summaryrefslogtreecommitdiffstats
path: root/RegularExpression.cxx
diff options
context:
space:
mode:
Diffstat (limited to 'RegularExpression.cxx')
-rw-r--r--RegularExpression.cxx1666
1 files changed, 818 insertions, 848 deletions
diff --git a/RegularExpression.cxx b/RegularExpression.cxx
index 22593b4..6d7f832 100644
--- a/RegularExpression.cxx
+++ b/RegularExpression.cxx
@@ -1,14 +1,5 @@
-/*============================================================================
- KWSys - Kitware System Library
- Copyright 2000-2009 Kitware, Inc., Insight Software Consortium
-
- Distributed under the OSI-approved BSD License (the "License");
- see accompanying file Copyright.txt for details.
-
- This software is distributed WITHOUT ANY WARRANTY; without even the
- implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
- See the License for more information.
-============================================================================*/
+/* Distributed under the OSI-approved BSD 3-Clause License. See accompanying
+ file Copyright.txt or https://cmake.org/licensing#kwsys for details. */
//
// Copyright (C) 1991 Texas Instruments Incorporated.
//
@@ -34,30 +25,29 @@
// Work-around CMake dependency scanning limitation. This must
// duplicate the above list of headers.
#if 0
-# include "RegularExpression.hxx.in"
+#include "RegularExpression.hxx.in"
#endif
#include <stdio.h>
#include <string.h>
-namespace KWSYS_NAMESPACE
-{
+namespace KWSYS_NAMESPACE {
// RegularExpression -- Copies the given regular expression.
-RegularExpression::RegularExpression (const RegularExpression& rxp) {
- if ( !rxp.program )
- {
+RegularExpression::RegularExpression(const RegularExpression& rxp)
+{
+ if (!rxp.program) {
this->program = 0;
return;
- }
+ }
int ind;
- this->progsize = rxp.progsize; // Copy regular expression size
- this->program = new char[this->progsize]; // Allocate storage
- for(ind=this->progsize; ind-- != 0;) // Copy regular expresion
+ this->progsize = rxp.progsize; // Copy regular expression size
+ this->program = new char[this->progsize]; // Allocate storage
+ for (ind = this->progsize; ind-- != 0;) // Copy regular expresion
this->program[ind] = rxp.program[ind];
- this->startp[0] = rxp.startp[0]; // Copy pointers into last
- this->endp[0] = rxp.endp[0]; // Successful "find" operation
- this->regmust = rxp.regmust; // Copy field
+ this->startp[0] = rxp.startp[0]; // Copy pointers into last
+ this->endp[0] = rxp.endp[0]; // Successful "find" operation
+ this->regmust = rxp.regmust; // Copy field
if (rxp.regmust != 0) {
char* dum = rxp.program;
ind = 0;
@@ -67,32 +57,30 @@ RegularExpression::RegularExpression (const RegularExpression& rxp) {
}
this->regmust = this->program + ind;
}
- this->regstart = rxp.regstart; // Copy starting index
- this->reganch = rxp.reganch; // Copy remaining private data
- this->regmlen = rxp.regmlen; // Copy remaining private data
+ this->regstart = rxp.regstart; // Copy starting index
+ this->reganch = rxp.reganch; // Copy remaining private data
+ this->regmlen = rxp.regmlen; // Copy remaining private data
}
// operator= -- Copies the given regular expression.
-RegularExpression& RegularExpression::operator= (const RegularExpression& rxp)
+RegularExpression& RegularExpression::operator=(const RegularExpression& rxp)
{
- if(this == &rxp)
- {
+ if (this == &rxp) {
return *this;
- }
- if ( !rxp.program )
- {
+ }
+ if (!rxp.program) {
this->program = 0;
return *this;
- }
+ }
int ind;
- this->progsize = rxp.progsize; // Copy regular expression size
- delete [] this->program;
- this->program = new char[this->progsize]; // Allocate storage
- for(ind=this->progsize; ind-- != 0;) // Copy regular expresion
+ this->progsize = rxp.progsize; // Copy regular expression size
+ delete[] this->program;
+ this->program = new char[this->progsize]; // Allocate storage
+ for (ind = this->progsize; ind-- != 0;) // Copy regular expresion
this->program[ind] = rxp.program[ind];
- this->startp[0] = rxp.startp[0]; // Copy pointers into last
- this->endp[0] = rxp.endp[0]; // Successful "find" operation
- this->regmust = rxp.regmust; // Copy field
+ this->startp[0] = rxp.startp[0]; // Copy pointers into last
+ this->endp[0] = rxp.endp[0]; // Successful "find" operation
+ this->regmust = rxp.regmust; // Copy field
if (rxp.regmust != 0) {
char* dum = rxp.program;
ind = 0;
@@ -102,37 +90,38 @@ RegularExpression& RegularExpression::operator= (const RegularExpression& rxp)
}
this->regmust = this->program + ind;
}
- this->regstart = rxp.regstart; // Copy starting index
- this->reganch = rxp.reganch; // Copy remaining private data
- this->regmlen = rxp.regmlen; // Copy remaining private data
+ this->regstart = rxp.regstart; // Copy starting index
+ this->reganch = rxp.reganch; // Copy remaining private data
+ this->regmlen = rxp.regmlen; // Copy remaining private data
return *this;
}
// operator== -- Returns true if two regular expressions have the same
// compiled program for pattern matching.
-bool RegularExpression::operator== (const RegularExpression& rxp) const {
- if (this != &rxp) { // Same address?
- int ind = this->progsize; // Get regular expression size
- if (ind != rxp.progsize) // If different size regexp
- return false; // Return failure
- while(ind-- != 0) // Else while still characters
- if(this->program[ind] != rxp.program[ind]) // If regexp are different
- return false; // Return failure
+bool RegularExpression::operator==(const RegularExpression& rxp) const
+{
+ if (this != &rxp) { // Same address?
+ int ind = this->progsize; // Get regular expression size
+ if (ind != rxp.progsize) // If different size regexp
+ return false; // Return failure
+ while (ind-- != 0) // Else while still characters
+ if (this->program[ind] != rxp.program[ind]) // If regexp are different
+ return false; // Return failure
}
- return true; // Else same, return success
+ return true; // Else same, return success
}
-
// deep_equal -- Returns true if have the same compiled regular expressions
// and the same start and end pointers.
-bool RegularExpression::deep_equal (const RegularExpression& rxp) const {
+bool RegularExpression::deep_equal(const RegularExpression& rxp) const
+{
int ind = this->progsize; // Get regular expression size
if (ind != rxp.progsize) // If different size regexp
return false; // Return failure
- while(ind-- != 0) // Else while still characters
- if(this->program[ind] != rxp.program[ind]) // If regexp are different
+ while (ind-- != 0) // Else while still characters
+ if (this->program[ind] != rxp.program[ind]) // If regexp are different
return false; // Return failure
return (this->startp[0] == rxp.startp[0] && // Else if same start/end ptrs,
this->endp[0] == rxp.endp[0]); // Return true
@@ -204,26 +193,26 @@ bool RegularExpression::deep_equal (const RegularExpression& rxp) const {
*/
// 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.
+#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.
+#define CLOSE 30 // no Analogous to OPEN.
/*
* Opcode notes:
@@ -258,32 +247,32 @@ bool RegularExpression::deep_equal (const RegularExpression& rxp) const {
* 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)
const unsigned char MAGIC = 0234;
/*
* Utility definitions.
*/
-#define UCHARAT(p) (reinterpret_cast<const unsigned char*>(p))[0]
-
-
-#define FAIL(m) { regerror(m); return(0); }
-#define ISMULT(c) ((c) == '*' || (c) == '+' || (c) == '?')
-#define META "^$.[()|?+*\\"
+#define UCHARAT(p) (reinterpret_cast<const unsigned char*>(p))[0]
+#define FAIL(m) \
+ { \
+ regerror(m); \
+ return (0); \
+ }
+#define ISMULT(c) ((c) == '*' || (c) == '+' || (c) == '?')
+#define META "^$.[()|?+*\\"
/*
* 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.
/////////////////////////////////////////////////////////////////////////
//
@@ -291,15 +280,14 @@ const unsigned char MAGIC = 0234;
//
/////////////////////////////////////////////////////////////////////////
-
/*
* Global work variables for compile().
*/
-static const char* regparse; // Input-scan pointer.
-static int regnpar; // () count.
-static char regdummy;
-static char* regcode; // Code-emit pointer; &regdummy = don't.
-static long regsize; // Code size.
+static const char* regparse; // Input-scan pointer.
+static int regnpar; // () count.
+static char regdummy;
+static char* regcode; // Code-emit pointer; &regdummy = don't.
+static long regsize; // Code size.
/*
* Forward declarations for compile()'s friends.
@@ -307,24 +295,22 @@ static long regsize; // Code size.
// #ifndef static
// #define static static
// #endif
-static char* reg (int, int*);
-static char* regbranch (int*);
-static char* regpiece (int*);
-static char* regatom (int*);
-static char* regnode (char);
-static const char* regnext (const char*);
-static char* regnext (char*);
-static void regc (char);
-static void reginsert (char, char*);
-static void regtail (char*, const char*);
-static void regoptail (char*, const char*);
+static char* reg(int, int*);
+static char* regbranch(int*);
+static char* regpiece(int*);
+static char* regatom(int*);
+static char* regnode(char);
+static const char* regnext(const char*);
+static char* regnext(char*);
+static void regc(char);
+static void reginsert(char, char*);
+static void regtail(char*, const char*);
+static void regoptail(char*, const char*);
#ifdef STRCSPN
-static int strcspn ();
+static int strcspn();
#endif
-
-
/*
* 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
@@ -339,101 +325,100 @@ static int strcspn ();
* of the structure of the compiled regexp.
*/
-
// compile -- compile a regular expression into internal code
// for later pattern matching.
-bool RegularExpression::compile (const char* exp) {
- const char* scan;
- const char* longest;
- size_t len;
- int flags;
+bool RegularExpression::compile(const char* exp)
+{
+ const char* scan;
+ const char* longest;
+ size_t len;
+ int flags;
+
+ if (exp == 0) {
+ // RAISE Error, SYM(RegularExpression), SYM(No_Expr),
+ printf("RegularExpression::compile(): No expression supplied.\n");
+ return false;
+ }
- if (exp == 0) {
- //RAISE Error, SYM(RegularExpression), SYM(No_Expr),
- printf ("RegularExpression::compile(): No expression supplied.\n");
- return false;
- }
+ // First pass: determine size, legality.
+ regparse = exp;
+ regnpar = 1;
+ regsize = 0L;
+ regcode = &regdummy;
+ regc(static_cast<char>(MAGIC));
+ if (!reg(0, &flags)) {
+ printf("RegularExpression::compile(): Error in compile.\n");
+ return false;
+ }
+ this->startp[0] = this->endp[0] = this->searchstring = 0;
- // First pass: determine size, legality.
- regparse = exp;
- regnpar = 1;
- regsize = 0L;
- regcode = &regdummy;
- regc(static_cast<char>(MAGIC));
- if(!reg(0, &flags))
- {
- printf ("RegularExpression::compile(): Error in compile.\n");
- return false;
- }
- this->startp[0] = this->endp[0] = this->searchstring = 0;
+ // Small enough for pointer-storage convention?
+ if (regsize >= 32767L) { // Probably could be 65535L.
+ // RAISE Error, SYM(RegularExpression), SYM(Expr_Too_Big),
+ printf("RegularExpression::compile(): Expression too big.\n");
+ return false;
+ }
- // Small enough for pointer-storage convention?
- if (regsize >= 32767L) { // Probably could be 65535L.
- //RAISE Error, SYM(RegularExpression), SYM(Expr_Too_Big),
- printf ("RegularExpression::compile(): Expression too big.\n");
- return false;
- }
+ // Allocate space.
+ //#ifndef _WIN32
+ if (this->program != 0)
+ delete[] this->program;
+ //#endif
+ this->program = new char[regsize];
+ this->progsize = static_cast<int>(regsize);
+
+ if (this->program == 0) {
+ // RAISE Error, SYM(RegularExpression), SYM(Out_Of_Memory),
+ printf("RegularExpression::compile(): Out of memory.\n");
+ return false;
+ }
- // Allocate space.
-//#ifndef _WIN32
- if (this->program != 0) delete [] this->program;
-//#endif
- this->program = new char[regsize];
- this->progsize = static_cast<int>(regsize);
-
- if (this->program == 0) {
- //RAISE Error, SYM(RegularExpression), SYM(Out_Of_Memory),
- printf ("RegularExpression::compile(): Out of memory.\n");
- return false;
- }
+ // Second pass: emit code.
+ regparse = exp;
+ regnpar = 1;
+ regcode = this->program;
+ regc(static_cast<char>(MAGIC));
+ reg(0, &flags);
+
+ // Dig out information for optimizations.
+ this->regstart = '\0'; // Worst-case defaults.
+ this->reganch = 0;
+ this->regmust = 0;
+ this->regmlen = 0;
+ scan = this->program + 1; // First BRANCH.
+ if (OP(regnext(scan)) == END) { // Only one top-level choice.
+ scan = OPERAND(scan);
+
+ // Starting-point info.
+ if (OP(scan) == EXACTLY)
+ this->regstart = *OPERAND(scan);
+ else if (OP(scan) == BOL)
+ this->reganch++;
- // Second pass: emit code.
- regparse = exp;
- regnpar = 1;
- regcode = this->program;
- regc(static_cast<char>(MAGIC));
- reg(0, &flags);
-
- // Dig out information for optimizations.
- this->regstart = '\0'; // Worst-case defaults.
- this->reganch = 0;
- this->regmust = 0;
- this->regmlen = 0;
- scan = this->program + 1; // First BRANCH.
- if (OP(regnext(scan)) == END) { // Only one top-level choice.
- scan = OPERAND(scan);
-
- // Starting-point info.
- if (OP(scan) == EXACTLY)
- this->regstart = *OPERAND(scan);
- else if (OP(scan) == BOL)
- this->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.
- //
- if (flags & SPSTART) {
- longest = 0;
- len = 0;
- for (; scan != 0; scan = regnext(scan))
- if (OP(scan) == EXACTLY && strlen(OPERAND(scan)) >= len) {
- longest = OPERAND(scan);
- len = strlen(OPERAND(scan));
- }
- this->regmust = longest;
- this->regmlen = len;
+ //
+ // 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.
+ //
+ if (flags & SPSTART) {
+ longest = 0;
+ len = 0;
+ for (; scan != 0; scan = regnext(scan))
+ if (OP(scan) == EXACTLY && strlen(OPERAND(scan)) >= len) {
+ longest = OPERAND(scan);
+ len = strlen(OPERAND(scan));
}
+ this->regmust = longest;
+ this->regmlen = len;
}
- return true;
+ }
+ return true;
}
-
/*
- reg - regular expression, i.e. main body or parenthesized thing
*
@@ -443,115 +428,112 @@ bool RegularExpression::compile (const char* exp) {
* is a trifle forced, but the need to tie the tails of the branches to what
* follows makes it hard to avoid.
*/
-static char* reg (int paren, int *flagp) {
- char* ret;
- char* br;
- char* ender;
- int parno =0;
- int flags;
-
- *flagp = HASWIDTH; // Tentatively.
-
- // Make an OPEN node, if parenthesized.
