[exim.git] / src / src / pcre / pcre_tables.c

/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */

/*************************************************
*      Perl-Compatible Regular Expressions       *
*************************************************/

/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.

                       Written by Philip Hazel
           Copyright (c) 1997-2007 University of Cambridge

-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:

    * Redistributions of source code must retain the above copyright notice,
      this list of conditions and the following disclaimer.

    * Redistributions in binary form must reproduce the above copyright
      notice, this list of conditions and the following disclaimer in the
      documentation and/or other materials provided with the distribution.

    * Neither the name of the University of Cambridge nor the names of its
      contributors may be used to endorse or promote products derived from
      this software without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/


/* 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
uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
clashes with the library. */


#include "pcre_internal.h"


/* 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 };


/*************************************************
*           Tables for UTF-8 support             *
*************************************************/

/* 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_table1_size = sizeof(_pcre_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};

/* 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,
  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 };

/* This table translates Unicode property names into type and code values. It
is searched by binary chop, so must be in collating sequence of name. */

const ucp_type_table _pcre_utt[] = {
  { "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 },
  { "Buginese",            PT_SC,   ucp_Buginese },
  { "Buhid",               PT_SC,   ucp_Buhid },
  { "C",                   PT_GC,   ucp_C },
  { "Canadian_Aboriginal", PT_SC,   ucp_Canadian_Aboriginal },
  { "Cc",                  PT_PC,   ucp_Cc },
  { "Cf",                  PT_PC,   ucp_Cf },
  { "Cherokee",            PT_SC,   ucp_Cherokee },
  { "Cn",                  PT_PC,   ucp_Cn },
  { "Co",                  PT_PC,   ucp_Co },
  { "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 },
  { "Devanagari",          PT_SC,   ucp_Devanagari },
  { "Ethiopic",            PT_SC,   ucp_Ethiopic },
  { "Georgian",            PT_SC,   ucp_Georgian },
  { "Glagolitic",          PT_SC,   ucp_Glagolitic },
  { "Gothic",              PT_SC,   ucp_Gothic },
  { "Greek",               PT_SC,   ucp_Greek },
  { "Gujarati",            PT_SC,   ucp_Gujarati },
  { "Gurmukhi",            PT_SC,   ucp_Gurmukhi },
  { "Han",                 PT_SC,   ucp_Han },
  { "Hangul",              PT_SC,   ucp_Hangul },
  { "Hanunoo",             PT_SC,   ucp_Hanunoo },
  { "Hebrew",              PT_SC,   ucp_Hebrew },
  { "Hiragana",            PT_SC,   ucp_Hiragana },
  { "Inherited",           PT_SC,   ucp_Inherited },
  { "Kannada",             PT_SC,   ucp_Kannada },
  { "Katakana",            PT_SC,   ucp_Katakana },
  { "Kharoshthi",          PT_SC,   ucp_Kharoshthi },
  { "Khmer",               PT_SC,   ucp_Khmer },
  { "L",                   PT_GC,   ucp_L },
  { "L&",                  PT_LAMP, 0 },
  { "Lao",                 PT_SC,   ucp_Lao },
  { "Latin",               PT_SC,   ucp_Latin },
  { "Limbu",               PT_SC,   ucp_Limbu },
  { "Linear_B",            PT_SC,   ucp_Linear_B },
  { "Ll",                  PT_PC,   ucp_Ll },
  { "Lm",                  PT_PC,   ucp_Lm },
  { "Lo",                  PT_PC,   ucp_Lo },
  { "Lt",                  PT_PC,   ucp_Lt },
  { "Lu",                  PT_PC,   ucp_Lu },
  { "M",                   PT_GC,   ucp_M },
  { "Malayalam",           PT_SC,   ucp_Malayalam },
  { "Mc",                  PT_PC,   ucp_Mc },
  { "Me",                  PT_PC,   ucp_Me },
  { "Mn",                  PT_PC,   ucp_Mn },
  { "Mongolian",           PT_SC,   ucp_Mongolian },
  { "Myanmar",             PT_SC,   ucp_Myanmar },
  { "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 },
  { "Old_Italic",          PT_SC,   ucp_Old_Italic },
  { "Old_Persian",         PT_SC,   ucp_Old_Persian },
  { "Oriya",               PT_SC,   ucp_Oriya },
  { "Osmanya",             PT_SC,   ucp_Osmanya },
  { "P",                   PT_GC,   ucp_P },
  { "Pc",                  PT_PC,   ucp_Pc },
  { "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 },
  { "Runic",               PT_SC,   ucp_Runic },
  { "S",                   PT_GC,   ucp_S },
  { "Sc",                  PT_PC,   ucp_Sc },
  { "Shavian",             PT_SC,   ucp_Shavian },
  { "Sinhala",             PT_SC,   ucp_Sinhala },
  { "Sk",                  PT_PC,   ucp_Sk },
  { "Sm",                  PT_PC,   ucp_Sm },
  { "So",                  PT_PC,   ucp_So },
  { "Syloti_Nagri",        PT_SC,   ucp_Syloti_Nagri },
  { "Syriac",              PT_SC,   ucp_Syriac },
  { "Tagalog",             PT_SC,   ucp_Tagalog },
  { "Tagbanwa",            PT_SC,   ucp_Tagbanwa },
  { "Tai_Le",              PT_SC,   ucp_Tai_Le },
  { "Tamil",               PT_SC,   ucp_Tamil },
  { "Telugu",              PT_SC,   ucp_Telugu },
  { "Thaana",              PT_SC,   ucp_Thaana },
  { "Thai",                PT_SC,   ucp_Thai },
  { "Tibetan",             PT_SC,   ucp_Tibetan },
  { "Tifinagh",            PT_SC,   ucp_Tifinagh },
  { "Ugaritic",            PT_SC,   ucp_Ugaritic },
  { "Yi",                  PT_SC,   ucp_Yi },
  { "Z",                   PT_GC,   ucp_Z },
  { "Zl",                  PT_PC,   ucp_Zl },
  { "Zp",                  PT_PC,   ucp_Zp },
  { "Zs",                  PT_PC,   ucp_Zs }
};

