Final tidies for new Unicode property code; upgrade to Unicode 5.1.0.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@351 2f5784b3-3f2a-0410-8824-cb99058d5e15

1 files changed, 144 insertions, 106 deletions

diff --git a/pcre_tables.c b/pcre_tables.c
index e37dcb6..160bc5d 100644
--- a/pcre_tables.c
+++ b/pcre_tables.c
@@ -87,6 +87,19 @@ const uschar _pcre_utf8_table4[] = {
   2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
   3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
 
+/* Table to translate from particular type value to the general value. */
+
+const int _pcre_ucp_gentype[] = {
+  ucp_C, ucp_C, ucp_C, ucp_C, ucp_C,  /* Cc, Cf, Cn, Co, Cs */
+  ucp_L, ucp_L, ucp_L, ucp_L, ucp_L,  /* Ll, Lu, Lm, Lo, Lt */
+  ucp_M, ucp_M, ucp_M,                /* Mc, Me, Mn */
+  ucp_N, ucp_N, ucp_N,                /* Nd, Nl, No */
+  ucp_P, ucp_P, ucp_P, ucp_P, ucp_P,  /* Pc, Pd, Pe, Pf, Pi */
+  ucp_P, ucp_P,                       /* Ps, Po */
+  ucp_S, ucp_S, ucp_S, ucp_S,         /* Sc, Sk, Sm, So */
+  ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
+};
+
 /* The pcre_utt[] table below translates Unicode property names into type and
 code values. It is searched by binary chop, so must be in collating sequence of
 name. Originally, the table contained pointers to the name strings in the first
@@ -94,7 +107,10 @@ field of each entry. However, that leads to a large number of relocations when
 a shared library is dynamically loaded. A significant reduction is made by
 putting all the names into a single, large string and then using offsets in the
 table itself. Maintenance is more error-prone, but frequent changes to this
-data is unlikely. */
+data are unlikely.
+
+July 2008: There is now a script called maint/GenerateUtt.py which can be used
+to generate this data instead of maintaining it entirely by hand. */
 
 const char _pcre_utt_names[] =
   "Any\0"
@@ -108,8 +124,10 @@ const char _pcre_utt_names[] =
   "Buhid\0"
   "C\0"
   "Canadian_Aboriginal\0"
+  "Carian\0"
   "Cc\0"
   "Cf\0"
+  "Cham\0"
   "Cherokee\0"
   "Cn\0"
   "Co\0"
@@ -136,12 +154,14 @@ const char _pcre_utt_names[] =
   "Inherited\0"
   "Kannada\0"
   "Katakana\0"
+  "Kayah_Li\0"
   "Kharoshthi\0"
   "Khmer\0"
   "L\0"
   "L&\0"
   "Lao\0"
   "Latin\0"
+  "Lepcha\0"
   "Limbu\0"
   "Linear_B\0"
   "Ll\0"
@@ -149,6 +169,8 @@ const char _pcre_utt_names[] =
   "Lo\0"
   "Lt\0"
   "Lu\0"
+  "Lycian\0"
+  "Lydian\0"
   "M\0"
   "Malayalam\0"
   "Mc\0"
