/src/poco/dependencies/pcre2/src/pcre2_newline.c

Source
/*************************************************
*      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
     Original API code Copyright (c) 1997-2012 University of Cambridge
         New API code Copyright (c) 2016 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, PCRE2 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/. */


#include "pcre2_internal.h"



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

/* This function is called only via the IS_NEWLINE macro, which does so only
when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the code unit
pointed to by ptr is less than the end of the string.

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

Returns:       TRUE or FALSE
*/

BOOL
PRIV(is_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR endptr,
  uint32_t *lenptr, BOOL utf)
{
uint32_t c;

#ifdef SUPPORT_UNICODE
if (utf) { GETCHAR(c, ptr); } else c = *ptr;
#else
(void)utf;
c = *ptr;
#endif  /* SUPPORT_UNICODE */

if (type == NLTYPE_ANYCRLF) switch(c)
  {
  case CHAR_LF:
  *lenptr = 1;
  return TRUE;

  case CHAR_CR:
  *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
  return TRUE;

  default:
  return FALSE;
  }

/* NLTYPE_ANY */

else switch(c)
  {
#ifdef EBCDIC
  case CHAR_NEL:
#endif
  case CHAR_LF:
  case CHAR_VT:
  case CHAR_FF:
  *lenptr = 1;
  return TRUE;

  case CHAR_CR:
  *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
  return TRUE;

#ifndef EBCDIC
#if PCRE2_CODE_UNIT_WIDTH == 8
  case CHAR_NEL:
  *lenptr = utf? 2 : 1;
  return TRUE;

  case 0x2028:   /* LS */
  case 0x2029:   /* PS */
  *lenptr = 3;
  return TRUE;

#else  /* 16-bit or 32-bit code units */
  case CHAR_NEL:
  case 0x2028:   /* LS */
  case 0x2029:   /* PS */
  *lenptr = 1;
  return TRUE;
#endif
#endif /* Not EBCDIC */

  default:
  return FALSE;
  }
}



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

/* This function is called only via the WAS_NEWLINE macro, which does so only
when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
newline (NLTYPE_FIXED) is handled inline. 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
  utf          TRUE if in utf mode

Returns:       TRUE or FALSE
*/

BOOL
PRIV(was_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR startptr,
  uint32_t *lenptr, BOOL utf)
{
uint32_t c;
ptr--;

#ifdef SUPPORT_UNICODE
if (utf)
  {
  BACKCHAR(ptr);
  GETCHAR(c, ptr);
  }
else c = *ptr;
#else
(void)utf;
c = *ptr;
#endif  /* SUPPORT_UNICODE */

if (type == NLTYPE_ANYCRLF) switch(c)
  {
  case CHAR_LF:
  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
  return TRUE;

  case CHAR_CR:
  *lenptr = 1;
  return TRUE;

  default:
  return FALSE;
  }

/* NLTYPE_ANY */

else switch(c)
  {
  case CHAR_LF:
  *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
  return TRUE;

#ifdef EBCDIC
  case CHAR_NEL:
#endif
  case CHAR_VT:
  case CHAR_FF:
  case CHAR_CR:
  *lenptr = 1;
  return TRUE;

#ifndef EBCDIC
#if PCRE2_CODE_UNIT_WIDTH == 8
  case CHAR_NEL:
  *lenptr = utf? 2 : 1;
  return TRUE;

  case 0x2028:   /* LS */
  case 0x2029:   /* PS */
  *lenptr = 3;
  return TRUE;

#else /* 16-bit or 32-bit code units */
  case CHAR_NEL:
  case 0x2028:   /* LS */
  case 0x2029:   /* PS */
  *lenptr = 1;
  return TRUE;
#endif
#endif /* Not EBCDIC */

