aboutsummaryrefslogtreecommitdiff
path: root/rune.c
blob: 92d9d2acdfc6ec21be0c882bf58ece8fd4a3a6bb (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
/*
 * The authors of this software are Rob Pike and Ken Thompson.
 *              Copyright (c) 2002 by Lucent Technologies.
 * Permission to use, copy, modify, and distribute this software for any
 * purpose without fee is hereby granted, provided that this entire notice
 * is included in all copies of any software which is or includes a copy
 * or modification of this software and in all copies of the supporting
 * documentation for such software.
 * THIS SOFTWARE IS BEING PROVIDED "AS IS", WITHOUT ANY EXPRESS OR IMPLIED
 * WARRANTY.  IN PARTICULAR, NEITHER THE AUTHORS NOR LUCENT TECHNOLOGIES MAKE ANY
 * REPRESENTATION OR WARRANTY OF ANY KIND CONCERNING THE MERCHANTABILITY
 * OF THIS SOFTWARE OR ITS FITNESS FOR ANY PARTICULAR PURPOSE.
 */
#include <stdarg.h>
#include <string.h>
#include "utf.h"
#include "utfdef.h"

enum
{
	Bit1	= 7,
	Bitx	= 6,
	Bit2	= 5,
	Bit3	= 4,
	Bit4	= 3,
	Bit5	= 2, 

	T1	= ((1<<(Bit1+1))-1) ^ 0xFF,	/* 0000 0000 */
	Tx	= ((1<<(Bitx+1))-1) ^ 0xFF,	/* 1000 0000 */
	T2	= ((1<<(Bit2+1))-1) ^ 0xFF,	/* 1100 0000 */
	T3	= ((1<<(Bit3+1))-1) ^ 0xFF,	/* 1110 0000 */
	T4	= ((1<<(Bit4+1))-1) ^ 0xFF,	/* 1111 0000 */
	T5	= ((1<<(Bit5+1))-1) ^ 0xFF,	/* 1111 1000 */

	Rune1	= (1<<(Bit1+0*Bitx))-1,		/* 0000 0000 0111 1111 */
	Rune2	= (1<<(Bit2+1*Bitx))-1,		/* 0000 0111 1111 1111 */
	Rune3	= (1<<(Bit3+2*Bitx))-1,		/* 1111 1111 1111 1111 */
	Rune4	= (1<<(Bit4+3*Bitx))-1,
                                        /* 0001 1111 1111 1111 1111 1111 */

	Maskx	= (1<<Bitx)-1,			/* 0011 1111 */
	Testx	= Maskx ^ 0xFF,			/* 1100 0000 */

	Bad	= Runeerror,
};

/*
 * Modified by Wei-Hwa Huang, Google Inc., on 2004-09-24
 * This is a slower but "safe" version of the old chartorune 
 * that works on strings that are not necessarily null-terminated.
 * 
 * If you know for sure that your string is null-terminated,
 * chartorune will be a bit faster.
 *
 * It is guaranteed not to attempt to access "length"
 * past the incoming pointer.  This is to avoid
 * possible access violations.  If the string appears to be
 * well-formed but incomplete (i.e., to get the whole Rune
 * we'd need to read past str+length) then we'll set the Rune
 * to Bad and return 0.
 *
 * Note that if we have decoding problems for other
 * reasons, we return 1 instead of 0.
 */
int
charntorune(Rune *rune, const char *str, int length)
{
	int c, c1, c2, c3;
	long l;

	/* When we're not allowed to read anything */
	if(length <= 0) {
		goto badlen;
	}

	/*
	 * one character sequence (7-bit value)
	 *	00000-0007F => T1
	 */
	c = *(uchar*)str;
	if(c < Tx) {
		*rune = c;
		return 1;
	}

	// If we can't read more than one character we must stop
	if(length <= 1) {
		goto badlen;
	}

	/*
	 * two character sequence (11-bit value)
	 *	0080-07FF => T2 Tx
	 */
	c1 = *(uchar*)(str+1) ^ Tx;
	if(c1 & Testx)
		goto bad;
	if(c < T3) {
		if(c < T2)
			goto bad;
		l = ((c << Bitx) | c1) & Rune2;
		if(l <= Rune1)
			goto bad;
		*rune = l;
		return 2;
	}

	// If we can't read more than two characters we must stop
	if(length <= 2) {
		goto badlen;
	}

	/*
	 * three character sequence (16-bit value)
	 *	0800-FFFF => T3 Tx Tx
	 */
	c2 = *(uchar*)(str+2) ^ Tx;
	if(c2 & Testx)
		goto bad;
	if(c < T4) {
		l = ((((c << Bitx) | c1) << Bitx) | c2) & Rune3;
		if(l <= Rune2)
			goto bad;
		*rune = l;
		return 3;
	}

	if (length <= 3)
		goto badlen;

	/*
	 * four character sequence (21-bit value)
	 *	10000-1FFFFF => T4 Tx Tx Tx
	 */
	c3 = *(uchar*)(str+3) ^ Tx;
	if (c3 & Testx)
		goto bad;
	if (c < T5) {
		l = ((((((c << Bitx) | c1) << Bitx) | c2) << Bitx) | c3) & Rune4;
		if (l <= Rune3)
			goto bad;
		if (l > Runemax)
			goto bad;
		*rune = l;
		return 4;
	}

	// Support for 5-byte or longer UTF-8 would go here, but
	// since we don't have that, we'll just fall through to bad.

