branches/pcre16/pcre16_valid_utf16.c

/*************************************************
*      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) 1997-2009 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 an internal function for validating UTF-16 character
strings. */


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

/* Generate code with 16 bit character support. */
#define COMPILE_PCRE16

#include "pcre_internal.h"


/*************************************************
*         Validate a UTF-16 string                *
*************************************************/

/* This function is called (optionally) at the start of compile or match, to
check that a supposed UTF-16 string is actually valid. The early check means
that subsequent code can assume it is dealing with a valid string. The check
can be turned off for maximum performance, but the consequences of supplying an
invalid string are then undefined.

From release 8.21 more information about the details of the error are passed
back in the returned value:

PCRE_UTF16_ERR0  No error
PCRE_UTF16_ERR1  Missing low surrogate at the end of the string
PCRE_UTF16_ERR2  Invalid low surrogate
PCRE_UTF16_ERR3  Isolated low surrogate
PCRE_UTF16_ERR4  Not allowed character

Arguments:
  string       points to the string
  length       length of string, or -1 if the string is zero-terminated
  errp         pointer to an error position offset variable

Returns:       = 0    if the string is a valid UTF-16 string
               > 0    otherwise, setting the offset of the bad character
*/

int
PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset)
{
#ifdef SUPPORT_UTF
register PCRE_PUCHAR p;
register pcre_uchar c;

if (length < 0)
  {
  for (p = string; *p != 0; p++);
  length = p - string;
  }

for (p = string; length-- > 0; p++)
  {
  c = *p;

  if ((c & 0xf800) != 0xd800)
    {
    /* Normal UTF-16 code point. Neither high nor low surrogate. */

    /* This is probably a BOM from a different byte-order.
    Regardless, the string is rejected. */
    if (c == 0xfffe)
      {
      *erroroffset = p - string;
      return PCRE_UTF16_ERR4;
      }
    }
  else if ((c & 0x0400) == 0)
    {
    /* High surrogate. */

    /* Must be a followed by a low surrogate. */
    if (length == 0)
      {
      *erroroffset = p - string;
      return PCRE_UTF16_ERR1;
      }
    p++;
    length--;
    if ((*p & 0xfc00) != 0xdc00)
      {
      *erroroffset = p - string;
      return PCRE_UTF16_ERR2;
      }
    }
  else
    {
    /* Isolated low surrogate. Always an error. */
    *erroroffset = p - string;
    return PCRE_UTF16_ERR3;
    }
  }

#else  /* SUPPORT_UTF */
(void)(string);  /* Keep picky compilers happy */
(void)(length);
#endif /* SUPPORT_UTF */

return PCRE_UTF16_ERR0;   /* This indicates success */
}

/* End of pcre16_valid_utf16.c */
1	/*************************************************
2	* Perl-Compatible Regular Expressions *
3	*************************************************/
4
5	/* PCRE is a library of functions to support regular expressions whose syntax
6	and semantics are as close as possible to those of the Perl 5 language.
7
8	Written by Philip Hazel
9	Copyright (c) 1997-2009 University of Cambridge
10
11	-----------------------------------------------------------------------------
12	Redistribution and use in source and binary forms, with or without
13	modification, are permitted provided that the following conditions are met:
14
15	* Redistributions of source code must retain the above copyright notice,
16	this list of conditions and the following disclaimer.
17
18	* Redistributions in binary form must reproduce the above copyright
19	notice, this list of conditions and the following disclaimer in the
20	documentation and/or other materials provided with the distribution.
21
22	* Neither the name of the University of Cambridge nor the names of its
23	contributors may be used to endorse or promote products derived from
24	this software without specific prior written permission.
25
26	THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
27	AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
28	IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
29	ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
30	LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
31	CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
32	SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
33	INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
34	CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
35	ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
36	POSSIBILITY OF SUCH DAMAGE.
37	-----------------------------------------------------------------------------
38	*/
39
40
41	/* This module contains an internal function for validating UTF-16 character
42	strings. */
43
44
45	#ifdef HAVE_CONFIG_H
46	#include "config.h"
47	#endif
48
49	/* Generate code with 16 bit character support. */
50	#define COMPILE_PCRE16
51
52	#include "pcre_internal.h"
53
54
55	/*************************************************
56	* Validate a UTF-16 string *
57	*************************************************/
58
59	/* This function is called (optionally) at the start of compile or match, to
60	check that a supposed UTF-16 string is actually valid. The early check means
61	that subsequent code can assume it is dealing with a valid string. The check
62	can be turned off for maximum performance, but the consequences of supplying an
63	invalid string are then undefined.
64
65	From release 8.21 more information about the details of the error are passed
66	back in the returned value:
67
68	PCRE_UTF16_ERR0 No error
69	PCRE_UTF16_ERR1 Missing low surrogate at the end of the string
70	PCRE_UTF16_ERR2 Invalid low surrogate
71	PCRE_UTF16_ERR3 Isolated low surrogate
72	PCRE_UTF16_ERR4 Not allowed character
73
74	Arguments:
75	string points to the string
76	length length of string, or -1 if the string is zero-terminated
77	errp pointer to an error position offset variable
78
79	Returns: = 0 if the string is a valid UTF-16 string
80	> 0 otherwise, setting the offset of the bad character
81	*/
82
83	int
84	PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *erroroffset)
85	{
86	#ifdef SUPPORT_UTF
87	register PCRE_PUCHAR p;
88	register pcre_uchar c;
89
90	if (length < 0)
91	{
92	for (p = string; *p != 0; p++);
93	length = p - string;
94	}
95
96	for (p = string; length-- > 0; p++)
97	{
98	c = *p;
99
100	if ((c & 0xf800) != 0xd800)
101	{
102	/* Normal UTF-16 code point. Neither high nor low surrogate. */
103
104	/* This is probably a BOM from a different byte-order.
105	Regardless, the string is rejected. */
106	if (c == 0xfffe)
107	{
108	*erroroffset = p - string;
109	return PCRE_UTF16_ERR4;
110	}
111	}
112	else if ((c & 0x0400) == 0)
113	{
114	/* High surrogate. */
115
116	/* Must be a followed by a low surrogate. */
117	if (length == 0)
118	{
119	*erroroffset = p - string;
120	return PCRE_UTF16_ERR1;
121	}
122	p++;
123	length--;
124	if ((*p & 0xfc00) != 0xdc00)
125	{
126	*erroroffset = p - string;
127	return PCRE_UTF16_ERR2;
128	}
129	}
130	else
131	{
132	/* Isolated low surrogate. Always an error. */
133	*erroroffset = p - string;
134	return PCRE_UTF16_ERR3;
135	}
136	}
137
138	#else /* SUPPORT_UTF */
139	(void)(string); /* Keep picky compilers happy */
140	(void)(length);
141	#endif /* SUPPORT_UTF */
142
143	return PCRE_UTF16_ERR0; /* This indicates success */
144	}
145
146	/* End of pcre16_valid_utf16.c */