Bug [#2157]. Fix regular expression search for word begin \< and word end \>.

5 files changed, 167 insertions, 12 deletions

diff --git a/doc/ScintillaHistory.html b/doc/ScintillaHistory.html
index b37d6bbf0..ed14dd626 100644
--- a/doc/ScintillaHistory.html
+++ b/doc/ScintillaHistory.html
@@ -605,6 +605,11 @@
 	<a href="https://sourceforge.net/p/scintilla/feature-requests/1502/">Feature #1502</a>.
 	</li>
 	<li>
+	Fix regular expression search for "\&lt;" matching beginning of search when not beginning of word and
+	for "\&gt;" not matching line end.
+	<a href="https://sourceforge.net/p/scintilla/bugs/2157/">Bug #2157</a>.
+	</li>
+	<li>
 	Fix regular expression search failure when search for "\&lt;" followed by search for "\&gt;".
 	<a href="https://sourceforge.net/p/scintilla/bugs/2413/">Bug #2413</a>.
 	</li>
diff --git a/src/Document.cxx b/src/Document.cxx
index a35105669..16595eafa 100644
--- a/src/Document.cxx
+++ b/src/Document.cxx
@@ -3232,8 +3232,10 @@ Sci::Position BuiltinRegex::FindText(Document *doc, Sci::Position minPos, Sci::P
 	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 == 1) {
 			if (line == resr.lineRangeStart) {
 				if ((resr.startPos != startOfLine) && searchforLineStart)
@@ -3259,6 +3261,7 @@ Sci::Position BuiltinRegex::FindText(Document *doc, Sci::Position minPos, Sci::P
 		}
 
 		const DocumentIndexer di(doc, endOfLine);
+		search.SetLineRange(lineStartPos, lineEndPos);
 		int success = search.Execute(di, startOfLine, endOfLine);
 		if (success) {
 			pos = search.bopat[0];
diff --git a/src/RESearch.cxx b/src/RESearch.cxx
index de4dc08a9..7b2701aba 100644
--- a/src/RESearch.cxx
+++ b/src/RESearch.cxx
@@ -253,7 +253,8 @@ RESearch::RESearch(CharClassify *charClassTable) {
 	failure = 0;
 	charClass = charClassTable;
 	sta = NOP;                  /* status of lastpat */
-	bol = 0;
+	lineStartPos = 0;
+	lineEndPos = 0;
 	nfa[0] = END;
 	Clear();
 }
@@ -740,7 +741,6 @@ int RESearch::Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Positio
 	Sci::Position ep = NOTFOUND;
 	const char * const ap = nfa;
 
-	bol = lp;
 	failure = 0;
 
 	Clear();
@@ -751,7 +751,7 @@ 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;
@@ -777,8 +777,19 @@ 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) {
+			if ((ap[1] == END || ((ap[1] == EOL && ap[2] == END))) && iswordc(ci.CharAt(lp - 1))) {
+				lp = endp;
+				ep = lp;
+			} else {
+				return 0;
+			}
+		} else {
+			return 0;
+		}
+	}
 
 	bopat[0] = lp;
 	eopat[0] = ep;
@@ -846,11 +857,11 @@ 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:
@@ -860,11 +871,11 @@ 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: {
diff --git a/src/RESearch.h b/src/RESearch.h
index b7955dc79..e3a9c8110 100644
--- a/src/RESearch.h
+++ b/src/RESearch.h
@@ -24,6 +24,10 @@ public:
 	void Clear();
 	const char *Compile(const char *pattern, Sci::Position length, bool caseSensitive, bool posix);
 	int Execute(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp);
+	void SetLineRange(Sci::Position startPos, Sci::Position endPos) noexcept {
+		lineStartPos = startPos;
+		lineEndPos = endPos;
+	}
 
 	static constexpr int MAXTAG = 10;
 	static constexpr int NOTFOUND = -1;
@@ -47,7 +51,9 @@ private:
 
 	Sci::Position PMatch(const CharacterIndexer &ci, Sci::Position lp, Sci::Position endp, const char *ap);
 
