Annotation of doc/help/texxml2latex.pl, revision 1.9

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

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