- if (paren) {
- if (regnpar >= RegularExpression::NSUBEXP) {
- //RAISE Error, SYM(RegularExpression), SYM(Too_Many_Parens),
- printf ("RegularExpression::compile(): Too many parentheses.\n");
- return 0;
- }
- parno = regnpar;
- regnpar++;
- ret = regnode(static_cast<char>(OPEN + parno));
+static char* reg(int paren, int* flagp)
+{
+ char* ret;
+ char* br;
+ char* ender;
+ int parno = 0;
+ int flags;
+
+ *flagp = HASWIDTH; // Tentatively.
+
+ // Make an OPEN node, if parenthesized.
+ if (paren) {
+ if (regnpar >= RegularExpression::NSUBEXP) {
+ // RAISE Error, SYM(RegularExpression), SYM(Too_Many_Parens),
+ printf("RegularExpression::compile(): Too many parentheses.\n");
+ return 0;
}
- else
- ret = 0;
-
- // Pick up the branches, linking them together.
+ parno = regnpar;
+ regnpar++;
+ ret = regnode(static_cast<char>(OPEN + parno));
+ } else
+ ret = 0;
+
+ // Pick up the branches, linking them together.
+ br = regbranch(&flags);
+ if (br == 0)
+ return (0);
+ if (ret != 0)
+ regtail(ret, br); // OPEN -> first.
+ else
+ ret = br;
+ if (!(flags & HASWIDTH))
+ *flagp &= ~HASWIDTH;
+ *flagp |= flags & SPSTART;
+ while (*regparse == '|') {
+ regparse++;
br = regbranch(&flags);
if (br == 0)
- return (0);
- if (ret != 0)
- regtail(ret, br); // OPEN -> first.
- else
- ret = br;
+ return (0);
+ regtail(ret, br); // BRANCH -> BRANCH.
if (!(flags & HASWIDTH))
- *flagp &= ~HASWIDTH;
+ *flagp &= ~HASWIDTH;
*flagp |= flags & SPSTART;
- while (*regparse == '|') {
- regparse++;
- br = regbranch(&flags);
- if (br == 0)
- return (0);
- 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(static_cast<char>((paren) ? CLOSE + parno : END));
- regtail(ret, ender);
-
- // Hook the tails of the branches to the closing node.
- for (br = ret; br != 0; br = regnext(br))
- regoptail(br, ender);
+ }
- // Check for proper termination.
- if (paren && *regparse++ != ')') {
- //RAISE Error, SYM(RegularExpression), SYM(Unmatched_Parens),
- printf ("RegularExpression::compile(): Unmatched parentheses.\n");
- return 0;
- }
- else if (!paren && *regparse != '\0') {
- if (*regparse == ')') {
- //RAISE Error, SYM(RegularExpression), SYM(Unmatched_Parens),
- printf ("RegularExpression::compile(): Unmatched parentheses.\n");
- return 0;
- }
- else {
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::compile(): Internal error.\n");
- return 0;
- }
- // NOTREACHED
+ // Make a closing node, and hook it on the end.
+ ender = regnode(static_cast<char>((paren) ? CLOSE + parno : END));
+ regtail(ret, ender);
+
+ // Hook the tails of the branches to the closing node.
+ for (br = ret; br != 0; br = regnext(br))
+ regoptail(br, ender);
+
+ // Check for proper termination.
+ if (paren && *regparse++ != ')') {
+ // RAISE Error, SYM(RegularExpression), SYM(Unmatched_Parens),
+ printf("RegularExpression::compile(): Unmatched parentheses.\n");
+ return 0;
+ } else if (!paren && *regparse != '\0') {
+ if (*regparse == ')') {
+ // RAISE Error, SYM(RegularExpression), SYM(Unmatched_Parens),
+ printf("RegularExpression::compile(): Unmatched parentheses.\n");
+ return 0;
+ } else {
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf("RegularExpression::compile(): Internal error.\n");
+ return 0;
}
- return (ret);
+ // NOTREACHED
+ }
+ return (ret);
}
-
/*
- regbranch - one alternative of an | operator
*
* Implements the concatenation operator.
*/
-static char* regbranch (int *flagp) {
- char* ret;
- char* chain;
- char* latest;
- int flags;
-
- *flagp = WORST; // Tentatively.
-
- ret = regnode(BRANCH);
- chain = 0;
- while (*regparse != '\0' && *regparse != '|' && *regparse != ')') {
- latest = regpiece(&flags);
- if (latest == 0)
- return (0);
- *flagp |= flags & HASWIDTH;
- if (chain == 0) // First piece.
- *flagp |= flags & SPSTART;
- else
- regtail(chain, latest);
- chain = latest;
- }
- if (chain == 0) // Loop ran zero times.
- regnode(NOTHING);
+static char* regbranch(int* flagp)
+{
+ char* ret;
+ char* chain;
+ char* latest;
+ int flags;
+
+ *flagp = WORST; // Tentatively.
+
+ ret = regnode(BRANCH);
+ chain = 0;
+ while (*regparse != '\0' && *regparse != '|' && *regparse != ')') {
+ latest = regpiece(&flags);
+ if (latest == 0)
+ return (0);
+ *flagp |= flags & HASWIDTH;
+ if (chain == 0) // First piece.
+ *flagp |= flags & SPSTART;
+ else
+ regtail(chain, latest);
+ chain = latest;
+ }
+ if (chain == 0) // Loop ran zero times.