-	Sci::Position bol;
+	// positions to match line start and line end
+	Sci::Position lineStartPos;
+	Sci::Position lineEndPos;
 	char nfa[MAXNFA];    /* automaton */
 	int sta;
 	int failure;
diff --git a/test/unit/testDocument.cxx b/test/unit/testDocument.cxx
index 85ed3b813..025de3012 100644
--- a/test/unit/testDocument.cxx
+++ b/test/unit/testDocument.cxx
@@ -512,6 +512,136 @@ TEST_CASE("Document") {
 		REQUIRE(substituted == "\tb\xCE\x93y\n");
 		#endif
 	}
+
+	SECTION("RegexAssertion") {
+		DocPlus doc("ab cd ef\r\ngh ij kl", CpUtf8);
+		const Sci::Position docLength = doc.document.Length();
+		constexpr std::string_view findingBOL = "^";
+		Sci::Position lengthFinding = findingBOL.length();
+		Sci::Position location = doc.document.FindText(0, docLength, findingBOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 0);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOL.length();
+		location = doc.document.FindText(1, docLength, findingBOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 10);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOL.length();
+		location = doc.document.FindText(docLength, 0, findingBOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 10);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOL.length();
+		location = doc.document.FindText(docLength - 1, 0, findingBOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 10);
+		REQUIRE(lengthFinding == 0);
+
+		#ifndef NO_CXX11_REGEX
+		lengthFinding = findingBOL.length();
+		location = doc.document.FindText(0, docLength, findingBOL.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 0);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOL.length();
+		location = doc.document.FindText(1, docLength, findingBOL.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 10);
+		REQUIRE(lengthFinding == 0);
+		#endif
+
+		constexpr std::string_view findingEOL = "$";
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(0, docLength, findingEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(1, docLength, findingEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(docLength, 0, findingEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 18);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(docLength - 1, 0, findingEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+
+		#ifndef NO_CXX11_REGEX
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(0, docLength, findingEOL.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOL.length();
+		location = doc.document.FindText(1, docLength, findingEOL.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+		#endif
+
+		constexpr std::string_view findingBOW = "\\<";
+		lengthFinding = findingBOW.length();
+		location = doc.document.FindText(0, docLength, findingBOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 0);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOW.length();
+		location = doc.document.FindText(1, docLength, findingBOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 3);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOW.length();
+		location = doc.document.FindText(docLength, 0, findingBOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 16);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingBOW.length();
+		location = doc.document.FindText(docLength - 1, 0, findingBOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 16);
+		REQUIRE(lengthFinding == 0);
+
+		constexpr std::string_view findingEOW = "\\>";
+		lengthFinding = findingEOW.length();
+		location = doc.document.FindText(0, docLength, findingEOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 2);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOW.length();
+		location = doc.document.FindText(1, docLength, findingEOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 2);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOW.length();
+		location = doc.document.FindText(docLength, 0, findingEOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 18);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOW.length();
+		location = doc.document.FindText(docLength - 1, 0, findingEOW.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 15);
+		REQUIRE(lengthFinding == 0);
+
+		constexpr std::string_view findingEOWEOL = "\\>$";
+		lengthFinding = findingEOWEOL.length();
+		location = doc.document.FindText(0, docLength, findingEOWEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 8);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingEOWEOL.length();
+		location = doc.document.FindText(10, docLength, findingEOWEOL.data(), FindOption::RegExp | FindOption::Posix, &lengthFinding);
+		REQUIRE(location == 18);
+		REQUIRE(lengthFinding == 0);
+
+#ifndef NO_CXX11_REGEX
+		constexpr std::string_view findingWB = "\\b";
+		lengthFinding = findingWB.length();
+		location = doc.document.FindText(0, docLength, findingWB.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 0);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingWB.length();
+		location = doc.document.FindText(1, docLength, findingWB.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 1);
+		REQUIRE(lengthFinding == 0);
+
+		constexpr std::string_view findingNWB = "\\B";
+		lengthFinding = findingNWB.length();
+		location = doc.document.FindText(0, docLength, findingNWB.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 1);
+		REQUIRE(lengthFinding == 0);
+		lengthFinding = findingNWB.length();
+		location = doc.document.FindText(1, docLength, findingNWB.data(), FindOption::RegExp | FindOption::Cxx11RegEx, &lengthFinding);
+		REQUIRE(location == 4);
+		REQUIRE(lengthFinding == 0);
+		#endif
+	}
 }
 
 TEST_CASE("Words") {