const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);

#endif  /* SUPPORT_UTF8 */

/* End of pcre_tables.c */
Commit	Line	Data
64f2600a	1	/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */
8ac170f3 PH	2
	3	/*************************************************
	4	* Perl-Compatible Regular Expressions *
	5	*************************************************/
	6
	7	/* PCRE is a library of functions to support regular expressions whose syntax
	8	and semantics are as close as possible to those of the Perl 5 language.
	9
	10	Written by Philip Hazel
64f2600a	11	Copyright (c) 1997-2007 University of Cambridge
8ac170f3 PH	12
	13	-----------------------------------------------------------------------------
	14	Redistribution and use in source and binary forms, with or without
	15	modification, are permitted provided that the following conditions are met:
	16
	17	* Redistributions of source code must retain the above copyright notice,
	18	this list of conditions and the following disclaimer.
	19
	20	* Redistributions in binary form must reproduce the above copyright
	21	notice, this list of conditions and the following disclaimer in the
	22	documentation and/or other materials provided with the distribution.
	23
	24	* Neither the name of the University of Cambridge nor the names of its
	25	contributors may be used to endorse or promote products derived from
	26	this software without specific prior written permission.
	27
	28	THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
	29	AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
	30	IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
	31	ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
	32	LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
	33	CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
	34	SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
	35	INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
	36	CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
	37	ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
	38	POSSIBILITY OF SUCH DAMAGE.
	39	-----------------------------------------------------------------------------
	40	*/
	41
	42
	43	/* This module contains some fixed tables that are used by more than one of the
aa41d2de PH	44	PCRE code modules. The tables are also #included by the pcretest program, which
	45	uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name
	46	clashes with the library. */
8ac170f3 PH	47
	48
	49	#include "pcre_internal.h"
	50
	51
	52	/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that
aa41d2de	53	the definition is next to the definition of the opcodes in pcre_internal.h. */
8ac170f3 PH	54
	55	const uschar _pcre_OP_lengths[] = { OP_LENGTHS };
	56
	57
	58
	59	/*************************************************
