oddmuse/modules/pdf.pl

# Copyright (C) 2005  Fletcher T. Penney <fletcher@freeshell.org>
#
# 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
#

use strict;

AddModuleDescription('pdf.pl', 'PDF Module');

*PdfOldDoBrowseRequest = \&DoBrowseRequest;
*DoBrowseRequest = \&PdfDoBrowseRequest;

our ($q, %Page, $OpenPageName, $ModuleDir, $ScriptName, $SiteName);
our (@NoLinkToPdf, $pdfDirectory, $pdfProcessCommand, $tempBaseDirectory); # TODO use CamelCase (first capital letter) for public vars

# These variables must be configured properly!
$pdfProcessCommand 		= "/path/to/your/pdflatexscript"
						unless defined $pdfProcessCommand;
# Note - this script will vary from machine to machine
# The key is to set up pdflatex to use the appropriate texmf folder
# Also, I recommend running three times, if you use indexing, etc
# You can also try to get latexmk to work (I could not)

# My file:

# #!/bin/sh
#
# # Use MultiMarkdown to automagically convert a text file to html and pdf
#
# IFS=' '
#
# export TEXINPUTS=/arpa/af/f/fletcher/texmf//:
#
# for filename in "$@"
# do
#
# # Use XSLT to process XHTML to LaTeX
# /usr/pkg/bin/xsltproc /www/af/f/fletcher/wiki/wikidb/modules/Markdown/xhtml2article.xslt "$filename" > "${filename%.*}.tex"
#
# /usr/pkg/bin/pdflatex "$filename"
# /usr/pkg/bin/pdflatex "$filename"
# /usr/pkg/bin/pdflatex "$filename"
#
# done

$tempBaseDirectory	= "$ModuleDir/Markdown/temp"
						unless defined $tempBaseDirectory;
$pdfDirectory		= "/path/to/your/pdf/directory"
						unless defined $pdfDirectory;


# Do not need to change these
my $tempDirectory		= "";


sub PdfDoBrowseRequest{
	my $id = GetId();
	$id = FreeToNormal($id);

	if (GetParam('pdf','')) {

		# Strip `.pdf` if present
		# This does cause problems if you have a page name
		# that ends in `.pdf`...

		$id =~ s/\.pdf$//;


		# Isolate ourselves
		local %Page;
		local $OpenPageName = '';

		OpenPage($id);

		# Create a working directory
		CreateTempDirectory($id);

		# Isolate our output
		outputHTML($id);

		createPDF($id);

		if (-f "$pdfDirectory/$id.pdf") {
			# Remove working directory/lockfile
			system ("/bin/rm -rf \"$tempDirectory\"");

			# pdf in place, redirect browser to download
			my %headers = (-uri=>"$ScriptName/pdf/$id.pdf");
			print $q->redirect(%headers);
		} else {
			# Something happened - pdf not in place
			# Leave lockfile to prevent the hard-headed from
			# killing your server, and for debugging

			ReportError(Ts('There was an error generating the pdf for %s.  Please report this to webmaster, but do not try to download again as it will not work.', $id));
		}

	} else {
		&PdfOldDoBrowseRequest();
	}
}


# Create an HTML file with just the content of the page body
sub outputHTML {
	my ($id) = @_;

	local *STDERR;
	open(STDERR, '>', '/dev/null');

	# Fix Markdown
	my $result = ToString sub { print PageHtml($id) };

	open(my $FILE, '>', "$tempDirectory/temp.html") or ReportError(Ts('Cannot write %s', "temp.html"));

	print $FILE qq{<?xml version="1.0" encoding="UTF-8" ?>
<html>
	<head>};

	# Create meta-data (you can customize this)
	print $FILE qq{<title>$OpenPageName</title>};
	print $FILE qq{<meta name="author" content="$SiteName"/>};
	print $FILE qq{<meta name="copyright" content="2005. This work is licensed under a Creative Commons License:  http://creativecommons.org/licenses/by-sa/2.5/"/>};
	print $FILE qq{<meta name="XMP" content="CCAttributionShareAlike"/>};
	print $FILE "</head><body>";

