Tristan Matthews | 0461646 | 2013-11-14 16:09:34 -0500 | [diff] [blame] | 1 | <html> |
| 2 | <head> |
| 3 | <title>pcredemo specification</title> |
| 4 | </head> |
| 5 | <body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> |
| 6 | <h1>pcredemo 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 | </ul> |
| 17 | <PRE> |
| 18 | /************************************************* |
| 19 | * PCRE DEMONSTRATION PROGRAM * |
| 20 | *************************************************/ |
| 21 | |
| 22 | /* This is a demonstration program to illustrate the most straightforward ways |
| 23 | of calling the PCRE regular expression library from a C program. See the |
| 24 | pcresample documentation for a short discussion ("man pcresample" if you have |
| 25 | the PCRE man pages installed). |
| 26 | |
| 27 | In Unix-like environments, if PCRE is installed in your standard system |
| 28 | libraries, you should be able to compile this program using this command: |
| 29 | |
| 30 | gcc -Wall pcredemo.c -lpcre -o pcredemo |
| 31 | |
| 32 | If PCRE is not installed in a standard place, it is likely to be installed with |
| 33 | support for the pkg-config mechanism. If you have pkg-config, you can compile |
| 34 | this program using this command: |
| 35 | |
| 36 | gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo |
| 37 | |
| 38 | If you do not have pkg-config, you may have to use this: |
| 39 | |
| 40 | gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ |
| 41 | -R/usr/local/lib -lpcre -o pcredemo |
| 42 | |
| 43 | Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and |
| 44 | library files for PCRE are installed on your system. Only some operating |
| 45 | systems (e.g. Solaris) use the -R option. |
| 46 | |
| 47 | Building under Windows: |
| 48 | |
| 49 | If you want to statically link this program against a non-dll .a file, you must |
| 50 | define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and |
| 51 | pcre_free() exported functions will be declared __declspec(dllimport), with |
| 52 | unwanted results. So in this environment, uncomment the following line. */ |
| 53 | |
| 54 | /* #define PCRE_STATIC */ |
| 55 | |
| 56 | #include <stdio.h> |
| 57 | #include <string.h> |
| 58 | #include <pcre.h> |
| 59 | |
| 60 | #define OVECCOUNT 30 /* should be a multiple of 3 */ |
| 61 | |
| 62 | |
| 63 | int main(int argc, char **argv) |
| 64 | { |
| 65 | pcre *re; |
| 66 | const char *error; |
| 67 | char *pattern; |
| 68 | char *subject; |
| 69 | unsigned char *name_table; |
| 70 | unsigned int option_bits; |
| 71 | int erroffset; |
| 72 | int find_all; |
| 73 | int crlf_is_newline; |
| 74 | int namecount; |
| 75 | int name_entry_size; |
| 76 | int ovector[OVECCOUNT]; |
| 77 | int subject_length; |
| 78 | int rc, i; |
| 79 | int utf8; |
| 80 | |
| 81 | |
| 82 | /************************************************************************** |
| 83 | * First, sort out the command line. There is only one possible option at * |
| 84 | * the moment, "-g" to request repeated matching to find all occurrences, * |
| 85 | * like Perl's /g option. We set the variable find_all to a non-zero value * |
| 86 | * if the -g option is present. Apart from that, there must be exactly two * |
| 87 | * arguments. * |
| 88 | **************************************************************************/ |
| 89 | |
| 90 | find_all = 0; |
| 91 | for (i = 1; i < argc; i++) |
| 92 | { |
| 93 | if (strcmp(argv[i], "-g") == 0) find_all = 1; |
| 94 | else break; |
| 95 | } |
| 96 | |
| 97 | /* After the options, we require exactly two arguments, which are the pattern, |
| 98 | and the subject string. */ |
| 99 | |
| 100 | if (argc - i != 2) |
| 101 | { |
| 102 | printf("Two arguments required: a regex and a subject string\n"); |
| 103 | return 1; |
| 104 | } |
| 105 | |
| 106 | pattern = argv[i]; |
| 107 | subject = argv[i+1]; |
| 108 | subject_length = (int)strlen(subject); |
| 109 | |
| 110 | |
| 111 | /************************************************************************* |
| 112 | * Now we are going to compile the regular expression pattern, and handle * |
| 113 | * and errors that are detected. * |
| 114 | *************************************************************************/ |
| 115 | |
| 116 | re = pcre_compile( |
| 117 | pattern, /* the pattern */ |
| 118 | 0, /* default options */ |
| 119 | &error, /* for error message */ |
| 120 | &erroffset, /* for error offset */ |
| 121 | NULL); /* use default character tables */ |
