unicode-data 6.1.0-1 / usr / share / unicode / ArabicShaping.txt

# ArabicShaping-6.1.0.txt
# Date: 2011-04-15, 23:16:00 GMT [KW]
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# Copyright (c) 1991-2011 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# This file defines the Joining_Type and Joining_Group
# property values for Arabic, Syriac, N'Ko, and Mandaic
# positional shaping, repeating in machine readable form the
# information exemplified in Tables 8-3, 8-8, 8-9, 8-10, 8-13, 8-14,
# 8-15, 13-5, 14-5, and 14-6 of The Unicode Standard, Version 6.1.
#
# See sections 8.2, 8.3, 13.5, and 14.12 of The Unicode Standard, 
# Version 6.1 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, Syriac, N'Ko, or Mandaic character.
#
# Field 1: gives a short schematic name for that character.
#   The schematic name is descriptive of the shape, based as
#   consistently as possible on a name for the skeleton and
#   then the diacritic marks applied to the skeleton, if any.
#   Note that this schematic name is considered a comment,
#   and does not constitute a formal property value.
#
# 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: The property value now designated [Joining_Group = Teh_Marbuta_Goal] 
#   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
#   prior Joining_Group value for U+06C3 (Hamza_On_Heh_Goal) has been
#   retained as a property value alias, despite the fact that it
#   no longer applies to its namesake character, U+06C2.
#   See PropertyValueAliases.txt.
#
# 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 and Mandaic scripts. 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 joining type T or U:
#
# - Those that not explicitly listed that are of General Category Mn, Me, or Cf
#   have joining type T.
# - 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 joining type L defined in Unicode.
#
# #############################################################
 
