Annotation of embedaddon/pcre/doc/html/pcre32.html, revision 1.1
1.1 ! misho 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 <pcre.h></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: </P>
! 48: <P>
! 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 char **<i>errptr</i>, int *<i>erroffset</i>,</b>
! 52: <b>const unsigned char *<i>tableptr</i>);</b>
! 53: </P>
! 54: <P>
! 55: <b>pcre32_extra *pcre32_study(const pcre32 *<i>code</i>, int <i>options</i>,</b>
! 56: <b>const char **<i>errptr</i>);</b>
! 57: </P>
! 58: <P>
! 59: <b>void pcre32_free_study(pcre32_extra *<i>extra</i>);</b>
! 60: </P>
! 61: <P>
! 62: <b>int pcre32_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
! 63: <b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
! 64: <b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
! 65: </P>
! 66: <P>
! 67: <b>int pcre32_dfa_exec(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
! 68: <b>PCRE_SPTR32 <i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
! 69: <b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
! 70: <b>int *<i>workspace</i>, int <i>wscount</i>);</b>
! 71: </P>
! 72: <br><a name="SEC2" href="#TOC1">PCRE 32-BIT API STRING EXTRACTION FUNCTIONS</a><br>
! 73: <P>
! 74: <b>int pcre32_copy_named_substring(const pcre32 *<i>code</i>,</b>
! 75: <b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
! 76: <b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
! 77: <b>PCRE_UCHAR32 *<i>buffer</i>, int <i>buffersize</i>);</b>
! 78: </P>
! 79: <P>
! 80: <b>int pcre32_copy_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
! 81: <b>int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR32 *<i>buffer</i>,</b>
! 82: <b>int <i>buffersize</i>);</b>
! 83: </P>
! 84: <P>
! 85: <b>int pcre32_get_named_substring(const pcre32 *<i>code</i>,</b>
! 86: <b>PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
! 87: <b>int <i>stringcount</i>, PCRE_SPTR32 <i>stringname</i>,</b>
! 88: <b>PCRE_SPTR32 *<i>stringptr</i>);</b>
! 89: </P>
! 90: <P>
! 91: <b>int pcre32_get_stringnumber(const pcre32 *<i>code</i>,</b>
! 92: <b>PCRE_SPTR32 <i>name</i>);</b>
! 93: </P>
! 94: <P>
! 95: <b>int pcre32_get_stringtable_entries(const pcre32 *<i>code</i>,</b>
! 96: <b>PCRE_SPTR32 <i>name</i>, PCRE_UCHAR32 **<i>first</i>, PCRE_UCHAR32 **<i>last</i>);</b>
! 97: </P>
! 98: <P>
! 99: <b>int pcre32_get_substring(PCRE_SPTR32 <i>subject</i>, int *<i>ovector</i>,</b>
! 100: <b>int <i>stringcount</i>, int <i>stringnumber</i>,</b>
! 101: <b>PCRE_SPTR32 *<i>stringptr</i>);</b>
! 102: </P>
! 103: <P>
! 104: <b>int pcre32_get_substring_list(PCRE_SPTR32 <i>subject</i>,</b>
! 105: <b>int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR32 **<i>listptr</i>);</b>
! 106: </P>
! 107: <P>
! 108: <b>void pcre32_free_substring(PCRE_SPTR32 <i>stringptr</i>);</b>
! 109: </P>
! 110: <P>
! 111: <b>void pcre32_free_substring_list(PCRE_SPTR32 *<i>stringptr</i>);</b>
! 112: </P>
! 113: <br><a name="SEC3" href="#TOC1">PCRE 32-BIT API AUXILIARY FUNCTIONS</a><br>
! 114: <P>
! 115: <b>pcre32_jit_stack *pcre32_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
! 116: </P>
! 117: <P>
! 118: <b>void pcre32_jit_stack_free(pcre32_jit_stack *<i>stack</i>);</b>
! 119: </P>
! 120: <P>
! 121: <b>void pcre32_assign_jit_stack(pcre32_extra *<i>extra</i>,</b>
! 122: <b>pcre32_jit_callback <i>callback</i>, void *<i>data</i>);</b>
! 123: </P>
! 124: <P>
! 125: <b>const unsigned char *pcre32_maketables(void);</b>
! 126: </P>
! 127: <P>
! 128: <b>int pcre32_fullinfo(const pcre32 *<i>code</i>, const pcre32_extra *<i>extra</i>,</b>
! 129: <b>int <i>what</i>, void *<i>where</i>);</b>
! 130: </P>
! 131: <P>
! 132: <b>int pcre32_refcount(pcre32 *<i>code</i>, int <i>adjust</i>);</b>
! 133: </P>
! 134: <P>