| 122 | |
| 123 | /* Compilation failed: print the error message and exit */ |
| 124 | |
| 125 | if (re == NULL) |
| 126 | { |
| 127 | printf("PCRE compilation failed at offset %d: %s\n", erroffset, error); |
| 128 | return 1; |
| 129 | } |
| 130 | |
| 131 | |
| 132 | /************************************************************************* |
| 133 | * If the compilation succeeded, we call PCRE again, in order to do a * |
| 134 | * pattern match against the subject string. This does just ONE match. If * |
| 135 | * further matching is needed, it will be done below. * |
| 136 | *************************************************************************/ |
| 137 | |
| 138 | rc = pcre_exec( |
| 139 | re, /* the compiled pattern */ |
| 140 | NULL, /* no extra data - we didn't study the pattern */ |
| 141 | subject, /* the subject string */ |
| 142 | subject_length, /* the length of the subject */ |
| 143 | 0, /* start at offset 0 in the subject */ |
| 144 | 0, /* default options */ |
| 145 | ovector, /* output vector for substring information */ |
| 146 | OVECCOUNT); /* number of elements in the output vector */ |
| 147 | |
| 148 | /* Matching failed: handle error cases */ |
| 149 | |
| 150 | if (rc < 0) |
| 151 | { |
| 152 | switch(rc) |
| 153 | { |
| 154 | case PCRE_ERROR_NOMATCH: printf("No match\n"); break; |
| 155 | /* |
| 156 | Handle other special cases if you like |
| 157 | */ |
| 158 | default: printf("Matching error %d\n", rc); break; |
| 159 | } |
| 160 | pcre_free(re); /* Release memory used for the compiled pattern */ |
| 161 | return 1; |
| 162 | } |
| 163 | |
| 164 | /* Match succeded */ |
| 165 | |
| 166 | printf("\nMatch succeeded at offset %d\n", ovector[0]); |
| 167 | |
| 168 | |
| 169 | /************************************************************************* |
| 170 | * We have found the first match within the subject string. If the output * |
| 171 | * vector wasn't big enough, say so. Then output any substrings that were * |
| 172 | * captured. * |
| 173 | *************************************************************************/ |
| 174 | |
| 175 | /* The output vector wasn't big enough */ |
| 176 | |
| 177 | if (rc == 0) |
| 178 | { |
| 179 | rc = OVECCOUNT/3; |
| 180 | printf("ovector only has room for %d captured substrings\n", rc - 1); |
| 181 | } |
| 182 | |
| 183 | /* Show substrings stored in the output vector by number. Obviously, in a real |
| 184 | application you might want to do things other than print them. */ |
| 185 | |
| 186 | for (i = 0; i < rc; i++) |
| 187 | { |
| 188 | char *substring_start = subject + ovector[2*i]; |
| 189 | int substring_length = ovector[2*i+1] - ovector[2*i]; |
| 190 | printf("%2d: %.*s\n", i, substring_length, substring_start); |
| 191 | } |
| 192 | |
| 193 | |
| 194 | /************************************************************************** |
| 195 | * That concludes the basic part of this demonstration program. We have * |
| 196 | * compiled a pattern, and performed a single match. The code that follows * |
| 197 | * shows first how to access named substrings, and then how to code for * |
| 198 | * repeated matches on the same subject. * |
| 199 | **************************************************************************/ |
| 200 | |
| 201 | /* See if there are any named substrings, and if so, show them by name. First |
| 202 | we have to extract the count of named parentheses from the pattern. */ |
| 203 | |
| 204 | (void)pcre_fullinfo( |
| 205 | re, /* the compiled pattern */ |
| 206 | NULL, /* no extra data - we didn't study the pattern */ |
| 207 | PCRE_INFO_NAMECOUNT, /* number of named substrings */ |
| 208 | &namecount); /* where to put the answer */ |
| 209 | |
| 210 | if (namecount <= 0) printf("No named substrings\n"); else |
| 211 | { |
| 212 | unsigned char *tabptr; |
| 213 | printf("Named substrings\n"); |
| 214 | |
| 215 | /* Before we can access the substrings, we must extract the table for |
| 216 | translating names to numbers, and the size of each entry in the table. */ |
| 217 | |
| 218 | (void)pcre_fullinfo( |
| 219 | re, /* the compiled pattern */ |
| 220 | NULL, /* no extra data - we didn't study the pattern */ |
| 221 | PCRE_INFO_NAMETABLE, /* address of the table */ |
| 222 | &name_table); /* where to put the answer */ |
| 223 | |
| 224 | (void)pcre_fullinfo( |
| 225 | re, /* the compiled pattern */ |
| 226 | NULL, /* no extra data - we didn't study the pattern */ |
| 227 | PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */ |
| 228 | &name_entry_size); /* where to put the answer */ |
| 229 | |
| 230 | /* Now we can scan the table and, for each entry, print the number, the name, |
| 231 | and the substring itself. */ |
| 232 | |
| 233 | tabptr = name_table; |
| 234 | for (i = 0; i < namecount; i++) |
| 235 | { |
| 236 | int n = (tabptr[0] << 8) | tabptr[1]; |
| 237 | printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, |
| 238 | ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); |
| 239 | tabptr += name_entry_size; |
| 240 | } |
| 241 | } |
| 242 | |
| 243 | |
| 244 | /************************************************************************* |
| 245 | * If the "-g" option was given on the command line, we want to continue * |
| 246 | * to search for additional matches in the subject string, in a similar * |
| 247 | * way to the /g option in Perl. This turns out to be trickier than you * |
| 248 | * might think because of the possibility of matching an empty string. * |
| 249 | * What happens is as follows: * |
| 250 | * * |
| 251 | * If the previous match was NOT for an empty string, we can just start * |
| 252 | * the next match at the end of the previous one. * |
| 253 | * * |
| 254 | * If the previous match WAS for an empty string, we can't do that, as it * |
| 255 | * would lead to an infinite loop. Instead, a special call of pcre_exec() * |
| 256 | * is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. * |
| 257 | * The first of these tells PCRE that an empty string at the start of the * |
| 258 | * subject is not a valid match; other possibilities must be tried. The * |
| 259 | * second flag restricts PCRE to one match attempt at the initial string * |
| 260 | * position. If this match succeeds, an alternative to the empty string * |
| 261 | * match has been found, and we can print it and proceed round the loop, * |
| 262 | * advancing by the length of whatever was found. If this match does not * |
| 263 | * succeed, we still stay in the loop, advancing by just one character. * |
| 264 | * In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be * |
| 265 | * more than one byte. * |
| 266 | * * |
| 267 | * However, there is a complication concerned with newlines. When the * |
| 268 | * newline convention is such that CRLF is a valid newline, we want must * |
| 269 | * advance by two characters rather than one. The newline convention can * |
| 270 | * be set in the regex by (*CR), etc.; if not, we must find the default. * |
| 271 | *************************************************************************/ |
| 272 | |
| 273 | if (!find_all) /* Check for -g */ |
| 274 | { |
| 275 | pcre_free(re); /* Release the memory used for the compiled pattern */ |
| 276 | return 0; /* Finish unless -g was given */ |
| 277 | } |
| 278 | |
| 279 | /* Before running the loop, check for UTF-8 and whether CRLF is a valid newline |
| 280 | sequence. First, find the options with which the regex was compiled; extract |
| 281 | the UTF-8 state, and mask off all but the newline options. */ |
| 282 | |
| 283 | (void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits); |
| 284 | utf8 = option_bits & PCRE_UTF8; |
| 285 | option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF| |
| 286 | PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF; |
| 287 | |
| 288 | /* If no newline options were set, find the default newline convention from the |
| 289 | build configuration. */ |
| 290 | |
| 291 | if (option_bits == 0) |
| 292 | { |
| 293 | int d; |
| 294 | (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); |
| 295 | /* Note that these values are always the ASCII ones, even in |
| 296 | EBCDIC environments. CR = 13, NL = 10. */ |
| 297 | option_bits = (d == 13)? PCRE_NEWLINE_CR : |
| 298 | (d == 10)? PCRE_NEWLINE_LF : |
| 299 | (d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : |
| 300 | (d == -2)? PCRE_NEWLINE_ANYCRLF : |
| 301 | (d == -1)? PCRE_NEWLINE_ANY : 0; |
| 302 | } |
| 303 | |
| 304 | /* See if CRLF is a valid newline sequence. */ |
| 305 | |
| 306 | crlf_is_newline = |
| 307 | option_bits == PCRE_NEWLINE_ANY || |
| 308 | option_bits == PCRE_NEWLINE_CRLF || |
| 309 | option_bits == PCRE_NEWLINE_ANYCRLF; |
| 310 | |
| 311 | /* Loop for second and subsequent matches */ |
| 312 | |
| 313 | for (;;) |
| 314 | { |
| 315 | int options = 0; /* Normally no options */ |
| 316 | int start_offset = ovector[1]; /* Start at end of previous match */ |
| 317 | |
