Bug [#2405]. Fix regular expression assertion (^, $, \b. \B) failures when using

SCFIND_CXX11REGEX.

3 files changed, 69 insertions, 33 deletions

diff --git a/doc/ScintillaHistory.html b/doc/ScintillaHistory.html
index 38cd4e3fa..dc2a8415e 100644
--- a/doc/ScintillaHistory.html
+++ b/doc/ScintillaHistory.html
@@ -614,6 +614,10 @@
 	<a href="https://sourceforge.net/p/scintilla/bugs/2413/">Bug #2413</a>.
 	</li>
 	<li>
+	Fix regular expression assertion (^, $, \b. \B) failures when using SCFIND_CXX11REGEX.
+	<a href="https://sourceforge.net/p/scintilla/bugs/2405/">Bug #2405</a>.
+	</li>
+	<li>
 	With a document that does not have the SC_DOCUMENTOPTION_TEXT_LARGE option set,
 	allocating more than 2G (calling SCI_ALLOCATE or similar) will now fail with SC_STATUS_FAILURE.
 	</li>
diff --git a/src/Document.cxx b/src/Document.cxx
index 16595eafa..84eea1394 100644
--- a/src/Document.cxx
+++ b/src/Document.cxx
@@ -2843,8 +2843,8 @@ public:
 		lineRangeEnd = doc->SciLineFromPosition(endPos);
 		lineRangeBreak = lineRangeEnd + increment;
 	}
-	Range LineRange(Sci::Line line) const {
-		Range range(doc->LineStart(line), doc->LineEnd(line));
+	Range LineRange(Sci::Line line, Sci::Position lineStartPos, Sci::Position lineEndPos) const noexcept {
+		Range range(lineStartPos, lineEndPos);
 		if (increment == 1) {
 			if (line == lineRangeStart)
 				range.start = startPos;
@@ -3082,12 +3082,24 @@ public:
 
 #endif
 
-std::regex_constants::match_flag_type MatchFlags(const Document *doc, Sci::Position startPos, Sci::Position endPos) noexcept {
+std::regex_constants::match_flag_type MatchFlags(const Document *doc, Sci::Position startPos, Sci::Position endPos, Sci::Position lineStartPos, Sci::Position lineEndPos) noexcept {
 	std::regex_constants::match_flag_type flagsMatch = std::regex_constants::match_default;
-	if (!doc->IsLineStartPosition(startPos))
+	if (startPos != lineStartPos) {
+#ifdef _LIBCPP_VERSION
 		flagsMatch |= std::regex_constants::match_not_bol;
-	if (!doc->IsLineEndPosition(endPos))
+		if (!doc->IsWordStartAt(startPos)) {
+			flagsMatch |= std::regex_constants::match_not_bow;
+		}
+#else
+		flagsMatch |= std::regex_constants::match_prev_avail;
+#endif
+	}
+	if (endPos != lineEndPos) {
 		flagsMatch |= std::regex_constants::match_not_eol;
+		if (!doc->IsWordEndAt(endPos)) {
+			flagsMatch |= std::regex_constants::match_not_eow;
+		}
+	}
 	return flagsMatch;
 }
 
@@ -3101,39 +3113,33 @@ bool MatchOnLines(const Document *doc, const Regex &regexp, const RESearchRange
 	// has not been implemented by compiler runtimes with MSVC always in multiline
 	// mode and libc++ and libstdc++ always in single-line mode.
 	// If multiline regex worked well then the line by line iteration could be removed
-	// for the forwards case and replaced with the following 4 lines:
+	// for the forwards case and replaced with the following:
 #ifdef REGEX_MULTILINE
+	const Sci::Position lineStartPos = doc->LineStart(resr.lineRangeStart);
+	const Sci::Position lineEndPos = doc->LineEnd(resr.lineRangeEnd);
 	Iterator itStart(doc, resr.startPos);
 	Iterator itEnd(doc, resr.endPos);
-	const std::regex_constants::match_flag_type flagsMatch = MatchFlags(doc, resr.startPos, resr.endPos);
+	const std::regex_constants::match_flag_type flagsMatch = MatchFlags(doc, resr.startPos, resr.endPos, lineStartPos, lineEndPos);
 	const bool matched = std::regex_search(itStart, itEnd, match, regexp, flagsMatch);
 #else
 	// Line by line.
 	bool matched = false;
 	for (Sci::Line line = resr.lineRangeStart; line != resr.lineRangeBreak; line += resr.increment) {
-		const Range lineRange = resr.LineRange(line);
+		const Sci::Position lineStartPos = doc->LineStart(line);
+		const Sci::Position lineEndPos = doc->LineEnd(line);
+		const Range lineRange = resr.LineRange(line, lineStartPos, lineEndPos);
 		Iterator itStart(doc, lineRange.start);
 		Iterator itEnd(doc, lineRange.end);
-		std::regex_constants::match_flag_type flagsMatch = MatchFlags(doc, lineRange.start, lineRange.end);
-		matched = std::regex_search(itStart, itEnd, match, regexp, flagsMatch);
-		// Check for the last match on this line.
-		if (matched) {
-			if (resr.increment == -1) {
-				while (matched) {
-					Iterator itNext(doc, match[0].second.PosRoundUp());
-					flagsMatch = MatchFlags(doc, itNext.Pos(), lineRange.end);
-					std::match_results<Iterator> matchNext;
-					matched = std::regex_search(itNext, itEnd, matchNext, regexp, flagsMatch);
-					if (matched) {
-						if (match[0].first == match[0].second) {
-							// Empty match means failure so exit
-							return false;
-						}
-						match = matchNext;
-					}
-				}
-				matched = true;
+		const std::regex_constants::match_flag_type flagsMatch = MatchFlags(doc, lineRange.start, lineRange.end, lineStartPos, lineEndPos);
+		std::regex_iterator<Iterator> it(itStart, itEnd, regexp, flagsMatch);
+		for (const std::regex_iterator<Iterator> last; it != last; ++it) {
+			match = *it;
+			matched = true;
+			if (resr.increment > 0) {
+				break;
 			}
+		}
+		if (matched) {
 			break;
 		}
 	}
@@ -3171,7 +3177,6 @@ Sci::Position Cxx11RegexFindText(const Document *doc, Sci::Position minPos, Sci:
 			std::wregex regexp;
 			regexp.assign(ws, flagsRe);
 			matched = MatchOnLines<UTF8Iterator>(doc, regexp, resr, search);
-
 		} else {
 			std::regex regexp;
 			regexp.assign(s, flagsRe);
diff --git a/test/unit/testDocument.cxx b/test/unit/testDocument.cxx
index ca95bda66..52af45167 100644
--- a/test/unit/testDocument.cxx
+++ b/test/unit/testDocument.cxx
@@ -555,6 +555,10 @@ TEST_CASE("Document") {
 		REQUIRE(match == Match(0));
 		match = doc.FindString(1, docLength, findingBOL, reCxx11);
 		REQUIRE(match == Match(10));
+		match = doc.FindString(docLength, 0, findingBOL, reCxx11);
+		REQUIRE(match == Match(10));
+		match = doc.FindString(docLength - 1, 0, findingBOL, reCxx11);
+		REQUIRE(match == Match(10));
 		#endif
 
