code/trunk/pcre_newline.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) 1997-2007 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 internal functions for testing newlines when more than
one kind of newline is to be recognized. When a newline is found, its length is
returned. In principle, we could implement several newline "types", each
referring to a different set of newline characters. At present, PCRE supports
only NLTYPE_FIXED, which gets handled without these functions, and NLTYPE_ALL,
so for now the type isn't passed into the functions. It can easily be added
later if required. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */


#include "pcre_internal.h"


/*************************************************
*      Check for newline at given position       *
*************************************************/

/* It is guaranteed that the initial value of ptr is less than the end of the
string that is being processed.

Arguments:
  ptr          pointer to possible newline
  endptr       pointer to the end of the string
  lenptr       where to return the length
  utf8         TRUE if in utf8 mode

Returns:       TRUE or FALSE
*/

BOOL
_pcre_is_newline(const uschar *ptr, const uschar *endptr, int *lenptr,
  BOOL utf8)
{
int c;
if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
switch(c)
  {
  case 0x000a:                                       /* LF */
  case 0x000b:                                       /* VT */
  case 0x000c: *lenptr = 1; return TRUE;             /* FF */
  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
               return TRUE;                          /* CR */
  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;   /* NEL */
  case 0x2028:                                       /* LS */
  case 0x2029: *lenptr = 3; return TRUE;             /* PS */
  default: return FALSE;
  }
}


/*************************************************
*     Check for newline at previous position     *
*************************************************/

/* It is guaranteed that the initial value of ptr is greater than the start of
the string that is being processed.

Arguments:
  ptr          pointer to possible newline
  startptr     pointer to the start of the string
  lenptr       where to return the length
  utf8         TRUE if in utf8 mode

Returns:       TRUE or FALSE
*/

BOOL
_pcre_was_newline(const uschar *ptr, const uschar *startptr, int *lenptr,
  BOOL utf8)
{
int c;
ptr--;
if (utf8)
  {
  BACKCHAR(ptr);
  GETCHAR(c, ptr);
  }
else c = *ptr;
switch(c)
  {
  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
               return TRUE;                         /* LF */
  case 0x000b:                                      /* VT */
  case 0x000c:                                      /* FF */
  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
  case 0x0085: *lenptr = utf8? 2 : 1; return TRUE;  /* NEL */
  case 0x2028:                                      /* LS */
  case 0x2029: *lenptr = 3; return TRUE;            /* PS */
  default: return FALSE;
  }
}

/* End of pcre_newline.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) 1997-2007 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 internal functions for testing newlines when more than
42	one kind of newline is to be recognized. When a newline is found, its length is
43	returned. In principle, we could implement several newline "types", each
44	referring to a different set of newline characters. At present, PCRE supports
45	only NLTYPE_FIXED, which gets handled without these functions, and NLTYPE_ALL,
46	so for now the type isn't passed into the functions. It can easily be added
47	later if required. The full list of Unicode newline characters is taken from
48	http://unicode.org/unicode/reports/tr18/. */
49
50
51	#include "pcre_internal.h"
52
53
54
55	/*************************************************
56	* Check for newline at given position *
57	*************************************************/
58
59	/* It is guaranteed that the initial value of ptr is less than the end of the
60	string that is being processed.
61
62	Arguments:
63	ptr pointer to possible newline
64	endptr pointer to the end of the string
65	lenptr where to return the length
66	utf8 TRUE if in utf8 mode
67
68	Returns: TRUE or FALSE
69	*/
70
71	BOOL
72	_pcre_is_newline(const uschar ptr, const uschar endptr, int *lenptr,
73	BOOL utf8)
74	{
75	int c;
76	if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
77	switch(c)
78	{
79	case 0x000a: /* LF */
80	case 0x000b: /* VT */
81	case 0x000c: lenptr = 1; return TRUE; / FF */
82	case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
83	return TRUE; /* CR */
84	case 0x0085: lenptr = utf8? 2 : 1; return TRUE; / NEL */
85	case 0x2028: /* LS */
86	case 0x2029: lenptr = 3; return TRUE; / PS */
87	default: return FALSE;
88	}
89	}
90
91
92
93	/*************************************************
94	* Check for newline at previous position *
95	*************************************************/
96
97	/* It is guaranteed that the initial value of ptr is greater than the start of
98	the string that is being processed.
99
100	Arguments:
101	ptr pointer to possible newline
102	startptr pointer to the start of the string
103	lenptr where to return the length
104	utf8 TRUE if in utf8 mode
105
106	Returns: TRUE or FALSE
107	*/
108
109	BOOL
110	_pcre_was_newline(const uschar ptr, const uschar startptr, int *lenptr,
111	BOOL utf8)
112	{
113	int c;
114	ptr--;
115	if (utf8)
116	{
117	BACKCHAR(ptr);
118	GETCHAR(c, ptr);
119	}
120	else c = *ptr;
121	switch(c)
122	{
123	case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
124	return TRUE; /* LF */
125	case 0x000b: /* VT */
126	case 0x000c: /* FF */
127	case 0x000d: lenptr = 1; return TRUE; / CR */
128	case 0x0085: lenptr = utf8? 2 : 1; return TRUE; / NEL */
129	case 0x2028: /* LS */
130	case 0x2029: lenptr = 3; return TRUE; / PS */
131	default: return FALSE;
132	}
133	}
134
135	/* End of pcre_newline.c */
Name	Value
svn:eol-style	native
svn:keywords	"Author Date Id Revision Url"