Return to pcre16.html CVS log | Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / pcre / doc / html |
1.1 ! misho 1: <html> ! 2: <head> ! 3: <title>pcre16 specification</title> ! 4: </head> ! 5: <body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> ! 6: <h1>pcre16 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 16-BIT API BASIC FUNCTIONS</a> ! 17: <li><a name="TOC2" href="#SEC2">PCRE 16-BIT API STRING EXTRACTION FUNCTIONS</a> ! 18: <li><a name="TOC3" href="#SEC3">PCRE 16-BIT API AUXILIARY FUNCTIONS</a> ! 19: <li><a name="TOC4" href="#SEC4">PCRE 16-BIT API INDIRECTED FUNCTIONS</a> ! 20: <li><a name="TOC5" href="#SEC5">PCRE 16-BIT API 16-BIT-ONLY FUNCTION</a> ! 21: <li><a name="TOC6" href="#SEC6">THE PCRE 16-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">16-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 16-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 16-BIT API BASIC FUNCTIONS</a><br> ! 43: <P> ! 44: <b>pcre16 *pcre16_compile(PCRE_SPTR16 <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>pcre16 *pcre16_compile2(PCRE_SPTR16 <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>pcre16_extra *pcre16_study(const pcre16 *<i>code</i>, int <i>options</i>,</b> ! 56: <b>const char **<i>errptr</i>);</b> ! 57: </P> ! 58: <P> ! 59: <b>void pcre16_free_study(pcre16_extra *<i>extra</i>);</b> ! 60: </P> ! 61: <P> ! 62: <b>int pcre16_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> ! 63: <b>PCRE_SPTR16 <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 pcre16_dfa_exec(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> ! 68: <b>PCRE_SPTR16 <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 16-BIT API STRING EXTRACTION FUNCTIONS</a><br> ! 73: <P> ! 74: <b>int pcre16_copy_named_substring(const pcre16 *<i>code</i>,</b> ! 75: <b>PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> ! 76: <b>int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> ! 77: <b>PCRE_UCHAR16 *<i>buffer</i>, int <i>buffersize</i>);</b> ! 78: </P> ! 79: <P> ! 80: <b>int pcre16_copy_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> ! 81: <b>int <i>stringcount</i>, int <i>stringnumber</i>, PCRE_UCHAR16 *<i>buffer</i>,</b> ! 82: <b>int <i>buffersize</i>);</b> ! 83: </P> ! 84: <P> ! 85: <b>int pcre16_get_named_substring(const pcre16 *<i>code</i>,</b> ! 86: <b>PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> ! 87: <b>int <i>stringcount</i>, PCRE_SPTR16 <i>stringname</i>,</b> ! 88: <b>PCRE_SPTR16 *<i>stringptr</i>);</b> ! 89: </P> ! 90: <P> ! 91: <b>int pcre16_get_stringnumber(const pcre16 *<i>code</i>,</b> ! 92: <b>PCRE_SPTR16 <i>name</i>);</b> ! 93: </P> ! 94: <P> ! 95: <b>int pcre16_get_stringtable_entries(const pcre16 *<i>code</i>,</b> ! 96: <b>PCRE_SPTR16 <i>name</i>, PCRE_UCHAR16 **<i>first</i>, PCRE_UCHAR16 **<i>last</i>);</b> ! 97: </P> ! 98: <P> ! 99: <b>int pcre16_get_substring(PCRE_SPTR16 <i>subject</i>, int *<i>ovector</i>,</b> ! 100: <b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> ! 101: <b>PCRE_SPTR16 *<i>stringptr</i>);</b> ! 102: </P> ! 103: <P> ! 104: <b>int pcre16_get_substring_list(PCRE_SPTR16 <i>subject</i>,</b> ! 105: <b>int *<i>ovector</i>, int <i>stringcount</i>, PCRE_SPTR16 **<i>listptr</i>);</b> ! 106: </P> ! 107: <P> ! 108: <b>void pcre16_free_substring(PCRE_SPTR16 <i>stringptr</i>);</b> ! 109: </P> ! 110: <P> ! 111: <b>void pcre16_free_substring_list(PCRE_SPTR16 *<i>stringptr</i>);</b> ! 112: </P> ! 