0: #!/usr/bin/perl -w
1: ##############################################################################
2: #
3: # XML2PDF
4: #
5: # Author : HolyGrail
6: # Version: 0.7
7: #
8: # Usage: xml2pdf {<xmlfile>}
9: #
10: # This conversionprogram translates XML into PDF. You can specify more than one
11: # xmlfile at the commandline and they will all be processed. The PDF files will
12: # replace ".xml" with ".pdf" or add ".pdf" if the sourcefile does not end with 
13: # ".xml". It does no XML validation at all. The XML file should conform to the 
14: # following DTD:
15: #
16: # <!ELEMENT document (section1)+>
17: # <!ATTLIST document
18: #     title CDATA #REQUIRED
19: # >
20: # 
21: # <!ELEMENT section1 (section2 | p | img)+>
22: # <!ATTLIST section1
23: #     title CDATA #REQUIRED
24: # >
25: #
26: # <!ELEMENT section2 (p | img)+>
27: # <!ATTLIST section2
28: #     title CDATA #REQUIRED
29: # >
30: #
31: # <!ELEMENT p (img | #PCDATA)>
32: #
33: # <!ELEMENT img>
34: # <!ATTLIST img
35: #     src CDATA #REQUIRED
36: # >
37: # 
38: # Known issues:
39: # * 'img'-elements are processed after a complete 'p' element is processed, 
40: #   so the images that are meant to come 'in' the text, come 'after' the 
41: #   text. The workaround for this should be to split the text up in multiple 
42: #   p-elements and put the img-element between two p-elements.
43: # * Images that are wider than the page fall off the page on the right side
44: #
45: # Bugs:
46: # * Lots of them, no doubt
47: #
48: # Changes:
49: #
50: # 0.7: 'img' tags can now also be url's and no longer just local files
51: # 0.6: It now also accepts images (JPG, GIF and PNG), changed the DTD 
52: #      accordingly.
53: # 0.5: Changed the program call, so you can process multiple files in one call
54: # 0.4: It now can handle sections that don't fit on one page. It starts new 
55: #      pages if needed.
56: # 0.3: Adapted it to conform to OeufMayo's DTD
57: # 0.2: Minor change (0.1 re-declared the global vars as 'my', thanks to davorg
58: # 0.1: First release
59: #
60: ##############################################################################
61: use strict;
62: use PDFLib;
63: use XML::XPath;
64: use LWP::Simple;
65: use vars qw ( $TOPMARGIN 
66:               $BOTTOMMARGIN 
67:               $LEFTMARGIN 
68:               $RIGHTMARGIN 
69:               $PAGEHEIGHTPOINTS 
70:               $PAGEWIDTHPOINTS
71: 	      $MAXYPOS
72: 	      %FONTDEFINITION
73: 	      %IMAGES
74:              );
75: # Define the fonts for each element
76: %FONTDEFINITION = ( section1  => [face => "Helvetica-Bold", size => "16.0"],
77:                     section2  => [face => "Helvetica-Bold", size => "14.0"],
78:                     p         => [face => "Helvetica", size => "12.0"]
79:                     );
80: 
81: # Pagesetup
82: my $pagename      = "a4";
83: $PAGEHEIGHTPOINTS = 842; # See PDFLib's documentation for 
84: $PAGEWIDTHPOINTS  = 595; # the size of your page
85: ($TOPMARGIN, $BOTTOMMARGIN, $LEFTMARGIN, $RIGHTMARGIN) = (10, 10, 15, 15);
86: 
87: foreach (@ARGV)
88: {
89:   # Documentsetup
90:   my $xmlfile = $_;
91:   my $xml = XML::XPath->new(filename => $xmlfile);
92:   s/\.xml$/\.pdf/i if /\.xml$/i;
93:   my $pdffile =  /\.pdf$/i ? $_ : "$_.pdf";
94:   my $pdf = PDFLib->new( filename => $pdffile,
95:                          papersize=> $pagename,
96:                          creator  => "XML2PDF",
97:                          title    => (($xml->findnodes('document'))[0]->getAttribute('name'))
98:                         );
