diff options
Diffstat (limited to 'lib/unicode/mktables.PL')
-rwxr-xr-x | lib/unicode/mktables.PL | 26 |
1 files changed, 17 insertions, 9 deletions
diff --git a/lib/unicode/mktables.PL b/lib/unicode/mktables.PL index 37b6e84874..d8b57b6a83 100755 --- a/lib/unicode/mktables.PL +++ b/lib/unicode/mktables.PL @@ -16,18 +16,26 @@ mkdir "To", 0755; @todo = ( # typical - ['IsWord', '$cat =~ /^L[ulot]|^Nd/ or $code eq "005F"', ''], - ['IsAlnum', '$cat =~ /^L[ulot]|^Nd/', ''], - ['IsAlpha', '$cat =~ /^L[ulot]/', ''], - ['IsSpace', 'White space', $PropData], + # 005F: SPACING UNDERSCROE + ['IsWord', '$cat =~ /^[LMN]/ or $code eq "005F"', ''], + ['IsAlnum', '$cat =~ /^[LMN]/', ''], + ['IsAlpha', '$cat =~ /^[LM]/', ''], + # 0009: HORIZONTAL TABULATION + # 000A: LINE FEED + # 000B: VERTICAL TABULATION + # 000C: FORM FEED + # 000D: CARRIAGE RETURN + ['IsSpace', '$cat =~ /^Z/ || + $code =~ /^(0009|000A|000B|000C|000D)$/', ''], ['IsDigit', '$cat =~ /^Nd$/', ''], ['IsUpper', '$cat =~ /^L[ut]$/', ''], ['IsLower', '$cat =~ /^Ll$/', ''], - ['IsASCII', 'hex $code <= 127', ''], + ['IsASCII', '$code le "007f"', ''], ['IsCntrl', '$cat =~ /^C/', ''], - ['IsGraph', '$cat =~ /^[^C]/ and ($cat !~ /^Z/ and $code ne "0020" or chr(hex $code) !~ /^\s/)', ''], - ['IsPrint', '$cat =~ /^[^C]/', ''], - ['IsPunct', 'Punctuation', $PropData], + ['IsGraph', '$cat =~ /^([LMNPS]|Co)/', ''], + ['IsPrint', '$cat =~ /^([LMNPS]|Co|Zs)/', ''], + ['IsPunct', '$cat =~ /^P/', ''], + # 003[0-9]: DIGIT ZERO..NINE, 00[46][1-6]: A..F, a..f ['IsXDigit', '$code =~ /^00(3[0-9]|[46][1-6])$/', ''], ['ToUpper', '$up', '$up'], ['ToLower', '$down', '$down'], @@ -145,7 +153,7 @@ mkdir "To", 0755; ['IsDCfont', '$decomp =~ /^<font>/', ''], ['IsDCnoBreak', '$decomp =~ /^<noBreak>/', ''], ['IsDCinitial', '$decomp =~ /^<initial>/', ''], - ['IsDCinital', '$decomp =~ /^<medial>/', ''], + ['IsDCmedial', '$decomp =~ /^<medial>/', ''], ['IsDCfinal', '$decomp =~ /^<final>/', ''], ['IsDCisolated', '$decomp =~ /^<isolated>/', ''], ['IsDCcircle', '$decomp =~ /^<circle>/', ''], |