1 files changed, 57 insertions, 45 deletions

diff --git a/Godeps/_workspace/src/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go b/Godeps/_workspace/src/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go
index e42af960c..85de6b1e6 100644
--- a/Godeps/_workspace/src/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go
+++ b/Godeps/_workspace/src/golang.org/x/text/encoding/simplifiedchinese/hzgb2312.go
@@ -140,71 +140,81 @@ func (e *hzGB2312Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int
 				dst[nDst+1] = '~'
 				nDst += 2
 				continue
-			}
-
-		} else {
-			// Decode a multi-byte rune.
-			r, size = utf8.DecodeRune(src[nSrc:])
-			if size == 1 {
-				// All valid runes of size 1 (those below utf8.RuneSelf) were
-				// handled above. We have invalid UTF-8 or we haven't seen the
-				// full character yet.
-				if !atEOF && !utf8.FullRune(src[nSrc:]) {
-					err = transform.ErrShortSrc
+			} else if *e != asciiState {
+				if nDst+3 > len(dst) {
+					err = transform.ErrShortDst
 					break
 				}
+				*e = asciiState
+				dst[nDst+0] = '~'
+				dst[nDst+1] = '}'
+				nDst += 2
+			} else if nDst >= len(dst) {
+				err = transform.ErrShortDst
+				break
 			}
+			dst[nDst] = uint8(r)
+			nDst += 1
+			continue
 
-			// func init checks that the switch covers all tables.
-			switch {
-			case encode0Low <= r && r < encode0High:
-				if r = rune(encode0[r-encode0Low]); r != 0 {
-					goto writeGB
-				}
-			case encode1Low <= r && r < encode1High:
-				if r = rune(encode1[r-encode1Low]); r != 0 {
-					goto writeGB
-				}
-			case encode2Low <= r && r < encode2High:
-				if r = rune(encode2[r-encode2Low]); r != 0 {
-					goto writeGB
-				}
-			case encode3Low <= r && r < encode3High:
-				if r = rune(encode3[r-encode3Low]); r != 0 {
-					goto writeGB
-				}
-			case encode4Low <= r && r < encode4High:
-				if r = rune(encode4[r-encode4Low]); r != 0 {
-					goto writeGB
-				}
+		}
+
+		// Decode a multi-byte rune.
+		r, size = utf8.DecodeRune(src[nSrc:])
+		if size == 1 {
+			// All valid runes of size 1 (those below utf8.RuneSelf) were
+			// handled above. We have invalid UTF-8 or we haven't seen the
+			// full character yet.
+			if !atEOF && !utf8.FullRune(src[nSrc:]) {
+				err = transform.ErrShortSrc
+				break
 			}
-			r = encoding.ASCIISub
 		}
 
-	writeASCII:
+		// func init checks that the switch covers all tables.
+		switch {
+		case encode0Low <= r && r < encode0High:
+			if r = rune(encode0[r-encode0Low]); r != 0 {
+				goto writeGB
+			}
+		case encode1Low <= r && r < encode1High:
+			if r = rune(encode1[r-encode1Low]); r != 0 {
+				goto writeGB
+			}
+		case encode2Low <= r && r < encode2High:
+			if r = rune(encode2[r-encode2Low]); r != 0 {
+				goto writeGB
+			}
+		case encode3Low <= r && r < encode3High:
+			if r = rune(encode3[r-encode3Low]); r != 0 {
+				goto writeGB
+			}
+		case encode4Low <= r && r < encode4High:
+			if r = rune(encode4[r-encode4Low]); r != 0 {
+				goto writeGB
+			}
+		}
+
+	terminateInASCIIState:
+		// Switch back to ASCII state in case of error so that an ASCII
+		// replacement character can be written in the correct state.
 		if *e != asciiState {
-			if nDst+3 > len(dst) {
+			if nDst+2 > len(dst) {
 				err = transform.ErrShortDst
 				break
 			}
-			*e = asciiState
 			dst[nDst+0] = '~'
 			dst[nDst+1] = '}'
 			nDst += 2
-		} else if nDst >= len(dst) {
-			err = transform.ErrShortDst
-			break
 		}
-		dst[nDst] = uint8(r)
-		nDst++
-		continue
+		err = internal.ErrASCIIReplacement
+		break
 
 	writeGB:
 		c0 := uint8(r>>8) - 0x80
 		c1 := uint8(r) - 0x80
 		if c0 < 0x21 || 0x7e <= c0 || c1 < 0x21 || 0x7f <= c1 {
-			r = encoding.ASCIISub
-			goto writeASCII
+			goto terminateInASCIIState
 		}
 		if *e == asciiState {
 			if nDst+4 > len(dst) {
@@ -224,5 +234,7 @@ func (e *hzGB2312Encoder) Transform(dst, src []byte, atEOF bool) (nDst, nSrc int
 		nDst += 2
 		continue
 	}
+	// TODO: should one always terminate in ASCII state to make it safe to
+	// concatenate two HZ-GB2312-encoded strings?
 	return nDst, nSrc, err
 }