[Summary view] [Print] [Text view]

   1  # ArabicShaping-5.0.0.txt
   2  # Date: 2006-07-14, 11:23:00 PST [KW]
   3  #
   4  # This file is a normative contributory data file in the
   5  # Unicode Character Database.
   6  #
   7  # Copyright (c) 1991-2006 Unicode, Inc.
   8  # For terms of use, see http://www.unicode.org/terms_of_use.html
   9  #
  10  # This file defines the shaping classes for Arabic and Syriac
  11  # positional shaping, repeating in machine readable form the
  12  # information printed in Tables 8-3, 8-7, 8-8, 8-11, 8-12, and
  13  # 8-13 of The Unicode Standard, Version 4.0.
  14  #
  15  # See sections 8.2 and 8.3 of The Unicode Standard, Version 4.0
  16  # for more information.
  17  #
  18  # Each line contains four fields, separated by a semicolon.
  19  #
  20  # Field 0: the code point, in 4-digit hexadecimal
  21  #   form, of an Arabic or Syriac character.
  22  # Field 1: gives a short schematic name for that character,
  23  #   abbreviated from the normative Unicode character name.
  24  # Field 2: defines the joining type (property name: Joining_Type)
  25  #   R Right_Joining
  26  #   L Left_Joining
  27  #   D Dual_Joining
  28  #   C Join_Causing
  29  #   U Non_Joining
  30  #   T Transparent
  31  #       See the Arabic block description for more information on these types.
  32  # Field 3: defines the joining group (property name: Joining_Group)
  33  #
  34  # The values of the joining group are based schematically on character
  35  # names. Where a schematic character name consists of two or more parts separated
  36  # by spaces, the formal Joining_Group property value, as specified in
  37  # PropertyValueAliases.txt, consists of the same name parts joined by
  38  # underscores. Hence, the entry:
  39  #
  40  #   0629; TEH MARBUTA; R; TEH MARBUTA
  41  #
  42  # corresponds to [Joining_Group = Teh_Marbuta].
  43  #
  44  # Note: For historical reasons, the property value [Joining_Group = Hamza_On_Heh_Goal]
  45  #   is anachronistically named. It used to apply to both of the following characters
  46  #   in earlier versions of the standard:
  47  #
  48  #   U+06C2 ARABIC LETTER HEH GOAL WITH HAMZA ABOVE
  49  #   U+06C3 ARABIC LETTER TEH MARBUTA GOAL
  50  #
  51  #   However, it currently applies only to U+06C3, and *not* to U+06C2.
  52  #   To avoid destabilizing existing Joining_Group property aliases, the
  53  #   value Hamza_On_Heh_Goal has not been changed, despite the fact that it
  54  #   no longer applies to Hamza On Heh Goal, but only to Teh Marbuta Goal.
  55  #
  56  # Note: Code points that are not explicitly listed in this file are
  57  # either of joining type T or U:
  58  #
  59  # - Those that not explicitly listed that are of General Category Mn, Me, or Cf
  60  #   have joining type T.
  61  # - All others not explicitly listed have type U.
  62  #
  63  # For an explicit listing of characters of joining type T, see
  64  # the derived property file DerivedJoiningType.txt.
  65  #
  66  # There are currently no characters of type L defined in Unicode.
