Annotation of doc/help/texxml2latex.pl, revision 1.10

1.1       bowersj2    1: #!/usr/bin/perl
                      2: 
1.2       bowersj2    3: # The LearningOnline Network with CAPA
                      4: # Converts a texxml file into a single tex file
                      5: #
                      6: # Copyright Michigan State University Board of Trustees
                      7: #
                      8: # This file is part of the LearningOnline Network with CAPA (LON-CAPA).
                      9: #
                     10: # LON-CAPA is free software; you can redistribute it and/or modify
                     11: # it under the terms of the GNU General Public License as published by
                     12: # the Free Software Foundation; either version 2 of the License, or
                     13: # (at your option) any later version.
                     14: #
                     15: # LON-CAPA is distributed in the hope that it will be useful,
                     16: # but WITHOUT ANY WARRANTY; without even the implied warranty of
                     17: # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
                     18: # GNU General Public License for more details.
                     19: #
                     20: # You should have received a copy of the GNU General Public License
                     21: # along with LON-CAPA; if not, write to the Free Software
                     22: # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
                     23: #
                     24: # /home/httpd/html/adm/gpl.txt
                     25: #
                     26: # http://www.lon-capa.org/
                     27: #
                     28: # 7-16-2002 Jeremy Bowers
                     29: 
1.1       bowersj2   30: use strict;
                     31: use HTML::TokeParser;
                     32: use GDBM_File;
1.5       bowersj2   33: use File::Temp;
1.1       bowersj2   34: 
                     35: # accept texxml document on standard in
                     36: my $p = HTML::TokeParser->new( $ARGV[0] );
1.4       albertel   37: my $dirprefix = "../../loncom/html/adm/help/tex/";
1.1       bowersj2   38: 
1.10    ! albertel   39: my $include_filenames = ($ARGV[1] eq '--with-filenames');
1.5       bowersj2   40: # Make myself a temp dir for processing POD
                     41: my $tmpdir = File::Temp::tempdir('loncapahelpgenXXXXXXX', TMPDIR => 1);
                     42: 
1.1       bowersj2   43: # Print the header
                     44: open (LATEX_FILE, $dirprefix . "Latex_Header.tex");
                     45: print <LATEX_FILE>;
                     46: 
                     47: while (my $token = $p->get_token())
                     48: {
                     49:     my $type = $token->[0];
1.5       bowersj2   50:     if ($type eq 'S') {
1.1       bowersj2   51: 	my $tag = $token->[1];
                     52: 	my $attr = $token->[2];
1.5       bowersj2   53: 	if ($tag eq 'section') {
1.1       bowersj2   54: 	    my $title = $attr->{'name'};
                     55: 	    print "\\section{$title}\n\n";
                     56: 	}
                     57: 
1.5       bowersj2   58: 	if ($tag eq 'subsection') {
1.1       bowersj2   59: 	    my $title = $attr->{'name'};
                     60: 	    print "\\subsection{$title}\n\n";
                     61: 	}
                     62: 
1.5       bowersj2   63: 	if ($tag eq 'subsubsection') {
1.1       bowersj2   64: 	    my $title = $attr->{'name'};
                     65: 	    print "\\subsubsection{$title}\n\n";
                     66: 	}
                     67: 
1.5       bowersj2   68: 	if ($tag eq 'file') {
1.1       bowersj2   69: 	    my $file = $attr->{'name'};
1.9       bowersj2   70: 	    open (LATEX_FILE, $dirprefix . $file) or 
                     71: 		($! = 1, die "Can't find LaTeX file $dirprefix/$file; terminating build.");
1.10    ! albertel   72: 	    my $esc_file=$file;
        !            73: 	    $esc_file=~s/_/\\_/g;
        !            74: 	    if ($include_filenames) {
        !            75: 		print "\\textrm{File: \\bf $esc_file}\\\\\n";
        !            76: 	    }
1.1       bowersj2   77: 	    print <LATEX_FILE>;
1.3       bowersj2   78: 	    print "\n\n";
1.1       bowersj2   79: 	}
                     80: 
