Skip to content

C
cpython
Kaydet (Commit) 7cdb495e authored tarafından Antoine Pitrou's avatar Antoine Pitrou
Dosyalara gözat
Seçenekler

Issue #3700: make test_bigmem py3k-compatible, and add bytes/bytearray tests 

(please note: some of the tests /do/ fail when run with a sufficiently large memory parameter (-M),
perhaps because of the str/bytes/bytearray overhaul)
üst d173589c
Show whitespace changes
Inline Side-by-side
Showing with 391 additions and 274 deletions
Lib/test/support.py
Dosyayı görüntüle @ 7cdb495e
...@@ -609,6 +609,10 @@ def bigmemtest(minsize, memuse, overhead=5*_1M): ...@@ -609,6 +609,10 @@ def bigmemtest(minsize, memuse, overhead=5*_1M):
""" """
def decorator(f): def decorator(f):
def wrapper(self): def wrapper(self):
# Retrieve values in case someone decided to adjust them
minsize = wrapper.minsize
memuse = wrapper.memuse
overhead = wrapper.overhead
if not max_memuse: if not max_memuse:
# If max_memuse is 0 (the default), # If max_memuse is 0 (the default),
# we still want to run the tests with size set to a few kb, # we still want to run the tests with size set to a few kb,
...@@ -636,6 +640,9 @@ def bigmemtest(minsize, memuse, overhead=5*_1M): ...@@ -636,6 +640,9 @@ def bigmemtest(minsize, memuse, overhead=5*_1M):
def precisionbigmemtest(size, memuse, overhead=5*_1M): def precisionbigmemtest(size, memuse, overhead=5*_1M):
def decorator(f): def decorator(f):
def wrapper(self): def wrapper(self):
size = wrapper.size
memuse = wrapper.memuse
overhead = wrapper.overhead
if not real_max_memuse: if not real_max_memuse:
maxsize = 5147 maxsize = 5147
else: else:
......
Lib/test/test_bigmem.py
Dosyayı görüntüle @ 7cdb495e
...@@ -4,6 +4,7 @@ from test.support import bigmemtest, _1G, _2G, _4G, precisionbigmemtest ...@@ -4,6 +4,7 @@ from test.support import bigmemtest, _1G, _2G, _4G, precisionbigmemtest
import unittest import unittest
import operator import operator
import sys import sys
import functools
# Bigmem testing houserules: # Bigmem testing houserules:
# #
...@@ -13,7 +14,7 @@ import sys ...@@ -13,7 +14,7 @@ import sys
# value has been created. Use 'del s' before the create_largestring call. # value has been created. Use 'del s' before the create_largestring call.
# #
# - Do *not* compare large objects using assertEquals or similar. It's a # - Do *not* compare large objects using assertEquals or similar. It's a
# lengty operation and the errormessage will be utterly useless due to # lengthy operation and the errormessage will be utterly useless due to
# its size. To make sure whether a result has the right contents, better # its size. To make sure whether a result has the right contents, better
# to use the strip or count methods, or compare meaningful slices. # to use the strip or count methods, or compare meaningful slices.
# #
...@@ -32,319 +33,284 @@ import sys ...@@ -32,319 +33,284 @@ import sys
# memuse-per-size should remain sane (less than a few thousand); if your # memuse-per-size should remain sane (less than a few thousand); if your
# test uses more, adjust 'size' upward, instead. # test uses more, adjust 'size' upward, instead.
class StrTest(unittest.TestCase): character_size = 4 if sys.maxunicode > 0xFFFF else 2
class BaseStrTest:
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_capitalize(self, size): def test_capitalize(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
s = '-' * size + SUBSTR SUBSTR = self.from_latin1(' abc def ghi')
s = _('-') * size + SUBSTR
caps = s.capitalize() caps = s.capitalize()
self.assertEquals(caps[-len(SUBSTR):], self.assertEquals(caps[-len(SUBSTR):],
SUBSTR.capitalize()) SUBSTR.capitalize())
self.assertEquals(caps.lstrip('-'), SUBSTR) self.assertEquals(caps.lstrip(_('-')), SUBSTR)
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
def test_center(self, size): def test_center(self, size):
SUBSTR = ' abc def ghi' SUBSTR = self.from_latin1(' abc def ghi')
s = SUBSTR.center(size)
self.assertEquals(len(s), size)
lpadsize = rpadsize = (len(s) - len(SUBSTR)) // 2
if len(s) % 2:
lpadsize += 1
self.assertEquals(s[lpadsize:-rpadsize], SUBSTR)
self.assertEquals(s.strip(), SUBSTR.strip())
@precisionbigmemtest(size=_2G - 1, memuse=1)
def test_center_unicode(self, size):
SUBSTR = ' abc def ghi'
try:
s = SUBSTR.center(size) s = SUBSTR.center(size)
except OverflowError:
pass # acceptable on 32-bit
else:
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
lpadsize = rpadsize = (len(s) - len(SUBSTR)) // 2 lpadsize = rpadsize = (len(s) - len(SUBSTR)) // 2
if len(s) % 2: if len(s) % 2:
lpadsize += 1 lpadsize += 1
self.assertEquals(s[lpadsize:-rpadsize], SUBSTR) self.assertEquals(s[lpadsize:-rpadsize], SUBSTR)
self.assertEquals(s.strip(), SUBSTR.strip()) self.assertEquals(s.strip(), SUBSTR.strip())
del s
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_count(self, size): def test_count(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
s = '.' * size + SUBSTR SUBSTR = _(' abc def ghi')
self.assertEquals(s.count('.'), size) s = _('.') * size + SUBSTR
s += '.' self.assertEquals(s.count(_('.')), size)
self.assertEquals(s.count('.'), size + 1) s += _('.')
