_1".

    

    Yet another example
    


    This header was in the same style, so it was assigned the same header
tag.  Note the anchor names in the HTML. (You probably can't see them
in your current document view.)  Its anchor is named "section_1_2". 
Get the picture?

    

    -- This is a custom header --
    


    You can define your own custom header patterns if you know what your
documents look like.

    

    Features of HTML::TextToHTML
    


      
  
    • Handles different kinds of lists
  
        
    
      1. Bulleted
    
      2. Numbered
    
          
      
        • You can nest them as far as you want.
      
        • It's pretty decent about figuring out which level of list it
        is supposed to be on.
      
            
        
          • You don't need to change bullet markers to start a new list.
      
          
    
        
    
      3. Lettered
    
          
      
        1. Finally handles lettered lists
      
        2. Upper and lower case both work
      
            
        
          1. Here's an example
        
          2. I've been meaning to add this for some time.
      
          
      
        3. HTML without CSS can't specify how ordered lists should be
        indicated, so it will be a numbered list in most browsers.
    
        
    
      4. Definition lists (see below)
  
      
  
    • Doesn't screw up mail-ish things
  
    • Spots preformated text

    

                     It just needs to have enough whitespace in the line.
        Surrounding blank lines aren't necessary.  If it sees enough
        whitespace in a line, it preformats it.  How much is enough?
        Set it yourself at command line if you want.

    

      
  
    • You can append a file automatically to all converted files.  This
   is handy for adding signatures to your documents.
  
    • Deals with paragraphs decently.

         Looks for short lines in the middle of paragraphs and keeps them
   short with the use of breaks (<BR>).  How short the lines need to
   be is configurable.

      

         Unhyphenates split words that are in the middle of paragraphs.  
   Let me know if trailing punctuation isn't handled "properly".  
   It should be.

      

         One can also have multi-paragraph list items, like this one.

      
  
    • Puts anchors at all headers and, if you're using the mail header
   features, at the beginning of each mail message.  The anchor names
   for headings are based on guessed section numbers.  
  
        
    
      • You can turn off this option too, if you don't like it.
  
      
  
    • Groks Mosaic-style "formatted text" headers (like the one below)
  
    • Can hyperlink things according to a dictionary file.
   The sample dictionary handles URLs like http://www.aigeek.com/ and
   <http://www.katspace.com/> and also shows how to do simpler
   things such as linking the word txt2html the first time it appeared.
  
    • One can also use the link-dictionary to define custom tags, for
   example using the star character to indicate italics.
  
    • Recognises and parses tables of different types:
  
        
    
      • DELIM: A table determined by delimiters.
    
      • ALIGN: No need for fancy delimiters, this figures out
     a table by looking at the layout, the spacing of the cells.
    
      • BORDER: has a nice border around the table
    
      • PGSQL: the same format as Postgresql query results.
  
      
  
    • Also with XHTML!  Turn on the --xhtml option and it will ensure that
   all paragraphs and list items have end-tags, all tags are in
   lower-case, and the doctype is for XHTML.

    

    Example of short lines
    


    We're the knights of the round table
    
We dance whene'er we're able
    
We do routines and chorus scenes
    
With footwork impeccable.
    
We dine well here in Camelot
    
We eat ham and jam and spam a lot.

    

    Example of varied formatting
    


    If I want to emphasize something, then I'd use stars to wrap
around the words, even if there were more than one, that's
what I'd do.  But I could also underline words, so long as
the darn thing was not a_variable_name, in which case I wouldn't
want to lose the underscores in something which thought it was
underlining.  Though we might want to underline more than one word
in a sentence.  Especially if it is The Title Of A Book.
For another kind of emphasis, let's go and put something in bold.

       But it doesn't even need to be that simple. Something which is really
exciting is coping with italics and similar things spread across
multiple lines.

    

    Example of Long Preformatting
    


    (extract from Let It Rain by Kristen Hall)

    

            I have given, I have given and got none
        Still I'm driven by something I can't explain
        It's not a cross, it is a choice
        I cannot help but hear his voice
        I only wish that I could listen without shame

        Let it rain, let it rain, on me
        Let it rain, oh let it rain,
        Let it rain, on me

        I have been a witness to the perfect crime
        Wipe the grin off of my face to hide the pain
        It isn't worth the tears you cry
        To have a perfect alibi
        Now I'm beaten at the hands of my own game

        Let it rain, let it rain, on me
        Let it rain, oh let it rain,
        Let it rain, on me

    

    Definition Lists
    


    A definition list comprises the following:

    

    
  
    Term
    

      The term part of a DL item is a word on a line by itself, ending
with a colon.
  
    Definition
    

    The definition part of a DL item is at least one paragraph following
the term.

      If one has more than one paragraph in the definition, the first line of
the next paragraph needs to be indented two spaces from where the term
starts, otherwise we don't know that it belongs to the definition.

    

    

    Examples of Tables
    


    ALIGN
    


    Here is a simple ALIGN table:

    

    

    -eFile exists.

    -zFile has zero size.

    -sFile has nonzero size (returns size).

    

    

    Here are some of the conditions of ALIGN tables:

    

    

    Context:A table needs to be surrounded by blank lines.

    Length:A table must contain at least two rows.

    Width:A table must contain at least two columns.

    Spacing:There needs to be at least two spaces between the columns,

    otherwise there might be some random paragraph which

    could have inter-word spacing that lined up by accident.

    Cell Size:If you have more than one line (as just above) then

    you will simply get empty cells where the other column is empty.

    Alignment:Alignment of cells is attempted to be preserved.

    

    

    BORDER
    


    This is a table with a border.

    

    

    FoodQty
    


    Bread1
    

    Milk1
    

    Oranges3
    

    Apples6
    
    

    


    PGSQL
    


    This is the same table like Postgresql would make it.

    

    

    FoodQty
    


    Bread1
    

    Milk1
    

    Oranges3
    

    Apples6
    
    

    

            (4 rows)
    



    DELIM
    


    A delimited table needs to have its delimiters at the start and end,
just to be sure that this is a table.

    

    

    FredNurk58
    

    GeorgeWashington62
    

    MaryQuant35
    

    


    And one can have almost any delimiter one wishes.

    

    

    Darcy, Fitzwilliamhero
    

    Bennet, Elizabethheroine
    

    Wickham, Georgevillain
    

    


    THINGS TO DO
    


    There are some things which this module doesn't handle yet which
I would like to implement.

    

      
  
    1. I would like to be able to preserve lettered lists, that is:
  
        
    
      1. recognise that they are letters and not numbers (which it already
      does)
    
      2. display the correct OL properties with CSS so as to preserve
      that information.
  
      

    

    


    The footer is everything from the end of this sentence to the
</BODY> tag.

    


    

    
KatSpace

    


txt2html-2.53/tfiles/heading1.txt000066400000000000000000000475321352116237600167610ustar00rootroot00000000000000Doctor Who New Adventures
*************************

*The Left-Handed Hummingbird* by Kate Orman
===========================================

(an attempt at a spoiler-free review by Kathryn Andersen)

This novel is right up there with Love & War in the best NA
category, I think.   Why?  Hmmm.  Many of the NA's are "okay".
They have nothing *wrong* with them.  But to be an outstanding story,
it needs something extra; some character insight or development
which changes the relationship of the major characters, an original
plot/twist/adversary, an excellent turn of phrase - and LHH had
all of these.  Here, the Doctor is put in a position he has
never been in before, hoist on his own petard, a victim of his
own way of doing things, caught in a trap that travels with him.

(I am reminded of the Blake's 7 quote:
*"When you know an enemy's strengths, and can use them against them,
they become weaknesses."*
-- Servalan, to Travis	(Blake's 7: Weapon [B3])
)

There are some good insights about him and Ace, wondering
if they are more alike than they like to admit...
And finally, those turning phrases, made me want to write again.
It's not often you get some lovely stuff you'd like to quote -
my quotes file has many gems from "Transit", but hardly anything
from the other NA's.  This one doesn't have as many quotable
jewels, but a number of places that made you sit up and take
notice.  My favourite is:
"Ashes to nothing.  Dust to nothing.  Live fast, die young, and
leave a beautiful empty space where you used to be." (p220)

-------------------------------------------------------------

This story stood out because, as I said above, this is the first time
that the *Doctor* has been a victim.  There have been times when
he has been helpless to help others. There have been times when
he has been at the losing end, but he has been in control, able to
play for time.  There has even been the time, with the Timewyrm,
where half the time he hasn't been in control, but he has always
been playing his game, fencing with the enemy.  This time he couldn't
fence at all.  The quote from Nietzsche at the start is doubly
fitting now that I know what happened.  Because that's what happened.
He gazed into the Abyss, and became a monster.  This is a good
follow-on from The Dimension Riders, because the stakes have upped.
In The Dimension Riders, for the first time, the Doctor's clever
plan didn't work, and someone else's clever plan did.  He was
helped by someone else.  And in The Left-Handed Hummingbird,
the Doctor was up against something too big for him to handle;
he hardly had a plan at all (no great plan involves suicide...),
and that didn't work either.
The Doctor is so used to being more capable than everyone else
he meets, is he incapable of accepting help from others?  I mean
real help, not directed assistance to fight the enemy.  He got
into this trouble because he went looking for it.

