Attachment 4093 Details for Bug 10402 – patch to fix gocr output and finding of tesseract version

[patch] patch to fix gocr output and finding of tesseract version

gscan2pdf-gocr-output-and-tesseract-version.patch (text/plain), 1.36 KB, created by Pablo Saratxaga on 2013-06-02 22:38:04 CEST

(hide)

Description:

Filename:

MIME Type:

Creator: Pablo Saratxaga

Created: 2013-06-02 22:38:04 CEST

Size: 1.36 KB

patch

obsolete

>--- /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf/Tesseract.pm_bak	2013-06-02 15:36:51.316070939 +0200
>+++ /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf/Tesseract.pm	2013-06-02 22:21:27.398604139 +0200
>@@ -19,7 +19,7 @@
>   return;
>  }
>  ( $tessdata, $version, $datasuffix ) =
>-   parse_tessdata(`tesseract '' '' -l '' 2>&1`);
>+   parse_tessdata(`tesseract -v 2>&1 ; tesseract '' '' -l '' 2>&1`);
> 
>  if ( not defined($tessdata) ) {
>   if ( defined($version) and $version > 3.01 ) {
>@@ -44,7 +44,8 @@
>  my @output = @_;
>  my $output = join ",", @output;
>  my ( $v, $suffix );
>- $v = $1 + 0 if ( $output =~ /\ v(\d\.\d\d)\ /x );
>+ $v = $1 + 0 if ( $output =~ /^tesseract\ (\d\.\d\d)\.\d+/x );
>+ $v = $1 + 0 if (!$v && $output =~ /\ v(\d\.\d\d)\ /x );
>  while ( $output =~ /\n/x ) {
>   $output =~ s/\n.*$//gx;
>  }
>--- /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf.pm_bak	2013-06-02 21:51:25.326366002 +0200
>+++ /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf.pm	2013-06-02 22:05:11.925765974 +0200
>@@ -1267,9 +1267,12 @@
> 
>  my $new = $page->clone;
> 
>- my $cmd = "gocr $pnm";
>+ my $txt = File::Temp->new( SUFFIX => '.txt' );
>+ my $cmd = "gocr -o $txt $pnm";
>  $logger->info($cmd);
>- $new->{hocr} = `echo $$ > $pidfile;$cmd`;
>+ $cmd = "echo $$ > $pidfile;$cmd";
>+ system($cmd);
>+ $new->{hocr} = Gscan2pdf::slurp($txt);
>  return if $_self->{cancel};
>  $new->{ocr_flag} = 1;    #FlagOCR
>  $new->{ocr_time} =

--- /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf/Tesseract.pm_bak	2013-06-02 15:36:51.316070939 +0200
+++ /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf/Tesseract.pm	2013-06-02 22:21:27.398604139 +0200
@@ -19,7 +19,7 @@
   return;
  }
  ( $tessdata, $version, $datasuffix ) =
-   parse_tessdata(`tesseract '' '' -l '' 2>&1`);
+   parse_tessdata(`tesseract -v 2>&1 ; tesseract '' '' -l '' 2>&1`);
 
  if ( not defined($tessdata) ) {
   if ( defined($version) and $version > 3.01 ) {
@@ -44,7 +44,8 @@
  my @output = @_;
  my $output = join ",", @output;
  my ( $v, $suffix );
- $v = $1 + 0 if ( $output =~ /\ v(\d\.\d\d)\ /x );
+ $v = $1 + 0 if ( $output =~ /^tesseract\ (\d\.\d\d)\.\d+/x );
+ $v = $1 + 0 if (!$v && $output =~ /\ v(\d\.\d\d)\ /x );
  while ( $output =~ /\n/x ) {
   $output =~ s/\n.*$//gx;
  }
--- /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf.pm_bak	2013-06-02 21:51:25.326366002 +0200
+++ /usr/lib/perl5/vendor_perl/5.16.2/Gscan2pdf.pm	2013-06-02 22:05:11.925765974 +0200
@@ -1267,9 +1267,12 @@
 
  my $new = $page->clone;
 
- my $cmd = "gocr $pnm";
+ my $txt = File::Temp->new( SUFFIX => '.txt' );
+ my $cmd = "gocr -o $txt $pnm";
  $logger->info($cmd);
- $new->{hocr} = `echo $$ > $pidfile;$cmd`;
+ $cmd = "echo $$ > $pidfile;$cmd";
+ system($cmd);
+ $new->{hocr} = Gscan2pdf::slurp($txt);
  return if $_self->{cancel};
  $new->{ocr_flag} = 1;    #FlagOCR
  $new->{ocr_time} =

Actions: View | Diff

Attachments on bug 10402: 4093 | 4096 | 4166 | 4169 | 4191 | 4192