1 /*
2 * Copyright (C) 2014 The Android Open Source Project
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * * Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * * Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in
12 * the documentation and/or other materials provided with the
13 * distribution.
14 *
15 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
16 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
17 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
18 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
19 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
20 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
21 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
22 * OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
23 * AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
24 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
25 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
26 * SUCH DAMAGE.
27 */
28
29 #include <assert.h>
30 #include <errno.h>
31 #include <uchar.h>
32 #include <wchar.h>
33
34 #include "private/bionic_mbstate.h"
35
mbspartialc16(const mbstate_t * state)36 static inline bool mbspartialc16(const mbstate_t* state) {
37 return mbstate_get_byte(state, 3) != 0;
38 }
39
begin_surrogate(char32_t c32,char16_t * pc16,size_t nconv,mbstate_t * state)40 static size_t begin_surrogate(char32_t c32, char16_t* pc16,
41 size_t nconv, mbstate_t* state) {
42 c32 -= 0x10000;
43 char16_t trail = (c32 & 0x3ff) | 0xdc00;
44
45 mbstate_set_byte(state, 0, trail & 0x00ff);
46 mbstate_set_byte(state, 1, (trail & 0xff00) >> 8);
47 mbstate_set_byte(state, 3, nconv & 0xff);
48
49 *pc16 = ((c32 & 0xffc00) >> 10) | 0xd800;
50 // https://issuetracker.google.com/289419882
51 //
52 // We misread the spec when implementing this. The first call should return
53 // the length of the decoded character, and the second call should return -3
54 // to indicate that the output is a continuation of the character decoded by
55 // the first call.
56 //
57 // C23 7.30.1.3.4:
58 //
59 // between 1 and n inclusive if the next n or fewer bytes complete a valid
60 // multibyte character (which is the value stored); the value returned is
61 // the number of bytes that complete the multibyte character.
62 //
63 // (size_t)(-3) if the next character resulting from a previous call has
64 // been stored (no bytes from the input have been consumed by this call).
65 //
66 // The first call returns the number of bytes consumed, and the second call
67 // returns -3.
68 //
69 // All UTF-8 sequences that encode a surrogate pair are 4 bytes, but we may
70 // not have seen the full sequence yet.
71 return nconv;
72 }
73
finish_surrogate(char16_t * pc16,mbstate_t * state)74 static size_t finish_surrogate(char16_t* pc16, mbstate_t* state) {
75 char16_t trail = mbstate_get_byte(state, 1) << 8 |
76 mbstate_get_byte(state, 0);
77 *pc16 = trail;
78 mbstate_reset(state);
79 return static_cast<size_t>(-3);
80 }
81
mbrtoc16(char16_t * pc16,const char * s,size_t n,mbstate_t * ps)82 size_t mbrtoc16(char16_t* pc16, const char* s, size_t n, mbstate_t* ps) {
83 static mbstate_t __private_state;
84 mbstate_t* state = (ps == nullptr) ? &__private_state : ps;
85
86 char16_t __private_pc16;
87 if (pc16 == nullptr) {
88 pc16 = &__private_pc16;
89 }
90
91 if (mbspartialc16(state)) {
92 return finish_surrogate(pc16, state);
93 }
94
95 char32_t c32;
96 size_t nconv = mbrtoc32(&c32, s, n, state);
97 if (__MB_IS_ERR(nconv)) {
98 return nconv;
99 } else if (nconv == 0) {
100 return mbstate_reset_and_return(nconv, state);
101 } else if (c32 < 0x10000) {
102 *pc16 = static_cast<char16_t>(c32);
103 return mbstate_reset_and_return(nconv, state);
104 } else if (c32 > 0x10ffff) {
105 // This case is currently handled by mbrtoc32() returning an error, but
106 // if that function is extended to cover 5-byte sequences (which are
107 // illegal at the moment), we'd need to explicitly handle the case of
108 // codepoints that can't be represented as a surrogate pair here.
109 return mbstate_reset_and_return_illegal(EILSEQ, state);
110 } else {
111 return begin_surrogate(c32, pc16, nconv, state);
112 }
113 }
114