1.5       bowersj2   81: 	if ($tag eq 'tex') {
1.3       bowersj2   82: 	    print "\n\n";
1.1       bowersj2   83: 	    print $attr->{'content'};
1.3       bowersj2   84: 	    print "\n\n";
1.1       bowersj2   85: 	}
1.5       bowersj2   86: 
                     87: 	if ($tag eq 'pod') {
                     88: 	    my $file = $attr->{'file'};
1.8       bowersj2   89: 	    my $section = $attr->{'section'};	    
1.5       bowersj2   90: 	    if (!defined($section)) { $section = ''; }
1.6       bowersj2   91: 	    else { 
1.8       bowersj2   92: 		$section = "-section '$section'";
1.6       bowersj2   93: 	    }
1.8       bowersj2   94: 	    my $h1level = $attr->{'h1level'};
                     95: 	    if (!defined($h1level)) { $h1level = '2'; }
1.5       bowersj2   96: 	    $file = '../../loncom/' . $file;
1.8       bowersj2   97: 	    my $filename = substr($file, rindex($file, '/') + 1);
                     98: 	    system ("cp $file $tmpdir\n");
1.9       bowersj2   99: 	    my $latexFile;
                    100: 	    if (index($filename, '.') == -1) {
                    101: 		# pod2latex *insists* that either the extension of the
                    102: 		# file be .pl|.pm|.pod or that it be executable. Some
                    103: 		# extension-less files like "lonsql' are none-of-the-above.
                    104: 		system ("cd $tmpdir; mv $filename $filename.pm");
                    105: 		$filename .= ".pm";
                    106: 		print STDERR $filename . "\n";
                    107: 	    }
1.8       bowersj2  108: 	    system ("cd $tmpdir; pod2latex -h1level $h1level $section $filename\n");
1.9       bowersj2  109: 	    $latexFile = substr($filename, 0, rindex($filename, '.')) . '.tex';
                    110: 	    open LATEX_FILE, $tmpdir . '/' . $latexFile or
                    111: 		($! = 1, die "Latex file $latexFile not found while trying to use pod2latex, ".
                    112: 		 "terminating build");
1.7       bowersj2  113: 	    # pod2latex inserts \labels and \indexs for every section,
                    114: 	    # which is horrible because the section names tend to get
                    115: 	    # reused a lot. This filters those out, so we need to do
                    116: 	    # create our own indexes.
                    117: 	    for (<LATEX_FILE>) {
1.8       bowersj2  118: 		$_ =~ s/\\([^{]*)(section|paragraph)(\*?)\{([^\\]+)\\label\{[^\\]+\}\\index\{([^\\]+)\}\}/\\\1\2\3\{\4\}/g;
1.7       bowersj2  119: 		print $_;
                    120: 	    }
1.5       bowersj2  121: 	    print "\n\n";
                    122: 	}
1.1       bowersj2  123:     }
                    124: }
                    125: 
                    126: # Print out the footer.
                    127: open (LATEX_FILE, $dirprefix . "Latex_Footer.tex");
                    128: print <LATEX_FILE>;
1.5       bowersj2  129: 
                    130: # Remove the temp directory
                    131: system ("rm -rf $tmpdir");
1.8       bowersj2  132: 
                    133: __END__
                    134: 
                    135: =pod
                    136: 
                    137: =head1 NAME
                    138: 
                    139: texxml2latex.pl - core script that drives the help file assembly
                    140:   applications
                    141: 
                    142: =head1 SYNOPSIS
                    143: 
                    144: LON-CAPA's help system is based on assembling various pieces into
                    145: LaTeX files for conversion into printed documents. The various pieces
                    146: can also be used as online help.
                    147: 
                    148: =head1 OVERVIEW
                    149: 
                    150: X<help system, overview>LON-CAPA's help system is based on the idea of
                    151: assembling various pieces as needed to create documents for printing,
                    152: and using these various pieces for online help. LaTeX is the primary
                    153: language of the help system, because we can easily convert it to HTML,
                    154: and it makes the nicest printed documents.
                    155: 
                    156: The scripts for the help system are stored in /docs/help in the CVS
                    157: repository.
