Home
last modified time | relevance | path

Searched +full:utf +full:- +full:8 (Results 1 – 25 of 1210) sorted by relevance

12345678910>>...49

/external/libxkbcommon/test/data/locale/
Dlocale.dir8 iso8859-1/XLC_LOCALE af_ZA.ISO8859-1
9 iso8859-6/XLC_LOCALE ar_AA.ISO8859-6
10 iso8859-6/XLC_LOCALE ar_BH.ISO8859-6
11 iso8859-6/XLC_LOCALE ar_DZ.ISO8859-6
12 iso8859-6/XLC_LOCALE ar_EG.ISO8859-6
13 iso8859-6/XLC_LOCALE ar_IQ.ISO8859-6
14 iso8859-6/XLC_LOCALE ar_JO.ISO8859-6
15 iso8859-6/XLC_LOCALE ar_KW.ISO8859-6
16 iso8859-6/XLC_LOCALE ar_LB.ISO8859-6
17 iso8859-6/XLC_LOCALE ar_LY.ISO8859-6
[all …]
Dcompose.dir7 iso8859-1/Compose C
8 iso8859-1/Compose af_ZA.ISO8859-1
9 iso8859-6/Compose ar_AA.ISO8859-6
10 iso8859-6/Compose ar_AE.ISO8859-6
11 iso8859-6/Compose ar_BH.ISO8859-6
12 iso8859-6/Compose ar_DZ.ISO8859-6
13 iso8859-6/Compose ar_EG.ISO8859-6
14 iso8859-6/Compose ar_IQ.ISO8859-6
15 iso8859-6/Compose ar_JO.ISO8859-6
16 iso8859-6/Compose ar_KW.ISO8859-6
[all …]
Dlocale.alias9 POSIX-UTF2 C
13 C.iso88591 en_US.ISO8859-1
14 Cextend en_US.ISO8859-1
15 Cextend.en en_US.ISO8859-1
16 English_United-States.437 C
17 C.UTF-8 en_US.UTF-8
19 a3 az_AZ.KOI8-C
20 a3_AZ az_AZ.KOI8-C
21 a3_AZ.koi8c az_AZ.KOI8-C
22 a3_AZ.KOI-C az_AZ.KOI8-C
[all …]
/external/python/cpython3/Lib/
Dlocale.py3 The module provides low-level access to the C lib's locale APIs and adds high
25 # Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
34 """ strcoll(string,string) -> int.
37 return (a > b) - (a < b)
40 """ strxfrm(string) -> string.
41 Returns a string that behaves for cmp locale-aware.
64 """ localeconv() -> dict.
65 Returns numeric and monetary locale-specific parameters.
88 """ setlocale(integer,string=None) -> string.
125 # if grouping is -1, we are done
[all …]
/external/tensorflow/tensorflow/python/kernel_tests/strings_ops/
Dunicode_transcode_op_test.py7 # http://www.apache.org/licenses/LICENSE-2.0
26 # Note: for now only tests for algorithmic converters since no file-based
37 input_encoding="UTF-8",
38 output_encoding="UTF-8",
47 input_encoding="ISO-8859-1",
48 output_encoding="UTF-8",
57 input_encoding="US-ASCII",
58 output_encoding="UTF-8",
67 expected = [s.decode("UTF-16-BE").encode("UTF-8") for s in strings]
72 input_encoding="UTF-16",
[all …]
Dunicode_decode_op_test.py1 # -*- coding: utf-8 -*-
8 # http://www.apache.org/licenses/LICENSE-2.0
47 b = list(x.encode("utf-32-be"))
50 return [(b0 << 24) + (b1 << 16) + (b2 << 8) + b3
61 encoded_x = x.encode("utf-32-be")
64 len(c.decode("utf-32-be").encode(encoding)) for c in encoded_chars
66 return [0] + np.cumsum(char_lens).tolist()[:-1]
74 b = x.encode("utf-32-be")
77 return [b"".join(c).decode("utf-32-be").encode(encoding) for c in chars]
79 return [bytes(c).decode("utf-32-be").encode(encoding) for c in chars]
[all …]
/external/python/cpython2/Lib/
Dlocale.py3 The module provides low-level access to the C lib's locale APIs and adds high
35 # Yuck: LC_MESSAGES is non-standard: can't tell whether it exists before
62 """ localeconv() -> dict.
63 Returns numeric and monetary locale-specific parameters.
86 """ setlocale(integer,string=None) -> string.
94 """ strcoll(string,string) -> int.
100 """ strxfrm(string) -> string.
