| # This file is derived from |
| # |
| # http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt |
| # |
| # Which was created by Markus Kuhn <mkuhn@acm.org> - 2000-09-02 |
| # |
| # lines begining with # and blank lines are ignored |
| # |
| # Beyond that, this file consists of a series of test cases. Each test case consists of |
| # 2 or 3 lines: |
| # |
| # 1. A UTF-8 string |
| # 2. A status |
| # VALID : The string is a valid UTF-8 representation of valid Unicode |
| # INCOMPLETE : The string has a partial character at the end |
| # NOTUNICODE : The string is valid UTF-8, but the characters represented |
| # are not valid unicode ( |
| # OVERLONG : The string includes overlong sequences |
| # MALFORMED : The string is not valid UTF-8 |
| # 3. If the status is VALID or NOTUNICODE, the UCS-4 representation of the string, |
| # as a series of hex numbers. |
| |
| # 1 Some correct UTF-8 text |
| κόÏμε |
| VALID |
| 03ba 1f79 03c3 03bc 03b5 |
| |
| # 2.1 First possible sequence of a certain length |
| # |
| # FIXME - handle NULLS? |
| # |
| # [ NULL BYTE ] |
| #VALID |
| #0000 |
| |
| Â |
| VALID |
| 0080 |
| |
| à |
| VALID |
| 0800 |
| |
| ð |
| VALID |
| 00010000 |
| |
| ø |
| NOTUNICODE |
| 00200000 |
| |
| ü |
| NOTUNICODE |
| 04000000 |
| |
| |
| VALID |
| 0000007f |
| |
| ß¿ |
| VALID |
| 000007ff |
| |
| ï¿¿ |
| VALID |
| 0000ffff |
| |
| ÷¿¿¿ |
| NOTUNICODE |
| 001fffff |
| |
| û¿¿¿¿ |
| NOTUNICODE |
| 03ffffff |
| |
| ý¿¿¿¿¿ |
| NOTUNICODE |
| 7fffffff |
| |
| # 2.3 Other boundary conditions |
| |
| í¿ |
| VALID |
| d7ff |
| |
| î |
| VALID |
| e000 |
| |
| � |
| VALID |
| fffd |
| |
| ô¿½ |
| VALID |
| 0010fffd |
| |
| ô¿¿ |
| VALID |
| 0010ffff |
| |
| ô |
| NOTUNICODE |
| 00110000 |
| |
| # 3.1 Unexpected continuation bytes |
| |
| |
| MALFORMED |
| ¿ |
| MALFORMED |
| ¿ |
| MALFORMED |
| ¿ |
| MALFORMED |
| ¿¿ |
| MALFORMED |
| ¿¿ |
| MALFORMED |
| ¿¿¿ |
| MALFORMED |
| ¿¿¿ |
| MALFORMED |
|
¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·¸¹º»¼½¾¿ |
| MALFORMED |
| |
| # 3.2 Lonely start characters |
| |
| À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï Ð Ñ Ò Ó Ô Õ Ö × Ø Ù Ú Û Ü Ý Þ ß |
| MALFORMED |
| à á â ã ä å æ ç è é ê ë ì í î ï |
| MALFORMED |
| ð ñ ò ó ô õ ö ÷ |
| MALFORMED |
| ø ù ú û |
| MALFORMED |
| ü ý |
| MALFORMED |
| |
| # 3.3 Sequences with last continuation byte missing |
| |
| À |
| INCOMPLETE |
| à |
| INCOMPLETE |
| ð |
| INCOMPLETE |
| ø |
| INCOMPLETE |
| ü |
| INCOMPLETE |
| ß |
| INCOMPLETE |
| ï¿ |
| INCOMPLETE |
| ÷¿¿ |
| INCOMPLETE |
| û¿¿¿ |
| INCOMPLETE |
| ý¿¿¿¿ |
| INCOMPLETE |
| |
| # 3.4 Concatenation of incomplete sequences |
| |
| Ààðøüßï¿÷¿¿û¿¿¿ý¿¿¿¿ |
| MALFORMED |
| |
| # 3.5 Impossible bytes |
| |
| þ |
| MALFORMED |
| ÿ |
| MALFORMED |
| þþÿÿ |
| MALFORMED |
| |
| # Examples of an overlong ASCII character |
| |
| À¯ |
| OVERLONG |
| ௠|
| OVERLONG |
| ð¯ |
| OVERLONG |
| ø¯ |
| OVERLONG |
| ü¯ |
| OVERLONG |
| |
| # Maximum overlong sequences |
| |
| Á¿ |
| OVERLONG |
| à¿ |
| OVERLONG |
| ð¿¿ |
| OVERLONG |
| ø¿¿¿ |
| OVERLONG |
| ü¿¿¿¿ |
| OVERLONG |
| |
| # Overlong representation of the NUL character |
| |
| À |
| OVERLONG |
| à |
| OVERLONG |
| ð |
| OVERLONG |
| ø |
| OVERLONG |
| ü |
| OVERLONG |
| |
| # Illegal code positions |
| |
| # Single UTF-16 surrogates |
| |
| í |
| NOTUNICODE |
| d800 |
| |
| í¿ |
| NOTUNICODE |
| db7f |
| |
| í® |
| NOTUNICODE |
| db80 |
| |
| í¯¿ |
| NOTUNICODE |
| dbff |
| |
| í° |
| NOTUNICODE |
| dc00 |
| |
| í¾ |
| NOTUNICODE |
| df80 |
| |
| í¿¿ |
| NOTUNICODE |
| dfff |
| |
| # Paired UTF-16 surrogates |
| |
| í í° |
| NOTUNICODE |
| d800 dc00 |
| |
| í í¿¿ |
| NOTUNICODE |
| d800 dfff |
| |
| í¿í° |
| NOTUNICODE |
| db7f dc00 |
| |
| í¿í¿¿ |
| NOTUNICODE |
| db7f dfff |
| |
| í®í° |
| NOTUNICODE |
| db80 dc00 |
| |
| í®í¿¿ |
| NOTUNICODE |
| db80 dfff |
| |
| í¯¿í° |
| NOTUNICODE |
| dbff dc00 |
| |
| 􏿿 |
| NOTUNICODE |
| dbff dfff |
| |
| ################ |
| # |
| # Some more tests, not from Markus Kuhn's file |
| # |
| |
| # Mixed plane 0 and higher planes |
| |
| AðBô¿½C |
| VALID |
| 41 00010000 42 10fffd 43 |