                    158: 
                    159: =head2 Data Sources
                    160: 
                    161: The help system can draw from the following sources to create help
                    162: documents:
                    163: 
                    164: =over 4
                    165: 
                    166: =item * B<LaTeX fragments>: LaTeX fragments stored in
                    167: C</loncom/html/adm/help/tex> in the CVS repository (which end up in
                    168: C</home/httpd/html/adm/help/tex>). A "LaTeX fragment" is a file that
                    169: contains LaTeX-style markup, but is not a complete LaTeX file with
                    170: header and footer.
                    171: 
                    172: =item * B<perl POD documentation>: POD documentation may be extracted
                    173: from perl modules used in LON-CAPA, using the syntax described in
                    174: podselect's man page.
                    175: 
                    176: =back
                    177: 
                    178: =head2 Online Help
                    179: 
                    180: The online aspect of the help system is covered in the documentation
                    181: for loncommon.pm; see L<Apache::loncommon>, look for
                    182: C<help_open_topic>.
                    183: 
                    184: Online help can only come from LaTeX fragments.
                    185: 
                    186: Access to the printed documents is partially provided online by
                    187: rendering the help files structure in a way that allows the user to
                    188: click through to the underlying help files; see 
                    189: L<http://msu.loncapa.org/adm/help/author.manual.access.hlp> for an
                    190: example. It's not very good, but it's marginally better then nothing.
                    191: 
                    192: =head2 Offline Documents 
                    193: 
                    194: Offline documents are generated from XML documents which tell a
                    195: rendering script how to assemble the various LaTeX fragments into a
                    196: single LaTeX file, which is then rendered into PostScript and PDF
                    197: files, suitable for download and printing. 
                    198: 
                    199: =head1 texxml And Rendering texxml
                    200: 
                    201: =head2 texxml 
                    202: 
                    203: X<texxml>
                    204: texxml is a little XML file format used to specify to the texxml2*.pl
                    205: scripts how to assemble the input sources into LaTeX documents. texxml
                    206: files end in the .texxml extension, and there is one texxml file per
                    207: final rendered document.
                    208: 
                    209: The texxml format is as follows: There is a root <texxml> element,
                    210: with no attributes and the following children:
                    211: 
                    212: =over 4
                    213: 
                    214: =item * B<title>: The B<name> attribute of this tag is used as the
                    215:    title of the document in texxml2index.pl; it is ignored in 
                    216:    texxml2latex.pl. If you don't intend to offer online-access
                    217:    to the rendered documents this may be skipped.
                    218: 
                    219: =item * B<section>, B<subsection>, and B<subsubsection>: These create
                    220:    the corresponding environments in the output file. The B<name>
                    221:    attribute is used to determine the name of the section.
                    222: 
                    223: =item * B<file>: The C<name> attribute specifies a LaTeX fragment by
                    224:    filename. The file is assumed to be located in the
                    225:    C<loncom/html/adm/help/tex/> directory in the CVS repository. The
                    226:    C<.tex> is required.
                    227: 
                    228: =item * B<tex>: The contents of the B<content> attribute are directly
                    229:    inserted into the rendered LaTeX file, followed by a paragraph
                    230:    break. This is generally used for little connective paragraphs in
                    231:    the documentation that don't make sense in the online help. See
                    232:    C<author.manual.texxml> for several example usages.
                    233: 
                    234: =item * B<pod>: The B<file> attribute specified a file to draw the POD
                    235:    documentation out of. The B<section> attribute is a section
                    236:    specification matching the format specified in the man page of
                    237:    podselect. By default, all POD will be included. The file is
                    238:    assumed to be relative to the C<loncom> directory in the CVS
                    239:    repository; you are allowed to escape from that with .. if
                    240:    necessary. The B<h1level> attribute can be used to change 
                    241:    the default depth of the headings; by default, this is set to 2,
                    242:    which makes =head1 a "subsection". Setting this higher can allow
                    243:    you to bundle several related pod files together; see 
                    244:    developer.manual.texxml for examples.
                    245: 
                    246: =back
                    247: 
                    248: texxml2latex.pl will automatically include C<Latex_Header.tex> at the
                    249: beginning and C<Latex_Footer.tex> at the end, to make a complete
                    250: document LaTeX document.