101 Returns a string that behaves for cmp locale-aware.
129 # if grouping is -1, we are done
132 # 0: re-use last group ad infinitum
[all …]
/external/lzma/CPP/Common/
DUTFConvert.h49 if (NonUtf) s.Add_OptSpaced("non-UTF8"); in PrintStatus()
84 if (allowReduced == false) - all UTF-8 character sequences must be finished.
85 if (allowReduced == true) - it allows truncated last character-Utf8-sequence
100 it processes SINGLE-SURROGATE-8 as valid Unicode point.
101 it converts SINGLE-SURROGATE-8 to SINGLE-SURROGATE-16
102 Note: some sequencies of two SINGLE-SURROGATE-8 points
103 will generate correct SURROGATE-16-PAIR, and
104 that SURROGATE-16-PAIR later will be converted to correct
105 UTF8-SURROGATE-21 point. So we don't restore original
106 STR-8 sequence in that case.
[all …]
/external/apache-commons-io/src/test/java/org/apache/commons/io/input/
DXmlStreamReaderUtilitiesTest.java9 * http://www.apache.org/licenses/LICENSE-2.0
46 private static final String APPXML_UTF8 = "application/xml;charset=UTF-8";
47 private static final String APPXML_UTF16 = "application/xml;charset=UTF-16";
48 private static final String APPXML_UTF32 = "application/xml;charset=UTF-32";
49 private static final String APPXML_UTF16BE = "application/xml;charset=UTF-16BE";
50 private static final String APPXML_UTF16LE = "application/xml;charset=UTF-16LE";
51 private static final String APPXML_UTF32BE = "application/xml;charset=UTF-32BE";
52 private static final String APPXML_UTF32LE = "application/xml;charset=UTF-32LE";
156 checkAppXml(true, "application/xml-dtd"); in testAppXml()
157 checkAppXml(true, "application/xml-external-parsed-entity"); in testAppXml()
[all …]
DXmlStreamReaderTest.java9 * http://www.apache.org/licenses/LICENSE-2.0
59 private static final String UTF_32 = "UTF-32";
60 private static final String UTF_32LE = "UTF-32LE";
61 private static final String UTF_32BE = "UTF-32BE";
63 private static final String XML5 = "xml-prolog-encoding-spaced-single-quotes";
64 private static final String XML4 = "xml-prolog-encoding-single-quotes";
65 private static final String XML3 = "xml-prolog-encoding-double-quotes";
66 private static final String XML2 = "xml-prolog";
91 BOMs.put("no-bom", NO_BOM_BYTES);
92 BOMs.put("UTF-16BE-bom", UTF_16BE_BOM_BYTES);
[all …]
/external/icu/icu4j/main/core/src/test/resources/com/ibm/icu/dev/test/charsetdet/
DCharsetDetectionTests.xml1 <?xml version="1.0" encoding="UTF-8"?>
3 <!-- Copyright (C) 2016 and later: Unicode, Inc. and others. -->
4 <!-- License & terms of use: http://www.unicode.org/copyright.html -->
5 <!-- Copyright (c) 2005-2015 IBM Corporation and others. All rights reserved -->
6 <!-- See individual test cases for their specific copyright. -->
8 <charset-detection-tests>
9 …<test-case id="IUC10-ar" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-6/ar window…
10 <!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
15 تسجّل الآن لحضور المؤتمر الدولي العاشر ليونيكود, الذي سيعقد في 10-12 آذار 1997 بمدينة ماينتس,
23 </test-case>
[all …]
/external/icu/android_icu4j/src/main/tests/android/icu/dev/test/charsetdet/
DCharsetDetectionTests.xml1 <?xml version="1.0" encoding="UTF-8"?>
3 <!-- Copyright (C) 2016 and later: Unicode, Inc. and others. -->
4 <!-- License & terms of use: http://www.unicode.org/copyright.html -->
5 <!-- Copyright (c) 2005-2015 IBM Corporation and others. All rights reserved -->
6 <!-- See individual test cases for their specific copyright. -->
8 <charset-detection-tests>
9 …<test-case id="IUC10-ar" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-6/ar window…
10 <!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
15 تسجّل الآن لحضور المؤتمر الدولي العاشر ليونيكود, الذي سيعقد في 10-12 آذار 1997 بمدينة ماينتس,
23 </test-case>
[all …]
