Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(363)

Side by Side Diff: utils/string_encoding/unicode_core.dart

Issue 9233041: String encoding utility methods and tests for Unicode, UTF-8, -16 and -32. (Closed) Base URL: https://dart.googlecode.com/svn/branches/bleeding_edge/dart
Patch Set: updates to comments. Created 8 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:
View unified diff | Download patch | Annotate | Revision Log
« no previous file with comments | « utils/string_encoding/Utf8_impl.dart ('k') | utils/tests/string_encoding/DUnit.dart » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
(Empty)
1 // Copyright (c) 2012, the Dart project authors. Please see the AUTHORS file
2 // for details. All rights reserved. Use of this source code is governed by a
3 // BSD-style license that can be found in the LICENSE file.
4
5 #library("unicode_core");
6
7 /*
8 * Test for presence of bug related to the use of UTF-16 code units for
9 * Dart compiled to JS.
10 */
11 bool _test16BitCodeUnit = null;
12 // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
13 // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
14 // removing after this issue is resolved.
15 bool is16BitCodeUnit() {
16 if (_test16BitCodeUnit == null) {
17 _test16BitCodeUnit = (new String.fromCharCodes([0x1D11E])) ==
18 (new String.fromCharCodes([0xD11E]));
19 }
20 return _test16BitCodeUnit;
21 }
22
23 /**
24 * Invalid codepoints or encodings may be substituted with the value U+fffd.
25 */
26 final int UNICODE_REPLACEMENT_CHARACTER_CODEPOINT = 0xfffd;
27 final int UNICODE_BOM = 0xfeff;
28 final int UNICODE_UTF_BOM_LO = 0xff;
29 final int UNICODE_UTF_BOM_HI = 0xfe;
30
31 final int UNICODE_BYTE_ZERO_MASK = 0xff;
32 final int UNICODE_BYTE_ONE_MASK = 0xff00;
33 final int UNICODE_VALID_RANGE_MAX = 0x10ffff;
34 final int UNICODE_PLANE_ONE_MAX = 0xffff;
35 final int UNICODE_UTF16_RESERVED_LO = 0xd800;
36 final int UNICODE_UTF16_RESERVED_HI = 0xdfff;
37 final int UNICODE_UTF16_OFFSET = 0x10000;
38 final int UNICODE_UTF16_SURROGATE_UNIT_0_BASE = 0xd800;
39 final int UNICODE_UTF16_SURROGATE_UNIT_1_BASE = 0xdc00;
40 final int UNICODE_UTF16_HI_MASK = 0xffc00;
41 final int UNICODE_UTF16_LO_MASK = 0x3ff;
42
43 /**
44 * Encode code points as UTF16 code units.
45 */
46 List<int> codepointsToUtf16CodeUnits(
47 List<int> codepoints, [int offset = 0, int length,
48 int replacementCodepoint = UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]) {
49 if (!(offset >= 0)) {
50 throw new IllegalArgumentException("offset");
51 }
52
53 if (!(length == null || length >= 0)) {
54 throw new IllegalArgumentException("length");
55 }
56
57 int end = length != null ?
58 Math.min(codepoints.length, offset + length) :
59 codepoints.length;
60
61 int encodedLength = 0;
62 for (int i = offset; i < end; i++) {
63 int value = codepoints[i];
64 if ((value >= 0 && value < UNICODE_UTF16_RESERVED_LO) ||
65 (value > UNICODE_UTF16_RESERVED_HI && value <= UNICODE_PLANE_ONE_MAX)) {
66 encodedLength++;
67 } else if (value > UNICODE_PLANE_ONE_MAX &&
68 value <= UNICODE_VALID_RANGE_MAX) {
69 encodedLength += 2;
70 } else {
71 encodedLength++;
72 }
73 }
74
75 void addReplacementCodepoint(List<int> codepointBuffer, int offset,
76 int replacementCodepoint) {
77 if(replacementCodepoint != null) {
78 codepointBuffer[offset] = replacementCodepoint;
79 } else {
80 throw new IllegalArgumentException("Invalid encoding");
81 }
82 }
83 List<int> codeUnitsBuffer = new List<int>(encodedLength);
84 int j = 0;
85 for (int i = offset; i < end; i++) {
86 int value = codepoints[i];
87 if ((value >= 0 && value < UNICODE_UTF16_RESERVED_LO) ||
88 (value > UNICODE_UTF16_RESERVED_HI && value <= UNICODE_PLANE_ONE_MAX)) {
89 codeUnitsBuffer[j++] = value;
90 } else if (value > UNICODE_PLANE_ONE_MAX &&
91 value <= UNICODE_VALID_RANGE_MAX) {
92 int base = value - UNICODE_UTF16_OFFSET;
93 codeUnitsBuffer[j++] = UNICODE_UTF16_SURROGATE_UNIT_0_BASE +
94 ((base & UNICODE_UTF16_HI_MASK) >> 10);
95 codeUnitsBuffer[j++] = UNICODE_UTF16_SURROGATE_UNIT_1_BASE +
96 (base & UNICODE_UTF16_LO_MASK);
97 } else {
98 addReplacementCodepoint(codeUnitsBuffer, j++, replacementCodepoint);
99 }
100 }
101 return codeUnitsBuffer;
102 }
103
104 /**
105 * Decodes the utf16 codeunits to codepoints.
