From c2587c76f1b416cdbecb979e54941933246bf856 Mon Sep 17 00:00:00 2001 From: Skip Montanaro Date: Tue, 16 Feb 2021 20:14:16 -0600 Subject: starting over --- src/regexp.c | 1948 +++++++++++++++++++++++++++++----------------------------- 1 file changed, 974 insertions(+), 974 deletions(-) (limited to 'src/regexp.c') diff --git a/src/regexp.c b/src/regexp.c index 50ce9b6..ed7756e 100644 --- a/src/regexp.c +++ b/src/regexp.c @@ -2,12 +2,12 @@ Copyright 1991 by Stichting Mathematisch Centrum, Amsterdam, The Netherlands. - All Rights Reserved + All Rights Reserved -Permission to use, copy, modify, and distribute this software and its -documentation for any purpose and without fee is hereby granted, +Permission to use, copy, modify, and distribute this software and its +documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that -both that copyright notice and this permission notice appear in +both that copyright notice and this permission notice appear in supporting documentation, and that the names of Stichting Mathematisch Centrum or CWI not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. @@ -25,50 +25,50 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. /* * regcomp and regexec -- regsub and regerror are elsewhere * - * Copyright (c) 1986 by University of Toronto. - * Written by Henry Spencer. Not derived from licensed software. + * Copyright (c) 1986 by University of Toronto. + * Written by Henry Spencer. Not derived from licensed software. #ifdef MULTILINE - * Changed by Guido van Rossum, CWI, Amsterdam - * for multi-line support. + * Changed by Guido van Rossum, CWI, Amsterdam + * for multi-line support. #endif * - * Permission is granted to anyone to use this software for any - * purpose on any computer system, and to redistribute it freely, - * subject to the following restrictions: + * Permission is granted to anyone to use this software for any + * purpose on any computer system, and to redistribute it freely, + * subject to the following restrictions: * - * 1. The author is not responsible for the consequences of use of - * this software, no matter how awful, even if they arise - * from defects in it. + * 1. The author is not responsible for the consequences of use of + * this software, no matter how awful, even if they arise + * from defects in it. * - * 2. The origin of this software must not be misrepresented, either - * by explicit claim or by omission. + * 2. The origin of this software must not be misrepresented, either + * by explicit claim or by omission. * - * 3. Altered versions must be plainly marked as such, and must not - * be misrepresented as being the original software. + * 3. Altered versions must be plainly marked as such, and must not + * be misrepresented as being the original software. * * Beware that some of this code is subtly aware of the way operator - * precedence is structured in regular expressions. Serious changes in + * precedence is structured in regular expressions. Serious changes in * regular-expression syntax might require a total rethink. */ #include #include "PROTO.h" #include "malloc.h" #undef ANY /* Conflicting identifier defined in malloc.h */ -#include /* XXX Remove if not found */ +#include /* XXX Remove if not found */ #include "regexp.h" #include "regmagic.h" #ifdef MULTILINE /* * Defining MULTILINE turns on the following changes in the semantics: - * 1. The '.' operator matches all characters except a newline. - * 2. The '^' operator matches at the beginning of the string or after - * a newline. (Anchored matches are retried after each newline.) - * 3. The '$' operator matches at the end of the string or before - * a newline. - * 4. A '\' followed by an 'n' matches a newline. (This is an - * unfortunate exception to the rule that '\' followed by a - * character matches that character...) + * 1. The '.' operator matches all characters except a newline. + * 2. The '^' operator matches at the beginning of the string or after + * a newline. (Anchored matches are retried after each newline.) + * 3. The '$' operator matches at the end of the string or before + * a newline. + * 4. A '\' followed by an 'n' matches a newline. (This is an + * unfortunate exception to the rule that '\' followed by a + * character matches that character...) * * Also, there is a new function reglexec(prog, string, offset) * which searches for a match starting at 'string+offset'; @@ -80,91 +80,91 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. /* * The "internal use only" fields in regexp.h are present to pass info from * compile to execute that permits the execute phase to run lots faster on - * simple cases. They are: + * simple cases. They are: * - * regstart char that must begin a match; '\0' if none obvious - * reganch is the match anchored (at beginning-of-line only)? - * regmust string (pointer into program) that match must include, or NULL - * regmlen length of regmust string + * regstart char that must begin a match; '\0' if none obvious + * reganch is the match anchored (at beginning-of-line only)? + * regmust string (pointer into program) that match must include, or NULL + * regmlen length of regmust string * * Regstart and reganch permit very fast decisions on suitable starting points - * for a match, cutting down the work a lot. Regmust permits fast rejection - * of lines that cannot possibly match. The regmust tests are costly enough + * for a match, cutting down the work a lot. Regmust permits fast rejection + * of lines that cannot possibly match. The regmust tests are costly enough * that regcomp() supplies a regmust only if the r.e. contains something * potentially expensive (at present, the only such thing detected is * or + - * at the start of the r.e., which can involve a lot of backup). Regmlen is + * at the start of the r.e., which can involve a lot of backup). Regmlen is * supplied because the test in regexec() needs it and regcomp() is computing * it anyway. */ /* - * Structure for regexp "program". This is essentially a linear encoding + * Structure for regexp "program". This is essentially a linear encoding * of a nondeterministic finite-state machine (aka syntax charts or - * "railroad normal form" in parsing technology). Each node is an opcode - * plus a "next" pointer, possibly plus an operand. "Next" pointers of + * "railroad normal form" in parsing technology). Each node is an opcode + * plus a "next" pointer, possibly plus an operand. "Next" pointers of * all nodes except BRANCH implement concatenation; a "next" pointer with - * a BRANCH on both ends of it is connecting two alternatives. (Here we - * have one of the subtle syntax dependencies: an individual BRANCH (as + * a BRANCH on both ends of it is connecting two alternatives. (Here we + * have one of the subtle syntax dependencies: an individual BRANCH (as * opposed to a collection of them) is never concatenated with anything - * because of operator precedence.) The operand of some types of node is - * a literal string; for others, it is a node leading into a sub-FSM. In + * because of operator precedence.) The operand of some types of node is + * a literal string; for others, it is a node leading into a sub-FSM. In * particular, the operand of a BRANCH node is the first node of the branch. - * (NB this is *not* a tree structure: the tail of the branch connects - * to the thing following the set of BRANCHes.) The opcodes are: + * (NB this is *not* a tree structure: the tail of the branch connects + * to the thing following the set of BRANCHes.) The opcodes are: */ -/* definition number opnd? meaning */ -#define END 0 /* no End of program. */ -#define BOL 1 /* no Match "" at beginning of line. */ -#define EOL 2 /* no Match "" at end of line. */ -#define ANY 3 /* no Match any one character. */ -#define ANYOF 4 /* str Match any character in this string. */ -#define ANYBUT 5 /* str Match any character not in this string. */ -#define BRANCH 6 /* node Match this alternative, or the next... */ -#define BACK 7 /* no Match "", "next" ptr points backward. */ -#define EXACTLY 8 /* str Match this string. */ -#define NOTHING 9 /* no Match empty string. */ -#define STAR 10 /* node Match this (simple) thing 0 or more times. */ -#define PLUS 11 /* node Match this (simple) thing 1 or more times. */ -#define OPEN 20 /* no Mark this point in input as start of #n. */ - /* OPEN+1 is number 1, etc. */ -#define CLOSE 30 /* no Analogous to OPEN. */ +/* definition number opnd? meaning */ +#define END 0 /* no End of program. */ +#define BOL 1 /* no Match "" at beginning of line. */ +#define EOL 2 /* no Match "" at end of line. */ +#define ANY 3 /* no Match any one character. */ +#define ANYOF 4 /* str Match any character in this string. */ +#define ANYBUT 5 /* str Match any character not in this string. */ +#define BRANCH 6 /* node Match this alternative, or the next... */ +#define BACK 7 /* no Match "", "next" ptr points backward. */ +#define EXACTLY 8 /* str Match this string. */ +#define NOTHING 9 /* no Match empty string. */ +#define STAR 10 /* node Match this (simple) thing 0 or more times. */ +#define PLUS 11 /* node Match this (simple) thing 1 or more times. */ +#define OPEN 20 /* no Mark this point in input as start of #n. */ + /* OPEN+1 is number 1, etc. */ +#define CLOSE 30 /* no Analogous to OPEN. */ /* * Opcode notes: * - * BRANCH The set of branches constituting a single choice are hooked - * together with their "next" pointers, since precedence prevents - * anything being concatenated to any individual branch. The - * "next" pointer of the last BRANCH in a choice points to the - * thing following the whole choice. This is also where the - * final "next" pointer of each individual branch points; each - * branch starts with the operand node of a BRANCH node. + * BRANCH The set of branches constituting a single choice are hooked + * together with their "next" pointers, since precedence prevents + * anything being concatenated to any individual branch. The + * "next" pointer of the last BRANCH in a choice points to the + * thing following the whole choice. This is also where the + * final "next" pointer of each individual branch points; each + * branch starts with the operand node of a BRANCH node. * - * BACK Normal "next" pointers all implicitly point forward; BACK - * exists to make loop structures possible. + * BACK Normal "next" pointers all implicitly point forward; BACK + * exists to make loop structures possible. * - * STAR,PLUS '?', and complex '*' and '+', are implemented as circular - * BRANCH structures using BACK. Simple cases (one character - * per match) are implemented with STAR and PLUS for speed - * and to minimize recursive plunges. + * STAR,PLUS '?', and complex '*' and '+', are implemented as circular + * BRANCH structures using BACK. Simple cases (one character + * per match) are implemented with STAR and PLUS for speed + * and to minimize recursive plunges. * - * OPEN,CLOSE ...are numbered at compile time. + * OPEN,CLOSE ...are numbered at compile time. */ /* * A node is one char of opcode followed by two chars of "next" pointer. - * "Next" pointers are stored as two 8-bit pieces, high order first. The + * "Next" pointers are stored as two 8-bit pieces, high order first. The * value is a positive offset from the opcode of the node containing it. - * An operand, if any, simply follows the node. (Note that much of the + * An operand, if any, simply follows the node. (Note that much of the * code generation knows about this implicit relationship.) * * Using two bytes for the "next" pointer is vast overkill for most things, * but allows patterns to get big without disasters. */ -#define OP(p) (*(p)) -#define NEXT(p) (((*((p)+1)&0377)<<8) + (*((p)+2)&0377)) -#define OPERAND(p) ((p) + 3) +#define OP(p) (*(p)) +#define NEXT(p) (((*((p)+1)&0377)<<8) + (*((p)+2)&0377)) +#define OPERAND(p) ((p) + 3) /* * See regmagic.h for one further detail of program structure. @@ -175,40 +175,40 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. * Utility definitions. */ #ifndef CHARBITS -#define UCHARAT(p) ((int)*(unsigned char *)(p)) +#define UCHARAT(p) ((int)*(unsigned char *)(p)) #else -#define UCHARAT(p) ((int)*(p)&CHARBITS) +#define UCHARAT(p) ((int)*(p)&CHARBITS) #endif -#define FAIL(m) { regerror(m); return(NULL); } -#define ISMULT(c) ((c) == '*' || (c) == '+' || (c) == '?') -#define META "^$.