Convert non-WHATWG text encoding to ASCII

third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp

Index: third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp
diff --git a/third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp b/third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp
index f0d9ccce852814c9fe7314361b4b12cbcbceec9e..c90f000243f5dc8072c5d9e011031578be049f99 100644
--- a/third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp
+++ b/third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp
@@ -62,13 +62,43 @@ bool detectTextEncoding(const char* data,
   if (encoding == UNKNOWN_ENCODING || encoding == UTF8)
     return false;
 
-  // 7-bit encodings (except ISO-2022-JP) are not supported in WHATWG encoding
-  // standard. Mark them as ASCII to keep the raw bytes intact.
+  // Map all the Shift-JIS variants to Shift-JIS.
+  if (hintUserLanguage && !strncmp(hintUserLanguage, "ja", 2) &&
+      IsShiftJisOrVariant(encoding)) {
+    encoding = JAPANESE_SHIFT_JIS;
+  }
+
+  // 7-bit encodings (except ISO-2022-JP), and some obscure encodings not
+  // supported in WHATWG encoding standard are marked as ASCII to keep the raw
+  // bytes intact.
+  // TODO(jinsukkim): Put this conversion into CED library, and enable "WHATWG"
+  // mode.
   switch (encoding) {
     case HZ_GB_2312:
     case ISO_2022_KR:
     case ISO_2022_CN:
     case UTF7:
+
+    case CHINESE_EUC_DEC:
+    case CHINESE_CNS:
+    case CHINESE_BIG5_CP950:
+    case MSFT_CP874:

[tkent, 2017/03/08 03:43:37]

We still need to list Shift_JIS variants for non-Japanese locale.

[Jinsuk Kim, 2017/03/08 04:05:54]

Right. done.

+    case TSCII:
+    case TAMIL_MONO:
+    case TAMIL_BI:
+    case JAGRAN:
+    case BHASKAR:
+    case HTCHANAKYA:
+    case BINARYENC:
+    case UTF8UTF8:
+    case TAM_ELANGO:
+    case TAM_LTTMBARANI:
+    case TAM_SHREE:
+    case TAM_TBOOMIS:
+    case TAM_TMNEWS:
+    case TAM_WEBTAMIL:
+    case KDDI_ISO_2022_JP:
+    case SOFTBANK_ISO_2022_JP:
       encoding = ASCII_7BIT;
       break;
     default: