Annotation of embedaddon/pcre/doc/pcre32.3, revision 1.1.1.2
1.1 misho 1: .TH PCRE 3 "12 May 2013" "PCRE 8.33"
2: .SH NAME
3: PCRE - Perl-compatible regular expressions
4: .sp
5: .B #include <pcre.h>
6: .
7: .
8: .SH "PCRE 32-BIT API BASIC FUNCTIONS"
9: .rs
10: .sp
1.1.1.2 ! misho 11: .nf
1.1 misho 12: .B pcre32 *pcre32_compile(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP,
1.1.1.2 ! misho 13: .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
! 14: .B " const unsigned char *\fItableptr\fP);"
! 15: .sp
1.1 misho 16: .B pcre32 *pcre32_compile2(PCRE_SPTR32 \fIpattern\fP, int \fIoptions\fP,
1.1.1.2 ! misho 17: .B " int *\fIerrorcodeptr\fP,"
! 18: .B " const unsigned char *\fItableptr\fP);"
! 19: .sp
1.1 misho 20: .B pcre32_extra *pcre32_study(const pcre32 *\fIcode\fP, int \fIoptions\fP,
1.1.1.2 ! misho 21: .B " const char **\fIerrptr\fP);"
! 22: .sp
1.1 misho 23: .B void pcre32_free_study(pcre32_extra *\fIextra\fP);
1.1.1.2 ! misho 24: .sp
1.1 misho 25: .B int pcre32_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP,"
1.1.1.2 ! misho 26: .B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
! 27: .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
! 28: .sp
1.1 misho 29: .B int pcre32_dfa_exec(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP,"
1.1.1.2 ! misho 30: .B " PCRE_SPTR32 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
! 31: .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
! 32: .B " int *\fIworkspace\fP, int \fIwscount\fP);"
! 33: .fi
1.1 misho 34: .
35: .
36: .SH "PCRE 32-BIT API STRING EXTRACTION FUNCTIONS"
37: .rs
38: .sp
1.1.1.2 ! misho 39: .nf
1.1 misho 40: .B int pcre32_copy_named_substring(const pcre32 *\fIcode\fP,
1.1.1.2 ! misho 41: .B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP,"
! 42: .B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP,"
! 43: .B " PCRE_UCHAR32 *\fIbuffer\fP, int \fIbuffersize\fP);"
! 44: .sp
1.1 misho 45: .B int pcre32_copy_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP,
1.1.1.2 ! misho 46: .B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR32 *\fIbuffer\fP,"
! 47: .B " int \fIbuffersize\fP);"
! 48: .sp
1.1 misho 49: .B int pcre32_get_named_substring(const pcre32 *\fIcode\fP,
1.1.1.2 ! misho 50: .B " PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP,"
! 51: .B " int \fIstringcount\fP, PCRE_SPTR32 \fIstringname\fP,"
! 52: .B " PCRE_SPTR32 *\fIstringptr\fP);"
! 53: .sp
1.1 misho 54: .B int pcre32_get_stringnumber(const pcre32 *\fIcode\fP,
1.1.1.2 ! misho 55: .B " PCRE_SPTR32 \fIname\fP);"
! 56: .sp
1.1 misho 57: .B int pcre32_get_stringtable_entries(const pcre32 *\fIcode\fP,
1.1.1.2 ! misho 58: .B " PCRE_SPTR32 \fIname\fP, PCRE_UCHAR32 **\fIfirst\fP, PCRE_UCHAR32 **\fIlast\fP);"
! 59: .sp
1.1 misho 60: .B int pcre32_get_substring(PCRE_SPTR32 \fIsubject\fP, int *\fIovector\fP,
1.1.1.2 ! misho 61: .B " int \fIstringcount\fP, int \fIstringnumber\fP,"
! 62: .B " PCRE_SPTR32 *\fIstringptr\fP);"
! 63: .sp
1.1 misho 64: .B int pcre32_get_substring_list(PCRE_SPTR32 \fIsubject\fP,
1.1.1.2 ! misho 65: .B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR32 **\fIlistptr\fP);"
! 66: .sp
1.1 misho 67: .B void pcre32_free_substring(PCRE_SPTR32 \fIstringptr\fP);
1.1.1.2 ! misho 68: .sp
1.1 misho 69: .B void pcre32_free_substring_list(PCRE_SPTR32 *\fIstringptr\fP);
1.1.1.2 ! misho 70: .fi
1.1 misho 71: .