 		constexpr std::string_view findingEOL = "$";
@@ -567,11 +571,15 @@ TEST_CASE("Document") {
 		match = doc.FindString(docLength - 1, 0, findingEOL, rePosix);
 		REQUIRE(match == Match(8));
 
-		#ifndef NO_CXX11_REGEX
+		#if !defined(NO_CXX11_REGEX) && !defined(_LIBCPP_VERSION)
 		match = doc.FindString(0, docLength, findingEOL, reCxx11);
 		REQUIRE(match == Match(8));
 		match = doc.FindString(1, docLength, findingEOL, reCxx11);
 		REQUIRE(match == Match(8));
+		match = doc.FindString(docLength, 0, findingEOL, reCxx11);
+		REQUIRE(match == Match(18));
+		match = doc.FindString(docLength - 1, 0, findingEOL, reCxx11);
+		REQUIRE(match == Match(8));
 		#endif
 
 		constexpr std::string_view findingBOW = "\\<";
@@ -605,13 +613,32 @@ TEST_CASE("Document") {
 		match = doc.FindString(0, docLength, findingWB, reCxx11);
 		REQUIRE(match == Match(0));
 		match = doc.FindString(1, docLength, findingWB, reCxx11);
-		REQUIRE(match == Match(1));
+		REQUIRE(match == Match(2));
+		match = doc.FindString(docLength, 0, findingWB, reCxx11);
+		#ifdef _LIBCPP_VERSION
+		REQUIRE(match == Match(16));
+		#else
+		REQUIRE(match == Match(18));
+		#endif
+		match = doc.FindString(docLength - 1, 0, findingWB, reCxx11);
+		REQUIRE(match == Match(16));
 
 		constexpr std::string_view findingNWB = "\\B";
 		match = doc.FindString(0, docLength, findingNWB, reCxx11);
 		REQUIRE(match == Match(1));
 		match = doc.FindString(1, docLength, findingNWB, reCxx11);
-		REQUIRE(match == Match(4));
+		REQUIRE(match == Match(1));
+		#ifdef _LIBCPP_VERSION
+		match = doc.FindString(docLength, 0, findingNWB, reCxx11);
+		REQUIRE(match == Match(18));
+		match = doc.FindString(docLength - 1, 0, findingNWB, reCxx11);
+		REQUIRE(match == Match(14));
+		#else
+		match = doc.FindString(docLength, 0, findingNWB, reCxx11);
+		REQUIRE(match == Match(17));
+		match = doc.FindString(docLength - 1, 0, findingNWB, reCxx11);
+		REQUIRE(match == Match(17));
+		#endif
 		#endif
 	}
 
@@ -637,7 +664,7 @@ TEST_CASE("Document") {
 		match = doc.FindString(0, docLength, "\\b[a-z]", reCxx11);
 		REQUIRE(match == Match(0, 1));
 		match = doc.FindString(1, docLength, "\\b[a-z]", reCxx11);
-		REQUIRE(match == Match(1, 1));	// Should be (3,1)
+		REQUIRE(match == Match(3, 1));
 		match = doc.FindString(0, docLength, "[a-z]\\b", reCxx11);
 		REQUIRE(match == Match(1, 1));
 		match = doc.FindString(2, docLength, "[a-z]\\b", reCxx11);
@@ -646,7 +673,7 @@ TEST_CASE("Document") {
 		match = doc.FindString(0, docLength, "\\B[a-z]", reCxx11);
 		REQUIRE(match == Match(1, 1));
 		match = doc.FindString(1, docLength, "\\B[a-z]", reCxx11);
-		REQUIRE(match == Match(4, 1));	// Should be (1,1)
+		REQUIRE(match == Match(1, 1));
 		match = doc.FindString(0, docLength, "[a-z]\\B", reCxx11);
 		REQUIRE(match == Match(0, 1));
 		match = doc.FindString(2, docLength, "[a-z]\\B", reCxx11);