[()|?+*\\" +#define FAIL(m) { regerror(m); return(NULL); } +#define ISMULT(c) ((c) == '*' || (c) == '+' || (c) == '?') +#define META "^$.[()|?+*\\" /* * Flags to be passed up and down. */ -#define HASWIDTH 01 /* Known never to match null string. */ -#define SIMPLE 02 /* Simple enough to be STAR/PLUS operand. */ -#define SPSTART 04 /* Starts with * or +. */ -#define WORST 0 /* Worst case. */ +#define HASWIDTH 01 /* Known never to match null string. */ +#define SIMPLE 02 /* Simple enough to be STAR/PLUS operand. */ +#define SPSTART 04 /* Starts with * or +. */ +#define WORST 0 /* Worst case. */ /* * Global work variables for regcomp(). */ -static char *regparse; /* Input-scan pointer. */ -static int regnpar; /* () count. */ +static char *regparse; /* Input-scan pointer. */ +static int regnpar; /* () count. */ static char regdummy; -static char *regcode; /* Code-emit pointer; ®dummy = don't. */ -static long regsize; /* Code size. */ +static char *regcode; /* Code-emit pointer; ®dummy = don't. */ +static long regsize; /* Code size. */ #ifdef MULTILINE -static int regnl; /* '\n' detected. */ +static int regnl; /* '\n' detected. */ #endif /* * Forward declarations for regcomp()'s friends. */ #ifndef STATIC -#define STATIC static +#define STATIC static #endif STATIC char *reg(); STATIC char *regbranch(); @@ -229,11 +229,11 @@ STATIC int strcspn(); * * We can't allocate space until we know how big the compiled form will be, * but we can't compile it (and thus know how big it is) until we've got a - * place to put the code. So we cheat: we compile it twice, once with code + * place to put the code. So we cheat: we compile it twice, once with code * generation turned off and size counting turned on, and once "for real". * This also means that we don't allocate space until we are sure that the * thing really will compile successfully, and we never have to move the - * code and thus invalidate pointers into it. (Note that it has to be in + * code and thus invalidate pointers into it. (Note that it has to be in * one piece because free() must be able to free it all.) * * Beware that the optimization-preparation code in here knows about some @@ -243,85 +243,85 @@ regexp * regcomp(exp) char *exp; { - register regexp *r; - register char *scan; - register char *longest; - register int len; - int flags; - - if (exp == NULL) - FAIL("NULL argument"); - - /* First pass: determine size, legality. */ - regparse = exp; - regnpar = 1; - regsize = 0L; - regcode = ®dummy; + register regexp *r; + register char *scan; + register char *longest; + register int len; + int flags; + + if (exp == NULL) + FAIL("NULL argument"); + + /* First pass: determine size, legality. */ + regparse = exp; + regnpar = 1; + regsize = 0L; + regcode = ®dummy; #ifdef MULTILINE - regnl = 0; + regnl = 0; #endif - regc(MAGIC); - if (reg(0, &flags) == NULL) - return(NULL); - - /* Small enough for pointer-storage convention? */ - if (regsize >= 32767L) /* Probably could be 65535L. */ - FAIL("regexp too big"); - - /* Allocate space. */ - r = (regexp *)malloc(sizeof(regexp) + (unsigned)regsize); - if (r == NULL) - FAIL("out of space"); - - /* Second pass: emit code. */ - regparse = exp; - regnpar = 1; - regcode = r->program; - regc(MAGIC); - if (reg(0, &flags) == NULL) - return(NULL); - - /* Dig out information for optimizations. */ - r->regstart = '\0'; /* Worst-case defaults. */ - r->reganch = 0; - r->regmust = NULL; - r->regmlen = 0; - scan = r->program+1; /* First BRANCH. */ - if (OP(regnext(scan)) == END) { /* Only one top-level choice. */ - scan = OPERAND(scan); - - /* Starting-point info. */ - if (OP(scan) == EXACTLY) - r->regstart = *OPERAND(scan); - else if (OP(scan) == BOL) - r->reganch++; - - /* - * If there's something expensive in the r.e., find the - * longest literal string that must appear and make it the - * regmust. Resolve ties in favor of later strings, since - * the regstart check works with the beginning of the r.e. - * and avoiding duplication strengthens checking. Not a - * strong reason, but sufficient in the absence of others. - */ + regc(MAGIC); + if (reg(0, &flags) == NULL) + return(NULL); + + /* Small enough for pointer-storage convention? */ + if (regsize >= 32767L) /* Probably could be 65535L. */ + FAIL("regexp too big"); + + /* Allocate space. */ + r = (regexp *)malloc(sizeof(regexp) + (unsigned)regsize); + if (r == NULL) + FAIL("out of space"); + + /* Second pass: emit code. */ + regparse = exp; + regnpar = 1; + regcode = r->program; + regc(MAGIC); + if (reg(0, &flags) == NULL) + return(NULL); + + /* Dig out information for optimizations. */ + r->regstart = '\0'; /* Worst-case defaults. */ + r->reganch = 0; + r->regmust = NULL; + r->regmlen = 0; + scan = r->program+1; /* First BRANCH. */ + if (OP(regnext(scan)) == END) { /* Only one top-level choice. */ + scan = OPERAND(scan); + + /* Starting-point info. */ + if (OP(scan) == EXACTLY) + r->regstart = *OPERAND(scan); + else if (OP(scan) == BOL) + r->reganch++; + + /* + * If there's something expensive in the r.e., find the + * longest literal string that must appear and make it the + * regmust. Resolve ties in favor of later strings, since + * the regstart check works with the beginning of the r.e. + * and avoiding duplication strengthens checking. Not a + * strong reason, but sufficient in the absence of others. + */ #ifdef MULTILINE - if ((flags&SPSTART) && !regnl) { + if ((flags&SPSTART) && !regnl) { #else - if (flags&SPSTART) { + if (flags&SPSTART) { #endif - longest = NULL; - len = 0; - for (; scan != NULL; scan = regnext(scan)) - if (OP(scan) == EXACTLY && strlen(OPERAND(scan)) >= len) { - longest = OPERAND(scan); - len = strlen(OPERAND(scan)); - } - r->regmust = longest; - r->regmlen = len; - } - } - - return(r); + longest = NULL; + len = 0; + for (; scan != NULL; scan = regnext(scan)) + if (OP(scan) == EXACTLY && strlen(OPERAND(scan)) >= len) { + longest = OPERAND(scan); + len = strlen(OPERAND(scan)); + } + r->regmust = longest; + r->regmlen = len; + } + } + + return(r); } /* @@ -335,69 +335,69 @@ char *exp; */ static char * reg(paren, flagp) -int paren; /* Parenthesized? */ +int paren; /* Parenthesized? */ int *flagp; { - register char *ret; - register char *br; - register char *ender; - register int parno; - int flags; - - *flagp = HASWIDTH; /* Tentatively. */ - - /* Make an OPEN node, if parenthesized. */ - if (paren) { - if (regnpar >= NSUBEXP) - FAIL("too many ()"); - parno = regnpar; - regnpar++; - ret = regnode(OPEN+parno); - } else - ret = NULL; - - /* Pick up the branches, linking them together. */ - br = regbranch(&flags); - if (br == NULL) - return(NULL); - if (ret != NULL) - regtail(ret, br); /* OPEN -> first. */ - else - ret = br; - if (!(flags&HASWIDTH)) - *flagp &= ~HASWIDTH; - *flagp |= flags&SPSTART; - while (*regparse == '|') { - regparse++; - br = regbranch(&flags); - if (br == NULL) - return(NULL); - regtail(ret, br); /* BRANCH -> BRANCH. */ - if (!(flags&HASWIDTH)) - *flagp &= ~HASWIDTH; - *flagp |= flags&SPSTART; - } - - /* Make a closing node, and hook it on the end. */ - ender = regnode((paren) ? CLOSE+parno : END); - regtail(ret, ender); - - /* Hook the tails of the branches to the closing node. */ - for (br = ret; br != NULL; br = regnext(br)) - regoptail(br, ender); - - /* Check for proper termination. */ - if (paren && *regparse++ != ')') { - FAIL("unmatched ()"); - } else if (!paren && *regparse != '\0') { - if (*regparse == ')') { - FAIL("unmatched ()"); - } else - FAIL("junk on end"); /* "Can't happen". */ - /* NOTREACHED */ - } - - return(ret); + register char *ret; + register char *br; + register char *ender; + register int parno; + int flags; + + *flagp = HASWIDTH; /* Tentatively. */ + + /* Make an OPEN node, if parenthesized. */ + if (paren) { + if (regnpar >= NSUBEXP) + FAIL("too many ()"); + parno = regnpar; + regnpar++; + ret = regnode(OPEN+parno); + } else + ret = NULL; + + /* Pick up the branches, linking them together. */ + br = regbranch(&flags); + if (br == NULL) + return(NULL); + if (ret != NULL) + regtail(ret, br); /* OPEN -> first. */ + else + ret = br; + if (!(flags&HASWIDTH)) + *flagp &= ~HASWIDTH; + *flagp |= flags&SPSTART; + while (*regparse == '|') { + regparse++; + br = regbranch(&flags); + if (br == NULL) + return(NULL); + regtail(ret, br); /* BRANCH -> BRANCH. */ + if (!(flags&HASWIDTH)) + *flagp &= ~HASWIDTH; + *flagp |= flags&SPSTART; + } + + /* Make a closing node, and hook it on the end. */ + ender = regnode((paren) ? CLOSE+parno : END); + regtail(ret, ender); + + /* Hook the tails of the branches to the closing node. */ + for (br = ret; br != NULL; br = regnext(br)) + regoptail(br, ender); + + /* Check for proper termination. */ + if (paren && *regparse++ != ')') { + FAIL("unmatched ()"); + } else if (!paren && *regparse != '\0') { + if (*regparse == ')') { + FAIL("unmatched ()"); + } else + FAIL("junk on end"); /* "Can't happen". */ + /* NOTREACHED */ + } + + return(ret); } /* @@ -409,37 +409,37 @@ static char * regbranch(flagp) int *flagp; { - register char *ret; - register char *chain; - register char *latest; - int flags; - - *flagp = WORST; /* Tentatively. */ - - ret = regnode(BRANCH); - chain = NULL; - while (*regparse != '\0' && *regparse != '|' && *regparse != ')') { - latest = regpiece(&flags); - if (latest == NULL) - return(NULL); - *flagp |= flags&HASWIDTH; - if (chain == NULL) /* First piece. */ - *flagp |= flags&SPSTART; - else - regtail(chain, latest); - chain = latest; - } - if (chain == NULL) /* Loop ran zero times. */ - (void) regnode(NOTHING); - - return(ret); + register char *ret; + register char *chain; + register char *latest; + int flags; + + *flagp = WORST; /* Tentatively. */ + + ret = regnode(BRANCH); + chain = NULL; + while (*regparse != '\0' && *regparse != '|' && *regparse != ')') { + latest = regpiece(&flags); + if (latest == NULL) + return(NULL); + *flagp |= flags&HASWIDTH; + if (chain == NULL) /* First piece. */ + *flagp |= flags&SPSTART; + else + regtail(chain, latest); + chain = latest; + } + if (chain == NULL) /* Loop ran zero times. */ + (void) regnode(NOTHING); + + return(ret); } /* - regpiece - something followed by possible [*+?] * * Note that the branching code sequences used for ? and the general cases - * of * and + are somewhat optimized: they use the same NOTHING node as + * of * and + are somewhat optimized: they use the same NOTHING node as * both the endmarker for their branch list and the body of the last branch. * It might seem that this node could be dispensed with entirely, but the * endmarker role is not redundant. @@ -448,207 +448,207 @@ static char * regpiece(flagp) int *flagp; { - register char *ret; - register char op; - register char *next; - int flags; - - ret = regatom(&flags); - if (ret == NULL) - return(NULL); - - op = *regparse; - if (!ISMULT(op)) { - *flagp = flags; - return(ret); - } - - if (!(flags&HASWIDTH) && op != '?') - FAIL("*+ operand could be empty"); - *flagp = (op != '+') ? (WORST|SPSTART) : (WORST|HASWIDTH); - - if (op == '*' && (flags&SIMPLE)) - reginsert(STAR, ret); - else if (op == '*') { - /* Emit x* as (x&|), where & means "self". */ - reginsert(BRANCH, ret); /* Either x */ - regoptail(ret, regnode(BACK)); /* and loop */ - regoptail(ret, ret); /* back */ - regtail(ret, regnode(BRANCH)); /* or */ - regtail(ret, regnode(NOTHING)); /* null. */ - } else if (op == '+' && (flags&SIMPLE)) - reginsert(PLUS, ret); - else if (op == '+') { - /* Emit x+ as x(&|), where & means "self". */ - next = regnode(BRANCH); /* Either */ - regtail(ret, next); - regtail(regnode(BACK), ret); /* loop back */ - regtail(next, regnode(BRANCH)); /* or */ - regtail(ret, regnode(NOTHING)); /* null. */ - } else if (op == '?') { - /* Emit x? as (x|) */ - reginsert(BRANCH, ret); /* Either x */ - regtail(ret, regnode(BRANCH)); /* or */ - next = regnode(NOTHING); /* null. */ - regtail(ret, next); - regoptail(ret, next); - } - regparse++; - if (ISMULT(*regparse)) - FAIL("nested *?