1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695
|
// detector.c written by Mitchell Foral. mitchell<att>caladbolg.net.
// See COPYING for license information.
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include "detector.h"
#include "languages.h"
#include "log.h"
#include "hash/cppheader_hash.h"
#include "hash/disambiguatefunc_hash.h"
#include "hash/extension_hash.h"
#include "hash/filename_hash.h"
#define ISBINARY(x) (x[0] == '\1')
#define ISAMBIGUOUS(x) (x[0] == '\2')
#define DISAMBIGUATEWHAT(x) &x[1]
const char *ohcount_detect_language(SourceFile *sourcefile) {
const char *language = NULL;
char *p, *pe;
int length;
// Attempt to detect based on file extension.
length = strlen(sourcefile->ext);
struct ExtensionMap *re = ohcount_hash_language_from_ext(sourcefile->ext,
length);
if (re) language = re->value;
if (language == NULL) {
// Try the lower-case version of this extension.
char lowerext[length + 1];
strncpy(lowerext, sourcefile->ext, length);
lowerext[length] = '\0';
for (p = lowerext; p < lowerext + length; p++) *p = tolower(*p);
struct ExtensionMap *re = ohcount_hash_language_from_ext(lowerext, length);
if (re) return re->value;
}
if (language) {
if (ISAMBIGUOUS(language)) {
// Call the appropriate function for disambiguation.
length = strlen(DISAMBIGUATEWHAT(language));
struct DisambiguateFuncsMap *rd =
ohcount_hash_disambiguate_func_from_id(DISAMBIGUATEWHAT(language),
length);
if (rd) return rd->value(sourcefile);
} else return ISBINARY(language) ? NULL : language;
}
// Attempt to detect based on filename.
length = strlen(sourcefile->filename);
struct FilenameMap *rf =
ohcount_hash_language_from_filename(sourcefile->filename, length);
if (rf) return rf->value;
char line[81] = { '\0' }, buf[81];
// Attempt to detect using Emacs mode line (/^-\*-\s*mode[\s:]*\w/i).
p = ohcount_sourcefile_get_contents(sourcefile);
pe = p;
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (pe < eof) {
// Get the contents of the first line.
while (pe < eof && *pe != '\r' && *pe != '\n') pe++;
length = (pe - p <= sizeof(line)) ? pe - p : sizeof(line);
strncpy(line, p, length);
line[length] = '\0';
if (*line == '#' && *(line + 1) == '!') {
// First line was sh-bang; loop to get contents of second line.
while (*pe == '\r' || *pe == '\n') pe++;
p = pe;
} else break;
}
char *eol = line + strlen(line);
for (p = line; p < eol; p++) *p = tolower(*p);
p = strstr(line, "-*-");
if (p) {
p += 3;
while (*p == ' ' || *p == '\t') p++;
if (strncmp(p, "mode", 4) == 0) {
p += 4;
while (*p == ' ' || *p == '\t' || *p == ':') p++;
}
pe = p;
while (isalnum(*pe)) pe++;
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
struct LanguageMap *rl = ohcount_hash_language_from_name(buf, length);
if (rl) return rl->name;
}
// Attempt to detect based on Unix 'file' command.
int tmpfile = 0;
char *path = sourcefile->filepath;
if (sourcefile->diskpath)
path = sourcefile->diskpath;
if (access(path, F_OK) != 0) { // create temporary file
path = malloc(21);
strncpy(path, "/tmp/ohcount_XXXXXXX", 20);
*(path + 21) = '\0';
int fd = mkstemp(path);
char *contents = ohcount_sourcefile_get_contents(sourcefile);
log_it("contents:");
log_it(contents);
length = contents ? strlen(contents) : 0;
write(fd, contents, length);
close(fd);
tmpfile = 1;
}
char command[strlen(path) + 11];
sprintf(command, "file -b '%s'", path);
FILE *f = popen(command, "r");
if (f) {
fgets(line, sizeof(line), f);
char *eol = line + strlen(line);
for (p = line; p < eol; p++) *p = tolower(*p);
p = strstr(line, "script text");
if (p && p == line) { // /^script text(?: executable)? for \w/
p = strstr(line, "for ");
if (p) {
p += 4;
pe = p;
while (isalnum(*pe)) pe++;
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
struct LanguageMap *rl = ohcount_hash_language_from_name(buf, length);
if (rl) language = rl->name;
}
} else if (p) { // /(\w+)(?: -\w+)* script text/
do {
p--;
pe = p;
while (*p == ' ') p--;
while (p != line && isalnum(*(p - 1))) p--;
if (p != line && *(p - 1) == '-') p--;
} while (*p == '-'); // Skip over any switches.
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
struct LanguageMap *rl = ohcount_hash_language_from_name(buf, length);
if (rl) language = rl->name;
} else if (strstr(line, "xml")) language = LANG_XML;
pclose(f);
if (tmpfile) {
remove(path);
free(path);
}
if (language) return language;
}
return NULL;
}
const char *disambiguate_aspx(SourceFile *sourcefile) {
char *p = ohcount_sourcefile_get_contents(sourcefile);
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
for (; p < eof; p++) {
// /<%@\s*Page[^>]+Language="VB"[^>]+%>/
p = strstr(p, "<%@");
if (!p)
break;
char *pe = strstr(p, "%>");
if (p && pe) {
p += 3;
const int length = pe - p;
char buf[length];
strncpy(buf, p, length);
buf[length] = '\0';
char *eol = buf + strlen(buf);
for (p = buf; p < eol; p++) *p = tolower(*p);
p = buf;
while (*p == ' ' || *p == '\t') p++;
if (strncmp(p, "page", 4) == 0) {
p += 4;
if (strstr(p, "language=\"vb\""))
return LANG_VB_ASPX;
}
}
}
return LANG_CS_ASPX;
}
const char *disambiguate_b(SourceFile *sourcefile) {
char *p = ohcount_sourcefile_get_contents(sourcefile);
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (p < eof) {
// /(implement[ \t])|(include[ \t]+"[^"]*";)|
// ((return|break|continue).*;|(pick|case).*\{)/
if (strncmp(p, "implement", 9) == 0 &&
(*(p + 9) == ' ' || *(p + 9) == '\t'))
return LANG_LIMBO;
else if (strncmp(p, "include", 7) == 0 &&
(*(p + 7) == ' ' || *(p + 7) == '\t')) {
p += 7;
while (*p == ' ' || *p == '\t') p++;
if (*p == '"') {
while (*p != '"' && p < eof) p++;
if (*p == '"' && *(p + 1) == ';')
return LANG_LIMBO;
}
} else if (strncmp(p, "return", 6) == 0 ||
strncmp(p, "break", 5) == 0 ||
strncmp(p, "continue", 8) == 0) {
if (strstr(p, ";"))
return LANG_LIMBO;
} else if (strncmp(p, "pick", 4) == 0 ||
strncmp(p, "case", 4) == 0) {
if (strstr(p, "{"))
return LANG_LIMBO;
}
p++;
}
return disambiguate_basic(sourcefile);
}
const char *disambiguate_basic(SourceFile *sourcefile) {
char *p, *pe;
int length;
// Attempt to detect based on file contents.
char line[81];
p = ohcount_sourcefile_get_contents(sourcefile);
pe = p;
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (pe < eof) {
// Get a line at a time.
while (pe < eof && *pe != '\r' && *pe != '\n') pe++;
length = (pe - p <= sizeof(line)) ? pe - p : sizeof(line);
strncpy(line, p, length);
line[length] = '\0';
char *line_end = pe;
p = line;
if (isdigit(*p)) {
// /^\d+\s+\w/
p++;
while (isdigit(*p)) p++;
if (*p == ' ' || *p == '\t') {
p++;
while (*p == ' ' || *p == '\t') p++;
if (isalnum(*p))
return LANG_CLASSIC_BASIC;
}
}
// Next line.
pe = line_end;
while (*pe == '\r' || *pe == '\n') pe++;
p = pe;
}
// Attempt to detect from associated VB files in file context.
char **filenames = ohcount_sourcefile_get_filenames(sourcefile);
if (filenames) {
int i;
for (i = 0; filenames[i] != NULL; i++) {
pe = filenames[i] + strlen(filenames[i]);
p = pe;
while (p > filenames[i] && *(p - 1) != '.') p--;
length = pe - p;
if (length == 3 &&
(strncmp(p, "frm", length) == 0 ||
strncmp(p, "frx", length) == 0 ||
strncmp(p, "vba", length) == 0 ||
strncmp(p, "vbp", length) == 0 ||
strncmp(p, "vbs", length) == 0)) {
return LANG_VISUALBASIC;
}
}
}
return LANG_STRUCTURED_BASIC;
}
const char *disambiguate_cs(SourceFile *sourcefile) {
// Attempt to detect based on file contents.
