1<html> 2<head> 3<title>pcre2demo specification</title> 4</head> 5<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> 6<h1>pcre2demo man page</h1> 7<p> 8Return to the <a href="index.html">PCRE2 index page</a>. 9</p> 10<p> 11This page is part of the PCRE2 HTML documentation. It was generated 12automatically from the original man page. If there is any nonsense in it, 13please consult the man page, in case the conversion went wrong. 14<br> 15<ul> 16</ul> 17<PRE> 18/************************************************* 19* PCRE2 DEMONSTRATION PROGRAM * 20*************************************************/ 21 22/* This is a demonstration program to illustrate a straightforward way of 23using the PCRE2 regular expression library from a C program. See the 24pcre2sample documentation for a short discussion ("man pcre2sample" if you have 25the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is 26incompatible with the original PCRE API. 27 28There are actually three libraries, each supporting a different code unit 29width. This demonstration program uses the 8-bit library. The default is to 30process each code unit as a separate character, but if the pattern begins with 31"(*UTF)", both it and the subject are treated as UTF-8 strings, where 32characters may occupy multiple code units. 33 34In Unix-like environments, if PCRE2 is installed in your standard system 35libraries, you should be able to compile this program using this command: 36 37cc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo 38 39If PCRE2 is not installed in a standard place, it is likely to be installed 40with support for the pkg-config mechanism. If you have pkg-config, you can 41compile this program using this command: 42 43cc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo 44 45If you do not have pkg-config, you may have to use something like this: 46 47cc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \ 48 -R/usr/local/lib -lpcre2-8 -o pcre2demo 49 50Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and 51library files for PCRE2 are installed on your system. Only some operating 52systems (Solaris is one) use the -R option. 53 54Building under Windows: 55 56If you want to statically link this program against a non-dll .a file, you must 57define PCRE2_STATIC before including pcre2.h, so in this environment, uncomment 58the following line. */ 59 60/* #define PCRE2_STATIC */ 61 62/* The PCRE2_CODE_UNIT_WIDTH macro must be defined before including pcre2.h. 63For a program that uses only one code unit width, setting it to 8, 16, or 32 64makes it possible to use generic function names such as pcre2_compile(). Note 65that just changing 8 to 16 (for example) is not sufficient to convert this 66program to process 16-bit characters. Even in a fully 16-bit environment, where 67string-handling functions such as strcmp() and printf() work with 16-bit 68characters, the code for handling the table of named substrings will still need 69to be modified. */ 70 71#define PCRE2_CODE_UNIT_WIDTH 8 72 73#include <stdio.h> 74#include <string.h> 75#include <pcre2.h> 76 77 78/************************************************************************** 79* Here is the program. The API includes the concept of "contexts" for * 80* setting up unusual interface requirements for compiling and matching, * 81* such as custom memory managers and non-standard newline definitions. * 82* This program does not do any of this, so it makes no use of contexts, * 83* always passing NULL where a context could be given. * 84**************************************************************************/ 85 86int main(int argc, char **argv) 87{ 88pcre2_code *re; 89PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */ 90PCRE2_SPTR subject; /* the appropriate width (in this case, 8 bits). */ 91PCRE2_SPTR name_table; 92 93int crlf_is_newline; 94int errornumber; 95int find_all; 96int i; 97int rc; 98int utf8; 99 100uint32_t option_bits; 101uint32_t namecount; 102uint32_t name_entry_size; 103uint32_t newline; 104 105PCRE2_SIZE erroroffset; 106PCRE2_SIZE *ovector; 107 108size_t subject_length; 109pcre2_match_data *match_data; 110 111 112 113/************************************************************************** 114* First, sort out the command line. There is only one possible option at * 115* the moment, "-g" to