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 | #ifdef HAVE_CONFIG_H |
52 | #include "config.h" |
53 | #endif |
54 | |
55 | #include "pcre2_internal.h" |
56 | |
57 | |
58 | |
59 | /************************************************* |
60 | * Check for newline at given position * |
61 | *************************************************/ |
62 | |
63 | /* This function is called only via the IS_NEWLINE macro, which does so only |
64 | when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed |
65 | newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the code unit |
66 | pointed to by ptr is less than the end of the string. |
67 | |
68 | Arguments: |
69 | ptr pointer to possible newline |
70 | type the newline type |
71 | endptr pointer to the end of the string |
72 | lenptr where to return the length |
73 | utf TRUE if in utf mode |
74 | |
75 | Returns: TRUE or FALSE |
76 | */ |
77 | |
78 | BOOL |
79 | PRIV(is_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR endptr, |
80 | uint32_t *lenptr, BOOL utf) |
81 | { |
82 | uint32_t c; |
83 | |
84 | #ifdef SUPPORT_UNICODE |
85 | if (utf) { GETCHAR(c, ptr); } else c = *ptr; |
86 | #else |
87 | (void)utf; |
88 | c = *ptr; |
89 | #endif /* SUPPORT_UNICODE */ |
90 | |
91 | if (type == NLTYPE_ANYCRLF) switch(c) |
92 | { |
93 | case CHAR_LF: |
94 | *lenptr = 1; |
95 | return TRUE; |
96 | |
97 | case CHAR_CR: |
98 | *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; |
99 | return TRUE; |
100 | |
101 | default: |
102 | return FALSE; |
103 | } |
104 | |
105 | /* NLTYPE_ANY */ |
106 | |
107 | else switch(c) |
108 | { |
109 | #ifdef EBCDIC |
110 | case CHAR_NEL: |
111 | #endif |
112 | case CHAR_LF: |
113 | case CHAR_VT: |
114 | case CHAR_FF: |
115 | *lenptr = 1; |
116 | return TRUE; |
117 | |
118 | case CHAR_CR: |
119 | *lenptr = (ptr < endptr - 1 && ptr[1] == CHAR_LF)? 2 : 1; |
120 | return TRUE; |
121 | |
122 | #ifndef EBCDIC |
123 | #if PCRE2_CODE_UNIT_WIDTH == 8 |
124 | case CHAR_NEL: |
125 | *lenptr = utf? 2 : 1; |
126 | return TRUE; |
127 | |
128 | case 0x2028: /* LS */ |
129 | case 0x2029: /* PS */ |
130 | *lenptr = 3; |
131 | return TRUE; |
132 | |
133 | #else /* 16-bit or 32-bit code units */ |
134 | case CHAR_NEL: |
135 | case 0x2028: /* LS */ |
136 | case 0x2029: /* PS */ |
137 | *lenptr = 1; |
138 | return TRUE; |
139 | #endif |
140 | #endif /* Not EBCDIC */ |
141 | |
142 | default: |
143 | return FALSE; |
144 | } |
145 | } |
146 | |
147 | |
148 | |
149 | /************************************************* |
150 | * Check for newline at previous position * |
151 | *************************************************/ |
152 | |
153 | /* This function is called only via the WAS_NEWLINE macro, which does so only |
154 | when the newline type is NLTYPE_ANY or NLTYPE_ANYCRLF. The case of a fixed |
155 | newline (NLTYPE_FIXED) is handled inline. It is guaranteed that the initial |
156 | value of ptr is greater than the start of the string that is being processed. |
157 | |
158 | Arguments: |
159 | ptr pointer to possible newline |
160 | type the newline type |
161 | startptr pointer to the start of the string |
162 | lenptr where to return the length |
163 | utf TRUE if in utf mode |
164 | |
165 | Returns: TRUE or FALSE |
166 | */ |
167 | |
168 | BOOL |
169 | PRIV(was_newline)(PCRE2_SPTR ptr, uint32_t type, PCRE2_SPTR startptr, |
170 | uint32_t *lenptr, BOOL utf) |
171 | { |
172 | uint32_t c; |
173 | ptr--; |
174 | |
175 | #ifdef SUPPORT_UNICODE |
176 | if (utf) |
177 | { |
178 | BACKCHAR(ptr); |
179 | GETCHAR(c, ptr); |
180 | } |
181 | else c = *ptr; |
182 | #else |
183 | (void)utf; |
184 | c = *ptr; |
185 | #endif /* SUPPORT_UNICODE */ |
186 | |
187 | if (type == NLTYPE_ANYCRLF) switch(c) |
188 | { |
189 | case CHAR_LF: |
190 | *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; |
191 | return TRUE; |
192 | |
193 | case CHAR_CR: |
194 | *lenptr = 1; |
195 | return TRUE; |
196 | |
197 | default: |
198 | return FALSE; |
199 | } |
200 | |
201 | /* NLTYPE_ANY */ |
202 | |
203 | else switch(c) |
204 | { |
205 | case CHAR_LF: |
206 | *lenptr = (ptr > startptr && ptr[-1] == CHAR_CR)? 2 : 1; |
207 | return TRUE; |
208 | |
209 | #ifdef EBCDIC |
210 | case CHAR_NEL: |
211 | #endif |
212 | case CHAR_VT: |
213 | case CHAR_FF: |
214 | case CHAR_CR: |
215 | *lenptr = 1; |
216 | return TRUE; |
217 | |
218 | #ifndef EBCDIC |
219 | #if PCRE2_CODE_UNIT_WIDTH == 8 |
220 | case CHAR_NEL: |
221 | *lenptr = utf? 2 : 1; |
222 | return TRUE; |
223 | |
224 | case 0x2028: /* LS */ |
225 | case 0x2029: /* PS */ |
226 | *lenptr = 3; |
227 | return TRUE; |
228 | |
229 | #else /* 16-bit or 32-bit code units */ |
230 | case CHAR_NEL: |
231 | case 0x2028: /* LS */ |
232 | case 0x2029: /* PS */ |
233 | *lenptr = 1; |
234 | return TRUE; |
235 | #endif |
236 | #endif /* Not EBCDIC */ |
237 | |
238 | default: |
239 | return FALSE; |
240 | } |
241 | } |
242 | |
243 | /* End of pcre2_newline.c */ |
244 | |