72: .
73: .SH "PCRE 32-BIT API AUXILIARY FUNCTIONS"
74: .rs
75: .sp
1.1.1.2 ! misho 76: .nf
1.1 misho 77: .B pcre32_jit_stack *pcre32_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
1.1.1.2 ! misho 78: .sp
1.1 misho 79: .B void pcre32_jit_stack_free(pcre32_jit_stack *\fIstack\fP);
1.1.1.2 ! misho 80: .sp
1.1 misho 81: .B void pcre32_assign_jit_stack(pcre32_extra *\fIextra\fP,
1.1.1.2 ! misho 82: .B " pcre32_jit_callback \fIcallback\fP, void *\fIdata\fP);"
! 83: .sp
1.1 misho 84: .B const unsigned char *pcre32_maketables(void);
1.1.1.2 ! misho 85: .sp
1.1 misho 86: .B int pcre32_fullinfo(const pcre32 *\fIcode\fP, "const pcre32_extra *\fIextra\fP,"
1.1.1.2 ! misho 87: .B " int \fIwhat\fP, void *\fIwhere\fP);"
! 88: .sp
1.1 misho 89: .B int pcre32_refcount(pcre32 *\fIcode\fP, int \fIadjust\fP);
1.1.1.2 ! misho 90: .sp
1.1 misho 91: .B int pcre32_config(int \fIwhat\fP, void *\fIwhere\fP);
1.1.1.2 ! misho 92: .sp
1.1 misho 93: .B const char *pcre32_version(void);
1.1.1.2 ! misho 94: .sp
1.1 misho 95: .B int pcre32_pattern_to_host_byte_order(pcre32 *\fIcode\fP,
1.1.1.2 ! misho 96: .B " pcre32_extra *\fIextra\fP, const unsigned char *\fItables\fP);"
! 97: .fi
1.1 misho 98: .
99: .
100: .SH "PCRE 32-BIT API INDIRECTED FUNCTIONS"
101: .rs
102: .sp
1.1.1.2 ! misho 103: .nf
1.1 misho 104: .B void *(*pcre32_malloc)(size_t);
1.1.1.2 ! misho 105: .sp
1.1 misho 106: .B void (*pcre32_free)(void *);
1.1.1.2 ! misho 107: .sp
1.1 misho 108: .B void *(*pcre32_stack_malloc)(size_t);
1.1.1.2 ! misho 109: .sp
1.1 misho 110: .B void (*pcre32_stack_free)(void *);
1.1.1.2 ! misho 111: .sp
1.1 misho 112: .B int (*pcre32_callout)(pcre32_callout_block *);
1.1.1.2 ! misho 113: .fi
1.1 misho 114: .
115: .
116: .SH "PCRE 32-BIT API 32-BIT-ONLY FUNCTION"
117: .rs
118: .sp
1.1.1.2 ! misho 119: .nf
1.1 misho 120: .B int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *\fIoutput\fP,
1.1.1.2 ! misho 121: .B " PCRE_SPTR32 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP,"
! 122: .B " int \fIkeep_boms\fP);"
! 123: .fi
1.1 misho 124: .
125: .
126: .SH "THE PCRE 32-BIT LIBRARY"
127: .rs
128: .sp
129: Starting with release 8.32, it is possible to compile a PCRE library that
130: supports 32-bit character strings, including UTF-32 strings, as well as or
131: instead of the original 8-bit library. This work was done by Christian Persch,
132: based on the work done by Zoltan Herczeg for the 16-bit library. All three
133: libraries contain identical sets of functions, used in exactly the same way.
134: Only the names of the functions and the data types of their arguments and
135: results are different. To avoid over-complication and reduce the documentation
136: maintenance load, most of the PCRE documentation describes the 8-bit library,
137: with only occasional references to the 16-bit and 32-bit libraries. This page
138: describes what is different when you use the 32-bit library.
