Mercurial > cpython-lru_cache-weakref
view Lib/test/test_html.py @ 87690:66c1c9f32567 default tip
Add use_weakref option to functools.lru_cache
The use_weakref option makes lru_cache create weak references to the function
arguments when creating the cache key, which prevents them from staying in the
memory forever even after all other references to them are gone.
This is a proof of concept for http://bugs.python.org/issue19859
| author | Radomir Dopieralski <devel@sheep.art.pl> |
|---|---|
| date | Tue, 03 Dec 2013 16:02:48 +0100 |
| parents | 7b9235852b3b |
| children |
line wrap: on
line source
""" Tests for the html module functions. """ import html import unittest from test.support import run_unittest class HtmlTests(unittest.TestCase): def test_escape(self): self.assertEqual( html.escape('\'<script>"&foo;"</script>\''), ''<script>"&foo;"</script>'') self.assertEqual( html.escape('\'<script>"&foo;"</script>\'', False), '\'<script>"&foo;"</script>\'') def test_unescape(self): numeric_formats = ['&#%d', '&#%d;', '&#x%x', '&#x%x;'] errmsg = 'unescape(%r) should have returned %r' def check(text, expected): self.assertEqual(html.unescape(text), expected, msg=errmsg % (text, expected)) def check_num(num, expected): for format in numeric_formats: text = format % num self.assertEqual(html.unescape(text), expected, msg=errmsg % (text, expected)) # check text with no character references check('no character references', 'no character references') # check & followed by invalid chars check('&\n&\t& &&', '&\n&\t& &&') # check & followed by numbers and letters check('&0 &9 &a &0; &9; &a;', '&0 &9 &a &0; &9; &a;') # check incomplete entities at the end of the string for x in ['&', '&#', '&#x', '&#X', '&#y', '&#xy', '&#Xy']: check(x, x) check(x+';', x+';') # check several combinations of numeric character references, # possibly followed by different characters formats = ['&#%d', '&#%07d', '&#%d;', '&#%07d;', '&#x%x', '&#x%06x', '&#x%x;', '&#x%06x;', '&#x%X', '&#x%06X', '&#X%x;', '&#X%06x;'] for num, char in zip([65, 97, 34, 38, 0x2603, 0x101234], ['A', 'a', '"', '&', '\u2603', '\U00101234']): for s in formats: check(s % num, char) for end in [' ', 'X']: check((s+end) % num, char+end) # check invalid codepoints for cp in [0xD800, 0xDB00, 0xDC00, 0xDFFF, 0x110000]: check_num(cp, '\uFFFD') # check more invalid codepoints for cp in [0x1, 0xb, 0xe, 0x7f, 0xfffe, 0xffff, 0x10fffe, 0x10ffff]: check_num(cp, '') # check invalid numbers for num, ch in zip([0x0d, 0x80, 0x95, 0x9d], '\r\u20ac\u2022\x9d'): check_num(num, ch) # check small numbers check_num(0, '\uFFFD') check_num(9, '\t') # check a big number check_num(1000000000000000000, '\uFFFD') # check that multiple trailing semicolons are handled correctly for e in ['";', '";', '";', '";']: check(e, '";') # check that semicolons in the middle don't create problems for e in ['"quot;', '"quot;', '"quot;', '"quot;']: check(e, '"quot;') # check triple adjacent charrefs for e in ['"', '"', '"', '"']: check(e*3, '"""') check((e+';')*3, '"""') # check that the case is respected for e in ['&', '&', '&', '&']: check(e, '&') for e in ['&Amp', '&Amp;']: check(e, e) # check that non-existent named entities are returned unchanged check('&svadilfari;', '&svadilfari;') # the following examples are in the html5 specs check('¬it', '¬it') check('¬it;', '¬it;') check('¬in', '¬in') check('∉', '∉') # a similar example with a long name check('¬ReallyAnExistingNamedCharacterReference;', '¬ReallyAnExistingNamedCharacterReference;') # longest valid name check('∳', '∳') # check a charref that maps to two unicode chars check('∾̳', '\u223E\u0333') check('&acE', '&acE') # see #12888 check('{ ' * 1050, '{ ' * 1050) # see #15156 check('ÉricÉric&alphacentauriαcentauri', 'ÉricÉric&alphacentauriαcentauri') check('&co;', '&co;') if __name__ == '__main__': unittest.main()