char *contents = ohcount_sourcefile_get_contents(sourcefile);
if (contents && strstr(contents, "<?cs"))
return LANG_CLEARSILVER_TEMPLATE;
else
return LANG_CSHARP;
}
const char *disambiguate_fortran(SourceFile *sourcefile) {
char *p, *pe;
p = ohcount_sourcefile_get_contents(sourcefile);
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (p < eof) {
if (*p == ' ' && p + 5 < eof) {
int i;
for (i = 1; i <= 5; i++)
if (!isdigit(*(p + i)) && *(p + i) != ' ')
return LANG_FORTRANFIXED; // definately not f77
// Possibly fixed (doesn't match /^\s*\d+\s*$/).
pe = p;
while (*pe == ' ' || *pe == '\t') pe++;
if (pe - p <= 5) {
if (!isdigit(*pe))
return LANG_FORTRANFIXED;
while (isdigit(*pe)) pe++;
while (*pe == ' ' || *pe == '\t') pe++;
if (*pe != '\r' && *pe != '\n' && pe - p == 5)
return LANG_FORTRANFIXED;
}
}
while (*p != '\r' && *p != '\n' && *p != '&' && p < eof) p++;
if (*p == '&') {
p++;
// Look for free-form continuation.
while (*p == ' ' || *p == '\t') p++;
if (*p == '\r' || *p == '\n') {
pe = p;
while (*pe == '\r' || *pe == '\n' || *pe == ' ' || *pe == '\t') pe++;
if (*pe == '&')
return LANG_FORTRANFREE;
}
}
while (*p == '\r' || *p == '\n') p++;
}
return LANG_FORTRANFREE; // might as well be free-form
}
const char *disambiguate_h(SourceFile *sourcefile) {
char *p, *pe;
int length;
// If the directory contains a matching *.m file, likely Objective C.
length = strlen(sourcefile->filename);
if (strcmp(sourcefile->ext, "h") == 0) {
char path[length];
strncpy(path, sourcefile->filename, length);
path[length] = '\0';
*(path + length - 1) = 'm';
char **filenames = ohcount_sourcefile_get_filenames(sourcefile);
if (filenames) {
int i;
for (i = 0; filenames[i] != NULL; i++)
if (strcmp(path, filenames[i]) == 0)
return LANG_OBJECTIVE_C;
}
}
// Attempt to detect based on file contents.
char line[81], buf[81];
p = ohcount_sourcefile_get_contents(sourcefile);
pe = p;
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (pe < eof) {
// Get a line at a time.
while (pe < eof && *pe != '\r' && *pe != '\n') pe++;
length = (pe - p <= sizeof(line)) ? pe - p : sizeof(line);
strncpy(line, p, length);
line[length] = '\0';
char *eol = line + strlen(line);
char *line_end = pe;
// Look for C++ headers.
if (*line == '#') {
p = line + 1;
while (*p == ' ' || *p == '\t') p++;
if (strncmp(p, "include", 7) == 0 &&
(*(p + 7) == ' ' || *(p + 7) == '\t')) {
// /^#\s*include\s+[<"][^>"]+[>"]/
p += 8;
while (*p == ' ' || *p == '\t') p++;
if (*p == '<' || *p == '"') {
// Is the header file a C++ header file?
p++;
pe = p;
while (pe < eol && *pe != '>' && *pe != '"') pe++;
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
if (ohcount_hash_is_cppheader(buf, length))
return LANG_CPP;
// Is the extension for the header file a C++ file?
p = pe;
while (p > line && *(p - 1) != '.') p--;
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
struct ExtensionMap *re = ohcount_hash_language_from_ext(buf, length);
if (re && strcmp(re->value, LANG_CPP) == 0)
return LANG_CPP;
}
}
}
// Look for C++ keywords.
p = line;
while (p < eol) {
if (islower(*p) && p != line && !isalnum(*(p - 1)) && *(p - 1) != '_') {
pe = p;
while (islower(*pe)) pe++;
if (!isalnum(*pe) && *pe != '_') {
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
if (strcmp(buf, "class") == 0 ||
strcmp(buf, "namespace") == 0 ||
strcmp(buf, "template") == 0 ||
strcmp(buf, "typename") == 0)
return LANG_CPP;
}
p = pe + 1;
} else p++;
}
// Next line.
pe = line_end;
while (*pe == '\r' || *pe == '\n') pe++;
p = pe;
}
// Nothing to suggest C++.
return LANG_C;
}
const char *disambiguate_in(SourceFile *sourcefile) {
char *p, *pe;
int length;
const char *language = NULL;
p = sourcefile->filepath;
pe = p + strlen(p) - 3;
if (strstr(p, ".") <= pe) {
// Only if the filename has an extension prior to the .in
length = pe - p;
char buf[length];
strncpy(buf, p, length);
buf[length] = '\0';
SourceFile *undecorated = ohcount_sourcefile_new(buf);
p = ohcount_sourcefile_get_contents(sourcefile);
if (!p) {
return NULL;
}
// The filepath without the '.in' extension does not exist on disk. The
// sourcefile->diskpath field must be set incase the detector needs to run
// 'file -b' on the file.
