📄 regexp.c
字号:
regparse++; if (ISMULT(*regparse)) FAIL("nested *"); return (ret);}/* - regatom - the lowest level * * Optimization: gobbles an entire sequence of ordinary characters so that * it can turn them into a single node, which is smaller to store and * faster to run. Backslashed characters are exceptions, each becoming a * separate node; the code is simpler that way and it's not worth fixing. */static char *regatom(flagp)int *flagp;{ register char *ret; int flags; *flagp = WORST; /* Tentatively. */ switch (*regparse++) { case '^': ret = regnode(BOL); break; case '$': ret = regnode(EOL); break; case '.': ret = regnode(ANY); *flagp |= HASWIDTH | SIMPLE; break; case '[':{ register int class; register int classend; if (*regparse == '^') { /* Complement of range. */ ret = regnode(ANYBUT); regparse++; } else ret = regnode(ANYOF); if (*regparse == ']' || *regparse == '-') regc(*regparse++); while (*regparse != '\0' && *regparse != ']') { if (*regparse == '-') { regparse++; if (*regparse == ']' || *regparse == '\0') regc('-'); else { class = UCHARAT(regparse - 2) + 1; classend = UCHARAT(regparse); if (class > classend + 1) FAIL("invalid [] range"); for (; class <= classend; class++) regc(class); regparse++; } } else regc(*regparse++); } regc('\0'); if (*regparse != ']') FAIL("unmatched []"); regparse++; *flagp |= HASWIDTH | SIMPLE; } break; case '(': ret = reg(1, &flags); if (ret == (char *)NULL) return ((char *)NULL); *flagp |= flags & (HASWIDTH | SPSTART); break; case '\0': case '|': case ')': FAIL("internal urp"); /* Supposed to be caught earlier. */ break; case '*': FAIL("* follows nothing"); break; case '\\': if (*regparse == '\0') FAIL("trailing \\"); ret = regnode(EXACTLY); regc(*regparse++); regc('\0'); *flagp |= HASWIDTH | SIMPLE; break; default:{ register int len; register char ender; regparse--; len = strcspn(regparse, META); if (len <= 0) FAIL("internal disaster"); ender = *(regparse + len); if (len > 1 && ISMULT(ender)) len--; /* Back off clear of * operand. */ *flagp |= HASWIDTH; if (len == 1) *flagp |= SIMPLE; ret = regnode(EXACTLY); while (len > 0) { regc(*regparse++); len--; } regc('\0'); } break; } return (ret);}/* - regnode - emit a node */static char *regnode(op)char op;{ register char *ret; register char *ptr; ret = regcode; if (ret == ®dummy) { regsize += 3; return (ret); } ptr = ret; *ptr++ = op; *ptr++ = '\0'; /* Null "nxt" pointer. */ *ptr++ = '\0'; regcode = ptr; return (ret);}/* - regc - emit (if appropriate) a byte of code */static void regc(b)char b;{ if (regcode != ®dummy) *regcode++ = b; else regsize++;}/* - reginsert - insert an operator in front of already-emitted operand * * Means relocating the operand. */static void reginsert(op, opnd)char op;char *opnd;{ register char *src; register char *dst; register char *place; if (regcode == ®dummy) { regsize += 3; return; } src = regcode; regcode += 3; dst = regcode; while (src > opnd) *--dst = *--src; place = opnd; /* Op node, where operand used to be. */ *place++ = op; *place++ = '\0'; *place++ = '\0';}/* - regtail - set the next-pointer at the end of a node chain */static void regtail(p, val)char *p;char *val;{ register char *scan; register char *temp; register int offset; if (p == ®dummy) return; /* Find last node. */ scan = p; for (;;) { temp = regnext(scan); if (temp == (char *)NULL) break; scan = temp; } if (OP(scan) == BACK) offset = scan - val; else offset = val - scan; *(scan + 1) = (offset >> 8) & 0377; *(scan + 2) = offset & 0377;}/* - regoptail - regtail on operand of first argument; nop if operandless */static void regoptail(p, val)char *p;char *val;{ /* "Operandless" and "op != BRANCH" are synonymous in practice. */ if (p == (char *)NULL || p == ®dummy || OP(p) != BRANCH) return; regtail(OPERAND(p), val);}/* * regexec and friends *//* * Global work variables for regexec(). */static char *reginput; /* String-input pointer. */static char *regbol; /* Beginning of input, for ^ check. */static char **regstartp; /* Pointer to startp array. */static char **regendp; /* Ditto for endp. *//* * Forwards. */STATIC int regtry();STATIC int regmatch();STATIC int regrepeat();#ifdef DEBUGint regnarrate = 0;void regdump();STATIC char *regprop();#endif/* - regexec - match a regexp against a string */int regexec(prog, string)register regexp *prog;register char *string;{ register char *s; /* Be paranoid... */ if (prog == (regexp *)NULL || string == (char *)NULL) { regerror("NULL parameter"); return (0); } /* Check validity of program. */ if (UCHARAT(prog->program) != MAGIC) { regerror("corrupted program"); return (0); } /* If there is a "must appear" string, look for it. */ if (prog->regmust != (char *)NULL) { s = string; while ((s = strchr(s, prog->regmust[0])) != (char *)NULL) { if (strncmp(s, prog->regmust, prog->regmlen) == 0) break; /* Found it. */ s++; } if (s == (char *)NULL) /* Not present. */ return (0); } /* Mark beginning of line for ^ . */ regbol = string; /* Simplest case: anchored match need be tried only once. */ if (prog->reganch) return (regtry(prog, string)); /* Messy cases: unanchored match. */ s = string; if (prog->regstart != '\0') /* We know what char it must start with. */ while ((s = strchr(s, prog->regstart)) != (char *)NULL) { if (regtry(prog, s)) return (1); s++; } else /* We don't -- general case. */ do { if (regtry(prog, s)) return (1); } while (*s++ != '\0'); /* Failure. */ return (0);}/* - regtry - try match at specific point */#ifdef __STDC__static int regtry(regexp *prog, char *string)#elsestatic int regtry(prog, string)regexp *prog;char *string;#endif{ register int i; register char **sp; register char **ep; reginput = string; regstartp = prog->startp; regendp = prog->endp; sp = prog->startp; ep = prog->endp; for (i = NSUBEXP; i > 0; i--) { *sp++ = (char *)NULL; *ep++ = (char *)NULL; } if (regmatch(prog->program + 1)) { prog->startp[0] = string; prog->endp[0] = reginput; return (1); } else return (0);}/* - regmatch - main matching routine * * Conceptually the strategy is simple: check to see whether the current * node matches, call self recursively to see whether the rest matches, * and then act accordingly. In practice we make some effort to avoid * recursion, in particular by going through "ordinary" nodes (that don't * need to know whether the rest of the match failed) by a loop instead of * by recursion. */#ifdef __STDC__static int regmatch(char *prog)#elsestatic int regmatch(prog)char *prog;#endif{ register char *scan; /* Current node. */ char *nxt; /* nxt node. */ scan = prog;#ifdef DEBUG if (scan != (char *)NULL && regnarrate) fprintf(stderr, "%s(\n", regprop(scan));#endif while (scan != (char *)NULL) {#ifdef DEBUG if (regnarrate) fprintf(stderr, "%s...\n", regprop(scan));#endif nxt = regnext(scan); switch (OP(scan)) { case BOL: if (reginput != regbol) return (0); break; case EOL: if (*reginput != '\0') return (0); break; case ANY: if (*reginput == '\0') return (0); reginput++; break; case EXACTLY:{ register int len; register char *opnd; opnd = OPERAND(scan); /* Inline the first character, for speed. */ if (*opnd != *reginput) return (0); len = strlen(opnd); if (len > 1 && strncmp(opnd, reginput, len) != 0) return (0); reginput += len; } break; case ANYOF: if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) == (char *)NULL) return (0); reginput++; break; case ANYBUT: if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != (char *)NULL) return (0); reginput++; break; case NOTHING: break; case BACK: break; case OPEN + 1: case OPEN + 2: case OPEN + 3: case OPEN + 4: case OPEN + 5: case OPEN + 6: case OPEN + 7: case OPEN + 8: case OPEN + 9:{ register int no; register char *save; no = OP(scan) - OPEN; save = reginput; if (regmatch(nxt)) { /* * Don't set startp if some later invocation of the same
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -