Update Unicode tables to Unicode version 5.2.0.

git-svn-id: svn://vcs.exim.org/pcre/code/trunk@491 2f5784b3-3f2a-0410-8824-cb99058d5e15

1 files changed, 163 insertions, 118 deletions

diff --git a/pcre_tables.c b/pcre_tables.c
index 6333134..2fd7031 100644
--- a/pcre_tables.c
+++ b/pcre_tables.c
@@ -120,7 +120,9 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Any0 STR_A STR_n STR_y "\0"
 #define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0"
 #define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0"
+#define STRING_Avestan0 STR_A STR_v STR_e STR_s STR_t STR_a STR_n "\0"
 #define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0"
+#define STRING_Bamum0 STR_B STR_a STR_m STR_u STR_m "\0"
 #define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0"
 #define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0"
 #define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0"
@@ -143,6 +145,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0"
 #define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0"
 #define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0"
+#define STRING_Egyptian_Hieroglyphs0 STR_E STR_g STR_y STR_p STR_t STR_i STR_a STR_n STR_UNDERSCORE STR_H STR_i STR_e STR_r STR_o STR_g STR_l STR_y STR_p STR_h STR_s "\0"
 #define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0"
 #define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0"
 #define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0"
@@ -155,7 +158,12 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0"
 #define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0"
 #define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0"
+#define STRING_Imperial_Aramaic0 STR_I STR_m STR_p STR_e STR_r STR_i STR_a STR_l STR_UNDERSCORE STR_A STR_r STR_a STR_m STR_a STR_i STR_c "\0"
 #define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0"
+#define STRING_Inscriptional_Pahlavi0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_h STR_l STR_a STR_v STR_i "\0"
+#define STRING_Inscriptional_Parthian0 STR_I STR_n STR_s STR_c STR_r STR_i STR_p STR_t STR_i STR_o STR_n STR_a STR_l STR_UNDERSCORE STR_P STR_a STR_r STR_t STR_h STR_i STR_a STR_n "\0"
+#define STRING_Javanese0 STR_J STR_a STR_v STR_a STR_n STR_e STR_s STR_e "\0"
+#define STRING_Kaithi0 STR_K STR_a STR_i STR_t STR_h STR_i "\0"
 #define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0"
 #define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0"
 #define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0"
@@ -168,6 +176,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0"
 #define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0"
 #define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0"
+#define STRING_Lisu0 STR_L STR_i STR_s STR_u "\0"
 #define STRING_Ll0 STR_L STR_l "\0"
