Changeset 34921 for main/trunk/greenstone2/perllib/cpan/Image/ExifTool/InDesign.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/InDesign.pm (modified) (13 diffs)

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

@@ -15 +15 @@
 use Image::ExifTool qw(:DataAccess :Utils);
 
-$VERSION = '1.02';
+$VERSION = '1.06';
 
 # map for writing metadata to InDesign files (currently only write XMP)
@@ -33 +33 @@
 sub ProcessIND($$)
 {
-    my ($exifTool, $dirInfo) = @_;
+    my ($et, $dirInfo) = @_;
     my $raf = $$dirInfo{RAF};
     my $outfile = $$dirInfo{OutFile};
@@ -42 +42 @@
     return 0 unless $hdr eq $masterPageGUID;
     return 0 unless $raf->Read($buff, 8) == 8;
-    $exifTool->SetFileType($buff eq 'DOCUMENT' ? 'INDD' : 'IND');   # set the FileType tag
+    $et->SetFileType($buff eq 'DOCUMENT' ? 'INDD' : 'IND');   # set the FileType tag
 
     # read the master pages
@@ -74 +74 @@
     $pages < 2 and $err = 'Invalid page count', goto DONE;
     my $pos = $pages * 4096;
-    if ($pos > 0x7fffffff and not $exifTool->Options('LargeFileSupport')) {
+    if ($pos > 0x7fffffff and not $et->Options('LargeFileSupport')) {
         $err = 'InDesign files larger than 2 GB not supported (LargeFileSupport not set)';
         goto DONE;
@@ -80 +80 @@
     if ($outfile) {
         # make XMP the preferred group for writing
-        $exifTool->InitWriteDirs(\%indMap, 'XMP');
+        $et->InitWriteDirs(\%indMap, 'XMP');
 
         Write($outfile, $buff, $buf2) or $err = 1, goto DONE;
@@ -93 +93 @@
     }
     # scan through the contiguous objects for XMP
-    my $verbose = $exifTool->Options('Verbose');
-    my $out = $exifTool->Options('TextOut');
+    my $verbose = $et->Options('Verbose');
+    my $out = $et->Options('TextOut');
     for (;;) {
         $raf->Read($hdr, 32) or last;
@@ -106 +106 @@
             printf $out "Contiguous object at offset 0x%x (%d bytes):\n", $raf->Tell(), $len;
             if ($verbose > 2) {
-                my %parms = (Addr => $raf->Tell());
-                $parms{MaxLen} = $verbose > 3 ? 1024 : 96 if $verbose < 5;
-                $raf->Seek(-$raf->Read($buff, $len), 1) or $err = 1;
-                Image::ExifTool::HexDump(\$buff, undef, %parms);
+                my $len2 = $len < 1024000 ? $len : 1024000;
+                $raf->Seek(-$raf->Read($buff, $len2), 1) or $err = 1;
+                $et->VerboseDump(\$buff, Addr => $raf->Tell());
             }
         }
@@ -119 +118 @@
                 my $lenWord = $1;   # save length word for writing later
                 $len -= 4;          # get length of XMP only
+                $foundXMP = 1;
+                # I have a sample where the XMP is 107 MB, and ActivePerl may run into
+                # memory troubles (with its apparent 1 GB limit) if the XMP is larger
+                # than about 400 MB, so guard against this
+                if ($len > 300 * 1024 * 1024) {
+                    my $msg = sprintf('Insanely large XMP (%.0f MB)', $len / (1024 * 1024));
+                    if ($outfile) {
+                        $et->Error($msg, 2) and $err = 1, last;
+                    } elsif ($et->Options('IgnoreMinorErrors')) {
+                        $et->Warn($msg);
+                    } else {
+                        $et->Warn("$msg. Ignored.", 1);
+                        $err = 1;
+                        last;
+                    }
+                }
                 # load and parse the XMP data
                 unless ($raf->Seek(-52, 1) and $raf->Read($buff, $len) == $len) {
@@ -124 +139 @@
                     last;
                 }
-                $foundXMP = 1;
                 my %dirInfo = (
                     DataPt  => \$buff,
@@ -130 +144 @@
                     NoDelete => 1, # do not allow this to be deleted when writing
                 );
+                # validate xmp data length (should be same as length in header - 4)
+                my $xmpLen = unpack($streamInt32u, $lenWord);
+                unless ($xmpLen == $len) {
+                    if ($xmpLen < $len) {
+                        $dirInfo{DirLen} = $xmpLen;
+                    } else {
+                        $err = 'Truncated XMP stream (missing ' . ($xmpLen - $len) . ' bytes)';
+                    }
+                }
                 my $tagTablePtr = GetTagTable('Image::ExifTool::XMP::Main');
                 if ($outfile) {
-                    # validate xmp data length (should be same as length in header - 4)
-                    my $xmpLen = unpack($streamInt32u, $lenWord);
-                    unless ($xmpLen == $len) {
-                        $err = "Incorrect XMP stream length ($xmpLen should be $len)";
-                        last;
-                    }
+                    last if $err;
                     # make sure that XMP is writable
                     my $classID = Get32u(\$hdr, 20);
                     $classID & 0x40000000 or $err = 'XMP stream is not writable', last;
-                    my $xmp = $exifTool->WriteDirectory(\%dirInfo, $tagTablePtr);
+                    my $xmp = $et->WriteDirectory(\%dirInfo, $tagTablePtr);
                     if ($xmp and length $xmp) {
                         # write new xmp with leading length word
@@ -149 +167 @@
                         Set32u(0xffffffff, \$hdr, 28);
                     } else {
-                        $$exifTool{CHANGED} = 0;    # didn't change anything
-                        $exifTool->Warn("Can't delete XMP as a block from InDesign file") if defined $xmp;
+                        $$et{CHANGED} = 0;    # didn't change anything
+                        $et->Warn("Can't delete XMP as a block from InDesign file") if defined $xmp;
                         # put length word back at start of stream
                         $buff = $lenWord . $buff;
                     }
                 } else {
-                    $exifTool->ProcessDirectory(\%dirInfo, $tagTablePtr);
+                    $et->ProcessDirectory(\%dirInfo, $tagTablePtr);
                 }
                 $len = 0;   # we got the full stream (nothing left to read)
@@ -198 +216 @@
 DONE:
     if (not $err) {
-        $exifTool->Warn('No XMP stream to edit') if $outfile and not $foundXMP;
+        $et->Warn('No XMP stream to edit') if $outfile and not $foundXMP;
         return 1;       # success!
     } elsif (not $outfile) {
         # issue warning on read error
-        $exifTool->Warn($err) unless $err eq '1';
+        $et->Warn($err) unless $err eq '1';
     } elsif ($err ne '1') {
         # set error and return success code
-        $exifTool->Error($err);
+        $et->Error($err);
     } else {
         return -1;      # write error
@@ -236 +254 @@
 InDesign files which previously contained XMP.
 
-3) File sizes of greater than 2 GB and are not currently supported because
-the ability to handle large files like this is system dependent.
+3) File sizes of greater than 2 GB are supported only if the system supports
+them and the LargeFileSupport option is enabled.
 
 =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