Sid & Nancy scale: a thunderstorm wrapped in blue

-------------------------------------------------------------

*First Frontier*
================

an attempt at a spoiler-free review by Kathryn Andersen

So, here's the latest NA to pass through my hands.  I'm wondering if
the inverse-cover-rule applies to this one: the cover is great, the book
isn't.  But actually, the book was okay, even if not terrific.  I can
understand why the author said he did it for fun.  Strangely enough, it
picked up in the latter half of the book - or else I merely changed my
mood and decided I wanted to read it.

The Ace characterisation harked back to the earlier Ace - or perhaps I
was reminded of her because this was, in its own way, a sequel to
"Survival", and that part of it it did well.  I tip my hat to the author
that I did not suspect who Kreer really was until it was revealed, even
though enough clues were left around for someone more astute than I to
figure it out, maybe.  If I were more up with UFO-ology, I might also
tip my hat to the author about his UFO research, but I don't know enough
to know if he did it well.

Benny doesn't seem to have much to do, and the Doctor doesn't feature as
much as he might - there seems to be an abundance of supporting
characters being suspicious of each other, following orders, or being
victims.

It was readable, but I'm keeping it for the cover.  8-)

Sid & Nancy scale: a model kit of a flying saucer

-------------------------------------------------------------

*Falls The Shadow*
==================

reviewed by Kathryn Andersen

Well, I finally read this one, months after I got it.

I can see why someone compared this with "Strange England", though in
one sense, "Strange England" was more vividly horrible.  There was more
horror in those singing insects than there was in the two villains.  Yet
another NA with a surreal landscape.  I wonder if it's a requirement.
No, I don't *dislike* surreal landscapes, it's just that you start to
get weary of them when they happen a lot.  Which NA's *didn't* have a
surreal landscape in there somewhere?

Am I becoming jaded, or are the NAs all running into each other in
ordinariness?

Okay spoiler warning time.  Discussion time.

The cover didn't help.  Hard to think of Gabriel and Tanith as perfect
in beauty when the pictures of them on the cover weren't very beautiful
at all.  Gabriel and Tanith were just violent.  Continuously and
sadistically violent.

But the most interesting question, and here's for the discussion time:
who *is* the grey man?  I mean the author seems to be proposing a change
in the metaphysical nature of the Whoniverse, but there are several
things that don't make sense about it.

- Grey.  With white as Good and Black as Evil, Grey seems to style
himself as Doubt.  But on the other hand, he seems to style himself as
Chaos.  Now, I agree that Order and Chaos are neither good nor evil
(since things like Nazi dictatorships can be very evil and very
orderly).  But...  aw, I think part of my problem here is that I
disagree with the standing metaphysical order of the Whoniverse with the
Black and White Guardians being *equal* and opposite, so trying to slot
a Grey Guardian in there is adding to my confusion.  But still, I don't
really understand what he's supposed to stand for.  Doubt?  (and how
would doubt apply to Evil?) Chaos?  (and doesn't Evil want to create
chaos as well as order?) Freedom?  (but doesn't Good want to create
freedom?)

- His people.  Who are his people?  Are the Black Guardian and the White
Guardian of his people, or something else?  And if they are, then who
are the rest, or are there only three of them?  Who are they?

I think I had some more questions, but I can't remember what they were.

Kathryn Andersen
(now I can read Set Piece!  Yay!)

Later, on Thu, 30 Mar 1995...

Ah, I remember now.  The other query/problem I had with "Falls the Shadow".
And it was the most important one too.

#Whoniversal metaphysics warning#

#Falls The Shadow spoiler warning#

Okay, so Gabriel and Tanith were born out of the pain of the universe, a
wounding of the universe, the pain of destroyed potential futures, such as
the one that Jane Page came from.  And the Doctor felt guilty because such
pain was caused by him and other time travellers.  Am I right, or did I
completely miss what was happening?

Because, if that's the case, however poetically appealing it is, it doesn't
make any sense.  Because time travel isn't the only thing that destroys
potential futures.  If time travel was never invented, millions of
potential futures are destroyed every second, every time someone makes a
decision.  Is the author trying to tell me that the *natural* order of the
universe (that is, a universe supposing time travel had never been
invented, an untampered-with universe) causes a wounding of the universe?
Where is the logic in that, the design?

I am assuming that the Darvil-Evans structure of the Whoniverse is the one
that needs to be used: the one which sets the Doctor's Gallifrey way way
back in (to us) the past, which is actually the Present.  And the nature of
time travel is such that it is impossible to travel into the Past, into a
point before the Present (thus nobody goes back in time to have a chat to
Rassillon etc), but it is possible to travel into the future, but the act
of travelling into the future and observing and participating in it, makes
that future certain (or almost certain) to occur.  It crystalizes it, so to
speak. That there is only one universe; parallel universes take a great
deal of energy to create and they are only temporary.  It is not impossible
to change history, but it is difficult, destructive, and a very Bad Thing.

So, in all this, why is there pain at the wiping out of possible futures?
It's not as if they had a *right* to exist: there can be only one
history-of-the-universe in the end.  What exists, exists.  What might have
existed does *not* exist, and should not exist.

Is it because these potential futures were wiped out "sooner" than they
might have been?  Because the actions/decisions that wiped them out
happened before the Present moment actually arrived there?  But what does
"before" mean in that context?  We're talking about meta-time here,
and that's so hairy I think I'll leave it.

(sigh)

Sid & Nancy scale: a Ken Done painting

-------------------------------------------------------------

*Set Piece* by Kate Orman
=========================

Date - June 5th 1995

reviewed by Kathryn Andersen

The obvious book to compare "Set Piece" to would be the previous
excursion of Kate Orman into the realms of the New Adventures - "The
Left-Handed Hummingbird" (otherwise known in fannish shorthand as
"Hummer").  Oddly enough, I think "Set Piece" was both better and not as
good as Hummer.  Better, because I can think of not a thing to point to
that was a problem (on the other hand, maybe I just wasn't looking
carefully enough?).  Not as good simply because it wasn't the same kind
of rollercoaster ride that Hummer was, not as much of the sheer
*angstiness* that was in Hummer.  Not the same psychological torture -
here I was more worried about Ace than the Doctor.  But maybe that's
just that it's a different book.  And it would be only half a point
difference anyway.  I did really like Set Piece.  Action and
characterisation in even amounts, a few surprises, and a few
not-surprises.  8.5 or 9 out of 10.

This story is really Ace's story, not really surprising since this is
the book in which she is written out of the series.  The Doctor and
Benny have their parts to play, but Ace is the emotional heart of the
tale.  The three time travellers are cast adrift through history when a
rescue attempt goes awry, and the three have to survive in different
eras while *something* living in a crack in space-time preys on people
from the past, present and future.

Here, Ace is all alone, in the alien (to her) culture of Ancient Egypt,
with only her own resources to fall back on, surviving and waiting,
waiting, waiting for the Doctor to turn up and tell her the sneaky plan
he had been preparing all this while.  But the last time she saw the
Doctor, "Benny was stooped over the Doctor, frantically trying to get a
response out of him.  Blood was trickling from his mouth and nose,
sluggishly.  His eyes had flicked shut.  Ace wished she could tell Benny
that the Doctor was dead."  Isolated, despairing, Ace is in danger of
losing her soul, of making the worst mistake in her life...

Again, Kate Orman has sprinkled the work with sharp pieces of prose:
"Suddenly the Doctor did not walk up and say hello." (p50) about Ace's
loneliness.  "When you're short of everything except the enemy, you know
you're in combat." (p138) was another good example.  And touches of
humour here and there.  One might make a complaint, though, that the
Whoniverse is becoming cluttered with metaphysical constructs; previous
New Adventures have dream-encounters with Death and Time - here we meet
Pain, with the Doctor as Time's butterfly.  I guess that depends on how
much one enjoys symbolism.  There are some very good character moments -
for Ace and the Doctor particularly.  Ace faces herself, and the Doctor
wins by losing.

The plot as a whole comes together piece by piece, jumping about from
time and place (with a flashback and a red herring or two to stop it
from being too straightforward), becoming clearer as it goes along, and
tieing itself together very satisfactorily.  No megalomaniacs, no 'fixed
up in the last five minutes with the wave of a gizmo', and not even a
'I've been subtly planning this behind the scenes for months' which
tends to happen with the 7th Doctor.

The way in which Ace departs the series had me cheering.  I couldn't
have asked for a better way for her to go.  And I'd better not say any
more about that for fear of letting slip hints about what happens.

If you are reading the New Adventures at all, there are no excuses for
not reading this one, except perhaps putting it off until you've read
all the previous ones by Paul Cornell, Ben Aaronovich and Kate Orman.

Sid & Nancy scale: chocolate cake with ice cream

-------------------------------------------------------------------

*Sky Pirates* by Dave Stone
===========================

note on rec.arts.drwho on Thu Aug 17 1995 from kat

I only have two things to say about this NA:
1. I expect that persons will have similar attitudes towards this as they
had about The Highest Science.
2. It made *me* laugh.

Kathryn Andersen

(who hasn't read radw for months...)

Sid & Nancy scale: Mystery Science Theatre 3000

-----------------------------------------------------------------------

*The Room With No Doors* by Kate Orman
======================================

a rambling rave by Kathryn Andersen

Whee!  She did it again!  So I couldn't put it down, what's the
surprise in that?

First warning - ignore the back cover blurb.  It's misleading.  It
tells you too much about the wrong things.

Okay, what did we get?

The Zen - that was cool.

An angst-guilty Chris - of course since I haven't read an NA since...
too long - I don't know what he was referring back to, except that it's
presumably spoiled a previous NA, probably the one just before,
"Eternity Weeps", yes?