+"); - - return(ret); + register char *ret; + register char op; + register char *next; + int flags; + + ret = regatom(&flags); + if (ret == NULL) + return(NULL); + + op = *regparse; + if (!ISMULT(op)) { + *flagp = flags; + return(ret); + } + + if (!(flags&HASWIDTH) && op != '?') + FAIL("*+ operand could be empty"); + *flagp = (op != '+') ? (WORST|SPSTART) : (WORST|HASWIDTH); + + if (op == '*' && (flags&SIMPLE)) + reginsert(STAR, ret); + else if (op == '*') { + /* Emit x* as (x&|), where & means "self". */ + reginsert(BRANCH, ret); /* Either x */ + regoptail(ret, regnode(BACK)); /* and loop */ + regoptail(ret, ret); /* back */ + regtail(ret, regnode(BRANCH)); /* or */ + regtail(ret, regnode(NOTHING)); /* null. */ + } else if (op == '+' && (flags&SIMPLE)) + reginsert(PLUS, ret); + else if (op == '+') { + /* Emit x+ as x(&|), where & means "self". */ + next = regnode(BRANCH); /* Either */ + regtail(ret, next); + regtail(regnode(BACK), ret); /* loop back */ + regtail(next, regnode(BRANCH)); /* or */ + regtail(ret, regnode(NOTHING)); /* null. */ + } else if (op == '?') { + /* Emit x? as (x|) */ + reginsert(BRANCH, ret); /* Either x */ + regtail(ret, regnode(BRANCH)); /* or */ + next = regnode(NOTHING); /* null. */ + regtail(ret, next); + regoptail(ret, next); + } + regparse++; + if (ISMULT(*regparse)) + FAIL("nested *?+"); + + return(ret); } /* - regatom - the lowest level * - * Optimization: gobbles an entire sequence of ordinary characters so that + * 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 + * 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 '$': - ret = regnode(EOL); - break; - case '.': - ret = regnode(ANY); - *flagp |= HASWIDTH|SIMPLE; - break; - case '[': { - register int class; - register int classend; - - if (*regparse == '^') { /* Complement of range. */ - ret = regnode(ANYBUT); - regparse++; - } else - ret = regnode(ANYOF); - if (*regparse == ']' || *regparse == '-') - regc(*regparse++); - while (*regparse != '\0' && *regparse != ']') { - if (*regparse == '-') { - regparse++; - if (*regparse == ']' || *regparse == '\0') - regc('-'); - else { - class = UCHARAT(regparse-2)+1; - classend = UCHARAT(regparse); - if (class > classend+1) - FAIL("invalid [] range"); - for (; class <= classend; class++) - regc(class); - regparse++; - } - } else - regc(*regparse++); - } - regc('\0'); - if (*regparse != ']') - FAIL("unmatched []"); - regparse++; - *flagp |= HASWIDTH|SIMPLE; - } - break; - case '(': - ret = reg(1, &flags); - if (ret == NULL) - return(NULL); - *flagp |= flags&(HASWIDTH|SPSTART); - break; - case '\0': - case '|': - case ')': - FAIL("internal urp"); /* Supposed to be caught earlier. */ - break; - case '?': - case '+': - case '*': - FAIL("?+* follows nothing"); - break; - case '\\': - if (*regparse == '\0') - FAIL("trailing \\"); - ret = regnode(EXACTLY); + register char *ret; + int flags; + + *flagp = WORST; /* Tentatively. */ + + switch (*regparse++) { + case '^': + ret = regnode(BOL); + break; + case '$': + 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 == NULL) + return(NULL); + *flagp |= flags&(HASWIDTH|SPSTART); + break; + case '\0': + case '|': + case ')': + FAIL("internal urp"); /* Supposed to be caught earlier. */ + break; + case '?': + case '+': + case '*': + FAIL("?+* follows nothing"); + break; + case '\\': + if (*regparse == '\0') + FAIL("trailing \\"); + ret = regnode(EXACTLY); #ifdef MULTILINE - if (*regparse == 'n') { - regc('\n'); - regparse++; - regnl++; - } - else + if (*regparse == 'n') { + regc('\n'); + regparse++; + regnl++; + } + else #endif - 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++); + 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) { #ifdef MULTILINE - if (*regparse == '\n') - regnl++; + if (*regparse == '\n') + regnl++; #endif - regc(*regparse++); - len--; - } - regc('\0'); - } - break; - } - - return(ret); + regc(*regparse++); + len--; + } + regc('\0'); + } + break; + } + + return(ret); } /* - regnode - emit a node */ -static char * /* Location. */ +static char * /* Location. */ 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 "next" pointer. */ - *ptr++ = '\0'; - regcode = ptr; - - return(ret); + register char *ret; + register char *ptr; + + ret = regcode; + if (ret == ®dummy) { + regsize += 3; + return(ret); + } + + ptr = ret; + *ptr++ = op; + *ptr++ = '\0'; /* Null "next" pointer. */ + *ptr++ = '\0'; + regcode = ptr; + + return(ret); } /* @@ -658,10 +658,10 @@ static void regc(b) char b; { - if (regcode != ®dummy) - *regcode++ = b; - else - regsize++; + if (regcode != ®dummy) + *regcode++ = b; + else + regsize++; } /* @@ -674,25 +674,25 @@ 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'; + 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'; } /* @@ -703,28 +703,28 @@ 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 == NULL) - break; - scan = temp; - } - - if (OP(scan) == BACK) - offset = scan - val; - else - offset = val - scan; - *(scan+1) = (offset>>8)&0377; - *(scan+2) = offset&0377; + register char *scan; + register char *temp; + register int offset; + + if (p == ®dummy) + return; + + /* Find last node. */ + scan = p; + for (;;) { + temp = regnext(scan); + if (temp == NULL) + break; + scan = temp; + } + + if (OP(scan) == BACK) + offset = scan - val; + else + offset = val - scan; + *(scan+1) = (offset>>8)&0377; + *(scan+2) = offset&0377; } /* @@ -735,10 +735,10 @@ regoptail(p, val) char *p; char *val; { - /* "Operandless" and "op != BRANCH" are synonymous in practice. */ - if (p == NULL || p == ®dummy || OP(p) != BRANCH) - return; - regtail(OPERAND(p), val); + /* "Operandless" and "op != BRANCH" are synonymous in practice. */ + if (p == NULL || p == ®dummy || OP(p) != BRANCH) + return; + regtail(OPERAND(p), val); } /* @@ -748,10 +748,10 @@ char *val; /* * 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. */ +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. @@ -774,64 +774,64 @@ regexec(prog, string) register regexp *prog; register char *string; { - register char *s; - extern char *strchr(); + register char *s; + extern char *strchr(); - /* Be paranoid... */ - if (prog == NULL || string == NULL) { - regerror("NULL parameter"); - return(0); - } + /* Be paranoid... */ + if (prog == NULL || string == NULL) { + regerror("NULL parameter"); + return(0); + } #ifdef MULTILINE - /* Check for \n in string, and if so, call the more general routine. */ - if (strchr(string, '\n') != NULL) - return reglexec(prog, string, 0); + /* Check for \n in string, and if so, call the more general routine. */ + if (strchr(string, '\n') != NULL) + return reglexec(prog, string, 0); #endif - /* 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 != NULL) { - s = string; - while ((s = strchr(s, prog->regmust[0])) != NULL) { - if (strncmp(s, prog->regmust, prog->regmlen) == 0) - break; /* Found it. */ - s++; - } - if (s == 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)) != 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); + /* 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 != NULL) { + s = string; + while ((s = strchr(s, prog->regmust[0])) != NULL) { + if (strncmp(s, prog->regmust, prog->regmlen) == 0) + break; /* Found it. */ + s++; + } + if (s == 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)) != 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); } #ifdef MULTILINE @@ -843,303 +843,303 @@ reglexec(prog, string, offset) register regexp *prog; register char *string; { - register char *s; - extern char *strchr(); - - /* Be paranoid... */ - if (prog == NULL || string == NULL) { - regerror("NULL parameter"); - return(0); - } - - /* Check validity of program. */ - if (UCHARAT(prog->program) != MAGIC) { - regerror("corrupted program"); - return(0); - } - - /* (Don't look for "must appear" string -- string can be long.) */ - - /* Mark beginning of line for ^ . */ - regbol = string; - - /* Apply offset. - Assume 0 <= offset <= strlen(string), but don't check, - as string can be long. */ - s= string + offset; - - /* Anchored match need be tried only at line starts. */ - if (prog->reganch) { - while (!regtry(prog, s)) { - s = strchr(s, '\n'); - if (s == NULL) - return(0); - s++; - } - return(1); - } - - /* Messy cases: unanchored match. */ - if (prog->regstart != '\0') - /* We know what char it must start with. */ - while ((s = strchr(s, prog->regstart)) != 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); + register char *s; + extern char *strchr(); + + /* Be paranoid... */ + if (prog == NULL || string == NULL) { + regerror("NULL parameter"); + return(0); + } + + /* Check validity of program. */ + if (UCHARAT(prog->program) != MAGIC) { + regerror("corrupted program"); + return(0); + } + + /* (Don't look for "must appear" string -- string can be long.) */ + + /* Mark beginning of line for ^ . */ + regbol = string; + + /* Apply offset. + Assume 0 <= offset <= strlen(string), but don't check, + as string can be long. */ + s= string + offset; + + /* Anchored match need be tried only at line starts. */ + if (prog->reganch) { + while (!regtry(prog, s)) { + s = strchr(s, '\n'); + if (s == NULL) + return(0); + s++; + } + return(1); + } + + /* Messy cases: unanchored match. */ + if (prog->regstart != '\0') + /* We know what char it must start with. */ + while ((s = strchr(s, prog->regstart)) != 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); } #endif /* - regtry - try match at specific point */ -static int /* 0 failure, 1 success */ +static int /* 0 failure, 1 success */ regtry(prog, string) regexp *prog; char *string; { - 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++ = NULL; - *ep++ = NULL; - } - if (regmatch(prog->program + 1)) { - prog->startp[0] = string; - prog->endp[0] = reginput; - return(1); - } else - return(0); + 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++ = NULL; + *ep++ = 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 + * 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 + * 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. */ -static int /* 0 failure, 1 success */ +static int /* 0 failure, 1 success */ regmatch(prog) char *prog; { - register char *scan; /* Current node. */ - char *next; /* Next node. */ - extern char *strchr(); + register char *scan; /* Current node. */ + char *next; /* Next node. */ + extern char *strchr(); - scan = prog; + scan = prog; #ifdef DEBUG - if (scan != NULL && regnarrate) - fprintf(stderr, "%s(\n", regprop(scan)); + if (scan != NULL && regnarrate) + fprintf(stderr, "%s(\n", regprop(scan)); #endif - while (scan != NULL) { + while (scan != NULL) { #ifdef DEBUG - if (regnarrate) - fprintf(stderr, "%s...\n", regprop(scan)); + if (regnarrate) + fprintf(stderr, "%s...\n", regprop(scan)); #endif - next = regnext(scan); + next = regnext(scan); - switch (OP(scan)) { - case BOL: + switch (OP(scan)) { + case BOL: #ifdef MULTILINE - if (!(reginput == regbol || - reginput > regbol && *(reginput-1) == '\n')) + if (!