99:   print "Converting $xmlfile to $pdffile \n";
100: 
101:   # pre-process the images:
102:   foreach my $img ($xml->findnodes('//img'))
103:   {
104:     my $filetype = 'jpeg' if $img->getAttribute('src')=~ /[jpg|jpeg]$/i;
105:     $filetype = 'gif' if $img->getAttribute('src')=~ /gif$/i;
106:     $filetype = 'png' if $img->getAttribute('src')=~ /png$/i;
107: 
108:     my $filename = $img->getAttribute('src');
109: 
110:     if ($filename =~ /^http:\/\//i)
111:     {
112:       $filename =~ /.*\/(.*\..*)/;
113:       print $1."\n";
114:       getstore($img->getAttribute('src'), $1);
115:       $filename=$1;
116:     }  
117: 
118:     $IMAGES{$img->getAttribute('src')} =  
119:        $pdf->load_image(filetype => $filetype || 'gif',
120:                         filename => $filename );
121:   }
122: 
123:   # Process the document
124:   foreach my $section ($xml->findnodes('document/section1'))
125:   {
126:     #start every section on a new page
127:     $pdf->start_page();
128:     
129:     # Calculate the starting Y-axis value
130:     $MAXYPOS = $PAGEHEIGHTPOINTS - $TOPMARGIN - $BOTTOMMARGIN;
131:     
132:     # Print the header
133:     printpdf($pdf, $FONTDEFINITION{section1}, 
134:              "\n".$section->getAttribute('title')."\n\n", $MAXYPOS);
135:     
136:     processsection($pdf, $section);
137:   }
138: }
139: 
140: sub printpdf
141: {
142:     my ($pdf, $font, $what, $ypos) = @_;
143:     $pdf->set_font( @{$font} );
144:     my $charsnotprinted = length($what);
145:     
146:     while ($charsnotprinted)
147:     {
148:       $charsnotprinted = $pdf->print_boxed($what,
149:                           mode => "left",
150:                           x    => $LEFTMARGIN,
151:                           y    => $BOTTOMMARGIN,
152:                           w    => $PAGEWIDTHPOINTS - $RIGHTMARGIN - 
153:                                    $LEFTMARGIN,
154:                           h    => $ypos || $pdf->get_value("texty")
155:                        );
156:        $what = substr($what, (length($what) - $charsnotprinted), length($what));
157:        $pdf->start_page() if $charsnotprinted;
158:        $ypos = $PAGEHEIGHTPOINTS - $TOPMARGIN - $BOTTOMMARGIN;
159:      }           
160: }
161: 
162: sub processsection
163: {
164:   my ($pdf, $section) = @_;
165:   foreach my $node ($section->findnodes('*'))
166:   {
167:     my $text;
168:     if ($node->getName() eq "section2")
169:     {
170:       printpdf($pdf, $FONTDEFINITION{$node->getName()}, 
171:                "\n".$node->getAttribute('title')."\n");
172:       processsection($pdf, $node); #recurse!
173:     }
174:     if ($node->getName() eq "p")
175:     {
176:       printpdf($pdf, $FONTDEFINITION{$node->getName()}, 
177:                "\n".$node->string_value()."\n");
178:       processsection($pdf, $node); #recurse!
179:     }
180:     if ($node->getName() eq "img")
181:     {
182:       if ($pdf->get_value('texty')-$IMAGES{$node->getAttribute('src')}->height() < 0)
183:       {
184:         $pdf->start_page();
185:         $pdf->set_text_pos($pdf->get_value('textx'), $PAGEHEIGHTPOINTS - $TOPMARGIN);
186:       }
187:       $pdf->add_image(img => $IMAGES{$node->getAttribute('src')},
188:                       x   => $LEFTMARGIN,
189: 		      y   => $pdf->get_value('texty')-$IMAGES{$node->getAttribute('src')}->height());
190:       $pdf->set_text_pos($pdf->get_value('textx'), 
191:                          $pdf->get_value('texty')-$IMAGES{$node->getAttribute('src')}->height());
192:     }
193:     
194:   }
195: 
196: }