self.assertEquals(s.count(' '), 3) self.assertEquals(s.count(_('.')), size + 1)
self.assertEquals(s.count('i'), 1) self.assertEquals(s.count(_(' ')), 3)
self.assertEquals(s.count('j'), 0) self.assertEquals(s.count(_('i')), 1)
self.assertEquals(s.count(_('j')), 0)
@bigmemtest(minsize=_2G + 2, memuse=3)
def test_decode(self, size):
s = b'.' * size
self.assertEquals(len(s.decode('utf-8')), size)
def basic_encode_test(self, size, enc, c='.', expectedsize=None):
if expectedsize is None:
expectedsize = size
s = c * size
self.assertEquals(len(s.encode(enc)), expectedsize)
@bigmemtest(minsize=_2G + 2, memuse=3)
def test_encode(self, size):
return self.basic_encode_test(size, 'utf-8')
@precisionbigmemtest(size=_4G / 6 + 2, memuse=2)
def test_encode_raw_unicode_escape(self, size):
try:
return self.basic_encode_test(size, 'raw_unicode_escape')
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_4G / 5 + 70, memuse=3)
def test_encode_utf7(self, size):
try:
return self.basic_encode_test(size, 'utf7')
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_4G / 4 + 5, memuse=6)
def test_encode_utf32(self, size):
try:
return self.basic_encode_test(size, 'utf32', expectedsize=4*size+4)
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_2G-1, memuse=2)
def test_decodeascii(self, size):
return self.basic_encode_test(size, 'ascii', c='A')
@precisionbigmemtest(size=_4G / 5, memuse=6+2)
def test_unicode_repr_oflw(self, size):
try:
s = "\uAAAA"*size
r = repr(s)
except MemoryError:
pass # acceptable on 32-bit
else:
self.failUnless(s == eval(r))
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_endswith(self, size): def test_endswith(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
s = '-' * size + SUBSTR SUBSTR = _(' abc def ghi')
s = _('-') * size + SUBSTR
self.failUnless(s.endswith(SUBSTR)) self.failUnless(s.endswith(SUBSTR))
self.failUnless(s.endswith(s)) self.failUnless(s.endswith(s))
s2 = '...' + s s2 = _('...') + s
self.failUnless(s2.endswith(s)) self.failUnless(s2.endswith(s))
self.failIf(s.endswith('a' + SUBSTR)) self.failIf(s.endswith(_('a') + SUBSTR))
self.failIf(SUBSTR.endswith(s)) self.failIf(SUBSTR.endswith(s))
@bigmemtest(minsize=_2G + 10, memuse=2) @bigmemtest(minsize=_2G + 10, memuse=2)
def test_expandtabs(self, size): def test_expandtabs(self, size):
s = '-' * size _ = self.from_latin1
s = _('-') * size
tabsize = 8 tabsize = 8
self.assertEquals(s.expandtabs(), s) self.assertEquals(s.expandtabs(), s)
del s del s
slen, remainder = divmod(size, tabsize) slen, remainder = divmod(size, tabsize)
s = ' \t' * slen s = _(' \t') * slen
s = s.expandtabs(tabsize) s = s.expandtabs(tabsize)
self.assertEquals(len(s), size - remainder) self.assertEquals(len(s), size - remainder)
self.assertEquals(len(s.strip(' ')), 0) self.assertEquals(len(s.strip(_(' '))), 0)
