⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 b.c

📁 早期freebsd实现
💻 C
📖 第 1 页 / 共 2 页
字号:
/****************************************************************Copyright (C) AT&T 1993All Rights ReservedPermission to use, copy, modify, and distribute this software andits documentation for any purpose and without fee is herebygranted, provided that the above copyright notice appear in allcopies and that both that the copyright notice and thispermission notice and warranty disclaimer appear in supportingdocumentation, and that the name of AT&T or any of its entitiesnot be used in advertising or publicity pertaining todistribution of the software without specific, written priorpermission.AT&T DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS.IN NO EVENT SHALL AT&T OR ANY OF ITS ENTITIES BE LIABLE FOR ANYSPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGESWHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHERIN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OFTHIS SOFTWARE.****************************************************************//* lasciate ogni speranza, voi ch'entrate. */#define	DEBUG#include <ctype.h>#include <stdio.h>#include <string.h>#include <stdlib.h>#include "awk.h"#include "y.tab.h"#define	HAT	(NCHARS-1)	/* matches ^ in regular expr */				/* NCHARS is 2**n */#define MAXLIN 512#define type(v)		(v)->nobj#define left(v)		(v)->narg[0]#define right(v)	(v)->narg[1]#define parent(v)	(v)->nnext#define LEAF	case CCL: case NCCL: case CHAR: case DOT: case FINAL: case ALL:#define UNARY	case STAR: case PLUS: case QUEST:/* encoding in tree Nodes:	leaf (CCL, NCCL, CHAR, DOT, FINAL, ALL):		left is index, right contains value or pointer to value	unary (STAR, PLUS, QUEST): left is child, right is null	binary (CAT, OR): left and right are children	parent contains pointer to parent*/uchar	chars[MAXLIN];int	setvec[MAXLIN];int	tmpset[MAXLIN];Node	*point[MAXLIN];int	rtok;		/* next token in current re */int	rlxval;uchar	*rlxstr;uchar	*prestr;	/* current position in current re */uchar	*lastre;	/* origin of last re */static	int setcnt;static	int poscnt;uchar	*patbeg;int	patlen;#define	NFA	20	/* cache this many dynamic fa's */fa	*fatab[NFA];int	nfatab	= 0;	/* entries in fatab */fa *makedfa(uchar *s, int anchor)	/* returns dfa for reg expr s */{	int i, use, nuse;	fa *pfa;	if (compile_time)	/* a constant for sure */		return mkdfa(s, anchor);	for (i = 0; i < nfatab; i++)	/* is it there already? */		if (fatab[i]->anchor == anchor && strcmp(fatab[i]->restr,s) == 0) {			fatab[i]->use++;			return fatab[i];	}	pfa = mkdfa(s, anchor);	if (nfatab < NFA) {	/* room for another */		fatab[nfatab] = pfa;		fatab[nfatab]->use = 1;		nfatab++;		return pfa;	}	use = fatab[0]->use;	/* replace least-recently used */	nuse = 0;	for (i = 1; i < nfatab; i++)		if (fatab[i]->use < use) {			use = fatab[i]->use;			nuse = i;		}	freefa(fatab[nuse]);	fatab[nuse] = pfa;	pfa->use = 1;	return pfa;}fa *mkdfa(uchar *s, int anchor)	/* does the real work of making a dfa */				/* anchor = 1 for anchored matches, else 0 */{	Node *p, *p1;	fa *f;	p = reparse(s);	p1 = op2(CAT, op2(STAR, op2(ALL, NIL, NIL), NIL), p);		/* put ALL STAR in front of reg.  exp. */	p1 = op2(CAT, p1, op2(FINAL, NIL, NIL));		/* put FINAL after reg.  exp. */	poscnt = 0;	penter(p1);	/* enter parent pointers and leaf indices */	if ((f = (fa *) calloc(1, sizeof(fa) + poscnt*sizeof(rrow))) == NULL)		overflo("out of space for fa");	f->accept = poscnt-1;	/* penter has computed number of positions in re */	cfoll(f, p1);	/* set up follow sets */	freetr(p1);	if ((f->posns[0] = (int *) calloc(1, *(f->re[0].lfollow)*sizeof(int))) == NULL)			overflo("out of space in makedfa");	if ((f->posns[1] = (int *) calloc(1, sizeof(int))) == NULL)		overflo("out of space in makedfa");	*f->posns[1] = 0;	f->initstat = makeinit(f, anchor);	f->anchor = anchor;	f->restr = tostring(s);	return f;}int makeinit(fa *f, int anchor){	register int i, k;	f->curstat = 2;	f->out[2] = 0;	f->reset = 0;	k = *(f->re[0].lfollow);	xfree(f->posns[2]);				if ((f->posns[2] = (int *) calloc(1, (k+1)*sizeof(int))) == NULL)		overflo("out of space in makeinit");	for (i=0; i<=k; i++) {		(f->posns[2])[i] = (f->re[0].lfollow)[i];	}	if ((f->posns[2])[1] == f->accept)		f->out[2] = 1;	for (i=0; i<NCHARS; i++)		f->gototab[2][i] = 0;	f->curstat = cgoto(f, 2, HAT);	if (anchor) {		*f->posns[2] = k-1;	/* leave out position 0 */		for (i=0; i<k; i++) {			(f->posns[0])[i] = (f->posns[2])[i];		}		