@@ -163,6 +185,7 @@ const char _pcre_utt_names[] =
   "Nl\0"
   "No\0"
   "Ogham\0"
+  "Ol_Chiki\0"
   "Old_Italic\0"
   "Old_Persian\0"
   "Oriya\0"
@@ -177,14 +200,17 @@ const char _pcre_utt_names[] =
   "Pi\0"
   "Po\0"
   "Ps\0"
+  "Rejang\0"
   "Runic\0"
   "S\0"
+  "Saurashtra\0"
   "Sc\0"
   "Shavian\0"
   "Sinhala\0"
   "Sk\0"
   "Sm\0"
   "So\0"
+  "Sundanese\0"
   "Syloti_Nagri\0"
   "Syriac\0"
   "Tagalog\0"
@@ -197,6 +223,7 @@ const char _pcre_utt_names[] =
   "Tibetan\0"
   "Tifinagh\0"
   "Ugaritic\0"
+  "Vai\0"
   "Yi\0"
   "Z\0"
   "Zl\0"
@@ -204,111 +231,122 @@ const char _pcre_utt_names[] =
   "Zs\0";
 
 const ucp_type_table _pcre_utt[] = {
-  { 0,   PT_ANY, 0 },
-  { 4,   PT_SC, ucp_Arabic },
-  { 11,  PT_SC, ucp_Armenian },
-  { 20,  PT_SC, ucp_Balinese },
-  { 29,  PT_SC, ucp_Bengali },
-  { 37,  PT_SC, ucp_Bopomofo },
-  { 46,  PT_SC, ucp_Braille },
-  { 54,  PT_SC, ucp_Buginese },
-  { 63,  PT_SC, ucp_Buhid },
-  { 69,  PT_GC, ucp_C },
-  { 71,  PT_SC, ucp_Canadian_Aboriginal },
-  { 91,  PT_PC, ucp_Cc },
-  { 94,  PT_PC, ucp_Cf },
-  { 97,  PT_SC, ucp_Cherokee },
-  { 106, PT_PC, ucp_Cn },
-  { 109, PT_PC, ucp_Co },
-  { 112, PT_SC, ucp_Common },
-  { 119, PT_SC, ucp_Coptic },
-  { 126, PT_PC, ucp_Cs },
-  { 129, PT_SC, ucp_Cuneiform },
-  { 139, PT_SC, ucp_Cypriot },
-  { 147, PT_SC, ucp_Cyrillic },
-  { 156, PT_SC, ucp_Deseret },
-  { 164, PT_SC, ucp_Devanagari },
-  { 175, PT_SC, ucp_Ethiopic },
-  { 184, PT_SC, ucp_Georgian },
-  { 193, PT_SC, ucp_Glagolitic },
-  { 204, PT_SC, ucp_Gothic },
-  { 211, PT_SC, ucp_Greek },
-  { 217, PT_SC, ucp_Gujarati },
-  { 226, PT_SC, ucp_Gurmukhi },
-  { 235, PT_SC, ucp_Han },
-  { 239, PT_SC, ucp_Hangul },
-  { 246, PT_SC, ucp_Hanunoo },
-  { 254, PT_SC, ucp_Hebrew },
-  { 261, PT_SC, ucp_Hiragana },
-  { 270, PT_SC, ucp_Inherited },
-  { 280, PT_SC, ucp_Kannada },
-  { 288, PT_SC, ucp_Katakana },
-  { 297, PT_SC, ucp_Kharoshthi },
-  { 308, PT_SC, ucp_Khmer },
-  { 314, PT_GC, ucp_L },
-  { 316, PT_LAMP, 0 },
-  { 319, PT_SC, ucp_Lao },
-  { 323, PT_SC, ucp_Latin },
-  { 329, PT_SC, ucp_Limbu },
-  { 335, PT_SC, ucp_Linear_B },
-  { 344, PT_PC, ucp_Ll },
-  { 347, PT_PC, ucp_Lm },
-  { 350, PT_PC, ucp_Lo },
-  { 353, PT_PC, ucp_Lt },
-  { 356, PT_PC, ucp_Lu },
-  { 359, PT_GC, ucp_M },
-  { 361, PT_SC, ucp_Malayalam },
-  { 371, PT_PC, ucp_Mc },
-  { 374, PT_PC, ucp_Me },
-  { 377, PT_PC, ucp_Mn },
-  { 380, PT_SC, ucp_Mongolian },
-  { 390, PT_SC, ucp_Myanmar },