113: <br><a name="SEC3" href="#TOC1">PCRE 16-BIT API AUXILIARY FUNCTIONS</a><br> ! 114: <P> ! 115: <b>pcre16_jit_stack *pcre16_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b> ! 116: </P> ! 117: <P> ! 118: <b>void pcre16_jit_stack_free(pcre16_jit_stack *<i>stack</i>);</b> ! 119: </P> ! 120: <P> ! 121: <b>void pcre16_assign_jit_stack(pcre16_extra *<i>extra</i>,</b> ! 122: <b>pcre16_jit_callback <i>callback</i>, void *<i>data</i>);</b> ! 123: </P> ! 124: <P> ! 125: <b>const unsigned char *pcre16_maketables(void);</b> ! 126: </P> ! 127: <P> ! 128: <b>int pcre16_fullinfo(const pcre16 *<i>code</i>, const pcre16_extra *<i>extra</i>,</b> ! 129: <b>int <i>what</i>, void *<i>where</i>);</b> ! 130: </P> ! 131: <P> ! 132: <b>int pcre16_refcount(pcre16 *<i>code</i>, int <i>adjust</i>);</b> ! 133: </P> ! 134: <P> ! 135: <b>int pcre16_config(int <i>what</i>, void *<i>where</i>);</b> ! 136: </P> ! 137: <P> ! 138: <b>const char *pcre16_version(void);</b> ! 139: </P> ! 140: <P> ! 141: <b>int pcre16_pattern_to_host_byte_order(pcre16 *<i>code</i>,</b> ! 142: <b>pcre16_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b> ! 143: </P> ! 144: <br><a name="SEC4" href="#TOC1">PCRE 16-BIT API INDIRECTED FUNCTIONS</a><br> ! 145: <P> ! 146: <b>void *(*pcre16_malloc)(size_t);</b> ! 147: </P> ! 148: <P> ! 149: <b>void (*pcre16_free)(void *);</b> ! 150: </P> ! 151: <P> ! 152: <b>void *(*pcre16_stack_malloc)(size_t);</b> ! 153: </P> ! 154: <P> ! 155: <b>void (*pcre16_stack_free)(void *);</b> ! 156: </P> ! 157: <P> ! 158: <b>int (*pcre16_callout)(pcre16_callout_block *);</b> ! 159: </P> ! 160: <br><a name="SEC5" href="#TOC1">PCRE 16-BIT API 16-BIT-ONLY FUNCTION</a><br> ! 161: <P> ! 162: <b>int pcre16_utf16_to_host_byte_order(PCRE_UCHAR16 *<i>output</i>,</b> ! 163: <b>PCRE_SPTR16 <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 16-BIT LIBRARY</a><br> ! 167: <P> ! 168: Starting with release 8.30, it is possible to compile a PCRE library that ! 169: supports 16-bit character strings, including UTF-16 strings, as well as or ! 170: instead of the original 8-bit library. The majority of the work to make this ! 171: possible was done by Zoltan Herczeg. The two libraries contain identical sets ! 172: of functions, used in exactly the same way. Only the names of the functions and ! 173: the data types of their arguments and results are different. To avoid ! 174: over-complication and reduce the documentation maintenance load, most of the ! 175: PCRE documentation describes the 8-bit library, with only occasional references ! 176: to the 16-bit library. This page describes what is different when you use the ! 177: 16-bit library. ! 178: </P> ! 179: <P> ! 180: WARNING: A single application can be linked with both libraries, but you must ! 181: take care when processing any particular pattern to use functions from just one ! 182: library. For example, if you want to study a pattern that was compiled with ! 183: <b>pcre16_compile()</b>, you must do so with <b>pcre16_study()</b>, not ! 184: <b>pcre_study()</b>, and you must free the study data with ! 185: <b>pcre16_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 both 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 16-bit library is called <b>libpcre16</b>, and can ! 196: normally be accesss by adding <b>-lpcre16</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 16-bit library, strings are passed as ! 203: vectors of unsigned 16-bit quantities. The macro PCRE_UCHAR16 specifies an ! 