code/trunk/pcre_ucp_searchfuncs.c

############################################################
############################################################
## As of PCRE 8.0 this file is OBSOLETE. A different way  ##
## of handling Unicode property data is now used. See the ##
## maint/README document.                                 ##
## PH 02 July 2008                                        ##
############################################################
############################################################

/*************************************************
*      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) 1997-2008 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 code for searching the table of Unicode character
properties. */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include "pcre_internal.h"

#include "ucp.h"               /* Category definitions */
#include "ucpinternal.h"       /* Internal table details */
#include "ucptable.h"          /* The table itself */


/* Table to translate from particular type value to the general value. */

static const int 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 */
};


/*************************************************
*         Search table and return type           *
*************************************************/

/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed
character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc.

Arguments:
  c           the character value
  type_ptr    the detailed character type is returned here
  script_ptr  the script is returned here

Returns:      the character type category
*/

int
_pcre_ucp_findprop(const unsigned int c, int *type_ptr, int *script_ptr)
{
int bot = 0;
int top = sizeof(ucp_table)/sizeof(cnode);
int mid;

/* The table is searched using a binary chop. You might think that using
intermediate variables to hold some of the common expressions would speed
things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
makes things a lot slower. */

for (;;)
  {
  if (top <= bot)
    {
    *type_ptr = ucp_Cn;
    *script_ptr = ucp_Common;
    return ucp_C;
    }
  mid = (bot + top) >> 1;
  if (c == (ucp_table[mid].f0 & f0_charmask)) break;
  if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
  else
    {
    if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
        c <= (ucp_table[mid].f0 & f0_charmask) +
             (ucp_table[mid].f1 & f1_rangemask)) break;
    bot = mid + 1;
    }
  }

/* Found an entry in the table. Set the script and detailed type values, and
return the general type. */

*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift;
*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift;

return ucp_gentype[*type_ptr];
}


/*************************************************
*       Search table and return other case       *
*************************************************/

/* If the given character is a letter, and there is another case for the
letter, return the other case. Otherwise, return -1.

Arguments:
  c           the character value

Returns:      the other case or NOTACHAR if none
*/

unsigned int
_pcre_ucp_othercase(const unsigned int c)
{
int bot = 0;
int top = sizeof(ucp_table)/sizeof(cnode);
int mid, offset;

/* The table is searched using a binary chop. You might think that using
intermediate variables to hold some of the common expressions would speed
things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
makes things a lot slower. */

for (;;)
  {
  if (top <= bot) return (unsigned int)(-1);
  mid = (bot + top) >> 1;
  if (c == (ucp_table[mid].f0 & f0_charmask)) break;
  if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
  else
    {
    if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
        c <= (ucp_table[mid].f0 & f0_charmask) +
             (ucp_table[mid].f1 & f1_rangemask)) break;
    bot = mid + 1;
    }
  }

/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise
return the other case if there is one, else NOTACHAR. */

if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR;

offset = ucp_table[mid].f1 & f1_casemask;
if ((offset & f1_caseneg) != 0) offset |= f1_caseneg;
return (offset == 0)? NOTACHAR : c + offset;
}


