Fix regex match bug for \<, \> and \>$, issue #161.

See https://sourceforge.net/p/scintilla/bugs/2157/
zufuliu · Oct 13, 2023 · 1bfaf31 · 1bfaf31
1 parent b70d686
commit 1bfaf31
Show file tree

Hide file tree

Showing 3 changed files with 38 additions and 18 deletions.
diff --git a/scintilla/src/Document.cxx b/scintilla/src/Document.cxx
@@ -3389,8 +3389,11 @@ Sci::Position BuiltinRegex::FindText(const Document *doc, Sci::Position minPos,
 	const char searchEndPrev = (*length > 1) ? s[*length - 2] : '\0';
 	const bool searchforLineEnd = (searchEnd == '$') && (searchEndPrev != '\\');
 	for (Sci::Line line = resr.lineRangeStart; line != resr.lineRangeBreak; line += resr.increment) {
-		Sci::Position startOfLine = doc->LineStart(line);
-		Sci::Position endOfLine = doc->LineEnd(line);
+		const Sci::Position lineStartPos = doc->LineStart(line);
+		const Sci::Position lineEndPos = doc->LineEnd(line);
+		Sci::Position startOfLine = lineStartPos;
+		Sci::Position endOfLine = lineEndPos;
+
 		if (resr.increment > 0) {
 			if (line == resr.lineRangeStart) {
 				if ((resr.startPos != startOfLine) && searchforLineStart)
@@ -3416,6 +3419,8 @@ Sci::Position BuiltinRegex::FindText(const Document *doc, Sci::Position minPos,
 		}
 
 		const DocumentIndexer di(doc, endOfLine);
+		search.lineStartPos = lineStartPos;
+		search.lineEndPos = lineEndPos;
 		int success = search.Execute(di, startOfLine, endOfLine);
 		if (success) {
 			pos = search.bopat[0];

diff --git a/scintilla/src/RESearch.cxx b/scintilla/src/RESearch.cxx
@@ -261,10 +261,11 @@ using namespace Scintilla::Internal;
  */
 
 RESearch::RESearch(const CharClassify *charClassTable) {
-	failure = 0;
 	charClass = charClassTable;
+	lineStartPos = 0;
+	lineEndPos = 0;
 	sta = NOP;                  /* status of lastpat */
-	bol = 0;
+	failure = 0;
 	previousFlags = FindOption::None;
 	constexpr unsigned char nul = 0;
 	std::fill(bittab, std::end(bittab), nul);
@@ -761,9 +762,8 @@ const char *RESearch::DoCompile(const char *pattern, Sci::Position length, bool
  */
 int RESearch::Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp) {
 	Sci::Position ep = NOTFOUND;
-	char *ap = nfa;
+	const char *ap = nfa;
 
-	bol = lp;
 	failure = 0;
 
 	Clear();
@@ -774,15 +774,15 @@ int RESearch::Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Positio
 		ep = PMatch(ci, lp, endp, ap);
 		break;
 	case EOL:			/* just searching for end of line normal path doesn't work */
-		if (*(ap + 1) == END) {
+		if (endp == lineEndPos && ap[1] == END) {
 			lp = endp;
 			ep = lp;
 			break;
 		} else {
 			return 0;
 		}
 	case CHR: {			/* ordinary char: locate it fast */
-		const unsigned char c = *(ap + 1);
+		const unsigned char c = ap[1];
 		while ((lp < endp) && (static_cast<unsigned char>(ci.CharAt(lp)) != c)) {
 			lp++;
 		}
@@ -801,8 +801,20 @@ int RESearch::Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Positio
 	case END:			/* munged automaton. fail always */
 		return 0;
 	}
-	if (ep == NOTFOUND)
-		return 0;
+	if (ep == NOTFOUND) {
+		/* similar to EOL, match EOW at line end */
+		if (endp == lineEndPos && *ap == EOW) {
+			++ap;
+			if ((*ap == END || ((*ap == EOL && ap[1] == END))) && iswordc(ci.CharAt(lp - 1))) {
+				lp = endp;
+				ep = lp;
+			} else {
+				return 0;
+			}
+		} else {
+			return 0;
+		}
+	}
 
 	lp = ci.MovePositionOutsideChar(lp, -1);
 	ep = ci.MovePositionOutsideChar(ep, 1);
@@ -850,7 +862,7 @@ int RESearch::Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Positio
 #define CHRSKIP 3	/* [CLO] CHR chr END      */
 #define CCLSKIP 34	/* [CLO] CCL 32 bytes END */
 
-Sci::Position RESearch::PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp, char *ap) {
+Sci::Position RESearch::PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp, const char *ap) {
 	uint8_t op;
 
 	while ((op = *ap++) != END) {
@@ -872,11 +884,11 @@ Sci::Position RESearch::PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci
 			ap += BITBLK;
 			break;
 		case BOL:
-			if (lp != bol)
+			if (lp != lineStartPos)
 				return NOTFOUND;
 			break;
 		case EOL:
-			if (lp < endp)
+			if (lp < lineEndPos)
 				return NOTFOUND;
 			break;
 		case BOT:
@@ -888,11 +900,11 @@ Sci::Position RESearch::PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci
 			eopat[static_cast<unsigned char>(*ap++)] = lp;
 			break;
 		case BOW:
-			if ((lp != bol && iswordc(ci.CharAt(lp - 1))) || !iswordc(ci.CharAt(lp)))
+			if ((lp != lineStartPos && iswordc(ci.CharAt(lp - 1))) || !iswordc(ci.CharAt(lp)))
 				return NOTFOUND;
 			break;
 		case EOW:
-			if (lp == bol || !iswordc(ci.CharAt(lp - 1)) || iswordc(ci.CharAt(lp)))
+			if (lp == lineStartPos || !iswordc(ci.CharAt(lp - 1)) || iswordc(ci.CharAt(lp)))
 				return NOTFOUND;
 			break;
 		case REF: {
@@ -922,7 +934,7 @@ Sci::Position RESearch::PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci
 				n = ANYSKIP;
 				break;
 			case CHR: {
-				const char c = *(ap + 1);
+				const char c = ap[1];
 				if (op == CLO || op == LCLO) {
 					while ((lp < endp) && (c == ci.CharAt(lp))) {
 						lp++;

diff --git a/scintilla/src/RESearch.h b/scintilla/src/RESearch.h
@@ -30,6 +30,10 @@ class RESearch {
 	Sci::Position bopat[MAXTAG];
 	Sci::Position eopat[MAXTAG];
 
+	// positions to match line start and line end
+	Sci::Position lineStartPos;
+	Sci::Position lineEndPos;
+
 private:
 	static constexpr int MAXNFA = 4096;
 	// The following constants are not meant to be changeable.
@@ -42,9 +46,8 @@ class RESearch {
 	int GetBackslashExpression(const char *pattern, int &incr) noexcept;
 
 	const char *DoCompile(const char *pattern, Sci::Position length, bool caseSensitive, bool posix) noexcept;
-	Sci::Position PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp, char *ap);
+	Sci::Position PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp, const char *ap);
 
-	Sci::Position bol;
 	Sci::Position tagstk[MAXTAG];  /* subpat tag stack */
 	char nfa[MAXNFA];    /* automaton */
 	int sta;