From e0c6872cf40896c7be36b11dcc744620f10adf1d Mon Sep 17 00:00:00 2001 From: Norbert Preining Date: Mon, 2 Sep 2019 13:46:59 +0900 Subject: Initial commit --- support/html2latex/HTML/COPYING | 339 +++++++ support/html2latex/HTML/Changes | 45 + support/html2latex/HTML/INSTALL | 15 + support/html2latex/HTML/Latex.pm | 1458 ++++++++++++++++++++++++++++ support/html2latex/HTML/MANIFEST | 17 + support/html2latex/HTML/Makefile.PL | 10 + support/html2latex/HTML/README | 64 ++ support/html2latex/HTML/README.win.txt | 16 + support/html2latex/HTML/TODO | 20 + support/html2latex/HTML/t/foreigns.correct | 7 + support/html2latex/HTML/t/foreigns.html | 1 + support/html2latex/HTML/t/foreigns.t | 20 + support/html2latex/HTML/t/tags.correct | 116 +++ support/html2latex/HTML/t/tags.gif | Bin 0 -> 2537 bytes support/html2latex/HTML/t/tags.html | 123 +++ support/html2latex/HTML/t/tags.png | Bin 0 -> 2481 bytes support/html2latex/HTML/t/tags.t | 19 + 17 files changed, 2270 insertions(+) create mode 100644 support/html2latex/HTML/COPYING create mode 100644 support/html2latex/HTML/Changes create mode 100644 support/html2latex/HTML/INSTALL create mode 100644 support/html2latex/HTML/Latex.pm create mode 100644 support/html2latex/HTML/MANIFEST create mode 100644 support/html2latex/HTML/Makefile.PL create mode 100644 support/html2latex/HTML/README create mode 100644 support/html2latex/HTML/README.win.txt create mode 100644 support/html2latex/HTML/TODO create mode 100644 support/html2latex/HTML/t/foreigns.correct create mode 100644 support/html2latex/HTML/t/foreigns.html create mode 100755 support/html2latex/HTML/t/foreigns.t create mode 100644 support/html2latex/HTML/t/tags.correct create mode 100644 support/html2latex/HTML/t/tags.gif create mode 100644 support/html2latex/HTML/t/tags.html create mode 100644 support/html2latex/HTML/t/tags.png create mode 100755 support/html2latex/HTML/t/tags.t (limited to 'support/html2latex/HTML') diff --git a/support/html2latex/HTML/COPYING b/support/html2latex/HTML/COPYING new file mode 100644 index 0000000000..a43ea2126f --- /dev/null +++ b/support/html2latex/HTML/COPYING @@ -0,0 +1,339 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc. + 675 Mass Ave, Cambridge, MA 02139, USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Library General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + Appendix: How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) 19yy + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, write to the Free Software + Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) 19yy name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + , 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Library General +Public License instead of this License. diff --git a/support/html2latex/HTML/Changes b/support/html2latex/HTML/Changes new file mode 100644 index 0000000000..acb53a1cb7 --- /dev/null +++ b/support/html2latex/HTML/Changes @@ -0,0 +1,45 @@ +Revision history for Perl extension HTML::Latex. + +1.0 Thurs Sep 14 11:38:12 MST 2000 + - removed invalids.t from testing and any log testing. It was + stupid to have it in there in the first place. + - added 'kill' type + - made SCRIPT into 'kill'. So, anything in SCRIPT /SCRIPT is + ignored. In other words, javascript is completely ignored now. + +0.9 Mon Aug 28 22:34:15 MST 2000 + - set_log now accepts IO::File objects or FileHandle objects. + - Added support for international characters. + - Added quote-expansion + - Added ability to pass a FileHandle to html2latex(). + - Added method parse_string(). + - ~ doesn't expand to $ENV{HOME} unless $ENV{HOME} exists. + +0.8 Thu Aug 17 00:32:36 2000 + - Changed handler routine paramater order and got rid of + $content_ref. + - Ported the conversion of images to ImageMagick + - Changed all calls to $html_element->content to + $html_element->content_list to deal with undef's (requires + HTML::Tree .68). + - Changed get_uri and store_uri a lot. + - Improved the information printed by &texify when using + $option{debug}. + - Tried to improve
 and  behavior.  I don't know what
+	to make it do.  It's sort of difficult.
+	- Fixed the 
  • bug. + - Added an HTML-style paragraph option (no indent and 1 line + paragraph spacing). + - Altered default behavior of \[sub]section to \[sub]section-. + - Changed call to texify from array of parents to single parent + (more efficient and also can check try attributes). + - Added the ban_tag option. + - Fixed "^" bug. + - Made relative local IMG sources work correcly. At least, I + hope. All this local/network absolute/relative crap is getting on + my nerves. It never seems to work correctly. + +0.01 Thu Aug 17 00:02:34 2000 + - original version; created by h2xs 1.20 with options + -XA -n HTML::Latex + diff --git a/support/html2latex/HTML/INSTALL b/support/html2latex/HTML/INSTALL new file mode 100644 index 0000000000..2abc3bae8a --- /dev/null +++ b/support/html2latex/HTML/INSTALL @@ -0,0 +1,15 @@ +Make sure before you do anything else that you install requirements. +See README for more information. After you're done with that try the +classic: + +perl Makefile.PL +make install + +That should just install it. Although, I recommend: + +perl Makefile.PL +make test +make install +make clean + +It's more safe (it's tested) and more clean (it's cleaned). diff --git a/support/html2latex/HTML/Latex.pm b/support/html2latex/HTML/Latex.pm new file mode 100644 index 0000000000..8b970f8485 --- /dev/null +++ b/support/html2latex/HTML/Latex.pm @@ -0,0 +1,1458 @@ +#!