Integrate mainline
[p5sagit/p5-mst-13.2.git] / lib / unicore / ArabicShaping.txt
CommitLineData
afc46004 1# ArabicShaping-4.txt
8836d2a5 2#
3# This file is a normative contributory data file in the
4# Unicode Character Database.
5#
6# This file defines the shaping classes for Arabic and Syriac
7# positional shaping, repeating in machine readable form the
8# information printed in Tables 8-6, 8-7, 8-8, 8-10, 8-11, and
9# 8-13 of The Unicode Standard, Version 3.0.
10#
11# See sections 8.2 and 8.3 of The Unicode Standard, Version 3.0
12# for more information.
13#
14# Each line contains four fields, separated by a semicolon.
15#
16# The first field gives the code point, in 4-digit hexadecimal
17# form, of an Arabic or Syriac character.
18# The second field gives a short schematic name for that character,
19# abbreviated from the normative Unicode character name.
20# The third field defines the joining type: R right-joining,
21# D dual-joining, U non-joining
22# The fourth field defines the joining group.
23#
afc46004 24#
25# Note: Characters of joining type T and most characters of
26# joining type U are not explicitly listed in this file.
27#
28# Characters of joining type T can derived by the following formula:
29# T = Mn + Cf - ZWNJ - ZWJ
30# where Mn and Cf are the general category values. In other words,
31# any non-spacing mark or any format control character, except
32# U+200C ZERO WIDTH NON-JOINER (joining type U) and U+200D ZERO WIDTH
33# JOINER (joining type C).
34#
35# For an explicit listing of characters of joining type T, see
36# the derived property file DerivedJoiningType.txt.
37#
38# There are currently no characters of type L defined in Unicode.
39#
40# Joining type U includes all characters which are neither joining
41# type T, nor explicitly marked in this file as types R, L, D, or C.
42#
8836d2a5 43# #############################################################
44
45# Unicode; Schematic Name; Joining Type; Joining Group
46
d357d9fe 47# Arabic characters
8836d2a5 48
afc46004 490621; HAMZA; U; <no shaping>
d357d9fe 500622; MADDA ON ALEF; R; ALEF
510623; HAMZA ON ALEF; R; ALEF
520624; HAMZA ON WAW; R; WAW
530625; HAMZA UNDER ALEF; R; ALEF
540626; HAMZA ON YEH; D; YEH
550627; ALEF; R; ALEF
560628; BEH; D; BEH
570629; TEH MARBUTA; R; TEH MARBUTA
58062A; TEH; D; BEH
59062B; THEH; D; BEH
60062C; JEEM; D; HAH
61062D; HAH; D; HAH
62062E; KHAH; D; HAH
63062F; DAL; R; DAL
640630; THAL; R; DAL
650631; REH; R; REH
660632; ZAIN; R; REH
670633; SEEN; D; SEEN
680634; SHEEN; D; SEEN
690635; SAD; D; SAD
700636; DAD; D; SAD
710637; TAH; D; TAH
720638; ZAH; D; TAH
