1PCRE(3) Library Functions Manual PCRE(3)
2
3
4
6 PCRE - Perl-compatible regular expressions
7
8 #include <pcre.h>
9
11
12 pcre32 *pcre32_compile(PCRE_SPTR32 pattern, int options,
13 const char **errptr, int *erroffset,
14 const unsigned char *tableptr);
15
16 pcre32 *pcre32_compile2(PCRE_SPTR32 pattern, int options,
17 int *errorcodeptr,
18 const unsigned char *tableptr);
19
20 pcre32_extra *pcre32_study(const pcre32 *code, int options,
21 const char **errptr);
22
23 void pcre32_free_study(pcre32_extra *extra);
24
25 int pcre32_exec(const pcre32 *code, const pcre32_extra *extra,
26 PCRE_SPTR32 subject, int length, int startoffset,
27 int options, int *ovector, int ovecsize);
28
29 int pcre32_dfa_exec(const pcre32 *code, const pcre32_extra *extra,
30 PCRE_SPTR32 subject, int length, int startoffset,
31 int options, int *ovector, int ovecsize,
32 int *workspace, int wscount);
33
35
36 int pcre32_copy_named_substring(const pcre32 *code,
37 PCRE_SPTR32 subject, int *ovector,
38 int stringcount, PCRE_SPTR32 stringname,
39 PCRE_UCHAR32 *buffer, int buffersize);
40
41 int pcre32_copy_substring(PCRE_SPTR32 subject, int *ovector,
42 int stringcount, int stringnumber, PCRE_UCHAR32 *buffer,
43 int buffersize);
44
45 int pcre32_get_named_substring(const pcre32 *code,
46 PCRE_SPTR32 subject, int *ovector,
47 int stringcount, PCRE_SPTR32 stringname,
48 PCRE_SPTR32 *stringptr);
49
50 int pcre32_get_stringnumber(const pcre32 *code,
51 PCRE_SPTR32 name);
52
53 int pcre32_get_stringtable_entries(const pcre32 *code,
54 PCRE_SPTR32 name, PCRE_UCHAR32 **first, PCRE_UCHAR32 **last);
55
56 int pcre32_get_substring(PCRE_SPTR32 subject, int *ovector,
57 int stringcount, int stringnumber,
58 PCRE_SPTR32 *stringptr);
59
60 int pcre32_get_substring_list(PCRE_SPTR32 subject,
61 int *ovector, int stringcount, PCRE_SPTR32 **listptr);
62
63 void pcre32_free_substring(PCRE_SPTR32 stringptr);
64
65 void pcre32_free_substring_list(PCRE_SPTR32 *stringptr);
66
68
69 pcre32_jit_stack *pcre32_jit_stack_alloc(int startsize, int maxsize);
70
71 void pcre32_jit_stack_free(pcre32_jit_stack *stack);
72
73 void pcre32_assign_jit_stack(pcre32_extra *extra,
74 pcre32_jit_callback callback, void *data);
75
76 const unsigned char *pcre32_maketables(void);
77
78 int pcre32_fullinfo(const pcre32 *code, const pcre32_extra *extra,
79 int what, void *where);
80
81 int pcre32_refcount(pcre32 *code, int adjust);
82
83 int pcre32_config(int what, void *where);
84
85 const char *pcre32_version(void);
86
87 int pcre32_pattern_to_host_byte_order(pcre32 *code,
88 pcre32_extra *extra, const unsigned char *tables);
89
91
92 void *(*pcre32_malloc)(size_t);
93
94 void (*pcre32_free)(void *);
95
96 void *(*pcre32_stack_malloc)(size_t);
97
98 void (*pcre32_stack_free)(void *);
99
100 int (*pcre32_callout)(pcre32_callout_block *);
101
103
104 int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *output,
105 PCRE_SPTR32 input, int length, int *byte_order,
106 int keep_boms);
107
109
110 Starting with release 8.32, it is possible to compile a PCRE library
111 that supports 32-bit character strings, including UTF-32 strings, as
112 well as or instead of the original 8-bit library. This work was done by
113 Christian Persch, based on the work done by Zoltan Herczeg for the
114 16-bit library. All three libraries contain identical sets of func‐
115 tions, used in exactly the same way. Only the names of the functions
116 and the data types of their arguments and results are different. To
117 avoid over-complication and reduce the documentation maintenance load,
118 most of the PCRE documentation describes the 8-bit library, with only
119 occasional references to the 16-bit and 32-bit libraries. This page
120 describes what is different when you use the 32-bit library.