Fanboy-Joel returns!  And drops in a few fannish references, B5
included...  Not to mention references back to "Return of the Living
Dad" and "Sleepy".  Probably other ones that I missed, too.

And the Doctor... his torture is on the inside, this time.  Sort of.

Plus assorted "demons", legends, fighting, and codes of honour.  And how
many ways can one pronounce "Chris"?

And I love it how it all came together.  Practically driving us nuts
with not knowing what this ruddy pod *is*!  Even though every man and
his dog is fighting over it... typical, neh.  *And* of course, driving
us nuts wondering what the Room With No Doors is too.  And What Does It
All Mean?  Read the book, and find out.

Can a house stand, if it is divided among itself?  Can a Doctor stand,
if he is not at peace?  This does a bit of foreshadowing about the 8th
Doctor's genesis, which is cool too.  Hmmm, can you call it
foreshadowing if we all know what it is referring to already?

This is a happening book - and not a happening book.  The universe is
not at stake, but that just brings it down to a level we can
comprehend.  People.  There's certainly a lot of running around.  And a
lot of thinking, too.

Oh, look, I don't know how it compares with her others, I just enjoyed
it.  I liked it better than Sleepy, but then that was the one of
Kate's that I liked the least.

Oh, and now that R.J. Anderson's "Sacrifice" is now officially
quoted in an NA, I'll just have to mention that you'd better go off
and read all of
's
11th Doctor stories, too.
(Two of which appeared in
).

-------------------------------------------------------------------

*So Vile A Sin* by Ben Aaronvich and Kate Orman
===============================================

reviewed by Kathryn Andersen

They did it again!  Another one of those "Huh, what the hell is going
on?" books, from the now-team of Ben Aaronvich and Kate Orman, where it
*does* all make sense in the end.  And here, when we thought everything
was fine, we knew it couldn't be, because the book wasn't over yet.
And again, got to a point where one was thinking, "How on earth are they
going to get out of *this*?" and they did anyway.  Surely it must be hard
to think of yet more universe-threatening threats, and yet they did it.
And very sensibly, they put the body on page one.  Since everybody knew
she was dead already, might as well take advantage of that, and still
manage to leave us in suspense.

And of course, the in-jokes and past-adventures references - noticed
the Tara reference - sneaky!  And Kate(?) put in more "guns and frocks"
jokes, um, in-jokes. I dunno, I can't see a reference to guns and frocks
in Kate's books any more without smiling.

But the title *still* looks like an anagram to me.

A silver-dusted Rubic's Cube that someone does for you, on the Sid &
Nancy scale.

---------------------------------------------------------------------

*Lungbarrow* by Marc Platt
==========================

reviewed by Kathryn Andersen

Well, I had gotten the impression from comments by other people that I
would find this one confusing, that it would raise more questions than
it answered, but I don't think so.  It answered quite a few questions,
or, strictly speaking, dropped the broadest of hints, hints which
followed up the intriguing hints about the Doctor's past which had
been dropped in COLD FUSION.  Tied up quite a few loose ends, really.
It even explained the return of the sonic screwdriver!  In atmosphere, it
reminded me somewhat of STRANGE ENGLAND, but more, really, of GHOST LIGHT.

After I read this, I realized something about many of the New Adventures.
Much of the TV Who was dedicated to de-mystifying things.  Gods are just
aliens, faith as a weapon against haemeovores, human culture as a result
of alien interference, and so on.  But the New Adventures are bringing the
Mystery back - and I don't just mean making the Doctor more mysterious,
Leela's comment in LUNGBARROW about the Doctor notwithstanding.  All the
bits about Death and Time and Pain, the "gods" of Gallifrey, are bringing
back the Otherness (and I don't mean the Other!), bringing the Mythic into
Doctor Who.  And I like it.

Sid & Nancy scale: a giant's house

---------------------------------------------------------------------

*The Dying Days* by Lance Parkin
================================

reviewed by Kathryn Andersen

Here we are - the first of the New Adventures to feature the 8th
Doctor instead of the seventh; the end of an era, and the beginning of
a new one; ushered in by another on of the NA authors that I admire.

Whee!  This one was more slow-moving than the others I had read in my
recent Who-thon.  It was also more straightforward.  I was tempted to
complain that there wasn't enough of the Doctor and too much of Benny
(if one could really have too much of a well-written Benny), that I
didn't get to see the 8th Doctor shine in his own unique Doctorish way,
but I was wrong.  It just took a while, that's all.  I kept on looking
at the cover to remind myself of him.  I'm looking forward to the
BBCNA's simply because I want more 8th Doctor.  But don't let me give
you the impression that the Doctor and Benny are the only decent
characters there.  The Brigadier's there as well, and gets in his own
thoughtful moments.  Plus other supporting decent characters;
particularly the little bits with Doug and Oswald.  (grin) I have a
suspicion that there are some in-jokes there that I missed.  Oh well,
didn't stop me from enjoying it.  Particularly the end.

Sid & Nancy scale: roast beef

txt2html-2.53/tfiles/hyphens.txt000066400000000000000000000001111352116237600167350ustar00rootroot00000000000000Blah blah blah blah blah blah.  This paragraph has a hyphen-
ated word.

txt2html-2.53/tfiles/links.txt000066400000000000000000000001351352116237600164050ustar00rootroot00000000000000This is a test of txt2html.

testing txt2html in a header
----------------------------

nu?

txt2html-2.53/tfiles/links2.txt000066400000000000000000000022531352116237600164720ustar00rootroot00000000000000This is a test file with some bizzare lines

These get converted:

I'm going to ftp.howdy.com     yay!!
I'm going to abbaftp.howdy.com     yay!!
I'm going to ftpabba.howdy.com     yay!!
I'm going to abftpba.howdy.com     yay!!
I'm going to a_ftp_a.howdy.com     yay!!
I'm going to ***a_ftp_a.howdy.com***     yay!!

These are correctly not converted:

I'm going to 9bftpba.howdy.com     yay!!
I'm going to -bftpba.howdy.com     yay!!
I'm going to ***-bftpba.howdy.com***     yay!!

These test beginning and end of line conversions:

ftp.howdy.com     yay!!
I'm going to ftp.howdy.com
ftp.howdy.com

The same jazz but with www in the name:
 
These get converted:

I'm going to www.howdy.com     yay!!
I'm going to abbawww.howdy.com     yay!!
I'm going to wwwabba.howdy.com     yay!!
I'm going to abwwwba.howdy.com     yay!!
I'm going to a_www_a.howdy.com     yay!!
I'm going to ***a_www_a.howdy.com***     yay!!

These are correctly not converted:

I'm going to 9bwwwba.howdy.com     yay!!
I'm going to -bwwwba.howdy.com     yay!!
I'm going to ***-bwwwba.howdy.com***     yay!!

These test beginning and end of line conversions:

www.howdy.com     yay!!
I'm going to www.howdy.com
www.howdy.com

txt2html-2.53/tfiles/links3.txt000066400000000000000000000003041352116237600164660ustar00rootroot00000000000000This is a link with a sub-anchor in it.

(http://www.steelypips.org/nethack/id_faq.html#general)

This should not be bolded.

But #this# should be.  And  should
be linked.
txt2html-2.53/tfiles/links4.txt000066400000000000000000000002071352116237600164710ustar00rootroot00000000000000This is to test links with underscores in them.

http://rapidshare.com/files/78582195/Futurama_-_S05E01_-_Crimes_Of_The_Hot.part1.rar

txt2html-2.53/tfiles/list-2.txt000066400000000000000000000013371352116237600164040ustar00rootroot00000000000000Simple Unordered
----------------

This is just an unordered list.

  - Background to building a jump start/install server.
  - Extra setup required for district servers (Modem Ports)
  - Extra setup required for district servers (External Modems)

Simple Ordered
--------------

This is just an ordered list.

  1. First
  2. Second
  3. Third




Mixed Lists
-----------

This list is mixed.  Each ordered item contains an unordered list.

   1. Bureau Server
      - Sun Sparcstation 20
      - Dual processor upgrade
   2. Bureau Contingency Server
      - Sun Sparcstation 20
      - Dual processor upgrade
   3. PC access Server (read only)
       - Sun Sparcstation 5/110Mhz
       - 96Meg of RAM
       - 4 X SCSI SBUS cards


txt2html-2.53/tfiles/list-3.txt000066400000000000000000000003231352116237600163770ustar00rootroot00000000000000
some random text here.

* part 1
  1. blah
  2. blah blah...

some random text here.

* part 2
  1. blah
  2. blah blah...

some random text here.

* part 3
  1. blah
  2. blah blah...

some random text here.

txt2html-2.53/tfiles/list-4.txt000066400000000000000000000017411352116237600164050ustar00rootroot00000000000000Header
-----

* Item 1: works but looks ugly in text
      This is list item 1 which I will pad with asdashjk kjashdkajsh
   kjhaskjahs kajshkajsdh kajshkajshd
      This is another paragraph of list item 1 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

* Item 2: doesn't work but is readable as text

     This is list item 2 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

      This is another paragraph of list item 2 which I will pad with
   asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

* Item 3: does work and is readable as text

  This is list item 3 which I will pad with
  asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

  This is another paragraph of list item 3 which I will pad with
  asdashjk kjashdkajsh kjhaskjahs kajshkajsdh kajshkajshd

* Item 4:

  This item explains the 2 test cases below:

    1) This is case 1

    2) This is case 2

* Item 5: does indent to the previous level

txt2html-2.53/tfiles/list-5.txt000066400000000000000000000015561352116237600164120ustar00rootroot00000000000000Definition Lists
=================

A definition list comprises the following:

Term:
  The term part of a DL item is a word on a line by itself, ending
with a colon.
Definition:
  The definition part of a DL item is at least one paragraph following
the term.

