1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # PDFPlug.pm -- reasonably with-it pdf plugin
|
---|
4 | # A component of the Greenstone digital library software
|
---|
5 | # from the New Zealand Digital Library Project at the
|
---|
6 | # University of Waikato, New Zealand.
|
---|
7 | #
|
---|
8 | # Copyright (C) 1999-2001 New Zealand Digital Library Project
|
---|
9 | #
|
---|
10 | # This program 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 | # This program 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 this program; if not, write to the Free Software
|
---|
22 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
23 | #
|
---|
24 | ###########################################################################
|
---|
25 |
|
---|
26 | package PDFPlug;
|
---|
27 |
|
---|
28 | use ConvertToPlug;
|
---|
29 |
|
---|
30 | sub BEGIN {
|
---|
31 | @ISA = ('ConvertToPlug');
|
---|
32 | }
|
---|
33 |
|
---|
34 | my $arguments =
|
---|
35 | [ { 'name' => "process_exp",
|
---|
36 | 'desc' => "{BasPlug.process_exp}",
|
---|
37 | 'type' => "regexp",
|
---|
38 | 'deft' => &get_default_process_exp(),
|
---|
39 | 'reqd' => "no" },
|
---|
40 | { 'name' => "block_exp",
|
---|
41 | 'desc' => "{BasPlug.block_exp}",
|
---|
42 | 'type' => "regexp",
|
---|
43 | 'deft' => &get_default_block_exp() },
|
---|
44 | { 'name' => "noimages",
|
---|
45 | 'desc' => "{PDFPlug.noimages}",
|
---|
46 | 'type' => "flag" },
|
---|
47 | { 'name' => "complex",
|
---|
48 | 'desc' => "{PDFPlug.complex}",
|
---|
49 | 'type' => "flag" },
|
---|
50 | { 'name' => "nohidden",
|
---|
51 | 'desc' => "{PDFPlug.nohidden}",
|
---|
52 | 'type' => "flag" },
|
---|
53 | { 'name' => "zoom",
|
---|
54 | 'desc' => "{PDFPlug.zoom}",
|
---|
55 | 'deft' => "2",
|
---|
56 | 'range' => "1,3", # actually the range is 0.5-3
|
---|
57 | 'type' => "int" },
|
---|
58 | { 'name' => "use_sections",
|
---|
59 | 'desc' => "{PDFPlug.use_sections}",
|
---|
60 | 'type' => "flag" } ];
|
---|
61 |
|
---|
62 | my $options = { 'name' => "PDFPlug",
|
---|
63 | 'desc' => "{PDFPlug.desc}",
|
---|
64 | 'abstract' => "no",
|
---|
65 | 'inherits' => "yes",
|
---|
66 | 'args' => $arguments };
|
---|
67 |
|
---|
68 | sub new {
|
---|
69 | my $class = shift (@_);
|
---|
70 |
|
---|
71 | my ($noimages, $complex, $zoom, $use_sections, $nohidden);
|
---|
72 |
|
---|
73 | my @args=@_;
|
---|
74 |
|
---|
75 | if (!parsargv::parse(\@_,
|
---|
76 | q^noimages^, \$noimages,
|
---|
77 | q^complex^, \$complex,
|
---|
78 | q^zoom/\d+/2^, \$zoom,
|
---|
79 | q^nohidden^, \$nohidden,
|
---|
80 | q^use_sections^, \$use_sections,
|
---|
81 | "allow_extra_options")) {
|
---|
82 |
|
---|
83 | local $self = new ConvertToPlug($class, @_, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
---|
84 | my $outhandle=$self->{'outhandle'};
|
---|
85 | print $outhandle "\nIncorrect options passed to PDFPlug, check your collect.cfg configuration file\n";
|
---|
86 | $self->print_txt_usage(""); # Use default resource bundle
|
---|
87 | exit 1;
|
---|
88 | }
|
---|
89 |
|
---|
90 |
|
---|
91 | if ($use_sections) {
|
---|
92 | push (@args, "-description_tags");
|
---|
93 | }
|
---|
94 |
|
---|
95 | # following title_sub removes "Page 1" added by pdftohtml, and a leading
|
---|
96 | # "1", which is often the page number at the top of the page. Bad Luck
|
---|
97 | # if your document title actually starts with "1 " - is there a better way?