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_find(self, size): def test_find(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
sublen = len(SUBSTR) sublen = len(SUBSTR)
s = ''.join([SUBSTR, '-' * size, SUBSTR]) s = _('').join([SUBSTR, _('-') * size, SUBSTR])
self.assertEquals(s.find(' '), 0) self.assertEquals(s.find(_(' ')), 0)
self.assertEquals(s.find(SUBSTR), 0) self.assertEquals(s.find(SUBSTR), 0)
self.assertEquals(s.find(' ', sublen), sublen + size) self.assertEquals(s.find(_(' '), sublen), sublen + size)
self.assertEquals(s.find(SUBSTR, len(SUBSTR)), sublen + size) self.assertEquals(s.find(SUBSTR, len(SUBSTR)), sublen + size)
self.assertEquals(s.find('i'), SUBSTR.find('i')) self.assertEquals(s.find(_('i')), SUBSTR.find(_('i')))
self.assertEquals(s.find('i', sublen), self.assertEquals(s.find(_('i'), sublen),
sublen + size + SUBSTR.find('i')) sublen + size + SUBSTR.find(_('i')))
self.assertEquals(s.find('i', size), self.assertEquals(s.find(_('i'), size),
sublen + size + SUBSTR.find('i')) sublen + size + SUBSTR.find(_('i')))
self.assertEquals(s.find('j'), -1) self.assertEquals(s.find(_('j')), -1)
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_index(self, size): def test_index(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
sublen = len(SUBSTR) sublen = len(SUBSTR)
s = ''.join([SUBSTR, '-' * size, SUBSTR]) s = _('').join([SUBSTR, _('-') * size, SUBSTR])
self.assertEquals(s.index(' '), 0) self.assertEquals(s.index(_(' ')), 0)
self.assertEquals(s.index(SUBSTR), 0) self.assertEquals(s.index(SUBSTR), 0)
self.assertEquals(s.index(' ', sublen), sublen + size) self.assertEquals(s.index(_(' '), sublen), sublen + size)
self.assertEquals(s.index(SUBSTR, sublen), sublen + size) self.assertEquals(s.index(SUBSTR, sublen), sublen + size)
self.assertEquals(s.index('i'), SUBSTR.index('i')) self.assertEquals(s.index(_('i')), SUBSTR.index(_('i')))
self.assertEquals(s.index('i', sublen), self.assertEquals(s.index(_('i'), sublen),
sublen + size + SUBSTR.index('i')) sublen + size + SUBSTR.index(_('i')))
self.assertEquals(s.index('i', size), self.assertEquals(s.index(_('i'), size),
sublen + size + SUBSTR.index('i')) sublen + size + SUBSTR.index(_('i')))
self.assertRaises(ValueError, s.index, 'j') self.assertRaises(ValueError, s.index, _('j'))
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_isalnum(self, size): def test_isalnum(self, size):
SUBSTR = '123456' _ = self.from_latin1
s = 'a' * size + SUBSTR SUBSTR = _('123456')
s = _('a') * size + SUBSTR
self.failUnless(s.isalnum()) self.failUnless(s.isalnum())
s += '.' s += _('.')
self.failIf(s.isalnum()) self.failIf(s.isalnum())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_isalpha(self, size): def test_isalpha(self, size):
SUBSTR = 'zzzzzzz' _ = self.from_latin1
s = 'a' * size + SUBSTR SUBSTR = _('zzzzzzz')
s = _('a') * size + SUBSTR
self.failUnless(s.isalpha()) self.failUnless(s.isalpha())
s += '.' s += _('.')
