16  * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
26     /* {"title", "test 1|test 2|...|test N!", (0 or 1)}, */
31     {"u-0 is a control character", "\x00!", 0},
32     {"u-80 is a control character", "\xc2\x80!", 0},
33     {"u-800 is valid", "\xe0\xa0\x80!", 1},
34     {"u-10000 is valid", "\xf0\x90\x80\x80!", 1},
38     {"u-7f is a control character", "\x7f!", 0},
39     {"u-7FF is valid", "\xdf\xbf!", 1},
40     {"u-FFFF is a control character", "\xef\xbf\xbf!", 0},
41     {"u-1FFFFF is too large", "\xf7\xbf\xbf\xbf!", 0},
42     {"u-3FFFFFF is 5 bytes", "\xfb\xbf\xbf\xbf\xbf!", 0},
43     {"u-7FFFFFFF is 6 bytes", "\xfd\xbf\xbf\xbf\xbf\xbf!", 0},
45     {"u-D7FF", "\xed\x9f\xbf!", 1},
46     {"u-E000", "\xee\x80\x80!", 1},
47     {"u-FFFD", "\xef\xbf\xbd!", 1},
48     {"u-10FFFF", "\xf4\x8f\xbf\xbf!", 1},
49     {"u-110000", "\xf4\x90\x80\x80!", 0},
54     {"2 continuation bytes", "\x80\xbf!", 0},
66     {"32 first bytes of 2-byte sequences {0xc0-0xdf}",
69     {"16 first bytes of 3-byte sequences {0xe0-0xef}",
71 …{"8 first bytes of 4-byte sequences {0xf0-0xf7}", "\xf0 |\xf1 |\xf2 |\xf3 |\xf4 |\xf5 |\xf6 |\xf7 …
72     {"4 first bytes of 5-byte sequences {0xf8-0xfb}", "\xf8 |\xf9 |\xfa |\xfb !", 0},
73     {"2 first bytes of 6-byte sequences {0xfc-0xfd}", "\xfc |\xfd !", 0},
75     {"sequences with last byte missing {u-0}",
77     {"sequences with last byte missing {u-...FF}",
82     {"overlong sequences {u-2f}",
91     {"single UTF-16 surrogates",
94     {"paired UTF-16 surrogates",
108     {"no bom (utf-8)", "Hi is \xd0\x9f\xd1\x80\xd0\xb8\xd0\xb2\xd0\xb5\xd1\x82!", 13},
109     {"bom (utf-8)", "\xef\xbb\xbfHi is \xd0\x9f\xd1\x80\xd0\xb8\xd0\xb2\xd0\xb5\xd1\x82!", 13},
110 …{"bom (utf-16-le)", "\xff\xfeH\x00i\x00 \x00i\x00s\x00 \x00\x1f\x04@\x04""8\x04""2\x04""5\x04""B\x…
111 …{"bom (utf-16-be)", "\xfe\xff\x00H\x00i\x00 \x00i\x00s\x00 \x04\x1f\x04@\x04""8\x04""2\x04""5\x04"…
122     printf("checking utf-8 sequences...\n");  in check_utf8_sequences()
133             yaml_parser_set_input_string(&parser, (unsigned char *)start, end-start);  in check_utf8_sequences()
134             result = yaml_parser_update_buffer(&parser, end-start);  in check_utf8_sequences()
136                 printf("\t\t- ");  in check_utf8_sequences()
146                 if (parser.problem_value != -1) {  in check_utf8_sequences()
161     printf("checking utf-8 sequences: %d fail(s)\n", failed);  in check_utf8_sequences()
180         yaml_parser_set_input_string(&parser, (unsigned char *)start, end-start);  in check_boms()
181         result = yaml_parser_update_buffer(&parser, end-start);  in check_boms()
183             printf("- (reader error: %s at %ld)\n", parser.problem, (long)parser.problem_offset);  in check_boms()
188                 printf("- (length=%ld while expected length=%d)\n", (long)parser.unread, check);  in check_boms()
192 …printf("- (value '%s' does not equal to the original value '%s')\n", parser.buffer.start, bom_orig…  in check_boms()
213     unsigned char ch0, ch1;  in check_long_utf8()  local
214     unsigned char *buffer = (unsigned char *)malloc(3+LONG*2);  in check_long_utf8()
221         if (j % 2) {  in check_long_utf8()
231     yaml_parser_set_input_string(&parser, buffer, 3+LONG*2);  in check_long_utf8()
245         if (k % 2) {  in check_long_utf8()
246             ch0 = '\xd0';  in check_long_utf8()
250             ch0 = '\xd0';  in check_long_utf8()
253         if (parser.buffer.pointer[0] != ch0 || parser.buffer.pointer[1] != ch1) {  in check_long_utf8()
254             printf("\tincorrect UTF-8 sequence: %X %X instead of %X %X\n",  in check_long_utf8()
256                     (int)ch0, (int)ch1);  in check_long_utf8()
260         parser.buffer.pointer += 2;  in check_long_utf8()
261         parser.unread -= 1;  in check_long_utf8()
285     unsigned char ch0, ch1;  in check_long_utf16()  local
286     unsigned char *buffer = (unsigned char *)malloc(2+LONG*2);  in check_long_utf16()
292         if (j % 2) {  in check_long_utf16()
302     yaml_parser_set_input_string(&parser, buffer, 2+LONG*2);  in check_long_utf16()
316         if (k % 2) {  in check_long_utf16()
317             ch0 = '\xd0';  in check_long_utf16()
321             ch0 = '\xd0';  in check_long_utf16()
324         if (parser.buffer.pointer[0] != ch0 || parser.buffer.pointer[1] != ch1) {  in check_long_utf16()
325             printf("\tincorrect UTF-8 sequence: %X %X instead of %X %X\n",  in check_long_utf16()
327                     (int)ch0, (int)ch1);  in check_long_utf16()
331         parser.buffer.pointer += 2;  in check_long_utf16()
332         parser.unread -= 1;  in check_long_utf16()