summaryrefslogtreecommitdiff
path: root/src/util/UTF8.cxx
blob: 273cbac1e0a127acace71001dfe4bd554a990cdd (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
/*
 * Copyright (C) 2011-2014 Max Kellermann <max@duempel.org>
 * http://www.musicpd.org
 *
 * 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.
 *
 * 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
 * FOUNDATION 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 "UTF8.hxx"
#include "CharUtil.hxx"

#include <algorithm>

/**
 * Is this a leading byte that is followed by 1 continuation byte?
 */
static constexpr bool
IsLeading1(unsigned char ch)
{
	return (ch & 0xe0) == 0xc0;
}

static constexpr unsigned char
MakeLeading1(unsigned char value)
{
	return 0xc0 | value;
}

/**
 * Is this a leading byte that is followed by 2 continuation byte?
 */
static constexpr bool
IsLeading2(unsigned char ch)
{
	return (ch & 0xf0) == 0xe0;
}

static constexpr unsigned char
MakeLeading2(unsigned char value)
{
	return 0xe0 | value;
}

/**
 * Is this a leading byte that is followed by 3 continuation byte?
 */
static constexpr bool
IsLeading3(unsigned char ch)
{
	return (ch & 0xf8) == 0xf0;
}

static constexpr unsigned char
MakeLeading3(unsigned char value)
{
	return 0xf0 | value;
}

/**
 * Is this a leading byte that is followed by 4 continuation byte?
 */
static constexpr bool
IsLeading4(unsigned char ch)
{
	return (ch & 0xfc) == 0xf8;
}

static constexpr unsigned char
MakeLeading4(unsigned char value)
{
	return 0xf8 | value;
}

/**
 * Is this a leading byte that is followed by 5 continuation byte?
 */
static constexpr bool
IsLeading5(unsigned char ch)
{
	return (ch & 0xfe) == 0xfc;
}

static constexpr unsigned char
MakeLeading5(unsigned char value)
{
	return 0xfc | value;
}

static constexpr bool
IsContinuation(unsigned char ch)
{
	return (ch & 0xc0) == 0x80;
}

/**
 * Generate a continuation byte of the low 6 bit.
 */
static constexpr unsigned char
MakeContinuation(unsigned char value)
{
	return 0x80 | (value & 0x3f);
}

bool
ValidateUTF8(const char *p)
{
	for (; *p != 0; ++p) {
		unsigned char ch = *p;
		if (IsASCII(ch))
			continue;

		if (IsContinuation(ch))
			/* continuation without a prefix */
			return false;

		if (IsLeading1(ch)) {
			/* 1 continuation */
			if (!IsContinuation(*++p))
				return false;
		} else if (IsLeading2(ch)) {
			/* 2 continuations */
			if (!IsContinuation(*++p) || !IsContinuation(*++p))
				return false;
		} else if (IsLeading3(ch)) {
			/* 3 continuations */
			if (!IsContinuation(*++p) || !IsContinuation(*++p) ||
			    !IsContinuation(*++p))
				return false;
		} else if (IsLeading4(ch)) {
			/* 4 continuations */
			if (!IsContinuation(*++p) || !IsContinuation(*++p) ||
			    !IsContinuation(*++p) || !IsContinuation(*++p))
				return false;
		} else if (IsLeading5(ch)) {
			/* 5 continuations */
			if (!IsContinuation(*++p) || !IsContinuation(*++p) ||
			    !IsContinuation(*++p) || !IsContinuation(*++p) ||
			    !IsContinuation(*++p))
				return false;
		} else
			return false;
	}

	return true;
}

static const char *
FindNonASCIIOrZero(const char *p)
{
  while (*p != 0 && IsASCII(*p))
    ++p;
  return p;
}

const char *
Latin1ToUTF8(const char *gcc_restrict src, char *gcc_restrict buffer,
	     size_t buffer_size)
{
	const char *p = FindNonASCIIOrZero(src);
	if (*p == 0)
		/* everything is plain ASCII, we don't need to convert anything */
		return src;

	if ((size_t)(p - src) >= buffer_size)
		/* buffer too small */
		return nullptr;

	const char *const end = buffer + buffer_size;
	char *q = std::copy(src, p, buffer);

	while (*p != 0) {
		unsigned char ch = *p++;

		if (IsASCII(ch)) {
			*q++ = ch;

			if (q >= end)
				/* buffer too small */
				return nullptr;
		} else {
			if (q + 2 >= end)
				/* buffer too small */
				return nullptr;

			*q++ = MakeLeading1(ch >> 6);
			*q++ = MakeContinuation(ch);
		}
	}

	*q = 0;
	return buffer;
}

char *
UnicodeToUTF8(unsigned ch, char *q)
{
  if (gcc_likely(ch < 0x80)) {
    *q++ = (char)ch;
  } else if (gcc_likely(ch < 0x800)) {
    *q++ = MakeLeading1(ch >> 6);
    *q++ = MakeContinuation(ch);
  } else if (ch < 0x10000) {
    *q++ = MakeLeading2(ch >> 12);
    *q++ = MakeContinuation(ch >> 6);
    *q++ = MakeContinuation(ch);
  } else if (ch < 0x200000) {
    *q++ = MakeLeading3(ch >> 18);
    *q++ = MakeContinuation(ch >> 12);
    *q++ = MakeContinuation(ch >> 6);
    *q++ = MakeContinuation(ch);
  } else if (ch < 0x4000000) {
    *q++ = MakeLeading4(ch >> 24);
    *q++ = MakeContinuation(ch >> 18);
    *q++ = MakeContinuation(ch >> 12);
    *q++ = MakeContinuation(ch >> 6);
    *q++ = MakeContinuation(ch);
  } else if (ch < 0x80000000) {
    *q++ = MakeLeading5(ch >> 30);
    *q++ = MakeContinuation(ch >> 24);
    *q++ = MakeContinuation(ch >> 18);
    *q++ = MakeContinuation(ch >> 12);
    *q++ = MakeContinuation(ch >> 6);
    *q++ = MakeContinuation(ch);
  } else {
    // error
  }

  return q;
}

size_t
LengthUTF8(const char *p)
{
	/* this is a very naive implementation: it does not do any
	   verification, it just counts the bytes that are not a UTF-8
	   continuation */

	size_t n = 0;
	for (; *p != 0; ++p)
		if (!IsContinuation(*p))
			++n;
	return n;
}