# Unicode; Schematic Name; Joining Type; Joining Group

# Arabic Characters

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
0604; ARABIC SIGN SAMVAT; U; No_Joining_Group
0608; ARABIC RAY; U; No_Joining_Group
060B; AFGHANI SIGN; U; No_Joining_Group
0620; DOTLESS YEH WITH SEPARATE RING BELOW; D; YEH
0621; HAMZA; U; No_Joining_Group
0622; ALEF WITH MADDA ABOVE; R; ALEF
0623; ALEF WITH HAMZA ABOVE; R; ALEF
0624; WAW WITH HAMZA ABOVE; R; WAW
0625; ALEF WITH HAMZA BELOW; R; ALEF
0626; DOTLESS YEH WITH HAMZA ABOVE; D; YEH
0627; ALEF; R; ALEF
0628; BEH; D; BEH
0629; TEH MARBUTA; R; TEH MARBUTA
062A; DOTLESS BEH WITH 2 DOTS ABOVE; D; BEH
062B; DOTLESS BEH WITH 3 DOTS ABOVE; D; BEH
062C; HAH WITH DOT BELOW; D; HAH
062D; HAH; D; HAH
062E; HAH WITH DOT ABOVE; D; HAH
062F; DAL; R; DAL
0630; DAL WITH DOT ABOVE; R; DAL
0631; REH; R; REH
0632; REH WITH DOT ABOVE; R; REH
0633; SEEN; D; SEEN
0634; SEEN WITH 3 DOTS ABOVE; D; SEEN
0635; SAD; D; SAD
0636; SAD WITH DOT ABOVE; D; SAD
0637; TAH; D; TAH
0638; TAH WITH DOT ABOVE; D; TAH
0639; AIN; D; AIN
063A; AIN WITH DOT ABOVE; D; AIN
063B; KEHEH WITH 2 DOTS ABOVE; D; GAF
063C; KEHEH WITH 3 DOTS BELOW; D; GAF
063D; FARSI YEH WITH INVERTED V ABOVE; 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
0644; LAM; D; LAM
0645; MEEM; D; MEEM
0646; NOON; D; NOON
0647; HEH; D; HEH
0648; WAW; R; WAW
0649; DOTLESS YEH; D; YEH
064A; YEH; D; YEH
066E; DOTLESS BEH; D; BEH
066F; DOTLESS QAF; D; QAF
0671; ALEF WITH WASLA ABOVE; R; ALEF
0672; ALEF WITH WAVY HAMZA ABOVE; R; ALEF
0673; ALEF WITH WAVY HAMZA BELOW; R; ALEF
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 ABOVE; R; WAW
0678; HIGH HAMZA DOTLESS YEH; D; YEH
0679; DOTLESS BEH WITH TAH ABOVE; D; BEH
067A; DOTLESS BEH WITH VERTICAL 2 DOTS ABOVE; D; BEH
067B; DOTLESS BEH WITH VERTICAL 2 DOTS BELOW; D; BEH
067C; DOTLESS BEH WITH ATTACHED RING BELOW AND 2 DOTS ABOVE; D; BEH
067D; DOTLESS BEH WITH INVERTED 3 DOTS ABOVE; D; BEH
067E; DOTLESS BEH WITH 3 DOTS BELOW; D; BEH
067F; DOTLESS BEH WITH 4 DOTS ABOVE; D; BEH
0680; DOTLESS BEH WITH 4 DOTS BELOW; D; BEH
0681; HAH WITH HAMZA ABOVE; D; HAH
0682; HAH WITH VERTICAL 2 DOTS ABOVE; D; HAH
0683; HAH WITH 2 DOTS BELOW; D; HAH
0684; HAH WITH VERTICAL 2 DOTS BELOW; D; HAH
0685; HAH WITH 3 DOTS ABOVE; D; HAH
0686; HAH WITH 3 DOTS BELOW; D; HAH
0687; HAH WITH 4 DOTS BELOW; D; HAH
0688; DAL WITH TAH ABOVE; R; DAL
0689; DAL WITH ATTACHED RING BELOW; R; DAL
068A; DAL WITH DOT BELOW; R; DAL
068B; DAL WITH DOT BELOW AND TAH ABOVE; R; DAL
068C; DAL WITH 2 DOTS ABOVE; R; DAL
068D; DAL WITH 2 DOTS BELOW; R; DAL
068E; DAL WITH 3 DOTS ABOVE; R; DAL
068F; DAL WITH INVERTED 3 DOTS ABOVE; R; DAL
0690; DAL WITH 4 DOTS ABOVE; R; DAL
0691; REH WITH TAH ABOVE; R; REH
0692; REH WITH V ABOVE; R; REH
0693; REH WITH ATTACHED RING BELOW; R; REH
0694; REH WITH DOT BELOW; R; REH
0695; REH WITH V BELOW; R; REH
0696; REH WITH DOT BELOW AND DOT WITHIN; R; REH
0697; REH WITH 2 DOTS ABOVE; R; REH
0698; REH WITH 3 DOTS ABOVE; R; REH
0699; REH WITH 4 DOTS ABOVE; R; REH
069A; SEEN WITH DOT BELOW AND DOT ABOVE; D; SEEN
069B; SEEN WITH 3 DOTS BELOW; D; SEEN
069C; SEEN WITH 3 DOTS BELOW AND 3 DOTS ABOVE; D; SEEN
069D; SAD WITH 2 DOTS BELOW; D; SAD
069E; SAD WITH 3 DOTS ABOVE; D; SAD
069F; TAH WITH 3 DOTS ABOVE; D; TAH
06A0; AIN WITH 3 DOTS ABOVE; D; AIN
06A1; DOTLESS FEH; D; FEH
06A2; DOTLESS FEH WITH DOT BELOW; D; FEH
06A3; FEH WITH DOT BELOW; D; FEH
06A4; DOTLESS FEH WITH 3 DOTS ABOVE; D; FEH
06A5; DOTLESS FEH WITH 3 DOTS BELOW; D; FEH
06A6; DOTLESS FEH WITH 4 DOTS ABOVE; D; FEH
06A7; DOTLESS QAF WITH DOT ABOVE; D; QAF
06A8; DOTLESS QAF WITH 3 DOTS ABOVE; D; QAF
06A9; KEHEH; D; GAF
06AA; SWASH KAF; D; SWASH KAF
06AB; KEHEH WITH ATTACHED RING BELOW; D; GAF
06AC; KAF WITH DOT ABOVE; D; KAF
06AD; KAF WITH 3 DOTS ABOVE; D; KAF
06AE; KAF WITH 3 DOTS BELOW; D; KAF
06AF; GAF; D; GAF
06B0; GAF WITH ATTACHED RING BELOW; D; GAF
06B1; GAF WITH 2 DOTS ABOVE; D; GAF
06B2; GAF WITH 2 DOTS BELOW; D; GAF
06B3; GAF WITH VERTICAL 2 DOTS BELOW; D; GAF
06B4; GAF WITH 3 DOTS ABOVE; D; GAF
06B5; LAM WITH V ABOVE; D; LAM
06B6; LAM WITH DOT ABOVE; D; LAM
06B7; LAM WITH 3 DOTS ABOVE; D; LAM
06B8; LAM WITH 3 DOTS BELOW; D; LAM
06B9; NOON WITH DOT BELOW; D; NOON
06BA; DOTLESS NOON; D; NOON
06BB; DOTLESS NOON WITH TAH ABOVE; D; NOON
06BC; NOON WITH ATTACHED RING BELOW; D; NOON
06BD; NYA; D; NYA
06BE; KNOTTED HEH; D; KNOTTED HEH
06BF; HAH WITH 3 DOTS BELOW AND DOT ABOVE; D; HAH
06C0; DOTLESS TEH MARBUTA WITH HAMZA ABOVE; R; TEH MARBUTA
06C1; HEH GOAL; D; HEH GOAL
06C2; HEH GOAL WITH HAMZA ABOVE; D; HEH GOAL
06C3; TEH MARBUTA GOAL; R; TEH MARBUTA GOAL
06C4; WAW WITH ATTACHED RING WITHIN; R; WAW
06C5; WAW WITH BAR; R; WAW
06C6; WAW WITH V ABOVE; R; WAW
06C7; WAW WITH DAMMA ABOVE; R; WAW
06C8; WAW WITH ALEF ABOVE; R; WAW
06C9; WAW WITH INVERTED V ABOVE; R; WAW
06CA; WAW WITH 2 DOTS ABOVE; R; WAW
06CB; WAW WITH 3 DOTS ABOVE; R; WAW
06CC; FARSI YEH; D; FARSI YEH
06CD; YEH WITH TAIL; R; YEH WITH TAIL
06CE; FARSI YEH WITH V ABOVE; D; FARSI YEH
06CF; WAW WITH DOT ABOVE; R; WAW
06D0; DOTLESS YEH WITH VERTICAL 2 DOTS BELOW; D; YEH
06D1; DOTLESS YEH WITH 3 DOTS BELOW; D; YEH
06D2; YEH BARREE; R; YEH BARREE
06D3; YEH BARREE WITH HAMZA ABOVE; R; YEH BARREE
06D5; DOTLESS TEH MARBUTA; R; TEH MARBUTA
06DD; ARABIC END OF AYAH; U; No_Joining_Group
06EE; DAL WITH INVERTED V ABOVE; R; DAL
06EF; REH WITH INVERTED V ABOVE; R; REH
06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN
06FB; SAD WITH DOT BELOW AND DOT ABOVE; D; SAD
06FC; AIN WITH DOT BELOW AND DOT ABOVE; D; AIN
06FF; KNOTTED HEH WITH INVERTED V ABOVE; D; KNOTTED HEH

