Changeset 34921 for main/trunk/greenstone2/perllib/cpan/Image/ExifTool/iWork.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/iWork.pm (modified) (11 diffs)

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

@@ -15 +15 @@
 use Image::ExifTool::ZIP;
 
-$VERSION = '1.02';
-
-# test for recognized iWork document extensions and outter XML elements
+$VERSION = '1.06';
+
+# test for recognized iWork document extensions and outer XML elements
 my %iWorkType = (
     # file extensions
-    NUMBERS => 'Apple Numbers',
-    PAGES   => 'Apple Pages',
-    KEY     => 'Apple Keynote',
-    KTH     => 'Apple Keynote Theme',
-    NMBTEMPLATE => 'Apple Numbers Template',
+    NUMBERS => 'NUMBERS',
+    PAGES   => 'PAGES',
+    KEY     => 'KEY',
+    KTH     => 'KTH',
+    NMBTEMPLATE => 'NMBTEMPLATE',
     # we don't support double extensions --
     # "PAGES.TEMPLATE" => 'Apple Pages Template',
-    # outter XML elements
-    'ls:document' => 'Apple Numbers',
-    'sl:document' => 'Apple Pages',
-    'key:presentation' => 'Apple Keynote',
+    # outer XML elements
+    'ls:document' => 'NUMBERS',
+    'sl:document' => 'PAGES',
+    'key:presentation' => 'KEY',
 );
 
@@ -37 +37 @@
 # indicates, but I think it refers to the new "flattened" package format)
 my %mimeType = (
-    'Apple Numbers' => 'application/x-iwork-numbers-sffnumbers',
-    'Apple Pages'   => 'application/x-iwork-pages-sffpages',
-    'Apple Keynote' => 'application/x-iWork-keynote-sffkey',
-    'Apple Numbers Template' => 'application/x-iwork-numbers-sfftemplate',
-    'Apple Pages Template'   => 'application/x-iwork-pages-sfftemplate',
-    'Apple Keynote Theme'    => 'application/x-iWork-keynote-sffkth',
+    'NUMBERS'       => 'application/x-iwork-numbers-sffnumbers',
+    'PAGES'         => 'application/x-iwork-pages-sffpages',
+    'KEY'           => 'application/x-iWork-keynote-sffkey',
+    'NMBTEMPLATE'   => 'application/x-iwork-numbers-sfftemplate',
+    'PAGES.TEMPLATE'=> 'application/x-iwork-pages-sfftemplate',
+    'KTH'           => 'application/x-iWork-keynote-sffkth',
 );
 
@@ -71 +71 @@
     my $props = shift;
     return 0 if $$props[-1] =~ /^\w+:ID$/;  # ignore ID tags
-    return ($$props[0] =~ /.*?:(.*)/) ? $1 : $$props[0];
+    return $$props[0] =~ /^.*?:(.*)/ ? $1 : $$props[0];
 }
 
@@ -82 +82 @@
 sub FoundTag($$$$;$)
 {
-    my ($exifTool, $tagTablePtr, $props, $val, $attrs) = @_;
+    my ($et, $tagTablePtr, $props, $val, $attrs) = @_;
     return 0 unless @$props;
-    my $verbose = $exifTool->Options('Verbose');
-
-    $exifTool->VPrint(0, "  | - Tag '", join('/',@$props), "'\n") if $verbose > 1;
+    my $verbose = $et->Options('Verbose');
+
+    $et->VPrint(0, "  | - Tag '", join('/',@$props), "'\n") if $verbose > 1;
 
     # un-escape XML character entities
     $val = Image::ExifTool::XMP::UnescapeXML($val);
     # convert from UTF8 to ExifTool Charset
-    $val = $exifTool->Decode($val, 'UTF8');
+    $val = $et->Decode($val, 'UTF8');
     my $tag = GetTagID($props) or return 0;
 
