-# ArabicShaping-12.1.0.txt
-# Date: 2019-03-08, 23:59:00 GMT [KW, RP]
-# © 2019 Unicode®, Inc.
+# ArabicShaping-15.0.0.txt
+# Date: 2022-02-14, 18:50:00 GMT [KW, RP]
+# © 2022 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# This file defines the Joining_Type and Joining_Group property
-# values for Arabic, Syriac, N'Ko, Mandaic, Manichaean,
-# Hanifi Rohingya, and Sogdian positional
+# values for Arabic, Syriac, N'Ko, Mandaic, and Manichaean positional
# shaping, repeating in machine readable form the information
# exemplified in Tables 9-3, 9-8, 9-9, 9-10, 9-14, 9-15, 9-16, 9-19,
-# 9-20, 10-4, 10-5, 10-6, 10-7, 14-10, 16-16, and 19-5 of The Unicode Standard core
+# 9-20, 10-4, 10-5, 10-6, 10-7, and 19-5 of The Unicode Standard core
# specification. This file also defines Joining_Type values for
-# Mongolian, Phags-pa, Psalter Pahlavi, and Adlam positional shaping,
+# Mongolian, Phags-pa, Psalter Pahlavi, Sogdian, Old Uyghur, Chorasmian,
+# and Adlam positional shaping,
+# and Joining_Type and Joining_Group values for Hanifi Rohingya positional shaping,
# which are not listed in tables in the standard.
#
-# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.4, 14.3, 14.10, 16.13, 19.4, and 19.9
+# See Sections 9.2, 9.3, 9.5, 10.5, 10.6, 13.5, 14.4, 14.10, 14.11, 16.14, 19.4, and 19.9
# of The Unicode Standard core specification 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, Mandaic, Mongolian,
-# Phags-pa, Manichaean, Psalter Pahlavi, Hanifi Rohingya, Sogdian,
-# or other character.
+# form, of a character.
#
# Field 1: gives a short schematic name for that character.
# The schematic name is descriptive of the shape, based as
# Note that for cursive joining scripts which are typically rendered
# top-to-bottom, rather than right-to-left, Joining_Type=L conventionally
# refers to bottom joining, and Joining_Type=R conventionally refers
-# to top joining. See Section 14.3, Phags-pa for more information on the
+# to top joining. See Section 14.4, Phags-pa for more information on the
# interpretation of joining types in vertical layout.
#
# Field 3: defines the joining group (property name: Joining_Group)
# 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, Mandaic, Mongolian,
-# Phags-pa, Psalter Pahlavi, and Sogdian scripts.
+# Phags-pa, Psalter Pahlavi, Sogdian, Old Uyghur, Chorasmian, and Adlam scripts.
# Only the Arabic, Manichaean, and Syriac scripts currently have
# explicit joining group values defined for all characters, including
# those which have only a single character in a particular Joining_Group
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
+0677; HIGH HAMZA WAW WITH COMMA 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
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
+06C5; WAW WITH LOOP; R; WAW
06C6; WAW WITH V ABOVE; R; WAW
-06C7; WAW WITH DAMMA ABOVE; R; WAW
+06C7; WAW WITH COMMA 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
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
+0856; MANDAIC DUSHENNA; R; No_Joining_Group
+0857; MANDAIC KAD; R; No_Joining_Group
+0858; MANDAIC AIN; R; No_Joining_Group
# Syriac Supplement Characters
0869; MALAYALAM LLLA; R; MALAYALAM LLLA
086A; MALAYALAM SSA; R; MALAYALAM SSA
+# Arabic Extended-B Characters
+
+0870; ALEF WITH ATTACHED FATHA; R; ALEF
+0871; ALEF WITH ATTACHED TOP RIGHT FATHA; R; ALEF
+0872; ALEF WITH RIGHT MIDDLE STROKE; R; ALEF
+0873; ALEF WITH LEFT MIDDLE STROKE; R; ALEF
+0874; ALEF WITH ATTACHED KASRA; R; ALEF
+0875; ALEF WITH ATTACHED BOTTOM RIGHT KASRA; R; ALEF
+0876; ALEF WITH ATTACHED ROUND DOT ABOVE; R; ALEF
+0877; ALEF WITH ATTACHED RIGHT ROUND DOT; R; ALEF
+0878; ALEF WITH ATTACHED LEFT ROUND DOT; R; ALEF
+0879; ALEF WITH ATTACHED ROUND DOT BELOW; R; ALEF
+087A; ALEF WITH DOT ABOVE; R; ALEF
+087B; ALEF WITH ATTACHED TOP RIGHT FATHA AND DOT ABOVE; R; ALEF
+087C; ALEF WITH RIGHT MIDDLE STROKE AND DOT ABOVE; R; ALEF
+087D; ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND DOT ABOVE; R; ALEF
+087E; ALEF WITH ATTACHED TOP RIGHT FATHA AND LEFT RING; R; ALEF
+087F; ALEF WITH RIGHT MIDDLE STROKE AND LEFT RING; R; ALEF
+0880; ALEF WITH ATTACHED BOTTOM RIGHT KASRA AND LEFT RING; R; ALEF
+0881; ALEF WITH ATTACHED RIGHT HAMZA; R; ALEF
+0882; ALEF WITH ATTACHED LEFT HAMZA; R; ALEF
+0883; TATWEEL WITH OVERSTRUCK HAMZA; C; No_Joining_Group
+0884; TATWEEL WITH OVERSTRUCK WAW; C; No_Joining_Group
+0885; TATWEEL WITH TWO DOTS BELOW; C; No_Joining_Group
+0886; THIN YEH; D; THIN YEH
+0887; ARABIC BASELINE ROUND DOT; U; No_Joining_Group
+0888; ARABIC RAISED ROUND DOT; U; No_Joining_Group
+0889; DOTLESS NOON WITH INVERTED V ABOVE; D; NOON
+088A; HAH WITH INVERTED V BELOW; D; HAH
+088B; TAH WITH DOT BELOW; D; TAH
+088C; TAH WITH 3 DOTS BELOW; D; TAH
+088D; KEHEH WITH VERTICAL 2 DOTS BELOW; D; GAF
+088E; VERTICAL TAIL; R; VERTICAL TAIL
+0890; ARABIC POUND MARK ABOVE; U; No_Joining_Group
+0891; ARABIC PIASTRE MARK ABOVE; U; No_Joining_Group
+
# Arabic Extended-A Characters
08A0; DOTLESS BEH WITH V BELOW; D; BEH
08B2; REH WITH DOT AND INVERTED V ABOVE; R; REH
08B3; AIN WITH 3 DOTS BELOW; D; AIN
08B4; KAF WITH DOT BELOW; D; KAF
+08B5; DOTLESS QAF WITH DOT BELOW; D; QAF
08B6; BEH WITH MEEM ABOVE; D; BEH
08B7; DOTLESS BEH WITH 3 DOTS BELOW AND MEEM ABOVE; D; BEH
08B8; DOTLESS BEH WITH TEH ABOVE; D; BEH
08BB; AFRICAN FEH; D; AFRICAN FEH
08BC; AFRICAN QAF; D; AFRICAN QAF
08BD; AFRICAN NOON; D; AFRICAN NOON
+08BE; DOTLESS BEH WITH 3 DOTS BELOW AND V ABOVE; D; BEH
+08BF; DOTLESS BEH WITH 2 DOTS AND V ABOVE; D; BEH
+08C0; DOTLESS BEH WITH TAH AND V ABOVE; D; BEH
+08C1; HAH WITH 3 DOTS BELOW AND V ABOVE; D; HAH
