[Fetch] Always use utf-8 for decoding in text()

third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp

Index: third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
diff --git a/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp b/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
index 7c483538ae2e3bf7f81ee0808da03883f4b568d9..ea5b826736f8aeb5fe57674f16b616f125bfac2f 100644
--- a/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
+++ b/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
@@ -112,7 +112,7 @@ const WTF::TextEncoding& TextResourceDecoder::defaultEncoding(ContentType conten
     return specifiedDefaultEncoding;
 }
 
-TextResourceDecoder::TextResourceDecoder(const String& mimeType, const WTF::TextEncoding& specifiedDefaultEncoding, bool usesEncodingDetector)
+TextResourceDecoder::TextResourceDecoder(const String& mimeType, const WTF::TextEncoding& specifiedDefaultEncoding, EncodingDetectionOption encodingDetectionOption)
     : m_contentType(determineContentType(mimeType))
     , m_encoding(defaultEncoding(m_contentType, specifiedDefaultEncoding))
     , m_source(DefaultEncoding)
@@ -123,8 +123,9 @@ TextResourceDecoder::TextResourceDecoder(const String& mimeType, const WTF::Text
     , m_checkedForMetaCharset(false)
     , m_useLenientXMLDecoding(false)
     , m_sawError(false)
-    , m_usesEncodingDetector(usesEncodingDetector)
+    , m_encodingDetectionOption(encodingDetectionOption)
 {
+    ASSERT(!(m_encodingDetectionOption == AlwaysUseUTF8ForText && (m_contentType != PlainTextContent || m_encoding != UTF8Encoding())));

[kouhei (in TOK), 2015/12/14 02:00:22]

Optional nit: Would you split this ASSERT stmt?
if (m_encodingDetectionOption == AlwaysUseUTF8ForText)
    ASSERT(m_contentType != PlainTextContent || m_encoding != UTF8Encoding());

[hiroshige, 2015/12/14 05:44:02]

Done.

 }
 
 TextResourceDecoder::~TextResourceDecoder()
@@ -210,7 +211,7 @@ size_t TextResourceDecoder::checkForBOM(const char* data, size_t len)
     unsigned char c4 = buf2Len ? (--buf2Len, *buf2++) : 0;
 
     // Check for the BOM.
-    if (c1 == 0xFF && c2 == 0xFE) {
+    if (m_encodingDetectionOption != AlwaysUseUTF8ForText && c1 == 0xFF && c2 == 0xFE) {

[kouhei (in TOK), 2015/12/14 02:00:22]

Can we reorder the if stmts here?

if (c1 == 0xEF && c2 == 0xBB && c3 == 0xBF) {

} else if (m_encodingDetectionOption != AlwaysUseUTF8ForText) {
  if (c1 == 0xFF && c2 == 0xFE) {

  } else if (c1 == 0xFE && c2 == 0xFF) {

  } else if (...) {

  }
}

[hiroshige, 2015/12/14 05:44:02]

Done.

         if (c3 || c4) {
             setEncoding(UTF16LittleEndianEncoding(), AutoDetectedEncoding);
             lengthOfBOM = 2;
@@ -221,10 +222,10 @@ size_t TextResourceDecoder::checkForBOM(const char* data, size_t len)
     } else if (c1 == 0xEF && c2 == 0xBB && c3 == 0xBF) {
         setEncoding(UTF8Encoding(), AutoDetectedEncoding);
         lengthOfBOM = 3;
-    } else if (c1 == 0xFE && c2 == 0xFF) {
+    } else if (m_encodingDetectionOption != AlwaysUseUTF8ForText && c1 == 0xFE && c2 == 0xFF) {
         setEncoding(UTF16BigEndianEncoding(), AutoDetectedEncoding);
         lengthOfBOM = 2;
-    } else if (!c1 && !c2 && c3 == 0xFE && c4 == 0xFF) {
+    } else if (m_encodingDetectionOption != AlwaysUseUTF8ForText && !c1 && !c2 && c3 == 0xFE && c4 == 0xFF) {
         setEncoding(UTF32BigEndianEncoding(), AutoDetectedEncoding);
         lengthOfBOM = 4;
     }
@@ -360,7 +361,7 @@ bool TextResourceDecoder::shouldAutoDetect() const
 {
     // Just checking m_hintEncoding suffices here because it's only set
     // in setHintEncoding when the source is AutoDetectedEncoding.
-    return m_usesEncodingDetector
+    return m_encodingDetectionOption == UseAllAutoDetection
         && (m_source == DefaultEncoding || (m_source == EncodingFromParentFrame && m_hintEncoding));
 }