Mercurial > bins

changeset 6:3021deef1599

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Encoding related fixes * chomp encoding string * reformat else (seems someone hacked it in) * debug print encoding * do not use :utf8 binmode ("re-encode") on written file if the input is _already_ UTF-8
author Peter Gervai <grin@grin.hu>
date Thu, 16 Oct 2008 00:02:14 +0200
parents e8a9408780ff
children 69923c621cfe
files bins_edit
diffstat 1 files changed, 13 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/bins_edit	Wed Oct 15 23:36:49 2008 +0200
+++ b/bins_edit	Thu Oct 16 00:02:14 2008 +0200
@@ -44,18 +44,19 @@
 
 my $localEncoding;
 $localEncoding = `locale charmap`;
+chomp $localEncoding;
 if ($? != 0 ) {
   $localEncoding = "LATIN1";
-}
-else {
-if (! $localEncoding or ($localEncoding eq "ANSI_X3.4-1968")) {
-  chop($localEncoding);
-  # ANSI is unspeakably primitive, promote it.
-  $localEncoding = "LATIN1";
-  print "Forcing encoding to $localEncoding\n" if ($verbose >=2);
-}
+} else {
+  if (! $localEncoding or ($localEncoding eq "ANSI_X3.4-1968")) {
+    chop($localEncoding);
+    # ANSI is unspeakably primitive, promote it.
+    $localEncoding = "LATIN1";
+    print "Forcing encoding to $localEncoding\n" if ($verbose >=2);
+  }
 }
 my $converter = Text::Iconv->new($localEncoding, "UTF-8");
+print "Using $localEncoding encoding on input\n" if ($verbose >=2);
 
 # decode HTML entites which doesn't exist in XML
 sub decodeEntites{
@@ -283,7 +284,10 @@
   my $fileHandler = new IO::File;
   open($fileHandler, '>', $file)
     or die("Cannot open file $file to write Exif tag ($!)");
-  binmode($fileHandler, ":utf8") if $^V ge v5.8.0;
+  if( $localEncoding !~ /utf-?8/i ) {
+      # if input is UTF-8 do not re-convert it again
+      binmode($fileHandler, ":utf8") if $^V ge v5.8.0;
+  }
 
   my $my_handler = new XML::Handler::YAWriter( 'Output' => $fileHandler,
 					 #      'Escape' => {