third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp - Issue 2697213002: Do not guess UTF8 encoding

Side by Side Diff: third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp

Issue 2697213002: Do not guess UTF8 encoding (Closed)

Patch Set: webkit layout htmls Created 3 years, 10 months ago

Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.

Jump to:

« no previous file with comments | « third_party/WebKit/LayoutTests/fast/text/ellipsis-at-edge-of-ltr-text-in-rtl-flow.html ('k') | third_party/WebKit/Source/platform/text/TextEncodingDetectorTest.cpp » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Hide Comments ('s')

OLD	NEW
1 /*	1 /*

2 * Copyright (C) 2008, 2009 Google Inc. All rights reserved.	2 * Copyright (C) 2008, 2009 Google Inc. All rights reserved.

3 *	3 *

4 * Redistribution and use in source and binary forms, with or without	4 * Redistribution and use in source and binary forms, with or without

5 * modification, are permitted provided that the following conditions are	5 * modification, are permitted provided that the following conditions are

6 * met:	6 * met:

7 *	7 *

8 * * Redistributions of source code must retain the above copyright	8 * * Redistributions of source code must retain the above copyright

9 * notice, this list of conditions and the following disclaimer.	9 * notice, this list of conditions and the following disclaimer.

10 * * Redistributions in binary form must reproduce the above	10 * * Redistributions in binary form must reproduce the above

(...skipping 34 matching lines...) Expand 10 before \| Expand all \| Expand 10 after Loading...
45 Language language;	45 Language language;

46 LanguageFromCode(hintUserLanguage, &language);	46 LanguageFromCode(hintUserLanguage, &language);

47 int consumedBytes;	47 int consumedBytes;

48 bool isReliable;	48 bool isReliable;

49 Encoding encoding = CompactEncDet::DetectEncoding(	49 Encoding encoding = CompactEncDet::DetectEncoding(

50 data, length, hintUrl, nullptr, nullptr,	50 data, length, hintUrl, nullptr, nullptr,

51 EncodingNameAliasToEncoding(hintEncodingName), language,	51 EncodingNameAliasToEncoding(hintEncodingName), language,

52 CompactEncDet::WEB_CORPUS,	52 CompactEncDet::WEB_CORPUS,

53 false, // Include 7-bit encodings to detect ISO-2022-JP	53 false, // Include 7-bit encodings to detect ISO-2022-JP

54 &consumedBytes, &isReliable);	54 &consumedBytes, &isReliable);

55 if (encoding == UNKNOWN_ENCODING)	55

	56 // Should return false if the detected encoding is UTF8. This helps prevent

	57 // modern web sites from neglecting proper encoding labelling and simply

	58 // relying on browser-side encoding detection. Encoding detection is supposed

	59 // to work for web sites with legacy encoding only. Detection failure leads

	60 // \|TextResourceDecoder\| to use its default encoding determined from system

	61 // locale or TLD.

	62 if (encoding == UNKNOWN_ENCODING \|\| encoding == UTF8)

56 return false;	63 return false;

57	64

58 // 7-bit encodings (except ISO-2022-JP) are not supported in WHATWG encoding	65 // 7-bit encodings (except ISO-2022-JP) are not supported in WHATWG encoding

59 // standard. Mark them as ASCII to keep the raw bytes intact.	66 // standard. Mark them as ASCII to keep the raw bytes intact.

60 switch (encoding) {	67 switch (encoding) {

61 case HZ_GB_2312:	68 case HZ_GB_2312:

62 case ISO_2022_KR:	69 case ISO_2022_KR:

63 case ISO_2022_CN:	70 case ISO_2022_CN:

64 case UTF7:	71 case UTF7:

65 encoding = ASCII_7BIT;	72 encoding = ASCII_7BIT;

66 break;	73 break;

67 default:	74 default:

68 break;	75 break;

69 }	76 }

70 *detectedEncoding = WTF::TextEncoding(MimeEncodingName(encoding));	77 *detectedEncoding = WTF::TextEncoding(MimeEncodingName(encoding));

71 return true;	78 return true;

72 }	79 }

73	80

74 } // namespace blink	81 } // namespace blink

OLD	NEW