third_party/WebKit/Source/platform/text/TextEncodingDetector.cpp - Issue 2742873002: Convert non-WHATWG text encoding to ASCII

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

Issue 2742873002: Convert non-WHATWG text encoding to ASCII (Closed)

Patch Set: Created 3 years, 9 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:

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 44 matching lines...) Expand 10 before \| Expand all \| Expand 10 after Loading...
55	55

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

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

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

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

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

61 // locale or TLD.	61 // locale or TLD.

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

63 return false;	63 return false;

64	64

65 // 7-bit encodings (except ISO-2022-JP) are not supported in WHATWG encoding	65 // Map all the Shift-JIS variants to Shift-JIS.

66 // standard. Mark them as ASCII to keep the raw bytes intact.	66 if (hintUserLanguage && !strncmp(hintUserLanguage, "ja", 2) &&

	67 IsShiftJisOrVariant(encoding)) {

	68 encoding = JAPANESE_SHIFT_JIS;

	69 }

	70

	71 // 7-bit encodings (except ISO-2022-JP), and some obscure encodings not

	72 // supported in WHATWG encoding standard are marked as ASCII to keep the raw

	73 // bytes intact.

	74 // TODO(jinsukkim): Put this conversion into CED library, and enable "WHATWG"

	75 // mode.

67 switch (encoding) {	76 switch (encoding) {

68 case HZ_GB_2312:	77 case HZ_GB_2312:

69 case ISO_2022_KR:	78 case ISO_2022_KR:

70 case ISO_2022_CN:	79 case ISO_2022_CN:

71 case UTF7:	80 case UTF7:

	81

	82 case CHINESE_EUC_DEC:

	83 case CHINESE_CNS:

	84 case CHINESE_BIG5_CP950:

	85 case JAPANESE_CP932:

	86 case MSFT_CP874:

	87 case TSCII:

	88 case TAMIL_MONO:

	89 case TAMIL_BI:

	90 case JAGRAN:

	91 case BHASKAR:

	92 case HTCHANAKYA:

	93 case BINARYENC:

	94 case UTF8UTF8:

	95 case TAM_ELANGO:

	96 case TAM_LTTMBARANI:

	97 case TAM_SHREE:

	98 case TAM_TBOOMIS:

	99 case TAM_TMNEWS:

	100 case TAM_WEBTAMIL:

	101 case KDDI_SHIFT_JIS:

	102 case DOCOMO_SHIFT_JIS:

	103 case SOFTBANK_SHIFT_JIS:

	104 case KDDI_ISO_2022_JP:

	105 case SOFTBANK_ISO_2022_JP:

72 encoding = ASCII_7BIT;	106 encoding = ASCII_7BIT;

73 break;	107 break;

74 default:	108 default:

75 break;	109 break;

76 }	110 }

77 *detectedEncoding = WTF::TextEncoding(MimeEncodingName(encoding));	111 *detectedEncoding = WTF::TextEncoding(MimeEncodingName(encoding));

78 return true;	112 return true;

79 }	113 }

80	114

81 } // namespace blink	115 } // namespace blink

OLD	NEW

« no previous file with comments | « no previous file | third_party/WebKit/Source/platform/text/TextEncodingDetectorTest.cpp » ('j') | no next file with comments »