/external/icu/icu4c/source/test/testdata/
Dcsdetest.xml1 <?xml version="1.0" encoding="UTF-8"?>
3 <!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.uni…
4 <!-- Copyright (c) 2005-2013 IBM Corporation and others. All rights reserved -->
5 <!-- See individual test cases for their specific copyright. -->
7 <charset-detection-tests>
8 …<test-case id="IUC10-ar" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-6/ar window…
9 <!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
14 تسجّل الآن لحضور المؤتمر الدولي العاشر ليونيكود, الذي سيعقد في 10-12 آذار 1997 بمدينة ماينتس,
22 </test-case>
24 … <test-case id="IUC10-da-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1252/da">
[all …]
/external/cronet/third_party/icu/source/test/testdata/
Dcsdetest.xml1 <?xml version="1.0" encoding="UTF-8"?>
3 <!-- Copyright (C) 2016 and later: Unicode, Inc. and others. License & terms of use: http://www.uni…
4 <!-- Copyright (c) 2005-2013 IBM Corporation and others. All rights reserved -->
5 <!-- See individual test cases for their specific copyright. -->
7 <charset-detection-tests>
8 …<test-case id="IUC10-ar" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE ISO-8859-6/ar window…
9 <!-- Copyright © 1991-2005 Unicode, Inc. All rights reserved. -->
14 تسجّل الآن لحضور المؤتمر الدولي العاشر ليونيكود, الذي سيعقد في 10-12 آذار 1997 بمدينة ماينتس,
22 </test-case>
24 … <test-case id="IUC10-da-Q" encodings="UTF-8 UTF-16LE UTF-16BE UTF-32BE UTF-32LE windows-1252/da">
[all …]
/external/tensorflow/tensorflow/python/
Dpywrap_mlir.py7 # http://www.apache.org/licenses/LICENSE-2.0
17 # pylint: disable=invalid-import-order, g-bad-import-order, wildcard-import, unused-import, undefin…
32 str(graphdef).encode('utf-8'), pass_pipeline.encode('utf-8'),
33 show_debug_info, ','.join(input_names).encode('utf-8'),
34 ','.join(input_data_types).encode('utf-8'),
35 ':'.join(input_data_shapes).encode('utf-8'),
36 ','.join(output_names).encode('utf-8'))
38 str(graphdef).encode('utf-8'), pass_pipeline.encode('utf-8'),
46 str(concrete_function.function_def).encode('utf-8'),
47 pass_pipeline.encode('utf-8'), show_debug_info)
[all …]
/external/libcups/cups/
Dtranscode.c4 * Copyright 2007-2014 by Apple Inc.
5 * Copyright 1997-2007 by Easy Software Products.
14 #include "cups-private.h"
15 #include "debug-internal.h"
30 static iconv_t map_from_utf8 = (iconv_t)-1;
31 /* Convert from UTF-8 to charset */
32 static iconv_t map_to_utf8 = (iconv_t)-1;
33 /* Convert from charset to UTF-8 */
40 * '_cupsCharmapFlush()' - Flush all character set maps out of cache.
47 if (map_from_utf8 != (iconv_t)-1) in _cupsCharmapFlush()
[all …]
/external/pcre/testdata/
Dtestoutput101 # This set of tests is for UTF-8 support and Unicode property support, with
2 # relevance only for the 8-bit library.
6 # The next 5 patterns have UTF-8 errors
8 /[�]/utf
9 Failed: error -8 at offset 1: UTF-8 error: byte 2 top bits not 0x80
11 /�/utf
12 Failed: error -3 at offset 0: UTF-8 error: 1 byte missing at end
14 /���xxx/utf
15 Failed: error -8 at offset 0: UTF-8 error: byte 2 top bits not 0x80
17 /��������/utf
[all …]
Dtestoutput14-81 # These test special UTF and UCP features of DFA matching. The output is
6 # ----------------------------------------------------
8 # non-DFA matching.
10 /X/utf
12 Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
14 Error -36 (bad UTF-8 offset)
18 Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
22 Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
26 Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
30 Failed: error -16: UTF-8 error: code points 0xd800-0xdfff are not defined at offset 2
[all …]
Dtestinput101 # This set of tests is for UTF-8 support and Unicode property support, with
2 # relevance only for the 8-bit library.
