--- embedaddon/pcre/pcre_tables.c	2012/02/21 23:05:51	1.1.1.1
+++ embedaddon/pcre/pcre_tables.c	2013/07/22 08:25:55	1.1.1.4
@@ -6,7 +6,7 @@
 and semantics are as close as possible to those of the Perl 5 language.
 
                        Written by Philip Hazel
-           Copyright (c) 1997-2009 University of Cambridge
+           Copyright (c) 1997-2012 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -37,6 +37,7 @@ POSSIBILITY OF SUCH DAMAGE.
 -----------------------------------------------------------------------------
 */
 
+#ifndef PCRE_INCLUDED
 
 /* This module contains some fixed tables that are used by more than one of the
 PCRE code modules. The tables are also #included by the pcretest program, which
@@ -50,14 +51,21 @@ clashes with the library. */
 
 #include "pcre_internal.h"
 
+#endif /* PCRE_INCLUDED */
 
 /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
 the definition is next to the definition of the opcodes in pcre_internal.h. */
 
-const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
+const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
 
+/* Tables of horizontal and vertical whitespace characters, suitable for
+adding to classes. */
 
+const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST };
+const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST };
 
+
+
 /*************************************************
 *           Tables for UTF-8 support             *
 *************************************************/
@@ -65,44 +73,38 @@ const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
 /* These are the breakpoints for different numbers of bytes in a UTF-8
 character. */
 
-#ifdef SUPPORT_UTF8
+#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \
+  || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32))
 
-const int _pcre_utf8_table1[] =
+/* These tables are also required by pcretest in 16- or 32-bit mode. */
+
+const int PRIV(utf8_table1)[] =
   { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
 
-const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);
+const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int);
 
 /* These are the indicator bits and the mask for the data bits to set in the
 first byte of a character, indexed by the number of additional bytes. */
 
-const int _pcre_utf8_table2[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
-const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
+const int PRIV(utf8_table2)[] = { 0,    0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
+const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
 
 /* Table of the number of extra bytes, indexed by the first byte masked with
 0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
 
-const uschar _pcre_utf8_table4[] = {
+const pcre_uint8 PRIV(utf8_table4)[] = {
   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
   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 };
 
-#ifdef SUPPORT_JIT
-/* Full table of the number of extra bytes when the
-character code is greater or equal than 0xc0.
-See _pcre_utf8_table4 above. */
+#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/
 
-const uschar _pcre_utf8_char_sizes[] = {
-  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
-  1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
-  2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
-  3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,
-};
-#endif
+#ifdef SUPPORT_UTF
 
 /* Table to translate from particular type value to the general value. */
 
-const int _pcre_ucp_gentype[] = {
+const pcre_uint32 PRIV(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 */
@@ -113,11 +115,71 @@ const int _pcre_ucp_gentype[] = {
   ucp_Z, ucp_Z, ucp_Z                 /* Zl, Zp, Zs */
 };
 
+/* This table encodes the rules for finding the end of an extended grapheme
+cluster. Every code point has a grapheme break property which is one of the
+ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the
+properties of two adjacent code points. The left property selects a word from
+the table, and the right property selects a bit from that word like this:
+
+  ucp_gbtable[left-property] & (1 << right-property)
+
+The value is non-zero if a grapheme break is NOT permitted between the relevant
+two code points. The breaking rules are as follows:
+
+1. Break at the start and end of text (pretty obviously).
+
+2. Do not break between a CR and LF; otherwise, break before and   after
+   controls.
+
+3. Do not break Hangul syllable sequences, the rules for which are:
+
+    L may be followed by L, V, LV or LVT
+    LV or V may be followed by V or T
+    LVT or T may be followed by T
+
+4. Do not break before extending characters.
+
+The next two rules are only for extended grapheme clusters (but that's what we
+are implementing).
+
+5. Do not break before SpacingMarks.
+
+6. Do not break after Prepend characters.
+
+7. Otherwise, break everywhere.
+*/
+
+const pcre_uint32 PRIV(ucp_gbtable[]) = {
+   (1<<ucp_gbLF),                                           /*  0 CR */
+   0,                                                       /*  1 LF */
+   0,                                                       /*  2 Control */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  3 Extend */
+   (1<<ucp_gbExtend)|(1<<ucp_gbPrepend)|                    /*  4 Prepend */
+     (1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|
+     (1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)|
+     (1<<ucp_gbLVT)|(1<<ucp_gbOther),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark),                /*  5 SpacingMark */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)|   /*  6 L */
+     (1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  7 V */
+     (1<<ucp_gbT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /*  8 T */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)|   /*  9 LV */
+     (1<<ucp_gbT),
+
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT),   /* 10 LVT */
+   (1<<ucp_gbRegionalIndicator),                            /* 11 RegionalIndicator */
+   (1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)                 /* 12 Other */
+};
+
 #ifdef SUPPORT_JIT
-/* This table reverses _pcre_ucp_gentype. We can save the cost
+/* This table reverses PRIV(ucp_gentype). We can save the cost
 of a memory load. */
 
