ViewVC logotype

Contents of /code/trunk/doc/html/pcre32.html

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1339 - (show annotations)
Fri Jun 14 09:09:28 2013 UTC (7 years, 11 months ago) by ph10
File MIME type: text/html
File size: 16098 byte(s)
Update man pages to avoid the use of .ti (which causes difficulties for some 
translation software).
1 <html>
2 <head>
3 <title>pcre32 specification</title>
4 </head>
5 <body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
6 <h1>pcre32 man page</h1>
7 <p>
8 Return to the <a href="index.html">PCRE index page</a>.
9 </p>
10 <p>
11 This page is part of the PCRE HTML documentation. It was generated automatically
12 from the original man page. If there is any nonsense in it, please consult the
13 man page, in case the conversion went wrong.
14 <br>
15 <ul>
16 <li><a name="TOC1" href="#SEC1">PCRE 32-BIT API BASIC FUNCTIONS</a>
17 <li><a name="TOC2" href="#SEC2">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a>
18 <li><a name="TOC3" href="#SEC3">PCRE 32-BIT API AUXILIARY FUNCTIONS</a>
19 <li><a name="TOC4" href="#SEC4">PCRE 32-BIT API INDIRECTED FUNCTIONS</a>
20 <li><a name="TOC5" href="#SEC5">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a>
21 <li><a name="TOC6" href="#SEC6">THE PCRE 32-BIT LIBRARY</a>
22 <li><a name="TOC7" href="#SEC7">THE HEADER FILE</a>
23 <li><a name="TOC8" href="#SEC8">THE LIBRARY NAME</a>
24 <li><a name="TOC9" href="#SEC9">STRING TYPES</a>
25 <li><a name="TOC10" href="#SEC10">STRUCTURE TYPES</a>
26 <li><a name="TOC11" href="#SEC11">32-BIT FUNCTIONS</a>
27 <li><a name="TOC12" href="#SEC12">SUBJECT STRING OFFSETS</a>
28 <li><a name="TOC13" href="#SEC13">NAMED SUBPATTERNS</a>
29 <li><a name="TOC14" href="#SEC14">OPTION NAMES</a>
30 <li><a name="TOC15" href="#SEC15">CHARACTER CODES</a>
31 <li><a name="TOC16" href="#SEC16">ERROR NAMES</a>
32 <li><a name="TOC17" href="#SEC17">ERROR TEXTS</a>
33 <li><a name="TOC18" href="#SEC18">CALLOUTS</a>
34 <li><a name="TOC19" href="#SEC19">TESTING</a>
35 <li><a name="TOC20" href="#SEC20">NOT SUPPORTED IN 32-BIT MODE</a>
36 <li><a name="TOC21" href="#SEC21">AUTHOR</a>
37 <li><a name="TOC22" href="#SEC22">REVISION</a>
38 </ul>
39 <P>
40 <b>#include &#60;pcre.h&#62;</b>
41 </P>
42 <br><a name="SEC1" href="#TOC1">PCRE 32-BIT API BASIC FUNCTIONS</a><br>
43 <P>
44 <b>pcre32 *pcre32_compile(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b>
45 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
46 <b> const unsigned char *<i>tableptr</i>);</b>
47 <br>
48 <br>
49 <b>pcre32 *pcre32_compile2(PCRE_SPTR32 <i>pattern</i>, int <i>options</i>,</b>
50 <b> int *<i>errorcodeptr</i>,</b>
51 <b> const unsigned char *<i>tableptr</i>);</b>
52 <br>
53 <br>
54 <b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b>
55 <b> const char **<i>errptr</i>);</b>
56 <br>
57 <br>
58 <b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b>
59 <br>
60 <br>
61 <b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
62 <b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
63 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
64 <br>
65 <br>
66 <b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
67 <b> PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
68 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
69 <b> int *<i>workspace</i>, int <i>wscount</i>);</b>
70 </P>
71 <br><a name="SEC2" href="#TOC1">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a><br>
72 <P>
73 <b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b>
74 <b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
75 <b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
76 <b> PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b>
77 <br>
78 <br>
79 <b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
80 <b> int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b>
81 <b> int <i>buffersize</i>);</b>
82 <br>
83 <br>
84 <b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b>
85 <b> PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
86 <b> int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