6 # The next 5 patterns have UTF-8 errors
8 /[�]/utf
10 /�/utf
12 /���xxx/utf
14 /��������/utf
20 /badutf/utf
21 \= Expect UTF-8 errors
62 /badutf/utf
[all …]
/external/rust/crates/grpcio-sys/grpc/third_party/utf8_range/utf8_corpus_dir/
Dutf8_corpus_kuhn.txt1 UTF-8 decoder capability and stress test
2 ----------------------------------------
4 Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> - 2015-08-28 - CC BY 4.0
6 This test file can help you examine, how your UTF-8 decoder handles
7 various types of correct, malformed, or otherwise interesting UTF-8
12 help you think about, and test, the behaviour of your UTF-8 decoder on a
14 that most first-time authors of UTF-8 decoders find at least one
17 The test lines below cover boundary conditions, malformed UTF-8
18 sequences, as well as correctly encoded UTF-8 sequences of Unicode code
19 points that should never occur in a correct UTF-8 file.
[all …]
/external/grpc-grpc/third_party/utf8_range/utf8_corpus_dir/
Dutf8_corpus_kuhn.txt1 UTF-8 decoder capability and stress test
2 ----------------------------------------
4 Markus Kuhn <http://www.cl.cam.ac.uk/~mgk25/> - 2015-08-28 - CC BY 4.0
6 This test file can help you examine, how your UTF-8 decoder handles
7 various types of correct, malformed, or otherwise interesting UTF-8
12 help you think about, and test, the behaviour of your UTF-8 decoder on a
14 that most first-time authors of UTF-8 decoders find at least one
17 The test lines below cover boundary conditions, malformed UTF-8
18 sequences, as well as correctly encoded UTF-8 sequences of Unicode code
19 points that should never occur in a correct UTF-8 file.
[all …]
/external/python/cpython3/Lib/test/test_email/
Dtest__encoded_words.py62 _ew.decode('=?utf-8?X?somevalue?=')
64 def _test(self, source, result, charset='us-ascii', lang='', defects=[]):
72 self._test('=?us-ascii?q?foo?=', 'foo')
75 self._test('=?us-ascii?b?dmk=?=', 'vi')
78 self._test('=?us-ascii?Q?foo?=', 'foo')
81 self._test('=?us-ascii?B?dmk=?=', 'vi')
84 self._test('=?latin-1?q?=20F=fcr=20Elise=20?=', ' Für Elise ', 'latin-1')
87 self._test(b'=?us-ascii?q?=20\xACfoo?='.decode('us-ascii',
93 self._test(b'=?us-ascii?b?dm\xACk?='.decode('us-ascii',
101 self._test('=?us-ascii?b?dm\x01k===?=',
[all …]
/external/protobuf/java/core/src/test/java/com/google/protobuf/
DCheckUtf8Test.java1 // Protocol Buffers - Google's data interchange format
3 // https://developers.google.com/protocol-buffers/
47 * UTF-8 checks.
74 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRequiredStringWithBadUtf8()
76 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildRequiredStringWithBadUtf8()
84 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildOptionalStringWithBadUtf8()
86 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildOptionalStringWithBadUtf8()
94 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRepeatedStringWithBadUtf8()
96 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildRepeatedStringWithBadUtf8()
111 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRequiredStringWithBadUtf8Size()
[all …]
/external/cronet/third_party/protobuf/java/core/src/test/java/com/google/protobuf/
DCheckUtf8Test.java1 // Protocol Buffers - Google's data interchange format
3 // https://developers.google.com/protocol-buffers/
47 * UTF-8 checks.
75 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRequiredStringWithBadUtf8()
77 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildRequiredStringWithBadUtf8()
85 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildOptionalStringWithBadUtf8()
87 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildOptionalStringWithBadUtf8()
95 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRepeatedStringWithBadUtf8()
97 assertThat(exception).hasMessageThat().isEqualTo("Byte string is not UTF-8."); in testBuildRepeatedStringWithBadUtf8()
112 assertWithMessage("Expected IllegalArgumentException for non UTF-8 byte string.").fail(); in testBuildRequiredStringWithBadUtf8Size()
[all …]
/external/rust/crates/bstr/src/
Dlib.rs5 difference: byte strings are only *conventionally* UTF-8 while Rust's standard
6 Unicode strings are *guaranteed* to be valid UTF-8. The primary motivation for
7 byte strings is for handling arbitrary bytes that are mostly UTF-8.
48 assert_eq!(matches, [0, 8, 12, 21]);
65 invalid UTF-8:
105 This library reflects my belief that UTF-8 by convention is a better trade
106 off in some circumstances than guaranteed UTF-8.
110 about searching valid UTF-8 encoded strings. Indeed, internally, the
112 just deals with raw bytes. UTF-8 match boundaries are then guaranteed by the
118 standard library's [`Read`](https://doc.rust-lang.org/std/io/trait.Read.html)
[all …]

12345678910>>...49