730639; AIN; D; AIN
74063A; GHAIN; D; AIN
750640; TATWEEL; C; <no shaping>
760641; FEH; D; FEH
770642; QAF; D; QAF
780643; KAF; D; KAF
790644; LAM; D; LAM
800645; MEEM; D; MEEM
810646; NOON; D; NOON
820647; HEH; D; HEH
830648; WAW; R; WAW
8836d2a5 840649; ALEF MAKSURA; D; YEH
d357d9fe 85064A; YEH; D; YEH
8836d2a5 860671; HAMZAT WASL ON ALEF; R; ALEF
d357d9fe 870672; WAVY HAMZA ON ALEF; R; ALEF
880673; WAVY HAMZA UNDER ALEF; R; ALEF
890674; HIGH HAMZA; U; <no shaping>
900675; HIGH HAMZA ALEF; R; ALEF
910676; HIGH HAMZA WAW; R; WAW
920677; HIGH HAMZA WAW WITH DAMMA; R; WAW
930678; HIGH HAMZA YEH; D; YEH
940679; TEH WITH SMALL TAH; D; BEH
95067A; TEH WITH 2 DOTS VERTICAL ABOVE; D; BEH
96067B; BEH WITH 2 DOTS VERTICAL BELOW; D; BEH
97067C; TEH WITH RING; D; BEH
98067D; TEH WITH 3 DOTS ABOVE DOWNWARD; D; BEH
99067E; TEH WITH 3 DOTS BELOW; D; BEH
100067F; TEH WITH 4 DOTS ABOVE; D; BEH
1010680; BEH WITH 4 DOTS BELOW; D; BEH
1020681; HAMZA ON HAH; D; HAH
1030682; HAH WITH 2 DOTS VERTICAL ABOVE; D; HAH
1040683; HAH WITH MIDDLE 2 DOTS; D; HAH
1050684; HAH WITH MIDDLE 2 DOTS VERTICAL; D; HAH
1060685; HAH WITH 3 DOTS ABOVE; D; HAH
1070686; HAH WITH MIDDLE 3 DOTS DOWNWARD; D; HAH
1080687; HAH WITH MIDDLE 4 DOTS; D; HAH
1090688; DAL WITH SMALL TAH; R; DAL
1100689; DAL WITH RING; R; DAL
111068A; DAL WITH DOT BELOW; R; DAL
112068B; DAL WITH DOT BELOW AND SMALL TAH; R; DAL
113068C; DAL WITH 2 DOTS ABOVE; R; DAL
114068D; DAL WITH 2 DOTS BELOW; R; DAL
115068E; DAL WITH 3 DOTS ABOVE; R; DAL
116068F; DAL WITH 3 DOTS ABOVE DOWNWARD; R; DAL
1170690; DAL WITH 4 DOTS ABOVE; R; DAL
1180691; REH WITH SMALL TAH; R; REH
1190692; REH WITH SMALL V; R; REH
1200693; REH WITH RING; R; REH
1210694; REH WITH DOT BELOW; R; REH
1220695; REH WITH SMALL V BELOW; R; REH
1230696; REH WITH DOT BELOW AND DOT ABOVE; R; REH
1240697; REH WITH 2 DOTS ABOVE; R; REH
1250698; REH WITH 3 DOTS ABOVE; R; REH
1260699; REH WITH 4 DOTS ABOVE; R; REH
127069A; SEEN WITH DOT BELOW AND DOT ABOVE; D; SEEN
128069B; SEEN WITH 3 DOTS BELOW; D; SEEN
129069C; SEEN WITH 3 DOTS BELOW AND 3 DOTS ABOVE; D; SEEN
130069D; SAD WITH 2 DOTS BELOW; D; SAD
131069E; SAD WITH 3 DOTS ABOVE; D; SAD
132069F; TAH WITH 3 DOTS ABOVE; D; TAH
13306A0; AIN WITH 3 DOTS ABOVE; D; AIN
13406A1; DOTLESS FEH; D; FEH
13506A2; FEH WITH DOT MOVED BELOW; D; FEH
13606A3; FEH WITH DOT BELOW; D; FEH
13706A4; FEH WITH 3 DOTS ABOVE; D; FEH
13806A5; FEH WITH 3 DOTS BELOW; D; FEH
13906A6; FEH WITH 4 DOTS ABOVE; D; FEH
14006A7; QAF WITH DOT ABOVE; D; QAF
14106A8; QAF WITH 3 DOTS ABOVE; D; QAF
14206A9; OPEN KAF; D; GAF
14306AA; SWASH KAF; D; SWASH KAF
