Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 1 | """ Test script for the Unicode implementation. |
| 2 | |
| 3 | Written by Bill Tutt. |
| 4 | |
| 5 | (c) Copyright CNRI, All Rights Reserved. NO WARRANTY. |
| 6 | |
| 7 | """#" |
Marc-André Lemburg | 3661908 | 2001-01-17 19:11:13 +0000 | [diff] [blame] | 8 | from test_support import verify, verbose |
| 9 | |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 10 | print 'Testing General Unicode Character Name, and case insensitivity...', |
| 11 | |
| 12 | # General and case insensitivity test: |
| 13 | s = u"\N{LATIN CAPITAL LETTER T}" \ |
| 14 | u"\N{LATIN SMALL LETTER H}" \ |
| 15 | u"\N{LATIN SMALL LETTER E}" \ |
| 16 | u"\N{SPACE}" \ |
| 17 | u"\N{LATIN SMALL LETTER R}" \ |
| 18 | u"\N{LATIN CAPITAL LETTER E}" \ |
| 19 | u"\N{LATIN SMALL LETTER D}" \ |
| 20 | u"\N{SPACE}" \ |
| 21 | u"\N{LATIN SMALL LETTER f}" \ |
| 22 | u"\N{LATIN CAPITAL LeTtEr o}" \ |
| 23 | u"\N{LATIN SMaLl LETTER x}" \ |
| 24 | u"\N{SPACE}" \ |
| 25 | u"\N{LATIN SMALL LETTER A}" \ |
| 26 | u"\N{LATIN SMALL LETTER T}" \ |
| 27 | u"\N{LATIN SMALL LETTER E}" \ |
| 28 | u"\N{SPACE}" \ |
| 29 | u"\N{LATIN SMALL LETTER T}" \ |
| 30 | u"\N{LATIN SMALL LETTER H}" \ |
| 31 | u"\N{LATIN SMALL LETTER E}" \ |
| 32 | u"\N{SpAcE}" \ |
| 33 | u"\N{LATIN SMALL LETTER S}" \ |
| 34 | u"\N{LATIN SMALL LETTER H}" \ |
| 35 | u"\N{LATIN SMALL LETTER E}" \ |
| 36 | u"\N{LATIN SMALL LETTER E}" \ |
| 37 | u"\N{LATIN SMALL LETTER P}" \ |
| 38 | u"\N{FULL STOP}" |
Marc-André Lemburg | 3661908 | 2001-01-17 19:11:13 +0000 | [diff] [blame] | 39 | verify(s == u"The rEd fOx ate the sheep.", s) |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 40 | print "done." |
| 41 | |
| 42 | # misc. symbol testing |
| 43 | print "Testing misc. symbols for unicode character name expansion....", |
Marc-André Lemburg | 3661908 | 2001-01-17 19:11:13 +0000 | [diff] [blame] | 44 | verify(u"\N{PILCROW SIGN}" == u"\u00b6") |
| 45 | verify(u"\N{REPLACEMENT CHARACTER}" == u"\uFFFD") |
| 46 | verify(u"\N{HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK}" == u"\uFF9F") |
| 47 | verify(u"\N{FULLWIDTH LATIN SMALL LETTER A}" == u"\uFF41") |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 48 | print "done." |
| 49 | |
| 50 | |
| 51 | # strict error testing: |
| 52 | print "Testing unicode character name expansion strict error handling....", |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 53 | try: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 54 | unicode("\N{blah}", 'unicode-escape', 'strict') |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 55 | except UnicodeError: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 56 | pass |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 57 | else: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 58 | raise AssertionError, "failed to raise an exception when given a bogus character name" |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 59 | |
| 60 | try: |
Fredrik Lundh | 0fdb90c | 2001-01-19 09:45:02 +0000 | [diff] [blame] | 61 | unicode("\N{" + "x" * 100000 + "}", 'unicode-escape', 'strict') |
| 62 | except UnicodeError: |
| 63 | pass |
| 64 | else: |
| 65 | raise AssertionError, "failed to raise an exception when given a very " \ |
| 66 | "long bogus character name" |
| 67 | |
| 68 | try: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 69 | unicode("\N{SPACE", 'unicode-escape', 'strict') |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 70 | except UnicodeError: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 71 | pass |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 72 | else: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 73 | raise AssertionError, "failed to raise an exception for a missing closing brace." |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 74 | |
| 75 | try: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 76 | unicode("\NSPACE", 'unicode-escape', 'strict') |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 77 | except UnicodeError: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 78 | pass |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 79 | else: |
Fred Drake | 004d5e6 | 2000-10-23 17:22:08 +0000 | [diff] [blame] | 80 | raise AssertionError, "failed to raise an exception for a missing opening brace." |
Marc-André Lemburg | 6cdec2e | 2000-06-30 09:45:20 +0000 | [diff] [blame] | 81 | print "done." |