blob: e95289e4714d207c30cd6e4c8cd8d87fab545430 [file] [log] [blame]
Elliott Hughes2faa5f12012-01-30 14:42:07 -08001/*
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 */
Elliott Hughes814e4032011-08-23 12:07:56 -070016
17#ifndef ART_SRC_UTF_H_
18#define ART_SRC_UTF_H_
19
Elliott Hughes76160052012-12-12 16:31:20 -080020#include "base/macros.h"
21
Elliott Hughes814e4032011-08-23 12:07:56 -070022#include <stddef.h>
23#include <stdint.h>
24
Elliott Hughesb465ab02011-08-24 11:21:21 -070025/*
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 */
Elliott Hughes814e4032011-08-23 12:07:56 -070031namespace art {
32
Ian Rogers0cfe1fb2011-08-26 03:29:44 -070033template<class T> class PrimitiveArray;
34typedef PrimitiveArray<uint16_t> CharArray;
35
Elliott Hughes814e4032011-08-23 12:07:56 -070036/*
37 * Returns the number of UTF-16 characters in the given modified UTF-8 string.
38 */
39size_t CountModifiedUtf8Chars(const char* utf8);
40
41/*
42 * Returns the number of modified UTF-8 bytes needed to represent the given
43 * UTF-16 string.
44 */
45size_t CountUtf8Bytes(const uint16_t* chars, size_t char_count);
46
47/*
Elliott Hughesb465ab02011-08-24 11:21:21 -070048 * Convert from Modified UTF-8 to UTF-16.
Elliott Hughes814e4032011-08-23 12:07:56 -070049 */
Elliott Hughesb465ab02011-08-24 11:21:21 -070050void ConvertModifiedUtf8ToUtf16(uint16_t* utf16_out, const char* utf8_in);
51
52/*
Ian Rogers0571d352011-11-03 19:51:38 -070053 * Compare two modified UTF-8 strings as UTF-16 code point values in a non-locale sensitive manner
54 */
55int CompareModifiedUtf8ToModifiedUtf8AsUtf16CodePointValues(const char* utf8_1, const char* utf8_2);
56
57/*
Elliott Hughesb465ab02011-08-24 11:21:21 -070058 * Convert from UTF-16 to Modified UTF-8. Note that the output is _not_
59 * NUL-terminated. You probably need to call CountUtf8Bytes before calling
60 * this anyway, so if you want a NUL-terminated string, you know where to
61 * put the NUL byte.
62 */
63void ConvertUtf16ToModifiedUtf8(char* utf8_out, const uint16_t* utf16_in, size_t char_count);
Elliott Hughes814e4032011-08-23 12:07:56 -070064
65/*
66 * The java.lang.String hashCode() algorithm.
67 */
Ian Rogers00f7d0e2012-07-19 15:28:27 -070068int32_t ComputeUtf16Hash(const CharArray* chars, int32_t offset, size_t char_count)
Ian Rogersb726dcb2012-09-05 08:57:23 -070069 SHARED_LOCKS_REQUIRED(Locks::mutator_lock_);
Elliott Hughes814e4032011-08-23 12:07:56 -070070int32_t ComputeUtf16Hash(const uint16_t* chars, size_t char_count);
71
72/*
73 * Retrieve the next UTF-16 character from a UTF-8 string.
74 *
75 * Advances "*utf8_data_in" to the start of the next character.
76 *
77 * WARNING: If a string is corrupted by dropping a '\0' in the middle
78 * of a 3-byte sequence, you can end up overrunning the buffer with
79 * reads (and possibly with the writes if the length was computed and
80 * cached before the damage). For performance reasons, this function
81 * assumes that the string being parsed is known to be valid (e.g., by
82 * already being verified). Most strings we process here are coming
83 * out of dex files or other internal translations, so the only real
84 * risk comes from the JNI NewStringUTF call.
85 */
86uint16_t GetUtf16FromUtf8(const char** utf8_data_in);
87
88} // namespace art
89
90#endif // ART_SRC_UTF_H_