-# ArabicShaping-4.0.0.txt
+# ArabicShaping-5.2.0.txt
+# Date: 2009-08-17, 11:11:00 PDT [KW]
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
-# This file defines the shaping classes for Arabic and Syriac
+# Copyright (c) 1991-2009 Unicode, Inc.
+# For terms of use, see http://www.unicode.org/terms_of_use.html
+#
+# This file defines the shaping classes for Arabic, Syriac, and N'Ko
# positional shaping, repeating in machine readable form the
-# information printed in Tables 8-3, 8-7, 8-8, 8-11, 8-12, and
-# 8-13 of The Unicode Standard, Version 4.0.
+# information exemplified in Tables 8-3, 8-7, 8-8, 8-11, 8-12,
+# 8-13, and 13-5 of The Unicode Standard, Version 5.2.
#
-# See sections 8.2 and 8.3 of The Unicode Standard, Version 4.0
+# See sections 8.2, 8.3, and 13.5 of The Unicode Standard, Version 5.2
# for more information.
#
# Each line contains four fields, separated by a semicolon.
#
# Field 0: the code point, in 4-digit hexadecimal
-# form, of an Arabic or Syriac character.
+# form, of an Arabic, Syriac, or N'Ko 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
-# See the Arabic block description for more information on these types.
-# Field 3: defines the joining group.
#
+# 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 Section 8.2, Arabic for more information on these types.
+#
+# 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.
+#
+# When other cursive scripts are added to the Unicode Standard in
+# the future, the joining group value of all its letters will default
+# to jg=No_Joining_Group in this data file. Other, more specific
+# joining group values will be defined only if an explicit proposal
+# to define those values exactly has been approved by the UTC. This
+# is the convention exemplified by the N'Ko script. Only the Arabic
+# and Syriac scripts currently have explicit joining group values defined.
#
# 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.
+# - All others not explicitly listed have joining type U.
#
# For an explicit listing of characters of joining type T, see
# the derived property file DerivedJoiningType.txt.
#
-# There are currently no characters of type L defined in Unicode.
+# There are currently no characters of joining type L defined in Unicode.
#
# #############################################################
# 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
+0608; ARABIC RAY; 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
0638; ZAH; D; TAH
0639; AIN; D; AIN
063A; GHAIN; D; AIN
-0640; TATWEEL; C; <no shaping>
+063B; KEHEH WITH 2 DOTS ABOVE; D; GAF
+063C; KEHEH WITH 3 DOTS BELOW; D; GAF
+063D; FARSI YEH WITH INVERTED V; D; FARSI YEH
+063E; FARSI YEH WITH 2 DOTS ABOVE; D; FARSI YEH
+063F; FARSI YEH WITH 3 DOTS ABOVE; D; FARSI YEH
+0640; TATWEEL; C; No_Joining_Group
0641; FEH; D; FEH
0642; QAF; D; QAF
0643; KAF; D; KAF
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
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
06BA; DOTLESS NOON; D; NOON
06BB; DOTLESS NOON WITH SMALL TAH; D; NOON
06BC; NOON WITH RING; D; NOON
-06BD; NOON WITH 3 DOTS ABOVE; D; NOON
+06BD; NYA; D; NYA
06BE; KNOTTED HEH; D; KNOTTED HEH
