Use string_view for UniConversion functions.

4 files changed, 42 insertions, 41 deletions

diff --git a/src/Document.cxx b/src/Document.cxx
index fbe387f6d..bcc368a68 100644
--- a/src/Document.cxx
+++ b/src/Document.cxx
@@ -2939,12 +2939,13 @@ Sci::Position Cxx11RegexFindText(const Document *doc, Sci::Position minPos, Sci:
 
 		bool matched = false;
 		if (SC_CP_UTF8 == doc->dbcsCodePage) {
-			const size_t lenS = strlen(s);
-			std::vector<wchar_t> ws(lenS + 1);
+			const std::string_view sv(s);
+			const size_t lenS = sv.length();
+			std::vector<wchar_t> ws(sv.length() + 1);
 #if WCHAR_T_IS_16
-			const size_t outLen = UTF16FromUTF8(s, lenS, &ws[0], lenS);
+			const size_t outLen = UTF16FromUTF8(sv, &ws[0], lenS);
 #else
-			const size_t outLen = UTF32FromUTF8(s, lenS, reinterpret_cast<unsigned int *>(&ws[0]), lenS);
+			const size_t outLen = UTF32FromUTF8(sv, reinterpret_cast<unsigned int *>(&ws[0]), lenS);
 #endif
 			ws[outLen] = 0;
 			std::wregex regexp;
diff --git a/src/Editor.cxx b/src/Editor.cxx
index 36ebc5cea..7a61d503a 100644
--- a/src/Editor.cxx
+++ b/src/Editor.cxx
@@ -1957,7 +1957,7 @@ void Editor::AddCharUTF(const char *s, unsigned int len, bool treatAsDBCS) {
 			// characters representing themselves.
 		} else {
 			unsigned int utf32[1] = { 0 };
-			UTF32FromUTF8(s, len, utf32, ELEMENTS(utf32));
+			UTF32FromUTF8(std::string_view(s, len), utf32, ELEMENTS(utf32));
 			byte = utf32[0];
 		}
 		NotifyChar(byte);
diff --git a/src/UniConversion.cxx b/src/UniConversion.cxx
index a6830f950..1287aa612 100644
--- a/src/UniConversion.cxx
+++ b/src/UniConversion.cxx
@@ -17,10 +17,10 @@ using namespace Scintilla;
 
 namespace Scintilla {
 
-size_t UTF8Length(const wchar_t *uptr, size_t tlen) {
+size_t UTF8Length(std::wstring_view wsv) {
 	size_t len = 0;
-	for (size_t i = 0; i < tlen && uptr[i];) {
-		const unsigned int uch = uptr[i];
+	for (size_t i = 0; i < wsv.length() && wsv[i];) {
+		const unsigned int uch = wsv[i];
 		if (uch < 0x80) {
 			len++;
 		} else if (uch < 0x800) {
@@ -37,10 +37,10 @@ size_t UTF8Length(const wchar_t *uptr, size_t tlen) {
 	return len;
 }
 
-void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len) {
+void UTF8FromUTF16(std::wstring_view wsv, char *putf, size_t len) {
 	size_t k = 0;
-	for (size_t i = 0; i < tlen && uptr[i];) {
-		const unsigned int uch = uptr[i];
+	for (size_t i = 0; i < wsv.length() && wsv[i];) {
+		const unsigned int uch = wsv[i];
 		if (uch < 0x80) {
 			putf[k++] = static_cast<char>(uch);
 		} else if (uch < 0x800) {
@@ -50,7 +50,7 @@ void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len) {
 			(uch <= SURROGATE_TRAIL_LAST)) {
 			// Half a surrogate pair
 			i++;
-			const unsigned int xch = 0x10000 + ((uch & 0x3ff) << 10) + (uptr[i] & 0x3ff);
+			const unsigned int xch = 0x10000 + ((uch & 0x3ff) << 10) + (wsv[i] & 0x3ff);
 			putf[k++] = static_cast<char>(0xF0 | (xch >> 18));
 			putf[k++] = static_cast<char>(0x80 | ((xch >> 12) & 0x3f));
 			putf[k++] = static_cast<char>(0x80 | ((xch >> 6) & 0x3f));
@@ -86,14 +86,14 @@ void UTF8FromUTF32Character(int uch, char *putf) {
 	putf[k] = '\0';
 }
 
