blob: a9d29a626a31a3e376ec232b9989a59ecf992c06 [file] [log] [blame]
Elliott Hughes814e4032011-08-23 12:07:56 -07001// Copyright 2011 Google Inc. All Rights Reserved.
2
3#ifndef ART_SRC_UTF_H_
4#define ART_SRC_UTF_H_
5
6#include <stddef.h>
7#include <stdint.h>
8
9namespace art {
10
11/*
12 * Returns the number of UTF-16 characters in the given modified UTF-8 string.
13 */
14size_t CountModifiedUtf8Chars(const char* utf8);
15
16/*
17 * Returns the number of modified UTF-8 bytes needed to represent the given
18 * UTF-16 string.
19 */
20size_t CountUtf8Bytes(const uint16_t* chars, size_t char_count);
21
22/*
23 * Convert Modified UTF-8 to UTF-16.
24 * http://en.wikipedia.org/wiki/UTF-8#Modified_UTF-8
25 */
26void ConvertModifiedUtf8ToUtf16(uint16_t* utf16_data_out, const char* utf8_data_in);
27
28/*
29 * The java.lang.String hashCode() algorithm.
30 */
31int32_t ComputeUtf16Hash(const uint16_t* chars, size_t char_count);
32
33/*
34 * Retrieve the next UTF-16 character from a UTF-8 string.
35 *
36 * Advances "*utf8_data_in" to the start of the next character.
37 *
38 * WARNING: If a string is corrupted by dropping a '\0' in the middle
39 * of a 3-byte sequence, you can end up overrunning the buffer with
40 * reads (and possibly with the writes if the length was computed and
41 * cached before the damage). For performance reasons, this function
42 * assumes that the string being parsed is known to be valid (e.g., by
43 * already being verified). Most strings we process here are coming
44 * out of dex files or other internal translations, so the only real
45 * risk comes from the JNI NewStringUTF call.
46 */
47uint16_t GetUtf16FromUtf8(const char** utf8_data_in);
48
49} // namespace art
50
51#endif // ART_SRC_UTF_H_