-  { 398, PT_GC, ucp_N },
-  { 400, PT_PC, ucp_Nd },
-  { 403, PT_SC, ucp_New_Tai_Lue },
-  { 415, PT_SC, ucp_Nko },
-  { 419, PT_PC, ucp_Nl },
-  { 422, PT_PC, ucp_No },
-  { 425, PT_SC, ucp_Ogham },
-  { 431, PT_SC, ucp_Old_Italic },
-  { 442, PT_SC, ucp_Old_Persian },
-  { 454, PT_SC, ucp_Oriya },
-  { 460, PT_SC, ucp_Osmanya },
-  { 468, PT_GC, ucp_P },
-  { 470, PT_PC, ucp_Pc },
-  { 473, PT_PC, ucp_Pd },
-  { 476, PT_PC, ucp_Pe },
-  { 479, PT_PC, ucp_Pf },
-  { 482, PT_SC, ucp_Phags_Pa },
-  { 491, PT_SC, ucp_Phoenician },
-  { 502, PT_PC, ucp_Pi },
-  { 505, PT_PC, ucp_Po },
-  { 508, PT_PC, ucp_Ps },
-  { 511, PT_SC, ucp_Runic },
-  { 517, PT_GC, ucp_S },
-  { 519, PT_PC, ucp_Sc },
-  { 522, PT_SC, ucp_Shavian },
-  { 530, PT_SC, ucp_Sinhala },
-  { 538, PT_PC, ucp_Sk },
-  { 541, PT_PC, ucp_Sm },
-  { 544, PT_PC, ucp_So },
-  { 547, PT_SC, ucp_Syloti_Nagri },
-  { 560, PT_SC, ucp_Syriac },
-  { 567, PT_SC, ucp_Tagalog },
-  { 575, PT_SC, ucp_Tagbanwa },
-  { 584, PT_SC, ucp_Tai_Le },
-  { 591, PT_SC, ucp_Tamil },
-  { 597, PT_SC, ucp_Telugu },
-  { 604, PT_SC, ucp_Thaana },
-  { 611, PT_SC, ucp_Thai },
-  { 616, PT_SC, ucp_Tibetan },
-  { 624, PT_SC, ucp_Tifinagh },
-  { 633, PT_SC, ucp_Ugaritic },
-  { 642, PT_SC, ucp_Yi },
-  { 645, PT_GC, ucp_Z },
-  { 647, PT_PC, ucp_Zl },
-  { 650, PT_PC, ucp_Zp },
-  { 653, PT_PC, ucp_Zs }
+  {   0, PT_ANY, 0 },
+  {   4, PT_SC, ucp_Arabic },
+  {  11, PT_SC, ucp_Armenian },
+  {  20, PT_SC, ucp_Balinese },
+  {  29, PT_SC, ucp_Bengali },
+  {  37, PT_SC, ucp_Bopomofo },
+  {  46, PT_SC, ucp_Braille },
+  {  54, PT_SC, ucp_Buginese },
+  {  63, PT_SC, ucp_Buhid },
+  {  69, PT_GC, ucp_C },
+  {  71, PT_SC, ucp_Canadian_Aboriginal },
+  {  91, PT_SC, ucp_Carian },
+  {  98, PT_PC, ucp_Cc },
+  { 101, PT_PC, ucp_Cf },
+  { 104, PT_SC, ucp_Cham },
+  { 109, PT_SC, ucp_Cherokee },
+  { 118, PT_PC, ucp_Cn },
+  { 121, PT_PC, ucp_Co },
+  { 124, PT_SC, ucp_Common },
+  { 131, PT_SC, ucp_Coptic },
+  { 138, PT_PC, ucp_Cs },
+  { 141, PT_SC, ucp_Cuneiform },
+  { 151, PT_SC, ucp_Cypriot },
+  { 159, PT_SC, ucp_Cyrillic },
+  { 168, PT_SC, ucp_Deseret },
+  { 176, PT_SC, ucp_Devanagari },
+  { 187, PT_SC, ucp_Ethiopic },
+  { 196, PT_SC, ucp_Georgian },
+  { 205, PT_SC, ucp_Glagolitic },
+  { 216, PT_SC, ucp_Gothic },
+  { 223, PT_SC, ucp_Greek },
+  { 229, PT_SC, ucp_Gujarati },
+  { 238, PT_SC, ucp_Gurmukhi },
+  { 247, PT_SC, ucp_Han },
+  { 251, PT_SC, ucp_Hangul },