  default:
  return FALSE;
  }
}

/* End of pcre2_newline.c */

Coverage Report

Created: 2026-01-07 06:46

Line	Count	Source
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		Original API code Copyright (c) 1997-2012 University of Cambridge
10		New API code Copyright (c) 2016 University of Cambridge
11
12		-----------------------------------------------------------------------------
13		Redistribution and use in source and binary forms, with or without
14		modification, are permitted provided that the following conditions are met:
15
16		* Redistributions of source code must retain the above copyright notice,
17		this list of conditions and the following disclaimer.
18
19		* Redistributions in binary form must reproduce the above copyright
20		notice, this list of conditions and the following disclaimer in the
21		documentation and/or other materials provided with the distribution.
22
23		* Neither the name of the University of Cambridge nor the names of its
24		contributors may be used to endorse or promote products derived from
25		this software without specific prior written permission.
26
27		THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
28		AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
29		IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
30		ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
31		LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
32		CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
33		SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
34		INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
35		CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
36		ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
37		POSSIBILITY OF SUCH DAMAGE.
38		-----------------------------------------------------------------------------
39		*/
40
41
42		/* This module contains internal functions for testing newlines when more than
43		one kind of newline is to be recognized. When a newline is found, its length is
44		returned. In principle, we could implement several newline "types", each
45		referring to a different set of newline characters. At present, PCRE2 supports
46		only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF,
47		and NLTYPE_ANY. The full list of Unicode newline characters is taken from
48		http://unicode.org/unicode/reports/tr18/. */
49
50
51		#include "pcre2_internal.h"
52
53
54
55		/*************************************************
56		* Check for newline at given position *
57		*************************************************/
58
59		/* This function is called only via the IS_NEWLINE macro, which does so only
60		when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
61		newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the code unit
62		pointed to by ptr is less than the end of the string.
63
64		Arguments:
65		ptr pointer to possible newline
66		type the newline type
67		endptr pointer to the end of the string
68		lenptr where to return the length
69		utf TRUE if in utf mode
70
71		Returns: TRUE or FALSE
72		*/
73
74		BOOL
75		PRIV(is_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR endptr,
76		uint32_t *lenptr, BOOL utf)
77	0	{
78	0	uint32_t c;
79
80	0	#ifdef SUPPORT_UNICODE
81	0	if (utf) { GETCHAR(c, ptr); } else c = *ptr;
82		#else
83		(void)utf;
84		c = *ptr;
85		#endif /* SUPPORT_UNICODE */
86
87	0	if (type == NLTYPE_ANYCRLF) switch(c)
88	0	{
89	0	case CHAR_LF:
90	0	*lenptr = 1;
91	0	return TRUE;
92
93	0	case CHAR_CR:
94	0	*lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
95	0	return TRUE;
96
97	0	default:
98	0	return FALSE;
99	0	}
100
101		/* NLTYPE_ANY */
102
103	0	else switch(c)
104	0	{
105		#ifdef EBCDIC
106		case CHAR_NEL:
107		#endif
108	0	case CHAR_LF:
109	0	case CHAR_VT:
110	0	case CHAR_FF:
111	0	*lenptr = 1;
112	0	return TRUE;
113
114	0	case CHAR_CR:
115	0	*lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1;
116	0	return TRUE;
117
118	0	#ifndef EBCDIC
119	0	#if PCRE2_CODE_UNIT_WIDTH == 8
120	0	case CHAR_NEL:
121	0	*lenptr = utf? 2 : 1;
122	0	return TRUE;
123
124	0	case 0x2028: /* LS */
125	0	case 0x2029: /* PS */
126	0	*lenptr = 3;
127	0	return TRUE;
128
129		#else /* 16-bit or 32-bit code units */
130		case CHAR_NEL:
131		case 0x2028: /* LS */
132		case 0x2029: /* PS */
133		*lenptr = 1;
134		return TRUE;
135		#endif
136	0	#endif /* Not EBCDIC */
137
138	0	default:
139	0	return FALSE;
140	0	}
141	0	}
142
143
144
145		/*************************************************
146		* Check for newline at previous position *
147		*************************************************/
148
149		/* This function is called only via the WAS_NEWLINE macro, which does so only
150		when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed
151		newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the initial
152		value of ptr is greater than the start of the string that is being processed.
153
154		Arguments:
155		ptr pointer to possible newline
156		type the newline type
157		startptr pointer to the start of the string
158		lenptr where to return the length
159		utf TRUE if in utf mode
160
161		Returns: TRUE or FALSE
162		*/
163
164		BOOL
165		PRIV(was_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR startptr,
166		uint32_t *lenptr, BOOL utf)
167	0	{
168	0	uint32_t c;
169	0	ptr--;
170
171	0	#ifdef SUPPORT_UNICODE
172	0	if (utf)
173	0	{
174	0	BACKCHAR(ptr);
175	0	GETCHAR(c, ptr);
176	0	}
177	0	else c = *ptr;
178		#else
179		(void)utf;
180		c = *ptr;
181		#endif /* SUPPORT_UNICODE */
182
183	0	if (type == NLTYPE_ANYCRLF) switch(c)
184	0	{
185	0	case CHAR_LF:
186	0	*lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
187	0	return TRUE;
188
189	0	case CHAR_CR:
190	0	*lenptr = 1;
191	0	return TRUE;
192
193	0	default:
194	0	return FALSE;
195	0	}
196
197		/* NLTYPE_ANY */
198
199	0	else switch(c)
200	0	{
201	0	case CHAR_LF:
202	0	*lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1;
203	0	return TRUE;
204
205		#ifdef EBCDIC
206		case CHAR_NEL:
207		#endif
208	0	case CHAR_VT:
209	0	case CHAR_FF:
210	0	case CHAR_CR:
211	0	*lenptr = 1;
212	0	return TRUE;
213
214	0	#ifndef EBCDIC
215	0	#if PCRE2_CODE_UNIT_WIDTH == 8
216	0	case CHAR_NEL:
217	0	*lenptr = utf? 2 : 1;
218	0	return TRUE;
219
220	0	case 0x2028: /* LS */
221	0	case 0x2029: /* PS */
222	0	*lenptr = 3;
223	0	return TRUE;
224
225		#else /* 16-bit or 32-bit code units */
226		case CHAR_NEL:
227		case 0x2028: /* LS */
228		case 0x2029: /* PS */
229		*lenptr = 1;
230		return TRUE;
231		#endif
232	0	#endif /* Not EBCDIC */
233
234	0	default:
235	0	return FALSE;
236	0	}
237	0	}
238
239		/* End of pcre2_newline.c */