87 <b> PCRE_SPTR32 *<i>stringptr</i>);</b>
88 <br>
89 <br>
90 <b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b>
91 <b> PCRE_SPTR32 <i>name</i>);</b>
92 <br>
93 <br>
94 <b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b>
95 <b> PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b>
96 <br>
97 <br>
98 <b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
99 <b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
100 <b> PCRE_SPTR32 *<i>stringptr</i>);</b>
101 <br>
102 <br>
103 <b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b>
104 <b> int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b>
105 <br>
106 <br>
107 <b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b>
108 <br>
109 <br>
110 <b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b>
111 </P>
112 <br><a name="SEC3" href="#TOC1">PCRE 32-BIT API AUXILIARY FUNCTIONS</a><br>
113 <P>
114 <b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
115 <br>
116 <br>
117 <b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b>
118 <br>
119 <br>
120 <b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b>
121 <b> pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b>
122 <br>
123 <br>
124 <b>const unsigned char *pcre32_maketables(void);</b>
125 <br>
126 <br>
127 <b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
128 <b> int <i>what</i>, void *<i>where</i>);</b>
129 <br>
130 <br>
131 <b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b>
132 <br>
133 <br>
134 <b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b>
135 <br>
136 <br>
137 <b>const char *pcre32_version(void);</b>
138 <br>
139 <br>
140 <b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b>
141 <b> pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
142 </P>
143 <br><a name="SEC4" href="#TOC1">PCRE 32-BIT API INDIRECTED FUNCTIONS</a><br>
144 <P>
145 <b>void *(*pcre32_malloc)(size_t);</b>
146 <br>
147 <br>
148 <b>void (*pcre32_free)(void *);</b>
149 <br>
150 <br>
151 <b>void *(*pcre32_stack_malloc)(size_t);</b>
152 <br>
153 <br>
154 <b>void (*pcre32_stack_free)(void *);</b>
155 <br>
156 <br>
157 <b>int (*pcre32_callout)(pcre32_callout_block *);</b>
158 </P>
159 <br><a name="SEC5" href="#TOC1">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a><br>
160 <P>
161 <b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b>
162 <b> PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b>
163 <b> int <i>keep_boms</i>);</b>
164 </P>
165 <br><a name="SEC6" href="#TOC1">THE PCRE 32-BIT LIBRARY</a><br>
166 <P>
167 Starting with release 8.32, it is possible to compile a PCRE library that
168 supports 32-bit character strings, including UTF-32 strings, as well as or
169 instead of the original 8-bit library. This work was done by Christian Persch,
170 based on the work done by Zoltan Herczeg for the 16-bit library. All three
171 libraries contain identical sets of functions, used in exactly the same way.
172 Only the names of the functions and the data types of their arguments and
173 results are different. To avoid over-complication and reduce the documentation
174 maintenance load, most of the PCRE documentation describes the 8-bit library,
175 with only occasional references to the 16-bit and 32-bit libraries. This page
176 describes what is different when you use the 32-bit library.
177 </P>
178 <P>
179 WARNING: A single application can be linked with all or any of the three
180 libraries, but you must take care when processing any particular pattern
181 to use functions from just one library. For example, if you want to study
182 a pattern that was compiled with <b>pcre32_compile()</b>, you must do so
183 with <b>pcre32_study()</b>, not <b>pcre_study()</b>, and you must free the
184 study data with <b>pcre32_free_study()</b>.
185 </P>
186 <br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br>
187 <P>
188 There is only one header file, <b>pcre.h</b>. It contains prototypes for all the
189 functions in all libraries, as well as definitions of flags, structures, error
190 codes, etc.
