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 16-BIT API BASIC FUNCTIONS"
9: .rs
10: .sp
11: .nf
12: .B pcre16 *pcre16_compile(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP,
13: .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
14: .B " const unsigned char *\fItableptr\fP);"
15: .sp
16: .B pcre16 *pcre16_compile2(PCRE_SPTR16 \fIpattern\fP, int \fIoptions\fP,
17: .B " int *\fIerrorcodeptr\fP,"
18: .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
19: .B " const unsigned char *\fItableptr\fP);"
20: .sp
21: .B pcre16_extra *pcre16_study(const pcre16 *\fIcode\fP, int \fIoptions\fP,
22: .B " const char **\fIerrptr\fP);"
23: .sp
24: .B void pcre16_free_study(pcre16_extra *\fIextra\fP);
25: .sp
26: .B int pcre16_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
27: .B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
28: .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
29: .sp
30: .B int pcre16_dfa_exec(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
31: .B " PCRE_SPTR16 \fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
32: .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
33: .B " int *\fIworkspace\fP, int \fIwscount\fP);"
34: .fi
35: .
36: .
37: .SH "PCRE 16-BIT API STRING EXTRACTION FUNCTIONS"
38: .rs
39: .sp
40: .nf
41: .B int pcre16_copy_named_substring(const pcre16 *\fIcode\fP,
42: .B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,"
43: .B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,"
44: .B " PCRE_UCHAR16 *\fIbuffer\fP, int \fIbuffersize\fP);"
45: .sp
46: .B int pcre16_copy_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
47: .B " int \fIstringcount\fP, int \fIstringnumber\fP, PCRE_UCHAR16 *\fIbuffer\fP,"
48: .B " int \fIbuffersize\fP);"
49: .sp
50: .B int pcre16_get_named_substring(const pcre16 *\fIcode\fP,
51: .B " PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,"
52: .B " int \fIstringcount\fP, PCRE_SPTR16 \fIstringname\fP,"
53: .B " PCRE_SPTR16 *\fIstringptr\fP);"
54: .sp
55: .B int pcre16_get_stringnumber(const pcre16 *\fIcode\fP,
56: .B " PCRE_SPTR16 \fIname\fP);
57: .sp
58: .B int pcre16_get_stringtable_entries(const pcre16 *\fIcode\fP,
59: .B " PCRE_SPTR16 \fIname\fP, PCRE_UCHAR16 **\fIfirst\fP, PCRE_UCHAR16 **\fIlast\fP);"
60: .sp
61: .B int pcre16_get_substring(PCRE_SPTR16 \fIsubject\fP, int *\fIovector\fP,
62: .B " int \fIstringcount\fP, int \fIstringnumber\fP,"
63: .B " PCRE_SPTR16 *\fIstringptr\fP);"
64: .sp
65: .B int pcre16_get_substring_list(PCRE_SPTR16 \fIsubject\fP,
66: .B " int *\fIovector\fP, int \fIstringcount\fP, PCRE_SPTR16 **\fIlistptr\fP);"
67: .sp
68: .B void pcre16_free_substring(PCRE_SPTR16 \fIstringptr\fP);
69: .sp
70: .B void pcre16_free_substring_list(PCRE_SPTR16 *\fIstringptr\fP);
71: .fi
72: .
73: .
74: .SH "PCRE 16-BIT API AUXILIARY FUNCTIONS"
75: .rs
76: .sp
77: .nf
78: .B pcre16_jit_stack *pcre16_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
79: .sp
80: .B void pcre16_jit_stack_free(pcre16_jit_stack *\fIstack\fP);
81: .sp
82: .B void pcre16_assign_jit_stack(pcre16_extra *\fIextra\fP,
83: .B " pcre16_jit_callback \fIcallback\fP, void *\fIdata\fP);"
84: .sp
85: .B const unsigned char *pcre16_maketables(void);
86: .sp
87: .B int pcre16_fullinfo(const pcre16 *\fIcode\fP, "const pcre16_extra *\fIextra\fP,"
88: .B " int \fIwhat\fP, void *\fIwhere\fP);"
89: .sp
90: .B int pcre16_refcount(pcre16 *\fIcode\fP, int \fIadjust\fP);
91: .sp
92: .B int pcre16_config(int \fIwhat\fP, void *\fIwhere\fP);
93: .sp
94: .B const char *pcre16_version(void);
95: .sp
96: .B int pcre16_pattern_to_host_byte_order(pcre16 *\fIcode\fP,
97: .B " pcre16_extra *\fIextra\fP, const unsigned char *\fItables\fP);"
98: .fi
99: .
100: .
101: .SH "PCRE 16-BIT API INDIRECTED FUNCTIONS"
102: .rs
103: .sp
104: .nf
105: .B void *(*pcre16_malloc)(size_t);
106: .sp
107: .B void (*pcre16_free)(void *);
108: .sp
109: .B void *(*pcre16_stack_malloc)(size_t);
110: .sp
111: .B void (*pcre16_stack_free)(void *);
112: .sp
113: .B int (*pcre16_callout)(pcre16_callout_block *);
114: .fi
115: .
116: .
