[Parse] Correct the range for the start of a UTF8 character

pinkjuice66 · pinkjuice66 · commit 1269b972fe9f · 2024-01-08T20:20:54.000+09:00
diff --git a/lib/Parse/Lexer.cpp b/lib/Parse/Lexer.cpp
@@ -102,7 +102,7 @@ static unsigned CLO8(unsigned char C) {
 static bool isStartOfUTF8Character(unsigned char C) {
   // RFC 2279: The octet values FE and FF never appear.
   // RFC 3629: The octet values C0, C1, F5 to FF never appear.
-  return C <= 0x80 || (C >= 0xC2 && C < 0xF5);
+  return C < 0x80 || (C >= 0xC2 && C < 0xF5);
 }
 
 /// validateUTF8CharacterAndAdvance - Given a pointer to the starting byte of a

Original file line number	Diff line number	Diff line change
`@@ -102,7 +102,7 @@ static unsigned CLO8(unsigned char C) {`
`102`	`102`	`static bool isStartOfUTF8Character(unsigned char C) {`
`103`	`103`	`// RFC 2279: The octet values FE and FF never appear.`
`104`	`104`	`// RFC 3629: The octet values C0, C1, F5 to FF never appear.`
`105`		`- return C <= 0x80 \|\| (C >= 0xC2 && C < 0xF5);`
	`105`	`+ return C < 0x80 \|\| (C >= 0xC2 && C < 0xF5);`
`106`	`106`	`}`
`107`	`107`
`108`	`108`	`/// validateUTF8CharacterAndAdvance - Given a pointer to the starting byte of a`