lib/pcre/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) 1997-2009 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 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, NLTYPE_ANYCRLF,
and NLTYPE_ANY. The full list of Unicode newline characters is taken from
http://unicode.org/unicode/reports/tr18/. */


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

#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
  type         the newline type
  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(USPTR ptr, int type, USPTR endptr, int *lenptr, BOOL utf8)
{
int c;
if (utf8) { GETCHAR(c, ptr); } else c = *ptr;

if (type == NLTYPE_ANYCRLF) switch(c)
  {
  case 0x000a: *lenptr = 1; return TRUE;             /* LF */
  case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
               return TRUE;                          /* CR */
  default: return FALSE;
  }

/* NLTYPE_ANY */

else 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
  type         the newline type
  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(USPTR ptr, int type, USPTR startptr, int *lenptr, BOOL utf8)
{
int c;
ptr--;
#ifdef SUPPORT_UTF8
if (utf8)
  {
  BACKCHAR(ptr);
  GETCHAR(c, ptr);
  }
else c = *ptr;
#else   /* no UTF-8 support */
c = *ptr;
#endif  /* SUPPORT_UTF8 */

if (type == NLTYPE_ANYCRLF) switch(c)
  {
  case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
               return TRUE;                         /* LF */
  case 0x000d: *lenptr = 1; return TRUE;            /* CR */
  default: return FALSE;
  }

else 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 */
Revision:	964
Committed:	Sat Aug 1 16:08:20 2009 UTC (14 years, 8 months ago) by michael
Content type:	text/x-csrc
File size:	5740 byte(s)
Log Message:	- add pcre_newline.c to lib/pcre/
#	Content
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 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, NLTYPE_ANYCRLF,
46	and NLTYPE_ANY. The full list of Unicode newline characters is taken from
47	http://unicode.org/unicode/reports/tr18/. */
48
49
50	#ifdef HAVE_CONFIG_H
51	#include "config.h"
52	#endif
53
54	#include "pcre_internal.h"
55
56
57
58	/*************************************************
59	* Check for newline at given position *
60	*************************************************/
61
62	/* It is guaranteed that the initial value of ptr is less than the end of the
63	string that is being processed.
64
65	Arguments:
66	ptr pointer to possible newline
67	type the newline type
68	endptr pointer to the end of the string
69	lenptr where to return the length
70	utf8 TRUE if in utf8 mode
71
72	Returns: TRUE or FALSE
73	*/
74
75	BOOL
76	_pcre_is_newline(USPTR ptr, int type, USPTR endptr, int *lenptr, BOOL utf8)
77	{
78	int c;
79	if (utf8) { GETCHAR(c, ptr); } else c = *ptr;
80
81	if (type == NLTYPE_ANYCRLF) switch(c)
82	{
83	case 0x000a: lenptr = 1; return TRUE; / LF */
84	case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
85	return TRUE; /* CR */
86	default: return FALSE;
87	}
88
89	/* NLTYPE_ANY */
90
91	else switch(c)
92	{
93	case 0x000a: /* LF */
94	case 0x000b: /* VT */
95	case 0x000c: lenptr = 1; return TRUE; / FF */
96	case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1;
97	return TRUE; /* CR */
98	case 0x0085: lenptr = utf8? 2 : 1; return TRUE; / NEL */
99	case 0x2028: /* LS */
100	case 0x2029: lenptr = 3; return TRUE; / PS */
101	default: return FALSE;
102	}
103	}
104
105
106
107	/*************************************************
108	* Check for newline at previous position *
109	*************************************************/
110
111	/* It is guaranteed that the initial value of ptr is greater than the start of
112	the string that is being processed.
113
114	Arguments:
115	ptr pointer to possible newline
116	type the newline type
117	startptr pointer to the start of the string
118	lenptr where to return the length
119	utf8 TRUE if in utf8 mode
120
121	Returns: TRUE or FALSE
122	*/
123
124	BOOL
125	_pcre_was_newline(USPTR ptr, int type, USPTR startptr, int *lenptr, BOOL utf8)
126	{
127	int c;
128	ptr--;
129	#ifdef SUPPORT_UTF8
130	if (utf8)
131	{
132	BACKCHAR(ptr);
133	GETCHAR(c, ptr);
134	}
135	else c = *ptr;
136	#else /* no UTF-8 support */
137	c = *ptr;
138	#endif /* SUPPORT_UTF8 */
139
140	if (type == NLTYPE_ANYCRLF) switch(c)
141	{
142	case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
143	return TRUE; /* LF */
144	case 0x000d: lenptr = 1; return TRUE; / CR */
145	default: return FALSE;
146	}
147
148	else switch(c)
149	{
150	case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1;
151	return TRUE; /* LF */
152	case 0x000b: /* VT */
153	case 0x000c: /* FF */
154	case 0x000d: lenptr = 1; return TRUE; / CR */
155	case 0x0085: lenptr = utf8? 2 : 1; return TRUE; / NEL */
156	case 0x2028: /* LS */
157	case 0x2029: lenptr = 3; return TRUE; / PS */
158	default: return FALSE;
159	}
160	}
161
162	/* End of pcre_newline.c */