/* - bothcases - emit a dualcase version of a two-case character == static void bothcases(struct parse *p, int ch); * * Boy, is this implementation ever a kludge... */ static void bothcases( struct parse *p, int ch) { const char *oldnext; const char *oldend; char bracket[3]; _DIAGASSERT(p != NULL); oldnext = p->next; oldend = p->end; assert(othercase(ch) != ch); /* p_bracket() would recurse */ p->next = bracket; p->end = bracket+2; bracket[0] = ch; bracket[1] = ']'; bracket[2] = '\0'; p_bracket(p); assert(p->next == bracket+2); p->next = oldnext; p->end = oldend; }
/* - ordinary - emit an ordinary character */ static void ordinary(struct parse *p, int ch) { cat_t *cap = p->g->categories; if ((p->g->cflags®_ICASE) && isalpha((uch)ch) && othercase(ch) != ch) bothcases(p, ch); else { EMIT(OCHAR, (uch)ch); if (cap[ch] == 0) cap[ch] = p->g->ncategories++; } }
/* - ordinary - emit an ordinary character == static void ordinary(struct parse *p, int ch); */ static void ordinary( struct parse *p, int ch) { cat_t *cap; _DIAGASSERT(p != NULL); cap = p->g->categories; if ((p->g->cflags®_ICASE) && isalpha((unsigned char) ch) && othercase((unsigned char) ch) != (unsigned char) ch) bothcases(p, (unsigned char) ch); else { EMIT(OCHAR, (unsigned char)ch); if (cap[ch] == 0) cap[ch] = p->g->ncategories++; } }
/* - p_bracket - parse a bracketed character list * * Note a significant property of this code: if the allocset() did SETERROR, * no set operations are done. */ static void p_bracket(struct parse *p) { cset *cs; int invert = 0; /* Dept of Truly Sickening Special-Case Kludges */ if (p->next + 5 < p->end && strncmp(p->next, "[:<:]]", 6) == 0) { EMIT(OBOW, 0); NEXTn(6); return; } if (p->next + 5 < p->end && strncmp(p->next, "[:>:]]", 6) == 0) { EMIT(OEOW, 0); NEXTn(6); return; } if ((cs = allocset(p)) == NULL) { /* allocset did set error status in p */ return; } if (EAT('^')) invert++; /* make note to invert set at end */ if (EAT(']')) CHadd(cs, ']'); else if (EAT('-')) CHadd(cs, '-'); while (MORE() && PEEK() != ']' && !SEETWO('-', ']')) p_b_term(p, cs); if (EAT('-')) CHadd(cs, '-'); MUSTEAT(']', REG_EBRACK); if (p->error != 0) { /* don't mess things up further */ freeset(p, cs); return; } if (p->g->cflags®_ICASE) { int i; int ci; for (i = p->g->csetsize - 1; i >= 0; i--) if (CHIN(cs, i) && isalpha(i)) { ci = othercase(i); if (ci != i) CHadd(cs, ci); } if (cs->multis != NULL) mccase(p, cs); } if (invert) { int i; for (i = p->g->csetsize - 1; i >= 0; i--) if (CHIN(cs, i)) CHsub(cs, i); else CHadd(cs, i); if (p->g->cflags®_NEWLINE) CHsub(cs, '\n'); if (cs->multis != NULL) mcinvert(p, cs); } assert(cs->multis == NULL); /* xxx */ if (nch(p, cs) == 1) { /* optimize singleton sets */ ordinary(p, firstch(p, cs)); freeset(p, cs); } else EMIT(OANYOF, freezeset(p, cs)); }