|
---|
98 |
|
---|
99 | my $self = new ConvertToPlug ($class, @args, "-title_sub", '^(Page\s+\d+)?(\s*1\s+)?');
|
---|
100 | $self->{'plugin_type'} = "PDFPlug";
|
---|
101 | if ($use_sections) {
|
---|
102 | $self->{'use_sections'}=1;
|
---|
103 | }
|
---|
104 |
|
---|
105 | # 14-05-02 To allow for proper inheritance of arguments - John Thompson
|
---|
106 | my $option_list = $self->{'option_list'};
|
---|
107 | push( @{$option_list}, $options );
|
---|
108 |
|
---|
109 | # these are passed through to gsConvert.pl by ConvertToPlug.pm
|
---|
110 | $self->{'convert_options'} = "-pdf_zoom $zoom";
|
---|
111 | $self->{'convert_options'} .= " -pdf_complex" if $complex;
|
---|
112 | $self->{'convert_options'} .= " -pdf_nohidden" if $nohidden;
|
---|
113 | $self->{'convert_options'} .= " -pdf_ignore_images" if $noimages;
|
---|
114 |
|
---|
115 | # pdftohtml will always produce html files encoded as utf-8
|
---|
116 | if ($self->{'input_encoding'} eq "auto") {
|
---|
117 | $self->{'input_encoding'} = "utf8";
|
---|
118 | $self->{'extract_language'} = 1;
|
---|
119 | }
|
---|
120 |
|
---|
121 | return bless $self, $class;
|
---|
122 | }
|
---|
123 |
|
---|
124 |
|
---|
125 | # sub print_usage {
|
---|
126 | # print STDERR "\n usage: plugin PDFPlug [options]\n\n";
|
---|
127 | # print STDERR " options:\n";
|
---|
128 | # print STDERR " -convert_to (html|text) Convert to TEXT or HTML (default html)\n";
|
---|
129 | # print STDERR " -use_sections Create a separate section for each page\n";
|
---|
130 | # print STDERR " of the PDF file.\n";
|
---|
131 | # print STDERR " -noimages Don't attempt to extract images from PDF.\n";
|
---|
132 | # print STDERR " -complex Create more complex output. With this option\n";
|
---|
133 | # print STDERR " set the output html will look much more like\n";
|
---|
134 | # print STDERR " the original PDF file. For this to function\n";
|
---|
135 | # print STDERR " properly you Ghostscript installed (for *nix\n";
|
---|
136 | # print STDERR " gs should be on your path while for windows\n";
|
---|
137 | # print STDERR " you must have gswin32c.exe on your path).\n";
|
---|
138 | # print STDERR " -nohidden Prevent pdftohtml from attempting to extract\n";
|
---|
139 | # print STDERR " hidden text. This is only useful if the -complex\n";
|
---|
140 | # print STDERR " option is also set.";
|
---|
141 | # print STDERR " -zoom The factor by which to zoomthe PDF for output\n";
|
---|
142 | # print STDERR " (this is only useful if -complex is set).\n\n";
|
---|
143 | # }
|
---|
144 |
|
---|
145 |
|
---|
146 |
|
---|
147 | sub get_default_process_exp {
|
---|
148 | my $self = shift (@_);
|
---|
149 |
|
---|
150 | return q^(?i)\.pdf$^;
|
---|
151 | }
|
---|
152 |
|
---|
153 | # so we don't inherit HTMLPlug's block exp...