! 135: <b>int pcre32_config(int <i>what</i>, void *<i>where</i>);</b>
! 136: </P>
! 137: <P>
! 138: <b>const char *pcre32_version(void);</b>
! 139: </P>
! 140: <P>
! 141: <b>int pcre32_pattern_to_host_byte_order(pcre32 *<i>code</i>,</b>
! 142: <b>pcre32_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
! 143: </P>
! 144: <br><a name="SEC4" href="#TOC1">PCRE 32-BIT API INDIRECTED FUNCTIONS</a><br>
! 145: <P>
! 146: <b>void *(*pcre32_malloc)(size_t);</b>
! 147: </P>
! 148: <P>
! 149: <b>void (*pcre32_free)(void *);</b>
! 150: </P>
! 151: <P>
! 152: <b>void *(*pcre32_stack_malloc)(size_t);</b>
! 153: </P>
! 154: <P>
! 155: <b>void (*pcre32_stack_free)(void *);</b>
! 156: </P>
! 157: <P>
! 158: <b>int (*pcre32_callout)(pcre32_callout_block *);</b>
! 159: </P>
! 160: <br><a name="SEC5" href="#TOC1">PCRE 32-BIT API 32-BIT-ONLY FUNCTION</a><br>
! 161: <P>
! 162: <b>int pcre32_utf32_to_host_byte_order(PCRE_UCHAR32 *<i>output</i>,</b>
! 163: <b>PCRE_SPTR32 <i>input</i>, int <i>length</i>, int *<i>byte_order</i>,</b>
! 164: <b>int <i>keep_boms</i>);</b>
! 165: </P>
! 166: <br><a name="SEC6" href="#TOC1">THE PCRE 32-BIT LIBRARY</a><br>
! 167: <P>
! 168: Starting with release 8.32, it is possible to compile a PCRE library that
! 169: supports 32-bit character strings, including UTF-32 strings, as well as or
! 170: instead of the original 8-bit library. This work was done by Christian Persch,
! 171: based on the work done by Zoltan Herczeg for the 16-bit library. All three
! 172: libraries contain identical sets of functions, used in exactly the same way.
! 173: Only the names of the functions and the data types of their arguments and
! 174: results are different. To avoid over-complication and reduce the documentation
! 175: maintenance load, most of the PCRE documentation describes the 8-bit library,
! 176: with only occasional references to the 16-bit and 32-bit libraries. This page
! 177: describes what is different when you use the 32-bit library.
! 178: </P>
! 179: <P>
! 180: WARNING: A single application can be linked with all or any of the three
! 181: libraries, but you must take care when processing any particular pattern
! 182: to use functions from just one library. For example, if you want to study
! 183: a pattern that was compiled with <b>pcre32_compile()</b>, you must do so
! 184: with <b>pcre32_study()</b>, not <b>pcre_study()</b>, and you must free the
! 185: study data with <b>pcre32_free_study()</b>.
! 186: </P>
! 187: <br><a name="SEC7" href="#TOC1">THE HEADER FILE</a><br>
! 188: <P>
! 189: There is only one header file, <b>pcre.h</b>. It contains prototypes for all the
! 190: functions in all libraries, as well as definitions of flags, structures, error
! 191: codes, etc.
! 192: </P>
! 193: <br><a name="SEC8" href="#TOC1">THE LIBRARY NAME</a><br>
! 194: <P>
! 195: In Unix-like systems, the 32-bit library is called <b>libpcre32</b>, and can
! 196: normally be accesss by adding <b>-lpcre32</b> to the command for linking an
! 197: application that uses PCRE.
! 198: </P>
! 199: <br><a name="SEC9" href="#TOC1">STRING TYPES</a><br>
! 200: <P>
! 201: In the 8-bit library, strings are passed to PCRE library functions as vectors
! 202: of bytes with the C type "char *". In the 32-bit library, strings are passed as
! 203: vectors of unsigned 32-bit quantities. The macro PCRE_UCHAR32 specifies an
! 204: appropriate data type, and PCRE_SPTR32 is defined as "const PCRE_UCHAR32 *". In
! 205: very many environments, "unsigned int" is a 32-bit data type. When PCRE is
! 206: built, it defines PCRE_UCHAR32 as "unsigned int", but checks that it really is
! 207: a 32-bit data type. If it is not, the build fails with an error message telling
! 208: the maintainer to modify the definition appropriately.
