strdup16to8.c revision 4f6e8d7a00cbeda1e70cc15be9c4af1018bdad53
1/* libs/cutils/strdup16to8.c
2**
3** Copyright 2006, The Android Open Source Project
4**
5** Licensed under the Apache License, Version 2.0 (the "License");
6** you may not use this file except in compliance with the License.
7** You may obtain a copy of the License at
8**
9**     http://www.apache.org/licenses/LICENSE-2.0
10**
11** Unless required by applicable law or agreed to in writing, software
12** distributed under the License is distributed on an "AS IS" BASIS,
13** WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14** See the License for the specific language governing permissions and
15** limitations under the License.
16*/
17
18#include <cutils/jstring.h>
19#include <assert.h>
20#include <stdlib.h>
21
22
23/**
24 * Given a UTF-16 string, compute the length of the corresponding UTF-8
25 * string in bytes.
26 */
27extern size_t strnlen16to8(const char16_t* utf16Str, size_t len)
28{
29   size_t utf8Len = 0;
30
31   while (len--) {
32       unsigned int uic = *utf16Str++;
33
34       if (uic > 0x07ff)
35           utf8Len += 3;
36       else if (uic > 0x7f || uic == 0)
37           utf8Len += 2;
38       else
39           utf8Len++;
40   }
41   return utf8Len;
42}
43
44
45/**
46 * Convert a Java-Style UTF-16 string + length to a JNI-Style UTF-8 string.
47 *
48 * This basically means: embedded \0's in the UTF-16 string are encoded
49 * as "0xc0 0x80"
50 *
51 * Make sure you allocate "utf8Str" with the result of strlen16to8() + 1,
52 * not just "len".
53 *
54 * Please note, a terminated \0 is always added, so your result will always
55 * be "strlen16to8() + 1" bytes long.
56 */
57extern char* strncpy16to8(char* utf8Str, const char16_t* utf16Str, size_t len)
58{
59    char* utf8cur = utf8Str;
60
61    while (len--) {
62        unsigned int uic = *utf16Str++;
63
64        if (uic > 0x07ff) {
65            *utf8cur++ = (uic >> 12) | 0xe0;
66            *utf8cur++ = ((uic >> 6) & 0x3f) | 0x80;
67            *utf8cur++ = (uic & 0x3f) | 0x80;
68        } else if (uic > 0x7f || uic == 0) {
69            *utf8cur++ = (uic >> 6) | 0xc0;
70            *utf8cur++ = (uic & 0x3f) | 0x80;
71        } else {
72            *utf8cur++ = uic;
73
74            if (uic == 0) {
75                break;
76            }
77        }
78    }
79
80   *utf8cur = '\0';
81
82   return utf8Str;
83}
84
85/**
86 * Convert a UTF-16 string to UTF-8.
87 *
88 * Make sure you allocate "dest" with the result of strblen16to8(),
89 * not just "strlen16()".
90 */
91char * strndup16to8 (const char16_t* s, size_t n)
92{
93    char *ret;
94
95    if (s == NULL) {
96        return NULL;
97    }
98
99    ret = malloc(strnlen16to8(s, n) + 1);
100
101    strncpy16to8 (ret, s, n);
102
103    return ret;
104}
105