utf.h revision fc0e3219edc9a5bf81b166e82fd5db2796eb6a0d 
1/*
2 * Copyright (C) 2011 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 *      http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17#ifndef ART_RUNTIME_UTF_H_
18#define ART_RUNTIME_UTF_H_
19
20#include "base/macros.h"
21
22#include <stddef.h>
23#include <stdint.h>
24
25/*
26 * All UTF-8 in art is actually modified UTF-8. Mostly, this distinction
27 * doesn't matter.
28 *
29 * See http://en.wikipedia.org/wiki/UTF-8#Modified_UTF-8 for the details.
30 */
31namespace art {
32namespace mirror {
33template<class T> class PrimitiveArray;
34typedef PrimitiveArray<uint16_t> CharArray;
35}  // namespace mirror
36
37/*
38 * Returns the number of UTF-16 characters in the given modified UTF-8 string.
39 */
40size_t CountModifiedUtf8Chars(const char* utf8);
41
42/*
43 * Returns the number of modified UTF-8 bytes needed to represent the given
44 * UTF-16 string.
45 */
46size_t CountUtf8Bytes(const uint16_t* chars, size_t char_count);
47
48/*
49 * Convert from Modified UTF-8 to UTF-16.
50 */
51void ConvertModifiedUtf8ToUtf16(uint16_t* utf16_out, const char* utf8_in);
52
53/*
54 * Compare two modified UTF-8 strings as UTF-16 code point values in a non-locale sensitive manner
55 */
56int CompareModifiedUtf8ToModifiedUtf8AsUtf16CodePointValues(const char* utf8_1, const char* utf8_2);
57
58/*
59 * Compare a modified UTF-8 string with a UTF-16 string as code point values in a non-locale
60 * sensitive manner.
61 */
62int CompareModifiedUtf8ToUtf16AsCodePointValues(const char* utf8_1, const uint16_t* utf8_2);
63
64/*
65 * Convert from UTF-16 to Modified UTF-8. Note that the output is _not_
66 * NUL-terminated. You probably need to call CountUtf8Bytes before calling
67 * this anyway, so if you want a NUL-terminated string, you know where to
68 * put the NUL byte.
69 */
70void ConvertUtf16ToModifiedUtf8(char* utf8_out, const uint16_t* utf16_in, size_t char_count);
71
72/*
73 * The java.lang.String hashCode() algorithm.
74 */
75int32_t ComputeUtf16Hash(const mirror::CharArray* chars, int32_t offset, size_t char_count)
76    SHARED_LOCKS_REQUIRED(Locks::mutator_lock_);
77int32_t ComputeUtf16Hash(const uint16_t* chars, size_t char_count);
78
79/*
80 * Retrieve the next UTF-16 character from a UTF-8 string.
81 *
82 * Advances "*utf8_data_in" to the start of the next character.
83 *
84 * WARNING: If a string is corrupted by dropping a '\0' in the middle
85 * of a 3-byte sequence, you can end up overrunning the buffer with
86 * reads (and possibly with the writes if the length was computed and
87 * cached before the damage). For performance reasons, this function
88 * assumes that the string being parsed is known to be valid (e.g., by
89 * already being verified). Most strings we process here are coming
90 * out of dex files or other internal translations, so the only real
91 * risk comes from the JNI NewStringUTF call.
92 */
93uint16_t GetUtf16FromUtf8(const char** utf8_data_in);
94
95}  // namespace art
96
97#endif  // ART_RUNTIME_UTF_H_
98