! 209: </P>
! 210: <br><a name="SEC10" href="#TOC1">STRUCTURE TYPES</a><br>
! 211: <P>
! 212: The types of the opaque structures that are used for compiled 32-bit patterns
! 213: and JIT stacks are <b>pcre32</b> and <b>pcre32_jit_stack</b> respectively. The
! 214: type of the user-accessible structure that is returned by <b>pcre32_study()</b>
! 215: is <b>pcre32_extra</b>, and the type of the structure that is used for passing
! 216: data to a callout function is <b>pcre32_callout_block</b>. These structures
! 217: contain the same fields, with the same names, as their 8-bit counterparts. The
! 218: only difference is that pointers to character strings are 32-bit instead of
! 219: 8-bit types.
! 220: </P>
! 221: <br><a name="SEC11" href="#TOC1">32-BIT FUNCTIONS</a><br>
! 222: <P>
! 223: For every function in the 8-bit library there is a corresponding function in
! 224: the 32-bit library with a name that starts with <b>pcre32_</b> instead of
! 225: <b>pcre_</b>. The prototypes are listed above. In addition, there is one extra
! 226: function, <b>pcre32_utf32_to_host_byte_order()</b>. This is a utility function
! 227: that converts a UTF-32 character string to host byte order if necessary. The
! 228: other 32-bit functions expect the strings they are passed to be in host byte
! 229: order.
! 230: </P>
! 231: <P>
! 232: The <i>input</i> and <i>output</i> arguments of
! 233: <b>pcre32_utf32_to_host_byte_order()</b> may point to the same address, that is,
! 234: conversion in place is supported. The output buffer must be at least as long as
! 235: the input.
! 236: </P>
! 237: <P>
! 238: The <i>length</i> argument specifies the number of 32-bit data units in the
! 239: input string; a negative value specifies a zero-terminated string.
! 240: </P>
! 241: <P>
! 242: If <i>byte_order</i> is NULL, it is assumed that the string starts off in host
! 243: byte order. This may be changed by byte-order marks (BOMs) anywhere in the
! 244: string (commonly as the first character).
! 245: </P>
! 246: <P>
! 247: If <i>byte_order</i> is not NULL, a non-zero value of the integer to which it
! 248: points means that the input starts off in host byte order, otherwise the
! 249: opposite order is assumed. Again, BOMs in the string can change this. The final
! 250: byte order is passed back at the end of processing.
! 251: </P>
! 252: <P>
! 253: If <i>keep_boms</i> is not zero, byte-order mark characters (0xfeff) are copied
! 254: into the output string. Otherwise they are discarded.
! 255: </P>
! 256: <P>
! 257: The result of the function is the number of 32-bit units placed into the output
! 258: buffer, including the zero terminator if the string was zero-terminated.
! 259: </P>
! 260: <br><a name="SEC12" href="#TOC1">SUBJECT STRING OFFSETS</a><br>
! 261: <P>
! 262: The lengths and starting offsets of subject strings must be specified in 32-bit
! 263: data units, and the offsets within subject strings that are returned by the
! 264: matching functions are in also 32-bit units rather than bytes.
! 265: </P>
! 266: <br><a name="SEC13" href="#TOC1">NAMED SUBPATTERNS</a><br>
! 267: <P>
! 268: The name-to-number translation table that is maintained for named subpatterns
! 269: uses 32-bit characters. The <b>pcre32_get_stringtable_entries()</b> function
! 270: returns the length of each entry in the table as the number of 32-bit data
! 271: units.
! 272: </P>
! 273: <br><a name="SEC14" href="#TOC1">OPTION NAMES</a><br>
! 274: <P>
! 275: There are two new general option names, PCRE_UTF32 and PCRE_NO_UTF32_CHECK,
! 276: which correspond to PCRE_UTF8 and PCRE_NO_UTF8_CHECK in the 8-bit library. In
! 277: fact, these new options define the same bits in the options word. There is a
! 278: discussion about the
! 279: <a href="pcreunicode.html#utf32strings">validity of UTF-32 strings</a>
! 280: in the
! 281: <a href="pcreunicode.html"><b>pcreunicode</b></a>
! 282: page.
! 283: </P>
! 284: <P>
! 285: For the <b>pcre32_config()</b> function there is an option PCRE_CONFIG_UTF32
! 286: that returns 1 if UTF-32 support is configured, otherwise 0. If this option is
! 287: given to <b>pcre_config()</b> or <b>pcre16_config()</b>, or if the
! 288: PCRE_CONFIG_UTF8 or PCRE_CONFIG_UTF16 option is given to <b>pcre32_config()</b>,
! 289: the result is the PCRE_ERROR_BADOPTION error.
