LayoutTests/fast/encoding/char-decoding.html - Issue 265973003: Implement "replacement" text encoding.

Side by Side Diff: LayoutTests/fast/encoding/char-decoding.html

Issue 265973003: Implement "replacement" text encoding. (Closed) Base URL: svn://svn.chromium.org/blink/trunk

Patch Set: Request rebaseline the temporary chaset-replacement output Created 6 years, 7 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:

View unified diff | Download patch | Annotate | Revision Log

OLD	NEW
1 <html>	1 <html>

2 <head>	2 <head>

3 <script src="../../resources/js-test.js"></script>	3 <script src="../../resources/js-test.js"></script>

4 <script src="resources/char-decoding-utils.js"></script>	4 <script src="resources/char-decoding-utils.js"></script>

5 </head>	5 </head>

6 <body>	6 <body>

7 <script>	7 <script>

8	8

9 description("This tests decoding characters in various character sets.");	9 description("This tests decoding characters in various character sets.");

10	10

(...skipping 11 matching lines...) Expand all Loading...
22 testDecode('Shift_JIS', '%82%d0', 'U+3072');	22 testDecode('Shift_JIS', '%82%d0', 'U+3072');

23 testDecode('shift-jis', '%82%d0', 'U+3072');	23 testDecode('shift-jis', '%82%d0', 'U+3072');

24	24

25 // Test that all Korean encodings of EUC-KR family are treated as windows-949.	25 // Test that all Korean encodings of EUC-KR family are treated as windows-949.

26 var korean = {	26 var korean = {

27 encodings: ['korean', 'EUC-KR', 'windows-949', 'x-windows-949', 'x-uhc',	27 encodings: ['korean', 'EUC-KR', 'windows-949', 'x-windows-949', 'x-uhc',

28 'iso-ir-149', 'KS_C_5601-1987', 'KS_C_5601-1989',	28 'iso-ir-149', 'KS_C_5601-1987', 'KS_C_5601-1989',

29 'KSC5601', 'KSC_5601'],	29 'KSC5601', 'KSC_5601'],

30 encoded: ['%A2%E6', '%A1%A4', '%A1%A9', '%A1%AA', '%A1%AD', '%A2%A6',	30 encoded: ['%A2%E6', '%A1%A4', '%A1%A9', '%A1%AA', '%A1%AD', '%A2%A6',

31 '%A2%C1', '%1A', '%1C', '%8F%A1', '%B4%D3', '%A2%41'],	31 '%A2%C1', '%1A', '%1C', '%8F%A1', '%B4%D3', '%A2%41'],

32 unicode: ['U+20AC', 'U+00B7', 'U+00AD', 'U+2015', 'U+223C', 'U+FF5E',	32 unicode: ['U+20AC', 'U+00B7', 'U+00AD', 'U+2015', 'U+223C', 'U+FF5E',

33 'U+2299', 'U+001A', 'U+001C', 'U+B8EA', 'U+B2D2', 'U+C910']	33 'U+2299', 'U+001A', 'U+001C', 'U+B8EA', 'U+B2D2', 'U+C910']

34 };	34 };

35	35

36 batchTestDecode(korean);	36 batchTestDecode(korean);

37	37

38 // Test that ISO-8859-9 (Turkish) is upgraded to windows-1254 with Euro symbol.	38 // Test that ISO-8859-9 (Turkish) is upgraded to windows-1254 with Euro symbol.

39 var turkish = {	39 var turkish = {

40 encodings: ['iso-8859-9', 'latin5', 'windows-1254'],	40 encodings: ['iso-8859-9', 'latin5', 'windows-1254'],

41 encoded: ['%80', '%9F', '%FD'],	41 encoded: ['%80', '%9F', '%FD'],

42 unicode: ['U+20AC', 'U+0178', 'U+0131']	42 unicode: ['U+20AC', 'U+0178', 'U+0131']

43 };	43 };

44	44

45 batchTestDecode(turkish);	45 batchTestDecode(turkish);

46	46

47 // FIXME: Have to add tests for Euro and a few new characters added to ISO-8859- x	47 // FIXME: Have to add tests for Euro and a few new characters added to ISO-8859- x

48 // that are NOT subsets of the corresponding Windows codepages. For instance,	48 // that are NOT subsets of the corresponding Windows codepages. For instance,

49 // ISO-8859-7:2003 has Euro at 0xA4 and a couple of other new characters.	49 // ISO-8859-7:2003 has Euro at 0xA4 and a couple of other new characters.

