diff options
Diffstat (limited to 'src/backend/utils/mb/Unicode/UCS_to_BIG5.pl')
| -rwxr-xr-x | src/backend/utils/mb/Unicode/UCS_to_BIG5.pl | 132 |
1 files changed, 80 insertions, 52 deletions
diff --git a/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl b/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl index b41e79703be..06d924853f3 100755 --- a/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl +++ b/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl @@ -33,68 +33,82 @@ require "ucs2utf.pl"; # $in_file = "BIG5.TXT"; -open( FILE, $in_file ) || die( "cannot open $in_file" ); +open(FILE, $in_file) || die("cannot open $in_file"); reset 'array'; -while( <FILE> ){ +while (<FILE>) +{ chop; - if( /^#/ ){ + if (/^#/) + { next; } - ( $c, $u, $rest ) = split; - $ucs = hex($u); + ($c, $u, $rest) = split; + $ucs = hex($u); $code = hex($c); - if( $code >= 0x80 && $ucs >= 0x0080){ + if ($code >= 0x80 && $ucs >= 0x0080) + { $utf = &ucs2utf($ucs); - if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; + if ($array{$utf} ne "") + { + printf STDERR "Warning: duplicate UTF8: %04x\n", $ucs; next; } $count++; - $array{ $utf } = $code; + $array{$utf} = $code; } } -close( FILE ); +close(FILE); $in_file = "CP950.TXT"; -open( FILE, $in_file ) || die( "cannot open $in_file" ); +open(FILE, $in_file) || die("cannot open $in_file"); -while( <FILE> ){ +while (<FILE>) +{ chop; - if( /^#/ ){ + if (/^#/) + { next; } - ( $c, $u, $rest ) = split; - $ucs = hex($u); + ($c, $u, $rest) = split; + $ucs = hex($u); $code = hex($c); # Pick only the ETEN extended characters in the range 0xf9d6 - 0xf9dc # from CP950.TXT - if( $code >= 0x80 && $ucs >= 0x0080 && - $code >= 0xf9d6 && $code <= 0xf9dc ){ + if ( $code >= 0x80 + && $ucs >= 0x0080 + && $code >= 0xf9d6 + && $code <= 0xf9dc) + { $utf = &ucs2utf($ucs); - if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; + if ($array{$utf} ne "") + { + printf STDERR "Warning: duplicate UTF8: %04x\n", $ucs; next; } $count++; - $array{ $utf } = $code; + $array{$utf} = $code; } } -close( FILE ); +close(FILE); $file = lc("utf8_to_big5.map"); -open( FILE, "> $file" ) || die( "cannot open $file" ); +open(FILE, "> $file") || die("cannot open $file"); print FILE "static pg_utf_to_local ULmapBIG5[ $count ] = {\n"; -for $index ( sort {$a <=> $b} keys( %array ) ){ - $code = $array{ $index }; +for $index (sort { $a <=> $b } keys(%array)) +{ + $code = $array{$index}; $count--; - if( $count == 0 ){ + if ($count == 0) + { printf FILE " {0x%04x, 0x%04x}\n", $index, $code; - } else { + } + else + { printf FILE " {0x%04x, 0x%04x},\n", $index, $code; } } @@ -107,67 +121,81 @@ close(FILE); # $in_file = "BIG5.TXT"; -open( FILE, $in_file ) || die( "cannot open $in_file" ); +open(FILE, $in_file) || die("cannot open $in_file"); reset 'array'; -while( <FILE> ){ +while (<FILE>) +{ chop; - if( /^#/ ){ + if (/^#/) + { next; } - ( $c, $u, $rest ) = split; - $ucs = hex($u); + ($c, $u, $rest) = split; + $ucs = hex($u); $code = hex($c); - if( $code >= 0x80 && $ucs >= 0x0080){ + if ($code >= 0x80 && $ucs >= 0x0080) + { $utf = &ucs2utf($ucs); - if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; + if ($array{$utf} ne "") + { + printf STDERR "Warning: duplicate UTF8: %04x\n", $ucs; next; } $count++; - $array{ $code } = $utf; + $array{$code} = $utf; } } -close( FILE ); +close(FILE); $in_file = "CP950.TXT"; -open( FILE, $in_file ) || die( "cannot open $in_file" ); +open(FILE, $in_file) || die("cannot open $in_file"); -while( <FILE> ){ +while (<FILE>) +{ chop; - if( /^#/ ){ + if (/^#/) + { next; } - ( $c, $u, $rest ) = split; - $ucs = hex($u); + ($c, $u, $rest) = split; + $ucs = hex($u); $code = hex($c); # Pick only the ETEN extended characters in the range 0xf9d6 - 0xf9dc # from CP950.TXT - if( $code >= 0x80 && $ucs >= 0x0080 && - $code >= 0xf9d6 && $code <= 0xf9dc ){ + if ( $code >= 0x80 + && $ucs >= 0x0080 + && $code >= 0xf9d6 + && $code <= 0xf9dc) + { $utf = &ucs2utf($ucs); - if( $array{ $utf } ne "" ){ - printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs; + if ($array{$utf} ne "") + { + printf STDERR "Warning: duplicate UTF8: %04x\n", $ucs; next; } $count++; - $array{ $code } = $utf; + $array{$code} = $utf; } } -close( FILE ); +close(FILE); $file = lc("big5_to_utf8.map"); -open( FILE, "> $file" ) || die( "cannot open $file" ); +open(FILE, "> $file") || die("cannot open $file"); print FILE "static pg_local_to_utf LUmapBIG5[ $count ] = {\n"; -for $index ( sort {$a <=> $b} keys( %array ) ){ - $utf = $array{ $index }; +for $index (sort { $a <=> $b } keys(%array)) +{ + $utf = $array{$index}; $count--; - if( $count == 0 ){ + if ($count == 0) + { printf FILE " {0x%04x, 0x%04x}\n", $index, $utf; - } else { + } + else + { printf FILE " {0x%04x, 0x%04x},\n", $index, $utf; } } |