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
|
/*
gen-utf.c - generate ASCII, UTF-8, and UTF-16 test files.
Paul Hardy, 2018
*/
#include <stdio.h>
int
main ()
{
int i; /* Loop variable */
int codept; /* Unicode code point to output */
int nbytes; /* Number of bytes in current UTF-8 character */
unsigned utf_bytes[5]; /* For UTF-8 encoded bytes */
int cvt2utf8 (unsigned, unsigned *); /* convert binary code point to UTF-8 */
FILE *utffp;
/*
ASCII
*/
utffp = fopen ("sample-ascii.txt", "w");
for (codept = 0x00; codept < 0x7F; codept++)
fputc (codept, utffp);
fclose (utffp);
/*
Shortened UTF-8 file with Byte Order Mark at beginning.
*/
utffp = fopen ("sample-utf8-bom-begin.txt", "w");
/* UTF-8 Byte Order Mark */
fputc ('\357', utffp); fputc ('\273', utffp); fputc ('\277', utffp);
for (codept = 0x00; codept < 0x7F; codept++)
fputc (codept, utffp);
fclose (utffp);
/*
Shortened UTF-8 file with Byte Order Mark at end, to check embedded BOM.
*/
utffp = fopen ("sample-utf8-bom-end.txt", "w");
for (codept = 0x00; codept < 0x7F; codept++)
fputc (codept, utffp);
/* UTF-8 Byte Order Mark */
fputc ('\357', utffp); fputc ('\273', utffp); fputc ('\277', utffp);
fclose (utffp);
/*
UTF-8
*/
utffp = fopen ("sample-utf8.txt", "w");
for (codept = 0x00; codept < 0xD800; codept++) {
nbytes = cvt2utf8 (codept, utf_bytes);
for (i = 0; i < nbytes; i++)
fputc (utf_bytes [i], utffp);
}
/* Skip over Unicode Surrogate Pair range; not valid UTF-8 */
for (codept = 0xE000; codept <= 0x10FFFF; codept++) {
nbytes = cvt2utf8 (codept, utf_bytes);
for (i = 0; i < nbytes; i++)
fputc (utf_bytes [i], utffp);
}
fclose (utffp);
/*
Big-endian UTF-16
*/
utffp = fopen ("sample-utf16-be.txt", "w");
/* Big-endian UTF-16 Byte Order Mark */
fputc (0xFE, utffp);
fputc (0xFF, utffp);
for (codept = 0x0000; codept <= 0x0100; codept++) {
fputc ((codept >> 8) & 0xFF, utffp);
fputc ( codept & 0xFF, utffp);
}
fclose (utffp);
/*
Little-endian UTF-16
*/
utffp = fopen ("sample-utf16-le.txt", "w");
/* Little-endian UTF-16 Byte Order Mark */
fputc (0xFF, utffp);
fputc (0xFE, utffp);
for (codept = 0x0000; codept <= 0x0100; codept++) {
fputc ( codept & 0xFF, utffp);
fputc ((codept >> 8) & 0xFF, utffp);
}
fclose (utffp);
/*
Binary
*/
utffp = fopen ("sample-binary.txt", "w");
for (codept = 0x00; codept <= 0xFF; codept++) {
fputc ( codept & 0xFF, utffp);
}
fclose (utffp);
/*
UTF-8 with embedded Surrogate Pairs -- not valid UTF-8
*/
utffp = fopen ("sample-utf8-surrogate.txt", "w");
nbytes = cvt2utf8 (0xD800, utf_bytes);
for (i = 0; i < nbytes; i++)
fputc (utf_bytes [i], utffp);
nbytes = cvt2utf8 (0xDC00, utf_bytes);
for (i = 0; i < nbytes; i++)
fputc (utf_bytes [i], utffp);
}
/*
Convert a Unicode code point to a UTF-8 string.
The allowable Unicode range is U+0000..U+10FFFF.
codept - the Unicode code point to encode
utf8_bytes - an array of 5 bytes to hold the UTF-8 encoded string;
the string will consist of up to 4 UTF-8-encoded bytes,
with null bytes after the last encoded byte to signal
to the end of the array, utf8_bytes[4].
*/
int
cvt2utf8 (unsigned codept, unsigned *utf8_bytes)
{
int bin_length; /* number of binary digits, for forming UTF-8 */
int byte_length; /* numberof bytes of UTF-8 */
int bin_digits (unsigned);
/*
If codept is within the valid Unicode range of
0x0 through 0x10FFFF inclusive, convert it to UTF-8.
*/
if (codept <= 0x10FFFF) {
byte_length = 0;
bin_length = bin_digits (codept);
if (bin_length < 8) { /* U+0000..U+007F */
byte_length = 1;
utf8_bytes [0] = codept;
utf8_bytes [1] =
utf8_bytes [2] =
utf8_bytes [3] =
utf8_bytes [4] = 0;
}
else if (bin_length < 12) { /* U+0080..U+07FF */
byte_length = 2;
utf8_bytes [0] = 0xC0 | ((codept >> 6) & 0x1F);
utf8_bytes [1] = 0x80 | ( codept & 0x3F);
utf8_bytes [2] =
utf8_bytes [3] =
utf8_bytes [4] = 0;
}
else if (bin_length < 17) { /* U+0800..U+FFFF */
byte_length = 3;
utf8_bytes [0] = 0xE0 | ((codept >> 12) & 0x0F);
utf8_bytes [1] = 0x80 | ((codept >> 6) & 0x3F);
utf8_bytes [2] = 0x80 | ( codept & 0x3F);
utf8_bytes [3] =
utf8_bytes [4] = 0;
}
else if (bin_length < 22) { /* U+010000..U+10FFFF */
byte_length = 4;
utf8_bytes [0] = 0xF0 | ((codept >> 18) & 0x07);
utf8_bytes [1] = 0x80 | ((codept >> 12) & 0x3F);
utf8_bytes [2] = 0x80 | ((codept >> 6) & 0x3F);
utf8_bytes [3] = 0x80 | ( codept & 0x3F);
utf8_bytes [4] = 0;
}
} /* encoded output for valid Unicode code point */
else { /* flag out of range Unicode code point */
/*
0xFF is never a valid UTF-8 code point, so testing
for it will be an easy check of a valid return value.
*/
byte_length = -1;
utf8_bytes [0] = 0xFF;
utf8_bytes [1] = 0xFF;
utf8_bytes [2] = 0xFF;
utf8_bytes [3] = 0xFF;
utf8_bytes [4] = 0;
}
return byte_length;
}
/*
Return the number of significant binary digits in an unsigned number.
*/
int
bin_digits (unsigned itest)
{
unsigned i;
int result;
i = 0x80000000; /* mask highest unsigned bit */
result = 32;
while ( (i != 0) && ((itest & i) == 0) ) {
i >>= 1;
result--;
}
return result;
}
|