	/*
	 * bad decoding
	 */
bad:
	*rune = Bad;
	return 1;
badlen:
	*rune = Bad;
	return 0;

}


/*
 * This is the older "unsafe" version, which works fine on 
 * null-terminated strings.
 */
int
chartorune(Rune *rune, const char *str)
{
	int c, c1, c2, c3;
	long l;

	/*
	 * one character sequence
	 *	00000-0007F => T1
	 */
	c = *(uchar*)str;
	if(c < Tx) {
		*rune = c;
		return 1;
	}

	/*
	 * two character sequence
	 *	0080-07FF => T2 Tx
	 */
	c1 = *(uchar*)(str+1) ^ Tx;
	if(c1 & Testx)
		goto bad;
	if(c < T3) {
		if(c < T2)
			goto bad;
		l = ((c << Bitx) | c1) & Rune2;
		if(l <= Rune1)
			goto bad;
		*rune = l;
		return 2;
	}

	/*
	 * three character sequence
	 *	0800-FFFF => T3 Tx Tx
	 */
	c2 = *(uchar*)(str+2) ^ Tx;
	if(c2 & Testx)
		goto bad;
	if(c < T4) {
		l = ((((c << Bitx) | c1) << Bitx) | c2) & Rune3;
		if(l <= Rune2)
			goto bad;
		*rune = l;
		return 3;
	}

	/*
	 * four character sequence (21-bit value)
	 *	10000-1FFFFF => T4 Tx Tx Tx
	 */
	c3 = *(uchar*)(str+3) ^ Tx;
	if (c3 & Testx)
		goto bad;
	if (c < T5) {
		l = ((((((c << Bitx) | c1) << Bitx) | c2) << Bitx) | c3) & Rune4;
		if (l <= Rune3)
			goto bad;
		if (l > Runemax)
			goto bad;
		*rune = l;
		return 4;
	}

	/*
	 * Support for 5-byte or longer UTF-8 would go here, but
	 * since we don't have that, we'll just fall through to bad.
	 */

	/*
	 * bad decoding
	 */
bad:
	*rune = Bad;
	return 1;
}

int
isvalidcharntorune(const char* str, int length, Rune* rune, int* consumed) {
	*consumed = charntorune(rune, str, length);
	return *rune != Runeerror || *consumed == 3;
}
    
int
runetochar(char *str, const Rune *rune)
{
	/* Runes are signed, so convert to unsigned for range check. */
	unsigned long c;

	/*
	 * one character sequence
	 *	00000-0007F => 00-7F
	 */
	c = *rune;
	if(c <= Rune1) {
		str[0] = c;
		return 1;
	}

	/*
	 * two character sequence
	 *	0080-07FF => T2 Tx
	 */
	if(c <= Rune2) {
		str[0] = T2 | (c >> 1*Bitx);
		str[1] = Tx | (c & Maskx);
		return 2;
	}

	/*
	 * If the Rune is out of range, convert it to the error rune.
	 * Do this test here because the error rune encodes to three bytes.
	 * Doing it earlier would duplicate work, since an out of range
	 * Rune wouldn't have fit in one or two bytes.
	 */
	if (c > Runemax)
		c = Runeerror;

	/*
	 * three character sequence
	 *	0800-FFFF => T3 Tx Tx
	 */
	if (c <= Rune3) {
		str[0] = T3 |  (c >> 2*Bitx);
		str[1] = Tx | ((c >> 1*Bitx) & Maskx);
		str[2] = Tx |  (c & Maskx);
		return 3;
	}

	/*
	 * four character sequence (21-bit value)
	 *     10000-1FFFFF => T4 Tx Tx Tx
	 */
	str[0] = T4 | (c >> 3*Bitx);
	str[1] = Tx | ((c >> 2*Bitx) & Maskx);
	str[2] = Tx | ((c >> 1*Bitx) & Maskx);
	str[3] = Tx | (c & Maskx);
	return 4;
}

int
runelen(Rune rune)
{
	char str[10];

	return runetochar(str, &rune);
}

int
runenlen(const Rune *r, int nrune)
{
	int nb;
	ulong c;	/* Rune is signed, so use unsigned for range check. */

	nb = 0;
	while(nrune--) {
		c = *r++;
		if (c <= Rune1)
			nb++;
		else if (c <= Rune2)
			nb += 2;
		else if (c <= Rune3)
			nb += 3;
		else if (c <= Runemax)
			nb += 4;
		else
			nb += 3;	/* Runeerror = 0xFFFD, see runetochar */
	}
	return nb;
}

int
fullrune(const char *str, int n)
{
	if (n > 0) {
		int c = *(uchar*)str;
		if (c < Tx)
			return 1;
		if (n > 1) {
			if (c < T3)
				return 1;
			if (n > 2) {
				if (c < T4 || n > 3)
					return 1;
			}
		}
	}
	return 0;
}