                    251: 
1.9       bowersj2  252: =head2 Rendering texxml 
1.8       bowersj2  253: 
1.9       bowersj2  254: =head3 render.texxml.pl 
1.8       bowersj2  255: 
1.9       bowersj2  256: X<texxml, rendering>X<render.texxml.pl>The C<render.texxml.pl> script
                    257: takes a .texxml file, and produces PostScript and PDF files. The LaTeX
                    258: files will be given access to .eps files in the
                    259: C</loncom/html/adm/help/eps/> directory while rendering. Call it as
                    260: follows, from the C<doc/help> directory:
1.8       bowersj2  261: 
                    262:  perl render.texxml.pl -- author.manual.texxml
                    263: 
                    264: substituting the appropriate texxml file.
                    265: 
1.9       bowersj2  266: =head3 texxml2latex.pl 
1.8       bowersj2  267: 
1.9       bowersj2  268: X<texxml2latex.pl>texxml2latex.pl is a perl script that takes texxml in and assembles
1.8       bowersj2  269: the final LaTeX file, outputting it on stout. Invoke it as follows:
                    270: 
                    271:  perl texxml2latex.pl author.manual.texx
                    272: 
                    273: Note that there is no error handling; if the script can not find a
                    274: .tex file, it is simply ignored. Generally, if a file is not in the
                    275: final render, it either could not be found, or you do not have
                    276: sufficient permissions with the current user to read it.
                    277: 
1.9       bowersj2  278: =head3 texxml2index.pl 
1.8       bowersj2  279: 
1.9       bowersj2  280: X<texxml2index.pl>texxml2index.pl is a perl script that takes texxml in and assembles a
1.8       bowersj2  281: file that can be used online to access all the .tex files that are
                    282: specified in the .texxml file. For an example of how this looks
                    283: online, see
                    284: C<http://msu.loncapa.org/adm/help/author.manual.access.hlp>.
                    285: 
                    286: =head2 texxml support
                    287: 
                    288: There are a couple of scripts that you may find useful for creating
                    289: texxml-based help:
                    290: 
1.9       bowersj2  291: =head3 latexSplitter.py 
1.8       bowersj2  292: 
1.9       bowersj2  293: X<latexSplitter.py>latexSplitter.py is a Python script that helps you seperate a
1.8       bowersj2  294: monolithic .tex file into the small pieces LON-CAPA's help system
                    295: expects. Invoke it like this:
                    296: 
                    297:  python latexSplitter.py monolithic.tex
                    298: 
                    299: where C<monolithic.tex> is the .tex file you want to split into
                    300: pieces. This requires Python 2.1 or greater (2.0 may work); on many
                    301: modern RedHat installs this is installed by default under the
                    302: executable name C<python2>.
                    303: 
                    304: Use the program by highlighting the desired section, give it a file
                    305: name in the textbox near the bottom, and hit the bottom button. The
                    306: program will remove that text from the textbox, and create a file in
                    307: the C<loncom/html/adm/help/tex/> directory containing that LaTeX. For
                    308: consistency, you should use underscores rather then spaces in the
                    309: filename, and note there are a few naming conventions for the .tex
                    310: files, which you can see just by listing the
                    311: C<loncom/html/adm/help/tex/> directory.
                    312: 
                    313: The idea behind this program is that if you are writing a big document
                    314: from scratch, you can use a "real" program like LyX to create the .tex
                    315: file, then easily split it with this program.
                    316: 
1.9       bowersj2  317: =head3 simpleEdit.py 
1.8       bowersj2  318: 
1.9       bowersj2  319: X<simpleEdit.py>simpleEdit.py is a python script that takes a .texxml file and shows
1.8       bowersj2  320: all the tex files that went into in sequence, allowing you to "edit"
                    321: the entire document as one entity. Note this is intended for simple
                    322: typo corrections and such in context, not major modification of the
                    323: document. Invoke it with 
                    324: 
                    325:  python simpleEdit.py author.manual.texxml
                    326: 
                    327: Make your changes, and hit the "Save" button to save them.
