summaryrefslogtreecommitdiffstats
path: root/src/corelib/codecs/qutfcodec_p.h
blob: cb789f935d49f55b5923534bc6298d7702b61899 (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
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
/****************************************************************************
**
** Copyright (C) 2016 The Qt Company Ltd.
** Copyright (C) 2013 Intel Corporation
** Contact: https://www.qt.io/licensing/
**
** This file is part of the QtCore module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** Commercial License Usage
** Licensees holding valid commercial Qt licenses may use this file in
** accordance with the commercial license agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and The Qt Company. For licensing terms
** and conditions see https://www.qt.io/terms-conditions. For further
** information use the contact form at https://www.qt.io/contact-us.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 3 as published by the Free Software
** Foundation and appearing in the file LICENSE.LGPL3 included in the
** packaging of this file. Please review the following information to
** ensure the GNU Lesser General Public License version 3 requirements
** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU
** General Public License version 2.0 or (at your option) the GNU General
** Public license version 3 or any later version approved by the KDE Free
** Qt Foundation. The licenses are as published by the Free Software
** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
** included in the packaging of this file. Please review the following
** information to ensure the GNU General Public License requirements will
** be met: https://www.gnu.org/licenses/gpl-2.0.html and
** https://www.gnu.org/licenses/gpl-3.0.html.
**
** $QT_END_LICENSE$
**
****************************************************************************/

#ifndef QUTFCODEC_P_H
#define QUTFCODEC_P_H

//
//  W A R N I N G
//  -------------
//
// This file is not part of the Qt API.  It exists purely as an
// implementation detail.  This header file may change from version to
// version without notice, or even be removed.
//
// We mean it.
//

#include "QtCore/qtextcodec.h"
#include "private/qtextcodec_p.h"

QT_BEGIN_NAMESPACE

struct QUtf8BaseTraits
{
    static const bool isTrusted = false;
    static const bool allowNonCharacters = true;
    static const bool skipAsciiHandling = false;
    static const int Error = -1;
    static const int EndOfString = -2;

    static bool isValidCharacter(uint u)
    { return int(u) >= 0; }

    static void appendByte(uchar *&ptr, uchar b)
    { *ptr++ = b; }

    static uchar peekByte(const uchar *ptr, int n = 0)
    { return ptr[n]; }

    static qptrdiff availableBytes(const uchar *ptr, const uchar *end)
    { return end - ptr; }

    static void advanceByte(const uchar *&ptr, int n = 1)
    { ptr += n; }

    static void appendUtf16(ushort *&ptr, ushort uc)
    { *ptr++ = uc; }

    static void appendUcs4(ushort *&ptr, uint uc)
    {
        appendUtf16(ptr, QChar::highSurrogate(uc));
        appendUtf16(ptr, QChar::lowSurrogate(uc));
    }

    static ushort peekUtf16(const ushort *ptr, int n = 0)
    { return ptr[n]; }

    static qptrdiff availableUtf16(const ushort *ptr, const ushort *end)
    { return end - ptr; }

    static void advanceUtf16(const ushort *&ptr, int n = 1)
    { ptr += n; }

    // it's possible to output to UCS-4 too
    static void appendUtf16(uint *&ptr, ushort uc)
    { *ptr++ = uc; }

    static void appendUcs4(uint *&ptr, uint uc)
    { *ptr++ = uc; }
};

struct QUtf8BaseTraitsNoAscii : public QUtf8BaseTraits
{
    static const bool skipAsciiHandling = true;
};

namespace QUtf8Functions
{
    /// returns 0 on success; errors can only happen if \a u is a surrogate:
    /// Error if \a u is a low surrogate;
    /// if \a u is a high surrogate, Error if the next isn't a low one,
    /// EndOfString if we run into the end of the string.
    template <typename Traits, typename OutputPtr, typename InputPtr> inline
    int toUtf8(ushort u, OutputPtr &dst, InputPtr &src, InputPtr end)
    {
        if (!Traits::skipAsciiHandling && u < 0x80) {
            // U+0000 to U+007F (US-ASCII) - one byte
            Traits::appendByte(dst, uchar(u));
            return 0;
        } else if (u < 0x0800) {
            // U+0080 to U+07FF - two bytes
            // first of two bytes
            Traits::appendByte(dst, 0xc0 | uchar(u >> 6));
        } else {
            if (!QChar::isSurrogate(u)) {
                // U+0800 to U+FFFF (except U+D800-U+DFFF) - three bytes
                if (!Traits::allowNonCharacters && QChar::isNonCharacter(u))
                    return Traits::Error;