  If one has more than one paragraph in the definition, the first line of
the next paragraph needs to be indented two spaces from where the term
starts, otherwise we don't know that it belongs to the definition.

This is a new, separate paragraph.

Mixed Lists
-----------

Yadda_Yadda:
  a) a meaningless term
  b) something which Fred Flinstone says
  c) something with lawn in it

Just to be clear, this is a paragraph.

* Here's some unordered things.
  Unordered:
    Something without order.
* Item 2 in the unordered list.

  Ordered:
    Something with order.

* This should be item 3 in the unordered list.

txt2html-2.53/tfiles/list-advanced.txt000066400000000000000000000045631352116237600200140ustar00rootroot00000000000000 
For Grand Falls E1 events (loss of service for a long time) huge
LOG files (200-300 thousand of lines) is a very typical and
complicating characteristics. Many process (SWERRs, TRAPs, INFOs,
etc) run in parallel and it is very important to understand what
caused what. I want to suggest some tips that can make easier
analysis of such log files.
 
1. First of all learn ALL logs AT THE BEGINNING of the event.
   It is very important to understand what process began first.
   You should understand the meaning of EVERY log here.
 
2. Unix tool awk could be very useful for logs files processing.
   Here are some simplest examples of its using.
 
 a) Cutting all logs of some definite type:

               awk '/PM189/,length < 2' inp_file > out_file
                       ^           ^
                       |           |
      Where:    Pattern in the   End condition
              first line of log  of log (empty string)
 
 b) Cutting all lines BEFORE lines with some pattern:
 
    awk '/INV CLASS/{print str;next}{str=$0}' inp_file > out_file
              ^          ^       ^      ^
       Where: |          |       |      |
              |     Output prev  |    Save full line
           Pattern     line    Go to
                              next line
 
 c) Cutting all lines TWO lines BEFORE lines with some pattern:
 
awk '/cp 35/{print str1;next}{str1=str;str=$0}' inp_file > out_file
 
 d) Prepare exec for site in the form: QDN dn
                                       QDN dn
                                       . . .
 
 awk '/  DN /{print "QDN " $8}' inp_file | sort | uniq > out_file
          ^                 ^
 Where:   |                 |
          |           Field number in line
   Selection pattern  that contains dn
 
3. If you need to answer question like that:
 
   "What dn's that appear in logs of type A appear in logs of type B
   too ?" (For example, how many dn's that appear in AUDT203 logs
   appear in logs of TPTSWER cp 35 - inter integrity lost ?)
 
   you could use the next procedure:
 
    a) Use 2a) for cutting all AUDT203 logs into one file and cp 35
       logs into another.
 
    b) Use 2d) for producing of sorted list of dn's from these two
       new files.
 
    c) Use tool comm in the form:
 
         comm dn_list1_file dn_list2_file > out_file
 
       and in the out_file you will see three columns - in the
       third one common dn's will appear.
txt2html-2.53/tfiles/list-custom.txt000066400000000000000000000004141352116237600175500ustar00rootroot00000000000000Testing Different Bullets
=========================

#) Is this an ordered list item?
#) Because somebody did something.
#) And added another!

And then we'll have an unordered list.

+ with a pluss
+ as the new bullet, man.
  - and another indent, why not?
+ bask up
txt2html-2.53/tfiles/list-styles.txt000066400000000000000000000037301352116237600175650ustar00rootroot00000000000000STRATEGISKA BESLUTSSTDSSYSTEM
==============================

Syfte
=====
Syftet med detta examensarbete r att studera vilka behov av beslutsunderlag som finns samt att i detta sammanhang underska vilka krav man br stlla p informationssystem fr beslutsstd.

Avgrnsningar
=============
Vi kommer endast att rikta in oss p stdet fr fretags strategiska beslut i samband med expansion p frmmande lnders marknader. Vi avser endast att studera dessa behov och krav ur beslutsfattarens synvinkel.

Innehll
========

* Mnniskan
	- Beslutsprocessen
	- Perception
		- Lshastighet
	- Hur tolkas informationen
	- Parametermngd

* Organisationen
	- Informationsfldet
	- Frndringar

* Marknaden
	- Hur ser dagens informationssystem ut?
	- Effektivitet
	- Dagens tillvgagngsstt

* Tekniken
	- Medium fr spridning
	- Statisk respektive dynamisk information
	- Databaser
	- Skerhet
		- Affrshemligheter
	- Agenter (robotar)


Bakgrund
========
I dagens samhlle av allt intensivare produktion av information och ven behov av information mste beslutsfattarna allt snabbare fatta viktiga beslut. Med marknadernas utveckling mot allt snabbare faktorrrelser p det internationella planet mste ven de strategiska besluten ofta fattas mycket snabbt. Man mste trots detta skaffa sig ett adekvat beslutsunderlag, vilket naturligtvis tar en viss tid, tid som man kanske inte har!

Beslutsfattare behver allts hjlp frn automatiserade verktyg. Frgor man stlls infr i detta sammanhang r bl.a. hur br beslutsunderlagen utformas och vilka krav br stllas p informationssystemen som frser beslutsfattarna med beslutsunderlagen.


Tillvgagngsstt
=================
Kvalitativ underskning genom intervjuer med fretags beslutsfattare p olika niver, frmst ansvariga fr internationella marknader.
Kvantitativ studie genom att underska vidtagna tgrder vi olika fretags etableringar utomlands, samt frska relatera dessa till de uppndda resultaten och sedan jmfra med hemmamarknaden.
txt2html-2.53/tfiles/list.txt000066400000000000000000000000371352116237600162410ustar00rootroot00000000000000 * foo
-------
 blah blah blah
txt2html-2.53/tfiles/mixed.txt000066400000000000000000000005431352116237600163760ustar00rootroot00000000000000This is an example of mixed input, with a list with what shouldn't be bold.

- The '#' character can be used to introduce comment lines. Comments and
   lines that are empty or contain only whitespace are ignored.
- Pipe characters and newlines within fields and '#' at the begin of the
   first field of an entry must be escaped with a backslash ('\').

txt2html-2.53/tfiles/news.txt000066400000000000000000000275231352116237600162530ustar00rootroot00000000000000From: force10ten@some.where.com (Force10Ten)
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 14 Jan 1996 02:03:01 -0500
Reply-To: force10ten@some.where.com (Force10Ten)

Because I'm looking for binoculars for use at the Olympic Games, I just
spent quite a bit of time talking about this very subject with Jim
Dougherty, Dave Myers, Jay Barrs and Dick Tone, all of whom have the
opinion that the really good binoculars show their stuff in twilight.  
Myers told me this story at the Bowhunting Trade Show.

He and his buddies were sheep hunting.   There were 5 or 6 guys.  One of
them told the others "there's a sheep in this hollow" several hundred
yards off.  It was dusk.   Nobody but this guy could see the sheep. 
Everybody had binoculars in the 100-300 dollar price range.  Except this
guy who had a set of Zeiss 10 x 50's.   As he passed the glasses around
every one of these guys could see the sheep perfectly clearly.   Nobody
could see it with the cheaper glasses.   

I chose a pair of Leica 10 x 42's for my task at the Olympics, which will
be to do TV and venue play by play coverage of archery.  I need to be able
to call the arrows in the head-to-head instantly.   These glasses are
perfect for the job, which will really involve several weeks of looking
through binoculars this year, what with test tournaments and my own
shooting.

My "A" list after shopping around is in the 700 to 1600 dollar price range
as follows:

1.  Leica 10 x 42
2.  Bausch & Lomb Elite 10 x 42
3.  Zeiss 10 x 42
4.  Svarovski
5.  Docter Optik

george t.

From: bowbuff@some.where.com (Bowbuff)
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 16 Jan 1996 06:37:05 -0500

Randy, just reread your question and it may be that the answers you
received didn't answer your question about 8 vs 10 power in low light. 
Considering magnification alone the higher the power the worse it is
likely to be in very low light.  More important is the "exit pupil" of the
binocs:   The second number divided by the first.  
For example a 10x50 binoc has an exit pupil of 5, the same as a 7x35 or
8x40.  This is the measure of light gathering ability of the unit. 
Ignoring power, quality of the optical elements, and lens coatings, an
e.p. of 5 is the optimum.  At least, I read somewhere that this is the
maximum the human eye can process.   All I know is that a top quality pair
of 10x50, 8x40, or 7x35 glasses will pick up more light at dark than you
can see with your naked eyes.  Seriously, I was watching two bull elk
fighting at dark in Rocky Mtn Nat'l Park and it became too dark to see
them although they were in the open only 75 yards away.  With my
Swarovskis I could watch them for about another half hour when I got tired
and gave up.  The higher the e.p. the larger the binocs are physically, of
course, as this means a bigger diameter exit lens and focal length as
well.

The lower the e.p., the worse your binocs will let you down in low light. 
This is why all the compacts are only useful during good light.  The
finest 8x24s or 10x25s will fit in your shirt pocket really neat....and
you'll soon be leaving them there unless it is the middle of the day...or
unless you really don't need to see very much.  

Optics and coatings are no less important for extended use, especially at
very long ranges in the daylight.  Unfortunately you cant sort this out by
looking through them in a store or looking down the street in front of a
store.  The best way is to take them-and all the others you can beg, bum,
or borrow out to the tallest mountain you know and compare them for hours,
especially as it gets dark.  The next best way is to follow the advice of
the Rocky Mountain Bighorn Society:  figure out what is the maximum you
can spend on the finest optics - and then spend 25% more!