                    328: 
                    329: =head2 texxml LaTeX Feature Support
                    330: 
                    331: =head3 Cross-referencing
                    332: 
                    333: LaTeX has a cross-referencing system build around labeling points in
                    334: the document with \label, and referencing those labels with \ref. In a
                    335: complete LaTeX document, there's no problem because all \refs and
                    336: \labels are present. However, for the online help, \ref'ing something
                    337: that is not in the current LaTeX fragment causes a TTH error when it
                    338: can't find the crossreference.
                    339: 
                    340: The solution is to do the cross-references for TTH. When LON-CAPA is
                    341: installed, the C<rebuildLabelHahs.pl>X<rebuildLabelHash.pl> script
                    342: is executed, which extracts all the labels from the LaTeX fragments
                    343: and stores them in the C<fragmentLabels.gdbm>X<fragmentLabels.gdbm> hash. 
                    344: The C<lonhelp.pm> handler then replaces \refs with appropriate
                    345: HTML to provide a link to the referenced help file while online. Thus,
                    346: you can freely use references, even in online help.
                    347: 
                    348: =head3 Indexing
                    349: 
                    350: LaTeX has a popular index making package called MakeIndex. LON-CAPA's
                    351: help system supports this, so you can create indices using the \index
                    352: LaTeX command. In perl POD files, use the X command. Note that in both
1.9       bowersj2  353: cases the index text is not included in the render, so the index must 
                    354: be included in addition to the indexed text, and need not match the 
                    355: indexed text precisely.
1.8       bowersj2  356: 
                    357: =head1 Writing POD: Style
                    358: 
                    359: Adopting a little bit from everybody who has included POD in their
                    360: documents to date, the help system is going to expect the following
                    361: format for POD documentation.
                    362: 
                    363: The POD should start with a C<=head1> with the title C<NAME> (in caps
                    364: as shown). The following paragraph should extremely briefly describe
                    365: what the module does and contains. Example:
                    366: 
                    367:  =head1 NAME
                    368: 
                    369:  Apache::lonflunkstudent - provides interface to set all
                    370:    student assessments point score to 0
                    371: 
                    372: Next should be a C<head1> titled C<SYNOPSIS> which contains a
                    373: paragraph or two description of the module.
                    374: 
                    375:  =head1 SYNOPSIS
                    376: 
                    377:  lonflunkstudent provides a handler to select a student and set all
                    378:  assignment values to zero, thereby flunking the student.
                    379: 
                    380:  Routines for setting all assessments to some value are provided by
                    381:  this module, as well as some useful student taunting routines.
                    382: 
                    383: Optionally, an C<OVERVIEW> section can be included. This can then be
                    384: extracted by the help system for the LON-CAPA subsystems overview
                    385: chapter. The overview should be a relatively high-level, but still
                    386: technical, overview of the module, sufficient to give the reader
                    387: enough context to understand what the module does, what it might be
                    388: useful for in other contexts, and what is going on in the code when it
                    389: is read.
                    390: 
                    391: The remainder should be formatted as appropriate for the file, such
                    392: that discarding the NAME, SYNOPSIS, and OVERVIEW sections provides a
1.9       bowersj2  393: useful API overview of the module. This may be anything from an 
                    394: elaborate discussion of the data structures, algorithms, and design 
                    395: principles that went into the module, or a simple listing of 
                    396: what functions exist, how to call them, and what they return, as
                    397: appropriate.
1.8       bowersj2  398: 
                    399: Routines that are private to the module should B<not> be documented;
                    400: document them in perl comments, or, as is the style of the time, not
                    401: at all, as is appropriate.
                    402: 
                    403: Method and function names should be bolded when being
1.9       bowersj2  404: documented. 
                    405: 
                    406: Literal string such as filename should be enclosed in
1.8       bowersj2  407: the C command, like this: C</home/httpd/lonTabs/>. 
1.9       bowersj2  408: 
                    409: Indexing can be done with the X command in perldoc, and should be used 
                    410: as appropriate. Do not include X commands in the headings, the output 
                    411: from pod2latex screws up some regexes in texxml2latex.pl.
1.8       bowersj2  412: 
                    413: =cut

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>