+ regnode(NOTHING);
- return (ret);
+ return (ret);
}
-
/*
- regpiece - something followed by possible [*+?]
*
@@ -561,66 +543,64 @@ static char* regbranch (int *flagp) {
* 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;
- char op;
- char* next;
- int flags;
-
- ret = regatom(&flags);
- if (ret == 0)
- return (0);
+static char* regpiece(int* flagp)
+{
+ char* ret;
+ char op;
+ char* next;
+ int flags;
- op = *regparse;
- if (!ISMULT(op)) {
- *flagp = flags;
- return (ret);
- }
+ ret = regatom(&flags);
+ if (ret == 0)
+ return (0);
- if (!(flags & HASWIDTH) && op != '?') {
- //RAISE Error, SYM(RegularExpression), SYM(Empty_Operand),
- printf ("RegularExpression::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(RegularExpression), SYM(Nested_Operand),
- printf ("RegularExpression::compile(): Nested *?+.\n");
- return 0;
- }
+ op = *regparse;
+ if (!ISMULT(op)) {
+ *flagp = flags;
return (ret);
-}
+ }
+ if (!(flags & HASWIDTH) && op != '?') {
+ // RAISE Error, SYM(RegularExpression), SYM(Empty_Operand),
+ printf("RegularExpression::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(RegularExpression), SYM(Nested_Operand),
+ printf("RegularExpression::compile(): Nested *?+.\n");
+ return 0;
+ }
+ return (ret);
+}
/*
- regatom - the lowest level
@@ -630,349 +610,340 @@ static char* regpiece (int *flagp) {
* 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 (int *flagp) {
- 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 '[':{
- int rxpclass;
- int rxpclassend;
-
- 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 {
- rxpclass = UCHARAT(regparse - 2) + 1;
- rxpclassend = UCHARAT(regparse);
- if (rxpclass > rxpclassend + 1) {
- //RAISE Error, SYM(RegularExpression), SYM(Invalid_Range),
- printf ("RegularExpression::compile(): Invalid range in [].\n");
- return 0;
- }
- for (; rxpclass <= rxpclassend; rxpclass++)
- regc(static_cast<char>(rxpclass));
- regparse++;
- }
- }
- else
- regc(*regparse++);
- }
- regc('\0');
- if (*regparse != ']') {
- //RAISE Error, SYM(RegularExpression), SYM(Unmatched_Bracket),
- printf ("RegularExpression::compile(): Unmatched [].\n");
- return 0;
- }
- regparse++;
- *flagp |= HASWIDTH | SIMPLE;
- }
- break;
- case '(':
- ret = reg(1, &flags);
- if (ret == 0)
- return (0);
- *flagp |= flags & (HASWIDTH | SPSTART);
- break;
- case '\0':
- case '|':
- case ')':
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::compile(): Internal error.\n"); // Never here
- return 0;
- case '?':
- case '+':
- case '*':
- //RAISE Error, SYM(RegularExpression), SYM(No_Operand),
- printf ("RegularExpression::compile(): ?+* follows nothing.\n");
- return 0;
- case '\\':
- if (*regparse == '\0') {
- //RAISE Error, SYM(RegularExpression), SYM(Trailing_Backslash),
- printf ("RegularExpression::compile(): Trailing backslash.\n");
- return 0;
- }
- ret = regnode(EXACTLY);
- regc(*regparse++);
- regc('\0');
- *flagp |= HASWIDTH | SIMPLE;
- break;
- default:{
- int len;
- char ender;
-
- regparse--;
- len = int(strcspn(regparse, META));
- if (len <= 0) {
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::compile(): Internal error.\n");
- return 0;
- }
- 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');
+static char* regatom(int* flagp)
+{
+ 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 '[': {
+ int rxpclass;
+ int rxpclassend;
+
+ 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 {
+ rxpclass = UCHARAT(regparse - 2) + 1;
+ rxpclassend = UCHARAT(regparse);
+ if (rxpclass > rxpclassend + 1) {
+ // RAISE Error, SYM(RegularExpression), SYM(Invalid_Range),
+ printf("RegularExpression::compile(): Invalid range in [].\n");
+ return 0;
}
- break;
- }
- return (ret);
+ for (; rxpclass <= rxpclassend; rxpclass++)
+ regc(static_cast<char>(rxpclass));
+ regparse++;
+ }
+ } else
+ regc(*regparse++);
+ }
+ regc('\0');
+ if (*regparse != ']') {
+ // RAISE Error, SYM(RegularExpression), SYM(Unmatched_Bracket),
+ printf("RegularExpression::compile(): Unmatched [].\n");
+ return 0;
+ }
+ regparse++;
+ *flagp |= HASWIDTH | SIMPLE;
+ } break;
+ case '(':
+ ret = reg(1, &flags);
+ if (ret == 0)
+ return (0);
+ *flagp |= flags & (HASWIDTH | SPSTART);
+ break;
+ case '\0':
+ case '|':
+ case ')':
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf("RegularExpression::compile(): Internal error.\n"); // Never here
+ return 0;
+ case '?':
+ case '+':
+ case '*':
+ // RAISE Error, SYM(RegularExpression), SYM(No_Operand),
+ printf("RegularExpression::compile(): ?+* follows nothing.\n");
+ return 0;
+ case '\\':
+ if (*regparse == '\0') {
+ // RAISE Error, SYM(RegularExpression), SYM(Trailing_Backslash),
+ printf("RegularExpression::compile(): Trailing backslash.\n");
+ return 0;
+ }
+ ret = regnode(EXACTLY);
+ regc(*regparse++);
+ regc('\0');
+ *flagp |= HASWIDTH | SIMPLE;
+ break;
+ default: {
+ int len;
+ char ender;
+
+ regparse--;
+ len = int(strcspn(regparse, META));
+ if (len <= 0) {
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf("RegularExpression::compile(): Internal error.\n");
+ return 0;
+ }
+ 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
Location.