-const int _pcre_ucp_typerange[] = {
+const int PRIV(ucp_typerange)[] = {
   ucp_Cc, ucp_Cs,
   ucp_Ll, ucp_Lu,
   ucp_Mc, ucp_Mn,
@@ -126,7 +188,7 @@ const int _pcre_ucp_typerange[] = {
   ucp_Sc, ucp_So,
   ucp_Zl, ucp_Zs,
 };
-#endif
+#endif /* SUPPORT_JIT */
 
 /* 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
@@ -163,6 +225,7 @@ strings to make sure that UTF-8 support works on EBCDI
 #define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0"
 #define STRING_Cc0 STR_C STR_c "\0"
 #define STRING_Cf0 STR_C STR_f "\0"
+#define STRING_Chakma0 STR_C STR_h STR_a STR_k STR_m STR_a "\0"
 #define STRING_Cham0 STR_C STR_h STR_a STR_m "\0"
 #define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0"
 #define STRING_Cn0 STR_C STR_n "\0"
@@ -220,6 +283,9 @@ strings to make sure that UTF-8 support works on EBCDI
 #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_Meroitic_Cursive0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c STR_UNDERSCORE STR_C STR_u STR_r STR_s STR_i STR_v STR_e "\0"
+#define STRING_Meroitic_Hieroglyphs0 STR_M STR_e STR_r STR_o STR_i STR_t STR_i STR_c 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_Miao0 STR_M STR_i STR_a STR_o "\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"
@@ -253,11 +319,13 @@ strings to make sure that UTF-8 support works on EBCDI
 #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_Sharada0 STR_S STR_h STR_a STR_r STR_a STR_d STR_a "\0"
 #define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0"
 #define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0"
 #define STRING_Sk0 STR_S STR_k "\0"
 #define STRING_Sm0 STR_S STR_m "\0"
 #define STRING_So0 STR_S STR_o "\0"
+#define STRING_Sora_Sompeng0 STR_S STR_o STR_r STR_a STR_UNDERSCORE STR_S STR_o STR_m STR_p STR_e STR_n STR_g "\0"
 #define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0"
 #define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0"
 #define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0"
@@ -266,6 +334,7 @@ strings to make sure that UTF-8 support works on EBCDI
 #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_Takri0 STR_T STR_a STR_k STR_r STR_i "\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"
@@ -277,6 +346,7 @@ strings to make sure that UTF-8 support works on EBCDI
 #define STRING_Xan0 STR_X STR_a STR_n "\0"
 #define STRING_Xps0 STR_X STR_p STR_s "\0"
 #define STRING_Xsp0 STR_X STR_s STR_p "\0"
+#define STRING_Xuc0 STR_X STR_u STR_c "\0"
 #define STRING_Xwd0 STR_X STR_w STR_d "\0"
 #define STRING_Yi0 STR_Y STR_i "\0"
 #define STRING_Z0 STR_Z "\0"
@@ -284,7 +354,7 @@ strings to make sure that UTF-8 support works on EBCDI
 #define STRING_Zp0 STR_Z STR_p "\0"
 #define STRING_Zs0 STR_Z STR_s "\0"
 
