Changeset 34921 for main/trunk/greenstone2/perllib/cpan/Image/ExifTool/DjVu.pm

Timestamp:

2021-02-26T19:39:51+13:00 (3 years ago)

Author:

anupama

Message:

Committing the improvements to EmbeddedMetaPlugin's processing of Keywords vs other metadata fields. Keywords were literally stored as arrays of words rather than phrases in PDFs (at least in Diego's sample PDF), whereas other meta fields like Subjects and Creators stored them as arrays of phrases. To get both to work, Kathy updated EXIF to a newer version, to retrieve the actual EXIF values stored in the PDF. And Kathy and Dr Bainbridge came up with a new option that I added called apply_join_before_split_to_metafields that's a regex which can list the metadata fields to apply the join_before_split to and whcih previously always got applied to all metadata fields. Now it's applied to any *Keywords metafields by default, as that's the metafield we have experience of that behaves differently to the others, as it stores by word instead of phrases. Tested on Diego's sample PDF. Diego has double-checked it to works on his sample PDF too, setting the split char to ; and turning on the join_before_split and leaving apply_join_before_split_to_metafields at its default of .*Keywords. File changes are strings.properties for the tooltip, the plugin introducing the option and working with it and Kathy's EXIF updates affecting cpan/File and cpan/Image.

File:

• main/trunk/greenstone2/perllib/cpan/Image/ExifTool/DjVu.pm (modified) (12 diffs)

main/trunk/greenstone2/perllib/cpan/Image/ExifTool/DjVu.pm

@@ -19 +19 @@
 use Image::ExifTool qw(:DataAccess :Utils);
 
-$VERSION = '1.03';
+$VERSION = '1.06';
 
 sub ParseAnt($);
@@ -29 +29 @@
 %Image::ExifTool::DjVu::Main = (
     GROUPS => { 2 => 'Image' },
-    NOTES => 'Information is extracted from the following chunks in DjVu images.',
+    NOTES => q{
+        Information is extracted from the following chunks in DjVu images. See
+        L<http://www.djvu.org/> for the DjVu specification.
+    },
     INFO => {
         SubDirectory => { TagTable => 'Image::ExifTool::DjVu::Info' },
@@ -136 +139 @@
         documentation endorses tags borrowed from two standards: 1) BibTeX
         bibliography system tags (all lowercase Tag ID's in the table below), and 2)
-        PDF DocInfo tags (uppercase Tag ID's).
+        PDF DocInfo tags (capitalized Tag ID's).
     },
     # BibTeX tags (ref http://en.wikipedia.org/wiki/BibTeX)
@@ -225 +228 @@
                 $tok .= '"';    # quote is part of the string
             }
+            # must protect unescaped "$" and "@" symbols, and "\" at end of string
+            $tok =~ s{\\(.)|([\$\@]|\\$)}{'\\'.($2 || $1)}sge;
             # convert C escape sequences (allowed in quoted text)
             $tok = eval qq{"$tok"};
@@ -231 +236 @@
             # allow anything in key but whitespace, braces and double quotes
             # (this is one of those assumptions I mentioned)
-            $$dataPt =~ /([^\s()"]+)/sg;
-            $tok = $1;
+            $tok = $$dataPt =~ /([^\s()"]+)/sg ? $1 : undef;
         }
         push @toks, $tok if defined $tok;
@@ -247 +251 @@
 sub ProcessAnt($$$)
 {
-    my ($exifTool, $dirInfo, $tagTablePtr) = @_;
+    my ($et, $dirInfo, $tagTablePtr) = @_;
     my $dataPt = $$dirInfo{DataPt};
 
@@ -265 +269 @@
         if ($tag eq 'metadata') {
             # ProcessMeta() takes array reference
-            $exifTool->HandleTag($tagTablePtr, $tag, $ant);
+            $et->HandleTag($tagTablePtr, $tag, $ant);
         } else {
             next if ref $$ant[0];   # only process simple values
-            $exifTool->HandleTag($tagTablePtr, $tag, $$ant[0]);
+            $et->HandleTag($tagTablePtr, $tag, $$ant[0]);
         }
     }
@@ -281 +285 @@
 sub ProcessMeta($$$)
 {
-    my ($exifTool, $dirInfo, $tagTablePtr) = @_;
+    my ($et, $dirInfo, $tagTablePtr) = @_;
     my $dataPt = $$dirInfo{DataPt};
     return 0 unless ref $$dataPt eq 'ARRAY';
-    $exifTool->VerboseDir('Metadata', scalar @$$dataPt);
+    $et->VerboseDir('Metadata', scalar @$$dataPt);
     my ($item, $err);
     foreach $item (@$$dataPt) {
@@ -295 +299 @@
             $name =~ tr/-_a-zA-Z0-9//dc; # remove illegal characters
             length $name or $err = 1, next;
-            Image::ExifTool::AddTagToTable($tagTablePtr, $$item[0], { Name => ucfirst($name) });
+            AddTagToTable($tagTablePtr, $$item[0], { Name => ucfirst($name) });
         }
-        $exifTool->HandleTag($tagTablePtr, $$item[0], $$item[1]);
-    }
-    $err and $exifTool->Warn('Ignored invalid metadata entry(s)');
+        $et->HandleTag($tagTablePtr, $$item[0], $$item[1]);
+    }
+    $err and $et->Warn('Ignored invalid metadata entry(s)');
     return 1;
 }
@@ -309 +313 @@
 sub ProcessBZZ($$$)
 {
-    my ($exifTool, $dirInfo, $tagTablePtr) = @_;
+    my ($et, $dirInfo, $tagTablePtr) = @_;
     require Image::ExifTool::BZZ;
     my $buff = Image::ExifTool::BZZ::Decode($$dirInfo{DataPt});
     unless (defined $buff) {
-        $exifTool->Warn("Error decoding $$dirInfo{DirName}");
+        $et->Warn("Error decoding $$dirInfo{DirName}");
         return 0;
     }
-    my $verbose = $exifTool->Options('Verbose');
+    my $verbose = $et->Options('Verbose');
     if ($verbose >= 3) {
         # dump the decoded data in very verbose mode
-        $exifTool->VerboseDir("Decoded $$dirInfo{DirName}", 0, length $buff);
-        $exifTool->VerboseDump(\$buff);
+        $et->VerboseDir("Decoded $$dirInfo{DirName}", 0, length $buff);
+        $et->VerboseDump(\$buff);
     }
     $$dirInfo{DataPt} = \$buff;
@@ -326 +330 @@
     # process the data using the default process proc for this table
     my $processProc = $$tagTablePtr{PROCESS_PROC} or return 0;
-    return &$processProc($exifTool, $dirInfo, $tagTablePtr);
+    return &$processProc($et, $dirInfo, $tagTablePtr);
 }
 
@@ -349 +353 @@
 =head1 AUTHOR
 
-Copyright 2003-2011, Phil Harvey (phil at owl.phy.queensu.ca)
+Copyright 2003-2021, Phil Harvey (philharvey66 at gmail.com)
 
 This library is free software; you can redistribute it and/or modify it