1 | ###########################################################################
|
---|
2 | #
|
---|
3 | # HTMLPlug.pm -- basic html 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 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 simple single-level document from .htm or .html files
|
---|
27 | # (case-insensitive match on filenames). Adds Title metadata
|
---|
28 | # taken from <title> tags if found otherwise first 100 characters
|
---|
29 | # outside of tags.
|
---|
30 | # will also attempt to include images which it will search for in
|
---|
31 | # the same directory as the document itself (it will also search
|
---|
32 | # directories relative to that directory).
|
---|
33 |
|
---|
34 | # this plugin currently does nothing with href links so relative links
|
---|
35 | # may become broken.
|
---|
36 |
|
---|
37 |
|
---|
38 | package HTMLPlug;
|
---|
39 |
|
---|
40 | use BasPlug;
|
---|
41 | use sorttools;
|
---|
42 | use util;
|
---|
43 |
|
---|
44 | sub BEGIN {
|
---|
45 | @ISA = ('BasPlug');
|
---|
46 | }
|
---|
47 |
|
---|
48 | sub new {
|
---|
49 | my ($class) = @_;
|
---|
50 | $self = new BasPlug ();
|
---|
51 |
|
---|
52 | return bless $self, $class;
|
---|
53 | }
|
---|
54 |
|
---|
55 | sub is_recursive {
|
---|
56 | my $self = shift (@_);
|
---|
57 |
|
---|
58 | return 0; # this is not a recursive plugin
|
---|
59 | }
|
---|
60 |
|
---|
61 |
|
---|
62 | # return number of files processed, undef if can't process
|
---|
63 | # Note that $base_dir might be "" and that $file might
|
---|
64 | # include directories
|
---|
65 | sub read {
|
---|
66 | my $self = shift (@_);
|
---|
67 | my ($pluginfo, $base_dir, $file, $metadata, $processor) = @_;
|
---|
68 |
|
---|
69 | my $filename = &util::filename_cat($base_dir, $file);
|
---|
70 | my $absdir = $filename;
|
---|
71 | $absdir =~ s/[^\/\\]*$//;
|
---|
72 |
|
---|
73 | return undef unless ($filename =~ /\.(html?(\.gz)?)$/i && (-e $filename));
|
---|
74 |
|
---|
75 | my $gz = 0;
|
---|
76 | if (defined $2) {
|
---|
77 | $gz = $2;
|
---|
78 | $gz = 1 if ($gz =~ /\.gz/i);
|
---|
79 | }
|
---|
80 |
|
---|
81 | print STDERR "HTMLPlug: processing $filename\n" if $processor->{'verbosity'};
|
---|
82 |
|
---|
83 | # create a new document
|
---|
84 | my $doc_obj = new doc ($file, "indexed_doc");
|
---|
85 |
|
---|
86 | if ($gz) {
|
---|
87 | open (FILE, "zcat $filename |") || die "HTMLPlug::read - zcat can't open $filename\n";
|
---|
88 | } else {
|
---|
89 | open (FILE, $filename) || die "HTMLPlug::read - can't open $filename\n";
|
---|
90 | }
|
---|
91 | my $cursection = $doc_obj->get_top_section();
|
---|
92 |
|
---|
93 | my $text = "";
|
---|
94 | my $line = "";
|
---|
95 | my $donehead = 0;
|
---|
96 | my $title = "";
|
---|
97 | while (defined ($line = <FILE>)) {
|
---|
98 | $text .= $line;
|
---|
99 | }
|
---|
100 |
|
---|
101 | # remove line breaks
|
---|
102 | $text =~ s/\s+/ /g;
|
---|
103 |
|
---|
104 | # see if there's a <title> tag
|
---|
105 | my $foundtitle = 0;
|
---|
106 | if ($text =~ /<title[^>]*>([^<]*)<\/title[^>]*>/i) {
|
---|
107 | if (defined $1) {
|
---|
108 | my $title = $1;
|
---|
109 | if ($title =~ /\w/) {
|
---|
110 | $doc_obj->add_metadata ($cursection, "Title", $title);
|
---|
111 | $foundtitle = 1;
|
---|
112 | }
|
---|
113 | }
|
---|
114 | }
|
---|
115 | # if no title use first 100 characters
|
---|
116 | if (!$foundtitle) {
|
---|
117 | my $tmptext = $text;
|
---|
118 | $tmptext =~ s/<[^>]*>//g;
|
---|
119 | my $title = substr ($tmptext, 0, 100);
|
---|
120 | $doc_obj->add_metadata ($cursection, "Title", $title);
|
---|
121 | }
|
---|
122 |
|
---|
123 | # remove header rubbish
|
---|
124 | $text =~ s/^.*?<body[^>]*>//i;
|
---|
125 |
|
---|
126 | # fix up the image links
|
---|
127 | $text =~ s/(<img[^>]*?src\s*=\s*\"?)([^\">]+)(\"?[^>]*>)/
|
---|
128 | &replace_image_links($absdir, $doc_obj, $1, $2, $3)/ige;
|
---|
129 |
|
---|
130 | # add a newline at the beginning of each paragraph
|
---|
131 | $text =~ s/(.)\s*<p\b/$1\n\n<p/gi;
|
---|
132 |
|
---|
133 | # add a newline every 80 characters at a word boundary
|
---|
134 | # Note: this regular expression puts a line feed before
|
---|
135 | # the last word in each section, even when it is not
|
---|
136 | # needed.