                // first of three bytes
                Traits::appendByte(dst, 0xe0 | uchar(u >> 12));
            } else {
                // U+10000 to U+10FFFF - four bytes
                // need to get one extra codepoint
                if (Traits::availableUtf16(src, end) == 0)
                    return Traits::EndOfString;

                ushort low = Traits::peekUtf16(src);
                if (!QChar::isHighSurrogate(u))
                    return Traits::Error;
                if (!QChar::isLowSurrogate(low))
                    return Traits::Error;

                Traits::advanceUtf16(src);
                uint ucs4 = QChar::surrogateToUcs4(u, low);

                if (!Traits::allowNonCharacters && QChar::isNonCharacter(ucs4))
                    return Traits::Error;

                // first byte
                Traits::appendByte(dst, 0xf0 | (uchar(ucs4 >> 18) & 0xf));

                // second of four bytes
                Traits::appendByte(dst, 0x80 | (uchar(ucs4 >> 12) & 0x3f));

                // for the rest of the bytes
                u = ushort(ucs4);
            }

            // second to last byte
            Traits::appendByte(dst, 0x80 | (uchar(u >> 6) & 0x3f));
        }

        // last byte
        Traits::appendByte(dst, 0x80 | (u & 0x3f));
        return 0;
    }

    inline bool isContinuationByte(uchar b)
    {
        return (b & 0xc0) == 0x80;
    }

    /// returns the number of characters consumed (including \a b) in case of success;
    /// returns negative in case of error: Traits::Error or Traits::EndOfString
    template <typename Traits, typename OutputPtr, typename InputPtr> inline
    int fromUtf8(uchar b, OutputPtr &dst, InputPtr &src, InputPtr end)
    {
        int charsNeeded;
        uint min_uc;
        uint uc;

        if (!Traits::skipAsciiHandling && b < 0x80) {
            // US-ASCII
            Traits::appendUtf16(dst, b);
            return 1;
        }

        if (!Traits::isTrusted && Q_UNLIKELY(b <= 0xC1)) {
            // an UTF-8 first character must be at least 0xC0
            // however, all 0xC0 and 0xC1 first bytes can only produce overlong sequences
            return Traits::Error;
        } else if (b < 0xe0) {
            charsNeeded = 2;
            min_uc = 0x80;
            uc = b & 0x1f;
        } else if (b < 0xf0) {
            charsNeeded = 3;
            min_uc = 0x800;
            uc = b & 0x0f;
        } else if (b < 0xf5) {
            charsNeeded = 4;
            min_uc = 0x10000;
            uc = b & 0x07;
        } else {
            // the last Unicode character is U+10FFFF
            // it's encoded in UTF-8 as "\xF4\x8F\xBF\xBF"
            // therefore, a byte higher than 0xF4 is not the UTF-8 first byte
            return Traits::Error;
        }

        int bytesAvailable = Traits::availableBytes(src, end);
        if (Q_UNLIKELY(bytesAvailable < charsNeeded - 1)) {
            // it's possible that we have an error instead of just unfinished bytes
            if (bytesAvailable > 0 && !isContinuationByte(Traits::peekByte(src, 0)))
                return Traits::Error;
            if (bytesAvailable > 1 && !isContinuationByte(Traits::peekByte(src, 1)))
                return Traits::Error;
            return Traits::EndOfString;
        }

        // first continuation character
        b = Traits::peekByte(src, 0);
        if (!isContinuationByte(b))
            return Traits::Error;
        uc <<= 6;
        uc |= b & 0x3f;

        if (charsNeeded > 2) {
            // second continuation character
            b = Traits::peekByte(src, 1);
            if (!isContinuationByte(b))
                return Traits::Error;
            uc <<= 6;
            uc |= b & 0x3f;

            if (charsNeeded > 3) {
                // third continuation character
                b = Traits::peekByte(src, 2);
                if (!isContinuationByte(b))
                    return Traits::Error;
                uc <<= 6;
                uc |= b & 0x3f;
            }
        }

