1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # GBBPlug.pm -- plugin for processing gb encoded html books
|
---|
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 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 | # creates multi-level document from document containing
|
---|
27 | # <<TOC>> level tags. Metadata for each section is taken from any
|
---|
28 | # other tags on the same line as the <<TOC>>. e.g. <<Title>>xxxx<</Title>>
|
---|
29 | # sets Title metadata.
|
---|
30 |
|
---|
31 | # Everything else between TOC tags is expected to be simple html
|
---|
32 | # and is treated accordingly.
|
---|
33 |
|
---|
34 | # Imput files are expected to be GB encoded and have .gbb file extension
|
---|
35 |
|
---|
36 | package GBBPlug;
|
---|
37 |
|
---|
38 | use BasPlug;
|
---|
39 | use sorttools;
|
---|
40 | use util;
|
---|
41 | use unicode;
|
---|
42 | use cnseg;
|
---|
43 | use gb;
|
---|
44 |
|
---|
45 |
|
---|
46 | sub BEGIN {
|
---|
47 | @ISA = ('BasPlug');
|
---|
48 | }
|
---|
49 |
|
---|
50 | sub new {
|
---|
51 | my ($class) = @_;
|
---|
52 | $self = new BasPlug ();
|
---|
53 |
|
---|
54 | return bless $self, $class;
|
---|
55 | }
|
---|
56 |
|
---|
57 | sub is_recursive {
|
---|
58 | my $self = shift (@_);
|
---|
59 |
|
---|
60 | return 0; # this is not a recursive plugin
|
---|
61 | }
|
---|
62 |
|
---|
63 |
|
---|
64 | # return number of files processed, undef if can't process
|
---|
65 | # Note that $base_dir might be "" and that $file might
|
---|
66 | # include directories
|
---|
67 | sub read {
|
---|
68 | my $self = shift (@_);
|
---|
69 | my ($pluginfo, $base_dir, $file, $metadata, $processor) = @_;
|
---|
70 |
|
---|
71 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
72 | my $absdir = $filename;
|
---|
73 | $absdir =~ s/[^\/\\]*$//;
|
---|
74 |
|
---|
75 | return undef unless ($filename =~ /\.gbb$/i && (-e $filename));
|
---|
76 |
|
---|
77 | print STDERR "GBBPlug: processing $filename\n" if $processor->{'verbosity'};
|
---|
78 |
|
---|
79 | # create a new document
|
---|
80 | my $doc_obj = new doc ($file, "indexed_doc");
|
---|
81 | open (FILE, $filename) || die "GBBPlug::read - ERROR: can't open $filename\n";
|
---|
82 |
|
---|
83 | my $cursection = $doc_obj->get_top_section();
|
---|
84 |
|
---|
85 | my $text = "";
|
---|
86 | my $line = "";
|
---|
87 | my $title = "";
|
---|
88 | while (defined ($line = <FILE>)) {
|
---|
89 | $text .= $line;
|
---|
90 | }
|
---|
91 |
|
---|
92 | # convert to unicode
|
---|
93 | $text = &unicode::unicode2utf8(&gb::gb2unicode($text));
|
---|
94 | # segment the Chinese words
|
---|
95 | $text = &cnseg::segment($text);
|
---|
96 |
|
---|
97 | # we'll use the worthless alarm thingy to temporarily replace
|
---|
98 | # '\n' so we'd better check it doesn't occur naturally
|
---|
99 | if ($text =~ /\a/) {
|
---|
100 | print STDERR "GBBPlug::read - 'WARNING '\a' character occurs in text!!\n";
|
---|
101 | }
|
---|
102 |
|
---|
103 | # need to add <classifytype> to each book as we'll be using 'Hierarchy'
|
---|
104 | # for HB collections rather than the default ('Book')
|
---|
105 | $doc_obj->add_metadata ($cursection, 'classifytype', 'Hierarchy');
|
---|
106 |
|
---|
107 | # remove line breaks
|
---|
108 | $text =~ s/\n/\a/g;
|
---|
109 |
|
---|
110 | # remove any leading rubbish
|
---|
111 | $text =~ s/^.*?(<<TOC)/$1/i;
|
---|
112 |
|
---|
113 | my $curtoclevel = 1;
|
---|
114 | my $firstsection = 1;
|
---|
115 | while (length ($text) > 0) {
|
---|
116 | $text =~ s/^<<TOC(\d+)>>([^\a]*)\a(.*?)(<<TOC|\Z)/$4/i;
|
---|
117 | my $toclevel = $1;
|
---|
118 | my $metadata = $2;
|
---|
119 | my $sectiontext = $3;
|
---|
120 |
|
---|
121 | # close any sections below the current level and
|
---|
122 | # create a new section (special case for the firstsection)
|
---|
123 | while (($curtoclevel > $toclevel) ||
|
---|
124 | (!$firstsection && $curtoclevel == $toclevel)) {
|
---|
125 | $cursection = $doc_obj->get_parent_section ($cursection);
|
---|
126 | $curtoclevel--;
|
---|
127 | }
|
---|
128 | if ($curtoclevel+1 < $toclevel) {
|
---|
129 | print STDERR "WARNING - jump in toc levels in $htmlfile " .