/* End of pcre_ucp_searchfuncs.c */
1	############################################################
2	############################################################
3	## As of PCRE 8.0 this file is OBSOLETE. A different way ##
4	## of handling Unicode property data is now used. See the ##
5	## maint/README document. ##
6	## PH 02 July 2008 ##
7	############################################################
8	############################################################
9
10	/*************************************************
11	* Perl-Compatible Regular Expressions *
12	*************************************************/
13
14	/* PCRE is a library of functions to support regular expressions whose syntax
15	and semantics are as close as possible to those of the Perl 5 language.
16
17	Written by Philip Hazel
18	Copyright (c) 1997-2008 University of Cambridge
19
20	-----------------------------------------------------------------------------
21	Redistribution and use in source and binary forms, with or without
22	modification, are permitted provided that the following conditions are met:
23
24	* Redistributions of source code must retain the above copyright notice,
25	this list of conditions and the following disclaimer.
26
27	* Redistributions in binary form must reproduce the above copyright
28	notice, this list of conditions and the following disclaimer in the
29	documentation and/or other materials provided with the distribution.
30
31	* Neither the name of the University of Cambridge nor the names of its
32	contributors may be used to endorse or promote products derived from
33	this software without specific prior written permission.
34
35	THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
36	AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
37	IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
38	ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
39	LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
40	CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
41	SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
42	INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
43	CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
44	ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
45	POSSIBILITY OF SUCH DAMAGE.
46	-----------------------------------------------------------------------------
47	*/
48
49
50	/* This module contains code for searching the table of Unicode character
51	properties. */
52
53	#ifdef HAVE_CONFIG_H
54	#include "config.h"
55	#endif
56
57	#include "pcre_internal.h"
58
59	#include "ucp.h" /* Category definitions */
60	#include "ucpinternal.h" /* Internal table details */
61	#include "ucptable.h" /* The table itself */
62
63
64	/* Table to translate from particular type value to the general value. */
65
66	static const int ucp_gentype[] = {
67	ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */
68	ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */
69	ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */
70	ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */
71	ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */
72	ucp_P, ucp_P, /* Ps, Po */
73	ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */
74	ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */
75	};
76
77
78
79	/*************************************************
80	* Search table and return type *
81	*************************************************/
82
83	/* Three values are returned: the category is ucp_C, ucp_L, etc. The detailed
84	character type is ucp_Lu, ucp_Nd, etc. The script is ucp_Latin, etc.
85
86	Arguments:
87	c the character value
88	type_ptr the detailed character type is returned here
89	script_ptr the script is returned here
90
91	Returns: the character type category
92	*/
93
94	int
95	_pcre_ucp_findprop(const unsigned int c, int type_ptr, int script_ptr)
96	{
97	int bot = 0;
98	int top = sizeof(ucp_table)/sizeof(cnode);
99	int mid;
100
101	/* The table is searched using a binary chop. You might think that using
102	intermediate variables to hold some of the common expressions would speed
103	things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
104	makes things a lot slower. */
105
106	for (;;)
107	{
108	if (top <= bot)
109	{
110	*type_ptr = ucp_Cn;
111	*script_ptr = ucp_Common;
112	return ucp_C;
113	}
114	mid = (bot + top) >> 1;
115	if (c == (ucp_table[mid].f0 & f0_charmask)) break;
116	if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
117	else
118	{
119	if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
120	c <= (ucp_table[mid].f0 & f0_charmask) +
121	(ucp_table[mid].f1 & f1_rangemask)) break;
122	bot = mid + 1;
123	}
124	}
125
126	/* Found an entry in the table. Set the script and detailed type values, and
127	return the general type. */
128
129	*script_ptr = (ucp_table[mid].f0 & f0_scriptmask) >> f0_scriptshift;
130	*type_ptr = (ucp_table[mid].f1 & f1_typemask) >> f1_typeshift;
131
132	return ucp_gentype[*type_ptr];
133	}
134
135
136
137	/*************************************************
138	* Search table and return other case *
139	*************************************************/
140
141	/* If the given character is a letter, and there is another case for the
142	letter, return the other case. Otherwise, return -1.
143
144	Arguments:
145	c the character value
146
147	Returns: the other case or NOTACHAR if none
148	*/
149
150	unsigned int
151	_pcre_ucp_othercase(const unsigned int c)
152	{
153	int bot = 0;
154	int top = sizeof(ucp_table)/sizeof(cnode);
155	int mid, offset;
156
157	/* The table is searched using a binary chop. You might think that using
158	intermediate variables to hold some of the common expressions would speed
159	things up, but tests with gcc 3.4.4 on Linux showed that, on the contrary, it
160	makes things a lot slower. */
161
162	for (;;)
163	{
164	if (top <= bot) return (unsigned int)(-1);
165	mid = (bot + top) >> 1;
166	if (c == (ucp_table[mid].f0 & f0_charmask)) break;
167	if (c < (ucp_table[mid].f0 & f0_charmask)) top = mid;
168	else
169	{
170	if ((ucp_table[mid].f0 & f0_rangeflag) != 0 &&
171	c <= (ucp_table[mid].f0 & f0_charmask) +
172	(ucp_table[mid].f1 & f1_rangemask)) break;
173	bot = mid + 1;
174	}
175	}
176
177	/* Found an entry in the table. Return NOTACHAR for a range entry. Otherwise
178	return the other case if there is one, else NOTACHAR. */
179
180	if ((ucp_table[mid].f0 & f0_rangeflag) != 0) return NOTACHAR;
181
182	offset = ucp_table[mid].f1 & f1_casemask;
183	if ((offset & f1_caseneg) != 0) offset \|= f1_caseneg;
184	return (offset == 0)? NOTACHAR : c + offset;
185	}
186
187
188	/* End of pcre_ucp_searchfuncs.c */
Name	Value
svn:eol-style	native
svn:keywords	"Author Date Id Revision Url"