Index: src/unicode.h |
diff --git a/src/unicode.h b/src/unicode.h |
index 6ba61d0e17b2a0b6ff7702c422c38ddf9276318a..bc57678fac9f2c87a760f6bd86fd6ca5240c33de 100644 |
--- a/src/unicode.h |
+++ b/src/unicode.h |
@@ -46,6 +46,12 @@ typedef unsigned char byte; |
*/ |
const int kMaxMappingSize = 4; |
+/** |
+ * The unicode replacement character, used to signal invalid unicode sequences |
+ * (e.g. an orphan surrogate) when converting to a UTF encoding. |
+ */ |
+const int kReplacementCharacter = 0xFFFD; |
+ |
template <class T, int size = 256> |
class Predicate { |
public: |
@@ -102,6 +108,9 @@ class UnicodeData { |
class Utf16 { |
public: |
+ static inline bool IsSurrogatePair(int lead, int trail) { |
+ return IsLeadSurrogate(lead) && IsTrailSurrogate(trail); |
+ } |
static inline bool IsLeadSurrogate(int code) { |
if (code == kNoPreviousCharacter) return false; |
return (code & 0xfc00) == 0xd800; |
@@ -146,8 +155,7 @@ class Utf8 { |
public: |
static inline uchar Length(uchar chr, int previous); |
static inline unsigned EncodeOneByte(char* out, uint8_t c); |
- static inline unsigned Encode( |
- char* out, uchar c, int previous); |
+ static inline unsigned Encode(char* str, uchar c, bool allow_invalid); |
static uchar CalculateValue(const byte* str, |
unsigned length, |
unsigned* cursor); |