	# Output the body and close the file
	print $FILE $result;
	print $FILE "\n</body>\n</html>\n";
	close $FILE;
}


# Run a series of steps to convert XHTML to pdf
# You may have to change this based on your system
sub createPDF {
	my $id = shift;
	local *STDOUT;
	open(STDOUT, '>', '/dev/null');
	local *STDERR;
	open(STDERR, '>', '/dev/null');

	# Run latex script and copy pdf to final location
	system("cd \"$tempDirectory\"; \"$pdfProcessCommand\" temp.html > /dev/null; /bin/cp temp.pdf \"$pdfDirectory/$id.pdf\" ");
}


# If we save a new version of a file, we want to delete the old pdf
# To save wasted time, don't recreate it until called for

*PdfOldDoPost = \&DoPost;
*DoPost = \&PdfNewDoPost;

sub PdfNewDoPost {
	my $id = FreeToNormal(shift);

	unlink("$pdfDirectory/$id.pdf");

	PdfOldDoPost($id);
}


sub CreateTempDirectory {
	my ($id) = @_;

	$tempDirectory = "$tempBaseDirectory/$id";

	# Create the general directory if it doesn't exist
	CreateDir($tempBaseDirectory);

	# Now, create a temp directory for this page
	# If it exists, then someone else is generating pdf - give error message

	if (-d $tempDirectory) {
		# Someone else is creating this pdf

		ReportError(Ts('Someone else is generating a pdf for %s.  Please wait a minute and then try again.', $id));

	}

	CreateDir($tempDirectory);
}


# Fix Wiki Links - they have to be fully qualified

*PdfOldCreateWikiLink = \&CreateWikiLink;
*CreateWikiLink = \&PdfNewCreateWikiLink;

sub PdfNewCreateWikiLink {
	my $title = shift;

	my $rawlink = PdfOldCreateWikiLink($title);

	if ($rawlink =~ /http\:\/\//) {
		return $rawlink;
	} else {
		$rawlink =~ s/\((.*)\)/($ScriptName\/$1)/;

		return $rawlink;
	}
}

*PdfOldGetFooterLinks = \&GetFooterLinks;
*GetFooterLinks = \&PdfNewGetFooterLinks;

sub PdfNewGetFooterLinks {
	my ($id, $rev) = @_;
	my $result = PdfOldGetFooterLinks($id,$rev);


	push(@NoLinkToPdf,"");
	foreach my $page (@NoLinkToPdf) {
		if ($id =~ /^$page$/) {
			return $result;
		}
	}

	return $result . "<br/>" . ScriptLink("pdf/$id.pdf",T('Download this page as PDF'));
}
Initialize module 2005-11-06 15:44:40 +00:00			`# Copyright (C) 2005 Fletcher T. Penney <fletcher@freeshell.org>`
			`#`
			`# 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`
			`#`

pdf.pl uses strict PdfNewGetFooterLinks shows that @NoLinkToPdf is simply a list of pages that should not offer a PDF link at the bottom. Authors can add their own exceptions to PdfNewGetFooterLinks, I guess, but in order to do this from your config file, use vars. createPDF needs $id as a parameter in order to use it. This code worked before because the calling context was missing a my $id and thus $id ended up being a global variable. 2015-03-29 23:27:00 +02:00			`use strict;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Fixed typo in AddModuleDescription sub name 2014-08-21 22:23:23 +02:00			`AddModuleDescription('pdf.pl', 'PDF Module');`
Add version string 2005-11-06 15:46:00 +00:00
No more "Sub = NewSub", \&NewSub used instead. (Partial progress) 2015-04-11 23:41:33 +03:00			`*PdfOldDoBrowseRequest = \&DoBrowseRequest;`
			`*DoBrowseRequest = \&PdfDoBrowseRequest;`
Initialize module 2005-11-06 15:44:40 +00:00
No more "use vars"! 2015-04-10 13:31:28 +03:00			`our ($q, %Page, $OpenPageName, $ModuleDir, $ScriptName, $SiteName);`
			`our (@NoLinkToPdf, $pdfDirectory, $pdfProcessCommand, $tempBaseDirectory); # TODO use CamelCase (first capital letter) for public vars`
Initialize module 2005-11-06 15:44:40 +00:00
			`# These variables must be configured properly!`
Further abstract the processing to separate it from the module 2005-11-06 16:35:15 +00:00			`$pdfProcessCommand = "/path/to/your/pdflatexscript"`
			`unless defined $pdfProcessCommand;`
Initialize module 2005-11-06 15:44:40 +00:00			`# Note - this script will vary from machine to machine`
			`# The key is to set up pdflatex to use the appropriate texmf folder`
			`# Also, I recommend running three times, if you use indexing, etc`
			`# You can also try to get latexmk to work (I could not)`