*/
-static char* regnode (char op) {
- char* ret;
- char* ptr;
-
- ret = regcode;
- if (ret == &regdummy) {
- regsize += 3;
- return (ret);
- }
-
- ptr = ret;
- *ptr++ = op;
- *ptr++ = '\0'; // Null "next" pointer.
- *ptr++ = '\0';
- regcode = ptr;
+static char* regnode(char op)
+{
+ char* ret;
+ char* ptr;
+ ret = regcode;
+ if (ret == &regdummy) {
+ regsize += 3;
return (ret);
-}
+ }
+ ptr = ret;
+ *ptr++ = op;
+ *ptr++ = '\0'; // Null "next" pointer.
+ *ptr++ = '\0';
+ regcode = ptr;
+
+ return (ret);
+}
/*
- regc - emit (if appropriate) a byte of code
*/
-static void regc (char b) {
- if (regcode != &regdummy)
- *regcode++ = b;
- else
- regsize++;
+static void regc(char b)
+{
+ if (regcode != &regdummy)
+ *regcode++ = b;
+ else
+ regsize++;
}
-
/*
- reginsert - insert an operator in front of already-emitted operand
*
* Means relocating the operand.
*/
-static void reginsert (char op, char* opnd) {
- char* src;
- char* dst;
- char* place;
-
- if (regcode == &regdummy) {
- regsize += 3;
- return;
- }
+static void reginsert(char op, char* opnd)
+{
+ char* src;
+ char* dst;
+ char* place;
+
+ if (regcode == &regdummy) {
+ regsize += 3;
+ return;
+ }
- src = regcode;
- regcode += 3;
- dst = regcode;
- while (src > opnd)
- *--dst = *--src;
+ 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';
+ 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 (char* p, const char* val) {
- char* scan;
- char* temp;
- int offset;
-
- if (p == &regdummy)
- return;
-
- // Find last node.
- scan = p;
- for (;;) {
- temp = regnext(scan);
- if (temp == 0)
- break;
- scan = temp;
- }
+static void regtail(char* p, const char* val)
+{
+ char* scan;
+ char* temp;
+ int offset;
- if (OP(scan) == BACK)
- offset = int(scan - val);
- else
- offset = int(val - scan);
- *(scan + 1) = static_cast<char>((offset >> 8) & 0377);
- *(scan + 2) = static_cast<char>(offset & 0377);
-}
+ if (p == &regdummy)
+ return;
+
+ // Find last node.
+ scan = p;
+ for (;;) {
+ temp = regnext(scan);
+ if (temp == 0)
+ break;
+ scan = temp;
+ }
+ if (OP(scan) == BACK)
+ offset = int(scan - val);
+ else
+ offset = int(val - scan);
+ *(scan + 1) = static_cast<char>((offset >> 8) & 0377);
+ *(scan + 2) = static_cast<char>(offset & 0377);
+}
/*
- regoptail - regtail on operand of first argument; nop if operandless
*/
-static void regoptail (char* p, const char* val) {
- // "Operandless" and "op != BRANCH" are synonymous in practice.
- if (p == 0 || p == &regdummy || OP(p) != BRANCH)
- return;
- regtail(OPERAND(p), val);
+static void regoptail(char* p, const char* val)
+{
+ // "Operandless" and "op != BRANCH" are synonymous in practice.
+ if (p == 0 || p == &regdummy || OP(p) != BRANCH)
+ return;
+ regtail(OPERAND(p), val);
}
-
-
////////////////////////////////////////////////////////////////////////
-//
+//
// find and friends
-//
+//
////////////////////////////////////////////////////////////////////////
-
/*
* Global work variables for find().
*/
-static const char* reginput; // String-input pointer.
-static const char* regbol; // Beginning of input, for ^ check.
-static const char* *regstartp; // Pointer to startp array.
-static const char* *regendp; // Ditto for endp.
+static const char* reginput; // String-input pointer.
+static const char* regbol; // Beginning of input, for ^ check.
+static const char** regstartp; // Pointer to startp array.
+static const char** regendp; // Ditto for endp.
/*
* Forwards.
*/
-static int regtry (const char*, const char* *,
- const char* *, const char*);
-static int regmatch (const char*);
-static int regrepeat (const char*);
+static int regtry(const char*, const char**, const char**, const char*);
+static int regmatch(const char*);
+static int regrepeat(const char*);
#ifdef DEBUG
-int regnarrate = 0;
-void regdump ();
-static char* regprop ();
+int regnarrate = 0;
+void regdump();
+static char* regprop();
#endif
// find -- Matches the regular expression to the given string.