# Syriac Characters

0710; ALAPH; R; ALAPH
0712; BETH; D; BETH
0713; GAMAL; D; GAMAL
0714; GAMAL GARSHUNI; D; GAMAL
0715; DALATH; R; DALATH RISH
0716; DOTLESS DALATH RISH; R; DALATH RISH
0717; HE; R; HE
0718; WAW; R; SYRIAC WAW
0719; ZAIN; R; ZAIN
071A; HETH; D; HETH
071B; TETH; D; TETH
071C; TETH GARSHUNI; D; TETH
071D; YUDH; D; YUDH
071E; YUDH HE; R; YUDH HE
071F; KAPH; D; KAPH
0720; LAMADH; D; LAMADH
0721; MIM; D; MIM
0722; NUN; D; NUN
0723; SEMKATH; D; SEMKATH
0724; FINAL SEMKATH; D; FINAL SEMKATH
0725; E; D; E
0726; PE; D; PE
0727; REVERSED PE; D; REVERSED PE
0728; SADHE; R; SADHE
0729; QAPH; D; QAPH
072A; RISH; R; DALATH RISH
072B; SHIN; D; SHIN
072C; TAW; R; TAW
072D; PERSIAN BHETH; D; BETH
072E; PERSIAN GHAMAL; D; GAMAL
072F; PERSIAN DHALATH; R; DALATH RISH
074D; SOGDIAN ZHAIN; R; ZHAIN
074E; SOGDIAN KHAPH; D; KHAPH
074F; SOGDIAN FE; D; FE