| 318 | /* If the previous match was for an empty string, we are finished if we are |
| 319 | at the end of the subject. Otherwise, arrange to run another match at the |
| 320 | same point to see if a non-empty match can be found. */ |
| 321 | |
| 322 | if (ovector[0] == ovector[1]) |
| 323 | { |
| 324 | if (ovector[0] == subject_length) break; |
| 325 | options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; |
| 326 | } |
| 327 | |
| 328 | /* Run the next matching operation */ |
| 329 | |
| 330 | rc = pcre_exec( |
| 331 | re, /* the compiled pattern */ |
| 332 | NULL, /* no extra data - we didn't study the pattern */ |
| 333 | subject, /* the subject string */ |
| 334 | subject_length, /* the length of the subject */ |
| 335 | start_offset, /* starting offset in the subject */ |
| 336 | options, /* options */ |
| 337 | ovector, /* output vector for substring information */ |
| 338 | OVECCOUNT); /* number of elements in the output vector */ |
| 339 | |
| 340 | /* This time, a result of NOMATCH isn't an error. If the value in "options" |
| 341 | is zero, it just means we have found all possible matches, so the loop ends. |
| 342 | Otherwise, it means we have failed to find a non-empty-string match at a |
| 343 | point where there was a previous empty-string match. In this case, we do what |
| 344 | Perl does: advance the matching position by one character, and continue. We |
| 345 | do this by setting the "end of previous match" offset, because that is picked |
| 346 | up at the top of the loop as the point at which to start again. |
| 347 | |
| 348 | There are two complications: (a) When CRLF is a valid newline sequence, and |
| 349 | the current position is just before it, advance by an extra byte. (b) |
| 350 | Otherwise we must ensure that we skip an entire UTF-8 character if we are in |
| 351 | UTF-8 mode. */ |
| 352 | |
| 353 | if (rc == PCRE_ERROR_NOMATCH) |
| 354 | { |
| 355 | if (options == 0) break; /* All matches found */ |
| 356 | ovector[1] = start_offset + 1; /* Advance one byte */ |
| 357 | if (crlf_is_newline && /* If CRLF is newline & */ |
| 358 | start_offset < subject_length - 1 && /* we are at CRLF, */ |
| 359 | subject[start_offset] == '\r' && |
| 360 | subject[start_offset + 1] == '\n') |
| 361 | ovector[1] += 1; /* Advance by one more. */ |
| 362 | else if (utf8) /* Otherwise, ensure we */ |
| 363 | { /* advance a whole UTF-8 */ |
| 364 | while (ovector[1] < subject_length) /* character. */ |
| 365 | { |
| 366 | if ((subject[ovector[1]] & 0xc0) != 0x80) break; |
| 367 | ovector[1] += 1; |
| 368 | } |
| 369 | } |
| 370 | continue; /* Go round the loop again */ |
| 371 | } |
| 372 | |
| 373 | /* Other matching errors are not recoverable. */ |
| 374 | |
| 375 | if (rc < 0) |
| 376 | { |
| 377 | printf("Matching error %d\n", rc); |
| 378 | pcre_free(re); /* Release memory used for the compiled pattern */ |
| 379 | return 1; |
| 380 | } |
| 381 | |
| 382 | /* Match succeded */ |
| 383 | |
| 384 | printf("\nMatch succeeded again at offset %d\n", ovector[0]); |
| 385 | |
| 386 | /* The match succeeded, but the output vector wasn't big enough. */ |
| 387 | |
| 388 | if (rc == 0) |
| 389 | { |
| 390 | rc = OVECCOUNT/3; |
| 391 | printf("ovector only has room for %d captured substrings\n", rc - 1); |
| 392 | } |
| 393 | |
| 394 | /* As before, show substrings stored in the output vector by number, and then |
| 395 | also any named substrings. */ |
| 396 | |
| 397 | for (i = 0; i < rc; i++) |
| 398 | { |
| 399 | char *substring_start = subject + ovector[2*i]; |
| 400 | int substring_length = ovector[2*i+1] - ovector[2*i]; |
| 401 | printf("%2d: %.*s\n", i, substring_length, substring_start); |
| 402 | } |
| 403 | |
| 404 | if (namecount <= 0) printf("No named substrings\n"); else |
| 405 | { |
| 406 | unsigned char *tabptr = name_table; |
| 407 | printf("Named substrings\n"); |
| 408 | for (i = 0; i < namecount; i++) |
| 409 | { |
| 410 | int n = (tabptr[0] << 8) | tabptr[1]; |
| 411 | printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2, |
| 412 | ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]); |
| 413 | tabptr += name_entry_size; |
| 414 | } |
| 415 | } |
| 416 | } /* End of loop to find second and subsequent matches */ |
| 417 | |
| 418 | printf("\n"); |
| 419 | pcre_free(re); /* Release memory used for the compiled pattern */ |
| 420 | return 0; |
| 421 | } |
| 422 | |
| 423 | /* End of pcredemo.c */ |
| 424 | <p> |
| 425 | Return to the <a href="index.html">PCRE index page</a>. |
| 426 | </p> |