 #define STRING_Lm0 STR_L STR_m "\0"
 #define STRING_Lo0 STR_L STR_o "\0"
@@ -179,6 +188,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0"
 #define STRING_Mc0 STR_M STR_c "\0"
 #define STRING_Me0 STR_M STR_e "\0"
+#define STRING_Meetei_Mayek0 STR_M STR_e STR_e STR_t STR_e STR_i STR_UNDERSCORE STR_M STR_a STR_y STR_e STR_k "\0"
 #define STRING_Mn0 STR_M STR_n "\0"
 #define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0"
 #define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0"
@@ -192,6 +202,8 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0"
 #define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0"
 #define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0"
+#define STRING_Old_South_Arabian0 STR_O STR_l STR_d STR_UNDERSCORE STR_S STR_o STR_u STR_t STR_h STR_UNDERSCORE STR_A STR_r STR_a STR_b STR_i STR_a STR_n "\0"
+#define STRING_Old_Turkic0 STR_O STR_l STR_d STR_UNDERSCORE STR_T STR_u STR_r STR_k STR_i STR_c "\0"
 #define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0"
 #define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0"
 #define STRING_P0 STR_P "\0"
@@ -207,6 +219,7 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0"
 #define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0"
 #define STRING_S0 STR_S "\0"
+#define STRING_Samaritan0 STR_S STR_a STR_m STR_a STR_r STR_i STR_t STR_a STR_n "\0"
 #define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0"
 #define STRING_Sc0 STR_S STR_c "\0"
 #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
@@ -220,6 +233,8 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0"
 #define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0"
 #define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0"
+#define STRING_Tai_Tham0 STR_T STR_a STR_i STR_UNDERSCORE STR_T STR_h STR_a STR_m "\0"
+#define STRING_Tai_Viet0 STR_T STR_a STR_i STR_UNDERSCORE STR_V STR_i STR_e STR_t "\0"
 #define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0"
 #define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0"
 #define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0"
@@ -234,11 +249,13 @@ strings to make sure that UTF-8 support works on EBCDIC platforms. */
 #define STRING_Zp0 STR_Z STR_p "\0"
 #define STRING_Zs0 STR_Z STR_s "\0"
 
-const char _pcre_utt_names[] =
+const char _pcre_utt_names[] = 
   STRING_Any0
   STRING_Arabic0
   STRING_Armenian0
+  STRING_Avestan0
   STRING_Balinese0
+  STRING_Bamum0
   STRING_Bengali0
   STRING_Bopomofo0
   STRING_Braille0
@@ -261,6 +278,7 @@ const char _pcre_utt_names[] =
   STRING_Cyrillic0
   STRING_Deseret0
   STRING_Devanagari0
+  STRING_Egyptian_Hieroglyphs0
   STRING_Ethiopic0
   STRING_Georgian0
   STRING_Glagolitic0
@@ -273,7 +291,12 @@ const char _pcre_utt_names[] =
   STRING_Hanunoo0
   STRING_Hebrew0
   STRING_Hiragana0