  67  #
  68  # #############################################################
  69   
  70  # Unicode; Schematic Name; Joining Type; Joining Group
  71  
  72  # Arabic characters
  73  
  74  0600; ARABIC NUMBER SIGN; U; No_Joining_Group
  75  0601; ARABIC SIGN SANAH; U; No_Joining_Group
  76  0602; ARABIC FOOTNOTE MARKER; U; No_Joining_Group
  77  0603; ARABIC SIGN SAFHA; U; No_Joining_Group
  78  060B; AFGHANI SIGN; U; No_Joining_Group
  79  0621; HAMZA; U; No_Joining_Group
  80  0622; MADDA ON ALEF; R; ALEF
  81  0623; HAMZA ON ALEF; R; ALEF
  82  0624; HAMZA ON WAW; R; WAW
  83  0625; HAMZA UNDER ALEF; R; ALEF
  84  0626; HAMZA ON YEH; D; YEH
  85  0627; ALEF; R; ALEF
  86  0628; BEH; D; BEH
  87  0629; TEH MARBUTA; R; TEH MARBUTA
  88  062A; TEH; D; BEH
  89  062B; THEH; D; BEH
  90  062C; JEEM; D; HAH
  91  062D; HAH; D; HAH
  92  062E; KHAH; D; HAH
  93  062F; DAL; R; DAL
  94  0630; THAL; R; DAL
  95  0631; REH; R; REH
  96  0632; ZAIN; R; REH
  97  0633; SEEN; D; SEEN
  98  0634; SHEEN; D; SEEN
  99  0635; SAD; D; SAD
 100  0636; DAD; D; SAD
 101  0637; TAH; D; TAH
 102  0638; ZAH; D; TAH
 103  0639; AIN; D; AIN
 104  063A; GHAIN; D; AIN
 105  0640; TATWEEL; C; No_Joining_Group
 106  0641; FEH; D; FEH
 107  0642; QAF; D; QAF
 108  0643; KAF; D; KAF
 109  0644; LAM; D; LAM
 110  0645; MEEM; D; MEEM
 111  0646; NOON; D; NOON
 112  0647; HEH; D; HEH
 113  0648; WAW; R; WAW
 114  0649; ALEF MAKSURA; D; YEH
 115  064A; YEH; D; YEH
 116  066E; DOTLESS BEH; D; BEH
 117  066F; DOTLESS QAF; D; QAF
 118  0671; HAMZAT WASL ON ALEF; R; ALEF
 119  0672; WAVY HAMZA ON ALEF; R; ALEF
 120  0673; WAVY HAMZA UNDER ALEF; R; ALEF
 121  0674; HIGH HAMZA; U; No_Joining_Group
 122  0675; HIGH HAMZA ALEF; R; ALEF
 123  0676; HIGH HAMZA WAW; R; WAW
 124  0677; HIGH HAMZA WAW WITH DAMMA; R; WAW
 125  0678; HIGH HAMZA YEH; D; YEH
 126  0679; TEH WITH SMALL TAH; D; BEH
 127  067A; TEH WITH 2 DOTS VERTICAL ABOVE; D; BEH
 128  067B; BEH WITH 2 DOTS VERTICAL BELOW; D; BEH
 129  067C; TEH WITH RING; D; BEH
 130  067D; TEH WITH 3 DOTS ABOVE DOWNWARD; D; BEH
 131  067E; TEH WITH 3 DOTS BELOW; D; BEH
 132  067F; TEH WITH 4 DOTS ABOVE; D; BEH
 133  0680; BEH WITH 4 DOTS BELOW; D; BEH
 134  0681; HAMZA ON HAH; D; HAH
 135  0682; HAH WITH 2 DOTS VERTICAL ABOVE; D; HAH
 136  0683; HAH WITH MIDDLE 2 DOTS; D; HAH
 137  0684; HAH WITH MIDDLE 2 DOTS VERTICAL; D; HAH
 138  0685; HAH WITH 3 DOTS ABOVE; D; HAH
 139  0686; HAH WITH MIDDLE 3 DOTS DOWNWARD; D; HAH
 140  0687; HAH WITH MIDDLE 4 DOTS; D; HAH
 141  0688; DAL WITH SMALL TAH; R; DAL