-const char _pcre_utt_names[] =
+const char PRIV(utt_names)[] =
   STRING_Any0
   STRING_Arabic0
   STRING_Armenian0
@@ -303,6 +373,7 @@ const char _pcre_utt_names[] =
   STRING_Carian0
   STRING_Cc0
   STRING_Cf0
+  STRING_Chakma0
   STRING_Cham0
   STRING_Cherokee0
   STRING_Cn0
@@ -360,6 +431,9 @@ const char _pcre_utt_names[] =
   STRING_Mc0
   STRING_Me0
   STRING_Meetei_Mayek0
+  STRING_Meroitic_Cursive0
+  STRING_Meroitic_Hieroglyphs0
+  STRING_Miao0
   STRING_Mn0
   STRING_Mongolian0
   STRING_Myanmar0
@@ -393,11 +467,13 @@ const char _pcre_utt_names[] =
   STRING_Samaritan0
   STRING_Saurashtra0
   STRING_Sc0
+  STRING_Sharada0
   STRING_Shavian0
   STRING_Sinhala0
   STRING_Sk0
   STRING_Sm0
   STRING_So0
+  STRING_Sora_Sompeng0
   STRING_Sundanese0
   STRING_Syloti_Nagri0
   STRING_Syriac0
@@ -406,6 +482,7 @@ const char _pcre_utt_names[] =
   STRING_Tai_Le0
   STRING_Tai_Tham0
   STRING_Tai_Viet0
+  STRING_Takri0
   STRING_Tamil0
   STRING_Telugu0
   STRING_Thaana0
@@ -417,6 +494,7 @@ const char _pcre_utt_names[] =
   STRING_Xan0
   STRING_Xps0
   STRING_Xsp0
+  STRING_Xuc0
   STRING_Xwd0
   STRING_Yi0
   STRING_Z0
@@ -424,7 +502,7 @@ const char _pcre_utt_names[] =
   STRING_Zp0
   STRING_Zs0;
 
