ObjFW  Check-in [a83b261f72]

Overview
Comment:of_string_utf8_decode(): Check all surrogate bytes
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: a83b261f72ee2830122ab1c3f868e9adc6698a429b136a4cc59c75b265256cb9
User & Date: js on 2016-03-13 13:16:56
Other Links: manifest | tags
Context
2016-03-13
19:33
OFStdIOStream_Win32Console: Improve writing check-in: 3a0fdb6701 user: js tags: trunk
13:16
of_string_utf8_decode(): Check all surrogate bytes check-in: a83b261f72 user: js tags: trunk
12:39
OFRunLoop: Tiny documentation improvement check-in: d4555b9c1a user: js tags: trunk
Changes

Modified src/OFString.m from [b713fffc4b] to [51291209ea].

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

	return 0;
}

ssize_t
of_string_utf8_decode(const char *buffer_, size_t length, of_unichar_t *ret)
{
	/* FIXME: Check if the following bytes are indeed surrogates */
	const uint8_t *buffer = (const uint8_t*)buffer_;

	if (!(*buffer & 0x80)) {
		*ret = buffer[0];
		return 1;
	}

	if ((*buffer & 0xE0) == 0xC0) {
		if OF_UNLIKELY (length < 2)
			return -2;




		*ret = ((buffer[0] & 0x1F) << 6) | (buffer[1] & 0x3F);
		return 2;
	}

	if ((*buffer & 0xF0) == 0xE0) {
		if OF_UNLIKELY (length < 3)
			return -3;





		*ret = ((buffer[0] & 0x0F) << 12) | ((buffer[1] & 0x3F) << 6) |
		    (buffer[2] & 0x3F);
		return 3;
	}

	if ((*buffer & 0xF8) == 0xF0) {
		if OF_UNLIKELY (length < 4)
			return -4;





		*ret = ((buffer[0] & 0x07) << 18) | ((buffer[1] & 0x3F) << 12) |
		    ((buffer[2] & 0x3F) << 6) | (buffer[3] & 0x3F);
		return 4;
	}

	return 0;







<










>
>
>








>
>
>
>









>
>
>
>







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

	return 0;
}

ssize_t
of_string_utf8_decode(const char *buffer_, size_t length, of_unichar_t *ret)
{

	const uint8_t *buffer = (const uint8_t*)buffer_;

	if (!(*buffer & 0x80)) {
		*ret = buffer[0];
		return 1;
	}

	if ((*buffer & 0xE0) == 0xC0) {
		if OF_UNLIKELY (length < 2)
			return -2;

		if OF_UNLIKELY ((buffer[1] & 0xC0) != 0x80)
			return 0;

		*ret = ((buffer[0] & 0x1F) << 6) | (buffer[1] & 0x3F);
		return 2;
	}

	if ((*buffer & 0xF0) == 0xE0) {
		if OF_UNLIKELY (length < 3)
			return -3;

		if OF_UNLIKELY ((buffer[1] & 0xC0) != 0x80 ||
		    (buffer[2] & 0xC0) != 0x80)
			return 0;

		*ret = ((buffer[0] & 0x0F) << 12) | ((buffer[1] & 0x3F) << 6) |
		    (buffer[2] & 0x3F);
		return 3;
	}

	if ((*buffer & 0xF8) == 0xF0) {
		if OF_UNLIKELY (length < 4)
			return -4;

		if OF_UNLIKELY ((buffer[1] & 0xC0) != 0x80 ||
		    (buffer[2] & 0xC0) != 0x80 || (buffer[3] & 0xC0) != 0x80)
			return 0;

		*ret = ((buffer[0] & 0x07) << 18) | ((buffer[1] & 0x3F) << 12) |
		    ((buffer[2] & 0x3F) << 6) | (buffer[3] & 0x3F);
		return 4;
	}

	return 0;