191 </P>
192 <br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br>
193 <P>
194 In Unix-like systems, the 32-bit library is called <b>libpcre32</b>, and can
195 normally be accesss by adding <b>-lpcre32</b> to the command for linking an
196 application that uses PCRE.
197 </P>
198 <br><a name="SEC9" href="#TOC1">STRING TYPES</a><br>
199 <P>
200 In the 8-bit library, strings are passed to PCRE library functions as vectors
201 of bytes with the C type "char *". In the 32-bit library, strings are passed as
202 vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an
203 appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In
204 very many environments, "unsigned int" is a 32-bit data type. When PCRE is
205 built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is
206 a 32-bit data type. If it is not, the build fails with an error message telling
207 the maintainer to modify the definition appropriately.
208 </P>
209 <br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br>
210 <P>
211 The types of the opaque structures that are used for compiled 32-bit patterns
212 and JIT stacks are <b>pcre32</b> and <b>pcre32_jit_stack</b> respectively. The
213 type of the user-accessible structure that is returned by <b>pcre32_study()</b>
214 is <b>pcre32_extra</b>, and the type of the structure that is used for passing
215 data to a callout function is <b>pcre32_callout_block</b>. These structures
216 contain the same fields, with the same names, as their 8-bit counterparts. The
217 only difference is that pointers to character strings are 32-bit instead of
218 8-bit types.
219 </P>
220 <br><a name="SEC11" href="#TOC1">32-BIT FUNCTIONS</a><br>
221 <P>
222 For every function in the 8-bit library there is a corresponding function in
223 the 32-bit library with a name that starts with <b>pcre32_</b> instead of
224 <b>pcre_</b>. The prototypes are listed above. In addition, there is one extra
225 function, <b>pcre32_utf32_to_host_byte_order()</b>. This is a utility function
226 that converts a UTF-32 character string to host byte order if necessary. The
227 other 32-bit functions expect the strings they are passed to be in host byte
228 order.
229 </P>
230 <P>
231 The <i>input</i> and <i>output</i> arguments of
232 <b>pcre32_utf32_to_host_byte_order()</b> may point to the same address, that is,
233 conversion in place is supported. The output buffer must be at least as long as
234 the input.
235 </P>
236 <P>
237 The <i>length</i> argument specifies the number of 32-bit data units in the
238 input string; a negative value specifies a zero-terminated string.
239 </P>
240 <P>
241 If <i>byte_order</i> is NULL, it is assumed that the string starts off in host
242 byte order. This may be changed by byte-order marks (BOMs) anywhere in the
243 string (commonly as the first character).
244 </P>
245 <P>
246 If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it
247 points means that the input starts off in host byte order, otherwise the
248 opposite order is assumed. Again, BOMs in the string can change this. The final
249 byte order is passed back at the end of processing.
250 </P>
251 <P>
252 If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied
253 into the output string. Otherwise they are discarded.
254 </P>
255 <P>
256 The result of the function is the number of 32-bit units placed into the output
257 buffer, including the zero terminator if the string was zero-terminated.
258 </P>
259 <br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br>
260 <P>
261 The lengths and starting offsets of subject strings must be specified in 32-bit
262 data units, and the offsets within subject strings that are returned by the
263 matching functions are in also 32-bit units rather than bytes.
264 </P>
265 <br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br>
266 <P>
267 The name-to-number translation table that is maintained for named subpatterns
268 uses 32-bit characters. The <b>pcre32_get_stringtable_entries()</b> function
269 returns the length of each entry in the table as the number of 32-bit data
270 units.
271 </P>
272 <br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br>
273 <P>
274 There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK,
275 which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
276 fact, these new options define the same bits in the options word. There is a
277 discussion about the
278 <a href="pcreunicode.html#utf32strings">validity of UTF-32 strings</a>
279 in the
280 <a href="pcreunicode.html"><b>pcreunicode</b></a>
281 page.