50 // ICU 3.8.x or later has them. Perhaps, we need to have a separate test that	50 // ICU 3.8.x or later has them. Perhaps, we need to have a separate test that

51 // can be enabled only with modern ICU.	51 // can be enabled only with modern ICU.

52	52

53 // Baltic encodings fine points.	53 // Baltic encodings fine points.

54 testDecode('ISO-8859-13', '%A1', 'U+201D');	54 testDecode('ISO-8859-13', '%A1', 'U+201D');

55 testDecode('ISO-8859-13', '%A5', 'U+201E');	55 testDecode('ISO-8859-13', '%A5', 'U+201E');

56 testDecode('ISO-8859-13', '%B4', 'U+201C');	56 testDecode('ISO-8859-13', '%B4', 'U+201C');

57 testDecode('ISO-8859-13', '%FF', 'U+2019');	57 testDecode('ISO-8859-13', '%FF', 'U+2019');

(...skipping 40 matching lines...) Expand 10 before \| Expand all \| Expand 10 after Loading...
98 testDecode('UTF-16', '%69%D8%D6%DE', 'U+D869/U+DED6');	98 testDecode('UTF-16', '%69%D8%D6%DE', 'U+D869/U+DED6');

99 testDecode('ISO-10646-UCS-2', '%69%D8%D6%DE', 'U+D869/U+DED6');	99 testDecode('ISO-10646-UCS-2', '%69%D8%D6%DE', 'U+D869/U+DED6');

100 testDecode('UCS-2', '%69%D8%D6%DE', 'U+D869/U+DED6');	100 testDecode('UCS-2', '%69%D8%D6%DE', 'U+D869/U+DED6');

101 testDecode('Unicode', '%69%D8%D6%DE', 'U+D869/U+DED6');	101 testDecode('Unicode', '%69%D8%D6%DE', 'U+D869/U+DED6');

102 testDecode('csUnicode', '%69%D8%D6%DE', 'U+D869/U+DED6');	102 testDecode('csUnicode', '%69%D8%D6%DE', 'U+D869/U+DED6');

103	103

104 // UTF-16BE and variants.	104 // UTF-16BE and variants.

105 testDecode('UTF-16BE', '%D8%69%DE%D6', 'U+D869/U+DED6');	105 testDecode('UTF-16BE', '%D8%69%DE%D6', 'U+D869/U+DED6');

106 testDecode('unicodeFFFE', '%D8%69%DE%D6', 'U+D869/U+DED6');	106 testDecode('unicodeFFFE', '%D8%69%DE%D6', 'U+D869/U+DED6');

107	107

	108 // Replacement encodings should decode as replacement (U+FFFD) then EOF

	109 testDecode("csiso2022kr", "%41%42%43%61%62%63%31%32%33%A0", "U+FFFD");

	110 testDecode("hz-gb-2312", "%41%42%43%61%62%63%31%32%33%A0", "U+FFFD");

	111 testDecode("iso-2022-cn", "%41%42%43%61%62%63%31%32%33%A0", "U+FFFD");

	112 testDecode("iso-2022-cn-ext", "%41%42%43%61%62%63%31%32%33%A0", "U+FFFD");

	113 testDecode("iso-2022-kr", "%41%42%43%61%62%63%31%32%33%A0", "U+FFFD");

	114

108 </script>	115 </script>

109 </body>	116 </body>

110 </html>	117 </html>

OLD	NEW

« no previous file with comments | « LayoutTests/TestExpectations ('k') | LayoutTests/fast/encoding/char-decoding-expected.txt » ('j') | no next file with comments »