	60	* Tables for UTF-8 support *
	61	*************************************************/
	62
	63	/* These are the breakpoints for different numbers of bytes in a UTF-8
	64	character. */
	65
64f2600a PH	66	#ifdef SUPPORT_UTF8
64f2600a PH	67
8ac170f3 PH	68	const int _pcre_utf8_table1[] =
	69	{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff};
	70
	71	const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int);
	72
	73	/* These are the indicator bits and the mask for the data bits to set in the
	74	first byte of a character, indexed by the number of additional bytes. */
	75
	76	const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc};
	77	const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01};
	78
6bf342e1 PH	79	/* Table of the number of extra bytes, indexed by the first byte masked with
6bf342e1 PH	80	0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */
8ac170f3 PH	81
	82	const uschar _pcre_utf8_table4[] = {
	83	1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
	84	1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
	85	2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
	86	3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 };
	87
aa41d2de PH	88	/* This table translates Unicode property names into type and code values. It
aa41d2de PH	89	is searched by binary chop, so must be in collating sequence of name. */
8ac170f3 PH	90
8ac170f3 PH	91	const ucp_type_table _pcre_utt[] = {
aa41d2de PH	92	{ "Any", PT_ANY, 0 },
	93	{ "Arabic", PT_SC, ucp_Arabic },
	94	{ "Armenian", PT_SC, ucp_Armenian },
6bf342e1	95	{ "Balinese", PT_SC, ucp_Balinese },
aa41d2de PH	96	{ "Bengali", PT_SC, ucp_Bengali },
	97	{ "Bopomofo", PT_SC, ucp_Bopomofo },
	98	{ "Braille", PT_SC, ucp_Braille },
	99	{ "Buginese", PT_SC, ucp_Buginese },
	100	{ "Buhid", PT_SC, ucp_Buhid },
	101	{ "C", PT_GC, ucp_C },
	102	{ "Canadian_Aboriginal", PT_SC, ucp_Canadian_Aboriginal },
	103	{ "Cc", PT_PC, ucp_Cc },
	104	{ "Cf", PT_PC, ucp_Cf },
	105	{ "Cherokee", PT_SC, ucp_Cherokee },
	106	{ "Cn", PT_PC, ucp_Cn },
	107	{ "Co", PT_PC, ucp_Co },
	108	{ "Common", PT_SC, ucp_Common },
	109	{ "Coptic", PT_SC, ucp_Coptic },
	110	{ "Cs", PT_PC, ucp_Cs },
6bf342e1	111	{ "Cuneiform", PT_SC, ucp_Cuneiform },
aa41d2de PH	112	{ "Cypriot", PT_SC, ucp_Cypriot },
	113	{ "Cyrillic", PT_SC, ucp_Cyrillic },
	114	{ "Deseret", PT_SC, ucp_Deseret },
	115	{ "Devanagari", PT_SC, ucp_Devanagari },
	116	{ "Ethiopic", PT_SC, ucp_Ethiopic },
	117	{ "Georgian", PT_SC, ucp_Georgian },
	118	{ "Glagolitic", PT_SC, ucp_Glagolitic },
	119	{ "Gothic", PT_SC, ucp_Gothic },
	120	{ "Greek", PT_SC, ucp_Greek },
	121	{ "Gujarati", PT_SC, ucp_Gujarati },
	122	{ "Gurmukhi", PT_SC, ucp_Gurmukhi },
	123	{ "Han", PT_SC, ucp_Han },
	124	{ "Hangul", PT_SC, ucp_Hangul },
	125	{ "Hanunoo", PT_SC, ucp_Hanunoo },
	126	{ "Hebrew", PT_SC, ucp_Hebrew },
	127	{ "Hiragana", PT_SC, ucp_Hiragana },
	128	{ "Inherited", PT_SC, ucp_Inherited },
	129	{ "Kannada", PT_SC, ucp_Kannada },
	130	{ "Katakana", PT_SC, ucp_Katakana },
	131	{ "Kharoshthi", PT_SC, ucp_Kharoshthi },
	132	{ "Khmer", PT_SC, ucp_Khmer },
	133	{ "L", PT_GC, ucp_L },
	134	{ "L&", PT_LAMP, 0 },
	135	{ "Lao", PT_SC, ucp_Lao },
	136	{ "Latin", PT_SC, ucp_Latin },
	137	{ "Limbu", PT_SC, ucp_Limbu },
	138	{ "Linear_B", PT_SC, ucp_Linear_B },
	139	{ "Ll", PT_PC, ucp_Ll },
	140	{ "Lm", PT_PC, ucp_Lm },
	141	{ "Lo", PT_PC, ucp_Lo },
	142	{ "Lt", PT_PC, ucp_Lt },
	143	{ "Lu", PT_PC, ucp_Lu },
	144	{ "M", PT_GC, ucp_M },
	145	{ "Malayalam", PT_SC, ucp_Malayalam },
	146	{ "Mc", PT_PC, ucp_Mc },
	147	{ "Me", PT_PC, ucp_Me },
	148	{ "Mn", PT_PC, ucp_Mn },
	149	{ "Mongolian", PT_SC, ucp_Mongolian },
	150	{ "Myanmar", PT_SC, ucp_Myanmar },
	151	{ "N", PT_GC, ucp_N },
	152	{ "Nd", PT_PC, ucp_Nd },
	153	{ "New_Tai_Lue", PT_SC, ucp_New_Tai_Lue },
6bf342e1	154	{ "Nko", PT_SC, ucp_Nko },
aa41d2de PH	155	{ "Nl", PT_PC, ucp_Nl },
	156	{ "No", PT_PC, ucp_No },
	157	{ "Ogham", PT_SC, ucp_Ogham },
	158	{ "Old_Italic", PT_SC, ucp_Old_Italic },
	159	{ "Old_Persian", PT_SC, ucp_Old_Persian },
	160	{ "Oriya", PT_SC, ucp_Oriya },
	161	{ "Osmanya", PT_SC, ucp_Osmanya },
	162	{ "P", PT_GC, ucp_P },
	163	{ "Pc", PT_PC, ucp_Pc },
	164	{ "Pd", PT_PC, ucp_Pd },
	165	{ "Pe", PT_PC, ucp_Pe },
	166	{ "Pf", PT_PC, ucp_Pf },
6bf342e1 PH	167	{ "Phags_Pa", PT_SC, ucp_Phags_Pa },
6bf342e1 PH	168	{ "Phoenician", PT_SC, ucp_Phoenician },
aa41d2de PH	169	{ "Pi", PT_PC, ucp_Pi },
	170	{ "Po", PT_PC, ucp_Po },
	171	{ "Ps", PT_PC, ucp_Ps },
	172	{ "Runic", PT_SC, ucp_Runic },
	173	{ "S", PT_GC, ucp_S },
	174	{ "Sc", PT_PC, ucp_Sc },
	175	{ "Shavian", PT_SC, ucp_Shavian },
	176	{ "Sinhala", PT_SC, ucp_Sinhala },
	177	{ "Sk", PT_PC, ucp_Sk },
	178	{ "Sm", PT_PC, ucp_Sm },
	179	{ "So", PT_PC, ucp_So },
	180	{ "Syloti_Nagri", PT_SC, ucp_Syloti_Nagri },
	181	{ "Syriac", PT_SC, ucp_Syriac },
	182	{ "Tagalog", PT_SC, ucp_Tagalog },
	183	{ "Tagbanwa", PT_SC, ucp_Tagbanwa },
	184	{ "Tai_Le", PT_SC, ucp_Tai_Le },
	185	{ "Tamil", PT_SC, ucp_Tamil },
	186	{ "Telugu", PT_SC, ucp_Telugu },
	187	{ "Thaana", PT_SC, ucp_Thaana },
	188	{ "Thai", PT_SC, ucp_Thai },
	189	{ "Tibetan", PT_SC, ucp_Tibetan },
	190	{ "Tifinagh", PT_SC, ucp_Tifinagh },
	191	{ "Ugaritic", PT_SC, ucp_Ugaritic },
	192	{ "Yi", PT_SC, ucp_Yi },
	193	{ "Z", PT_GC, ucp_Z },
	194	{ "Zl", PT_PC, ucp_Zl },
	195	{ "Zp", PT_PC, ucp_Zp },
	196	{ "Zs", PT_PC, ucp_Zs }
8ac170f3 PH	197	};
	198
	199	const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table);
	200
64f2600a PH	201	#endif /* SUPPORT_UTF8 */
64f2600a PH	202
8ac170f3	203	/* End of pcre_tables.c */