|
---|
130 | "from $curtoclevel to $toclevel\n";
|
---|
131 | }
|
---|
132 | while ($curtoclevel < $toclevel) {
|
---|
133 | $curtoclevel++;
|
---|
134 | $cursection =
|
---|
135 | $doc_obj->insert_section($doc_obj->get_end_child($cursection));
|
---|
136 | }
|
---|
137 |
|
---|
138 | # sort out metadata
|
---|
139 | while ($metadata =~ s/^.*?<<([^>]*)>>(.*?)<<[^>]*>>//) {
|
---|
140 | my $metakey = $1;
|
---|
141 | my $metavalue = $2;
|
---|
142 |
|
---|
143 | if ($metavalue ne "" && $metakey ne "") {
|
---|
144 | # make sure key fits in with gsdl naming scheme
|
---|
145 | $metakey =~ tr/[A-Z]/[a-z]/;
|
---|
146 | $metakey = ucfirst ($metakey);
|
---|
147 | $doc_obj->add_utf8_metadata ($cursection, $metakey, $metavalue);
|
---|
148 | }
|
---|
149 | }
|
---|
150 |
|
---|
151 |
|
---|
152 | # remove header rubbish
|
---|
153 | $sectiontext =~ s/^.*?<body[^>]*>//i;
|
---|
154 |
|
---|
155 | # and any other unwanted tags
|
---|
156 | $sectiontext =~ s/<(\/p|\/html|\/body)>//g;
|
---|
157 |
|
---|
158 | # fix up the image links
|
---|
159 | $sectiontext =~ s/(<img[^>]*?src\s*=\s*\"?)([^\">]+)(\"?[^>]*>)/
|
---|
160 | &replace_image_links($absdir, $doc_obj, $1, $2, $3)/ige;
|
---|
161 |
|
---|
162 | # put line breaks back in
|
---|
163 | $sectiontext =~ s/\a/\n/g;
|
---|
164 |
|
---|
165 | # add the text
|
---|
166 | $doc_obj->add_utf8_text($cursection, $sectiontext);
|
---|
167 |
|
---|
168 | $firstsection = 0;
|
---|
169 | }
|
---|
170 |
|
---|
171 | # add OID
|
---|
172 | $doc_obj->set_OID ();
|
---|
173 |
|
---|
174 | # process the document
|
---|
175 | $processor->process($doc_obj);
|
---|
176 |
|
---|
177 | return 1; # processed the file
|
---|
178 | }
|
---|
179 |
|
---|
180 | sub replace_image_links {
|
---|
181 |
|
---|
182 | my ($dir, $doc_obj, $front, $link, $back) = @_;
|
---|
183 |
|
---|
184 | my ($filename, $error);
|
---|
185 | my $foundimage = 0;
|
---|
186 |
|
---|
187 | $link =~ s/\/\///;
|
---|
188 | my ($imagetype) = $link =~ /([^\.]*)$/;
|
---|
189 | $imagetype =~ tr/[A-Z]/[a-z]/;
|
---|
190 | if ($imagetype eq "jpg") {$imagetype = "jpeg";}
|
---|
191 | if ($imagetype !~ /^(jpg|gif|png)$/) {
|
---|
192 | print STDERR "GBHPlug: Warning - unknown image type ($imagetype)\n";
|
---|
193 | }
|
---|
194 | my ($imagefile) = $link =~ /([^\/]*)$/;
|
---|
195 | my ($imagepath) = $link =~ /^[^\/]*(.*)$/;
|
---|
196 |
|
---|
197 | if (defined $imagepath && $imagepath =~ /\w/) {
|
---|
198 | # relative link
|
---|
199 | $filename = &util::filename_cat ($dir, $imagepath);
|
---|
200 | if (-e $filename) {
|
---|
201 | $doc_obj->associate_file ($filename, $imagefile, "image/$imagetype");
|
---|
202 | $foundimage = 1;
|
---|
203 | } else {
|
---|
204 | $error = "GBHPlug: Warning - couldn't find image file $imagefile in either $filename or";
|
---|
205 | }
|
---|
206 | }
|
---|
207 |
|
---|
208 | if (!$foundimage) {
|
---|
209 | $filename = &util::filename_cat ($dir, $imagefile);
|
---|
210 | if (-e $filename) {
|
---|
211 | $doc_obj->associate_file ($filename, $imagefile, "image/$imagetype");
|
---|
212 | $foundimage = 1;
|
---|
213 | } elsif (defined $error) {
|
---|
214 | print STDERR "$error $filename\n";
|
---|
215 | } else {
|
---|
216 | print STDERR "GBHPlug: Warning - couldn't find image file $imagefile in $filename\n";
|
---|
217 | }
|
---|
218 | }
|
---|
219 |
|
---|
220 | if ($foundimage) {
|
---|
221 | return "${front}_httpcollection_/archives/_thisOID_/${imagefile}${back}";
|
---|
222 | } else {
|
---|
223 | return "";
|
---|
224 | }
|
---|
225 | }
|
---|
226 |
|
---|
227 | 1;
|
---|
228 |
|
---|
229 |
|
---|
230 |
|
---|
231 |
|
---|
232 |
|
---|
233 |
|
---|
234 |
|
---|
235 |
|
---|
236 |
|
---|
237 |
|
---|
238 |
|
---|