ohcount_sourcefile_set_diskpath(undecorated, sourcefile->filepath);
ohcount_sourcefile_set_contents(undecorated, p);
char **filenames = ohcount_sourcefile_get_filenames(sourcefile);
ohcount_sourcefile_set_filenames(undecorated, filenames);
language = ohcount_sourcefile_get_language(undecorated);
ohcount_sourcefile_free(undecorated);
}
return language;
}
const char *disambiguate_inc(SourceFile *sourcefile) {
char *p = ohcount_sourcefile_get_contents(sourcefile);
if (p) {
char *eof = p + strlen(p);
while (p < eof) {
if (*p == '\0')
return BINARY;
else if (*p == '?' && strncmp(p + 1, "php", 3) == 0)
return LANG_PHP;
p++;
}
}
return NULL;
}
const char *disambiguate_m(SourceFile *sourcefile) {
char *p, *pe;
int length;
// Attempt to detect based on a weighted heuristic of file contents.
int matlab_score = 0;
int objective_c_score = 0;
int limbo_score = 0;
int octave_syntax_detected = 0;
int i, has_h_headers = 0, has_c_files = 0;
char **filenames = ohcount_sourcefile_get_filenames(sourcefile);
if (filenames) {
for (i = 0; filenames[i] != NULL; i++) {
p = filenames[i];
pe = p + strlen(p);
if (pe - p >= 4) {
if (*(pe - 4) == '.' && *(pe - 3) == 'c' &&
((*(pe - 2) == 'p' && *(pe - 1) == 'p') ||
(*(pe - 2) == '+' && *(pe - 1) == '+') ||
(*(pe - 2) == 'x' && *(pe - 1) == 'x'))) {
has_c_files = 1;
break; // short circuit
}
} else if (pe - p >= 3) {
if (*(pe - 3) == '.' && *(pe - 2) == 'c' && *(pe - 1) == 'c') {
has_c_files = 1;
break; // short circuit
}
} else if (pe - p >= 2) {
if (*(pe - 2) == '.') {
if (*(pe - 1) == 'h')
has_h_headers = 1;
else if (*(pe - 1) == 'c' || *(pe - 1) == 'C') {
has_c_files = 1;
break; // short circuit
}
}
}
}
}
if (has_h_headers && !has_c_files)
objective_c_score += 5;
char line[81], buf[81];
p = ohcount_sourcefile_get_contents(sourcefile);
pe = p;
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (pe < eof) {
// Get a line at a time.
while (pe < eof && *pe != '\r' && *pe != '\n') pe++;
length = (pe - p <= sizeof(line)) ? pe - p : sizeof(line);
strncpy(line, p, length);
line[length] = '\0';
char *eol = line + strlen(line);
char *line_end = pe;
// Look for tell-tale lines.
p = line;
while (*p == ' ' || *p == '\t') p++;
if (*p == '%') { // Matlab comment
matlab_score++;
} else if (*p == '#' && strncmp(p, "#import", 7) == 0) { // Objective C
objective_c_score++;
} else if (*p == '#') { // Limbo or Octave comment
while (*p == '#') p++;
if (*p == ' ' || *p == '\t') {
limbo_score++;
matlab_score++;
octave_syntax_detected = 1;
}
} else if (*p == '/' && *(p + 1) == '/' || *(p + 1) == '*') {
objective_c_score++; // Objective C comment
} else if (*p == '+' || *p == '-') { // Objective C method signature
objective_c_score++;
} else if (*p == '@' || *p == '#') { // Objective C method signature
if (strncmp(p, "@implementation", 15) == 0 ||
strncmp(p, "@interface", 10) == 0)
objective_c_score++;
} else if (strncmp(p, "function", 8) == 0) { // Matlab or Octave function
p += 8;
while (*p == ' ' || *p == '\t') p++;
if (*p == '(')
matlab_score++;
} else if (strncmp(p, "include", 7) == 0) { // Limbo include
// /^include[ \t]+"[^"]+\.m";/
p += 7;
if (*p == ' ' || *p == '\t') {
while (*p == ' ' || *p == '\t') p++;
if (*p == '"') {
while (*p != '"' && p < eol) p++;
if (*p == '"' && *(p - 2) == '.' && *(p - 1) == 'm')
limbo_score++;
}
}
}
// Look for Octave keywords.
p = line;
while (p < eol) {
if (islower(*p) && p != line && !isalnum(*(p - 1))) {
pe = p;
while (islower(*pe) || *pe == '_') pe++;
if (!isalnum(*pe)) {
length = pe - p;
strncpy(buf, p, length);
buf[length] = '\0';
if (strcmp(buf, "end_try_catch") == 0 ||
strcmp(buf, "end_unwind_protect") == 0 ||
strcmp(buf, "endfunction") == 0 ||
strcmp(buf, "endwhile") == 0)
octave_syntax_detected = 1;
}
p = pe + 1;
} else p++;
}
// Look for Limbo declarations
p = line;
while (p < eol) {
if (*p == ':' && (*(p + 1) == ' ' || *(p + 1) == '\t')) {
// /:[ \t]+(module|adt|fn ?\(|con[ \t])/
p += 2;
if (strncmp(p, "module", 6) == 0 && !isalnum(*(p + 6)) ||
strncmp(p, "adt", 3) == 0 && !isalnum(*(p + 3)) ||
strncmp(p, "fn", 2) == 0 &&
(*(p + 2) == ' ' && *(p + 3) == '(' || *(p + 2) == '(') ||
strncmp(p, "con", 3) == 0 &&
(*(p + 3) == ' ' || *(p + 3) == '\t'))
limbo_score++;
} else p++;
}
// Next line.
pe = line_end;
while (*pe == '\r' || *pe == '\n') pe++;
p = pe;
}
if (limbo_score > objective_c_score && limbo_score > matlab_score)
return LANG_LIMBO;
else if (objective_c_score > matlab_score)
return LANG_OBJECTIVE_C;
else
return octave_syntax_detected ? LANG_OCTAVE : LANG_MATLAB;
}
#define QMAKE_SOURCES_SPACE "SOURCES +="
#define QMAKE_SOURCES "SOURCES+="
#define QMAKE_CONFIG_SPACE "CONFIG +="
#define QMAKE_CONFIG "CONFIG+="
const char *disambiguate_pro(SourceFile *sourcefile) {
char *p = ohcount_sourcefile_get_contents(sourcefile);
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
for (; p < eof; p++) {
if (strncmp(p, QMAKE_SOURCES_SPACE, strlen(QMAKE_SOURCES_SPACE)) == 0 ||
strncmp(p, QMAKE_SOURCES, strlen(QMAKE_SOURCES)) == 0 ||
strncmp(p, QMAKE_CONFIG_SPACE, strlen(QMAKE_CONFIG_SPACE)) == 0 ||
strncmp(p, QMAKE_CONFIG, strlen(QMAKE_CONFIG)) == 0)
return LANG_MAKE; // really QMAKE
}
return LANG_IDL_PVWAVE;
}
const char *disambiguate_st(SourceFile *sourcefile) {
char *p, *pe;
int length;
// Attempt to detect based on file contents.
int found_assignment = 0, found_block_start = 0, found_block_end = 0;
char line[81];
p = ohcount_sourcefile_get_contents(sourcefile);
pe = p;
char *eof = p + ohcount_sourcefile_get_contents_size(sourcefile);
while (pe < eof) {
// Get a line at a time.
while (p < eof && *pe != '\r' && *pe != '\n') pe++;
length = (pe - p <= sizeof(line)) ? pe - p : sizeof(line);
strncpy(line, p, length);
line[length] = '\0';
char *eol = line + strlen(line);
char *line_end = pe;
for (p = line; p < eol; p++) {
if (*p == ':') {
p++;
while (p < eol && (*p == ' ' || *p == '\t')) p++;
if (*p == '=')
found_assignment = 1;
else if (*p == '[')
found_block_start = 1;
} else if (*p == ']' && *(p + 1) == '.') found_block_end = 1;
if (found_assignment && found_block_start && found_block_end)
return LANG_SMALLTALK;
}
// Next line.
pe = line_end;
while (*pe == '\r' || *pe == '\n') pe++;
p = pe;
}
return NULL;
}
int ohcount_is_binary_filename(const char *filename) {
char *p = (char *)filename + strlen(filename);
while (p > filename && *(p - 1) != '.') p--;
if (p > filename) {
struct ExtensionMap *re;
int length = strlen(p);
re = ohcount_hash_language_from_ext(p, length);
if (re) return ISBINARY(re->value);
// Try the lower-case version of this extension.
char lowerext[length];
strncpy(lowerext, p, length);
lowerext[length] = '\0';
for (p = lowerext; p < lowerext + length; p++) *p = tolower(*p);
re = ohcount_hash_language_from_ext(lowerext, length);
if (re) return ISBINARY(re->value);
}
return 0;
}
|