[popfile-commit] engine/UI HTML.pm,1.205,1.206

[<jgr...@us...>]

Update of /cvsroot/popfile/engine/UI
In directory sc8-pr-cvs1:/tmp/cvs-serv21997/UI

Modified Files:
	HTML.pm 
Log Message:
Merge patch that makes POPFile work well with the Japanese language

Index: HTML.pm
===================================================================
RCS file: /cvsroot/popfile/engine/UI/HTML.pm,v
retrieving revision 1.205
retrieving revision 1.206
diff -C2 -d -r1.205 -r1.206
*** HTML.pm	22 Sep 2003 13:06:39 -0000	1.205
--- HTML.pm	22 Sep 2003 13:27:22 -0000	1.206
***************
*** 44,47 ****
--- 44,61 ----
  my $seconds_per_day = 60 * 60 * 24;
  
+ # These are used for Japanese support
+ 
+ # ASCII characters
+ my $ascii = '[\x00-\x7F]';
+ 
+ # EUC-JP 2 byte characters
+ my $two_bytes_euc_jp = '(?:[\x8E\xA1-\xFE][\xA1-\xFE])'; 
+ 
+ # EUC-JP 3 byte characters
+ my $three_bytes_euc_jp = '(?:\x8F[\xA1-\xFE][\xA1-\xFE])';
+ 
+ # EUC-JP characters
+ my $euc_jp = "(?:$ascii|$two_bytes_euc_jp|$three_bytes_euc_jp)";
+ 
  #----------------------------------------------------------------------------
  # new
***************
*** 1340,1373 ****
      my @words = $self->{classifier__}->get_stopword_list();
  
!     for my $word (sort @words) {
!         $word =~ /^(.)/;
!         if ( $1 ne $last )  {
!             if (! $firstRow) {
!                 $body .= "</td></tr>\n";
!             } else {
!                 $firstRow = 0;
!             }
!             $body .= "<tr><th scope=\"row\" class=\"advancedAlphabet";
!             if ($groupCounter == $groupSize) {
!                 $body .= "GroupSpacing";
              }
!             $body .= "\"><b>$1</b></th>\n";
!             $body .= "<td class=\"advancedWords";
!             if ($groupCounter == $groupSize) {
!                 $body .= "GroupSpacing";
!                 $groupCounter = 0;
              }
!             $body .= "\">";
  
  
!             $last = $1;
!             $need_comma = 0;
!             $groupCounter += 1;
!         }
!         if ( $need_comma == 1 ) {
!             $body .= ", $word";
!         } else {
!             $body .= $word;
!             $need_comma = 1;
          }
      }
--- 1354,1430 ----
      my @words = $self->{classifier__}->get_stopword_list();
  
!     # In Japanese mode, disable locale.
!     # Sorting Japanese with "use locale" is memory and time consuming,
!     # and may cause perl crash.
! 
!     if ( $self->config_( 'language' ) eq 'Nihongo' ) {
!         no locale;
!         for my $word (sort @words) {
! 
!             # First character of stop word is EUC-JP in Japanese mode
! 
!             $word =~ /^($euc_jp)/;
! 
!             if ( $1 ne $last )  {
!                 if ( !$firstRow ) {
!                     $body .= "</td></tr>\n";
!                 } else {
!                     $firstRow = 0;
!                 }
!                 $body .= "<tr><th scope=\"row\" class=\"advancedAlphabet";
!                 if ( $groupCounter == $groupSize ) {
!                     $body .= "GroupSpacing";
!                 }
!                 $body .= "\"><b>$1</b></th>\n";
!                 $body .= "<td class=\"advancedWords";
!                 if ( $groupCounter == $groupSize ) {
!                     $body .= "GroupSpacing";
!                     $groupCounter = 0;
!                 }
!                 $body .= "\">";
!                 $last = $1;
!                 $need_comma = 0;
!                 $groupCounter += 1;
              }
!             if ( $need_comma == 1 ) {
!                 $body .= ", $word";
!             } else {
!                 $body .= $word;
!                 $need_comma = 1;
              }
!         }
!     } else {
!         for my $word (sort @words) {
!             $word =~ /^(.)/;
! 
!             if ( $1 ne $last )  {
!                 if (! $firstRow) {
!                     $body .= "</td></tr>\n";
!                 } else {
!                     $firstRow = 0;
!                 }
!                 $body .= "<tr><th scope=\"row\" class=\"advancedAlphabet";
!                 if ($groupCounter == $groupSize) {
!                     $body .= "GroupSpacing";
!                 }
!                 $body .= "\"><b>$1</b></th>\n";
!                 $body .= "<td class=\"advancedWords";
!                 if ($groupCounter == $groupSize) {
!                     $body .= "GroupSpacing";
!                     $groupCounter = 0;
!                 }
!                 $body .= "\">";
  
  
!                 $last = $1;
!                 $need_comma = 0;
!                 $groupCounter += 1;
!             }
!             if ( $need_comma == 1 ) {
!                 $body .= ", $word";
!             } else {
!                 $body .= $word;
!                 $need_comma = 1;
!             }
          }
      }
***************
*** 2571,2580 ****
      my $from    = '';
      my $subject = '';
  
      if ( open MAIL, '<'. $self->global_config_( 'msgdir' ) . $file ) {
          while ( <MAIL> )  {
              last          if ( /^(\r\n|\r|\n)/ );
!             $from = $1    if ( /^From: *(.*)/i );
!             $subject = $1 if ( /^Subject: *(.*)/i );
              last if ( ( $from ne '' ) && ( $subject ne '' ) );
          }
--- 2628,2661 ----
      my $from    = '';
      my $subject = '';
+     my $long_header = '';
  
      if ( open MAIL, '<'. $self->global_config_( 'msgdir' ) . $file ) {
          while ( <MAIL> )  {
              last          if ( /^(\r\n|\r|\n)/ );
! 
!             # Support long header that has more than 2 lines by JI
! 
!             if(/^[\t ]+(=\?[\w-]+\?[BQ]\?.*\?=.*)/){
!                 if($long_header eq 'from'){
!                     $from .= $1;
!                     next;
!                 }
!                 if($long_header eq 'subject'){
!                     $subject .= $1;
!                     next;
!                 }
!             }else{
!                 if(/^From: *(.*)/i){
!                     $long_header = 'from';
!                     $from = $1;
!                     next;
!                 }elsif (/^Subject: *(.*)/i){
!                     $long_header = 'subject';
!                     $subject = $1;
!                     next;
!                 }
!                 $long_header = '';
!             }
! 
              last if ( ( $from ne '' ) && ( $subject ne '' ) );
          }