// Returns true if found, and sets start and end indexes accordingly.
-bool RegularExpression::find (const char* string) {
- const char* s;
+bool RegularExpression::find(const char* string)
+{
+ const char* s;
- this->searchstring = string;
+ this->searchstring = string;
- if (!this->program)
- {
- return false;
- }
+ if (!this->program) {
+ return false;
+ }
- // Check validity of program.
- if (UCHARAT(this->program) != MAGIC) {
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::find(): Compiled regular expression corrupted.\n");
- return 0;
- }
+ // Check validity of program.
+ if (UCHARAT(this->program) != MAGIC) {
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf(
+ "RegularExpression::find(): Compiled regular expression corrupted.\n");
+ return 0;
+ }
- // If there is a "must appear" string, look for it.
- if (this->regmust != 0) {
- s = string;
- while ((s = strchr(s, this->regmust[0])) != 0) {
- if (strncmp(s, this->regmust, this->regmlen) == 0)
- break; // Found it.
- s++;
- }
- if (s == 0) // Not present.
- return (0);
+ // If there is a "must appear" string, look for it.
+ if (this->regmust != 0) {
+ s = string;
+ while ((s = strchr(s, this->regmust[0])) != 0) {
+ if (strncmp(s, this->regmust, this->regmlen) == 0)
+ break; // Found it.
+ s++;
}
+ if (s == 0) // Not present.
+ return (0);
+ }
- // Mark beginning of line for ^ .
- regbol = string;
-
- // Simplest case: anchored match need be tried only once.
- if (this->reganch)
- return (regtry(string, this->startp, this->endp, this->program) != 0);
+ // Mark beginning of line for ^ .
+ regbol = string;
- // Messy cases: unanchored match.
- s = string;
- if (this->regstart != '\0')
- // We know what char it must start with.
- while ((s = strchr(s, this->regstart)) != 0) {
- if (regtry(s, this->startp, this->endp, this->program))
- return (1);
- s++;
+ // Simplest case: anchored match need be tried only once.
+ if (this->reganch)
+ return (regtry(string, this->startp, this->endp, this->program) != 0);
- }
- else
- // We don't -- general case.
- do {
- if (regtry(s, this->startp, this->endp, this->program))
- return (1);
- } while (*s++ != '\0');
+ // Messy cases: unanchored match.
+ s = string;
+ if (this->regstart != '\0')
+ // We know what char it must start with.
+ while ((s = strchr(s, this->regstart)) != 0) {
+ if (regtry(s, this->startp, this->endp, this->program))
+ return (1);
+ s++;
+ }
+ else
+ // We don't -- general case.
+ do {
+ if (regtry(s, this->startp, this->endp, this->program))
+ return (1);
+ } while (*s++ != '\0');
- // Failure.
- return (0);
+ // Failure.
+ return (0);
}
-
/*
- regtry - try match at specific point
0 failure, 1 success
*/
-static int regtry (const char* string, const char* *start,
- const char* *end, const char* prog) {
- int i;
- const char* *sp1;
- const char* *ep;
-
- reginput = string;
- regstartp = start;
- regendp = end;
-
- sp1 = start;
- ep = end;
- for (i = RegularExpression::NSUBEXP; i > 0; i--) {
- *sp1++ = 0;
- *ep++ = 0;
- }
- if (regmatch(prog + 1)) {
- start[0] = string;
- end[0] = reginput;
- return (1);
- }
- else
- return (0);
+static int regtry(const char* string, const char** start, const char** end,
+ const char* prog)
+{
+ int i;
+ const char** sp1;
+ const char** ep;
+
+ reginput = string;
+ regstartp = start;
+ regendp = end;
+
+ sp1 = start;
+ ep = end;
+ for (i = RegularExpression::NSUBEXP; i > 0; i--) {
+ *sp1++ = 0;
+ *ep++ = 0;
+ }
+ if (regmatch(prog + 1)) {
+ start[0] = string;
+ end[0] = reginput;
+ return (1);
+ } else
+ return (0);
}
-
/*
- regmatch - main matching routine
*
@@ -984,261 +955,260 @@ static int regtry (const char* string, const char* *start,
* by recursion.
* 0 failure, 1 success
*/
-static int regmatch (const char* prog) {
- const char* scan; // Current node.
- const char* next; // Next node.
-
- scan = prog;
-
- while (scan != 0) {
-
- next = 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:{
- size_t len;
- const 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) == 0)
- return (0);
- reginput++;
- break;
- case ANYBUT:
- if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != 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:{
- int no;
- const 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] == 0)
- 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:{
- int no;
- const 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] == 0)
- regendp[no] = save;
- return (1);
- }
- else
- return (0);
- }
-// break;
- case BRANCH:{
-
- const 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 != 0 && OP(scan) == BRANCH);
- return (0);
- // NOTREACHED
- }
- }
- break;
- case STAR:
- case PLUS:{
- char nextch;
- int no;
- const char* save;
- int min_no;
-
- //
- // Lookahead to avoid useless match attempts when we know
- // what character comes next.
- //
- nextch = '\0';
- if (OP(next) == EXACTLY)
- nextch = *OPERAND(next);
- min_no = (OP(scan) == STAR) ? 0 : 1;
- save = reginput;
- no = regrepeat(OPERAND(scan));
- while (no >= min_no) {
- // 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!