282 </P>
283 <P>
284 For the <b>pcre32_config()</b> function there is an option PCRE_CONFIG_UTF32
285 that returns 1 if UTF-32 support is configured, otherwise 0. If this option is
286 given to <b>pcre_config()</b> or <b>pcre16_config()</b>, or if the
287 PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to <b>pcre32_config()</b>,
288 the result is the PCRE_ERROR_BADOPTION error.
289 </P>
290 <br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br>
291 <P>
292 In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the
293 same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
294 from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less
295 than 0xff can therefore be influenced by the locale in the same way as before.
296 Characters greater than 0xff have only one case, and no "type" (such as letter
297 or digit).
298 </P>
299 <P>
300 In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
301 the exception of values in the range 0xd800 to 0xdfff because those are
302 "surrogate" values that are ill-formed in UTF-32.
303 </P>
304 <P>
305 A UTF-32 string can indicate its endianness by special code knows as a
306 byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
307 to be in host byte order. A utility function called
308 <b>pcre32_utf32_to_host_byte_order()</b> is provided to help with this (see
309 above).
310 </P>
311 <br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br>
312 <P>
313 The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart.
314 The error PCRE_ERROR_BADMODE is given when a compiled
315 pattern is passed to a function that processes patterns in the other
316 mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to
317 <b>pcre32_exec()</b>.
318 </P>
319 <P>
320 There are new error codes whose names begin with PCRE_UTF32_ERR for invalid
321 UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
322 are described in the section entitled
323 <a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a>
324 in the main
325 <a href="pcreapi.html"><b>pcreapi</b></a>
326 page. The UTF-32 errors are:
327 <pre>
328 PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
329 PCRE_UTF32_ERR2 Non-character
330 PCRE_UTF32_ERR3 Character &#62; 0x10ffff
331 </PRE>
332 </P>
333 <br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br>
334 <P>
335 If there is an error while compiling a pattern, the error text that is passed
336 back by <b>pcre32_compile()</b> or <b>pcre32_compile2()</b> is still an 8-bit
337 character string, zero-terminated.
338 </P>
339 <br><a name="SEC18" href="#TOC1">CALLOUTS</a><br>
340 <P>
341 The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to
342 a callout function point to 32-bit vectors.
343 </P>
344 <br><a name="SEC19" href="#TOC1">TESTING</a><br>
345 <P>
346 The <b>pcretest</b> program continues to operate with 8-bit input and output
347 files, but it can be used for testing the 32-bit library. If it is run with the
348 command line option <b>-32</b>, patterns and subject strings are converted from
349 8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions
350 are used instead of the 8-bit ones. Returned 32-bit strings are converted to
351 8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled,
352 <b>pcretest</b> defaults to 32-bit and the <b>-32</b> option is ignored.
353 </P>
354 <P>
355 When PCRE is being built, the <b>RunTest</b> script that is called by "make
356 check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit,
357 16-bit and 32-bit libraries has been built, and runs the tests appropriately.
358 </P>
359 <br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 32-BIT MODE</a><br>
360 <P>
361 Not all the features of the 8-bit library are available with the 32-bit
362 library. The C++ and POSIX wrapper functions support only the 8-bit library,
363 and the <b>pcregrep</b> program is at present 8-bit only.
364 </P>
365 <br><a name="SEC21" href="#TOC1">AUTHOR</a><br>
366 <P>
367 Philip Hazel
368 <br>
369 University Computing Service
370 <br>
371 Cambridge CB2 3QH, England.
372 <br>
373 </P>
374 <br><a name="SEC22" href="#TOC1">REVISION</a><br>
375 <P>
376 Last updated: 12 May 2013
377 <br>
378 Copyright &copy; 1997-2013 University of Cambridge.
379 <br>
380 <p>
381 Return to the <a href="index.html">PCRE index page</a>.
382 </p>

  ViewVC Help
Powered by ViewVC 1.1.5