-const ucp_type_table _pcre_utt[] = {
+const ucp_type_table PRIV(utt)[] = {
   {   0, PT_ANY, 0 },
   {   4, PT_SC, ucp_Arabic },
   {  11, PT_SC, ucp_Armenian },
@@ -443,130 +521,138 @@ const ucp_type_table _pcre_utt[] = {
   { 118, PT_SC, ucp_Carian },
   { 125, PT_PC, ucp_Cc },
   { 128, PT_PC, ucp_Cf },
-  { 131, PT_SC, ucp_Cham },
-  { 136, PT_SC, ucp_Cherokee },
-  { 145, PT_PC, ucp_Cn },
-  { 148, PT_PC, ucp_Co },
-  { 151, PT_SC, ucp_Common },
-  { 158, PT_SC, ucp_Coptic },
-  { 165, PT_PC, ucp_Cs },
-  { 168, PT_SC, ucp_Cuneiform },
-  { 178, PT_SC, ucp_Cypriot },
-  { 186, PT_SC, ucp_Cyrillic },
-  { 195, PT_SC, ucp_Deseret },
-  { 203, PT_SC, ucp_Devanagari },
-  { 214, PT_SC, ucp_Egyptian_Hieroglyphs },
-  { 235, PT_SC, ucp_Ethiopic },
-  { 244, PT_SC, ucp_Georgian },
-  { 253, PT_SC, ucp_Glagolitic },
-  { 264, PT_SC, ucp_Gothic },
-  { 271, PT_SC, ucp_Greek },
-  { 277, PT_SC, ucp_Gujarati },
-  { 286, PT_SC, ucp_Gurmukhi },
-  { 295, PT_SC, ucp_Han },
-  { 299, PT_SC, ucp_Hangul },
-  { 306, PT_SC, ucp_Hanunoo },
-  { 314, PT_SC, ucp_Hebrew },
-  { 321, PT_SC, ucp_Hiragana },
-  { 330, PT_SC, ucp_Imperial_Aramaic },
-  { 347, PT_SC, ucp_Inherited },
-  { 357, PT_SC, ucp_Inscriptional_Pahlavi },
-  { 379, PT_SC, ucp_Inscriptional_Parthian },
-  { 402, PT_SC, ucp_Javanese },
-  { 411, PT_SC, ucp_Kaithi },
-  { 418, PT_SC, ucp_Kannada },
-  { 426, PT_SC, ucp_Katakana },
-  { 435, PT_SC, ucp_Kayah_Li },
-  { 444, PT_SC, ucp_Kharoshthi },
-  { 455, PT_SC, ucp_Khmer },
-  { 461, PT_GC, ucp_L },
-  { 463, PT_LAMP, 0 },
-  { 466, PT_SC, ucp_Lao },
-  { 470, PT_SC, ucp_Latin },
-  { 476, PT_SC, ucp_Lepcha },
-  { 483, PT_SC, ucp_Limbu },
-  { 489, PT_SC, ucp_Linear_B },
-  { 498, PT_SC, ucp_Lisu },
-  { 503, PT_PC, ucp_Ll },
-  { 506, PT_PC, ucp_Lm },
-  { 509, PT_PC, ucp_Lo },
-  { 512, PT_PC, ucp_Lt },
-  { 515, PT_PC, ucp_Lu },
-  { 518, PT_SC, ucp_Lycian },
-  { 525, PT_SC, ucp_Lydian },
-  { 532, PT_GC, ucp_M },
-  { 534, PT_SC, ucp_Malayalam },
-  { 544, PT_SC, ucp_Mandaic },
-  { 552, PT_PC, ucp_Mc },
-  { 555, PT_PC, ucp_Me },
-  { 558, PT_SC, ucp_Meetei_Mayek },
-  { 571, PT_PC, ucp_Mn },
-  { 574, PT_SC, ucp_Mongolian },
-  { 584, PT_SC, ucp_Myanmar },
-  { 592, PT_GC, ucp_N },
-  { 594, PT_PC, ucp_Nd },
-  { 597, PT_SC, ucp_New_Tai_Lue },
-  { 609, PT_SC, ucp_Nko },
-  { 613, PT_PC, ucp_Nl },
-  { 616, PT_PC, ucp_No },
-  { 619, PT_SC, ucp_Ogham },
-  { 625, PT_SC, ucp_Ol_Chiki },
-  { 634, PT_SC, ucp_Old_Italic },
-  { 645, PT_SC, ucp_Old_Persian },
-  { 657, PT_SC, ucp_Old_South_Arabian },
-  { 675, PT_SC, ucp_Old_Turkic },
-  { 686, PT_SC, ucp_Oriya },
-  { 692, PT_SC, ucp_Osmanya },
-  { 700, PT_GC, ucp_P },
-  { 702, PT_PC, ucp_Pc },
-  { 705, PT_PC, ucp_Pd },