 142  0689; DAL WITH RING; R; DAL
 143  068A; DAL WITH DOT BELOW; R; DAL
 144  068B; DAL WITH DOT BELOW AND SMALL TAH; R; DAL
 145  068C; DAL WITH 2 DOTS ABOVE; R; DAL
 146  068D; DAL WITH 2 DOTS BELOW; R; DAL
 147  068E; DAL WITH 3 DOTS ABOVE; R; DAL
 148  068F; DAL WITH 3 DOTS ABOVE DOWNWARD; R; DAL
 149  0690; DAL WITH 4 DOTS ABOVE; R; DAL
 150  0691; REH WITH SMALL TAH; R; REH
 151  0692; REH WITH SMALL V; R; REH
 152  0693; REH WITH RING; R; REH
 153  0694; REH WITH DOT BELOW; R; REH
 154  0695; REH WITH SMALL V BELOW; R; REH
 155  0696; REH WITH DOT BELOW AND DOT ABOVE; R; REH
 156  0697; REH WITH 2 DOTS ABOVE; R; REH
 157  0698; REH WITH 3 DOTS ABOVE; R; REH
 158  0699; REH WITH 4 DOTS ABOVE; R; REH
 159  069A; SEEN WITH DOT BELOW AND DOT ABOVE; D; SEEN
 160  069B; SEEN WITH 3 DOTS BELOW; D; SEEN
 161  069C; SEEN WITH 3 DOTS BELOW AND 3 DOTS ABOVE; D; SEEN
 162  069D; SAD WITH 2 DOTS BELOW; D; SAD
 163  069E; SAD WITH 3 DOTS ABOVE; D; SAD
 164  069F; TAH WITH 3 DOTS ABOVE; D; TAH
 165  06A0; AIN WITH 3 DOTS ABOVE; D; AIN
 166  06A1; DOTLESS FEH; D; FEH
 167  06A2; FEH WITH DOT MOVED BELOW; D; FEH
 168  06A3; FEH WITH DOT BELOW; D; FEH
 169  06A4; FEH WITH 3 DOTS ABOVE; D; FEH
 170  06A5; FEH WITH 3 DOTS BELOW; D; FEH
 171  06A6; FEH WITH 4 DOTS ABOVE; D; FEH
 172  06A7; QAF WITH DOT ABOVE; D; QAF
 173  06A8; QAF WITH 3 DOTS ABOVE; D; QAF
 174  06A9; KEHEH; D; GAF
 175  06AA; SWASH KAF; D; SWASH KAF
 176  06AB; KAF WITH RING; D; GAF
 177  06AC; KAF WITH DOT ABOVE; D; KAF
 178  06AD; KAF WITH 3 DOTS ABOVE; D; KAF
 179  06AE; KAF WITH 3 DOTS BELOW; D; KAF
 180  06AF; GAF; D; GAF
 181  06B0; GAF WITH RING; D; GAF
 182  06B1; GAF WITH 2 DOTS ABOVE; D; GAF
 183  06B2; GAF WITH 2 DOTS BELOW; D; GAF
 184  06B3; GAF WITH 2 DOTS VERTICAL BELOW; D; GAF
 185  06B4; GAF WITH 3 DOTS ABOVE; D; GAF
 186  06B5; LAM WITH SMALL V; D; LAM
 187  06B6; LAM WITH DOT ABOVE; D; LAM
 188  06B7; LAM WITH 3 DOTS ABOVE; D; LAM
 189  06B8; LAM WITH 3 DOTS BELOW; D; LAM
 190  06B9; NOON WITH DOT BELOW; D; NOON
 191  06BA; DOTLESS NOON; D; NOON
 192  06BB; DOTLESS NOON WITH SMALL TAH; D; NOON
 193  06BC; NOON WITH RING; D; NOON
 194  06BD; NOON WITH 3 DOTS ABOVE; D; NOON
 195  06BE; KNOTTED HEH; D; KNOTTED HEH
 196  06BF; HAH WITH MIDDLE 3 DOTS DOWNWARD AND DOT ABOVE; D; HAH
 197  06C0; HAMZA ON HEH; R; TEH MARBUTA
 198  06C1; HEH GOAL; D; HEH GOAL
 199  06C2; HAMZA ON HEH GOAL; D; HEH GOAL
 200  06C3; TEH MARBUTA GOAL; R; HAMZA ON HEH GOAL
 201  06C4; WAW WITH RING; R; WAW
 202  06C5; WAW WITH BAR; R; WAW
 203  06C6; WAW WITH SMALL V; R; WAW