Good Luck!

From: abqkelly@some.where.netcom.com(John Kelly )
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Warsaw Pact Binocs
Date: 16 Jan 1996 16:52:11 GMT

>Optics and coatings are no less important for extended use, especially
at
>very long ranges in the daylight.  Unfortunately you cant sort this
out by
>looking through them in a store or looking down the street in front of
a
>store.  

I had an opportunity to compare Leica, Swarkkkovyjowskiiskiskzsky,
Zeiss, and "Warsaw Pact" 8X50s last year at a Rockey Mt Elk Camp event.
You CAN make certain interesting and useful appraisals in that sort of
situation. For example, you can evaluate color and contrast. You can
look right into backlit areas, right at objects next to bright lights
in the trade show ceiling, and judge internal refraction, contrast, and
glare. IMHO the Leicas "looked" prettiest overall, I'd have loved a
pair, were I a successful cocaine dealer or Phil Gramm. 

But a bowhunting pal bought WARSAW PACT "cheapies" ($500..widely
advertised in hunting magazines) there, since they were MUCH brighter
(apparently the equivalent of maybe two f-stops) and more contrasty
than ANY of the others (not to mention, ahem, AFFORDABLE). They were
VASTLY SUPERIOR in those respects. 

In the woods I later found you can look into deep shadows and they are
lit as if they were video amplified. You can look directly into scenes
involving the setting sun and still see clearly, FAR better than with
the naked eye. 

There IS one BIG drawback: everything is a sickly greenish orange or
yellow. The damned things are color blind. Otherwise they are
exceptional at picking out shapes, movement etc under extremely
difficult lighting conditions. That is exactly what they were designed
for, of course, being military equipment, not bird watching equipment.
NOTHING looks pretty through them. Is that a sacrifice that makes
sense? Hmmm. Maybe that depends on your reasons for hunting. 

I've got Pentax and Nikon, under $200ea, and they have to fill the bill
for now. I'm waiting for money from heaven. Maybe I'll go for better
Nikons.

JK

From: Perry Ratcliff 
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: Sun, 14 Jan 96 07:36:28 PDT

> I plan on purchasing a new pair of binoculars next hunting season and 
> would like some help.  Let me know what you like or dislike.  Also can 
> anyone tell what difference I might expect between an 8X and 10X 
> binocular.  How does light conditions affect either one?
> 
I also have Swarovskis 10x50 but haven't used them for a couple of 
years because they are so heavy.  I'm now using Pentax 12x42 
binoculars and am extremely pleased with them.  They are very light
for the size and have good light gathering capabilities.  They are
nitrogen filled and have never fogged up on me.  I believe they cost
me around $300 and feel that they are an outstanding value.

If you are on a more modest budget there are some very good 
compact binoculars in the $150 range.  Make sure that they are
nitrogen filled to prevent fogging in the rain.  If you wear
glasses make certain that the binoculars have a long eye relief
or you will lose a lot of light through the binoculars.

Good Luck,

Perry

From: ap941@some.where.ysu.edu (Mark W. Thurm)
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 16 Jan 1996 17:07:13 GMT
Reply-To: ap941@some.where.ysu.edu (Mark W. Thurm)

>I plan on purchasing a new pair of binoculars next hunting season and 
>would like some help.  Let me know what you like or dislike.  Also can 
>anyone tell what difference I might expect between an 8X and 10X 
>binocular.  How does light conditions affect either one?

 
 I have a pair of Cabellas compacts, 8 power, nitrogen filled, long
eye relief. For the money ($100) they're a good deal (IMHO). I've
looked at Ziess, Swarvoski. Brunton, etc. and they were excellent
but with my constrants (married with children) my wife wouldn't
authorize er... I couldn't justfy the 6-10 times price diferential.

 A 10 power compact will not gather much light and will be harder to hold
steady. I hunt in the west and the 8x has worked well fo me.

MT

-- 
   
            It's not the bible that's filled with contradictions,
                 It's our brains that are filled with them.
                             J. Vernon McGee

Newsgroups: alt.archery
From: jwf20@some.where.ccc.amdahl.com (Jim Flenniken)
Subject: Re: Binocular Purchase - Advice
Date: Tue, 16 Jan 1996 18:14:09 GMT

Randy Ross  wrote:

>I plan on purchasing a new pair of binoculars next hunting season and 
>would like some help.  Let me know what you like or dislike.  Also can 
>anyone tell what difference I might expect between an 8X and 10X 
>binocular.  How does light conditions affect either one?

>Thanks.

>Randy

Bushnell makes a pair of 'glasses on' binoculars that are _excellent_
for those of us that wear glasses. the long eye-relief is a blessing
when scanning a field while wearing glasses and the price is about
$125. 

From: Alex Hoover 
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 16 Jan 1996 22:17:34 GMT

I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

Regards,
alex.hoover@some.where.com
Denver, CO

From: Alex Hoover 
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 16 Jan 1996 22:18:10 GMT

I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

Regards,
alex.hoover@some.where.com
Denver, CO

From: Alex Hoover 
Newsgroups: alt.archery
Subject: Re: Binocular Purchase - Advice
Date: 16 Jan 1996 22:18:19 GMT

I love my Pentax 10x24 UCF compact binocs.  Small and lightweight, so I don't
hesitate to take them everywhere.  They are with me 100% of the time that I
hunt.  Bigger binocs are nicer, but can get in the way (especially if primary
use will be while bowhunting).

In the Fall 95 issue of the Gander Mountain catalog, the 10x cost $155, the 8x
cost $140.

There's some kind of formula about exit pupil that give guidelines on best
magnification power.  The gist is that unless you have a very large objective
diameter (for the 10x24's, the objective is 24mm, which is relatively small),
light will be transmitted bettter with a lower magnification.  If I had it to
do over, I would buy the Pentax compact binocs again, but I would get an 8x24
instead of 10x24.  

Regards,
alex.hoover@some.where.com
Denver, CO

The following should be treated as mail quote, not as pre-formatted

> 1      more
> 2      more
> 3      more
> 4      more
> 5      more

Back to normal again. more and more, make it a long line, not a short one. 

> 1      more and more, make it a long line, not a short one. 
> 2      more and more, make it a long line, not a short one. 
> 3      more and more, make it a long line, not a short one. 

txt2html-2.53/tfiles/pre.txt000066400000000000000000000006011352116237600160510ustar00rootroot00000000000000## Test on pre-in-list

txt2html.pl -p 7 -pb 1

Here is an example bad file:

 1. text (should be translated as 
  • ) (there should be *no*  tag
at this point)
       preformatted text..
       ... and more 
     
 2. this *should* be translated as 
  • 

## Test on mail_quote-in-pre_explicit


    Here is the actuall file content. 
Maybe more lines.
> 1	 more
> 2	 more

    
txt2html-2.53/tfiles/pre2.txt000066400000000000000000000001711352116237600161350ustar00rootroot00000000000000This is a text file.

        The text file ends with a block of preformatted text.
        This is the end of the file.
txt2html-2.53/tfiles/punct.txt000066400000000000000000000015301352116237600164160ustar00rootroot00000000000000*Why do I keep on having these bright ideas?* Miles wondered as he
crawled through the service tunnel.  It gave him uncomfortable
flashbacks to the time he'd crawled through the ducting on Aslund
station.  Though at least this time he didn't have Gregor to worry
about.  No, just lizard things, and the Doctor.  Now there was an
unknown quantity.  Sharp, yes, and knew too much about the wrong things,
but... *You are supposed to be a good judge of character, Miles,* he
thought to himself.  *It's a bit late to be second-guessing now.*

Miles sat up straighter in the chair and checked the settings again.
The earbud in his ear had warmed to body-temperature, but it was still a
hard lump.  Part of him was gibbering *Aliens!  You're going to be
talking to aliens!* while another part of him was just getting
impatient, waiting for the Doctor to return.

txt2html-2.53/tfiles/robo.txt000066400000000000000000000026651352116237600162400ustar00rootroot00000000000000Type:     cmu.cs.robotics
Topic:    Robotics Seminar, Prof. John Canny, Friday Oct 11, 3:30, Adamson Wing, Baker Hall
Dates:    11-Oct-91
Time:     3:30
Place:    Adamson Wing, Baker Hall
PostedBy: me on 11-Oct-91 at 01:39 from H.GP.CS.CMU.EDU (Michael Erdmann)
Abstract: 


^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
         ***** Friendly Reminder:  Robotics Seminar Today!! *****
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

   Date:    11-Oct-91
   Time:    3:30 (Refreshments at 3:15)
   Place:   Adamson Wing, Baker Hall

			    RISC-Robotics

			      John Canny
			    U.C. Berkeley

   RISC in a robotics context stands for Reduced Intricacy in Sensing and
   Control.  But it shares the same philosophy as RISC computer design.
   The idea is to replace complicated manipulation and sensing steps with
   combinations of simple ones.  Industrial robotics research has focussed
   on anthropomorphism in the hope that once robots become sufficiently
   human-like, they will be able to solve all the tasks that they are
   currently incapable of doing.  This approach is seductive and has led
   researchers further and further away from the real problems that
   hinder the proliferation of robots in manufacturing.  The enthusiasm
   for robotics in industry which reached a peak in the mid 80's has all
   but disappeared after a protracted lack of progress on these problems.
txt2html-2.53/tfiles/sample.foot000066400000000000000000000001121352116237600166710ustar00rootroot00000000000000
    

    
KatSpace

    
txt2html-2.53/tfiles/sample.foot2000066400000000000000000000001131352116237600167540ustar00rootroot00000000000000
    

    
KatSpace

    
txt2html-2.53/tfiles/sample.txt000066400000000000000000000222501352116237600165500ustar00rootroot00000000000000txt2html/HTML::TextToHTML Sample Conversion

This sample is based hugely on the original sample.txt produced
by Seth Golub for txt2html.