14406AB; KAF WITH RING; D; GAF
14506AC; KAF WITH DOT ABOVE; D; KAF
14606AD; KAF WITH 3 DOTS ABOVE; D; KAF
14706AE; KAF WITH 3 DOTS BELOW; D; KAF
14806AF; GAF; D; GAF
14906B0; GAF WITH RING; D; GAF
15006B1; GAF WITH 2 DOTS ABOVE; D; GAF
15106B2; GAF WITH 2 DOTS BELOW; D; GAF
15206B3; GAF WITH 2 DOTS VERTICAL BELOW; D; GAF
15306B4; GAF WITH 3 DOTS ABOVE; D; GAF
15406B5; LAM WITH SMALL V; D; LAM
15506B6; LAM WITH DOT ABOVE; D; LAM
15606B7; LAM WITH 3 DOTS ABOVE; D; LAM
15706B8; LAM WITH 3 DOTS BELOW; D; LAM
15806B9; NOON WITH DOT BELOW; D; NOON
15906BA; DOTLESS NOON; D; NOON
16006BB; DOTLESS NOON WITH SMALL TAH; D; NOON
16106BC; NOON WITH RING; D; NOON
16206BD; NOON WITH 3 DOTS ABOVE; D; NOON
16306BE; KNOTTED HEH; D; KNOTTED HEH
16406BF; HAH WITH MIDDLE 3 DOTS DOWNWARD AND DOT ABOVE; D; HAH
16506C0; HAMZA ON HEH; R; TEH MARBUTA
16606C1; HEH GOAL; D; HEH GOAL
16706C2; HAMZA ON HEH GOAL; R; HAMZA ON HEH GOAL
16806C3; TEH MARBUTA GOAL; R; HAMZA ON HEH GOAL
16906C4; WAW WITH RING; R; WAW
17006C5; WAW WITH BAR; R; WAW
17106C6; WAW WITH SMALL V; R; WAW
17206C7; WAW WITH DAMMA; R; WAW
17306C8; WAW WITH ALEF ABOVE; R; WAW
17406C9; WAW WITH INVERTED SMALL V; R; WAW
17506CA; WAW WITH 2 DOTS ABOVE; R; WAW
17606CB; WAW WITH 3 DOTS ABOVE; R; WAW
17706CC; DOTLESS YEH; D; YEH
17806CD; YEH WITH TAIL; R; YEH WITH TAIL
17906CE; YEH WITH SMALL V; D; YEH
18006CF; WAW WITH DOT ABOVE; R; WAW
18106D0; YEH WITH 2 DOTS VERTICAL BELOW; D; YEH
18206D1; YEH WITH 3 DOTS BELOW; D; YEH
18306D2; YEH BARREE; R; YEH BARREE
18406D3; HAMZA ON YEH BARREE; R; YEH BARREE
afc46004 18506D5; AE; R; TEH MARBUTA
d357d9fe 18606FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN
18706FB; DAD WITH DOT BELOW; D; SAD
18806FC; GHAIN WITH DOT BELOW; D; AIN
8836d2a5 189
d357d9fe 190# Syriac characters
8836d2a5 191
d357d9fe 1920710; ALAPH; R; ALAPH
1930712; BETH; D; BETH
1940713; GAMAL; D; GAMAL
1950714; GAMAL GARSHUNI; D; GAMAL
1960715; DALATH; R; DALATH RISH
1970716; DOTLESS DALATH RISH; R; DALATH RISH
1980717; HE; R; HE
1990718; WAW; R; WAW
2000719; ZAIN; R; ZAIN
201071A; HETH; D; HETH
202071B; TETH; D; TETH
203071C; TETH GARSHUNI; D; TETH
204071D; YUDH; D; YUDH
205071E; YUDH HE; R; YUDH HE
206071F; KAPH; D; KAPH
2070720; LAMADH; D; LAMADH
2080721; MIM; D; MIM
2090722; NUN; D; NUN
2100723; SEMKATH; D; SEMKATH
2110724; FINAL SEMKATH; D; FINAL SEMKATH
2120725; E; D; E
2130726; PE; D; PE
2140727; REVERSED PE; D; REVERSED PE
2150728; SADHE; R; SADHE
2160729; QAPH; D; QAPH
217072A; RISH; R; DALATH RISH
218072B; SHIN; D; SHIN
219072C; TAW; R; TAW
afc46004 220
221# Other
222
223200D; ZERO WIDTH JOINER; C; <no shaping>