117: .SH "PCRE 16-BIT API 16-BIT-ONLY FUNCTION"
118: .rs
119: .sp
120: .nf
121: .B int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *\fIoutput\fP,
122: .B " PCRE_SPTR16 \fIinput\fP, int \fIlength\fP, int *\fIbyte_order\fP,"
123: .B " int \fIkeep_boms\fP);"
124: .fi
125: .
126: .
127: .SH "THE PCRE 16-BIT LIBRARY"
128: .rs
129: .sp
130: Starting with release 8.30, it is possible to compile a PCRE library that
131: supports 16-bit character strings, including UTF-16 strings, as well as or
132: instead of the original 8-bit library. The majority of the work to make this
133: possible was done by Zoltan Herczeg. The two libraries contain identical sets
134: of functions, used in exactly the same way. Only the names of the functions and
135: the data types of their arguments and results are different. To avoid
136: over-complication and reduce the documentation maintenance load, most of the
137: PCRE documentation describes the 8-bit library, with only occasional references
138: to the 16-bit library. This page describes what is different when you use the
139: 16-bit library.
140: .P
141: WARNING: A single application can be linked with both libraries, but you must
142: take care when processing any particular pattern to use functions from just one
143: library. For example, if you want to study a pattern that was compiled with
144: \fBpcre16_compile()\fP, you must do so with \fBpcre16_study()\fP, not
145: \fBpcre_study()\fP, and you must free the study data with
146: \fBpcre16_free_study()\fP.
147: .
148: .
149: .SH "THE HEADER FILE"
150: .rs
151: .sp
152: There is only one header file, \fBpcre.h\fP. It contains prototypes for all the
153: functions in all libraries, as well as definitions of flags, structures, error
154: codes, etc.
155: .
156: .
157: .SH "THE LIBRARY NAME"
158: .rs
159: .sp
160: In Unix-like systems, the 16-bit library is called \fBlibpcre16\fP, and can
161: normally be accesss by adding \fB-lpcre16\fP to the command for linking an
162: application that uses PCRE.
163: .
164: .
165: .SH "STRING TYPES"
166: .rs
167: .sp
168: In the 8-bit library, strings are passed to PCRE library functions as vectors
169: of bytes with the C type "char *". In the 16-bit library, strings are passed as
170: vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an
171: appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In
172: very many environments, "short int" is a 16-bit data type. When PCRE is built,
173: it defines PCRE_UCHAR16 as "unsigned short int", but checks that it really is a
174: 16-bit data type. If it is not, the build fails with an error message telling
175: the maintainer to modify the definition appropriately.
176: .
177: .
178: .SH "STRUCTURE TYPES"
179: .rs
180: .sp
181: The types of the opaque structures that are used for compiled 16-bit patterns
182: and JIT stacks are \fBpcre16\fP and \fBpcre16_jit_stack\fP respectively. The
183: type of the user-accessible structure that is returned by \fBpcre16_study()\fP
184: is \fBpcre16_extra\fP, and the type of the structure that is used for passing
185: data to a callout function is \fBpcre16_callout_block\fP. These structures
186: contain the same fields, with the same names, as their 8-bit counterparts. The
187: only difference is that pointers to character strings are 16-bit instead of
188: 8-bit types.
189: .
190: .
191: .SH "16-BIT FUNCTIONS"
192: .rs
193: .sp
194: For every function in the 8-bit library there is a corresponding function in
195: the 16-bit library with a name that starts with \fBpcre16_\fP instead of
196: \fBpcre_\fP. The prototypes are listed above. In addition, there is one extra
197: function, \fBpcre16_utf16_to_host_byte_order()\fP. This is a utility function
198: that converts a UTF-16 character string to host byte order if necessary. The
199: other 16-bit functions expect the strings they are passed to be in host byte
200: order.
201: .P
202: The \fIinput\fP and \fIoutput\fP arguments of
203: \fBpcre16_utf16_to_host_byte_order()\fP may point to the same address, that is,
204: conversion in place is supported. The output buffer must be at least as long as
205: the input.
206: .P
207: The \fIlength\fP argument specifies the number of 16-bit data units in the
208: input string; a negative value specifies a zero-terminated string.
209: .P
210: If \fIbyte_order\fP is NULL, it is assumed that the string starts off in host
211: byte order. This may be changed by byte-order marks (BOMs) anywhere in the
212: string (commonly as the first character).
213: .P
214: If \fIbyte_order\fP is not NULL, a non-zero value of the integer to which it
215: points means that the input starts off in host byte order, otherwise the
216: opposite order is assumed. Again, BOMs in the string can change this. The final
217: byte order is passed back at the end of processing.
218: .P
219: If \fIkeep_boms\fP is not zero, byte-order mark characters (0xfeff) are copied
220: into the output string. Otherwise they are discarded.
221: .P
222: The result of the function is the number of 16-bit units placed into the output
223: buffer, including the zero terminator if the string was zero-terminated.
224: .
225: .
226: .SH "SUBJECT STRING OFFSETS"
227: .rs
228: .sp
229: The lengths and starting offsets of subject strings must be specified in 16-bit
230: data units, and the offsets within subject strings that are returned by the
231: matching functions are in also 16-bit units rather than bytes.