f->out[0] = f->out[2];		if (f->curstat != 2)			--(*f->posns[f->curstat]);	}	return f->curstat;}void penter(Node *p)	/* set up parent pointers and leaf indices */{	switch (type(p)) {	LEAF		left(p) = (Node *) poscnt;		if (poscnt >= MAXLIN)			overflo("leaf index overflow in penter");		point[poscnt++] = p;		break;	UNARY		penter(left(p));		parent(left(p)) = p;		break;	case CAT:	case OR:		penter(left(p));		penter(right(p));		parent(left(p)) = p;		parent(right(p)) = p;		break;	default:	/* can't happen */		ERROR "unknown type %d in penter", type(p) FATAL;		break;	}}void freetr(Node *p)	/* free parse tree */{	switch (type(p)) {	LEAF		xfree(p);		break;	UNARY		freetr(left(p));		xfree(p);		break;	case CAT:	case OR:		freetr(left(p));		freetr(right(p));		xfree(p);		break;	default:	/* can't happen */		ERROR "unknown type %d in freetr", type(p) FATAL;		break;	}}/* in the parsing of regular expressions, metacharacters like . have *//* to be seen literally;  \056 is not a metacharacter. */hexstr(char **pp)	/* find and eval hex string at pp, return new p */{	char *p;	int n = 0;	for (p = *pp; isxdigit(*p); p++) {		if (isdigit(*p))			n = 16 * n + *p - '0';		else if (*p >= 'a' && *p <= 'f')			n = 16 * n + *p - 'a' + 10;		else if (*p >= 'A' && *p <= 'F')			n = 16 * n + *p - 'A' + 10;	}	*pp = p;	return n;}#define isoctdigit(c) ((c) >= '0' && (c) <= '8')	/* multiple use of arg */quoted(char **pp)	/* pick up next thing after a \\ */			/* and increment *pp */{	char *p = *pp;	int c;	if ((c = *p++) == 't')		c = '\t';	else if (c == 'n')		c = '\n';	else if (c == 'f')		c = '\f';	else if (c == 'r')		c = '\r';	else if (c == 'b')		c = '\b';	else if (c == '\\')		c = '\\';	else if (c == 'x') {	/* hexadecimal goo follows */		c = hexstr(&p);	} else if (isoctdigit(c)) {	/* \d \dd \ddd */		int n = c - '0';		if (isoctdigit(*p)) {			n = 8 * n + *p++ - '0';			if (isoctdigit(*p))				n = 8 * n + *p++ - '0';		}		c = n;	} /* else */		/* c = c; */	*pp = p;	return c;}uchar *cclenter(uchar *p)	/* add a character class */{	register int i, c, c2;	uchar *op;	op = p;	i = 0;	while ((c = *p++) != 0) {		if (c == '\\') {			c = quoted(&p);		} else if (c == '-' && i > 0 && chars[i-1] != 0) {			if (*p != 0) {				c = chars[i-1];				c2 = *p++;				if (c2 == '\\')					c2 = quoted(&p);				while (c < c2) {					if (i >= MAXLIN-1)						overflo("character class too big");					chars[i++] = ++c;				}				continue;			}		}		if (i >= MAXLIN-1)			overflo("character class too big");		chars[i++] = c;	}	chars[i++] = '\0';	dprintf( ("cclenter: in = |%s|, out = |%s|\n", op, chars) );	xfree(op);	return(tostring(chars));}void overflo(uchar *s){	ERROR "regular expression too big: %.30s...", s FATAL;}void cfoll(fa *f, Node *v)	/* enter follow set of each leaf of vertex v into lfollow[leaf] */{	register int i;	register int *p;	switch (type(v)) {	LEAF		f->re[(int) left(v)].ltype = type(v);		f->re[(int) left(v)].lval = (long) right(v);	/* assumes ptr & long fit */		for (i=0; i<=f->accept; i++)			setvec[i] = 0;		setcnt = 0;		follow(v);	/* computes setvec and setcnt */		if ((p = (int *) calloc(1, (setcnt+1)*sizeof(int))) == NULL)			overflo("out of space building follow set");		f->re[(int) left(v)].lfollow = p;		*p = setcnt;		for (i = f->accept; i >= 0; i--)			if (setvec[i] == 1) *++p = i;		break;	UNARY		cfoll(f,left(v));		break;	case CAT:	case OR:		cfoll(f,left(v));		cfoll(f,right(v));		break;	default:	/* can't happen */		ERROR "unknown type %d in cfoll", type(v) FATAL;	}}first(Node *p)	/* collects initially active leaves of p into setvec */		/* returns 0 or 1 depending on whether p matches empty string */{	register int b;	switch (type(p)) {	LEAF		if (setvec[(int) left(p)] != 1) {			setvec[(int) left(p)] = 1;			setcnt++;		}		if (type(p) == CCL && (*(uchar *) right(p)) == '\0')			return(0);		/* empty CCL */		else return(1);	case PLUS:		if (first(left(p)) == 0) return(0);		return(1);	case STAR:	case QUEST:		first(left(p));		return(0);	case CAT:		if (first(left(p)) == 0 && first(right(p)) == 0) return(0);		return(1);	case OR:		b = first(right(p));		if (first(left(p)) == 0 || b == 0) return(0);		return(1);	}	ERROR "unknown type %d in first", type(p) FATAL;	/* can't happen */	return(-1);}void follow(Node *v)	/* collects leaves that can follow v into setvec */{	Node *p;	if (type(v) == FINAL)		return;	p = parent(v);	switch (type(p)) {	case STAR:	case PLUS:		first(v);		follow(p);		return;	case OR:	case QUEST:

⌨️ 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 + -