aboutsummaryrefslogtreecommitdiff
path: root/src/common/string_conversion.cc
blob: 040d3e86ea3a7a8991e425ba3501244806e7b4d7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
// Copyright (c) 2006, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//     * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#include <string.h>

#include "common/convert_UTF.h"
#include "common/scoped_ptr.h"
#include "common/string_conversion.h"
#include "common/using_std_string.h"

namespace google_breakpad {

using std::vector;

void UTF8ToUTF16(const char *in, vector<uint16_t> *out) {
  size_t source_length = strlen(in);
  const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in);
  const UTF8 *source_end_ptr = source_ptr + source_length;
  // Erase the contents and zero fill to the expected size
  out->clear();
  out->insert(out->begin(), source_length, 0);
  uint16_t *target_ptr = &(*out)[0];
  uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t);
  ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr,
                                               &target_ptr, target_end_ptr,
                                               strictConversion);

  // Resize to be the size of the # of converted characters + NULL
  out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0);
}

int UTF8ToUTF16Char(const char *in, int in_length, uint16_t out[2]) {
  const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in);
  const UTF8 *source_end_ptr = source_ptr + 1;
  uint16_t *target_ptr = out;
  uint16_t *target_end_ptr = target_ptr + 2;
  out[0] = out[1] = 0;

  // Process one character at a time
  while (1) {
    ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr,
                                                 &target_ptr, target_end_ptr,
                                                 strictConversion);

    if (result == conversionOK)
      return static_cast<int>(source_ptr - reinterpret_cast<const UTF8 *>(in));

    // Add another character to the input stream and try again
    source_ptr = reinterpret_cast<const UTF8 *>(in);
    ++source_end_ptr;

    if (source_end_ptr > reinterpret_cast<const UTF8 *>(in) + in_length)
      break;
  }

  return 0;
}

void UTF32ToUTF16(const wchar_t *in, vector<uint16_t> *out) {
  size_t source_length = wcslen(in);
  const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(in);
  const UTF32 *source_end_ptr = source_ptr + source_length;
  // Erase the contents and zero fill to the expected size
  out->clear();
  out->insert(out->begin(), source_length, 0);
  uint16_t *target_ptr = &(*out)[0];
  uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t);
  ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr,
                                                &target_ptr, target_end_ptr,
                                                strictConversion);

  // Resize to be the size of the # of converted characters + NULL
  out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0);
}

void UTF32ToUTF16Char(wchar_t in, uint16_t out[2]) {
  const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(&in);
  const UTF32 *source_end_ptr = source_ptr + 1;
  uint16_t *target_ptr = out;
  uint16_t *target_end_ptr = target_ptr + 2;
  out[0] = out[1] = 0;
  ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr,
                                                &target_ptr, target_end_ptr,
                                                strictConversion);

  if (result != conversionOK) {
    out[0] = out[1] = 0;
  }
}

static inline uint16_t Swap(uint16_t value) {
  return (value >> 8) | static_cast<uint16_t>(value << 8);
}

string UTF16ToUTF8(const vector<uint16_t> &in, bool swap) {
  const UTF16 *source_ptr = &in[0];
  scoped_array<uint16_t> source_buffer;

  // If we're to swap, we need to make a local copy and swap each byte pair
  if (swap) {
    int idx = 0;
    source_buffer.reset(new uint16_t[in.size()]);
    UTF16 *source_buffer_ptr = source_buffer.get();
    for (vector<uint16_t>::const_iterator it = in.begin();
         it != in.end(); ++it, ++idx)
      source_buffer_ptr[idx] = Swap(*it);

    source_ptr = source_buffer.get();
  }

  // The maximum expansion would be 4x the size of the input string.
  const UTF16 *source_end_ptr = source_ptr + in.size();
  size_t target_capacity = in.size() * 4;
  scoped_array<UTF8> target_buffer(new UTF8[target_capacity]);
  UTF8 *target_ptr = target_buffer.get();
  UTF8 *target_end_ptr = target_ptr + target_capacity;
  ConversionResult result = ConvertUTF16toUTF8(&source_ptr, source_end_ptr,
                                               &target_ptr, target_end_ptr,
                                               strictConversion);

  if (result == conversionOK) {
    const char *targetPtr = reinterpret_cast<const char *>(target_buffer.get());
    return targetPtr;
  }

  return "";
}

}  // namespace google_breakpad