			`# My file:`

			`# #!/bin/sh`
			`#`
			`# # Use MultiMarkdown to automagically convert a text file to html and pdf`
			`#`
			`# IFS=' '`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`#`
Initialize module 2005-11-06 15:44:40 +00:00			`# export TEXINPUTS=/arpa/af/f/fletcher/texmf//:`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`#`
Initialize module 2005-11-06 15:44:40 +00:00			`# for filename in "$@"`
			`# do`
Further abstract the processing to separate it from the module 2005-11-06 16:35:15 +00:00			`#`
			`# # Use XSLT to process XHTML to LaTeX`
			`# /usr/pkg/bin/xsltproc /www/af/f/fletcher/wiki/wikidb/modules/Markdown/xhtml2article.xslt "$filename" > "${filename%.*}.tex"`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`#`
Initialize module 2005-11-06 15:44:40 +00:00			`# /usr/pkg/bin/pdflatex "$filename"`
			`# /usr/pkg/bin/pdflatex "$filename"`
			`# /usr/pkg/bin/pdflatex "$filename"`
			`#`
			`# done`

			`$tempBaseDirectory = "$ModuleDir/Markdown/temp"`
			`unless defined $tempBaseDirectory;`
			`$pdfDirectory = "/path/to/your/pdf/directory"`
			`unless defined $pdfDirectory;`


			`# Do not need to change these`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`my $tempDirectory = "";`
Initialize module 2005-11-06 15:44:40 +00:00

			`sub PdfDoBrowseRequest{`
			`my $id = GetId();`
			`$id = FreeToNormal($id);`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`if (GetParam('pdf','')) {`

Fix incompatibility with Firefox (and possibly other browsers); download links should now end in `.pdf` 2006-01-08 20:48:00 +00:00			# Strip `.pdf` if present
			`# This does cause problems if you have a page name`
			# that ends in `.pdf`...
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Fix incompatibility with Firefox (and possibly other browsers); download links should now end in `.pdf` 2006-01-08 20:48:00 +00:00			`$id =~ s/\.pdf$//;`


Initialize module 2005-11-06 15:44:40 +00:00			`# Isolate ourselves`
			`local %Page;`
			`local $OpenPageName = '';`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`OpenPage($id);`

"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`# Create a working directory`
Initialize module 2005-11-06 15:44:40 +00:00			`CreateTempDirectory($id);`

			`# Isolate our output`
			`outputHTML($id);`

pdf.pl uses strict PdfNewGetFooterLinks shows that @NoLinkToPdf is simply a list of pages that should not offer a PDF link at the bottom. Authors can add their own exceptions to PdfNewGetFooterLinks, I guess, but in order to do this from your config file, use vars. createPDF needs $id as a parameter in order to use it. This code worked before because the calling context was missing a my $id and thus $id ended up being a global variable. 2015-03-29 23:27:00 +02:00			`createPDF($id);`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`if (-f "$pdfDirectory/$id.pdf") {`
			`# Remove working directory/lockfile`
			`system ("/bin/rm -rf \"$tempDirectory\"");`