232: .
233: .
234: .SH "NAMED SUBPATTERNS"
235: .rs
236: .sp
237: The name-to-number translation table that is maintained for named subpatterns
238: uses 16-bit characters. The \fBpcre16_get_stringtable_entries()\fP function
239: returns the length of each entry in the table as the number of 16-bit data
240: units.
241: .
242: .
243: .SH "OPTION NAMES"
244: .rs
245: .sp
246: There are two new general option names, PCRE_UTF16 and PCRE_NO_UTF16_CHECK,
247: which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
248: fact, these new options define the same bits in the options word. There is a
249: discussion about the
250: .\" HTML <a href="pcreunicode.html#utf16strings">
251: .\" </a>
252: validity of UTF-16 strings
253: .\"
254: in the
255: .\" HREF
256: \fBpcreunicode\fP
257: .\"
258: page.
259: .P
260: For the \fBpcre16_config()\fP function there is an option PCRE_CONFIG_UTF16
261: that returns 1 if UTF-16 support is configured, otherwise 0. If this option is
262: given to \fBpcre_config()\fP or \fBpcre32_config()\fP, or if the
263: PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF32 option is given to \fBpcre16_config()\fP,
264: the result is the PCRE_ERROR_BADOPTION error.
265: .
266: .
267: .SH "CHARACTER CODES"
268: .rs
269: .sp
270: In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the
271: same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
272: from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than
273: 0xff can therefore be influenced by the locale in the same way as before.
274: Characters greater than 0xff have only one case, and no "type" (such as letter
275: or digit).
276: .P
277: In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
278: the exception of values in the range 0xd800 to 0xdfff because those are
279: "surrogate" values that are used in pairs to encode values greater than 0xffff.
280: .P
281: A UTF-16 string can indicate its endianness by special code knows as a
282: byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
283: to be in host byte order. A utility function called
284: \fBpcre16_utf16_to_host_byte_order()\fP is provided to help with this (see
285: above).
286: .
287: .
288: .SH "ERROR NAMES"
289: .rs
290: .sp
291: The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to
292: their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled
293: pattern is passed to a function that processes patterns in the other
294: mode, for example, if a pattern compiled with \fBpcre_compile()\fP is passed to
295: \fBpcre16_exec()\fP.
296: .P
297: There are new error codes whose names begin with PCRE_UTF16_ERR for invalid
298: UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
299: are described in the section entitled
300: .\" HTML <a href="pcreapi.html#badutf8reasons">
301: .\" </a>
302: "Reason codes for invalid UTF-8 strings"
303: .\"
304: in the main
305: .\" HREF
306: \fBpcreapi\fP
307: .\"
308: page. The UTF-16 errors are:
309: .sp
310: PCRE_UTF16_ERR1 Missing low surrogate at end of string
311: PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate
312: PCRE_UTF16_ERR3 Isolated low surrogate
313: PCRE_UTF16_ERR4 Non-character
314: .
315: .
316: .SH "ERROR TEXTS"
317: .rs
318: .sp
319: If there is an error while compiling a pattern, the error text that is passed
320: back by \fBpcre16_compile()\fP or \fBpcre16_compile2()\fP is still an 8-bit
321: character string, zero-terminated.
322: .
323: .
324: .SH "CALLOUTS"
325: .rs
326: .sp
327: The \fIsubject\fP and \fImark\fP fields in the callout block that is passed to
328: a callout function point to 16-bit vectors.
329: .
330: .
331: .SH "TESTING"
332: .rs
333: .sp
334: The \fBpcretest\fP program continues to operate with 8-bit input and output
335: files, but it can be used for testing the 16-bit library. If it is run with the
336: command line option \fB-16\fP, patterns and subject strings are converted from
337: 8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions
338: are used instead of the 8-bit ones. Returned 16-bit strings are converted to
339: 8-bit for output. If both the 8-bit and the 32-bit libraries were not compiled,
340: \fBpcretest\fP defaults to 16-bit and the \fB-16\fP option is ignored.
341: .P
342: When PCRE is being built, the \fBRunTest\fP script that is called by "make
343: check" uses the \fBpcretest\fP \fB-C\fP option to discover which of the 8-bit,
344: 16-bit and 32-bit libraries has been built, and runs the tests appropriately.
345: .
346: .
347: .SH "NOT SUPPORTED IN 16-BIT MODE"
348: .rs
349: .sp
350: Not all the features of the 8-bit library are available with the 16-bit
351: library. The C++ and POSIX wrapper functions support only the 8-bit library,
352: and the \fBpcregrep\fP program is at present 8-bit only.
353: .
354: .
355: .SH AUTHOR
356: .rs
357: .sp
358: .nf
359: Philip Hazel
360: University Computing Service
361: Cambridge CB2 3QH, England.
362: .fi
363: .
364: .
365: .SH REVISION
366: .rs
367: .sp
368: .nf
369: Last updated: 12 May 2013
370: Copyright (c) 1997-2013 University of Cambridge.
371: .fi
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to pcre16.3 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