OLD | NEW |
| (Empty) |
1 // Copyright (c) 2006, Google Inc. | |
2 // All rights reserved. | |
3 // | |
4 // Redistribution and use in source and binary forms, with or without | |
5 // modification, are permitted provided that the following conditions are | |
6 // met: | |
7 // | |
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 | |
11 // copyright notice, this list of conditions and the following disclaimer | |
12 // in the documentation and/or other materials provided with the | |
13 // distribution. | |
14 // * Neither the name of Google Inc. nor the names of its | |
15 // contributors may be used to endorse or promote products derived from | |
16 // this software without specific prior written permission. | |
17 // | |
18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
19 // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
20 // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | |
21 // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT | |
22 // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
23 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
24 // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, | |
25 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY | |
26 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
27 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
28 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
29 | |
30 #include "common/convert_UTF.h" | |
31 #include "processor/scoped_ptr.h" | |
32 #include "common/string_conversion.h" | |
33 #include <string.h> | |
34 | |
35 namespace google_breakpad { | |
36 | |
37 using std::string; | |
38 using std::vector; | |
39 | |
40 void UTF8ToUTF16(const char *in, vector<u_int16_t> *out) { | |
41 size_t source_length = strlen(in); | |
42 const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in); | |
43 const UTF8 *source_end_ptr = source_ptr + source_length; | |
44 // Erase the contents and zero fill to the expected size | |
45 out->empty(); | |
46 out->insert(out->begin(), source_length, 0); | |
47 u_int16_t *target_ptr = &(*out)[0]; | |
48 u_int16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(u_int16_t); | |
49 ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr, | |
50 &target_ptr, target_end_ptr, | |
51 strictConversion); | |
52 | |
53 // Resize to be the size of the # of converted characters + NULL | |
54 out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0); | |
55 } | |
56 | |
57 int UTF8ToUTF16Char(const char *in, int in_length, u_int16_t out[2]) { | |
58 const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in); | |
59 const UTF8 *source_end_ptr = source_ptr + sizeof(char); | |
60 u_int16_t *target_ptr = out; | |
61 u_int16_t *target_end_ptr = target_ptr + 2 * sizeof(u_int16_t); | |
62 out[0] = out[1] = 0; | |
63 | |
64 // Process one character at a time | |
65 while (1) { | |
66 ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr, | |
67 &target_ptr, target_end_ptr, | |
68 strictConversion); | |
69 | |
70 if (result == conversionOK) | |
71 return source_ptr - reinterpret_cast<const UTF8 *>(in); | |
72 | |
73 // Add another character to the input stream and try again | |
74 source_ptr = reinterpret_cast<const UTF8 *>(in); | |
75 ++source_end_ptr; | |
76 | |
77 if (source_end_ptr > reinterpret_cast<const UTF8 *>(in) + in_length) | |
78 break; | |
79 } | |
80 | |
81 return 0; | |
82 } | |
83 | |
84 void UTF32ToUTF16(const wchar_t *in, vector<u_int16_t> *out) { | |
85 size_t source_length = wcslen(in); | |
86 const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(in); | |
87 const UTF32 *source_end_ptr = source_ptr + source_length; | |
88 // Erase the contents and zero fill to the expected size | |
89 out->empty(); | |
90 out->insert(out->begin(), source_length, 0); | |
91 u_int16_t *target_ptr = &(*out)[0]; | |
92 u_int16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(u_int16_t); | |
93 ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr, | |
94 &target_ptr, target_end_ptr, | |
95 strictConversion); | |
96 | |
97 // Resize to be the size of the # of converted characters + NULL | |
98 out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0); | |
99 } | |
100 | |
101 void UTF32ToUTF16Char(wchar_t in, u_int16_t out[2]) { | |
102 const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(&in); | |
103 const UTF32 *source_end_ptr = source_ptr + 1; | |
104 u_int16_t *target_ptr = out; | |
105 u_int16_t *target_end_ptr = target_ptr + 2 * sizeof(u_int16_t); | |
106 out[0] = out[1] = 0; | |
107 ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr, | |
108 &target_ptr, target_end_ptr, | |
109 strictConversion); | |
110 | |
111 if (result != conversionOK) { | |
112 out[0] = out[1] = 0; | |
113 } | |
114 } | |
115 | |
116 static inline u_int16_t Swap(u_int16_t value) { | |
117 return (value >> 8) | (value << 8); | |
118 } | |
119 | |
120 string UTF16ToUTF8(const vector<u_int16_t> &in, bool swap) { | |
121 const UTF16 *source_ptr = &in[0]; | |
122 scoped_ptr<u_int16_t> source_buffer; | |
123 | |
124 // If we're to swap, we need to make a local copy and swap each byte pair | |
125 if (swap) { | |
126 int idx = 0; | |
127 source_buffer.reset(new u_int16_t[in.size()]); | |
128 UTF16 *source_buffer_ptr = source_buffer.get(); | |
129 for (vector<u_int16_t>::const_iterator it = in.begin(); | |
130 it != in.end(); ++it, ++idx) | |
131 source_buffer_ptr[idx] = Swap(*it); | |
132 | |
133 source_ptr = source_buffer.get(); | |
134 } | |
135 | |
136 // The maximum expansion would be 4x the size of the input string. | |
137 const UTF16 *source_end_ptr = source_ptr + in.size(); | |
138 int target_capacity = in.size() * 4; | |
139 scoped_array<UTF8> target_buffer(new UTF8[target_capacity]); | |
140 UTF8 *target_ptr = target_buffer.get(); | |
141 UTF8 *target_end_ptr = target_ptr + target_capacity; | |
142 ConversionResult result = ConvertUTF16toUTF8(&source_ptr, source_end_ptr, | |
143 &target_ptr, target_end_ptr, | |
144 strictConversion); | |
145 | |
146 if (result == conversionOK) { | |
147 const char *targetPtr = reinterpret_cast<const char *>(target_buffer.get()); | |
148 string result(targetPtr); | |
149 return result; | |
150 } | |
151 | |
152 return ""; | |
153 } | |
154 | |
155 } // namespace google_breakpad | |
OLD | NEW |