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
06C9; WAW WITH INVERTED SMALL V; R; WAW
06CA; WAW WITH 2 DOTS ABOVE; R; WAW
06CB; WAW WITH 3 DOTS ABOVE; R; WAW
-06CC; DOTLESS YEH; D; YEH
+06CC; FARSI YEH; D; FARSI YEH
06CD; YEH WITH TAIL; R; YEH WITH TAIL
-06CE; YEH WITH SMALL V; D; YEH
+06CE; FARSI YEH WITH SMALL V; D; FARSI YEH
06CF; WAW WITH DOT ABOVE; R; WAW
06D0; YEH WITH 2 DOTS VERTICAL BELOW; D; YEH
06D1; YEH WITH 3 DOTS BELOW; D; YEH
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
-06FF; HEH WITH INVERTED V; D; KNOTTED HEH
06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN
06FB; DAD WITH DOT BELOW; D; SAD
06FC; GHAIN WITH DOT BELOW; D; AIN
+06FF; HEH WITH INVERTED V; D; KNOTTED HEH
# Syriac characters
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
+076E; HAH WITH SMALL TAH BELOW; D; HAH
+076F; HAH WITH SMALL TAH AND 2 DOTS; D; HAH
+0770; SEEN WITH SMALL TAH AND 2 DOTS; D; SEEN
+0771; REH WITH SMALL TAH AND 2 DOTS; R; REH
+0772; HAH WITH SMALL TAH ABOVE; D; HAH
+0773; ALEF WITH DIGIT TWO ABOVE; R; ALEF
+0774; ALEF WITH DIGIT THREE ABOVE; R; ALEF
+0775; FARSI YEH WITH DIGIT TWO ABOVE; D; FARSI YEH
+0776; FARSI YEH WITH DIGIT THREE ABOVE; D; FARSI YEH
+0777; YEH WITH DIGIT FOUR BELOW; D; YEH
+0778; WAW WITH DIGIT TWO ABOVE; R; WAW
+0779; WAW WITH DIGIT THREE ABOVE; R; WAW
+077A; YEH BARREE WITH DIGIT TWO ABOVE; D; BURUSHASKI YEH BARREE
+077B; YEH BARREE WITH DIGIT THREE ABOVE; D; BURUSHASKI YEH BARREE
+077C; HAH WITH DIGIT FOUR BELOW; D; HAH
+077D; SEEN WITH DIGIT FOUR ABOVE; D; SEEN
+077E; SEEN WITH INVERTED V; D; SEEN
+077F; KAF WITH 2 DOTS ABOVE; D; KAF
+
+# N'Ko Characters
+
+07CA; NKO A; D; No_Joining_Group
+07CB; NKO EE; D; No_Joining_Group
+07CC; NKO I; D; No_Joining_Group
+07CD; NKO E; D; No_Joining_Group
+07CE; NKO U; D; No_Joining_Group
+07CF; NKO OO; D; No_Joining_Group
+07D0; NKO O; D; No_Joining_Group
+07D1; NKO DAGBASINNA; D; No_Joining_Group
+07D2; NKO N; D; No_Joining_Group
+07D3; NKO BA; D; No_Joining_Group
+07D4; NKO PA; D; No_Joining_Group
+07D5; NKO TA; D; No_Joining_Group
+07D6; NKO JA; D; No_Joining_Group
+07D7; NKO CHA; D; No_Joining_Group
+07D8; NKO DA; D; No_Joining_Group
+07D9; NKO RA; D; No_Joining_Group
+07DA; NKO RRA; D; No_Joining_Group
+07DB; NKO SA; D; No_Joining_Group
+07DC; NKO GBA; D; No_Joining_Group
+07DD; NKO FA; D; No_Joining_Group
+07DE; NKO KA; D; No_Joining_Group
+07DF; NKO LA; D; No_Joining_Group
+07E0; NKO NA WOLOSO; D; No_Joining_Group
+07E1; NKO MA; D; No_Joining_Group
+07E2; NKO NYA; D; No_Joining_Group
+07E3; NKO NA; D; No_Joining_Group
+07E4; NKO HA; D; No_Joining_Group
+07E5; NKO WA; D; No_Joining_Group
+07E6; NKO YA; D; No_Joining_Group
+07E7; NKO NYA WOLOSO; D; No_Joining_Group
+07E8; NKO JONA JA; D; No_Joining_Group
+07E9; NKO JONA CHA; D; No_Joining_Group
+07EA; NKO JONA RA; D; No_Joining_Group
+07FA; NKO LAJANYALAN; C; No_Joining_Group
+
# Other
-200D; ZERO WIDTH JOINER; C; <no shaping>
-200C; ZERO WIDTH NON-JOINER; U; <no shaping>
+200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
+200D; ZERO WIDTH JOINER; C; No_Joining_Group
+
+# EOF
projects / p5sagit/p5-mst-13.2.git / blobdiff