-# ArabicShaping-4.txt
+# ArabicShaping-4.0.0.txt
#
# This file is a normative contributory data file in the
# Unicode Character Database.
#
# This file defines the shaping classes for Arabic and Syriac
# positional shaping, repeating in machine readable form the
-# information printed in Tables 8-6, 8-7, 8-8, 8-10, 8-11, and
-# 8-13 of The Unicode Standard, Version 3.0.
+# information printed in Tables 8-3, 8-7, 8-8, 8-11, 8-12, and
+# 8-13 of The Unicode Standard, Version 4.0.
#
-# See sections 8.2 and 8.3 of The Unicode Standard, Version 3.0
+# See sections 8.2 and 8.3 of The Unicode Standard, Version 4.0
# for more information.
#
# Each line contains four fields, separated by a semicolon.
#
-# The first field gives the code point, in 4-digit hexadecimal
+# Field 0: the code point, in 4-digit hexadecimal
# form, of an Arabic or Syriac character.
-# The second field gives a short schematic name for that character,
+# Field 1: gives a short schematic name for that character,
# abbreviated from the normative Unicode character name.
-# The third field defines the joining type: R right-joining,
-# D dual-joining, U non-joining
-# The fourth field defines the joining group.
+# 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.
#
#
-# Note: Characters of joining type T and most characters of
-# joining type U are not explicitly listed in this file.
+# Note: Code points that are not explicitly listed in this file are
+# either of type T or U:
#
-# Characters of joining type T can derived by the following formula:
-# T = Mn + Cf - ZWNJ - ZWJ
-# where Mn and Cf are the general category values. In other words,
-# any non-spacing mark or any format control character, except
-# U+200C ZERO WIDTH NON-JOINER (joining type U) and U+200D ZERO WIDTH
-# JOINER (joining type C).
+# - Those that not explicitly listed that are of General Category Mn or Cf
+# have joining type T.
+# - All others not explicitly listed have 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.
#
-# Joining type U includes all characters which are neither joining
-# type T, nor explicitly marked in this file as types R, L, D, or C.
-#
# #############################################################
# Unicode; Schematic Name; Joining Type; Joining Group
# 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>
0622; MADDA ON ALEF; R; ALEF
0623; HAMZA ON ALEF; R; ALEF
0648; WAW; R; WAW
0649; ALEF MAKSURA; D; YEH
064A; YEH; D; YEH
+066E; DOTLESS BEH; D; BEH
+066F; DOTLESS QAF; D; QAF
0671; HAMZAT WASL ON ALEF; R; ALEF
0672; WAVY HAMZA ON ALEF; R; ALEF
0673; WAVY HAMZA UNDER ALEF; R; ALEF
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>
+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
0715; DALATH; R; DALATH RISH
0716; DOTLESS DALATH RISH; R; DALATH RISH
0717; HE; R; HE
-0718; WAW; R; WAW
+0718; WAW; R; SYRIAC WAW
0719; ZAIN; R; ZAIN
071A; HETH; D; HETH
071B; TETH; D; TETH
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
# Other
200D; ZERO WIDTH JOINER; C; <no shaping>
+200C; ZERO WIDTH NON-JOINER; U; <no shaping>
projects / p5sagit/p5-mst-13.2.git / blobdiff