request repeated matching to find all occurrences, * 116* like Perl's /g option. We set the variable find_all to a non-zero value * 117* if the -g option is present. * 118**************************************************************************/ 119 120find_all = 0; 121for (i = 1; i < argc; i++) 122 { 123 if (strcmp(argv[i], "-g") == 0) find_all = 1; 124 else if (argv[i][0] == '-') 125 { 126 printf("Unrecognised option %s\n", argv[i]); 127 return 1; 128 } 129 else break; 130 } 131 132/* After the options, we require exactly two arguments, which are the pattern, 133and the subject string. */ 134 135if (argc - i != 2) 136 { 137 printf("Exactly two arguments required: a regex and a subject string\n"); 138 return 1; 139 } 140 141/* As pattern and subject are char arguments, they can be straightforwardly 142cast to PCRE2_SPTR as we are working in 8-bit code units. */ 143 144pattern = (PCRE2_SPTR)argv[i]; 145subject = (PCRE2_SPTR)argv[i+1]; 146subject_length = strlen((char *)subject); 147 148 149/************************************************************************* 150* Now we are going to compile the regular expression pattern, and handle * 151* any errors that are detected. * 152*************************************************************************/ 153 154re = pcre2_compile( 155 pattern, /* the pattern */ 156 PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */ 157 0, /* default options */ 158 &errornumber, /* for error number */ 159 &erroroffset, /* for error offset */ 160 NULL); /* use default compile context */ 161 162/* Compilation failed: print the error message and exit. */ 163 164if (re == NULL) 165 { 166 PCRE2_UCHAR buffer[256]; 167 pcre2_get_error_message(errornumber, buffer, sizeof(buffer)); 168 printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset, 169 buffer); 170 return 1; 171 } 172 173 174/************************************************************************* 175* If the compilation succeeded, we call PCRE again, in order to do a * 176* pattern match against the subject string. This does just ONE match. If * 177* further matching is needed, it will be done below. Before running the * 178* match we must set up a match_data block for holding the result. * 179*************************************************************************/ 180 181/* Using this function ensures that the block is exactly the right size for 182the number of capturing parentheses in the pattern. */ 183 184match_data = pcre2_match_data_create_from_pattern(re, NULL); 185 186rc = pcre2_match( 187 re, /* the compiled pattern */ 188 subject, /* the subject string */ 189 subject_length, /* the length of the subject */ 190 0, /* start at offset 0 in the subject */ 191 0, /* default options */ 192 match_data, /* block for storing the result */ 193 NULL); /* use default match context */ 194 195/* Matching failed: handle error cases */ 196 197if (rc < 0) 198 { 199 switch(rc) 200 { 201 case PCRE2_ERROR_NOMATCH: printf("No match\n"); break; 202 /* 203 Handle other special cases if you like 204 */ 205 default: printf("Matching error %d\n", rc); break; 206 } 207 pcre2_match_data_free(match_data); /* Release memory used for the match */ 208 pcre2_code_free(re); /* data and the compiled pattern. */ 209 return 1; 210 } 211 212/* Match succeded. Get a pointer to the output vector, where string offsets are 213stored. */ 214 215ovector = pcre2_get_ovector_pointer(match_data); 216printf("Match succeeded at offset %d\n", (int)ovector[0]); 217 218 219/************************************************************************* 220* We have found the first match within the subject string. If the output * 221* vector wasn't big enough, say so. Then output any substrings that were * 222* captured. * 223*************************************************************************/ 224 225/* The output vector wasn't big enough. This should not happen, because we used 226pcre2_match_data_create_from_pattern() above. */ 227 228if (rc == 0) 229 printf("ovector was not big enough for all the captured substrings\n"); 230 231/* Show substrings stored in the output vector by number. Obviously, in a real 232application you might want to do things other than print them. */ 233 234for (i = 0; i < rc; i++) 235 { 236 PCRE2_SPTR substring_start = subject + ovector[2*i]; 237 size_t substring_length = ovector[2*i+1] - ovector[2*i]; 238 printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start); 239 } 240 241 242/************************************************************************** 243* That concludes the basic part of this demonstration program. We have * 244* compiled a pattern, and performed a single match. The code that follows * 245* shows first how to access named substrings, and then how to code for * 246* repeated matches on the same subject. * 247**************************************************************************/ 248 249/* See if there are any named substrings, and if so, show them by name. First 250we have to extract the count of named parentheses from the pattern. */ 251 252(void)pcre2_pattern_info( 253 re, /* the compiled pattern */ 254 PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */ 255 &namecount); /* where to put the answer */ 256 257if (namecount == 0) printf("No named substrings\n"); else 258 { 259 PCRE2_SPTR tabptr; 260 printf("Named substrings\n"); 261 262 /* Before we can access the substrings, we must extract the table for 263 translating names to numbers, and the size of each entry in the table. */ 264 265 (void)pcre2_pattern_info( 266 re, /* the compiled pattern */ 267 PCRE2_INFO_NAMETABLE, /* address of the table */ 268 &name_table); /* where to put the answer */ 269 270 (void)pcre2_pattern_info( 271 re, /* the compiled pattern */ 272 PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ 273 &name_entry_size); /* where to put the answer */ 274 275 /* Now we can scan the table and, for each entry, print the number, the name, 276 and the substring itself. In the 8-bit library the number is held in two 277 bytes, most significant first. */ 278 279 tabptr = name_table; 280 for (i = 0; i < namecount; i++) 281 { 282 int n = (tabptr[0] << 8) | tabptr[1]; 283 printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, 284 (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]); 285 tabptr += name_entry_size; 286 } 287 } 288 289 290/************************************************************************* 291* If the "-g" option was given on the command line, we want to continue * 292* to search for additional matches in the subject string, in a similar * 293* way to the /g option in Perl. This turns out to be trickier than you * 294* might think because of the possibility of matching an empty string. * 295* What happens is as follows: * 296* * 297* If the previous match was NOT for an empty string, we can just start * 298* the next match at the end of the previous one. * 299* * 300* If the previous match WAS for an empty string, we can't do that, as it * 301* would lead to an infinite loop. Instead, a call of pcre2_match() is * 302* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The * 303* first of these tells PCRE2 that an empty string at the start of the * 304* subject is not a valid match; other possibilities must be tried. The * 305* second flag restricts PCRE2 to one match attempt at the initial string * 306* position. If this match succeeds, an alternative to the empty string * 307* match has been found, and we can print it and proceed round the loop, * 308* advancing by the length of whatever was found. If this match does not * 309* succeed, we still stay in the loop, advancing by just one character. * 310* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be * 311* more than one byte. * 312* * 313* However, there is a complication concerned with newlines. When the * 314* newline convention is such that CRLF is a valid newline, we must * 315* advance by two characters rather than one. The newline convention can * 316* be set in the regex by (*CR), etc.; if not, we must find the default. * 317*************************************************************************/ 318 319if (!find_all) /* Check for -g */ 320 { 321 pcre2_match_data_free(match_data); /* Release the memory that was used */ 322 pcre2_code_free(re); /* for the match data and the pattern. */ 323 return 0; /* Exit the program. */ 324 } 325 326/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline 327sequence. First, find the options with which the regex was compiled and extract 328the UTF state. */ 329 330(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &option_bits); 331utf8 = (option_bits & PCRE2_UTF) != 0; 332 333/* Now find the newline convention and see whether CRLF is a valid newline 334sequence. */ 335 336(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &newline); 337crlf_is_newline = newline == PCRE2_NEWLINE_ANY || 338 newline == PCRE2_NEWLINE_CRLF || 339 newline == PCRE2_NEWLINE_ANYCRLF; 340 341/* Loop for second and subsequent matches */ 342 343for (;;) 344 { 345 uint32_t options = 0; /* Normally no options */ 346 PCRE2_SIZE start_offset = ovector[1]; /* Start at end of previous match */ 347 348 /* If the previous match was for an empty string, we are finished if we are 349 at the end of the subject. Otherwise, arrange to run another match at the 350 same point to see if a non-empty match can be found. */ 351 352 if (ovector[0] == ovector[1]) 353 { 354 if (ovector[0] == subject_length) break; 355 options = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED; 356 } 357 358 /* Run the next matching operation */ 359 360 rc = pcre2_match( 361 re, /* the compiled pattern */ 362 subject, /* the subject string */ 363 subject_length, /* the length of the subject */ 364 start_offset, /* starting offset in the subject */ 365 options, /* options */ 366 match_data, /* block for storing the result */ 367 NULL); /* use default match context */ 368 369 /* This time, a result of NOMATCH isn't an error. If the value in "options" 370 is zero, it just means we have found all possible matches, so the loop ends. 371 Otherwise, it means we have failed to find a non-empty-string match at a 372 point where there was a previous empty-string match. In this case, we do what 373 Perl does: advance the matching position by one character, and continue. We 374 do this by setting the "end of previous match" offset, because that is picked 375 up at the top of the loop as the point at which to start again. 376 377 There are two complications: (a) When CRLF is a valid newline sequence, and 378 the current position is just before it, advance by an extra byte. (b) 379 Otherwise we must ensure that we skip an entire UTF character if we are in 380 UTF mode. */ 381 382 if (rc == PCRE2_ERROR_NOMATCH) 383 { 384 if (options == 0) break; /* All matches found */ 385 ovector[1] = start_offset + 1; /* Advance one code unit */ 386 if (crlf_is_newline && /* If CRLF is a newline & */ 387 start_offset < subject_length - 1 && /* we are at CRLF, */ 388 subject[start_offset] == '\r' && 389 subject[start_offset + 1] == '\n') 390 ovector[1] += 1; /* Advance by one more. */ 391 else if (utf8) /* Otherwise, ensure we */ 392 { /* advance a whole UTF-8 */ 393 while (ovector[1] < subject_length) /* character. */ 394 { 395 if ((subject[ovector[1]] & 0xc0) != 0x80) break; 396 ovector[1] += 1; 397 } 398 } 399 continue; /* Go round the loop again */ 400 } 401 402 /* Other matching errors are not recoverable. */ 403 404 if (rc < 0) 405 { 406 printf("Matching error %d\n", rc); 407 pcre2_match_data_free(match_data); 408 pcre2_code_free(re); 409 return 1; 410 } 411 412 /* Match succeded */ 413 414 printf("\nMatch succeeded again at offset %d\n", (int)ovector[0]); 415 416 /* The match succeeded, but the output vector wasn't big enough. This 417 should not happen. */ 418 419 if (rc == 0) 420 printf("ovector was not big enough for all the captured substrings\n"); 421 422 /* As before, show substrings stored in the output vector by number, and then 423 also any named substrings. */ 424 425 for (i = 0; i < rc; i++) 426 { 427 PCRE2_SPTR substring_start = subject + ovector[2*i]; 428 size_t substring_length = ovector[2*i+1] - ovector[2*i]; 429 printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start); 430 } 431 432 if (namecount == 0) printf("No named substrings\n"); else 433 { 434 PCRE2_SPTR tabptr = name_table; 435 printf("Named substrings\n"); 436 for (i = 0; i < namecount; i++) 437 { 438 int n = (tabptr[0] << 8) | tabptr[1]; 439 printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, 440 (int)(ovector[2*n+1] - ovector[2*n]), subject + ovector[2*n]); 441 tabptr += name_entry_size; 442 } 443 } 444 } /* End of loop to find second and subsequent matches */ 445 446printf("\n"); 447pcre2_match_data_free(match_data); 448pcre2_code_free(re); 449return 0; 450} 451 452/* End of pcre2demo.c */ 453<p> 454Return to the <a href="index.html">PCRE2 index page</a>. 455</p> 456