        // we've decoded something; safety-check it
        if (!Traits::isTrusted) {
            if (uc < min_uc)
                return Traits::Error;
            if (QChar::isSurrogate(uc) || uc > QChar::LastValidCodePoint)
                return Traits::Error;
            if (!Traits::allowNonCharacters && QChar::isNonCharacter(uc))
                return Traits::Error;
        }

        // write the UTF-16 sequence
        if (!QChar::requiresSurrogates(uc)) {
            // UTF-8 decoded and no surrogates are required
            // detach if necessary
            Traits::appendUtf16(dst, ushort(uc));
        } else {
            // UTF-8 decoded to something that requires a surrogate pair
            Traits::appendUcs4(dst, uc);
        }

        Traits::advanceByte(src, charsNeeded - 1);
        return charsNeeded;
    }
}

enum DataEndianness
{
    DetectEndianness,
    BigEndianness,
    LittleEndianness
};

struct QUtf8
{
    static QChar *convertToUnicode(QChar *, const char *, int) Q_DECL_NOTHROW;
    static QString convertToUnicode(const char *, int);
    static QString convertToUnicode(const char *, int, QTextCodec::ConverterState *);
    static QByteArray convertFromUnicode(const QChar *, int);
    static QByteArray convertFromUnicode(const QChar *, int, QTextCodec::ConverterState *);
};

struct QUtf16
{
    static QString convertToUnicode(const char *, int, QTextCodec::ConverterState *, DataEndianness = DetectEndianness);
    static QByteArray convertFromUnicode(const QChar *, int, QTextCodec::ConverterState *, DataEndianness = DetectEndianness);
};

struct QUtf32
{
    static QString convertToUnicode(const char *, int, QTextCodec::ConverterState *, DataEndianness = DetectEndianness);
    static QByteArray convertFromUnicode(const QChar *, int, QTextCodec::ConverterState *, DataEndianness = DetectEndianness);
};

#ifndef QT_NO_TEXTCODEC

class QUtf8Codec : public QTextCodec {
public:
    ~QUtf8Codec();

    QByteArray name() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;

    QString convertToUnicode(const char *, int, ConverterState *) const Q_DECL_OVERRIDE;
    QByteArray convertFromUnicode(const QChar *, int, ConverterState *) const Q_DECL_OVERRIDE;
    void convertToUnicode(QString *target, const char *, int, ConverterState *) const;
};

class QUtf16Codec : public QTextCodec {
protected:
public:
    QUtf16Codec() { e = DetectEndianness; }
    ~QUtf16Codec();

    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;

    QString convertToUnicode(const char *, int, ConverterState *) const Q_DECL_OVERRIDE;
    QByteArray convertFromUnicode(const QChar *, int, ConverterState *) const Q_DECL_OVERRIDE;

protected:
    DataEndianness e;
};

class QUtf16BECodec : public QUtf16Codec {
public:
    QUtf16BECodec() : QUtf16Codec() { e = BigEndianness; }
    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;
};

class QUtf16LECodec : public QUtf16Codec {
public:
    QUtf16LECodec() : QUtf16Codec() { e = LittleEndianness; }
    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;
};

class QUtf32Codec : public QTextCodec {
public:
    QUtf32Codec() { e = DetectEndianness; }
    ~QUtf32Codec();

    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;

    QString convertToUnicode(const char *, int, ConverterState *) const Q_DECL_OVERRIDE;
    QByteArray convertFromUnicode(const QChar *, int, ConverterState *) const Q_DECL_OVERRIDE;

protected:
    DataEndianness e;
};

class QUtf32BECodec : public QUtf32Codec {
public:
    QUtf32BECodec() : QUtf32Codec() { e = BigEndianness; }
    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;
};

class QUtf32LECodec : public QUtf32Codec {
public:
    QUtf32LECodec() : QUtf32Codec() { e = LittleEndianness; }
    QByteArray name() const Q_DECL_OVERRIDE;
    QList<QByteArray> aliases() const Q_DECL_OVERRIDE;
    int mibEnum() const Q_DECL_OVERRIDE;
};


#endif // QT_NO_TEXTCODEC

QT_END_NAMESPACE

#endif // QUTFCODEC_P_H