 204  06C7; WAW WITH DAMMA; R; WAW
 205  06C8; WAW WITH ALEF ABOVE; R; WAW
 206  06C9; WAW WITH INVERTED SMALL V; R; WAW
 207  06CA; WAW WITH 2 DOTS ABOVE; R; WAW
 208  06CB; WAW WITH 3 DOTS ABOVE; R; WAW
 209  06CC; DOTLESS YEH; D; YEH
 210  06CD; YEH WITH TAIL; R; YEH WITH TAIL
 211  06CE; YEH WITH SMALL V; D; YEH
 212  06CF; WAW WITH DOT ABOVE; R; WAW
 213  06D0; YEH WITH 2 DOTS VERTICAL BELOW; D; YEH
 214  06D1; YEH WITH 3 DOTS BELOW; D; YEH
 215  06D2; YEH BARREE; R; YEH BARREE
 216  06D3; HAMZA ON YEH BARREE; R; YEH BARREE
 217  06D5; AE; R; TEH MARBUTA
 218  06DD; ARABIC END OF AYAH; U; No_Joining_Group
 219  06EE; DAL WITH INVERTED V; R; DAL
 220  06EF; REH WITH INVERTED V; R; REH
 221  06FA; SEEN WITH DOT BELOW AND 3 DOTS ABOVE; D; SEEN
 222  06FB; DAD WITH DOT BELOW; D; SAD
 223  06FC; GHAIN WITH DOT BELOW; D; AIN
 224  06FF; HEH WITH INVERTED V; D; KNOTTED HEH
 225  
 226  # Syriac characters
 227  
 228  0710; ALAPH; R; ALAPH
 229  0712; BETH; D; BETH
 230  0713; GAMAL; D; GAMAL
 231  0714; GAMAL GARSHUNI; D; GAMAL
 232  0715; DALATH; R; DALATH RISH
 233  0716; DOTLESS DALATH RISH; R; DALATH RISH
 234  0717; HE; R; HE
 235  0718; WAW; R; SYRIAC WAW
 236  0719; ZAIN; R; ZAIN
 237  071A; HETH; D; HETH
 238  071B; TETH; D; TETH
 239  071C; TETH GARSHUNI; D; TETH
 240  071D; YUDH; D; YUDH
 241  071E; YUDH HE; R; YUDH HE
 242  071F; KAPH; D; KAPH
 243  0720; LAMADH; D; LAMADH
 244  0721; MIM; D; MIM
 245  0722; NUN; D; NUN
 246  0723; SEMKATH; D; SEMKATH
 247  0724; FINAL SEMKATH; D; FINAL SEMKATH
 248  0725; E; D; E
 249  0726; PE; D; PE
 250  0727; REVERSED PE; D; REVERSED PE
 251  0728; SADHE; R; SADHE
 252  0729; QAPH; D; QAPH
 253  072A; RISH; R; DALATH RISH
 254  072B; SHIN; D; SHIN
 255  072C; TAW; R; TAW
 256  072D; PERSIAN BHETH; D; BETH
 257  072E; PERSIAN GHAMAL; D; GAMAL
 258  072F; PERSIAN DHALATH; R; DALATH RISH
 259  074D; SOGDIAN ZHAIN; R; ZHAIN
 260  074E; SOGDIAN KHAPH; D; KHAPH
 261  074F; SOGDIAN FE; D; FE
 262  
 263  # Arabic supplement characters
 264  
 265  0750; BEH WITH 3 DOTS HORIZONTALLY BELOW; D; BEH
 266  0751; BEH WITH DOT BELOW AND 3 DOTS ABOVE; D; BEH
 267  0752; BEH WITH 3 DOTS POINTING UPWARDS BELOW; D; BEH
 268  0753; BEH WITH 3 DOTS POINTING UPWARDS BELOW AND 2 DOTS ABOVE; D; BEH
 269  0754; BEH WITH 2 DOTS BELOW AND DOT ABOVE; D; BEH
 270  0755; BEH WITH INVERTED SMALL V BELOW; D; BEH
 271  0756; BEH WITH SMALL V; D; BEH
 272  0757; HAH WITH 2 DOTS ABOVE; D; HAH
 273  0758; HAH WITH 3 DOTS POINTING UPWARDS BELOW; D; HAH