I used the following options to convert this document:

     -titlefirst -mailmode -make_tables
     --custom_heading_regexp '^ *--[\w\s]+-- *$'
     --system_link_dict txt2html.dict
     --append_body sample.foot --infile sample.txt --outfile sample.html

This has either been done at the command line with:

	perl -MHTML::TextToHTML -e run_txt2html -- *options*

or using the script

	txt2html *options*

or from a (test) perl script with:
	
	use HTML::TextToHTML;
	my $conv = new HTML::TextToHTML();
	$conv->txt2html([*options*]);

======================================================================

From bozo@clown.wustl.edu
Return-Path: 
Message-Id: <9405102200.AA04736@clown.wustl.edu>
Content-Length: 1070
From: bozo@clown.wustl.edu (Bozo the Clown)
To: kitty@example.com (Kathryn Andersen)
Subject: Re: HTML::TextToHTML
Date: Sun, 12 May 2002 10:01:10 -0500

Bozo wrote:
BtC> Can you post an example text file with its html'ed output?
BtC> That would provide a much better first glance at what it does
BtC> without having to look through and see what the perl code does.

Good idea.  I'll write something up.

       -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

The header lines were kept separate because they looked like mail
headers and I have mailmode on.  The same thing applies to Bozo's
quoted text.  Mailmode doesn't screw things up very often, but since
most people are usually converting non-mail, it's off by default.

Paragraphs are handled ok.  In fact, this one is here just to
demonstrate that.

THIS LINE IS VERY IMPORTANT!
(Ok, it wasn't *that* important)


EXAMPLE HEADER
==============

Since this is the first header noticed (all caps, underlined with an
"="), it will be a level 1 header.  It gets an anchor named
"section_1".

Another example
===============
This is the second type of header (not all caps, underlined with "=").
It gets an anchor named "section_1_1".

Yet another example
===================

This header was in the same style, so it was assigned the same header
tag.  Note the anchor names in the HTML. (You probably can't see them
in your current document view.)  Its anchor is named "section_1_2". 
Get the picture?



                    -- This is a custom header --

You can define your own custom header patterns if you know what your
documents look like.



Features of HTML::TextToHTML
============================

 * Handles different kinds of lists
   1. Bulleted
   2. Numbered
      - You can nest them as far as you want.
      - It's pretty decent about figuring out which level of list it
        is supposed to be on.
        - You don't need to change bullet markers to start a new list.
   3. Lettered
      A. Finally handles lettered lists
      B. Upper and lower case both work
         a) Here's an example
         b) I've been meaning to add this for some time.
      C. HTML without CSS can't specify how ordered lists should be
        indicated, so it will be a numbered list in most browsers.
   4. Definition lists (see below)
 * Doesn't screw up mail-ish things
 * Spots preformated text

                 It just needs to have enough whitespace in the line.
        Surrounding blank lines aren't necessary.  If it sees enough
        whitespace in a line, it preformats it.  How much is enough?
        Set it yourself at command line if you want.

 * You can append a file automatically to all converted files.  This
   is handy for adding signatures to your documents.

 * Deals with paragraphs decently.

   Looks for short lines in the middle of paragraphs and keeps them
   short with the use of breaks (
    ).  How short the lines need to
   be is configurable.

   Unhyphenates split words that are in the middle of para-
   graphs.  Let me know if trailing punctuation isn't handled "prop-
   erly".  It should be.

   One can also have multi-paragraph list items, like this one.

 * Puts anchors at all headers and, if you're using the mail header
   features, at the beginning of each mail message.  The anchor names
   for headings are based on guessed section numbers.  
   - You can turn off this option too, if you don't like it.

 * Groks Mosaic-style "formatted text" headers (like the one below)

 * Can hyperlink things according to a dictionary file.
   The sample dictionary handles URLs like http://www.aigeek.com/ and
    and also shows how to do simpler
   things such as linking the word txt2html the first time it appeared.
 * One can also use the link-dictionary to define custom tags, for
   example using the star character to indicate *italics*.

 * Recognises and parses tables of different types:
   o DELIM: A table determined by delimiters.
   o ALIGN: No need for fancy delimiters, this figures out
     a table by looking at the layout, the spacing of the cells.
   o BORDER: has a nice border around the table
   o PGSQL: the same format as Postgresql query results.

 * Also with XHTML!  Turn on the --xhtml option and it will ensure that
   all paragraphs and list items have end-tags, all tags are in
   lower-case, and the doctype is for XHTML.

Example of short lines
----------------------

We're the knights of the round table
We dance whene'er we're able
We do routines and chorus scenes
With footwork impeccable.
We dine well here in Camelot
We eat ham and jam and spam a lot.

Example of varied formatting
----------------------------

If I want to *emphasize* something, then I'd use stars to wrap
around the words, *even if there were more than one*, *that's*
what I'd do.  But I could also _underline_ words, so long as
the darn thing was not a_variable_name, in which case I wouldn't
want to lose the underscores in something which thought it was
underlining.  Though we might want to _underline more than one word_
in a sentence.  Especially if it is _The Title Of A Book_.
For another kind of emphasis, let's go and #put something in bold#.
   But it doesn't even need to be that simple. Something which is *really
exciting* is coping with italics and similar things *spread across
multiple lines*.

Example of Long Preformatting
-----------------------------

(extract from Let It Rain by Kristen Hall)

	I have given, I have given and got none
	Still I'm driven by something I can't explain
	It's not a cross, it is a choice
	I cannot help but hear his voice
	I only wish that I could listen without shame

	Let it rain, let it rain, on me
	Let it rain, oh let it rain,
	Let it rain, on me

	I have been a witness to the perfect crime
	Wipe the grin off of my face to hide the pain
	It isn't worth the tears you cry
	To have a perfect alibi
	Now I'm beaten at the hands of my own game

	Let it rain, let it rain, on me
	Let it rain, oh let it rain,
	Let it rain, on me

Definition Lists
----------------

A definition list comprises the following:

Term:
  The term part of a DL item is a word on a line by itself, ending
with a colon.
Definition:
The definition part of a DL item is at least one paragraph following
the term.

  If one has more than one paragraph in the definition, the first line of
the next paragraph needs to be indented two spaces from where the term
starts, otherwise we don't know that it belongs to the definition.

Examples of Tables
------------------

ALIGN
~~~~~

Here is a simple ALIGN table:

    -e  File exists.
    -z  File has zero size.
    -s  File has nonzero size (returns size).

Here are some of the conditions of ALIGN tables:

  #Context:#  A table needs to be surrounded by blank lines.
   #Length:#  A table must contain at least two rows.
    #Width:#  A table must contain at least two columns.
  #Spacing:#  There needs to be at least two spaces between the columns,
              otherwise there might be some random paragraph which
              could have inter-word spacing that lined up by accident.
#Cell Size:#  If you have more than one line (as just above) then
              you will simply get empty cells where the other column is empty.
#Alignment:#  Alignment of cells is attempted to be preserved.

BORDER
~~~~~~

This is a table with a border.

	+---------+-----+
	| Food    | Qty |
	+---------+-----+
	| Bread   |   1 |
	| Milk    |   1 |
	| Oranges |   3 |
	| Apples  |   6 |
	+---------+-----+

PGSQL
~~~~~~

This is the same table like Postgresql would make it.

	 Food    | Qty 
	---------+-----
	 Bread   |   1 
	 Milk    |   1 
	 Oranges |   3 
	 Apples  |   6 
	(4 rows)

DELIM
~~~~~

A delimited table needs to have its delimiters at the start and end,
just to be sure that this is a table.

:Fred:Nurk:58:
:George:Washington:62:
:Mary:Quant:35:

And one can have almost any delimiter one wishes.

| Darcy, Fitzwilliam | hero    |
| Bennet, Elizabeth  | heroine |
| Wickham, George    | villain |

THINGS TO DO
============

There are some things which this module doesn't handle yet which
I would like to implement.

A. I would like to be able to preserve lettered lists, that is:
   a) recognise that they are letters and not numbers (which it already
      does)
   b) display the correct OL properties with CSS so as to preserve
      that information.

----------------------------------------

The footer is everything from the end of this sentence to the
 tag.

txt2html-2.53/tfiles/table-align.txt000066400000000000000000000005401352116237600174440ustar00rootroot00000000000000This is for testing a table which is regognised by its alignment.

	Fruit   Vegetable
       Banana   Carrot
        Apple   Celery

The following is not a table because there aren't enough spaces between
items.

Fred Nurk    ate
Mary Norton  slept
Hugh Jackman snarled

But this one is.

Fred  Nurk     ate
Mary  Norton   slept
Hugh  Jackman  snarled
txt2html-2.53/tfiles/table-border.txt000066400000000000000000000033711352116237600176340ustar00rootroot00000000000000+--------+-----------------------+----------+-------+
| Schema |         Name          |   Type   | Owner |
+--------+-----------------------+----------+-------+
| public | actor_episodes        | view     | kat   |
| public | actors                | table    | kat   |
| public | copyable              | view     | kat   |
| public | episode_recording     | view     | kat   |
| public | episodes              | table    | kat   |
| public | episodes_title_id_seq | sequence | kat   |
| public | pal_recordings        | view     | kat   |
| public | recordings            | table    | kat   |
| public | sorted_eps            | view     | kat   |
| public | tapes                 | table    | kat   |
| public | unrecorded            | view     | kat   |
| public | wanting               | view     | kat   |
+--------+-----------------------+----------+-------+

And the same table could be indented.

	+--------+-----------------------+----------+-------+
	| Schema |         Name          |   Type   | Owner |
	+--------+-----------------------+----------+-------+
	| public | actor_episodes        | view     | kat   |
	| public | actors                | table    | kat   |
	| public | copyable              | view     | kat   |
	| public | episode_recording     | view     | kat   |
	| public | episodes              | table    | kat   |
	| public | episodes_title_id_seq | sequence | kat   |
	| public | pal_recordings        | view     | kat   |
	| public | recordings            | table    | kat   |
	| public | sorted_eps            | view     | kat   |
	| public | tapes                 | table    | kat   |
	| public | unrecorded            | view     | kat   |
	| public | wanting               | view     | kat   |
	+--------+-----------------------+----------+-------+

txt2html-2.53/tfiles/table-delim.txt000066400000000000000000000021721352116237600174470ustar00rootroot00000000000000Delimited Table
===============

This one was a border table from which I removed the divider lines.

| Schema |         Name          |   Type   | Owner |
| public | actor_episodes        | view     | kat   |
| public | actors                | table    | kat   |
| public | copyable              | view     | kat   |
| public | episode_recording     | view     | kat   |
| public | episodes              | table    | kat   |
| public | episodes_title_id_seq | sequence | kat   |
| public | pal_recordings        | view     | kat   |
| public | recordings            | table    | kat   |
| public | sorted_eps            | view     | kat   |
| public | tapes                 | table    | kat   |
| public | unrecorded            | view     | kat   |
| public | wanting               | view     | kat   |

And this is a homegrown one.

:Fred:Nurk:lives:
:Kerr:Avon:is wonderfule:
::Servalan:has no first name:

And the next one has a caption, and a possibly tricky delimiter.

	     Actors
	& Paul & Darrow &
	& Jackie & Pierce &

Note that a CSV table doesn't work for delimiter stuff,
because it isn't *bounded* by commas.

Fred,Nurk
Joe,Schmoe
txt2html-2.53/tfiles/table-pgsql.txt000066400000000000000000000013421352116237600175010ustar00rootroot00000000000000                 List of relations
 Schema |         Name          |   Type   | Owner 
--------+-----------------------+----------+-------
 public | actor_episodes        | view     | kat
 public | actors                | table    | kat
 public | copyable              | view     | kat
 public | episode_recording     | view     | kat
 public | episodes              | table    | kat
 public | episodes_title_id_seq | sequence | kat
 public | pal_recordings        | view     | kat
 public | recordings            | table    | kat
 public | sorted_eps            | view     | kat
 public | tapes                 | table    | kat
 public | unrecorded            | view     | kat
 public | wanting               | view     | kat
(12 rows)

