-/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.3 2006/11/07 16:50:36 ph10 Exp $ */
+/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */
/*************************************************
* Perl-Compatible Regular Expressions *
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
- Copyright (c) 1997-2006 University of Cambridge
+ Copyright (c) 1997-2007 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
/* These are the breakpoints for different numbers of bytes in a UTF-8
character. */
+#ifdef SUPPORT_UTF8
+
const int _pcre_utf8_table1[] =
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
-/* Table of the number of extra characters, indexed by the first character
-masked with 0x3f. The highest number for a valid UTF-8 character is in fact
-0x3d. */
+/* 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[] = {
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
{ "Any", PT_ANY, 0 },
{ "Arabic", PT_SC, ucp_Arabic },
{ "Armenian", PT_SC, ucp_Armenian },
+ { "Balinese", PT_SC, ucp_Balinese },
{ "Bengali", PT_SC, ucp_Bengali },
{ "Bopomofo", PT_SC, ucp_Bopomofo },
{ "Braille", PT_SC, ucp_Braille },
{ "Common", PT_SC, ucp_Common },
{ "Coptic", PT_SC, ucp_Coptic },
{ "Cs", PT_PC, ucp_Cs },
+ { "Cuneiform", PT_SC, ucp_Cuneiform },
{ "Cypriot", PT_SC, ucp_Cypriot },
{ "Cyrillic", PT_SC, ucp_Cyrillic },
{ "Deseret", PT_SC, ucp_Deseret },
{ "N", PT_GC, ucp_N },
{ "Nd", PT_PC, ucp_Nd },
{ "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue },
+ { "Nko", PT_SC, ucp_Nko },
{ "Nl", PT_PC, ucp_Nl },
{ "No", PT_PC, ucp_No },
{ "Ogham", PT_SC, ucp_Ogham },
{ "Pd", PT_PC, ucp_Pd },
{ "Pe", PT_PC, ucp_Pe },
{ "Pf", PT_PC, ucp_Pf },
+ { "Phags_Pa", PT_SC, ucp_Phags_Pa },
+ { "Phoenician", PT_SC, ucp_Phoenician },
{ "Pi", PT_PC, ucp_Pi },
{ "Po", PT_PC, ucp_Po },
{ "Ps", PT_PC, ucp_Ps },
const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
+#endif /* SUPPORT_UTF8 */
+
/* End of pcre_tables.c */