/*
- 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
* 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.
*/
char* ossimRegExp::regpiece (int *flagp) {
char* ret;
char op;
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 != '?') {
//RAISE Error, SYM(ossimRegExp), SYM(Empty_Operand),
printf ("ossimRegExp::compile() : *+ operand could be empty.\n");
return 0;
}
*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)) {
//RAISE Error, SYM(ossimRegExp), SYM(Nested_Operand),
printf ("ossimRegExp::compile(): Nested *?+.\n");
return 0;
}
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
* 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.
*/
static char *
regpiece(int *flagp)
{
register char *ret;
register char *op;
register char *next;
int flags;
int len = 0;
ret = regatom(&flags);
if (ret == NULL)
return(NULL);
op = regparse;
if (!ISMULT(op)) {
*flagp = flags;
return(ret);
}
len = CHARLEN(op);
if (!(flags & HASWIDTH) && ((len != 1) || (*op != '?')) )
FAIL("*+ operand could be empty");
*flagp = ((len != 1) || (*op != '+')) ? (WORST | SPSTART) : (WORST | HASWIDTH);
if ((len == 1) && (*op == '*') && (flags & SIMPLE))
reginsert(STAR, ret);
else if ((len == 1) &&
(*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 ((len == 1) && (*op == '+') && (flags & SIMPLE))
reginsert(PLUS, ret);
else if ((len == 1) && (*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 ((len == 1) && (*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 += INCRLEN(len);
if (ISMULT(regparse))
FAIL("nested *?+");
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
* 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.
*/
static char *
regpiece(i4 *flagp)
{
register char *ret;
register char op;
register char *next;
i4 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);
}
CMnext( regparse );
if (ISMULT(*regparse))
_FAIL("nested *?+");
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
* 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.
*/
static char *regpiece( int *flagp )
{
char *ret, op, *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( ERR_RE_EMPTY_OPERAND );
}
*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( ERR_RE_NESTED_OPERAND );
}
return( ret );
}
/*
- regpiece - something followed by possible [*+?]
*
* Note that the branching code sequence used for ? and the general cases 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.
*/
static char *regpiece (int * flagp)
{
register char *ret;
register short op;
register char *nxt;
int flags;
ret = regatom(&flags);
if (ret == (char *) NULL)
return ((char *) NULL);
op = *regparse;
if (!ISMULT(op)) {
*flagp = flags;
return (ret);
}
if (!(flags & HASWIDTH) && op != QMARK)
FAIL("*+ operand could be empty\n");
*flagp = (op != PLUSS) ? (WORST | SPSTART) : (WORST | HASWIDTH);
if (op == ASTERIX && (flags & SIMPLE))
reginsert(STAR, ret);
else if (op == ASTERIX) {
/* 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 == PLUSS && (flags & SIMPLE))
reginsert(PLUS, ret);
else if (op == PLUSS) {
/* Emit x+ as x(&|), where & means "self". */
nxt = regnode(BRANCH); /* Either */
regtail(ret, nxt);
regtail(regnode(BACK), ret); /* loop back */
regtail(nxt, regnode(BRANCH)); /* or */
regtail(ret, regnode(NOTHING)); /* null. */
} else if (op == QMARK) {
/* Emit x? as (x|) */
reginsert(BRANCH, ret); /* Either x */
regtail(ret, regnode(BRANCH)); /* or */
nxt = regnode(NOTHING); /* null. */
regtail(ret, nxt);
regoptail(ret, nxt);
}
regparse++;
if (ISMULT(*regparse))
FAIL("nested *?+\n");
return (ret);
}
TCHAR *CRegExp::regpiece(int *flagp)
{
TCHAR *ret;
TCHAR op;
TCHAR *next;
int flags;
ret = regatom(&flags);
if (ret == NULL)
return(NULL);
op = *regparse;
if (!ISREPN(op)) {
*flagp = flags;
return(ret);
}
if (!(flags&HASWIDTH) && op != _T('?'))
{
TRACE0("*+ operand could be empty\n");
return NULL;
}
switch (op) {
case _T('*'): *flagp = WORST|SPSTART; break;
case _T('+'): *flagp = WORST|SPSTART|HASWIDTH; break;
case _T('?'): *flagp = WORST; break;
}
if (op == _T('*') && (flags&SIMPLE))
reginsert(STAR, ret);
else if (op == _T('*')) {
// 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 == _T('+') && (flags&SIMPLE))
reginsert(PLUS, ret);
else if (op == _T('+')) {
// 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 == _T('?')) {
// 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 (ISREPN(*regparse))
{
TRACE0("nested *?+\n");
return NULL;
}
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
* 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.
*/
static int regpiece(regex_t *preg, int *flagp)
{
int ret;
char op;
int next;
int flags;
int min;
int max;
ret = regatom(preg, &flags);
if (ret == 0)
return 0;
op = *preg->regparse;
if (!ISMULT(op)) {
*flagp = flags;
return(ret);
}
if (!(flags&HASWIDTH) && op != '?') {
preg->err = REG_ERR_OPERAND_COULD_BE_EMPTY;
return 0;
}
/* Handle braces (counted repetition) by expansion */
if (op == '{') {
char *end;
min = strtoul(preg->regparse + 1, &end, 10);
if (end == preg->regparse + 1) {
preg->err = REG_ERR_BAD_COUNT;
return 0;
}
if (*end == '}') {
max = min;
}
else {
preg->regparse = end;
max = strtoul(preg->regparse + 1, &end, 10);
if (*end != '}') {
preg->err = REG_ERR_UNMATCHED_BRACES;
return 0;
}
}
if (end == preg->regparse + 1) {
max = MAX_REP_COUNT;
}
else if (max < min || max >= 100) {
preg->err = REG_ERR_BAD_COUNT;
return 0;
}
if (min >= 100) {
preg->err = REG_ERR_BAD_COUNT;
return 0;
}
preg->regparse = strchr(preg->regparse, '}');
}
else {
min = (op == '+');
max = (op == '?' ? 1 : MAX_REP_COUNT);
}
if (preg->regparse[1] == '?') {
preg->regparse++;
next = reginsert(preg, flags & SIMPLE ? REPMIN : REPXMIN, 5, ret);
}
else {
next = reginsert(preg, flags & SIMPLE ? REP: REPX, 5, ret);
}
preg->program[ret + 2] = max;
preg->program[ret + 3] = min;
preg->program[ret + 4] = 0;
*flagp = (min) ? (WORST|HASWIDTH) : (WORST|SPSTART);
if (!(flags & SIMPLE)) {
int back = regnode(preg, BACK);
regtail(preg, back, ret);
regtail(preg, next, back);
}
preg->regparse++;
if (ISMULT(*preg->regparse)) {
preg->err = REG_ERR_NESTED_COUNT;
return 0;
}
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
* 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.
*/
static char *
regpiece(int *flagp)
{
register char *next;
register char *ret;
register char op;
unsigned char max;
unsigned char min;
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 != '+' && 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 == '{') {
for (min = 0, regparse++ ; *regparse && isdigit(*regparse) ; regparse++) {
min = min * 10 + (*regparse - '0');
}
for (max = 0, regparse++ ; *regparse && isdigit(*regparse) ; regparse++) {
max = max * 10 + (*regparse - '0');
}
reginsert(max, ret);
next = OPERAND(ret);
reginsert(min, ret);
next = OPERAND(next);
reginsert(MINMAX, ret);
regtail(ret, OPERAND(next)); /* MINMAX->next = x */
} 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);
}