(reginput == regbol || + reginput > regbol && *(reginput-1) == '\n')) #else - if (reginput != regbol) + if (reginput != regbol) #endif - return(0); - break; - case EOL: + return(0); + break; + case EOL: #ifdef MULTILINE - if (*reginput != '\0' && *reginput != '\n') + if (*reginput != '\0' && *reginput != '\n') #else - if (*reginput != '\0') + if (*reginput != '\0') #endif - return(0); - break; - case ANY: + return(0); + break; + case ANY: #ifdef MULTILINE - if (*reginput == '\0' || *reginput == '\n') + if (*reginput == '\0' || *reginput == '\n') #else - if (*reginput == '\0') + if (*reginput == '\0') #endif - 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) == NULL) - return(0); - reginput++; - break; - case ANYBUT: + 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) == NULL) + return(0); + reginput++; + break; + case ANYBUT: #ifdef MULTILINE - if (*reginput == '\0' || *reginput == '\n' || - strchr(OPERAND(scan), *reginput) != NULL) + if (*reginput == '\0' || *reginput == '\n' || + strchr(OPERAND(scan), *reginput) != NULL) #else - if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != NULL) + if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != NULL) #endif - 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(next)) { - /* - * Don't set startp if some later - * invocation of the same parentheses - * already has. - */ - if (regstartp[no] == NULL) - regstartp[no] = save; - return(1); - } else - return(0); - } - break; - case CLOSE+1: - case CLOSE+2: - case CLOSE+3: - case CLOSE+4: - case CLOSE+5: - case CLOSE+6: - case CLOSE+7: - case CLOSE+8: - case CLOSE+9: { - register int no; - register char *save; - - no = OP(scan) - CLOSE; - save = reginput; - - if (regmatch(next)) { - /* - * Don't set endp if some later - * invocation of the same parentheses - * already has. - */ - if (regendp[no] == NULL) - regendp[no] = save; - return(1); - } else - return(0); - } - break; - case BRANCH: { - register char *save; - - if (OP(next) != BRANCH) /* No choice. */ - next = OPERAND(scan); /* Avoid recursion. */ - else { - do { - save = reginput; - if (regmatch(OPERAND(scan))) - return(1); - reginput = save; - scan = regnext(scan); - } while (scan != NULL && OP(scan) == BRANCH); - return(0); - /* NOTREACHED */ - } - } - break; - case STAR: - case PLUS: { - register char nextch; - register int no; - register char *save; - register int min; - - /* - * Lookahead to avoid useless match attempts - * when we know what character comes next. - */ - nextch = '\0'; - if (OP(next) == EXACTLY) - nextch = *OPERAND(next); - min = (OP(scan) == STAR) ? 0 : 1; - save = reginput; - no = regrepeat(OPERAND(scan)); - while (no >= min) { - /* If it could work, try it. */ - if (nextch == '\0' || *reginput == nextch) - if (regmatch(next)) - return(1); - /* Couldn't or didn't -- back up. */ - no--; - reginput = save + no; - } - return(0); - } - break; - case END: - return(1); /* Success! */ - break; - default: - regerror("memory corruption"); - return(0); - break; - } - - scan = next; - } - - /* - * We get here only if there's trouble -- normally "case END" is - * the terminating point. - */ - regerror("corrupted pointers"); - return(0); + 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(next)) { + /* + * Don't set startp if some later + * invocation of the same parentheses + * already has. + */ + if (regstartp[no] == NULL) + regstartp[no] = save; + return(1); + } else + return(0); + } + break; + case CLOSE+1: + case CLOSE+2: + case CLOSE+3: + case CLOSE+4: + case CLOSE+5: + case CLOSE+6: + case CLOSE+7: + case CLOSE+8: + case CLOSE+9: { + register int no; + register char *save; + + no = OP(scan) - CLOSE; + save = reginput; + + if (regmatch(next)) { + /* + * Don't set endp if some later + * invocation of the same parentheses + * already has. + */ + if (regendp[no] == NULL) + regendp[no] = save; + return(1); + } else + return(0); + } + break; + case BRANCH: { + register char *save; + + if (OP(next) != BRANCH) /* No choice. */ + next = OPERAND(scan); /* Avoid recursion. */ + else { + do { + save = reginput; + if (regmatch(OPERAND(scan))) + return(1); + reginput = save; + scan = regnext(scan); + } while (scan != NULL && OP(scan) == BRANCH); + return(0); + /* NOTREACHED */ + } + } + break; + case STAR: + case PLUS: { + register char nextch; + register int no; + register char *save; + register int min; + + /* + * Lookahead to avoid useless match attempts + * when we know what character comes next. + */ + nextch = '\0'; + if (OP(next) == EXACTLY) + nextch = *OPERAND(next); + min = (OP(scan) == STAR) ? 0 : 1; + save = reginput; + no = regrepeat(OPERAND(scan)); + while (no >= min) { + /* If it could work, try it. */ + if (nextch == '\0' || *reginput == nextch) + if (regmatch(next)) + return(1); + /* Couldn't or didn't -- back up. */ + no--; + reginput = save + no; + } + return(0); + } + break; + case END: + return(1); /* Success! */ + break; + default: + regerror("memory corruption"); + return(0); + break; + } + + scan = next; + } + + /* + * We get here only if there's trouble -- normally "case END" is + * the terminating point. + */ + regerror("corrupted pointers"); + return(0); } /* @@ -1149,58 +1149,58 @@ static int regrepeat(p) char *p; { - register int count = 0; - register char *scan; - register char *opnd; + register int count = 0; + register char *scan; + register char *opnd; #ifdef MULTILINE - register char *eol; + register char *eol; #endif - scan = reginput; - opnd = OPERAND(p); - switch (OP(p)) { - case ANY: + scan = reginput; + opnd = OPERAND(p); + switch (OP(p)) { + case ANY: #ifdef MULTILINE - if ((eol = strchr(scan, '\n')) != NULL) { - count += eol - scan; - scan = eol; - break; - } + if ((eol = strchr(scan, '\n')) != NULL) { + count += eol - scan; + scan = eol; + break; + } #endif - count = strlen(scan); - scan += count; - break; - case EXACTLY: - while (*opnd == *scan) { - count++; - scan++; - } - break; - case ANYOF: - while (*scan != '\0' && strchr(opnd, *scan) != NULL) { - count++; - scan++; - } - break; - case ANYBUT: + count = strlen(scan); + scan += count; + break; + case EXACTLY: + while (*opnd == *scan) { + count++; + scan++; + } + break; + case ANYOF: + while (*scan != '\0' && strchr(opnd, *scan) != NULL) { + count++; + scan++; + } + break; + case ANYBUT: #ifdef MULTILINE - while (*scan != '\0' && *scan != '\n' && - strchr(opnd, *scan) == NULL) { + while (*scan != '\0' && *scan != '\n' && + strchr(opnd, *scan) == NULL) { #else - while (*scan != '\0' && strchr(opnd, *scan) == NULL) { + while (*scan != '\0' && strchr(opnd, *scan) == NULL) { #endif - count++; - scan++; - } - break; - default: /* Oh dear. Called inappropriately. */ - regerror("internal foulup"); - count = 0; /* Best compromise. */ - break; - } - reginput = scan; - - return(count); + count++; + scan++; + } + break; + default: /* Oh dear. Called inappropriately. */ + regerror("internal foulup"); + count = 0; /* Best compromise. */ + break; + } + reginput = scan; + + return(count); } /* @@ -1210,19 +1210,19 @@ static char * regnext(p) register char *p; { - register int offset; + register int offset; - if (p == ®dummy) - return(NULL); + if (p == ®dummy) + return(NULL); - offset = NEXT(p); - if (offset == 0) - return(NULL); + offset = NEXT(p); + if (offset == 0) + return(NULL); - if (OP(p) == BACK) - return(p-offset); - else - return(p+offset); + if (OP(p) == BACK) + return(p-offset); + else + return(p+offset); } #ifdef DEBUG @@ -1236,46 +1236,46 @@ void regdump(r) regexp *r; { - register char *s; - register char op = EXACTLY; /* Arbitrary non-END op. */ - register char *next; - extern char *strchr(); - - - s = r->program + 1; - while (op != END) { /* While that wasn't END last time... */ - op = OP(s); - printf("%2d%s", (int)(s-r->program), regprop(s)); /* Where, what. */ - next = regnext(s); - if (next == NULL) /* Next ptr. */ - printf("(0)"); - else - printf("(%d)", (int)((s-r->program)+(next-s))); - s += 3; - if (op == ANYOF || op == ANYBUT || op == EXACTLY) { - /* Literal string, where present. */ - while (*s != '\0') { + register char *s; + register char op = EXACTLY; /* Arbitrary non-END op. */ + register char *next; + extern char *strchr(); + + + s = r->program + 1; + while (op != END) { /* While that wasn't END last time... */ + op = OP(s); + printf("%2d%s", (int)(s-r->program), regprop(s)); /* Where, what. */ + next = regnext(s); + if (next == NULL) /* Next ptr. */ + printf("(0)"); + else + printf("(%d)", (int)((s-r->program)+(next-s))); + s += 3; + if (op == ANYOF || op == ANYBUT || op == EXACTLY) { + /* Literal string, where present. */ + while (*s != '\0') { #ifdef MULTILINE - if (*s == '\n') - printf("\\n"); - else + if (*s == '\n') + printf("\\n"); + else #endif - putchar(*s); - s++; - } - s++; - } - putchar('\n'); - } - - /* Header fields of interest. */ - if (r->regstart != '\0') - printf("start `%c' ", r->regstart); - if (r->reganch) - printf("anchored "); - if (r->regmust != NULL) - printf("must have \"%s\"", r->regmust); - printf("\n"); + putchar(*s); + s++; + } + s++; + } + putchar('\n'); + } + + /* Header fields of interest. */ + if (r->regstart != '\0') + printf("start `%c' ", r->regstart); + if (r->reganch) + printf("anchored "); + if (r->regmust != NULL) + printf("must have \"%s\"", r->regmust); + printf("\n"); } /* @@ -1285,85 +1285,85 @@ static char * regprop(op) char *op; { - register char *p; - static char buf[50]; - - (void) strcpy(buf, ":"); - - switch (OP(op)) { - case BOL: - p = "BOL"; - break; - case EOL: - p = "EOL"; - break; - case ANY: - p = "ANY"; - break; - case ANYOF: - p = "ANYOF"; - break; - case ANYBUT: - p = "ANYBUT"; - break; - case BRANCH: - p = "BRANCH"; - break; - case EXACTLY: - p = "EXACTLY"; - break; - case NOTHING: - p = "NOTHING"; - break; - case BACK: - p = "BACK"; - break; - case END: - p = "END"; - 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: - sprintf(buf+strlen(buf), "OPEN%d", (int)(OP(op)-OPEN)); - p = NULL; - break; - case CLOSE+1: - case CLOSE+2: - case CLOSE+3: - case CLOSE+4: - case CLOSE+5: - case CLOSE+6: - case CLOSE+7: - case CLOSE+8: - case CLOSE+9: - sprintf(buf+strlen(buf), "CLOSE%d", (int)(OP(op)-CLOSE)); - p = NULL; - break; - case STAR: - p = "STAR"; - break; - case PLUS: - p = "PLUS"; - break; - default: - regerror("corrupted opcode"); - break; - } - if (p != NULL) - (void) strcat(buf, p); - return(buf); + register char *p; + static char buf[50]; + + (void) strcpy(buf, ":"); + + switch (OP(op)) { + case BOL: + p = "BOL"; + break; + case EOL: + p = "EOL"; + break; + case ANY: + p = "ANY"; + break; + case ANYOF: + p = "ANYOF"; + break; + case ANYBUT: + p = "ANYBUT"; + break; + case BRANCH: + p = "BRANCH"; + break; + case EXACTLY: + p = "EXACTLY"; + break; + case NOTHING: + p = "NOTHING"; + break; + case BACK: + p = "BACK"; + break; + case END: + p = "END"; + 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: + sprintf(buf+strlen(buf), "OPEN%d", (int)(OP(op)-OPEN)); + p = NULL; + break; + case CLOSE+1: + case CLOSE+2: + case CLOSE+3: + case CLOSE+4: + case CLOSE+5: + case CLOSE+6: + case CLOSE+7: + case CLOSE+8: + case CLOSE+9: + sprintf(buf+strlen(buf), "CLOSE%d", (int)(OP(op)-CLOSE)); + p = NULL; + break; + case STAR: + p = "STAR"; + break; + case PLUS: + p = "PLUS"; + break; + default: + regerror("corrupted opcode"); + break; + } + if (p != NULL) + (void) strcat(buf, p); + return(buf); } #endif /* * The following is provided for those people who do not have strcspn() in - * their C libraries. They should get off their butts and do something + * their C libraries. They should get off their butts and do something * about it; at least one public-domain implementation of those (highly * useful) string routines has been published on Usenet. */ @@ -1378,17 +1378,17 @@ strcspn(s1, s2) char *s1; char *s2; { - register char *scan1; - register char *scan2; - register int count; - - count = 0; - for (scan1 = s1; *scan1 != '\0'; scan1++) { - for (scan2 = s2; *scan2 != '\0';) /* ++ moved down. */ - if (*scan1 == *scan2++) - return(count); - count++; - } - return(count); + register char *scan1; + register char *scan2; + register int count; + + count = 0; + for (scan1 = s1; *scan1 != '\0'; scan1++) { + for (scan2 = s2; *scan2 != '\0';) /* ++ moved down. */ + if (*scan1 == *scan2++) + return(count); + count++; + } + return(count); } #endif -- cgit v1.2.3