139: .P
140: WARNING: A single application can be linked with all or any of the three
141: libraries, but you must take care when processing any particular pattern
142: to use functions from just one library. For example, if you want to study
143: a pattern that was compiled with \fBpcre32_compile()\fP, you must do so
144: with \fBpcre32_study()\fP, not \fBpcre_study()\fP, and you must free the
145: study data with \fBpcre32_free_study()\fP.
146: .
147: .
148: .SH "THE HEADER FILE"
149: .rs
150: .sp
151: There is only one header file, \fBpcre.h\fP. It contains prototypes for all the
152: functions in all libraries, as well as definitions of flags, structures, error
153: codes, etc.
154: .
155: .
156: .SH "THE LIBRARY NAME"
157: .rs
158: .sp
159: In Unix-like systems, the 32-bit library is called \fBlibpcre32\fP, and can
160: normally be accesss by adding \fB-lpcre32\fP to the command for linking an
161: application that uses PCRE.
162: .
163: .
164: .SH "STRING TYPES"
165: .rs
166: .sp
167: In the 8-bit library, strings are passed to PCRE library functions as vectors
168: of bytes with the C type "char *". In the 32-bit library, strings are passed as
169: vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an
170: appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In
171: very many environments, "unsigned int" is a 32-bit data type. When PCRE is
172: built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is
173: a 32-bit data type. If it is not, the build fails with an error message telling
174: the maintainer to modify the definition appropriately.
175: .
176: .
177: .SH "STRUCTURE TYPES"
178: .rs
179: .sp
180: The types of the opaque structures that are used for compiled 32-bit patterns
181: and JIT stacks are \fBpcre32\fP and \fBpcre32_jit_stack\fP respectively. The
182: type of the user-accessible structure that is returned by \fBpcre32_study()\fP
183: is \fBpcre32_extra\fP, and the type of the structure that is used for passing
184: data to a callout function is \fBpcre32_callout_block\fP. These structures
185: contain the same fields, with the same names, as their 8-bit counterparts. The
186: only difference is that pointers to character strings are 32-bit instead of
187: 8-bit types.
188: .
189: .
190: .SH "32-BIT FUNCTIONS"
191: .rs
192: .sp
193: For every function in the 8-bit library there is a corresponding function in
194: the 32-bit library with a name that starts with \fBpcre32_\fP instead of
195: \fBpcre_\fP. The prototypes are listed above. In addition, there is one extra
196: function, \fBpcre32_utf32_to_host_byte_order()\fP. This is a utility function
197: that converts a UTF-32 character string to host byte order if necessary. The
198: other 32-bit functions expect the strings they are passed to be in host byte
199: order.
200: .P
201: The \fIinput\fP and \fIoutput\fP arguments of
202: \fBpcre32_utf32_to_host_byte_order()\fP may point to the same address, that is,
203: conversion in place is supported. The output buffer must be at least as long as
204: the input.
205: .P
206: The \fIlength\fP argument specifies the number of 32-bit data units in the
207: input string; a negative value specifies a zero-terminated string.
208: .P
209: If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host
210: byte order. This may be changed by byte-order marks (BOMs) anywhere in the
211: string (commonly as the first character).
212: .P
213: If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it
214: points means that the input starts off in host byte order, otherwise the
215: opposite order is assumed. Again, BOMs in the string can change this. The final
216: byte order is passed back at the end of processing.
217: .P
218: If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied
219: into the output string. Otherwise they are discarded.
220: .P
221: The result of the function is the number of 32-bit units placed into the output
222: buffer, including the zero terminator if the string was zero-terminated.
223: .
224: .
225: .SH "SUBJECT STRING OFFSETS"
226: .rs
227: .sp
228: The lengths and starting offsets of subject strings must be specified in 32-bit
229: data units, and the offsets within subject strings that are returned by the
230: matching functions are in also 32-bit units rather than bytes.
231: .
232: .
233: .SH "NAMED SUBPATTERNS"
234: .rs
235: .sp
236: The name-to-number translation table that is maintained for named subpatterns
237: uses 32-bit characters. The \fBpcre32_get_stringtable_entries()\fP function
238: returns the length of each entry in the table as the number of 32-bit data
239: units.
240: .
241: .