|
---|
137 | $text =~ s/(.{1,80})\s/$1\n/g;
|
---|
138 |
|
---|
139 | $doc_obj->add_text ($cursection, $text);
|
---|
140 |
|
---|
141 | foreach $field (keys(%$metadata)) {
|
---|
142 | # $metadata->{$field} may be an array reference
|
---|
143 | if (ref ($metadata->{$field}) eq "ARRAY") {
|
---|
144 | map {
|
---|
145 | $doc_obj->add_metadata ($cursection, $field, $_);
|
---|
146 | } @{$metadata->{$field}};
|
---|
147 | } else {
|
---|
148 | $doc_obj->add_metadata ($cursection, $field, $metadata->{$field});
|
---|
149 | }
|
---|
150 | }
|
---|
151 |
|
---|
152 | # add OID
|
---|
153 | $doc_obj->set_OID ();
|
---|
154 |
|
---|
155 | # process the document
|
---|
156 | $processor->process($doc_obj);
|
---|
157 |
|
---|
158 | return 1; # processed the file
|
---|
159 | }
|
---|
160 |
|
---|
161 | sub replace_image_links {
|
---|
162 |
|
---|
163 | my ($dir, $doc_obj, $front, $link, $back) = @_;
|
---|
164 |
|
---|
165 | my ($filename, $error);
|
---|
166 | my $foundimage = 0;
|
---|
167 |
|
---|
168 | $link =~ s/\/\///;
|
---|
169 | my ($imagetype) = $link =~ /([^\.]*)$/;
|
---|
170 | $imagetype =~ tr/[A-Z]/[a-z]/;
|
---|
171 | if ($imagetype eq "jpg") {$imagetype = "jpeg";}
|
---|
172 | if ($imagetype !~ /^(jpg|gif|png)$/) {
|
---|
173 | print STDERR "HTMLPlug: Warning - unknown image type ($imagetype)\n";
|
---|
174 | }
|
---|
175 | my ($imagefile) = $link =~ /([^\/]*)$/;
|
---|
176 | my ($imagepath) = $link =~ /^[^\/]*(.*)$/;
|
---|
177 |
|
---|
178 | if (defined $imagepath && $imagepath =~ /\w/) {
|
---|
179 | # relative link
|
---|
180 | $filename = &util::filename_cat ($dir, $imagepath);
|
---|
181 | if (-e $filename) {
|
---|
182 | $doc_obj->associate_file ($filename, $imagefile, "image/$imagetype");
|
---|
183 | $foundimage = 1;
|
---|
184 | } else {
|
---|
185 | $error = "HTMLPlug: Warning - couldn't find image file $imagefile in either $filename or";
|
---|
186 | }
|
---|
187 | }
|
---|
188 |
|
---|
189 | if (!$foundimage) {
|
---|
190 | $filename = &util::filename_cat ($dir, $imagefile);
|
---|
191 | if (-e $filename) {
|
---|
192 | $doc_obj->associate_file ($filename, $imagefile, "image/$imagetype");
|
---|
193 | $foundimage = 1;
|
---|
194 | } elsif (defined $error) {
|
---|
195 | print STDERR "$error $filename\n";
|
---|
196 | } else {
|
---|
197 | print STDERR "HTMLPlug: Warning - couldn't find image file $imagefile in $filename\n";
|
---|
198 | }
|
---|
199 | }
|
---|
200 |
|
---|
201 | if ($foundimage) {
|
---|
202 | return "${front}_httpcollection_/archives/_thisOID_/${imagefile}${back}";
|
---|
203 | } else {
|
---|
204 | return "";
|
---|
205 | }
|
---|
206 | }
|
---|
207 |
|
---|
208 | 1;
|
---|
209 |
|
---|
210 |
|
---|
211 |
|
---|
212 |
|
---|
213 |
|
---|
214 |
|
---|
215 |
|
---|
216 |
|
---|
217 |
|
---|
218 |
|
---|
219 |
|
---|