aboutsummaryrefslogtreecommitdiffstats
path: root/lib/charset/utf8/core.h
blob: 693d388c078de9870d2f19be75d4e7483c393e77 (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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
// Copyright 2006 Nemanja Trifunovic

/*
Permission is hereby granted, free of charge, to any person or organization
obtaining a copy of the software and accompanying documentation covered by
this license (the "Software") to use, reproduce, display, distribute,
execute, and transmit the Software, and to prepare derivative works of the
Software, and to permit third-parties to whom the Software is furnished to
do so, all subject to the following:

The copyright notices in the Software and this entire statement, including
the above license grant, this restriction and the following disclaimer,
must be included in all copies of the Software, in whole or in part, and
all derivative works of the Software, unless such copies or derivative
works are solely in the form of machine-executable object code generated by
a source language processor.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT. IN NO EVENT
SHALL THE COPYRIGHT HOLDERS OR ANYONE DISTRIBUTING THE SOFTWARE BE LIABLE
FOR ANY DAMAGES OR OTHER LIABILITY, WHETHER IN CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
DEALINGS IN THE SOFTWARE.
*/


#ifndef UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731
#define UTF8_FOR_CPP_CORE_H_2675DCD0_9480_4c0c_B92A_CC14C027B731

#include <iterator>

namespace utf8
{
    // The typedefs for 8-bit, 16-bit and 32-bit unsigned integers
    // You may need to change them to match your system.
    // These typedefs have the same names as ones from cstdint, or boost/cstdint
    typedef unsigned char   uint8_t;
    typedef unsigned short  uint16_t;
    typedef unsigned int    uint32_t;

// Helper code - not intended to be directly called by the library users. May be changed at any time
namespace internal
{
    // Unicode constants
    // Leading (high) surrogates: 0xd800 - 0xdbff
    // Trailing (low) surrogates: 0xdc00 - 0xdfff
    const uint16_t LEAD_SURROGATE_MIN  = 0xd800u;
    const uint16_t LEAD_SURROGATE_MAX  = 0xdbffu;
    const uint16_t TRAIL_SURROGATE_MIN = 0xdc00u;
    const uint16_t TRAIL_SURROGATE_MAX = 0xdfffu;
    const uint16_t LEAD_OFFSET         = LEAD_SURROGATE_MIN - (0x10000 >> 10);
    const uint32_t SURROGATE_OFFSET    = 0x10000u - (LEAD_SURROGATE_MIN << 10) - TRAIL_SURROGATE_MIN;

    // Maximum valid value for a Unicode code point
    const uint32_t CODE_POINT_MAX      = 0x0010ffffu;

    template<typename octet_type>
    inline uint8_t mask8(octet_type oc)
    {
        return static_cast<uint8_t>(0xff & oc);
    }
    template<typename u16_type>
    inline uint16_t mask16(u16_type oc)
    {
        return static_cast<uint16_t>(0xffff & oc);
    }
    template<typename octet_type>
    inline bool is_trail(octet_type oc)
    {
        return ((utf8::internal::mask8(oc) >> 6) == 0x2);
    }

    template <typename u16>
    inline bool is_lead_surrogate(u16 cp)
    {
        return (cp >= LEAD_SURROGATE_MIN && cp <= LEAD_SURROGATE_MAX);
    }

    template <typename u16>
    inline bool is_trail_surrogate(u16 cp)
    {
        return (cp >= TRAIL_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
    }

    template <typename u16>
    inline bool is_surrogate(u16 cp)
    {
        return (cp >= LEAD_SURROGATE_MIN && cp <= TRAIL_SURROGATE_MAX);
    }

    template <typename u32>
    inline bool is_code_point_valid(u32 cp)
    {
        return (cp <= CODE_POINT_MAX && !utf8::internal::is_surrogate(cp));
    }

    template <typename octet_iterator>
    inline typename std::iterator_traits<octet_iterator>::difference_type
    sequence_length(octet_iterator lead_it)
    {
        uint8_t lead = utf8::internal::mask8(*lead_it);
        if (lead < 0x80)
            return 1;
        else if ((lead >> 5) == 0x6)
            return 2;
        else if ((lead >> 4) == 0xe)
            return 3;
        else if ((lead >> 3) == 0x1e)
            return 4;
        else
            return 0;
    }

    template <typename octet_difference_type>
    inline bool is_overlong_sequence(uint32_t cp, octet_difference_type length)
    {
        if (cp < 0x80) {
            if (length != 1) 
                return true;
        }
        else if (cp < 0x800) {
            if (length != 2) 
                return true;
        }
        else if (cp < 0x10000) {
            if (length != 3) 
                return true;
        }

        return false;
    }

    enum utf_error {UTF8_OK, NOT_ENOUGH_ROOM, INVALID_LEAD, INCOMPLETE_SEQUENCE, OVERLONG_SEQUENCE, INVALID_CODE_POINT};

    /// Helper for get_sequence_x
    template <typename octet_iterator>
    utf_error increase_safely(octet_iterator& it, octet_iterator end)
    {
        if (++it == end)
            return NOT_ENOUGH_ROOM;

        if (!utf8::internal::is_trail(*it))
            return INCOMPLETE_SEQUENCE;
        
        return UTF8_OK;
    }

    #define UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(IT, END) {utf_error ret = increase_safely(IT, END); if (ret != UTF8_OK) return ret;}    

    /// get_sequence_x functions decode utf-8 sequences of the length x
    template <typename octet_iterator>
    utf_error get_sequence_1(octet_iterator& it, octet_iterator end, uint32_t& code_point)
    {
        if (it == end)
            return NOT_ENOUGH_ROOM;

        code_point = utf8::internal::mask8(*it);

        return UTF8_OK;
    }

    template <typename octet_iterator>
    utf_error get_sequence_2(octet_iterator& it, octet_iterator end, uint32_t& code_point)
    {
        if (it == end) 
            return NOT_ENOUGH_ROOM;
        
        code_point = utf8::internal::mask8(*it);

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point = ((code_point << 6) & 0x7ff) + ((*it) & 0x3f);

        return UTF8_OK;
    }

    template <typename octet_iterator>
    utf_error get_sequence_3(octet_iterator& it, octet_iterator end, uint32_t& code_point)
    {
        if (it == end)
            return NOT_ENOUGH_ROOM;
            
        code_point = utf8::internal::mask8(*it);

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point = ((code_point << 12) & 0xffff) + ((utf8::internal::mask8(*it) << 6) & 0xfff);

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point += (*it) & 0x3f;

        return UTF8_OK;
    }

    template <typename octet_iterator>
    utf_error get_sequence_4(octet_iterator& it, octet_iterator end, uint32_t& code_point)
    {
        if (it == end)
           return NOT_ENOUGH_ROOM;

        code_point = utf8::internal::mask8(*it);

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point = ((code_point << 18) & 0x1fffff) + ((utf8::internal::mask8(*it) << 12) & 0x3ffff);

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point += (utf8::internal::mask8(*it) << 6) & 0xfff;

        UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR(it, end)

        code_point += (*it) & 0x3f;

        return UTF8_OK;
    }

    #undef UTF8_CPP_INCREASE_AND_RETURN_ON_ERROR

    template <typename octet_iterator>
    utf_error validate_next(octet_iterator& it, octet_iterator end, uint32_t& code_point)
    {
        // Save the original value of it so we can go back in case of failure
        // Of course, it does not make much sense with i.e. stream iterators
        octet_iterator original_it = it;

        uint32_t cp = 0;
        // Determine the sequence length based on the lead octet
        typedef typename std::iterator_traits<octet_iterator>::difference_type octet_difference_type;
        const octet_difference_type length = utf8::internal::sequence_length(it);

        // Get trail octets and calculate the code point
        utf_error err = UTF8_OK;
        switch (length) {
            case 0: 
                return INVALID_LEAD;
            case 1:
                err = utf8::internal::get_sequence_1(it, end, cp);
                break;
            case 2:
                err = utf8::internal::get_sequence_2(it, end, cp);
            break;
            case 3:
                err = utf8::internal::get_sequence_3(it, end, cp);
            break;
            case 4:
                err = utf8::internal::get_sequence_4(it, end, cp);
            break;
        }

        if (err == UTF8_OK) {
            // Decoding succeeded. Now, security checks...
            if (utf8::internal::is_code_point_valid(cp)) {
                if (!utf8::internal::is_overlong_sequence(cp, length)){
                    // Passed! Return here.
                    code_point = cp;
                    ++it;
                    return UTF8_OK;
                }
                else
                    err = OVERLONG_SEQUENCE;
            }
            else 
                err = INVALID_CODE_POINT;
        }

        // Failure branch - restore the original value of the iterator
        it = original_it;
        return err;
    }

    template <typename octet_iterator>
    inline utf_error validate_next(octet_iterator& it, octet_iterator end) {
        uint32_t ignored;
        return utf8::internal::validate_next(it, end, ignored);
    }

} // namespace internal

    /// The library API - functions intended to be called by the users

    // Byte order mark
    const uint8_t bom[] = {0xef, 0xbb, 0xbf};

    template <typename octet_iterator>
    octet_iterator find_invalid(octet_iterator start, octet_iterator end)
    {
        octet_iterator result = start;
        while (result != end) {
            utf8::internal::utf_error err_code = utf8::internal::validate_next(result, end);
            if (err_code != internal::UTF8_OK)
                return result;
        }
        return result;
    }

    template <typename octet_iterator>
    inline bool is_valid(octet_iterator start, octet_iterator end)
    {
        return (utf8::find_invalid(start, end) == end);
    }

    template <typename octet_iterator>
    inline bool starts_with_bom (octet_iterator it, octet_iterator end)
    {
        return (
            ((it != end) && (utf8::internal::mask8(*it++)) == bom[0]) &&
            ((it != end) && (utf8::internal::mask8(*it++)) == bom[1]) &&
            ((it != end) && (utf8::internal::mask8(*it))   == bom[2])
           );
    }
	
    //Deprecated in release 2.3 
    template <typename octet_iterator>
    inline bool is_bom (octet_iterator it)
    {
        return (
            (utf8::internal::mask8(*it++)) == bom[0] &&
            (utf8::internal::mask8(*it++)) == bom[1] &&
            (utf8::internal::mask8(*it))   == bom[2]
           );
    }
} // namespace utf8

#endif // header guard