204: appropriate data type, and PCRE_SPTR16 is defined as "const PCRE_UCHAR16 *". In ! 205: very many environments, "short int" is a 16-bit data type. When PCRE is built, ! 206: it defines PCRE_UCHAR16 as "short int", but checks that it really is a 16-bit ! 207: data type. If it is not, the build fails with an error message telling the ! 208: 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 16-bit patterns ! 213: and JIT stacks are <b>pcre16</b> and <b>pcre16_jit_stack</b> respectively. The ! 214: type of the user-accessible structure that is returned by <b>pcre16_study()</b> ! 215: is <b>pcre16_extra</b>, and the type of the structure that is used for passing ! 216: data to a callout function is <b>pcre16_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 16-bit instead of ! 219: 8-bit types. ! 220: </P> ! 221: <br><a name="SEC11" href="#TOC1">16-BIT FUNCTIONS</a><br> ! 222: <P> ! 223: For every function in the 8-bit library there is a corresponding function in ! 224: the 16-bit library with a name that starts with <b>pcre16_</b> instead of ! 225: <b>pcre_</b>. The prototypes are listed above. In addition, there is one extra ! 226: function, <b>pcre16_utf16_to_host_byte_order()</b>. This is a utility function ! 227: that converts a UTF-16 character string to host byte order if necessary. The ! 228: other 16-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>pcre16_utf16_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 16-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 16-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 offsets within subject strings that are returned by the matching functions ! 263: are in 16-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 16-bit characters. The <b>pcre16_get_stringtable_entries()</b> function ! 269: returns the length of each entry in the table as the number of 16-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_UTF16 and PCRE_NO_UTF16_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. ! 277: </P> ! 278: <P> ! 279: For the <b>pcre16_config()</b> function there is an option PCRE_CONFIG_UTF16 ! 280: that returns 1 if UTF-16 support is configured, otherwise 0. If this option is ! 281: given to <b>pcre_config()</b>, or if the PCRE_CONFIG_UTF8 option is given to ! 282: <b>pcre16_config()</b>, the result is the PCRE_ERROR_BADOPTION error. ! 283: </P> ! 284: <br><a name="SEC15" href="#TOC1">CHARACTER CODES</a><br> ! 285: <P> ! 286: In 16-bit mode, when PCRE_UTF16 is not set, character values are treated in the ! 287: same way as in 8-bit, non UTF-8 mode, except, of course, that they can range ! 288: from 0 to 0xffff instead of 0 to 0xff. Character types for characters less than ! 289: 0xff can therefore be influenced by the locale in the same way as before. ! 290: Characters greater than 0xff have only one case, and no "type" (such as letter ! 291: or digit). ! 292: </P> ! 293: <P> ! 294: In UTF-16 mode, the character code is Unicode, in the range 0 to 0x10ffff, with ! 295: the exception of values in the range 0xd800 to 0xdfff because those are ! 296: "surrogate" values that are used in pairs to encode values greater than 0xffff. ! 297: </P> ! 298: <P> ! 299: A UTF-16 string can indicate its endianness by special code knows as a ! 300: byte-order mark (BOM). The PCRE functions do not handle this, expecting strings ! 301: to be in host byte order. A utility function called ! 