# Arabic Supplement Characters

0750; DOTLESS BEH WITH HORIZONTAL 3 DOTS BELOW; D; BEH
0751; BEH WITH 3 DOTS ABOVE; D; BEH
0752; DOTLESS BEH WITH INVERTED 3 DOTS BELOW; D; BEH
0753; DOTLESS BEH WITH INVERTED 3 DOTS BELOW AND 2 DOTS ABOVE; D; BEH
0754; DOTLESS BEH WITH 2 DOTS BELOW AND DOT ABOVE; D; BEH
0755; DOTLESS BEH WITH INVERTED V BELOW; D; BEH
0756; DOTLESS BEH WITH V ABOVE; D; BEH
0757; HAH WITH 2 DOTS ABOVE; D; HAH
0758; HAH WITH INVERTED 3 DOTS BELOW; D; HAH
0759; DAL WITH VERTICAL 2 DOTS BELOW AND TAH ABOVE; R; DAL
075A; DAL WITH INVERTED V BELOW; R; DAL
075B; REH WITH BAR; R; REH
075C; SEEN WITH 4 DOTS ABOVE; D; SEEN
075D; AIN WITH 2 DOTS ABOVE; D; AIN
075E; AIN WITH INVERTED 3 DOTS ABOVE; D; AIN
075F; AIN WITH VERTICAL 2 DOTS ABOVE; D; AIN
0760; DOTLESS FEH WITH 2 DOTS BELOW; D; FEH
0761; DOTLESS FEH WITH INVERTED 3 DOTS BELOW; D; FEH
0762; KEHEH WITH DOT ABOVE; D; GAF
0763; KEHEH WITH 3 DOTS ABOVE; D; GAF
0764; KEHEH WITH INVERTED 3 DOTS 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 TAH ABOVE; D; NOON
0769; NOON WITH V ABOVE; D; NOON
076A; LAM WITH BAR; D; LAM
076B; REH WITH VERTICAL 2 DOTS ABOVE; R; REH
076C; REH WITH HAMZA ABOVE; R; REH
076D; SEEN WITH VERTICAL 2 DOTS ABOVE; D; SEEN
076E; HAH WITH TAH BELOW; D; HAH
076F; HAH WITH TAH AND 2 DOTS BELOW; D; HAH
0770; SEEN WITH 2 DOTS AND TAH ABOVE; D; SEEN
0771; REH WITH 2 DOTS AND TAH ABOVE; R; REH
0772; HAH WITH 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; DOTLESS YEH WITH DIGIT FOUR BELOW; D; YEH
0778; WAW WITH DIGIT TWO ABOVE; R; WAW
0779; WAW WITH DIGIT THREE ABOVE; R; WAW
077A; BURUSHASKI YEH BARREE WITH DIGIT TWO ABOVE; D; BURUSHASKI YEH BARREE
077B; BURUSHASKI 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 ABOVE; 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

# Mandaic Characters

0840; MANDAIC HALQA; R; No_Joining_Group
0841; MANDAIC AB; D; No_Joining_Group
0842; MANDAIC AG; D; No_Joining_Group
0843; MANDAIC AD; D; No_Joining_Group
0844; MANDAIC AH; D; No_Joining_Group
0845; MANDAIC USHENNA; D; No_Joining_Group
0846; MANDAIC AZ; R; No_Joining_Group
0847; MANDAIC IT; D; No_Joining_Group
0848; MANDAIC ATT; D; No_Joining_Group
0849; MANDAIC AKSA; R; No_Joining_Group
084A; MANDAIC AK; D; No_Joining_Group
084B; MANDAIC AL; D; No_Joining_Group
084C; MANDAIC AM; D; No_Joining_Group
084D; MANDAIC AN; D; No_Joining_Group
084E; MANDAIC AS; D; No_Joining_Group
084F; MANDAIC IN; R; No_Joining_Group
0850; MANDAIC AP; D; No_Joining_Group
0851; MANDAIC ASZ; D; No_Joining_Group
0852; MANDAIC AQ; D; No_Joining_Group
0853; MANDAIC AR; D; No_Joining_Group
0854; MANDAIC ASH; R; No_Joining_Group
0855; MANDAIC AT; D; No_Joining_Group
0856; MANDAIC DUSHENNA; U; No_Joining_Group
0857; MANDAIC KAD; U; No_Joining_Group
0858; MANDAIC AIN; U; No_Joining_Group

# Arabic Extended-A Characters

08A0; DOTLESS BEH WITH V BELOW; D; BEH
08A2; HAH WITH DOT BELOW AND 2 DOTS ABOVE; D; HAH
08A3; TAH WITH 2 DOTS ABOVE; D; TAH
08A4; DOTLESS FEH WITH DOT BELOW AND 3 DOTS ABOVE; D; FEH
08A5; QAF WITH DOT BELOW; D; QAF
08A6; LAM WITH DOUBLE BAR; D; LAM
08A7; MEEM WITH 3 DOTS ABOVE; D; MEEM
08A8; YEH WITH HAMZA ABOVE; D; YEH
08A9; YEH WITH DOT ABOVE; D; YEH
08AA; REH WITH LOOP; R; REH
08AB; WAW WITH DOT WITHIN; R; WAW
08AC; ROHINGYA YEH; R; ROHINGYA YEH

# Other

200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
200D; ZERO WIDTH JOINER; C; No_Joining_Group

# EOF