			`# pdf in place, redirect browser to download`
Fix incompatibility with Firefox (and possibly other browsers); download links should now end in `.pdf` 2006-01-08 20:48:00 +00:00			`my %headers = (-uri=>"$ScriptName/pdf/$id.pdf");`
Initialize module 2005-11-06 15:44:40 +00:00			`print $q->redirect(%headers);`
			`} else {`
			`# Something happened - pdf not in place`
			`# Leave lockfile to prevent the hard-headed from`
			`# killing your server, and for debugging`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`ReportError(Ts('There was an error generating the pdf for %s. Please report this to webmaster, but do not try to download again as it will not work.', $id));`
			`}`

			`} else {`
			`&PdfOldDoBrowseRequest();`
			`}`
			`}`


			`# Create an HTML file with just the content of the page body`
			`sub outputHTML {`
pdf.pl uses strict PdfNewGetFooterLinks shows that @NoLinkToPdf is simply a list of pages that should not offer a PDF link at the bottom. Authors can add their own exceptions to PdfNewGetFooterLinks, I guess, but in order to do this from your config file, use vars. createPDF needs $id as a parameter in order to use it. This code worked before because the calling context was missing a my $id and thus $id ended up being a global variable. 2015-03-29 23:27:00 +02:00			`my ($id) = @_;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`local *STDERR;`
No more two-arg open 2015-05-02 03:19:25 +03:00			`open(STDERR, '>', '/dev/null');`
Initialize module 2005-11-06 15:44:40 +00:00
			`# Fix Markdown`
UTF-8, again! Also, new ToString sub. 2015-05-17 03:35:35 +03:00			`my $result = ToString sub { print PageHtml($id) };`
Initialize module 2005-11-06 15:44:40 +00:00
No more two-arg open 2015-05-02 03:19:25 +03:00			`open(my $FILE, '>', "$tempDirectory/temp.html") or ReportError(Ts('Cannot write %s', "temp.html"));`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
No more two-arg open 2015-05-02 03:19:25 +03:00			`print $FILE qq{<?xml version="1.0" encoding="UTF-8" ?>`
Initialize module 2005-11-06 15:44:40 +00:00			`<html>`
			`<head>};`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`# Create meta-data (you can customize this)`
No more two-arg open 2015-05-02 03:19:25 +03:00			`print $FILE qq{<title>$OpenPageName</title>};`
			`print $FILE qq{<meta name="author" content="$SiteName"/>};`
			`print $FILE qq{<meta name="copyright" content="2005. This work is licensed under a Creative Commons License: http://creativecommons.org/licenses/by-sa/2.5/"/>};`
			`print $FILE qq{<meta name="XMP" content="CCAttributionShareAlike"/>};`
			`print $FILE "</head><body>";`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`# Output the body and close the file`
No more two-arg open 2015-05-02 03:19:25 +03:00			`print $FILE $result;`
			`print $FILE "\n</body>\n</html>\n";`
			`close $FILE;`
Initialize module 2005-11-06 15:44:40 +00:00			`}`


			`# Run a series of steps to convert XHTML to pdf`
			`# You may have to change this based on your system`
			`sub createPDF {`
pdf.pl uses strict PdfNewGetFooterLinks shows that @NoLinkToPdf is simply a list of pages that should not offer a PDF link at the bottom. Authors can add their own exceptions to PdfNewGetFooterLinks, I guess, but in order to do this from your config file, use vars. createPDF needs $id as a parameter in order to use it. This code worked before because the calling context was missing a my $id and thus $id ended up being a global variable. 2015-03-29 23:27:00 +02:00			`my $id = shift;`
Initialize module 2005-11-06 15:44:40 +00:00			`local *STDOUT;`
No more two-arg open 2015-05-02 03:19:25 +03:00			`open(STDOUT, '>', '/dev/null');`
Initialize module 2005-11-06 15:44:40 +00:00			`local *STDERR;`
No more two-arg open 2015-05-02 03:19:25 +03:00			`open(STDERR, '>', '/dev/null');`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`# Run latex script and copy pdf to final location`
Further abstract the processing to separate it from the module 2005-11-06 16:35:15 +00:00			`system("cd \"$tempDirectory\"; \"$pdfProcessCommand\" temp.html > /dev/null; /bin/cp temp.pdf \"$pdfDirectory/$id.pdf\" ");`
Initialize module 2005-11-06 15:44:40 +00:00			`}`