-
- default:
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::find(): Internal error -- memory corrupted.\n");
- return 0;
+static int regmatch(const char* prog)
+{
+ const char* scan; // Current node.
+ const char* next; // Next node.
+
+ scan = prog;
+
+ while (scan != 0) {
+
+ next = 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: {
+ size_t len;
+ const 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) == 0)
+ return (0);
+ reginput++;
+ break;
+ case ANYBUT:
+ if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != 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: {
+ int no;
+ const 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] == 0)
+ 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: {
+ int no;
+ const 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] == 0)
+ regendp[no] = save;
+ return (1);
+ } else
+ return (0);
+ }
+ // break;
+ case BRANCH: {
+
+ const 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 != 0 && OP(scan) == BRANCH);
+ return (0);
+ // NOTREACHED
+ }
+ } break;
+ case STAR:
+ case PLUS: {
+ char nextch;
+ int no;
+ const char* save;
+ int min_no;
+
+ //
+ // Lookahead to avoid useless match attempts when we know
+ // what character comes next.
+ //
+ nextch = '\0';
+ if (OP(next) == EXACTLY)
+ nextch = *OPERAND(next);
+ min_no = (OP(scan) == STAR) ? 0 : 1;
+ save = reginput;
+ no = regrepeat(OPERAND(scan));
+ while (no >= min_no) {
+ // 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;
}
- scan = next;
+ return (0);
+ }
+ // break;
+ case END:
+ return (1); // Success!
+
+ default:
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf(
+ "RegularExpression::find(): Internal error -- memory corrupted.\n");
+ return 0;
}
+ scan = next;
+ }
- //
- // We get here only if there's trouble -- normally "case END" is the
- // terminating point.
- //
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("RegularExpression::find(): Internal error -- corrupted pointers.\n");
- return (0);
+ //
+ // We get here only if there's trouble -- normally "case END" is the
+ // terminating point.
+ //
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf("RegularExpression::find(): Internal error -- corrupted pointers.\n");
+ return (0);
}
-
/*
- regrepeat - repeatedly match something simple, report how many
*/
-static int regrepeat (const char* p) {
- int count = 0;
- const char* scan;
- const char* opnd;
-
- scan = reginput;
- opnd = OPERAND(p);
- switch (OP(p)) {
- case ANY:
- count = int(strlen(scan));
- scan += count;
- break;
- case EXACTLY:
- while (*opnd == *scan) {
- count++;
- scan++;
- }
- break;
- case ANYOF:
- while (*scan != '\0' && strchr(opnd, *scan) != 0) {
- count++;
- scan++;
- }
- break;
- case ANYBUT:
- while (*scan != '\0' && strchr(opnd, *scan) == 0) {
- count++;
- scan++;
- }
- break;
- default: // Oh dear. Called inappropriately.
- //RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
- printf ("cm RegularExpression::find(): Internal error.\n");
- return 0;
- }
- reginput = scan;
- return (count);
+static int regrepeat(const char* p)
+{
+ int count = 0;
+ const char* scan;
+ const char* opnd;
+
+ scan = reginput;
+ opnd = OPERAND(p);
+ switch (OP(p)) {
+ case ANY:
+ count = int(strlen(scan));
+ scan += count;
+ break;
+ case EXACTLY:
+ while (*opnd == *scan) {
+ count++;
+ scan++;
+ }
+ break;
+ case ANYOF:
+ while (*scan != '\0' && strchr(opnd, *scan) != 0) {
+ count++;
+ scan++;
+ }
+ break;
+ case ANYBUT:
+ while (*scan != '\0' && strchr(opnd, *scan) == 0) {
+ count++;
+ scan++;
+ }
+ break;
+ default: // Oh dear. Called inappropriately.
+ // RAISE Error, SYM(RegularExpression), SYM(Internal_Error),
+ printf("cm RegularExpression::find(): Internal error.\n");
+ return 0;
+ }
+ reginput = scan;
+ return (count);
}
-
/*
- regnext - dig the "next" pointer out of a node
*/
-static const char* regnext (const char* p) {
- int offset;
+static const char* regnext(const char* p)
+{
+ int offset;
- if (p == &regdummy)
- return (0);
+ if (p == &regdummy)
+ return (0);
- offset = NEXT(p);
- if (offset == 0)
- return (0);
+ offset = NEXT(p);
+ if (offset == 0)
+ return (0);
- if (OP(p) == BACK)
- return (p - offset);
- else
- return (p + offset);
+ if (OP(p) == BACK)
+ return (p - offset);
+ else
+ return (p + offset);
}
-static char* regnext (char* p) {
- int offset;
+static char* regnext(char* p)
+{
+ int offset;
- if (p == &regdummy)
- return (0);
+ if (p == &regdummy)
+ return (0);
- offset = NEXT(p);
- if (offset == 0)
- return (0);
+ offset = NEXT(p);
+ if (offset == 0)
+ return (0);
- if (OP(p) == BACK)
- return (p - offset);
- else
- return (p + offset);
+ if (OP(p) == BACK)
+ return (p - offset);
+ else
+ return (p + offset);
}
} // namespace KWSYS_NAMESPACE