/usr/bin/perl -w +# HTML::Latex +# Copyright (C) 2000 Peter Thatcher + +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; either version 2 +# of the License, or (at your option) any later version. +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + +package HTML::Latex; +$VERSION = '1.1'; + +use strict; +# use warnings; +# use diagnostics; +use FileHandle; +use File::Path; +use File::Basename; +use Data::Dumper; +use Carp; +use vars qw($packages $heads $tags $options $pres $banned $LOG $VERSION %present); + +#extra +use HTML::TreeBuilder; +use XML::Simple; + +################### BEGIN DOCUMENTATIEN ##################### + +=head1 NAME + +HTML::Latex - Creates a Latex file from an HTML file. + +=head1 SYNOPSIS + + use HTML::Latex + + my $parser = new HTML::Latex($conffile); + $parser->set_option(\%options); + $parser->add_package(@packages); + $parser->ban_tag(@banned); + $parser->set_log($logfile); + + # Option 1: + foreach my $uri (@ARGV) { + my ($htmlfile,$latexfile) = $parser->html2latex($uri); + } + + # Option 2: + foreach my $uri (@ARGV) { + my $in = IO::File->new("< $uri"); + my $out = IO::File->new("> $uri.tex"); + $parser->html2latex($in,$out); + } + + # Option 3: + my $html_string = join("\n",<>); + my $tex_string = $parser->parse_string($html_string,1); + + # Option 4: + my $html_string = join("",@ARGV); + my $tex_string = $parser->parse_string($html_string); + +print $tex_string; + +=head1 DESCRIPTION + +This class is used to create a text file in Latex format from a file +in HTML format. Use the class as follows: + +1. Create a new HTML::Latex object. + +2. Override any options using set_option(), add_package(), ban_tag(), or set_log(). + +3. Run html2latex() on a file or URL. + +4. Do whatever you want with the filename that was returned. + +=head1 METHODS + +=over + +=item B<$p = HTML::Latex-Enew($conffile)> + +Creates a new HTML::Latex object. It parses the configuation file +$conffile to set attributes. The format of that file can be found in +the CONFIGURATION FILE section. + +Example: + + my $parser = HTML::Latex->new(); + +=item B<($htmlfile,$latexfile) = $p-Ehtml2latex($in,$out)> + +$in is any URL or filename or FileHandle. If it is a URL, it is +mirrored locally. The local location is returned as $htmlfile. The +method produces a Latex file $latexfile. + +Locally mirrored files are all stored in the "store" directory which +can be set with either set_option() or in the configuration file. See +B under the OPTIONS section for more details. + +A mirrored file will automatically be re-downloaded when the URL is +updated. If it has not been updated, html2latex() will use the local +file only. + +Also, html2latex() defaults to index.html when a file is not given. +For instance, if you used C, then the +url http://slashdot.org/index.html would be used. + +Example: + + my($htmlfile,$latexfile) = + $parser->html2latex('report01.html'); + + +=item B<$tex_string = $p-Eparse_string($html_string [,$full])> + +$html_string is an HTML string. $tex_string is a LaTeX string. If +$full is 0, then any and tags are ignored, and the +string is just plain tex. If $full is 1, then and tags +are implicitly added. Basically, it's a choice as to whether or not +$tex_string has a LaTeX preamble in it. + +=item Bset_option(\%options)> + +Sets on option. For a description of options, see the OPTION section +below. Returns an list of all the old values based on the keys of +%options. + +Example: + + $parser->set_option({border => 0, debug => 1}); + +=item B<$p-Eadd_package(@packages)> + +Adds packages to the list used by \usepackage{} in Latex. The +defaults are fullpage, graphicx, and url. + +Example: + + $parser->add_package('doublespace'); + +=item B<$p-Eadd_head(@heads)> + +Adds options to the list used by \documentclass[OPTIONS]{article} in +Latex. Font is automatically put there, so don't put it there +yourself. + +Example: + + $parser->add_head('twocolumn'); + +=item B<$p-Eban_tag(@banned)> + +Add @banned to the list of tags that html2latex() will ignore. This +overrides tag definitions in the configuration file. By default, the + tag is banned. That is because some people were using +
    , which can be really bad if both are parsed. + +Example: + + $parser->ban_tag('code'); + +=item Bset_log($logfile)> + +Have errors and messages printed to the filename or FileHandle or +IO::File $logfile. By default, things are printed to STDERR. +set_log() returns the FileHandle of the log file. + +Example: + + my $filehandle = $parser->set_log('report01.log'); + +=back + +=head1 CONFIGURATION FILE + +The configuration file is a very simple XML file. The root element is +. Nested inside are four tags: . + +=head2 tag + + has 2 attributes: I and I. Inside of is +nested zero to many tags. Each of these is described below. + +=over + +=item name + +The I attributes assigns the other values (I and I) +to an HTML tag of a certain name. + +=item type + +The type of a tag basically tells html2latex() how to handle it. +Internally, this assigns the tag to a certain handler. + +=item tex + +When handling a tag, html2latex must know what TeX string to replace +the HTML tags with. This is done with the use of tex +string. Different types require 0,1,or 2 such tags nested +inside of . You can think of tags as arguments to pass to +a I handler. Internally, that is what it is. + +Extraneous White space is ignored; do not rely upon it. \N is replaced +with newlines. Everything else is just as you type it. + +=head2 tag examples + +For a lot of examples, just look at the default configuration file, +html2latex.xml. We will go over 1 example in detail. This example is +for the HTML tag. + + + textbf + + +This text tells html2latex() to treat the tag as a TeX command. +It gives it the additional argument of 'textbf'. html2latex() will +call the command_handler('textbf') and the output will be \textbf{NESTED DATA}. + +=back + +=head2 package + +For each package_name given, package_name is added +to the list printed in the Latex file. For instance, the lines + + fullpage + graphicx + url + +adds the packages fullpage, graphicx, and url. The package 'fullpage' +is often recommended. + +=head2 head + +For each head given, head is added to the list of options +printed in the \documentclass command. For instance, the line + + twocolumn + +creates the command \documentclass[10pt,twocolumn]{article}. + +=head2 ban + + will make html2latex ignore a tag. For instance, the line + + code + +makes html2latex() ignore even though it has a definition in +the configuration file. This can be useful to turn on/turn off tags +when trying different configurations. + +=head2 options + +Inside of are a number of other tags. Each is described +below in OPTIONS. The value inside of a given +provides a default value that can be overridden with command-line +options. For instance, 10 will set the default font size +to 10. + +=head1 TYPES + +There are a number of different types of HTML tags support by +HTML::Latex. The list is: command, environment, single, other, table, +image, and ignore. Each are described below. TEX1 and TEX2 mean the +first and second value given by . NAME is given by the name +attribute. VALUE is the value nested within an HTML tag. + +=head2 command + + HTML Key: VALUE + HTML Example: Foo + TeX Key: \TEX1{VALUE} + TeX Example: \textbf{Foo} + +=head2 environment + + HTML Key: VALUE + HTML Example:
      Foo
    + TeX Key: \begin{TEX1} VALUE \end{TEX1} + TeX Example: \begin{enumerate} Foo \end{enumerate} + +=head2 single + + HTML Key: VALUE + HTML Example:
  • Foo + TeX Key: \TEX1 VALUE + TeX Example: \item Foo + +=head2 other + + HTML Key: VALUE + HTML Example:
    Foo + TeX Key: TEX1 VALUE TEX2 + TeX Example: \item[Foo] + +=head2 kill + + HTML Key: VALUE + HTML Example: + TeX Key: "" + TeX Example: "" + +This is of particular fun because any nested HTML tags are also ignored. Good for removing unwanted javascript. + +=head2 table + +This should be applied if and only if a tag is of type TABLE,TR, or TD. + +=head2 image + +This should be applied if and only if a tag is of type IMG. + +=head2 ignore + +Do nothing. Has the same affect as banning a tag. + +=head1 OPTIONS + +=over + +=item B + +"store" is the directory that mirrored files are stored in. It is +~/.html2latex by default. In side of this directory are +subdirectories representing the HOST in a URL and the path from that +HOST. For instance, if you used +C, it would store +the file as ~/.html2latex/slashdot.org/path/to/file.html. + +=item B + +This will force html2latex to use cached files if possible. It always +caches anyway, and uses the cached file if the network file has not +changed. This just forces the use of the local file if available. + +=item B + +Set the documentclass to use. Any valid latex document class is +valid. Examples are B, B, and B
    . B
    +is the default. If an invalid document class is used, the output +latex file will not compile. + +=item B + +True uses HTML-style paragraphs. They leave a newline between +paragraphs. False uses TeX-style paragraphs. They have no newline, +but indent the first line of every paragraph. Default is true. + +=item B + +Set the font size. Can be 10,11, or 12. Do not try anything else. +html2latex will not check it, but the latex file will not compile (at +least I think not). Default is 12. + +=item B + +Set the scale for images in the latex file. This is useful because +some images in HTML or much to big to fit on a page. Default is 1.0. +Scale can be any non-zero positive floating point number; large +numbers are not recommended. + +=item B + +True means table borders are on. False mean they are off. This is +always overridden by HTML attributes. + +=item B + +html2latex() will put a tex \mbox around all of the tables it creates. +I do not know why, but with a lot of tables (especially nested ones), +the tex and pdf output will work better. So, if you do not like your +output with tables, try this. True means on, false means off. +Default is false. + +=item B + +The bigger the number set, the more the debugging info printed. 0 +means things relevant to the user. 1 means things that trace some +code. 2 or greater means dumping data structures. + +=head1 Extending + +Extending HTML::Latex basically means making a new tag work. Usually, +this would call for writing a new handler. If a present handler will +suffice, then you can stip to the 3rd step. It's very simple to do so. +There are 3 easy steps: + +=head2 Write the function. + +Write a function (preferably ending in '_handler'). It's input is 1 +HTML::Element and several tex strings. The type of HTML::Element and +the value of the strings is set in the XML config file. Your furtions +responsibilty is to return a TeX string representing the HTML::Element +and all of it's children elements. + +The children are very easy to take care of. The string representing +the children elements is obtained by calling C. +So, the function really only has to worry about the current +HTML::Element. + +In particular, it must return that comes before and goes after the +string represting the current HTML::Element. So, if you wanted a +handler that print \TAG as the TeX for any in HTML and a special +TEX value given in the config file for , then the handler would +look like this: + + sub my_handler{ + my ($html_element,$tex) = @_; + return '\' . $html_element->tag() . texify($html_element) . $tex; + } + +In this example, one TEX parameter was passed in by the XML config +file. The handler return what comes before the children concatenated +with the texify-ed children texified with what comes after the +children. See the documentation for HTML::Element for all of the +things you can do with them. + +=head2 Assign a tag type to a handler. + +Just add an entry to %types below. It should have a type name as a +key and a reference to your handler as a value. Following our +example, we could add the line: + + "my_type" => \&my_handler, + +To %types. + +=head2 Add support in the configuration file. + +The format of the configuration file is in XML and can be found above +under CONFIGURATION FILE. The default XML file is at the bottom of +Latex.pm under __DATA__. Basically, for every tag you want to use your +new handler, use as follows: + + + TEX_PARAMATER + + +TAG_NAME is, of course, the tag name. "my_type" is the name of the +type you assigned your handler to. TEX_PARAMATER is the value that +gets placed under $tex in the example handler. + + +That's it. Now HTML::Latex should obey the new handler and behave +correctly. + +=head1 NOTES + +In you call html2latex() on several URLs any filename given after a +URL will continue to use the latest HOST given. Also, files default +to index.html, regardless of what the server thinks. So, if you use: + + html2latex(http://slashdot.org) + html2latex(foo.html) + html2latex(http://linuxtoday.net) + html2latex(bar.html) + +html2latex() will try to grab http://slashdot.org/index.html, +http://slashdot.org/foo.html, http://linuxtoday.net/index.html, and +http://linuxtoday.net/bar.html + +=head1 BUGS + +* Anything between and and