|
---|
154 | sub get_default_block_exp {
|
---|
155 | return "";
|
---|
156 | }
|
---|
157 |
|
---|
158 |
|
---|
159 | # do plugin specific processing of doc_obj for HTML type
|
---|
160 | sub process {
|
---|
161 | my $self = shift (@_);
|
---|
162 | my $outhandle=$self->{'outhandle'};
|
---|
163 |
|
---|
164 | if ($self->{'use_sections'}
|
---|
165 | && $self->{'converted_to'} eq "HTML") {
|
---|
166 |
|
---|
167 | print $outhandle "PDFPlug: Calculating sections...\n";
|
---|
168 | my $textref=$_[0];
|
---|
169 |
|
---|
170 | # we have "<a name=1></a>" etc for each page
|
---|
171 | my @sections = split('<a name=', $$textref);
|
---|
172 |
|
---|
173 | if (scalar (@sections) == 1) { #only one section - no split!
|
---|
174 | print $outhandle "PDFPlug: warning - no sections found\n";
|
---|
175 | } else {
|
---|
176 | shift @sections; # don't need HTML header, etc
|
---|
177 | }
|
---|
178 |
|
---|
179 | # handle first section specially for title? Or all use first 100...
|
---|
180 |
|
---|
181 | my $title = $sections[0];
|
---|
182 | $title =~ s/^\d+>//; # specific for pdftohtml...
|
---|
183 | $title =~ s/<\/([^>]+)><\1>//g; # (eg) </b><b> - no space
|
---|
184 | $title =~ s/<[^>]*>/ /g;
|
---|
185 | $title =~ s/(?: |\xc2\xa0)/ /g; # utf-8 for nbsp...
|
---|
186 | $title =~ s/^\s+//s;
|
---|
187 | $title =~ s/\s+$//;
|
---|
188 | $title =~ s/\s+/ /gs;
|
---|
189 | $title =~ s/^$self->{'title_sub'}// if ($self->{'title_sub'});
|
---|
190 | $title =~ s/^\s+//s; # in case title_sub introduced any...
|
---|
191 | $title = substr ($title, 0, 100);
|
---|
192 | $title =~ s/\s\S*$/.../;
|
---|
193 |
|
---|
194 | my $top_section;
|
---|
195 | if (scalar (@sections) == 1) { # no sections found
|
---|
196 | $top_section=$sections[0];
|
---|
197 | @sections=();
|
---|
198 | } else {
|
---|
199 | $top_section = "<!--<Section>\n<Metadata name=\"Title\">$title</Metadata>\n-->\n <!--</Section>-->\n";
|
---|
200 | }
|
---|
201 |
|
---|
202 | # add metadata per section...
|
---|
203 | foreach my $section (@sections) {
|
---|
204 | $section =~ s@^(\d+)></a>@@; # leftover from split expression...
|
---|
205 |
|
---|
206 | $title = $1; # Greenstone does magic if sections are titled digits
|
---|
207 | if (! defined($title) ) {
|
---|
208 | print STDERR "no title: $section\n";
|
---|
209 | }
|
---|
210 | my $newsection = "<!-- from PDFPlug -->\n<!-- <Section>\n";
|
---|
211 | $newsection .= "<Metadata name=\"Title\">" . $title
|
---|
212 | . "</Metadata>\n--><p>\n";
|
---|
213 | $newsection .= $section;
|
---|
214 | $newsection .= "<!--</Section>-->\n";
|
---|
215 | $section = $newsection;
|
---|
216 | }
|
---|
217 |
|
---|
218 | $$textref=join('', ($top_section, @sections));
|
---|
219 | }
|
---|
220 |
|
---|
221 | print $outhandle "PDFPlug: passing $_[3] on to $self->{'converted_to'}Plug\n"
|
---|
222 | if $self->{'verbosity'} > 1;
|
---|
223 |
|
---|
224 | return ConvertToPlug::process_type($self,"pdf",@_);
|
---|
225 | }
|
---|
226 |
|
---|
227 | 1;
|
---|