121
122 WARNING: A single application can be linked with all or any of the
123 three libraries, but you must take care when processing any particular
124 pattern to use functions from just one library. For example, if you
125 want to study a pattern that was compiled with pcre32_compile(), you
126 must do so with pcre32_study(), not pcre_study(), and you must free the
127 study data with pcre32_free_study().
128
130
131 There is only one header file, pcre.h. It contains prototypes for all
132 the functions in all libraries, as well as definitions of flags, struc‐
133 tures, error codes, etc.
134
136
137 In Unix-like systems, the 32-bit library is called libpcre32, and can
138 normally be accesss by adding -lpcre32 to the command for linking an
139 application that uses PCRE.
140
142
143 In the 8-bit library, strings are passed to PCRE library functions as
144 vectors of bytes with the C type "char *". In the 32-bit library,
145 strings are passed as vectors of unsigned 32-bit quantities. The macro
146 PCRE_UCHAR32 specifies an appropriate data type, and PCRE_SPTR32 is
147 defined as "const PCRE_UCHAR32 *". In very many environments, "unsigned
148 int" is a 32-bit data type. When PCRE is built, it defines PCRE_UCHAR32
149 as "unsigned int", but checks that it really is a 32-bit data type. If
150 it is not, the build fails with an error message telling the maintainer
151 to modify the definition appropriately.
152
154
155 The types of the opaque structures that are used for compiled 32-bit
156 patterns and JIT stacks are pcre32 and pcre32_jit_stack respectively.
157 The type of the user-accessible structure that is returned by
158 pcre32_study() is pcre32_extra, and the type of the structure that is
159 used for passing data to a callout function is pcre32_callout_block.
160 These structures contain the same fields, with the same names, as their
161 8-bit counterparts. The only difference is that pointers to character
162 strings are 32-bit instead of 8-bit types.
163
165
166 For every function in the 8-bit library there is a corresponding func‐
167 tion in the 32-bit library with a name that starts with pcre32_ instead
168 of pcre_. The prototypes are listed above. In addition, there is one
169 extra function, pcre32_utf32_to_host_byte_order(). This is a utility
170 function that converts a UTF-32 character string to host byte order if
171 necessary. The other 32-bit functions expect the strings they are
172 passed to be in host byte order.
173
174 The input and output arguments of pcre32_utf32_to_host_byte_order() may
175 point to the same address, that is, conversion in place is supported.
176 The output buffer must be at least as long as the input.
177
178 The length argument specifies the number of 32-bit data units in the
179 input string; a negative value specifies a zero-terminated string.
180
181 If byte_order is NULL, it is assumed that the string starts off in host
182 byte order. This may be changed by byte-order marks (BOMs) anywhere in
183 the string (commonly as the first character).
184
185 If byte_order is not NULL, a non-zero value of the integer to which it
186 points means that the input starts off in host byte order, otherwise
187 the opposite order is assumed. Again, BOMs in the string can change
188 this. The final byte order is passed back at the end of processing.
189
190 If keep_boms is not zero, byte-order mark characters (0xfeff) are
191 copied into the output string. Otherwise they are discarded.
192
193 The result of the function is the number of 32-bit units placed into
194 the output buffer, including the zero terminator if the string was
195 zero-terminated.
196
198
199 The lengths and starting offsets of subject strings must be specified
200 in 32-bit data units, and the offsets within subject strings that are
201 returned by the matching functions are in also 32-bit units rather than
202 bytes.
203
205
206 The name-to-number translation table that is maintained for named sub‐
207 patterns uses 32-bit characters. The pcre32_get_stringtable_entries()
208 function returns the length of each entry in the table as the number of
209 32-bit data units.
210
212
213 There are two new general option names, PCRE_UTF32 and
214 PCRE_NO_UTF32_CHECK, which correspond to PCRE_UTF8 and
215 PCRE_NO_UTF8_CHECK in the 8-bit library. In fact, these new options
216 define the same bits in the options word. There is a discussion about
217 the validity of UTF-32 strings in the pcreunicode page.
218
219 For the pcre32_config() function there is an option PCRE_CONFIG_UTF32
220 that returns 1 if UTF-32 support is configured, otherwise 0. If this
221 option is given to pcre_config() or pcre16_config(), or if the
222 PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to pcre32_con‐
223 fig(), the result is the PCRE_ERROR_BADOPTION error.
224
226
227 In 32-bit mode, when PCRE_UTF32 is not set, character values are
228 treated in the same way as in 8-bit, non UTF-8 mode, except, of course,
229 that they can range from 0 to 0x7fffffff instead of 0 to 0xff. Charac‐
230 ter types for characters less than 0xff can therefore be influenced by
231 the locale in the same way as before. Characters greater than 0xff
232 have only one case, and no "type" (such as letter or digit).
233
234 In UTF-32 mode, the character code is Unicode, in the range 0 to
235 0x10ffff, with the exception of values in the range 0xd800 to 0xdfff
236 because those are "surrogate" values that are ill-formed in UTF-32.
237
238 A UTF-32 string can indicate its endianness by special code knows as a
239 byte-order mark (BOM). The PCRE functions do not handle this, expecting
240 strings to be in host byte order. A utility function called
241 pcre32_utf32_to_host_byte_order() is provided to help with this (see
242 above).
243
245
246 The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart.
247 The error PCRE_ERROR_BADMODE is given when a compiled pattern is passed
248 to a function that processes patterns in the other mode, for example,
249 if a pattern compiled with pcre_compile() is passed to pcre32_exec().
250
251 There are new error codes whose names begin with PCRE_UTF32_ERR for
252 invalid UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for
253 UTF-8 strings that are described in the section entitled "Reason codes
254 for invalid UTF-8 strings" in the main pcreapi page. The UTF-32 errors
255 are:
256
257 PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
258 PCRE_UTF32_ERR2 Non-character
259 PCRE_UTF32_ERR3 Character > 0x10ffff
260
262
263 If there is an error while compiling a pattern, the error text that is
264 passed back by pcre32_compile() or pcre32_compile2() is still an 8-bit
265 character string, zero-terminated.
266
268
269 The subject and mark fields in the callout block that is passed to a
270 callout function point to 32-bit vectors.
271
273
274 The pcretest program continues to operate with 8-bit input and output
275 files, but it can be used for testing the 32-bit library. If it is run
276 with the command line option -32, patterns and subject strings are con‐
277 verted from 8-bit to 32-bit before being passed to PCRE, and the 32-bit
278 library functions are used instead of the 8-bit ones. Returned 32-bit
279 strings are converted to 8-bit for output. If both the 8-bit and the
280 16-bit libraries were not compiled, pcretest defaults to 32-bit and the
281 -32 option is ignored.
282
283 When PCRE is being built, the RunTest script that is called by "make
284 check" uses the pcretest -C option to discover which of the 8-bit,
285 16-bit and 32-bit libraries has been built, and runs the tests appro‐
286 priately.
287
289
290 Not all the features of the 8-bit library are available with the 32-bit
291 library. The C++ and POSIX wrapper functions support only the 8-bit
292 library, and the pcregrep program is at present 8-bit only.
293
295
296 Philip Hazel
297 University Computing Service
298 Cambridge CB2 3QH, England.
299
301
302 Last updated: 12 May 2013
303 Copyright (c) 1997-2013 University of Cambridge.
304
305
306
307PCRE 8.33 12 May 2013 PCRE(3)