| 1 | ###########################################################################
|
|---|
| 2 | #
|
|---|
| 3 | # GMLPlug.pm --
|
|---|
| 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 | # plugin which processes a GML format document
|
|---|
| 27 | # assumes that gml tags are all in lower-case.
|
|---|
| 28 |
|
|---|
| 29 | package GMLPlug;
|
|---|
| 30 |
|
|---|
| 31 | use BasPlug;
|
|---|
| 32 | use util;
|
|---|
| 33 | use doc;
|
|---|
| 34 |
|
|---|
| 35 | sub BEGIN {
|
|---|
| 36 | @ISA = ('BasPlug');
|
|---|
| 37 | }
|
|---|
| 38 |
|
|---|
| 39 | sub new {
|
|---|
| 40 | my ($class) = @_;
|
|---|
| 41 | my $self = new BasPlug ("GMLPlug", @_);
|
|---|
| 42 |
|
|---|
| 43 | return bless $self, $class;}
|
|---|
| 44 |
|
|---|
| 45 | sub get_default_process_exp {
|
|---|
| 46 | my $self = shift (@_);
|
|---|
| 47 |
|
|---|
| 48 | return q^(?i)\.gml?$^;
|
|---|
| 49 | }
|
|---|
| 50 |
|
|---|
| 51 | # return number of files processed, undef if can't process
|
|---|
| 52 | # Note that $base_dir might be "" and that $file might
|
|---|
| 53 | # include directories
|
|---|
| 54 | sub read {
|
|---|
| 55 | my $self = shift (@_);
|
|---|
| 56 | my ($pluginfo, $base_dir, $file, $metadata, $processor, $maxdocs) = @_;
|
|---|
| 57 | my $outhandle = $self->{'outhandle'};
|
|---|
| 58 |
|
|---|
| 59 | my $filename = $file;
|
|---|
| 60 | $filename = &util::filename_cat ($base_dir, $file) if $base_dir =~ /\w/;
|
|---|
| 61 |
|
|---|
| 62 | return 0 if $self->{'block_exp'} ne "" && $filename =~ /$self->{'block_exp'}/;
|
|---|
| 63 | if ($filename !~ /$self->{'process_exp'}/ || !-f $filename) {
|
|---|
| 64 | return undef;
|
|---|
| 65 | }
|
|---|
| 66 | $file =~ s/^[\/\\]+//; # $file often begins with / so we'll tidy it up
|
|---|
| 67 |
|
|---|
| 68 | print $outhandle "GMLPlug: processing $file\n";
|
|---|
| 69 |
|
|---|
| 70 | my $parent_dir = $file;
|
|---|
| 71 | $parent_dir =~ s/[^\\\/]*$//;
|
|---|
| 72 | $parent_dir = &util::filename_cat ($base_dir, $parent_dir);
|
|---|
| 73 |
|
|---|
| 74 | if (!open (INFILE, $filename)) {
|
|---|
| 75 | print $outhandle "GMLPlug::read - couldn't read $filename\n";
|
|---|
| 76 | return 0;
|
|---|
| 77 | }
|
|---|
| 78 |
|
|---|
| 79 | undef $/;
|
|---|
| 80 | my $gml = <INFILE>;
|
|---|
| 81 | $/ = "\n";
|
|---|
| 82 | close (INFILE);
|
|---|
| 83 |
|
|---|
| 84 | my @gml_sections = split("</gsdlsection>",$gml);
|
|---|
| 85 | $gml = shift(@gml_sections);
|
|---|
| 86 |
|
|---|
| 87 | my $no_docs = 0;
|
|---|
| 88 |
|
|---|
| 89 | while (1) {
|
|---|
| 90 | # create a new document
|
|---|
| 91 | my $doc_obj = new doc ();
|
|---|
| 92 | my $section = $doc_obj->get_top_section();
|
|---|
| 93 |
|
|---|
| 94 | # process the document
|
|---|
| 95 | my $firstsection = 1;
|
|---|
| 96 | while (1) {
|
|---|
| 97 | my ($tags, $text) = ("", "");
|
|---|
| 98 |
|
|---|
| 99 | my @indenting_sections = split("<gsdlsection", $gml);
|
|---|
| 100 | shift(@indenting_sections); # skips over xml header if present
|
|---|
| 101 |
|
|---|
| 102 | foreach $gml (@indenting_sections) {
|
|---|
| 103 |
|
|---|
| 104 | if ($gml =~ /^\s*([^>]*)>(.*)$/so) {
|
|---|
| 105 | $tags = $1 if defined $1;
|
|---|
| 106 | $text = &GMLPlug::_unescape_text($2);
|
|---|
| 107 |
|
|---|
| 108 | } else {
|
|---|
| 109 | print $outhandle "GMLPlug::read - error in file $filename\n";
|
|---|
| 110 | print $outhandle "text: \"$gml\"\n";
|
|---|
| 111 | last;
|
|---|
| 112 | }
|
|---|
| 113 |
|
|---|
| 114 | # create the section (unless this is the first section)
|
|---|
| 115 | if ($firstsection) {
|
|---|
| 116 | $firstsection = 0;
|
|---|
| 117 | # $tags =~ /gsdlsourcefilename\s*=\s*(?:\"([^\"]*)\")/o;
|
|---|
| 118 | # $src_filename = $2 || $3;
|
|---|
| 119 |
|
|---|
| 120 | } else {
|
|---|
| 121 |
|
|---|
| 122 | $tags =~ s/gsdlnum\s*=\s*\"?(\d+)\"?//o;
|
|---|
| 123 | if (defined $1) {
|
|---|
| 124 | $section .= ".$1";
|
|---|
| 125 | $doc_obj->create_named_section($section);
|
|---|
| 126 | } else {
|
|---|
| 127 | $section = $doc_obj->insert_section($doc_obj->get_end_child($section));
|
|---|
| 128 | }
|
|---|
| 129 | }
|
|---|
| 130 |
|
|---|
| 131 | # add the metadata
|
|---|
| 132 | # could be stored as either attributes or ....