			`# If we save a new version of a file, we want to delete the old pdf`
			`# To save wasted time, don't recreate it until called for`

No more "Sub = NewSub", \&NewSub used instead. (Partial progress) 2015-04-11 23:41:33 +03:00			`*PdfOldDoPost = \&DoPost;`
			`*DoPost = \&PdfNewDoPost;`
Initialize module 2005-11-06 15:44:40 +00:00
			`sub PdfNewDoPost {`
			`my $id = FreeToNormal(shift);`

			`unlink("$pdfDirectory/$id.pdf");`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`PdfOldDoPost($id);`
			`}`


			`sub CreateTempDirectory {`
			`my ($id) = @_;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`$tempDirectory = "$tempBaseDirectory/$id";`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`# Create the general directory if it doesn't exist`
			`CreateDir($tempBaseDirectory);`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`# Now, create a temp directory for this page`
			`# If it exists, then someone else is generating pdf - give error message`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`if (-d $tempDirectory) {`
			`# Someone else is creating this pdf`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`ReportError(Ts('Someone else is generating a pdf for %s. Please wait a minute and then try again.', $id));`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`}`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`CreateDir($tempDirectory);`
			`}`



			`# Fix Wiki Links - they have to be fully qualified`

No more "Sub = NewSub", \&NewSub used instead. (Partial progress) 2015-04-11 23:41:33 +03:00			`*PdfOldCreateWikiLink = \&CreateWikiLink;`
			`*CreateWikiLink = \&PdfNewCreateWikiLink;`
Initialize module 2005-11-06 15:44:40 +00:00
			`sub PdfNewCreateWikiLink {`
			`my $title = shift;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`my $rawlink = PdfOldCreateWikiLink($title);`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`if ($rawlink =~ /http\:\/\//) {`
			`return $rawlink;`
			`} else {`
			`$rawlink =~ s/\((.*)\)/($ScriptName\/$1)/;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Initialize module 2005-11-06 15:44:40 +00:00			`return $rawlink;`
			`}`
Add "Download this page as PDF" link to footer 2005-11-06 18:54:15 +00:00			`}`

No more "Sub = NewSub", \&NewSub used instead. (Partial progress) 2015-04-11 23:41:33 +03:00			`*PdfOldGetFooterLinks = \&GetFooterLinks;`
			`*GetFooterLinks = \&PdfNewGetFooterLinks;`
Add "Download this page as PDF" link to footer 2005-11-06 18:54:15 +00:00
			`sub PdfNewGetFooterLinks {`
			`my ($id, $rev) = @_;`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`my $result = PdfOldGetFooterLinks($id,$rev);`
Add "Download this page as PDF" link to footer 2005-11-06 18:54:15 +00:00

"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00			`push(@NoLinkToPdf,"");`
Add "Download this page as PDF" link to footer 2005-11-06 18:54:15 +00:00			`foreach my $page (@NoLinkToPdf) {`
			`if ($id =~ /^$page$/) {`
			`return $result;`
			`}`
			`}`
"use strict;" in modules (some modules have problems) 2015-03-27 03:01:01 +02:00
Fix incompatibility with Firefox (and possibly other browsers); download links should now end in `.pdf` 2006-01-08 20:48:00 +00:00			`return $result . "<br/>" . ScriptLink("pdf/$id.pdf",T('Download this page as PDF'));`
getting rid of $Id$ tags in $WikiDescription Replaced the $Id$ tags in $WikiDescription for all the modules and wiki.pl itself with a link to the source and an appropriate wiki page, if possible. This is shown in action=version and should help users figure out what another wiki has installed. 2012-04-19 02:18:45 +02:00			`}`