242: .SH "OPTION NAMES"
243: .rs
244: .sp
245: There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK,
246: which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
247: fact, these new options define the same bits in the options word. There is a
248: discussion about the
249: .\" HTML <a href="pcreunicode.html#utf32strings">
250: .\" </a>
251: validity of UTF-32 strings
252: .\"
253: in the
254: .\" HREF
255: \fBpcreunicode\fP
256: .\"
257: page.
258: .P
259: For the \fBpcre32_config()\fP function there is an option PCRE_CONFIG_UTF32
260: that returns 1 if UTF-32 support is configured, otherwise 0. If this option is
261: given to \fBpcre_config()\fP or \fBpcre16_config()\fP, or if the
262: PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to \fBpcre32_config()\fP,
263: the result is the PCRE_ERROR_BADOPTION error.
264: .
265: .
266: .SH "CHARACTER CODES"
267: .rs
268: .sp
269: In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the
270: same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
271: from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less
272: than 0xff can therefore be influenced by the locale in the same way as before.
273: Characters greater than 0xff have only one case, and no "type" (such as letter
274: or digit).
275: .P
276: In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
277: the exception of values in the range 0xd800 to 0xdfff because those are
278: "surrogate" values that are ill-formed in UTF-32.
279: .P
280: A UTF-32 string can indicate its endianness by special code knows as a
281: byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
282: to be in host byte order. A utility function called
283: \fBpcre32_utf32_to_host_byte_order()\fP is provided to help with this (see
284: above).
285: .
286: .
287: .SH "ERROR NAMES"
288: .rs
289: .sp
290: The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart.
291: The error PCRE_ERROR_BADMODE is given when a compiled
292: pattern is passed to a function that processes patterns in the other
293: mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to
294: \fBpcre32_exec()\fP.
295: .P
296: There are new error codes whose names begin with PCRE_UTF32_ERR for invalid
297: UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
298: are described in the section entitled
299: .\" HTML <a href="pcreapi.html#badutf8reasons">
300: .\" </a>
301: "Reason codes for invalid UTF-8 strings"
302: .\"
303: in the main
304: .\" HREF
305: \fBpcreapi\fP
306: .\"
307: page. The UTF-32 errors are:
308: .sp
309: PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
310: PCRE_UTF32_ERR2 Non-character
311: PCRE_UTF32_ERR3 Character > 0x10ffff
312: .
313: .
314: .SH "ERROR TEXTS"
315: .rs
316: .sp
317: If there is an error while compiling a pattern, the error text that is passed
318: back by \fBpcre32_compile()\fP or \fBpcre32_compile2()\fP is still an 8-bit
319: character string, zero-terminated.
320: .
321: .
322: .SH "CALLOUTS"
323: .rs
324: .sp
325: The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to
326: a callout function point to 32-bit vectors.
327: .
328: .
329: .SH "TESTING"
330: .rs
331: .sp
332: The \fBpcretest\fP program continues to operate with 8-bit input and output
333: files, but it can be used for testing the 32-bit library. If it is run with the
334: command line option \fB-32\fP, patterns and subject strings are converted from
335: 8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions
336: are used instead of the 8-bit ones. Returned 32-bit strings are converted to
337: 8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled,
338: \fBpcretest\fP defaults to 32-bit and the \fB-32\fP option is ignored.
339: .P
340: When PCRE is being built, the \fBRunTest\fP script that is called by "make
341: check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit,
342: 16-bit and 32-bit libraries has been built, and runs the tests appropriately.
343: .
344: .
345: .SH "NOT SUPPORTED IN 32-BIT MODE"
346: .rs
347: .sp
348: Not all the features of the 8-bit library are available with the 32-bit
349: library. The C++ and POSIX wrapper functions support only the 8-bit library,
350: and the \fBpcregrep\fP program is at present 8-bit only.
351: .
352: .
353: .SH AUTHOR
354: .rs
355: .sp
356: .nf
357: Philip Hazel
358: University Computing Service
359: Cambridge CB2 3QH, England.
360: .fi
361: .
362: .
363: .SH REVISION
364: .rs
365: .sp
366: .nf
367: Last updated: 12 May 2013
368: Copyright (c) 1997-2013 University of Cambridge.
369: .fi
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to pcre32.3 CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / doc