    is ignored. I do not + + +* Anything between
      or
        and
      • will not be ignored, but will + really mess Latex up. + +=cut + +################### END DOCUMENTATION ####################### + +################### BEGIN DEFENITIONS ####################### + +# Test what modules we can use +eval {require URI}; +$present{'URI'} = 1 unless $@; + +eval {require LWP::Simple}; +$present{'LWP::Simple'} = 1 unless $@; + +eval {require Image::Magick}; +$present{'Image::Magick'} = 1 unless $@; + +# The configuration file gives a "type" to each tag. This hash tells +# what functions to use on each type +my %types = ( + "command" => \&command_handler, + "environment" => \&environment_handler, + "single" => \&single_handler, + "ignore" => \&texify, + "other" => \&other_handler, + "kill" => sub {return ""}, + + "image" => \&image_handler, + "table" => \&table_handler, + "pre" => \&pre_handler, # Experimental; don't use + ); + +# Some characters typed in HTML need to be altered to be correct in +# Latex. These must be done this specific order All the foreign +# characters or special ascii characters that need to be altered. * +# next the comment means it doesn't really work or is faked. If it's +# commented out, that means it doesn't work at all. +my @specials = ( + ['' , '' ], #comments + ['\$' , '\$' ], + ['\\\\(?!\$)', "\$\\backslash\$"], #\ + ['<' , '$<$' ], + ['>' , '$>$' ], + ['&' , '\&' ], + ['%' , '\%' ], + ['#' , '\#' ], + ['{' , '\{' ], + ['}' , '\}' ], + ['_' , '\_' ], + ['\^' , '\^{}' ], + [chr(161), '!`' ], #¡ + #[chr(162), '' ], #¢* + [chr(163), '{\\pounds}' ], #£ + #[chr(164), '' ], #¤* + [chr(165), '{Y\hspace*{-1.4ex}--}'], #¥* + [chr(166), '$|$' ], #¦* + [chr(167), '{\\S}' ], #§ + [chr(168), '\\"{}' ], #¨ + [chr(169), '{\\copyright}' ], #© + [chr(170), '$^{\underline{a}}$'], #ª* + [chr(171), '<<' ], #« + [chr(172), '$\\neg$' ], #¬ + [chr(173), '$-$' ], #­ + #[chr(174), '' ], #®* + [chr(175), '$^-$' ], #¯ + [chr(176), '$^{\\circ}$' ], #° + [chr(177), '$\\pm$' ], #± + [chr(178), '$^2$' ], #² + [chr(179), '$^3$' ], #³ + [chr(180), '$^\\prime$' ], #´ + [chr(181), '$\\mu$' ], #µ + [chr(182), '{\P}' ], #¶ + [chr(183), '$\cdot$' ], #· + [chr(184), ',' ], #¸* + [chr(185), '$^1$' ], #¹ + [chr(186), '$^{\\underline{\\circ}}$'], #º* + [chr(187), '>>' ], #» + [chr(188), '$\frac{1}{4}$' ], #¼ + [chr(189), '$\frac{1}{2}$' ], #½ + [chr(190), '$\frac{3}{4}$' ], #¾ + [chr(191), '?`' ], #¿ + [chr(192), '\\`A' ], #À + [chr(193), '\\\'A' ], #Á + [chr(194), '\\^A' ], #A + [chr(195), '\\~A' ], #Ã + [chr(196), '\\"A' ], #Ä + [chr(197), '{\\AA}' ], #Å + [chr(198), '{\\AE}' ], #Æ + [chr(199), '\\c{C}' ], #Ç + [chr(200), '\\`E' ], #È + [chr(201), '\\\'E' ], #É + [chr(202), '\\^E' ], #Ê + [chr(203), '\\"E' ], #Ë + [chr(204), '\\`I' ], #Ì + [chr(205), '\\\'I' ], #Í + [chr(206), '\\^I' ], #I + [chr(207), '\\"I' ], #Ï + [chr(208), '{D\\hspace*{-1.7ex}-\\hspace{.9ex}}'], #Ð* + [chr(209), '\\~N' ], #Ñ + [chr(210), '\\`O' ], #Ò + [chr(211), '\\\'O' ], #Ó + [chr(212), '\\^O' ], #Ô + [chr(213), '\\~O' ], #Õ + [chr(214), '\\"O' ], #Ö + [chr(215), '$\chi$' ], #× + [chr(216), '{\\O}' ], #Ø + [chr(217), '\\`U' ], #Ù + [chr(218), '\\\'U' ], #Ú + [chr(219), '\\^U' ], #Û + [chr(220), '\\"U' ], #Ü + [chr(221), '\\\'Y' ], #Ý* + [chr(222), 'P' ], #Þ* + [chr(223), '"s' ], #ß + [chr(224), '\\`a' ], #á + [chr(225), '\\\'a' ], #à + [chr(226), '\\^a' ], #â + [chr(227), '\\~a' ], #ã + [chr(228), '\\"a' ], #ä + [chr(229), '\\r{a}' ], #å + [chr(230), '{\ae}' ], #æ + [chr(231), '\\c{c}' ], #ç + [chr(232), '\\`e' ], #é + [chr(233), '\\\'e' ], #è + [chr(234), '\\^e' ], #ê + [chr(235), '\\"e' ], #ë + [chr(236), '\\`{\i}' ], #ì + [chr(237), '\\\'{\\i}' ], #í + [chr(238), '\\^{\\i}' ], #î + [chr(239), '\\"{\\i}' ], #ï + [chr(240), '\\v{o}' ], #ð + [chr(241), '\\~n' ], #ñ + [chr(242), '\\`o' ], #ò + [chr(243), '\\\'o' ], #ó + [chr(244), '\\^o' ], #ô + [chr(245), '\\~o' ], #õ + [chr(246), '\\"o' ], #ö + [chr(247), '$\\div$' ], #÷ + [chr(248), '{\\o}' ], #ø + [chr(249), '\\`u' ], #ù + [chr(250), '\\\'u' ], #ú + [chr(251), '\\^u' ], #û + [chr(252), '\\"u' ], #ü + [chr(253), '\\\'y' ], #ý + [chr(254), 'p' ], #þ* + [chr(255), '\\"y' ], #ÿ + ); + +# complie matchings +foreach my $set (@specials) { + $set->[0] = qr|$set->[0]|; +} + +################### END DEFENITIONS ####################### + +# Paramaters for HANDLERs and SUBs are shown as and [N]. N is the +# number of the parameter, starting with 1. So, the first paramater +# would be <1>, the second <2>, and so on. means the paramater is +# mandatory. [N] means it is optional. + +##################### BEGIN METHODS ###################### + +# initializes options with optional configuration file +sub new { + my ($class,$conffilename) = @_; + + my $conffile; + if(defined($conffilename)){ + $conffile = IO::File->new("< $conffilename"); + } else { + $conffile = \*DATA; + } + + my $conf = XMLin($conffile,forcearray => ['tex','pre','ban']); + + # moved @banned from an array to a hash for fast lookup later + my $banned_ref = $conf->{ban}; + $conf->{ban} = {}; + foreach my $banned (@$banned_ref){ + $conf->{ban}{$banned}++; + } + + # make any refrences in @tex (see handlers below) to empty strings and new lines + # Ugly, I know. Perhaps XML::Simple is too simple. + foreach my $tag (keys %{$conf->{tag}}){ + foreach my $tex (@{$conf->{tag}{$tag}{tex}}){ #some derefrence, eh? + $tex = (ref($tex) ? '' : $tex); # {} => '' + $tex =~ s/\\N/\n/g; # \N => newline + # if it's a verbatim and not banned + push @{$conf->{pre}}, $tag if ($tex eq 'verbatim' && !