txt2html-2.53/tfiles/table-pgsql2.txt000066400000000000000000000653061352116237600175750ustar00rootroot00000000000000                              title                               |           sub_title            | title_id |   category   |          series_title          | episode_position | season | season_position | episode_code | wanting 
------------------------------------------------------------------+--------------------------------+----------+--------------+--------------------------------+------------------+--------+-----------------+--------------+---------
 Gathering, The                                                   |                                |      687 | SERIES       | Highlander                     |                1 | 1      |               1 |              | 
 Innocent Man                                                     |                                |      689 | SERIES       | Highlander                     |                2 | 1      |               2 |              | 
 Road Not Taken                                                   |                                |      694 | SERIES       | Highlander                     |                3 | 1      |               3 |              | 
 Bad Day In Building A                                            |                                |      677 | SERIES       | Highlander                     |                4 | 1      |               4 |              | 
 Free Fall                                                        |                                |      686 | SERIES       | Highlander                     |                5 | 1      |               5 |              | 
 Deadly Medicine                                                  |                                |      680 | SERIES       | Highlander                     |                6 | 1      |               6 |              | 
 Mountain Men                                                     |                                |      691 | SERIES       | Highlander                     |                7 | 1      |               7 |              | 
 Revenge Is Sweet                                                 |                                |      693 | SERIES       | Highlander                     |                8 | 1      |               8 |              | 
 Sea Witch, The                                                   |                                |      696 | SERIES       | Highlander                     |                9 | 1      |               9 |              | 
 Eye Witness                                                      |                                |      681 | SERIES       | Highlander                     |               10 | 1      |              10 |              | 
 Family Tree                                                      |                                |      683 | SERIES       | Highlander                     |               11 | 1      |              11 |              | 
 See No Evil                                                      |                                |      697 | SERIES       | Highlander                     |               12 | 1      |              12 |              | 
 Band of Brothers                                                 |                                |      678 | SERIES       | Highlander                     |               13 | 1      |              13 |              | 
 For Evil's Sake                                                  |                                |      684 | SERIES       | Highlander                     |               14 | 1      |              14 |              | 
 For Tomorrow We Die                                              |                                |      685 | SERIES       | Highlander                     |               15 | 1      |              15 |              | 
 Beast Below, The                                                 |                                |      679 | SERIES       | Highlander                     |               16 | 1      |              16 |              | 
 Saving Grace                                                     |                                |      695 | SERIES       | Highlander                     |               17 | 1      |              17 |              | 
 Lady and the Tiger, The                                          |                                |      690 | SERIES       | Highlander                     |               18 | 1      |              18 |              | 
 Avenging Angel                                                   |                                |      676 | SERIES       | Highlander                     |               19 | 1      |              19 |              | 
 Eye of the Beholder                                              |                                |      682 | SERIES       | Highlander                     |               20 | 1      |              20 |              | 
 Nowhere To Run                                                   |                                |      692 | SERIES       | Highlander                     |               21 | 1      |              21 |              | 
 Hunters, The                                                     |                                |      688 | SERIES       | Highlander                     |               22 | 1      |              22 |              | 
 Watchers, The                                                    |                                |      698 | SERIES       | Highlander                     |               23 | 2      |               1 |              | 
 Studies in Light                                                 |                                |     2820 | SERIES       | Highlander                     |               24 | 2      |               2 |              | 
 Turnabout                                                        |                                |     2821 | SERIES       | Highlander                     |               25 | 2      |               3 |              | 
 Darkness, The                                                    |                                |     2822 | SERIES       | Highlander                     |               26 | 2      |               4 |              | 
 Eye For An Eye                                                   |                                |     2823 | SERIES       | Highlander                     |               27 | 2      |               5 |              | 
 Zone, The                                                        |                                |     2824 | SERIES       | Highlander                     |               28 | 2      |               6 |              | 
 Return of Amanda, The                                            |                                |     2825 | SERIES       | Highlander                     |               29 | 2      |               7 |              | 
 Revenge of The Sword                                             |                                |     2826 | SERIES       | Highlander                     |               30 | 2      |               8 |              | 
 Run For Your Life                                                |                                |     2827 | SERIES       | Highlander                     |               31 | 2      |               9 |              | 
 Epitaph For Tommy                                                |                                |     2828 | SERIES       | Highlander                     |               32 | 2      |              10 |              | 
 Bless The Child                                                  |                                |     2829 | SERIES       | Highlander                     |               33 | 2      |              11 |              | 
 Fighter, The                                                     |                                |     2830 | SERIES       | Highlander                     |               34 | 2      |              12 |              | 
 Under Color of Authority                                         |                                |     2831 | SERIES       | Highlander                     |               35 | 2      |              13 |              | 
 Unholy Alliance (1)                                              |                                |     2832 | SERIES       | Highlander                     |               36 | 2      |              14 |              | 
 Unholy Alliance (2)                                              |                                |     2833 | SERIES       | Highlander                     |               37 | 2      |              15 |              | 
 Vampire, The                                                     |                                |     2834 | SERIES       | Highlander                     |               38 | 2      |              16 |              | 
 Warmonger                                                        |                                |     2835 | SERIES       | Highlander                     |               39 | 2      |              17 |              | 
 Pharaoh's Daughter                                               |                                |     2836 | SERIES       | Highlander                     |               40 | 2      |              18 |              | 
 Legacy                                                           |                                |     2837 | SERIES       | Highlander                     |               41 | 2      |              19 |              | 
 Prodigal Son                                                     |                                |     2838 | SERIES       | Highlander                     |               42 | 2      |              20 |              | 
 Counterfeit (1)                                                  |                                |     2839 | SERIES       | Highlander                     |               43 | 2      |              21 |              | 
 Counterfiet (2)                                                  |                                |     2840 | SERIES       | Highlander                     |               44 | 2      |              22 |              | 
 Samurai, The                                                     |                                |     2875 | SERIES       | Highlander                     |               45 | 3      |               1 |              | 
 Line of Fire                                                     |                                |     2876 | SERIES       | Highlander                     |               46 | 3      |               2 |              | 
 Revolutionary, The                                               |                                |     2877 | SERIES       | Highlander                     |               47 | 3      |               3 |              | 
 Cross of St. Antoine                                             |                                |     2878 | SERIES       | Highlander                     |               48 | 3      |               4 |              | 
 Rite of Passage                                                  |                                |     2879 | SERIES       | Highlander                     |               49 | 3      |               5 |              | 
 Courage                                                          |                                |     2880 | SERIES       | Highlander                     |               50 | 3      |               6 |              | 
 Lamb, The                                                        |                                |     2881 | SERIES       | Highlander                     |               51 | 3      |               7 |              | 
 Obsession                                                        |                                |     2882 | SERIES       | Highlander                     |               52 | 3      |               8 |              | 
 Shadows                                                          |                                |     2883 | SERIES       | Highlander                     |               53 | 3      |               9 |              | 
 Blackmail                                                        | Swords, Lies & Videotape       |     2884 | SERIES       | Highlander                     |               54 | 3      |              10 |              | 
 Vendetta                                                         |                                |     2885 | SERIES       | Highlander                     |               55 | 3      |              11 |              | 
 They Also Serve                                                  |                                |     2886 | SERIES       | Highlander                     |               56 | 3      |              12 |              | 
 Blind Faith                                                      |                                |     2887 | SERIES       | Highlander                     |               57 | 3      |              13 |              | 
 Song of the Executioner                                          |                                |     3002 | SERIES       | Highlander                     |               58 | 3      |              14 |              | 
 Star Crossed                                                     |                                |     3003 | SERIES       | Highlander                     |               59 | 3      |              15 |              | 
 Methos                                                           |                                |     3004 | SERIES       | Highlander                     |               60 | 3      |              16 |              | 
 Take Back the Night                                              |                                |     3005 | SERIES       | Highlander                     |               61 | 3      |              17 |              | 
 Testimony                                                        |                                |     3006 | SERIES       | Highlander                     |               62 | 3      |              18 |              | 
 Mortal Sins                                                      |                                |     3007 | SERIES       | Highlander                     |               63 | 3      |              19 |              | 
 Reasonable Doubt                                                 |                                |     3163 | SERIES       | Highlander                     |                0 | 3      |              20 |              | 
 Finale                                                           |                                |     3164 | SERIES       | Highlander                     |                0 | 3      |              21 |              | 
 Finale II                                                        |                                |     3165 | SERIES       | Highlander                     |                0 | 3      |              22 |              | 
 Homeland                                                         |                                |     3166 | SERIES       | Highlander                     |                0 | 4      |               1 |              | 
 Brothers In Arms                                                 |                                |     3167 | SERIES       | Highlander                     |                0 | 4      |               2 |              | 
 Innocent, The                                                    |                                |     3168 | SERIES       | Highlander                     |                0 | 4      |               3 |              | 
 Leader of the Pack                                               |                                |     3169 | SERIES       | Highlander                     |                0 | 4      |               4 |              | 
 Double Eagle                                                     |                                |     3170 | SERIES       | Highlander                     |                0 | 4      |               5 |              | 
 Reunion                                                          |                                |     3171 | SERIES       | Highlander                     |                0 | 4      |               6 |              | 
 Colonel, The                                                     |                                |     3172 | SERIES       | Highlander                     |                0 | 4      |               7 |              | 
 Reluctant Heroes                                                 |                                |     3173 | SERIES       | Highlander                     |                0 | 4      |               8 |              | 
 Wrath of Kali, The                                               |                                |     3174 | SERIES       | Highlander                     |                0 | 4      |               9 |              | 
 Chivalry                                                         |                                |     3175 | SERIES       | Highlander                     |                0 | 4      |              10 |              | 
 Timeless                                                         |                                |     3176 | SERIES       | Highlander                     |                0 | 4      |              11 |              | 
 Blitz, The                                                       |                                |     3177 | SERIES       | Highlander                     |                0 | 4      |              12 |              | 
 Something Wicked                                                 | Hakoya                         |     3261 | SERIES       | Highlander                     |                0 | 4      |              13 |              | 
 Deliverance                                                      | Leap of Faith                  |     3262 | SERIES       | Highlander                     |                0 | 4      |              14 |              | 
 Promises                                                         |                                |     3180 | SERIES       | Highlander                     |                0 | 4      |              15 |              | 
 Methuselah's Gift                                                |                                |     3426 | SERIES       | Highlander                     |                0 | 4      |              16 |              | 
 Immortal Cimoli, The                                             |                                |     3263 | SERIES       | Highlander                     |                0 | 4      |              17 |              | 
 Through a Glass Darkly                                           |                                |     3427 | SERIES       | Highlander                     |                0 | 4      |              18 |              | 
 Double Jeopardy                                                  |                                |     3453 | SERIES       | Highlander                     |                0 | 4      |              19 |              | 
 Till Death                                                       |                                |     3428 | SERIES       | Highlander                     |                0 | 4      |              20 |              | 
 Judgement Day                                                    |                                |     3429 | SERIES       | Highlander                     |                0 | 4      |              21 |              | 
 One Minute To Midnight                                           |                                |     3430 | SERIES       | Highlander                     |                0 | 4      |              22 |              | 
 Prophecy                                                         |                                |     3454 | SERIES       | Highlander                     |                0 | 5      |               1 |              | 
 End of Innocence, The                                            |                                |     3455 | SERIES       | Highlander                     |                0 | 5      |               2 |              | 
 Manhunt                                                          |                                |     3456 | SERIES       | Highlander                     |                0 | 5      |               3 |              | 
 Glory Days                                                       |                                |     3457 | SERIES       | Highlander                     |                0 | 5      |               4 |              | 
 Dramatic Licence                                                 |                                |     3458 | SERIES       | Highlander                     |                0 | 5      |               5 |              | 
 Money's No Object                                                |                                |     3459 | SERIES       | Highlander                     |                0 | 5      |               6 |              | 
 Haunted                                                          |                                |     3460 | SERIES       | Highlander                     |                0 | 5      |               7 |              | 
 Little Tin God                                                   |                                |     3461 | SERIES       | Highlander                     |                0 | 5      |               8 |              | 
 Messenger, The                                                   |                                |     3462 | SERIES       | Highlander                     |                0 | 5      |               9 |              | 
 Valkyrie, The                                                    |                                |     3463 | SERIES       | Highlander                     |                0 | 5      |              10 |              | 
 Comes A Horseman                                                 |                                |     3464 | SERIES       | Highlander                     |                0 | 5      |              11 |              | 
 Revelations 6:8                                                  |                                |     3465 | SERIES       | Highlander                     |                0 | 5      |              12 |              | 
 Ransom of Richard Redstone, The                                  |                                |     3466 | SERIES       | Highlander                     |                0 | 5      |              13 |              | 
 Duende                                                           |                                |     3467 | SERIES       | Highlander                     |                0 | 5      |              14 |              | 
 Stone of Scone, The                                              |                                |     3468 | SERIES       | Highlander                     |                0 | 5      |              15 |              | 
 Forgive Us Our Trespasses                                        |                                |     3469 | SERIES       | Highlander                     |                0 | 5      |              16 |              | 
 Modern Prometheus, The                                           |                                |     3470 | SERIES       | Highlander                     |                0 | 5      |              17 |              | 
 Archangel                                                        |                                |     3471 | SERIES       | Highlander                     |                0 | 5      |              18 |              | 
 Avatar                                                           |                                |     3624 | SERIES       | Highlander                     |                0 | 6      |               1 |              | 
 Armageddon                                                       |                                |     3625 | SERIES       | Highlander                     |                0 | 6      |               2 |              | 
 Sins of the Father                                               |                                |     3626 | SERIES       | Highlander                     |                0 | 6      |               3 |              | 
 Diplomatic Immunity                                              |                                |     3888 | SERIES       | Highlander                     |                0 | 6      |               4 |              | 
 Patient Number 7                                                 |                                |     3889 | SERIES       | Highlander                     |                0 | 6      |               5 |              | 
 Black Tower                                                      |                                |     3936 | SERIES       | Highlander                     |                0 | 6      |               6 |              | 
 Unusual Suspects                                                 |                                |     3904 | SERIES       | Highlander                     |                0 | 6      |               7 |              | 
 Justice                                                          |                                |     3905 | SERIES       | Highlander                     |                0 | 6      |               8 |              | 
 Deadly Exposure                                                  |                                |     3906 | SERIES       | Highlander                     |                0 | 6      |               9 |              | 
 Two of Hearts                                                    |                                |     3937 | SERIES       | Highlander                     |                0 | 6      |              10 |              | 
 Indiscretions                                                    |                                |     3938 | SERIES       | Highlander                     |                0 | 6      |              11 |              | 
 To Be                                                            |                                |     3939 | SERIES       | Highlander                     |                0 | 6      |              12 |              | 
 Not To Be                                                        |                                |     3940 | SERIES       | Highlander                     |                0 | 6      |              13 |              | 
 Highlander                                                       |                                |     3105 | MOVIE        | Highlander                     |                0 |        |               0 |              | 
 bloopers                                                         |                                |     3523 | SERIES       | Highlander                     |                0 |        |               0 |              | 
(121 rows)

txt2html-2.53/tfiles/umlauttest.txt000066400000000000000000000002731352116237600174770ustar00rootroot00000000000000Es geht darum, sie zu *verndern* zu *ndern* zu *ndern*.
Es geht darum, sie zu #verndern# zu #ndern# zu #ndern#.
Es _geht_ darum, sie zu _verndern_ zu _ndern_ zu _ndern_.

NDERN
txt2html-2.53/tfiles/utf8.txt000066400000000000000000000001461352116237600161550ustar00rootroot00000000000000Some UTF-8 characters
=====================

$ echo 門牌號碼規劃

Perhaps just tip of iceberg.