302: <b>pcre16_utf16_to_host_byte_order()</b> is provided to help with this (see ! 303: above). ! 304: </P> ! 305: <br><a name="SEC16" href="#TOC1">ERROR NAMES</a><br> ! 306: <P> ! 307: The errors PCRE_ERROR_BADUTF16_OFFSET and PCRE_ERROR_SHORTUTF16 correspond to ! 308: their 8-bit counterparts. The error PCRE_ERROR_BADMODE is given when a compiled ! 309: pattern is passed to a function that processes patterns in the other ! 310: mode, for example, if a pattern compiled with <b>pcre_compile()</b> is passed to ! 311: <b>pcre16_exec()</b>. ! 312: </P> ! 313: <P> ! 314: There are new error codes whose names begin with PCRE_UTF16_ERR for invalid ! 315: UTF-16 strings, corresponding to the PCRE_UTF8_ERR codes for UTF-8 strings that ! 316: are described in the section entitled ! 317: <a href="pcreapi.html#badutf8reasons">"Reason codes for invalid UTF-8 strings"</a> ! 318: in the main ! 319: <a href="pcreapi.html"><b>pcreapi</b></a> ! 320: page. The UTF-16 errors are: ! 321: <pre> ! 322: PCRE_UTF16_ERR1 Missing low surrogate at end of string ! 323: PCRE_UTF16_ERR2 Invalid low surrogate follows high surrogate ! 324: PCRE_UTF16_ERR3 Isolated low surrogate ! 325: PCRE_UTF16_ERR4 Invalid character 0xfffe ! 326: </PRE> ! 327: </P> ! 328: <br><a name="SEC17" href="#TOC1">ERROR TEXTS</a><br> ! 329: <P> ! 330: If there is an error while compiling a pattern, the error text that is passed ! 331: back by <b>pcre16_compile()</b> or <b>pcre16_compile2()</b> is still an 8-bit ! 332: character string, zero-terminated. ! 333: </P> ! 334: <br><a name="SEC18" href="#TOC1">CALLOUTS</a><br> ! 335: <P> ! 336: The <i>subject</i> and <i>mark</i> fields in the callout block that is passed to ! 337: a callout function point to 16-bit vectors. ! 338: </P> ! 339: <br><a name="SEC19" href="#TOC1">TESTING</a><br> ! 340: <P> ! 341: The <b>pcretest</b> program continues to operate with 8-bit input and output ! 342: files, but it can be used for testing the 16-bit library. If it is run with the ! 343: command line option <b>-16</b>, patterns and subject strings are converted from ! 344: 8-bit to 16-bit before being passed to PCRE, and the 16-bit library functions ! 345: are used instead of the 8-bit ones. Returned 16-bit strings are converted to ! 346: 8-bit for output. If the 8-bit library was not compiled, <b>pcretest</b> ! 347: defaults to 16-bit and the <b>-16</b> option is ignored. ! 348: </P> ! 349: <P> ! 350: When PCRE is being built, the <b>RunTest</b> script that is called by "make ! 351: check" uses the <b>pcretest</b> <b>-C</b> option to discover which of the 8-bit ! 352: and 16-bit libraries has been built, and runs the tests appropriately. ! 353: </P> ! 354: <br><a name="SEC20" href="#TOC1">NOT SUPPORTED IN 16-BIT MODE</a><br> ! 355: <P> ! 356: Not all the features of the 8-bit library are available with the 16-bit ! 357: library. The C++ and POSIX wrapper functions support only the 8-bit library, ! 358: and the <b>pcregrep</b> program is at present 8-bit only. ! 359: </P> ! 360: <br><a name="SEC21" href="#TOC1">AUTHOR</a><br> ! 361: <P> ! 362: Philip Hazel ! 363: <br> ! 364: University Computing Service ! 365: <br> ! 366: Cambridge CB2 3QH, England. ! 367: <br> ! 368: </P> ! 369: <br><a name="SEC22" href="#TOC1">REVISION</a><br> ! 370: <P> ! 371: Last updated: 08 January 2012 ! 372: <br> ! 373: Copyright © 1997-2012 University of Cambridge. ! 374: <br> ! 375: <p> ! 376: Return to the <a href="index.html">PCRE index page</a>. ! 377: </p>