-size_t UTF16Length(const char *s, size_t len) {
+size_t UTF16Length(std::string_view sv) {
 	size_t ulen = 0;
-	for (size_t i = 0; i < len;) {
-		const unsigned char ch = s[i];
+	for (size_t i = 0; i<sv.length();) {
+		const unsigned char ch = sv[i];
 		const unsigned int byteCount = UTF8BytesOfLead[ch];
 		const unsigned int utf16Len = UTF16LengthFromUTF8ByteCount(byteCount);
 		i += byteCount;
-		ulen += (i > len) ? 1 : utf16Len;
+		ulen += (i > sv.length()) ? 1 : utf16Len;
 	}
 	return ulen;
 }
@@ -104,14 +104,14 @@ constexpr unsigned char TrailByteValue(unsigned char c) {
 	return c & 0b0011'1111;
 }
 
-size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
+size_t UTF16FromUTF8(std::string_view sv, wchar_t *tbuf, size_t tlen) {
 	size_t ui = 0;
-	for (size_t i = 0; i < len;) {
-		unsigned char ch = s[i];
+	for (size_t i = 0; i < sv.length();) {
+		unsigned char ch = sv[i];
 		const unsigned int byteCount = UTF8BytesOfLead[ch];
 		unsigned int value;
 
-		if (i + byteCount > len) {
+		if (i + byteCount > sv.length()) {
 			// Trying to read past end but still have space to write
 			if (ui < tlen) {
 				tbuf[ui] = ch;
@@ -132,26 +132,26 @@ size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
 			break;
 		case 2:
 			value = (ch & 0x1F) << 6;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			tbuf[ui] = static_cast<wchar_t>(value);
 			break;
 		case 3:
 			value = (ch & 0xF) << 12;
-			ch = s[i++];
+			ch = sv[i++];
 			value += (TrailByteValue(ch) << 6);
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			tbuf[ui] = static_cast<wchar_t>(value);
 			break;
 		default:
 			// Outside the BMP so need two surrogates
 			value = (ch & 0x7) << 18;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch) << 12;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch) << 6;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			tbuf[ui] = static_cast<wchar_t>(((value - 0x10000) >> 10) + SURROGATE_LEAD_FIRST);
 			ui++;
@@ -163,14 +163,14 @@ size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen) {
 	return ui;
 }
 
-size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen) {
+size_t UTF32FromUTF8(std::string_view sv, unsigned int *tbuf, size_t tlen) {
 	size_t ui = 0;
-	for (size_t i = 0; i < len;) {
-		unsigned char ch = s[i];
+	for (size_t i = 0; i < sv.length();) {
+		unsigned char ch = sv[i];
 		const unsigned int byteCount = UTF8BytesOfLead[ch];
 		unsigned int value;
 
-		if (i + byteCount > len) {
+		if (i + byteCount > sv.length()) {
 			// Trying to read past end but still have space to write
 			if (ui < tlen) {
 				tbuf[ui] = ch;
@@ -190,23 +190,23 @@ size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen)
 			break;
 		case 2:
 			value = (ch & 0x1F) << 6;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			break;
 		case 3:
 			value = (ch & 0xF) << 12;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch) << 6;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			break;
 		default:
 			value = (ch & 0x7) << 18;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch) << 12;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch) << 6;
-			ch = s[i++];
+			ch = sv[i++];
 			value += TrailByteValue(ch);
 			break;
 		}
diff --git a/src/UniConversion.h b/src/UniConversion.h
index 4cdfe1fac..1b84b8f81 100644
--- a/src/UniConversion.h
+++ b/src/UniConversion.h
@@ -14,12 +14,12 @@ const int UTF8MaxBytes = 4;
 
 const int unicodeReplacementChar = 0xFFFD;
 
-size_t UTF8Length(const wchar_t *uptr, size_t tlen);
-void UTF8FromUTF16(const wchar_t *uptr, size_t tlen, char *putf, size_t len);
+size_t UTF8Length(std::wstring_view wsv);
+void UTF8FromUTF16(std::wstring_view wsv, char *putf, size_t len);
 void UTF8FromUTF32Character(int uch, char *putf);
-size_t UTF16Length(const char *s, size_t len);
-size_t UTF16FromUTF8(const char *s, size_t len, wchar_t *tbuf, size_t tlen);
-size_t UTF32FromUTF8(const char *s, size_t len, unsigned int *tbuf, size_t tlen);
+size_t UTF16Length(std::string_view sv);
+size_t UTF16FromUTF8(std::string_view sv, wchar_t *tbuf, size_t tlen);
+size_t UTF32FromUTF8(std::string_view sv, unsigned int *tbuf, size_t tlen);
 unsigned int UTF16FromUTF32Character(unsigned int val, wchar_t *tbuf) noexcept;
 std::string FixInvalidUTF8(const std::string &text);