|
|---|
| 133 | while ((defined $tags) && ($tags =~ s/^\s*(\S+)=\"([^\"]*)\"//o)) {
|
|---|
| 134 | $doc_obj->add_utf8_metadata($section, $1, &GMLPlug::_unescape_text($2))
|
|---|
| 135 | if (defined $1 and defined $2);
|
|---|
| 136 |
|
|---|
| 137 | }
|
|---|
| 138 |
|
|---|
| 139 | # ... or tags (xml compliant)
|
|---|
| 140 | if ($text =~ m/^\s*<metadata>/)
|
|---|
| 141 | {
|
|---|
| 142 | my ($metadata, $tagname, $tagvalue);
|
|---|
| 143 | ($metadata,$text)
|
|---|
| 144 | = ($text =~ m/\s*<metadata>\s*(<.*)\s*<\/metadata>(.*)$/s);
|
|---|
| 145 |
|
|---|
| 146 | # note: \1 refers to 1st match within regexp, so we can
|
|---|
| 147 | # handle the unescaped text here...
|
|---|
| 148 | while ((defined $metadata)
|
|---|
| 149 | && ($metadata =~ s/<(.*?)>(.*?)<\/\1>//s))
|
|---|
| 150 | {
|
|---|
| 151 | if (defined $1 && defined $2)
|
|---|
| 152 | {
|
|---|
| 153 | $tagname = $1;
|
|---|
| 154 | $tagvalue = $2;
|
|---|
| 155 |
|
|---|
| 156 | # if tagname begins with '/' it will be escaped
|
|---|
| 157 | $tagname =~ s/^&\#47;/\//;
|
|---|
| 158 |
|
|---|
| 159 | $doc_obj->add_utf8_metadata($section, $tagname, &GMLPlug::_unescape_text($tagvalue));
|
|---|
| 160 | }
|
|---|
| 161 | }
|
|---|
| 162 | }
|
|---|
| 163 |
|
|---|
| 164 | # add the text
|
|---|
| 165 |
|
|---|
| 166 | $doc_obj->add_utf8_text($section, $text)
|
|---|
| 167 | if ((defined $text) && ($text ne ""));
|
|---|
| 168 | }
|
|---|
| 169 |
|
|---|
| 170 | $gml = shift(@gml_sections); # get next bit of data
|
|---|
| 171 | last unless defined $gml;
|
|---|
| 172 | last if $section eq ""; # back to top level again (more than one document in gml file)
|
|---|
| 173 | $section = $doc_obj->get_parent_section ($section);
|
|---|
| 174 | } # while (1) section level
|
|---|
| 175 |
|
|---|
| 176 | # add the associated files
|
|---|
| 177 | my $assoc_files = $doc_obj->get_metadata($doc_obj->get_top_section(), "gsdlassocfile");
|
|---|
| 178 | my ($assoc_file_info);
|
|---|
| 179 |
|
|---|
| 180 | foreach $assoc_file_info (@$assoc_files)
|
|---|
| 181 | {
|
|---|
| 182 | my ($assoc_file, $mime_type, $dir) = split (":", $assoc_file_info);
|
|---|
| 183 | my $real_dir = &util::filename_cat($parent_dir, $assoc_file),
|
|---|
| 184 | my $assoc_dir = (defined $dir && $dir ne "")
|
|---|
| 185 | ? &util::filename_cat($dir, $assoc_file) : $assoc_file;
|
|---|
| 186 | $doc_obj->associate_file($real_dir, $assoc_dir, $mime_type);
|
|---|
| 187 |
|
|---|
| 188 | }
|
|---|
| 189 | $doc_obj->delete_metadata($doc_obj->get_top_section(), "gsdlassocfile");
|
|---|
| 190 |
|
|---|
| 191 | # add metadata passed in from elsewhere
|
|---|
| 192 | $self->extra_metadata ($doc_obj, $doc_obj->get_top_section(), $metadata);
|
|---|
| 193 |
|
|---|
| 194 | # do any automatic metadata extraction
|
|---|
| 195 | $self->auto_extract_metadata ($doc_obj);
|
|---|
| 196 |
|
|---|
| 197 | # assume the document has an OID already
|
|---|
| 198 |
|
|---|
| 199 | # process the document
|
|---|
| 200 | $processor->process($doc_obj, $file);
|
|---|
| 201 |
|
|---|
| 202 | $no_docs++;
|
|---|
| 203 | last if ($maxdocs > -1 && $no_docs >= $maxdocs);
|
|---|
| 204 | last unless defined $gml && $gml =~ /\w/;
|
|---|
| 205 | } # while(1) document level
|
|---|
| 206 |
|
|---|
| 207 | return $no_docs; # no of docs processed
|
|---|
| 208 | }
|
|---|
| 209 |
|
|---|
| 210 | sub _unescape_text {
|
|---|
| 211 | my ($text) = @_;
|
|---|
| 212 |
|
|---|
| 213 | # special characters in the gml encoding
|
|---|
| 214 | $text =~ s/</</g;
|
|---|
| 215 | $text =~ s/>/>/g;
|
|---|
| 216 | $text =~ s/"/\"/g;
|
|---|
| 217 | $text =~ s/&/&/g; # this has to be last...
|
|---|
| 218 |
|
|---|
| 219 | return $text;
|
|---|
| 220 | }
|
|---|
| 221 |
|
|---|
| 222 | 1;
|
|---|