+  STRING_Imperial_Aramaic0
   STRING_Inherited0
+  STRING_Inscriptional_Pahlavi0
+  STRING_Inscriptional_Parthian0
+  STRING_Javanese0
+  STRING_Kaithi0
   STRING_Kannada0
   STRING_Katakana0
   STRING_Kayah_Li0
@@ -286,6 +309,7 @@ const char _pcre_utt_names[] =
   STRING_Lepcha0
   STRING_Limbu0
   STRING_Linear_B0
+  STRING_Lisu0
   STRING_Ll0
   STRING_Lm0
   STRING_Lo0
@@ -297,6 +321,7 @@ const char _pcre_utt_names[] =
   STRING_Malayalam0
   STRING_Mc0
   STRING_Me0
+  STRING_Meetei_Mayek0
   STRING_Mn0
   STRING_Mongolian0
   STRING_Myanmar0
@@ -310,6 +335,8 @@ const char _pcre_utt_names[] =
   STRING_Ol_Chiki0
   STRING_Old_Italic0
   STRING_Old_Persian0
+  STRING_Old_South_Arabian0
+  STRING_Old_Turkic0
   STRING_Oriya0
   STRING_Osmanya0
   STRING_P0
@@ -325,6 +352,7 @@ const char _pcre_utt_names[] =
   STRING_Rejang0
   STRING_Runic0
   STRING_S0
+  STRING_Samaritan0
   STRING_Saurashtra0
   STRING_Sc0
   STRING_Shavian0
@@ -338,6 +366,8 @@ const char _pcre_utt_names[] =
   STRING_Tagalog0
   STRING_Tagbanwa0
   STRING_Tai_Le0
+  STRING_Tai_Tham0
+  STRING_Tai_Viet0
   STRING_Tamil0
   STRING_Telugu0
   STRING_Thaana0
@@ -352,123 +382,138 @@ const char _pcre_utt_names[] =
   STRING_Zp0
   STRING_Zs0;
 
-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_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 ucp_type_table _pcre_utt[] = { 
+  {   0, PT_ANY, 0 }, 
+  {   4, PT_SC, ucp_Arabic }, 
+  {  11, PT_SC, ucp_Armenian }, 
+  {  20, PT_SC, ucp_Avestan }, 
+  {  28, PT_SC, ucp_Balinese }, 
+  {  37, PT_SC, ucp_Bamum }, 
+  {  43, PT_SC, ucp_Bengali }, 
+  {  51, PT_SC, ucp_Bopomofo }, 
+  {  60, PT_SC, ucp_Braille }, 
+  {  68, PT_SC, ucp_Buginese }, 
+  {  77, PT_SC, ucp_Buhid }, 
+  {  83, PT_GC, ucp_C }, 
+  {  85, PT_SC, ucp_Canadian_Aboriginal }, 
+  { 105, PT_SC, ucp_Carian }, 
+  { 112, PT_PC, ucp_Cc }, 
+  { 115, PT_PC, ucp_Cf }, 
+  { 118, PT_SC, ucp_Cham }, 
+  { 123, PT_SC, ucp_Cherokee }, 
+  { 132, PT_PC, ucp_Cn }, 
+  { 135, PT_PC, ucp_Co }, 
+  { 138, PT_SC, ucp_Common }, 
+  { 145, PT_SC, ucp_Coptic }, 
+  { 152, PT_PC, ucp_Cs }, 
+  { 155, PT_SC, ucp_Cuneiform }, 
+  { 165, PT_SC, ucp_Cypriot }, 
+  { 173, PT_SC, ucp_Cyrillic }, 
+  { 182, PT_SC, ucp_Deseret }, 
+  { 190, PT_SC, ucp_Devanagari }, 
+  { 201, PT_SC, ucp_Egyptian_Hieroglyphs }, 
+  { 222, PT_SC, ucp_Ethiopic }, 
+  { 231, PT_SC, ucp_Georgian }, 
+  { 240, PT_SC, ucp_Glagolitic }, 
+  { 251, PT_SC, ucp_Gothic }, 
+  { 258, PT_SC, ucp_Greek }, 
+  { 264, PT_SC, ucp_Gujarati }, 
+  { 273, PT_SC, ucp_Gurmukhi }, 
+  { 282, PT_SC, ucp_Han }, 
+  { 286, PT_SC, ucp_Hangul }, 
+  { 293, PT_SC, ucp_Hanunoo }, 
+  { 301, PT_SC, ucp_Hebrew }, 
+  { 308, PT_SC, ucp_Hiragana }, 
+  { 317, PT_SC, ucp_Imperial_Aramaic }, 
+  { 334, PT_SC, ucp_Inherited }, 
+  { 344, PT_SC, ucp_Inscriptional_Pahlavi }, 