     # add any unknown tags to table
     unless ($$tagTablePtr{$tag}) {
-        $exifTool->VPrint(0, "  [adding $tag]\n") if $verbose;
-        Image::ExifTool::AddTagToTable($tagTablePtr, $tag, { Name => ucfirst $tag });
+        $et->VPrint(0, "  [adding $tag]\n") if $verbose;
+        AddTagToTable($tagTablePtr, $tag, { Name => ucfirst $tag });
     }
     # save the tag
-    $exifTool->HandleTag($tagTablePtr, $tag, $val);
+    $et->HandleTag($tagTablePtr, $tag, $val);
 
     return 1;
@@ -113 +113 @@
 sub Process_iWork($$)
 {
-    my ($exifTool, $dirInfo) = @_;
+    my ($et, $dirInfo) = @_;
     my $zip = $$dirInfo{ZIP};
     my ($type, $index, $indexFile, $status);
@@ -120 +120 @@
     local $SIG{'__WARN__'} = \&Image::ExifTool::ZIP::WarnProc;
     # trust type given by file extension if available
-    $type = $iWorkType{$$exifTool{FILE_EXT}} if $$exifTool{FILE_EXT};
+    $type = $iWorkType{$$et{FILE_EXT}} if $$et{FILE_EXT};
     unless ($type) {
         # read the index file
@@ -132 +132 @@
                 }
             }
+        } else {
+            @members = $zip->membersMatching('(?i)^.*\.(pages|numbers|key)/Index.*');
+            if (@members) {
+                my $tmp = $members[0]->fileName();
+                $type = $iWorkType{uc $1} if $tmp =~ /\.(pages|numbers|key)/i;
+            }
         }
         $type or $type = 'ZIP';     # assume ZIP by default
     }
-    $exifTool->SetFileType($type, $mimeType{$type});
+    $et->SetFileType($type, $mimeType{$type});
 
     my @members = $zip->members();
@@ -144 +150 @@
         my $file = $member->fileName();
         next unless defined $file;
-        $exifTool->VPrint(0, "File: $file\n");
+        $et->VPrint(0, "File: $file\n");
         # set the document number and extract ZIP tags
-        $$exifTool{DOC_NUM} = ++$docNum;
-        Image::ExifTool::ZIP::HandleMember($exifTool, $member);
-
-        # process only the index XML and JPEG thumbnail files
-        next unless $file =~ m{^(index\.(xml|apxl)|QuickLook/Thumbnail\.jpg)$}i;
+        $$et{DOC_NUM} = ++$docNum;
+        Image::ExifTool::ZIP::HandleMember($et, $member);
+
+        # process only the index XML and JPEG thumbnail/preview files
+        next unless $file =~ m{^(index\.(xml|apxl)|QuickLook/Thumbnail\.jpg|[^/]+/preview(-micro|-web)?.jpg)$}i;
         # get the file contents if necessary
         # (CAREFUL! $buff MUST be local since we hand off a value ref to PreviewImage)
@@ -159 +165 @@
         } else {
             ($buff, $status) = $zip->contents($member);
-            $status and $exifTool->Warn("Error extracting $file"), next;
+            $status and $et->Warn("Error extracting $file"), next;
             $buffPt = \$buff;
         }
         # extract JPEG as PreviewImage (should only be QuickLook/Thumbnail.jpg)
         if ($file =~ /\.jpg$/) {
-            $exifTool->FoundTag('PreviewImage', $buffPt);
+            my $type = ($file =~ /preview-(\w+)/) ? ($1 eq 'web' ? 'Other' : 'Thumbnail') : 'Preview';
+            $et->FoundTag($type . 'Image', $buffPt);
             next;
         }
@@ -183 +190 @@
         );
         my $tagTablePtr = GetTagTable('Image::ExifTool::iWork::Main');
-        $exifTool->ProcessDirectory(\%dirInfo, $tagTablePtr);
+        $et->ProcessDirectory(\%dirInfo, $tagTablePtr);
         undef $$buffPt; # (free memory now)
     }
-    delete $$exifTool{DOC_NUM};
+    delete $$et{DOC_NUM};
     return 1;
 }
@@ -209 +216 @@
 =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