UTF-8 detector for pages missing encoding info

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 49897d7c3ac409bd860dbaf44bbc4786a39ad3b4..6881b2ab106473377b9ed92399c3fcf896287f47 100644
--- a/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
+++ b/third_party/WebKit/Source/core/html/parser/TextResourceDecoder.cpp
@@ -406,6 +406,8 @@ String TextResourceDecoder::decode(const char* data, size_t len)
         WTF::TextEncoding detectedEncoding;
         if (detectTextEncoding(data, len, m_hintEncoding, &detectedEncoding))
             setEncoding(detectedEncoding, EncodingFromContentSniffing);
+    } else if ((m_source == DefaultEncoding || (m_source == EncodingFromParentFrame && m_hintEncoding)) && isUTF8Encoded(data, len)) {

[aelias_OOO_until_Jul13, 2016/02/24 04:37:53]

This if statement is duplicative with the other and also with
shouldAutodetect(), could you create a small method for it?

[Jinsuk Kim, 2016/02/24 06:54:54]

Done.

+        setEncoding(UTF8Encoding(), EncodingFromContentSniffing);
     }
 
     ASSERT(m_encoding.isValid());
@@ -424,11 +426,15 @@ String TextResourceDecoder::flush()
     // If we can not identify the encoding even after a document is completely
     // loaded, we need to detect the encoding if other conditions for
     // autodetection is satisfied.
-    if (m_buffer.size() && shouldAutoDetect()
+    if (m_buffer.size()
         && ((!m_checkedForXMLCharset && (m_contentType == HTMLContent || m_contentType == XMLContent)) || (!m_checkedForCSSCharset && (m_contentType == CSSContent)))) {
-        WTF::TextEncoding detectedEncoding;
-        if (detectTextEncoding(m_buffer.data(), m_buffer.size(), m_hintEncoding, &detectedEncoding))
-            setEncoding(detectedEncoding, EncodingFromContentSniffing);
+        if (shouldAutoDetect()) {
+            WTF::TextEncoding detectedEncoding;
+            if (detectTextEncoding(m_buffer.data(), m_buffer.size(), m_hintEncoding, &detectedEncoding))
+                setEncoding(detectedEncoding, EncodingFromContentSniffing);
+        } else if ((m_source == DefaultEncoding || (m_source == EncodingFromParentFrame && m_hintEncoding)) && isUTF8Encoded(m_buffer.data(), m_buffer.size())) {
+            setEncoding(UTF8Encoding(), EncodingFromContentSniffing);
+        }
     }
 
     if (!m_codec)