-  { 708, PT_PC, ucp_Pe },
-  { 711, PT_PC, ucp_Pf },
-  { 714, PT_SC, ucp_Phags_Pa },
-  { 723, PT_SC, ucp_Phoenician },
-  { 734, PT_PC, ucp_Pi },
-  { 737, PT_PC, ucp_Po },
-  { 740, PT_PC, ucp_Ps },
-  { 743, PT_SC, ucp_Rejang },
-  { 750, PT_SC, ucp_Runic },
-  { 756, PT_GC, ucp_S },
-  { 758, PT_SC, ucp_Samaritan },
-  { 768, PT_SC, ucp_Saurashtra },
-  { 779, PT_PC, ucp_Sc },
-  { 782, PT_SC, ucp_Shavian },
-  { 790, PT_SC, ucp_Sinhala },
-  { 798, PT_PC, ucp_Sk },
-  { 801, PT_PC, ucp_Sm },
-  { 804, PT_PC, ucp_So },
-  { 807, PT_SC, ucp_Sundanese },
-  { 817, PT_SC, ucp_Syloti_Nagri },
-  { 830, PT_SC, ucp_Syriac },
-  { 837, PT_SC, ucp_Tagalog },
-  { 845, PT_SC, ucp_Tagbanwa },
-  { 854, PT_SC, ucp_Tai_Le },
-  { 861, PT_SC, ucp_Tai_Tham },
-  { 870, PT_SC, ucp_Tai_Viet },
-  { 879, PT_SC, ucp_Tamil },
-  { 885, PT_SC, ucp_Telugu },
-  { 892, PT_SC, ucp_Thaana },
-  { 899, PT_SC, ucp_Thai },
-  { 904, PT_SC, ucp_Tibetan },
-  { 912, PT_SC, ucp_Tifinagh },
-  { 921, PT_SC, ucp_Ugaritic },
-  { 930, PT_SC, ucp_Vai },
-  { 934, PT_ALNUM, 0 },
-  { 938, PT_PXSPACE, 0 },
-  { 942, PT_SPACE, 0 },
-  { 946, PT_WORD, 0 },
-  { 950, PT_SC, ucp_Yi },
-  { 953, PT_GC, ucp_Z },
-  { 955, PT_PC, ucp_Zl },
-  { 958, PT_PC, ucp_Zp },
-  { 961, PT_PC, ucp_Zs }
+  { 131, PT_SC, ucp_Chakma },
+  { 138, PT_SC, ucp_Cham },
+  { 143, PT_SC, ucp_Cherokee },
+  { 152, PT_PC, ucp_Cn },
+  { 155, PT_PC, ucp_Co },
+  { 158, PT_SC, ucp_Common },
+  { 165, PT_SC, ucp_Coptic },
+  { 172, PT_PC, ucp_Cs },
+  { 175, PT_SC, ucp_Cuneiform },
+  { 185, PT_SC, ucp_Cypriot },
+  { 193, PT_SC, ucp_Cyrillic },
+  { 202, PT_SC, ucp_Deseret },
+  { 210, PT_SC, ucp_Devanagari },
+  { 221, PT_SC, ucp_Egyptian_Hieroglyphs },
+  { 242, PT_SC, ucp_Ethiopic },
+  { 251, PT_SC, ucp_Georgian },
+  { 260, PT_SC, ucp_Glagolitic },
+  { 271, PT_SC, ucp_Gothic },
+  { 278, PT_SC, ucp_Greek },
+  { 284, PT_SC, ucp_Gujarati },
+  { 293, PT_SC, ucp_Gurmukhi },
+  { 302, PT_SC, ucp_Han },
+  { 306, PT_SC, ucp_Hangul },
+  { 313, PT_SC, ucp_Hanunoo },
+  { 321, PT_SC, ucp_Hebrew },
+  { 328, PT_SC, ucp_Hiragana },
+  { 337, PT_SC, ucp_Imperial_Aramaic },
+  { 354, PT_SC, ucp_Inherited },
+  { 364, PT_SC, ucp_Inscriptional_Pahlavi },
+  { 386, PT_SC, ucp_Inscriptional_Parthian },
+  { 409, PT_SC, ucp_Javanese },
+  { 418, PT_SC, ucp_Kaithi },
+  { 425, PT_SC, ucp_Kannada },
+  { 433, PT_SC, ucp_Katakana },
+  { 442, PT_SC, ucp_Kayah_Li },
+  { 451, PT_SC, ucp_Kharoshthi },
+  { 462, PT_SC, ucp_Khmer },
+  { 468, PT_GC, ucp_L },
+  { 470, PT_LAMP, 0 },
+  { 473, PT_SC, ucp_Lao },
+  { 477, PT_SC, ucp_Latin },
+  { 483, PT_SC, ucp_Lepcha },
+  { 490, PT_SC, ucp_Limbu },
+  { 496, PT_SC, ucp_Linear_B },
+  { 505, PT_SC, ucp_Lisu },
+  { 510, PT_PC, ucp_Ll },
+  { 513, PT_PC, ucp_Lm },
+  { 516, PT_PC, ucp_Lo },
+  { 519, PT_PC, ucp_Lt },
+  { 522, PT_PC, ucp_Lu },
+  { 525, PT_SC, ucp_Lycian },
+  { 532, PT_SC, ucp_Lydian },
+  { 539, PT_GC, ucp_M },
+  { 541, PT_SC, ucp_Malayalam },
+  { 551, PT_SC, ucp_Mandaic },
+  { 559, PT_PC, ucp_Mc },
+  { 562, PT_PC, ucp_Me },
+  { 565, PT_SC, ucp_Meetei_Mayek },
+  { 578, PT_SC, ucp_Meroitic_Cursive },
+  { 595, PT_SC, ucp_Meroitic_Hieroglyphs },
+  { 616, PT_SC, ucp_Miao },
+  { 621, PT_PC, ucp_Mn },
+  { 624, PT_SC, ucp_Mongolian },
+  { 634, PT_SC, ucp_Myanmar },
+  { 642, PT_GC, ucp_N },
+  { 644, PT_PC, ucp_Nd },
+  { 647, PT_SC, ucp_New_Tai_Lue },
+  { 659, PT_SC, ucp_Nko },
+  { 663, PT_PC, ucp_Nl },
+  { 666, PT_PC, ucp_No },
+  { 669, PT_SC, ucp_Ogham },
+  { 675, PT_SC, ucp_Ol_Chiki },
+  { 684, PT_SC, ucp_Old_Italic },
+  { 695, PT_SC, ucp_Old_Persian },
+  { 707, PT_SC, ucp_Old_South_Arabian },
+  { 725, PT_SC, ucp_Old_Turkic },
+  { 736, PT_SC, ucp_Oriya },
+  { 742, PT_SC, ucp_Osmanya },
+  { 750, PT_GC, ucp_P },
+  { 752, PT_PC, ucp_Pc },
+  { 755, PT_PC, ucp_Pd },
+  { 758, PT_PC, ucp_Pe },
+  { 761, PT_PC, ucp_Pf },
+  { 764, PT_SC, ucp_Phags_Pa },
+  { 773, PT_SC, ucp_Phoenician },
+  { 784, PT_PC, ucp_Pi },
+  { 787, PT_PC, ucp_Po },
+  { 790, PT_PC, ucp_Ps },
+  { 793, PT_SC, ucp_Rejang },
+  { 800, PT_SC, ucp_Runic },
+  { 806, PT_GC, ucp_S },
+  { 808, PT_SC, ucp_Samaritan },
+  { 818, PT_SC, ucp_Saurashtra },
+  { 829, PT_PC, ucp_Sc },
+  { 832, PT_SC, ucp_Sharada },
+  { 840, PT_SC, ucp_Shavian },
+  { 848, PT_SC, ucp_Sinhala },
+  { 856, PT_PC, ucp_Sk },
+  { 859, PT_PC, ucp_Sm },
+  { 862, PT_PC, ucp_So },
+  { 865, PT_SC, ucp_Sora_Sompeng },
+  { 878, PT_SC, ucp_Sundanese },
+  { 888, PT_SC, ucp_Syloti_Nagri },
+  { 901, PT_SC, ucp_Syriac },
+  { 908, PT_SC, ucp_Tagalog },
+  { 916, PT_SC, ucp_Tagbanwa },
+  { 925, PT_SC, ucp_Tai_Le },
+  { 932, PT_SC, ucp_Tai_Tham },
+  { 941, PT_SC, ucp_Tai_Viet },
+  { 950, PT_SC, ucp_Takri },
+  { 956, PT_SC, ucp_Tamil },
+  { 962, PT_SC, ucp_Telugu },
+  { 969, PT_SC, ucp_Thaana },
+  { 976, PT_SC, ucp_Thai },
+  { 981, PT_SC, ucp_Tibetan },
+  { 989, PT_SC, ucp_Tifinagh },
+  { 998, PT_SC, ucp_Ugaritic },
+  { 1007, PT_SC, ucp_Vai },
+  { 1011, PT_ALNUM, 0 },
+  { 1015, PT_PXSPACE, 0 },
+  { 1019, PT_SPACE, 0 },
+  { 1023, PT_UCNC, 0 },
+  { 1027, PT_WORD, 0 },
+  { 1031, PT_SC, ucp_Yi },
+  { 1034, PT_GC, ucp_Z },
+  { 1036, PT_PC, ucp_Zl },
+  { 1039, PT_PC, ucp_Zp },
+  { 1042, PT_PC, ucp_Zs }
 };
 
-const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
+const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table);
 
-#endif  /* SUPPORT_UTF8 */
+#endif /* SUPPORT_UTF */
 
 /* End of pcre_tables.c */