+  { 366, PT_SC, ucp_Inscriptional_Parthian }, 
+  { 389, PT_SC, ucp_Javanese }, 
+  { 398, PT_SC, ucp_Kaithi }, 
+  { 405, PT_SC, ucp_Kannada }, 
+  { 413, PT_SC, ucp_Katakana }, 
+  { 422, PT_SC, ucp_Kayah_Li }, 
+  { 431, PT_SC, ucp_Kharoshthi }, 
+  { 442, PT_SC, ucp_Khmer }, 
+  { 448, PT_GC, ucp_L }, 
+  { 450, PT_LAMP, 0 }, 
+  { 453, PT_SC, ucp_Lao }, 
+  { 457, PT_SC, ucp_Latin }, 
+  { 463, PT_SC, ucp_Lepcha }, 
+  { 470, PT_SC, ucp_Limbu }, 
+  { 476, PT_SC, ucp_Linear_B }, 
+  { 485, PT_SC, ucp_Lisu }, 
+  { 490, PT_PC, ucp_Ll }, 
+  { 493, PT_PC, ucp_Lm }, 
+  { 496, PT_PC, ucp_Lo }, 
+  { 499, PT_PC, ucp_Lt }, 
+  { 502, PT_PC, ucp_Lu }, 
+  { 505, PT_SC, ucp_Lycian }, 
+  { 512, PT_SC, ucp_Lydian }, 
+  { 519, PT_GC, ucp_M }, 
+  { 521, PT_SC, ucp_Malayalam }, 
+  { 531, PT_PC, ucp_Mc }, 
+  { 534, PT_PC, ucp_Me }, 
+  { 537, PT_SC, ucp_Meetei_Mayek }, 
+  { 550, PT_PC, ucp_Mn }, 
+  { 553, PT_SC, ucp_Mongolian }, 
+  { 563, PT_SC, ucp_Myanmar }, 
+  { 571, PT_GC, ucp_N }, 
+  { 573, PT_PC, ucp_Nd }, 
+  { 576, PT_SC, ucp_New_Tai_Lue }, 
+  { 588, PT_SC, ucp_Nko }, 
+  { 592, PT_PC, ucp_Nl }, 
+  { 595, PT_PC, ucp_No }, 
+  { 598, PT_SC, ucp_Ogham }, 
+  { 604, PT_SC, ucp_Ol_Chiki }, 
+  { 613, PT_SC, ucp_Old_Italic }, 
+  { 624, PT_SC, ucp_Old_Persian }, 
+  { 636, PT_SC, ucp_Old_South_Arabian }, 
+  { 654, PT_SC, ucp_Old_Turkic }, 
+  { 665, PT_SC, ucp_Oriya }, 
+  { 671, PT_SC, ucp_Osmanya }, 
+  { 679, PT_GC, ucp_P }, 
+  { 681, PT_PC, ucp_Pc }, 
+  { 684, PT_PC, ucp_Pd }, 
+  { 687, PT_PC, ucp_Pe }, 
+  { 690, PT_PC, ucp_Pf }, 
+  { 693, PT_SC, ucp_Phags_Pa }, 
+  { 702, PT_SC, ucp_Phoenician }, 
+  { 713, PT_PC, ucp_Pi }, 
+  { 716, PT_PC, ucp_Po }, 
+  { 719, PT_PC, ucp_Ps }, 
+  { 722, PT_SC, ucp_Rejang }, 
+  { 729, PT_SC, ucp_Runic }, 
+  { 735, PT_GC, ucp_S }, 
+  { 737, PT_SC, ucp_Samaritan }, 
+  { 747, PT_SC, ucp_Saurashtra }, 
+  { 758, PT_PC, ucp_Sc }, 
+  { 761, PT_SC, ucp_Shavian }, 
+  { 769, PT_SC, ucp_Sinhala }, 
+  { 777, PT_PC, ucp_Sk }, 
+  { 780, PT_PC, ucp_Sm }, 
+  { 783, PT_PC, ucp_So }, 
+  { 786, PT_SC, ucp_Sundanese }, 
+  { 796, PT_SC, ucp_Syloti_Nagri }, 
+  { 809, PT_SC, ucp_Syriac }, 
+  { 816, PT_SC, ucp_Tagalog }, 
+  { 824, PT_SC, ucp_Tagbanwa }, 
+  { 833, PT_SC, ucp_Tai_Le }, 
+  { 840, PT_SC, ucp_Tai_Tham }, 
+  { 849, PT_SC, ucp_Tai_Viet }, 
+  { 858, PT_SC, ucp_Tamil }, 
+  { 864, PT_SC, ucp_Telugu }, 
+  { 871, PT_SC, ucp_Thaana }, 
+  { 878, PT_SC, ucp_Thai }, 
+  { 883, PT_SC, ucp_Tibetan }, 
+  { 891, PT_SC, ucp_Tifinagh }, 
+  { 900, PT_SC, ucp_Ugaritic }, 
+  { 909, PT_SC, ucp_Vai }, 
+  { 913, PT_SC, ucp_Yi }, 
+  { 916, PT_GC, ucp_Z }, 
+  { 918, PT_PC, ucp_Zl }, 
+  { 921, PT_PC, ucp_Zp }, 
+  { 924, PT_PC, ucp_Zs } 
 };
 
 const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);