$conf->{ban}{$tag}); + } + } + + #open logging files + $conf->{log} = $conf->{conf}{options} ? + FileHandle->new($conf->{options}{log},'w') : + \*STDERR; + + return bless $conf,$class; +} + +# converts html2latex using &texify. +# <1> The html filename or filehandle +# <2> optional second filehandle +sub html2latex { + my ($conf,$in,$out) = @_; + + #global to functions called below, which is what we want + local $packages = $conf->{package} || []; + local $heads = $conf->{head} || []; + local $tags = $conf->{tag} || {}; + local $options = $conf->{options} || {}; + local $banned = $conf->{ban} || {}; + local $pres = $conf->{pre} || {}; + local $LOG = $conf->{log}; + $options->{store} =~ s/^\s*~/$ENV{HOME}/ if exists $ENV{HOME}; + + print $LOG Dumper $conf if $options->{debug} > 1; + + #open files. + my($filenamein,$filenameout); + unless(ref $in and ref $out){ #filenhadles -- leave them alone. + ($in,$out,$filenamein,$filenameout) = open_files($in,1) if defined($in); + } + + #if you have a uri and it exists + #build the HTML tree + if($in && $out){ + my $tree = HTML::TreeBuilder->new; + $tree->warn(1); + my $result = $tree->parse_file($in); + + #here's where all the big magic happens + print $out &preamble_handler($tree->root); + + #destroy the HTML tree + $tree->delete; + + return ($filenamein,$filenameout) if ($filenamein && $filenameout); + return $result; #If you recieved filehandles, just return the return of $tree->parse + } else { + # print $LOG "You better give html2latex() a valid filename if you want it to do anything.\n"; + return; + } +} + +sub parse_string { + my ($conf,$input,$full) = @_; + return unless defined($input); + + local $packages = $conf->{package} || []; + local $heads = $conf->{head} || []; + local $tags = $conf->{tag} || {}; + local $options = $conf->{options} || {}; + local $banned = $conf->{ban} || {}; + local $pres = $conf->{pre} || {}; + local $LOG = $conf->{log}; + $options->{store} =~ s/^\s*~/$ENV{HOME}/ if exists $ENV{HOME}; + + print $LOG Dumper $conf if $options->{debug} > 1; + + my $tree = HTML::TreeBuilder->new; + $tree->warn(1); + $tree->parse($input); + + my $result; + if($full){ + $result = preamble_handler($tree->root); # Print whole file + } else { + $result = texify($tree->find_by_tag_name('body')); + } + $tree->delete; + + return $result; +} + +# set options for running html2latex +# <1> is a hash refrence of options +sub set_option { + my ($conf,$options) = @_; + my @old_values = (); + while(my ($key,$value) = each %$options){ + if(defined($value)){ + push @old_values, $conf->{options}{$key}; + $conf->{options}{$key} = $value; + } + } +} + +sub add_package { + my $conf = shift; + push @{$conf->{package}}, @_; +} + +sub add_head { + my $conf = shift; + push @{$conf->{head}}, @_; +} + +sub ban_tag { + my $conf = shift; + foreach my $banned (@_){ + $conf->{ban}{$banned}++; + } +} + +#set log file to $logfile +#return FileHandle to log file. +sub set_log { + my ($conf,$logfile) = @_; + if(ref $logfile){ + $conf->{log} = $logfile; + } else { + $conf->{log} = FileHandle->new($logfile,'w') or + die "FILE: Bad logfile: $logfile"; + } + return $conf->{log}; +} +##################### END HANDLERS ######################### + +##################### BEGIN HANDLERS ####################### + +# All HANDLERs are called like so: +# &HANDLER($html_element,@tex); + +# @tex is a list of latex strings $html_elmemnt is a node in the HTML +# tree. HTML::ELement man page for more on that. + +# Anyway, the comments for each HANDLER represent the starting HTML +# string and the output tex string. Anything inbetween HTML tags is +# recursivly texified by the big sub &texify, which then calls other +# HANDLERs. + +# HTML input form: Bar +# Latex output form: \command{bar} +sub command_handler{ + my($html_element,$command) = @_; + return "\\$command\{" . texify($html_element) . "\}\n"; +} + +# HTML input form: Bar +# Latex output form: tex1 bar tex2 +sub other_handler{ + my($html_element,@tex) = @_; + return $tex[0] . texify($html_element) . $tex[1]; +} + +# HTML input form: Bar +# Latex output form: \begin{tex} Bar \end{tex} +sub environment_handler{ + my($html_element,$environment) = @_; + return '\begin{' . $environment . '}' . "\n" . + texify($html_element) . "\n" . '\end{' . $environment . '}' . "\n"; +} + +# HTML input form: Bar (implicit end) +# Latex output form: \tex Bar +sub single_handler{ + my($html_element,$single) = @_; + return $single . " " . texify($html_element) . "\n"; +} + +# HTML input form:
         Bar 
        +# Latex output has all of the spaces made into hard spaces and +# newlines into hard newlines. It's the best I can do since latex +# doesn't want to respect whitespace. It's very experimental. One +# should really just use the verbatim environment, but what the heck, +# give people the option. +sub pre_handler{ + my($html_elemnt) = shift; + my $text = $html_elemnt->as_text; + + $text =~ s/[ ]/\\ /og; + $text =~ s/\n/\\\\\n/og; + + return $text; +} + +# Does a lot of work to create a table in latex format. +# It takes , , and
        . It works by finding those tags nested inside +# and then calling texify on them while keepind track of when to print +# latex syntax. It's messy, I know. Nested tables are completely +# ignored, and anything inside a table but not inside of a tag is +# also ignored. If anyone would like to improve this, that would be +# very cool. +# <3> The HTML::Element representing the table. It doesn't use +# $content_ref, so you don't really need it. + +sub table_handler{ + my($html_element,$tex) = @_; + my $output = ""; + if($tex eq "table"){ + # It's a table tag + $output = ($options->{mbox}? '\mbox{' : '') . + create_latex_table($html_element) . ($options->{mbox}? '}' : ''); + } else { + # It's a td or tr, let create_latex_table() take care of "\\" and "&" + # add the texified text inside + $output = texify($html_element); + } + return $output; +} + +# HTML input form: +# Latex output form: \includegraphic{bar.png} +# In also converts the image to a .png using "convert". +# <3> The HTML::Element representing the tag. It doesn't use +# $content_ref, so you don't really need it. +sub image_handler{ + my($html_element,$tex) = @_; + my $source = $html_element->attr('src') || ""; + my $scale = $html_element->attr('scale') || $options->{image}; + my $alt = $html_element->attr('alt') || ""; + + if($scale and my $image = convert_image($source,$scale)){ + # convert worked + return "\\$tex\[scale=$scale\]\{$image\} "; + } else { + #convert didn't work or images weren't selected. + print $LOG "IMG: Couldn't convert $source; using alt\n"; + print $LOG "\tRecieved <$image>\n" if $options->{debug}; + return $alt; + } +} + +# Prints the preamble. Not to extensize right now, but will become +# very extensive if I decide to parse stuff in the HEAD tag. +sub preamble_handler{ + my($html_element,$tex) = @_; + my $document_class = $html_element->attr('class') || $options->{document_class} || 'article'; + my $font_size = $html_element->attr('fontsize') || $options->{font_size} || 10; + my $output; + + $output .