Changeset 34921 for main/trunk/greenstone2/perllib/cpan/Image/ExifTool/CaptureOne.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/CaptureOne.pm (modified) (12 diffs)

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

@@ -18 +18 @@
 use Image::ExifTool::ZIP;
 
-$VERSION = '1.02';
+$VERSION = '1.04';
 
 # CaptureOne COS XML tags
@@ -34 +34 @@
 # Inputs: 0) attribute list ref, 1) attr hash ref,
 #         2) property name ref, 3) property value ref
+# Returns: true if value was changed
 sub HandleCOSAttrs($$$$)
 {
     my ($attrList, $attrs, $prop, $valPt) = @_;
+    my $changed;
     if (not length $$valPt and defined $$attrs{K} and defined $$attrs{V}) {
         $$prop = $$attrs{K};
@@ -51 +53 @@
             }
         }
-    }
+        $changed = 1;
+    }
+    return $changed;
 }
 
@@ -62 +66 @@
 sub FoundCOS($$$$;$)
 {
-    my ($exifTool, $tagTablePtr, $props, $val, $attrs) = @_;
+    my ($et, $tagTablePtr, $props, $val, $attrs) = @_;
 
     my $tag = $$props[-1];
     unless ($$tagTablePtr{$tag}) {
-        $exifTool->VPrint(0, "  | [adding $tag]\n");
+        $et->VPrint(0, "  | [adding $tag]\n");
         my $name = ucfirst $tag;
         $name =~ tr/-_a-zA-Z0-9//dc;
@@ -78 +82 @@
             $tagInfo{PrintConv} = '$self->ConvertDateTime($val)';
         }
-        Image::ExifTool::AddTagToTable($tagTablePtr, $tag, \%tagInfo);
+        AddTagToTable($tagTablePtr, $tag, \%tagInfo);
     }
     # convert from UTF8 to ExifTool Charset
-    $val = $exifTool->Decode($val, "UTF8");
+    $val = $et->Decode($val, "UTF8");
     # un-escape XML character entities
     $val = Image::ExifTool::XMP::UnescapeXML($val);
-    $exifTool->HandleTag($tagTablePtr, $tag, $val);
+    $et->HandleTag($tagTablePtr, $tag, $val);
     return 0;
 }
@@ -94 +98 @@
 sub ProcessCOS($$)
 {
-    my ($exifTool, $dirInfo) = @_;
+    my ($et, $dirInfo) = @_;
 
     # process using XMP module, but override handling of attributes and tags
@@ -102 +106 @@
     };
     my $tagTablePtr = GetTagTable('Image::ExifTool::CaptureOne::Main');
-    my $success = $exifTool->ProcessDirectory($dirInfo, $tagTablePtr);
+    my $success = $et->ProcessDirectory($dirInfo, $tagTablePtr);
     delete $$dirInfo{XMLParseArgs};
     return $success;
@@ -116 +120 @@
 sub ProcessEIP($$)
 {
-    my ($exifTool, $dirInfo) = @_;
+    my ($et, $dirInfo) = @_;
     my $zip = $$dirInfo{ZIP};
     my ($file, $buff, $status, $member, %parseFile);
 
-    $exifTool->SetFileType('EIP');
+    $et->SetFileType('EIP');
 
     # must catch all Archive::Zip warnings
@@ -156 +160 @@
         $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
-        $$exifTool{DOC_NUM} = ++$docNum;
-        Image::ExifTool::ZIP::HandleMember($exifTool, $member);
+        $$et{DOC_NUM} = ++$docNum;
+        Image::ExifTool::ZIP::HandleMember($et, $member);
         if (%parseFile) {
             next unless $parseFile{$file};
@@ -170 +174 @@
         # Note: this could use a LOT of memory here for RAW images...
         ($buff, $status) = $zip->contents($member);
-        $status and $exifTool->Warn("Error extracting $file"), next;
+        $status and $et->Warn("Error extracting $file"), next;
         if ($file =~ /\.cos$/i) {
             # process Capture One Settings files
@@ -178 +182 @@
                 DataLen => length $buff,
             );
-            ProcessCOS($exifTool, \%dirInfo);
+            ProcessCOS($et, \%dirInfo);
         } else {
             # set HtmlDump error if necessary because it doesn't work with embedded files
-            if ($$exifTool{HTML_DUMP}) {
-                $$exifTool{HTML_DUMP}{Error} = "Sorry, can't dump images embedded in ZIP files";
+            if ($$et{HTML_DUMP}) {
+                $$et{HTML_DUMP}{Error} = "Sorry, can't dump images embedded in ZIP files";
             }
             # process IIQ, JPEG and TIFF images
-            $exifTool->ExtractInfo(\$buff, { ReEntry => 1 });
+            $et->ExtractInfo(\$buff, { ReEntry => 1 });
         }
         undef $buff;    # (free memory now)
     }
-    delete $$exifTool{DOC_NUM};
+    delete $$et{DOC_NUM};
     return 1;
 }
@@ -218 +222 @@
 =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