+  { 258, PT_SC, ucp_Hanunoo },
+  { 266, PT_SC, ucp_Hebrew },
+  { 273, PT_SC, ucp_Hiragana },
+  { 282, PT_SC, ucp_Inherited },
+  { 292, PT_SC, ucp_Kannada },
+  { 300, PT_SC, ucp_Katakana },
+  { 309, PT_SC, ucp_Kayah_Li },
+  { 318, PT_SC, ucp_Kharoshthi },
+  { 329, PT_SC, ucp_Khmer },
+  { 335, PT_GC, ucp_L },
+  { 337, PT_LAMP, 0 },
+  { 340, PT_SC, ucp_Lao },
+  { 344, PT_SC, ucp_Latin },
+  { 350, PT_SC, ucp_Lepcha },
+  { 357, PT_SC, ucp_Limbu },
+  { 363, PT_SC, ucp_Linear_B },
+  { 372, PT_PC, ucp_Ll },
+  { 375, PT_PC, ucp_Lm },
+  { 378, PT_PC, ucp_Lo },
+  { 381, PT_PC, ucp_Lt },
+  { 384, PT_PC, ucp_Lu },
+  { 387, PT_SC, ucp_Lycian },
+  { 394, PT_SC, ucp_Lydian },
+  { 401, PT_GC, ucp_M },
+  { 403, PT_SC, ucp_Malayalam },
+  { 413, PT_PC, ucp_Mc },
+  { 416, PT_PC, ucp_Me },
+  { 419, PT_PC, ucp_Mn },
+  { 422, PT_SC, ucp_Mongolian },
+  { 432, PT_SC, ucp_Myanmar },
+  { 440, PT_GC, ucp_N },
+  { 442, PT_PC, ucp_Nd },
+  { 445, PT_SC, ucp_New_Tai_Lue },
+  { 457, PT_SC, ucp_Nko },
+  { 461, PT_PC, ucp_Nl },
+  { 464, PT_PC, ucp_No },
+  { 467, PT_SC, ucp_Ogham },
+  { 473, PT_SC, ucp_Ol_Chiki },
+  { 482, PT_SC, ucp_Old_Italic },
+  { 493, PT_SC, ucp_Old_Persian },
+  { 505, PT_SC, ucp_Oriya },
+  { 511, PT_SC, ucp_Osmanya },
+  { 519, PT_GC, ucp_P },
+  { 521, PT_PC, ucp_Pc },
+  { 524, PT_PC, ucp_Pd },
+  { 527, PT_PC, ucp_Pe },
+  { 530, PT_PC, ucp_Pf },
+  { 533, PT_SC, ucp_Phags_Pa },
+  { 542, PT_SC, ucp_Phoenician },
+  { 553, PT_PC, ucp_Pi },
+  { 556, PT_PC, ucp_Po },
+  { 559, PT_PC, ucp_Ps },
+  { 562, PT_SC, ucp_Rejang },
+  { 569, PT_SC, ucp_Runic },
+  { 575, PT_GC, ucp_S },
+  { 577, PT_SC, ucp_Saurashtra },
+  { 588, PT_PC, ucp_Sc },
+  { 591, PT_SC, ucp_Shavian },
+  { 599, PT_SC, ucp_Sinhala },
+  { 607, PT_PC, ucp_Sk },
+  { 610, PT_PC, ucp_Sm },
+  { 613, PT_PC, ucp_So },
+  { 616, PT_SC, ucp_Sundanese },
+  { 626, PT_SC, ucp_Syloti_Nagri },
+  { 639, PT_SC, ucp_Syriac },
+  { 646, PT_SC, ucp_Tagalog },
+  { 654, PT_SC, ucp_Tagbanwa },
+  { 663, PT_SC, ucp_Tai_Le },
+  { 670, PT_SC, ucp_Tamil },
+  { 676, PT_SC, ucp_Telugu },
+  { 683, PT_SC, ucp_Thaana },
+  { 690, PT_SC, ucp_Thai },
+  { 695, PT_SC, ucp_Tibetan },
+  { 703, PT_SC, ucp_Tifinagh },
+  { 712, PT_SC, ucp_Ugaritic },
+  { 721, PT_SC, ucp_Vai },
+  { 725, PT_SC, ucp_Yi },
+  { 728, PT_GC, ucp_Z },
+  { 730, PT_PC, ucp_Zl },
+  { 733, PT_PC, ucp_Zp },
+  { 736, PT_PC, ucp_Zs }
 };
 
 const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);