106 */
107 List<int> utf16CodeUnitsToCodepoints(
108 List<int> utf16CodeUnits, [int offset = 0, int length,
109 int replacementCodepoint = UNICODE_REPLACEMENT_CHARACTER_CODEPOINT]) {
110 if (!(offset >= 0)) {
111 throw new IllegalArgumentException("offset");
112 }
113
114 if (!(length == null || length >= 0)) {
115 throw new IllegalArgumentException("length");
116 }
117
118 int end = length != null ?
119 Math.min(utf16CodeUnits.length, offset + length) :
120 utf16CodeUnits.length;
121
122 void addReplacementCodepoint(void f(int v), int replacementCodepoint) {
123 if(replacementCodepoint != null) {
124 f(replacementCodepoint);
125 } else {
126 throw new IllegalArgumentException("Invalid encoding");
127 }
128 }
129
130 void apply(void f(int v)) {
131 int i = offset;
132 // skip the first entry if it is a BOM.
133 if (end > 0 && utf16CodeUnits[0] == UNICODE_BOM) {
134 i++;
135 }
136 while (i < end) {
137 int value = utf16CodeUnits[i++];
138 if (value < 0) {
139 addReplacementCodepoint(f, replacementCodepoint);
140 continue;
141 }
142 if (value < UNICODE_UTF16_RESERVED_LO ||
143 (value > UNICODE_UTF16_RESERVED_HI &&
144 value <= UNICODE_PLANE_ONE_MAX)) {
145 // transfer directly
146 f(value);
147 } else if (value < UNICODE_UTF16_SURROGATE_UNIT_1_BASE && i < end) {
148 // merge surrogate pair
149 int nextValue = utf16CodeUnits[i++];
150 if (nextValue >= UNICODE_UTF16_SURROGATE_UNIT_1_BASE &&
151 nextValue <= UNICODE_UTF16_RESERVED_HI) {
152 value = (value - UNICODE_UTF16_SURROGATE_UNIT_0_BASE) << 10;
153 value += UNICODE_UTF16_OFFSET +
154 (nextValue - UNICODE_UTF16_SURROGATE_UNIT_1_BASE);
155 f(value);
156 } else {
157 if (nextValue >= UNICODE_UTF16_SURROGATE_UNIT_0_BASE &&
158 nextValue < UNICODE_UTF16_SURROGATE_UNIT_1_BASE) {
159 i--;
160 }
161 addReplacementCodepoint(f, replacementCodepoint);
162 continue;
163 }
164 } else {
165 addReplacementCodepoint(f, replacementCodepoint);
166 continue;
167 }
168 }
169 }
170 int codepointBufferLength = 0;
171 apply(void _(int value) {
172 codepointBufferLength++;
173 });
174
175 List<int> codepointBuffer = new List<int>(codepointBufferLength);
176 int i = 0;
177 apply(void _(int value) {
178 codepointBuffer[i++] = value;
179 });
180 return codepointBuffer;
181 }
OLDNEW
« no previous file with comments | « utils/string_encoding/Utf8_impl.dart ('k') | utils/tests/string_encoding/DUnit.dart » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698