= join ('', + '\documentclass[', + join (",","${font_size}pt",@$heads), + ']{', + $document_class, + '}', + "\n", + '\usepackage{', + join(", ",@$packages), + '}', + "\n" + ); + $output .= join ('', + '\setlength{\parskip}{1ex}', + "\n", + '\setlength{\parindent}{0ex}', + "\n", + ) if $options->{paragraph}; + + $output .= texify($html_element); + + return $output; +} + +###################### END HANDLERS ####################### + + +# Takes in an array of HTML::Element-es which calls a handler on all of its +# children, which calls texify recursively, and eventually makes a +# string. + +sub texify { + my $parent_element = shift; + my $output = ""; + + foreach my $html_element ($parent_element->content_list){ + if(ref $html_element){ + # If this element is another HTML::Element + my $tag = $html_element->tag(); + print $LOG "\t" x ($html_element->depth - 1) . "<$tag> " if $options->{debug}; + + if(my $tag_hash_ref = $tags->{$tag} and !$banned->{$tag}){ + # If the tag is used with a handler and it isn't banned, use it. + my $handler_ref = $types{$tag_hash_ref->{type}} or + die "<$tag> needs a proper type (not $tag_hash_ref->{type})\n"; + my @tex = @{$tag_hash_ref->{tex} || []}; + print $LOG "is of type $tag_hash_ref->{type}: calling handler with \"" . + join(",",@tex) . "\"\n" if $options->{debug}; + $output .= $handler_ref->($html_element,@tex); + } else { + # Otherwise, just texify the contents; + print $LOG "has no type \n" if $options->{debug}; + $output .= texify($html_element); + } + } else { + # Otherwise, it's just a string + print $LOG "\t" x ($parent_element->depth + 1), $html_element if $options->{debug} > 1; + unless($parent_element->is_inside(@$pres)){ + #don't change any characters if inside a tag such as PRE. + #Quote expansion needs more finese. + $html_element =~ s/([^\s\[\{\(~])"/$1''/og; #" preceded by character not \s,[,{,or [ + $html_element =~ s/"/``/og; + foreach my $special (@specials){ + $html_element =~ s/$special->[0]/$special->[1]/g; + } + } + $output .= urlify($html_element); + } + } + return $output; +} + + +# opens necessary files +# <1> The base of the filename +sub open_files { + return unless (my $htmlfile = get_uri(@_)); + + #if filename has anything .*html, then remove the extension + my ($filename,$path,$suffix) = fileparse($htmlfile,'\.\w*html?'); + my $texfile = "$path$filename.tex"; + + check_for_previous_files($texfile); + + my $fh_in = FileHandle->new("< $htmlfile") or die "Can't open $htmlfile: $!"; + my $fh_out = FileHandle->new("> $texfile") or die "Can't open $texfile: $!"; + print $LOG "FILE: Processing $htmlfile and writing to $texfile\n"; + return ($fh_in,$fh_out,$htmlfile,$texfile); +} + +# checks for existance of file and moves it to name .old . +# <1> The filename +# [2] whether files should be renamed and overridden or just left alone. +# default is rename override +# returns whether the file exists or not +sub check_for_previous_files { + my $filename = shift; + my $override = shift || 1; + + if(-f $filename && $override){ + rename $filename, "$filename.old"; + print $LOG "FILE: renamed $filename $filename.old\n"; + } + return $filename; +} + +# checks for existance of file and prints that it successfully created it. +# <1> filename +# [2] error to print if didn't create; +sub check_for_current_files { + my $filename = shift; + if( -f $filename){ + print $LOG "FILE: Successfully created $filename\n"; + return $filename; + } + else{ + print $LOG "FILE: Failed to create $filename\n"; + return; + } +} +# Creates a latex table from an html table using the other table sub procedures. +# <1> The $html_element that is a table tag. +# Returns the table in latex string form +sub create_latex_table { + my $table = shift; + my $output; + my($latex_table_ref,$row_number,$column_number) = create_latex_table_def($table); + my $border = $table->attr('border') || $options->{border}; + + $output .= "\n\n" . '\begin{tabular}{' . $latex_table_ref . '}' . "\n"; + $output .= "\\hline \n" if $border; + + #pay attention to only the TR tags inside the TABLE tag. + my @rows = grep 'tr', $table->content_list; + foreach my $row (@rows){ + #pay attention to only the TD tags inside the TR tags. + my @columns = grep 'td', $row->content_list; + + for my $i (0 .. $column_number - 1){ + # Make Sure to fill in blank ones if necessary + my $column = $columns[$i]; + # Add the td data + $output .= texify($column) if $column; + # Add the puncation at the end if not the last one + $output .= (($i < $column_number -1)? " &" : ""); + } + + # Add the puncation at the end if not the last one + $output .= (($row->pindex() < $row_number -1 or $border)? " \\\\" : "") . "\n"; + $output .= " \\hline \n" if $border; + } + + $output .= "\n" . '\end{tabular}' . "\n\n"; + + return $output; +} + +# Based on the alignments of the rows, create a latex table defenition (i.e. "cccc") +# <1> The the number of columns the table has; +# <2> A refrence to an array with alignment defenitions +# <3> Whether it has a border or not; +# Returns the table definition, the number of columns and the number of rows +sub create_latex_table_def { + # get variables + my $table = shift; + my $border = $table->attr('border') || $options->{border}; + my ($row_number,$column_number) = find_table_lengths($table); + my @column_alignments = create_column_alignments($table); + + # define table_def + my $latex_table_def = ($border? "|" : ""); + for my $i (0 .. $column_number - 1){ + my $align = $column_alignments[$i]; + $latex_table_def .= ($align? ($border? $align . "|" : $align) : ($border? "c|" : "c")); + } + + return ($latex_table_def,$row_number,$column_number); +} + +# Finds the maximum number of columns that any row in a table has +# and also the number of rows it has. +# <1> the refrence to the HTML::Element table. +sub find_table_lengths { + my $table = shift; + #only care about TR children + my @rows = grep 'tr', $table->content_list; + my $max_row_length = 0; + foreach my $row (@rows){ + #only care about the TD children + my @columns = grep 'td', $row->content_list; + if(@columns > $max_row_length){ + $max_row_length = @columns; + } + } + + # row_number column_number + return (scalar(@rows),$max_row_length); +} + +# returns an array of column alignments +# <1> the refrence to the HTML::Element table. +sub create_column_alignments { + my $table = shift; + my @column_alignments; + #only care about TR children + my @rows = grep 'tr', $table->content_list; + if($rows[0]){ + #only care about the TD children + my @columns = grep 'td', $rows[0]->content_list; + foreach my $column (@columns){ + my $align = $column->attr('align'); + if($align and $align eq 'left'){ + $align = 'l'; + } elsif($align and $align eq 'right'){ + $align = 'r'; + } else { + $align = 'c'; + } + + push @column_alignments, $align; + } + } + + return @column_alignments; +} + + +# converts an image from jpeg or gif into png +# returns the name of the new filename is successfull +# <1> filename + +sub convert_image { + my $source = shift; + + my($absolute,$relative) = get_uri($source); + if ($absolute and $relative){ #If we can find the file + #if it successfully stores the file + my ($aname,$apath,$asuffix) = fileparse($absolute,'\.(gif|png|jpe?g)'); + my ($rname,$rpath,$rsuffix) = fileparse($relative,'\.(gif|png|jpe?g)'); + + if($asuffix eq '.gif' || $asuffix eq '.jpg' || $asuffix eq '.jpeg'){ # + # Picture is of a convertable type + if($present{'Image::Magick'}){ + # convert it with Image::Magick + require Image::Magick; + + my $aoutput = "$apath$aname.png"; #write to and return with png + my $routput = "$rpath$rname.png"; + my $image = Image::Magick->new(); + $image->Read("$absolute"); + $image->Write("$aoutput"); + undef $image; + + print $LOG "IMG: Converted $source to $routput\n"; + return $routput; + } else { + # No Image::Magick. Warn user and return nothing. + print $LOG "IMG: Can't convert $source without Image::Magick; using alt\n"; + return; + } + } elsif ($asuffix eq '.png'){ + # It's a PNG for sure. + my $routput = "$rpath$rname.png"; + return $routput; + } else { + # so, it's not a png,gif, or jpg. That means it's an invalid. + print $LOG "IMG: Invalid picture type: $source; using alt\n"; + return; + } + } else { + # We can't even get at the file. + return; + } +} + +# If the filename is really a URL, then go grab it, translate +# the name to the local file directory, and return that file name. +# Otherwise, just return the thing you got in. +# <1> is the URI +# [2] can specify to change the default host for subsiquent calls +# return ($absolute_path_to_file,$relative_path_to_file); +# The relative can be absolute itself (same as $absolute). +{ + #variables to stay the same across calls of get_uri. It's used in + #case we get image URLs with no host or scheme or path. + my $HOST = undef; #global value of current HOST + my $PATH = undef; #path inside host where we start + my $SCHEME = undef; #scheme originally used + + sub get_uri { + my ($uri,$absolute_local,$relative_local); + $uri = $absolute_local = $relative_local = shift; + print $LOG "looking for $uri\n" if $options->{debug}; + my $override = shift || 0; #absolute means that you replace $HOST and $PATH + + if(-f $uri){ + # it's an absolute local file. + $PATH = dirname($uri) if $override; + print $LOG "returning $uri\n" if $options->{debug}; + return ($uri,$uri); + } elsif(defined($PATH) && -f "$PATH/$uri") { + #it must be a local relative image + print $LOG "returning $PATH/$uri\n" if $options->{debug}; + return ("$PATH/$uri",$uri); + } elsif($uri =~ m|://|){ + #It's a full URL + + # Load necessary modules if you can. + unless($present{'URI'}) { + print $LOG "NEED: Can't handle request of $uri without module URI\n"; + return; + } + + require URI; + URI->import(); + + unless($present{'LWP::Simple'}) { + print $LOG "NEED: Can't handle request of $uri without module LWP::Simple\n"; + return; + } + + require LWP::Simple; + LWP::Simple->import(); + + $uri = new URI($uri); + my ($path,$filename) = ($uri->path =~ m|(.*/)(.*)|); + #replace the host,host_path, and scheme if it doesn't have a value and we're allowed to + + print $LOG "It's a full URL\n" if $options->{debug}; + if($override){ + $HOST = $uri->host; + $PATH = $path || '/'; + $SCHEME = $uri->scheme; + print $LOG "Setting HOST to $HOST, PATH to $PATH, and SCHEME to $SCHEME\n" if $options->{debug}; + } + + my $absolute = ($options->{store} || '.') . '/' . ($uri->host || "") . ($path || "/") . ($filename || "index.html"); + + if(store_uri($uri,$absolute)){ #Now, download the file. If it fails, return 0. + print $LOG "returning $absolute\n" if $options->{debug}; + return ($absolute,$absolute); + } else { + return; + } + } elsif(defined($HOST) && defined($SCHEME)){ + #It's a partial URL. + if($uri =~ m|^/|){ + #it's an absolute partial URL + my $absolute_uri = $SCHEME . '://' . $HOST . $uri; + $absolute_local = ($options->{store} || '.') . '/' . $HOST . $uri; + if(store_uri($absolute_uri,$absolute_local)){ #Now, download the file. If it fails, return nothing. + return($absolute_local,$absolute_local); + } else { + return; + } + } else { + #it's a relative partial URL + my $absolute_uri = $SCHEME . '://' . $HOST . $PATH . $uri; + $absolute_local = ($options->{store} || '.') . '/' . $HOST . $PATH . $uri; + if(store_uri($absolute_uri,$absolute_local)){ #Now, download the file. If it fails, return nothing. + return($absolute_local,$uri); + } else { + return; + } + } + } else { + print $LOG "FILE: Unable to access $uri\n"; + return; + } + } +} + +# store a URI as a local file, and create a path if necessary +# <1> The URI +# <2> The file to store it in +# returns the base of a filename +sub store_uri { + my ($uri,$localfile) = @_; + my ($name,$path) = fileparse($localfile); + + if(-f $localfile && $options->{cache}){ + #Use localfile if it's cached and caching is allowed + print $LOG "URI: Using $localfile for $uri. See -h to stop cacheing\n"; + return $localfile; + } else { + #Override localfile if new. + mkpath($path,1) if (head($uri)); + if (is_error(mirror($uri,$localfile))){ + print $LOG "URI: Unable to access $uri\n"; + return; + } else { + print $LOG "URI: Mirrored $uri in $localfile\n"; + return $localfile; + } + } +} + +# replaces URL with \url{URL}. This code is taken right from the Perl +# Cookbook, which I reccomend. Honestly, I'm not quite sure how it +# works; but, it does. +# <1> string to urlify. +{ + + # I think putting them here will prevent them from needing to be + # loaded into memory after each function call. + my $urls = '(http|telnet|gopher|file|wais|ftp)'; + my $ltrs = '\w'; + my $gunk = '/#~:.?+=&%@!\-'; + my $punc = '.:?\-'; + my $any = "${ltrs}${gunk}${punc}"; + sub urlify { + $_[0] =~ s!\b($urls:[$any]+?)(?=[$punc]*[^$any]|$)!\\url{$1}!igox; + return $_[0]; + } +} +1; #package must return true. +########################## END SUBS ############################# + +__DATA__ + + + + + + + textbf + + + document + + + \\ + + + quote + + + center + + + verbatim + + + + \N + + + description + + + \item[ + ] + + + emph + + + section* + + + subsection*7 + + + subsubsection* + + + textbf + + + textbf + + + textbf + + + \hline + + + emph + + + includegraphics + + + \item + + + enumerate + + + \N\N + + + verbatim + + + + textbf + + + table + + + tr + + + title + + + td + + + itemize + + + + + ~/.html2latex + 0 + article + 1 + 10 + 1 + 0 + 0 + 0 + + + + fullpage + graphicx + url + + + code + diff --git a/support/html2latex/HTML/MANIFEST b/support/html2latex/HTML/MANIFEST new file mode 100644 index 0000000000..f20fd7dafd --- /dev/null +++ b/support/html2latex/HTML/MANIFEST @@ -0,0 +1,17 @@ +Changes +COPYING +INSTALL +Latex.pm +Makefile.PL +MANIFEST +README +README.win.txt +TODO +t/tags.gif +t/tags.correct +t/tags.html +t/tags.png +t/tags.t +t/foreigns.html +t/foreigns.correct +t/foreigns.t \ No newline at end of file diff --git a/support/html2latex/HTML/Makefile.PL b/support/html2latex/HTML/Makefile.PL new file mode 100644 index 0000000000..c7b2b16b77 --- /dev/null +++ b/support/html2latex/HTML/Makefile.PL @@ -0,0 +1,10 @@ +use ExtUtils::MakeMaker; + +WriteMakefile( + 'NAME' => 'HTML::Latex', + 'VERSION_FROM' => 'Latex.pm', + 'PREREQ_PM' => { + XML::Simple => 1.04, + HTML::TreeBuilder => 2.97, + }, + ); diff --git a/support/html2latex/HTML/README b/support/html2latex/HTML/README new file mode 100644 index 0000000000..01747601f8 --- /dev/null +++ b/support/html2latex/HTML/README @@ -0,0 +1,64 @@ +====================================================================== + HTML::Latex +====================================================================== + +Summary +======= + +Converts properly formatted HTML files, filehandles, or strings to +LaTeX. It offers several options in processing, such a the ignoring +of tags, the configuration of the TeX, and downloading of URLs. It is +also much easier to extend than any other html2latex converter. + +License +======= + +It is available under the GPL by default. If you are faced with +license compatibility issues because of Perl's dual-license +configuration, I will _consider_ releasing it under the Artistic +License as well. Contact me at peterthatcher@asu.edu + +Requirements +============ + +For a convinient place for all of the following modules, look for +ftp://html2latex.sourceforge.net/html2latex/pub/. They won't be the +lastest ones, but they should work. + +html2latex requires the following perl modules: + *HTML::TreeBuilder + *XML::Simple + +html2latex can use, but does not require (I hope not, anway): + *LWP::Simple (called libwwwperl too) + *URI + *Image::Magik + +These are needed if you want to use URLs instead of just files, or if +you want to use images in your HTML that are not on your computer, but +are on the Internet + +Each of the modules may require further modules installed; check their +documentation to see. + +If you want a really easy way to install both of these, try typing +"perl -MCPAN -e shell" on the command line. This is a voodoo magic +interface to CPAN (Comprehensize Perl Archive Network). You will need +an internet connection running, and should be root to install as well. +Once their, type "install MODULE", where MODULE is the name of the +module you wish to install, such as HTML::TreeBuilder. For more info, +try "man CPAN". + +Documentation +============= + +All Documentation is in HTML::Latex.pm itself. The default +configuration file (in XML) is at the bottom of it under __DATA__. + + +Other +============= + +If you need a good example of how to use HTML::Latex, look for +html2latex at http://html2latex.sourceforge.net. It's why HTML::Latex +exists. diff --git a/support/html2latex/HTML/README.win.txt b/support/html2latex/HTML/README.win.txt new file mode 100644 index 0000000000..3bb25ac110 --- /dev/null +++ b/support/html2latex/HTML/README.win.txt @@ -0,0 +1,16 @@ +Special Instructions for Windows Users: +======================================= + +They only thing you really have to worry about beyond a regular UNIX +installation is: + +1) Use nmake instead of make. Or, if make is unavailable, you will + have to copy the modules by hand. To the correct perl library + directory. (c:\perl\site\lib if you are using ActiveState, for + instance). + +2) Change the "store" directory. This is where all web-mirrored files + will be stored. The location for the store directory is found in + the XML configuration file at the bottom of Latex.pm under +