! 290: </P>
! 291: <br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br>
! 292: <P>
! 293: In 32-bit mode, when PCRE_UTF32 is not set, character values are treated in the
! 294: same way as in 8-bit, non UTF-8 mode, except, of course, that they can range
! 295: from 0 to 0x7fffffff instead of 0 to 0xff. Character types for characters less
! 296: than 0xff can therefore be influenced by the locale in the same way as before.
! 297: Characters greater than 0xff have only one case, and no "type" (such as letter
! 298: or digit).
! 299: </P>
! 300: <P>
! 301: In UTF-32 mode, the character code is Unicode, in the range 0 to 0x10ffff, with
! 302: the exception of values in the range 0xd800 to 0xdfff because those are
! 303: "surrogate" values that are ill-formed in UTF-32.
! 304: </P>
! 305: <P>
! 306: A UTF-32 string can indicate its endianness by special code knows as a
! 307: byte-order mark (BOM). The PCRE functions do not handle this, expecting strings
! 308: to be in host byte order. A utility function called
! 309: <b>pcre32_utf32_to_host_byte_order()</b> is provided to help with this (see
! 310: above).
! 311: </P>
! 312: <br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br>
! 313: <P>
! 314: The error PCRE_ERROR_BADUTF32 corresponds to its 8-bit counterpart.
! 315: The error PCRE_ERROR_BADMODE is given when a compiled
! 316: pattern is passed to a function that processes patterns in the other
! 317: mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to
! 318: <b>pcre32_exec()</b>.
! 319: </P>
! 320: <P>
! 321: There are new error codes whose names begin with PCRE_UTF32_ERR for invalid
! 322: UTF-32 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that
! 323: are described in the section entitled
! 324: <a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a>
! 325: in the main
! 326: <a href="pcreapi.html"><b>pcreapi</b></a>
! 327: page. The UTF-32 errors are:
! 328: <pre>
! 329: PCRE_UTF32_ERR1 Surrogate character (range from 0xd800 to 0xdfff)
! 330: PCRE_UTF32_ERR2 Non-character
! 331: PCRE_UTF32_ERR3 Character > 0x10ffff
! 332: </PRE>
! 333: </P>
! 334: <br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br>
! 335: <P>
! 336: If there is an error while compiling a pattern, the error text that is passed
! 337: back by <b>pcre32_compile()</b> or <b>pcre32_compile2()</b> is still an 8-bit
! 338: character string, zero-terminated.
! 339: </P>
! 340: <br><a name="SEC18" href="#TOC1">CALLOUTS</a><br>
! 341: <P>
! 342: The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to
! 343: a callout function point to 32-bit vectors.
! 344: </P>
! 345: <br><a name="SEC19" href="#TOC1">TESTING</a><br>
! 346: <P>
! 347: The <b>pcretest</b> program continues to operate with 8-bit input and output
! 348: files, but it can be used for testing the 32-bit library. If it is run with the
! 349: command line option <b>-32</b>, patterns and subject strings are converted from
! 350: 8-bit to 32-bit before being passed to PCRE, and the 32-bit library functions
! 351: are used instead of the 8-bit ones. Returned 32-bit strings are converted to
! 352: 8-bit for output. If both the 8-bit and the 16-bit libraries were not compiled,
! 353: <b>pcretest</b> defaults to 32-bit and the <b>-32</b> option is ignored.
! 354: </P>
! 355: <P>
! 356: When PCRE is being built, the <b>RunTest</b> script that is called by "make
! 357: check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit,
! 358: 16-bit and 32-bit libraries has been built, and runs the tests appropriately.
! 359: </P>
! 360: <br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 32-BIT MODE</a><br>
! 361: <P>
! 362: Not all the features of the 8-bit library are available with the 32-bit
! 363: library. The C++ and POSIX wrapper functions support only the 8-bit library,
! 364: and the <b>pcregrep</b> program is at present 8-bit only.
! 365: </P>
! 366: <br><a name="SEC21" href="#TOC1">AUTHOR</a><br>
! 367: <P>
! 368: Philip Hazel
! 369: <br>
! 370: University Computing Service
! 371: <br>
! 372: Cambridge CB2 3QH, England.
! 373: <br>
! 374: </P>
! 375: <br><a name="SEC22" href="#TOC1">REVISION</a><br>
! 376: <P>
! 377: Last updated: 12 May 2013
! 378: <br>
! 379: Copyright © 1997-2013 University of Cambridge.
! 380: <br>
! 381: <p>
! 382: Return to the <a href="index.html">PCRE index page</a>.
! 383: </p>
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>