diff options
Diffstat (limited to 'lib/unicore/ArabicShaping.txt')
| -rw-r--r-- | lib/unicore/ArabicShaping.txt | 105 |
1 files changed, 82 insertions, 23 deletions
diff --git a/lib/unicore/ArabicShaping.txt b/lib/unicore/ArabicShaping.txt index 84c308ac8a..ec2e024101 100644 --- a/lib/unicore/ArabicShaping.txt +++ b/lib/unicore/ArabicShaping.txt @@ -1,8 +1,12 @@ -# ArabicShaping-4.0.1.txt +# ArabicShaping-4.1.0.txt +# Date: 2005-03-17, 15:21:00 PST [KW] # # This file is a normative contributory data file in the # Unicode Character Database. # +# Copyright (c) 1991-2005 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# # This file defines the shaping classes for Arabic and Syriac # positional shaping, repeating in machine readable form the # information printed in Tables 8-3, 8-7, 8-8, 8-11, 8-12, and @@ -17,21 +21,42 @@ # form, of an Arabic or Syriac character. # Field 1: gives a short schematic name for that character, # abbreviated from the normative Unicode character name. -# Field 2: defines the joining type -# R right-joining, -# L left-joining, -# D dual-joining, -# C join-causing -# U non-joining -# T transparent +# Field 2: defines the joining type (property name: Joining_Type) +# R Right_Joining +# L Left_Joining +# D Dual_Joining +# C Join_Causing +# U Non_Joining +# T Transparent # See the Arabic block description for more information on these types. -# Field 3: defines the joining group. +# Field 3: defines the joining group (property name: Joining_Group) +# +# The values of the joining group are based schematically on character +# names. Where a schematic character name consists of two or more parts separated +# by spaces, the formal Joining_Group property value, as specified in +# PropertyValueAliases.txt, consists of the same name parts joined by +# underscores. Hence, the entry: +# +# 0629; TEH MARBUTA; R; TEH MARBUTA +# +# corresponds to [Joining_Group = Teh_Marbuta]. # +# Note: For historical reasons, the property value [Joining_Group = Hamza_On_Heh_Goal] +# is anachronistically named. It used to apply to both of the following characters +# in earlier versions of the standard: +# +# U+06C2 ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +# U+06C3 ARABIC LETTER TEH MARBUTA GOAL +# +# However, it currently applies only to U+06C3, and *not* to U+06C2. +# To avoid destabilizing existing Joining_Group property aliases, the +# value Hamza_On_Heh_Goal has not been changed, despite the fact that it +# no longer applies to Hamza On Heh Goal, but only to Teh Marbuta Goal. # # Note: Code points that are not explicitly listed in this file are -# either of type T or U: +# either of joining type T or U: # -# - Those that not explicitly listed that are of General Category Mn or Cf +# - Those that not explicitly listed that are of General Category Mn, Me, or Cf # have joining type T. # - All others not explicitly listed have type U. # @@ -46,11 +71,12 @@ # Arabic characters -0600; ARABIC NUMBER SIGN; U; <no shaping> -0601; ARABIC SIGN SANAH; U; <no shaping> -0602; ARABIC FOOTNOTE MARKER; U; <no shaping> -0603; ARABIC SIGN SAFHA; U; <no shaping> -0621; HAMZA; U; <no shaping> +0600; ARABIC NUMBER SIGN; U; No_Joining_Group +0601; ARABIC SIGN SANAH; U; No_Joining_Group +0602; ARABIC FOOTNOTE MARKER; U; No_Joining_Group +0603; ARABIC SIGN SAFHA; U; No_Joining_Group +060B; AFGHANI SIGN; U; No_Joining_Group +0621; HAMZA; U; No_Joining_Group 0622; MADDA ON ALEF; R; ALEF 0623; HAMZA ON ALEF; R; ALEF 0624; HAMZA ON WAW; R; WAW @@ -76,7 +102,7 @@ 0638; ZAH; D; TAH 0639; AIN; D; AIN 063A; GHAIN; D; AIN -0640; TATWEEL; C; <no shaping> +0640; TATWEEL; C; No_Joining_Group 0641; FEH; D; FEH 0642; QAF; D; QAF 0643; KAF; D; KAF @@ -92,7 +118,7 @@ 0671; HAMZAT WASL ON ALEF; R; ALEF 0672; WAVY HAMZA ON ALEF; R; ALEF 0673; WAVY HAMZA UNDER ALEF; R; ALEF -0674; HIGH HAMZA; U; <no shaping> +0674; HIGH HAMZA; U; No_Joining_Group 0675; HIGH HAMZA ALEF; R; ALEF 0676; HIGH HAMZA WAW; R; WAW 0677; HIGH HAMZA WAW WITH DAMMA; R; WAW @@ -145,7 +171,7 @@ 06A6; FEH WITH 4 DOTS ABOVE; D; FEH 06A7; QAF WITH DOT ABOVE; D; QAF 06A8; QAF WITH 3 DOTS ABOVE; D; QAF -06A9; OPEN KAF; D; GAF +06A9; KEHEH; D; GAF 06AA; SWASH KAF; D; SWASH KAF 06AB; KAF WITH RING; D; GAF 06AC; KAF WITH DOT ABOVE; D; KAF @@ -170,7 +196,7 @@ 06BF; HAH WITH MIDDLE 3 DOTS DOWNWARD AND DOT ABOVE; D; HAH 06C0; HAMZA ON HEH; R; TEH MARBUTA 06C1; HEH GOAL; D; HEH GOAL -06C2; HAMZA ON HEH GOAL; R; HAMZA ON HEH GOAL +06C2; HAMZA ON HEH GOAL; D; HEH GOAL 06C3; TEH MARBUTA GOAL; R; HAMZA ON HEH GOAL 06C4; WAW WITH RING; R; WAW 06C5; WAW WITH BAR; R; WAW @@ -189,7 +215,7 @@ 06D2; YEH BARREE; R; YEH BARREE 06D3; HAMZA ON YEH BARREE; R; YEH BARREE 06D5; AE; R; TEH MARBUTA -06DD; ARABIC END OF AYAH; U; <no shaping> +06DD; ARABIC END OF AYAH; U; No_Joining_Group 06EE; DAL WITH INVERTED V; R; DAL 06EF; REH WITH INVERTED V; R; REH 06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN @@ -234,7 +260,40 @@ 074E; SOGDIAN KHAPH; D; KHAPH 074F; SOGDIAN FE; D; FE +# Arabic supplement characters + +0750; BEH WITH 3 DOTS HORIZONTALLY BELOW; D; BEH +0751; BEH WITH DOT BELOW AND 3 DOTS ABOVE; D; BEH +0752; BEH WITH 3 DOTS POINTING UPWARDS BELOW; D; BEH +0753; BEH WITH 3 DOTS POINTING UPWARDS BELOW AND 2 DOTS ABOVE; D; BEH +0754; BEH WITH 2 DOTS BELOW AND DOT ABOVE; D; BEH +0755; BEH WITH INVERTED SMALL V BELOW; D; BEH +0756; BEH WITH SMALL V; D; BEH +0757; HAH WITH 2 DOTS ABOVE; D; HAH +0758; HAH WITH 3 DOTS POINTING UPWARDS BELOW; D; HAH +0759; DAL WITH 2 DOTS VERTICALLY BELOW AND SMALL TAH; R; DAL +075A; DAL WITH INVERTED SMALL V BELOW; R; DAL +075B; REH WITH STROKE; R; REH +075C; SEEN WITH 4 DOTS ABOVE; D; SEEN +075D; AIN WITH 2 DOTS ABOVE; D; AIN +075E; AIN WITH 3 DOTS POINTING DOWNWARDS ABOVE; D; AIN +075F; AIN WITH 2 DOTS VERTICALLY ABOVE; D; AIN +0760; FEH WITH 2 DOTS BELOW; D; FEH +0761; FEH WITH 3 DOTS POINTING UPWARDS BELOW; D; FEH +0762; KEHEH WITH DOT ABOVE; D; GAF +0763; KEHEH WITH 3 DOTS ABOVE; D; GAF +0764; KEHEH WITH 3 DOTS POINTING UPWARDS BELOW; D; GAF +0765; MEEM WITH DOT ABOVE; D; MEEM +0766; MEEM WITH DOT BELOW; D; MEEM +0767; NOON WITH 2 DOTS BELOW; D; NOON +0768; NOON WITH SMALL TAH; D; NOON +0769; NOON WITH SMALL V; D; NOON +076A; LAM WITH BAR; D; LAM +076B; REH WITH 2 DOTS VERTICALLY ABOVE; R; REH +076C; REH WITH HAMZA ABOVE; R; REH +076D; SEEN WITH 2 DOTS VERTICALLY ABOVE; D; SEEN + # Other -200D; ZERO WIDTH JOINER; C; <no shaping> -200C; ZERO WIDTH NON-JOINER; U; <no shaping> +200D; ZERO WIDTH JOINER; C; No_Joining_Group +200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group |