 274  0759; DAL WITH 2 DOTS VERTICALLY BELOW AND SMALL TAH; R; DAL
 275  075A; DAL WITH INVERTED SMALL V BELOW; R; DAL
 276  075B; REH WITH STROKE; R; REH
 277  075C; SEEN WITH 4 DOTS ABOVE; D; SEEN
 278  075D; AIN WITH 2 DOTS ABOVE; D; AIN
 279  075E; AIN WITH 3 DOTS POINTING DOWNWARDS ABOVE; D; AIN
 280  075F; AIN WITH 2 DOTS VERTICALLY ABOVE; D; AIN
 281  0760; FEH WITH 2 DOTS BELOW; D; FEH
 282  0761; FEH WITH 3 DOTS POINTING UPWARDS BELOW; D; FEH
 283  0762; KEHEH WITH DOT ABOVE; D; GAF
 284  0763; KEHEH WITH 3 DOTS ABOVE; D; GAF
 285  0764; KEHEH WITH 3 DOTS POINTING UPWARDS BELOW; D; GAF
 286  0765; MEEM WITH DOT ABOVE; D; MEEM
 287  0766; MEEM WITH DOT BELOW; D; MEEM
 288  0767; NOON WITH 2 DOTS BELOW; D; NOON
 289  0768; NOON WITH SMALL TAH; D; NOON
 290  0769; NOON WITH SMALL V; D; NOON
 291  076A; LAM WITH BAR; D; LAM
 292  076B; REH WITH 2 DOTS VERTICALLY ABOVE; R; REH
 293  076C; REH WITH HAMZA ABOVE; R; REH
 294  076D; SEEN WITH 2 DOTS VERTICALLY ABOVE; D; SEEN
 295  
 296  # N'Ko Characters
 297  
 298  07CA; NKO A; D; No_Joining_Group
 299  07CB; NKO EE; D; No_Joining_Group
 300  07CC; NKO I; D; No_Joining_Group
 301  07CD; NKO E; D; No_Joining_Group
 302  07CE; NKO U; D; No_Joining_Group
 303  07CF; NKO OO; D; No_Joining_Group
 304  07D0; NKO O; D; No_Joining_Group
 305  07D1; NKO DAGBASINNA; D; No_Joining_Group
 306  07D2; NKO N; D; No_Joining_Group
 307  07D3; NKO BA; D; No_Joining_Group
 308  07D4; NKO PA; D; No_Joining_Group
 309  07D5; NKO TA; D; No_Joining_Group
 310  07D6; NKO JA; D; No_Joining_Group
 311  07D7; NKO CHA; D; No_Joining_Group
 312  07D8; NKO DA; D; No_Joining_Group
 313  07D9; NKO RA; D; No_Joining_Group
 314  07DA; NKO RRA; D; No_Joining_Group
 315  07DB; NKO SA; D; No_Joining_Group
 316  07DC; NKO GBA; D; No_Joining_Group
 317  07DD; NKO FA; D; No_Joining_Group
 318  07DE; NKO KA; D; No_Joining_Group
 319  07DF; NKO LA; D; No_Joining_Group
 320  07E0; NKO NA WOLOSO; D; No_Joining_Group
 321  07E1; NKO MA; D; No_Joining_Group
 322  07E2; NKO NYA; D; No_Joining_Group
 323  07E3; NKO NA; D; No_Joining_Group
 324  07E4; NKO HA; D; No_Joining_Group
 325  07E5; NKO WA; D; No_Joining_Group
 326  07E6; NKO YA; D; No_Joining_Group
 327  07E7; NKO NYA WOLOSO; D; No_Joining_Group
 328  07E8; NKO JONA JA; D; No_Joining_Group
 329  07E9; NKO JONA CHA; D; No_Joining_Group
 330  07EA; NKO JONA RA; D; No_Joining_Group
 331  07FA; NKO LAJANYALAN; C; No_Joining_Group
 332  
 333  # Other
 334  
 335  200D; ZERO WIDTH JOINER; C; No_Joining_Group
 336  200C; ZERO WIDTH NON-JOINER; U; No_Joining_Group
 337  
 338  # EOF