+08C2; KEHEH WITH V ABOVE; D; GAF
+08C3; AIN WITH DIAMOND 4 DOTS ABOVE; D; AIN
+08C4; AFRICAN QAF WITH 3 DOTS ABOVE; D; AFRICAN QAF
+08C5; HAH WITH DOT BELOW AND 3 DOTS ABOVE; D; HAH
+08C6; HAH WITH DIAMOND 4 DOTS BELOW; D; HAH
+08C7; LAM WITH TAH ABOVE; D; LAM
+08C8; KEHEH WITH ELONGATED HAMZA ABOVE; D; GAF
08E2; ARABIC DISPUTED END OF AYAH; U; No_Joining_Group
# Mongolian Characters
10F53; SOGDIAN TWENTY; D; No_Joining_Group
10F54; SOGDIAN ONE HUNDRED; R; No_Joining_Group
+# Old Uyghur Characters
+
+10F70; OLD UYGHUR ALEPH; D; No_Joining_Group
+10F71; OLD UYGHUR BETH; D; No_Joining_Group
+10F72; OLD UYGHUR GIMEL-HETH; D; No_Joining_Group
+10F73; OLD UYGHUR WAW; D; No_Joining_Group
+10F74; OLD UYGHUR ZAYIN; R; No_Joining_Group
+10F75; OLD UYGHUR FINAL HETH; R; No_Joining_Group
+10F76; OLD UYGHUR YODH; D; No_Joining_Group
+10F77; OLD UYGHUR KAPH; D; No_Joining_Group
+10F78; OLD UYGHUR LAMEDH; D; No_Joining_Group
+10F79; OLD UYGHUR MEM; D; No_Joining_Group
+10F7A; OLD UYGHUR NUN; D; No_Joining_Group
+10F7B; OLD UYGHUR SAMEKH; D; No_Joining_Group
+10F7C; OLD UYGHUR PE; D; No_Joining_Group
+10F7D; OLD UYGHUR SADHE; D; No_Joining_Group
+10F7E; OLD UYGHUR RESH; D; No_Joining_Group
+10F7F; OLD UYGHUR SHIN; D; No_Joining_Group
+10F80; OLD UYGHUR TAW; D; No_Joining_Group
+10F81; OLD UYGHUR LESH; D; No_Joining_Group
+
+# Chorasmian Characters
+
+10FB0; CHORASMIAN ALEPH; D; No_Joining_Group
+10FB1; CHORASMIAN SMALL ALEPH; U; No_Joining_Group
+10FB2; CHORASMIAN BETH; D; No_Joining_Group
+10FB3; CHORASMIAN GIMEL; D; No_Joining_Group
+10FB4; CHORASMIAN DALETH; R; No_Joining_Group
+10FB5; CHORASMIAN HE; R; No_Joining_Group
+10FB6; CHORASMIAN WAW; R; No_Joining_Group
+10FB7; CHORASMIAN CURLED WAW; U; No_Joining_Group
+10FB8; CHORASMIAN ZAYIN; D; No_Joining_Group
+10FB9; CHORASMIAN HETH; R; No_Joining_Group
+10FBA; CHORASMIAN YODH; R; No_Joining_Group
+10FBB; CHORASMIAN KAPH; D; No_Joining_Group
+10FBC; CHORASMIAN LAMEDH; D; No_Joining_Group
+10FBD; CHORASMIAN MEM; R; No_Joining_Group
+10FBE; CHORASMIAN NUN; D; No_Joining_Group
+10FBF; CHORASMIAN SAMEKH; D; No_Joining_Group
+10FC0; CHORASMIAN AYIN; U; No_Joining_Group
+10FC1; CHORASMIAN PE; D; No_Joining_Group
+10FC2; CHORASMIAN RESH; R; No_Joining_Group
+10FC3; CHORASMIAN SHIN; R; No_Joining_Group
+10FC4; CHORASMIAN TAW; D; No_Joining_Group
+10FC5; CHORASMIAN ONE; U; No_Joining_Group
+10FC6; CHORASMIAN TWO; U; No_Joining_Group
+10FC7; CHORASMIAN THREE; U; No_Joining_Group
+10FC8; CHORASMIAN FOUR; U; No_Joining_Group
+10FC9; CHORASMIAN TEN; R; No_Joining_Group
+10FCA; CHORASMIAN TWENTY; D; No_Joining_Group
+10FCB; CHORASMIAN ONE HUNDRED; L; No_Joining_Group
+
# Kaithi Number Signs
# These are prepended concatenation marks, comparable
# to the number signs in the Arabic script.
projects / factor.git / blobdiff