self.failIf(s.isalpha()) self.failIf(s.isalpha())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_isdigit(self, size): def test_isdigit(self, size):
SUBSTR = '123456' _ = self.from_latin1
s = '9' * size + SUBSTR SUBSTR = _('123456')
s = _('9') * size + SUBSTR
self.failUnless(s.isdigit()) self.failUnless(s.isdigit())
s += 'z' s += _('z')
self.failIf(s.isdigit()) self.failIf(s.isdigit())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_islower(self, size): def test_islower(self, size):
chars = ''.join([ chr(c) for c in range(255) if not chr(c).isupper() ]) _ = self.from_latin1
chars = _(''.join(
chr(c) for c in range(255) if not chr(c).isupper()))
repeats = size // len(chars) + 2 repeats = size // len(chars) + 2
s = chars * repeats s = chars * repeats
self.failUnless(s.islower()) self.failUnless(s.islower())
s += 'A' s += _('A')
self.failIf(s.islower()) self.failIf(s.islower())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_isspace(self, size): def test_isspace(self, size):
whitespace = ' \f\n\r\t\v' _ = self.from_latin1
whitespace = _(' \f\n\r\t\v')
repeats = size // len(whitespace) + 2 repeats = size // len(whitespace) + 2
s = whitespace * repeats s = whitespace * repeats
self.failUnless(s.isspace()) self.failUnless(s.isspace())
s += 'j' s += _('j')
self.failIf(s.isspace()) self.failIf(s.isspace())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_istitle(self, size): def test_istitle(self, size):
SUBSTR = '123456' _ = self.from_latin1
s = ''.join(['A', 'a' * size, SUBSTR]) SUBSTR = _('123456')
s = _('').join([_('A'), _('a') * size, SUBSTR])
self.failUnless(s.istitle()) self.failUnless(s.istitle())
s += 'A' s += _('A')
self.failUnless(s.istitle()) self.failUnless(s.istitle())
s += 'aA' s += _('aA')
self.failIf(s.istitle()) self.failIf(s.istitle())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_isupper(self, size): def test_isupper(self, size):
chars = ''.join([ chr(c) for c in range(255) if not chr(c).islower() ]) _ = self.from_latin1
chars = _(''.join(
chr(c) for c in range(255) if not chr(c).islower()))
repeats = size // len(chars) + 2 repeats = size // len(chars) + 2
s = chars * repeats s = chars * repeats
self.failUnless(s.isupper()) self.failUnless(s.isupper())
s += 'a' s += _('a')
self.failIf(s.isupper()) self.failIf(s.isupper())
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_join(self, size): def test_join(self, size):
s = 'A' * size _ = self.from_latin1
x = s.join(['aaaaa', 'bbbbb']) s = _('A') * size
self.assertEquals(x.count('a'), 5) x = s.join([_('aaaaa'), _('bbbbb')])
self.assertEquals(x.count('b'), 5) self.assertEquals(x.count(_('a')), 5)
self.failUnless(x.startswith('aaaaaA')) self.assertEquals(x.count(_('b')), 5)
self.failUnless(x.endswith('Abbbbb')) self.failUnless(x.startswith(_('aaaaaA')))
self.failUnless(x.endswith(_('Abbbbb')))
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
def test_ljust(self, size): def test_ljust(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
s = SUBSTR.ljust(size) s = SUBSTR.ljust(size)
self.failUnless(s.startswith(SUBSTR + ' ')) self.failUnless(s.startswith(SUBSTR + _(' ')))
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.strip(), SUBSTR.strip()) self.assertEquals(s.strip(), SUBSTR.strip())
@bigmemtest(minsize=_2G + 10, memuse=2) @bigmemtest(minsize=_2G + 10, memuse=2)
def test_lower(self, size): def test_lower(self, size):
s = 'A' * size _ = self.from_latin1
s = _('A') * size
s = s.lower() s = s.lower()
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.count('a'), size) self.assertEquals(s.count(_('a')), size)
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
def test_lstrip(self, size): def test_lstrip(self, size):
SUBSTR = 'abc def ghi' _ = self.from_latin1
SUBSTR = _('abc def ghi')
s = SUBSTR.rjust(size) s = SUBSTR.rjust(size)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.lstrip(), SUBSTR.lstrip()) self.assertEquals(s.lstrip(), SUBSTR.lstrip())
del s del s
s = SUBSTR.ljust(size) s = SUBSTR.ljust(size)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
# Type-specific optimization
if isinstance(s, (str, bytes)):
stripped = s.lstrip() stripped = s.lstrip()
self.failUnless(stripped is s) self.failUnless(stripped is s)
@bigmemtest(minsize=_2G + 10, memuse=2) @bigmemtest(minsize=_2G + 10, memuse=2)
def test_replace(self, size): def test_replace(self, size):
replacement = 'a' _ = self.from_latin1
s = ' ' * size replacement = _('a')
s = s.replace(' ', replacement) s = _(' ') * size
s = s.replace(_(' '), replacement)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.count(replacement), size) self.assertEquals(s.count(replacement), size)
s = s.replace(replacement, ' ', size - 4) s = s.replace(replacement, _(' '), size - 4)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.count(replacement), 4) self.assertEquals(s.count(replacement), 4)
self.assertEquals(s[-10:], ' aaaa') self.assertEquals(s[-10:], _(' aaaa'))
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_rfind(self, size): def test_rfind(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
sublen = len(SUBSTR) sublen = len(SUBSTR)
s = ''.join([SUBSTR, '-' * size, SUBSTR]) s = _('').join([SUBSTR, _('-') * size, SUBSTR])
self.assertEquals(s.rfind(' '), sublen + size + SUBSTR.rfind(' ')) self.assertEquals(s.rfind(_(' ')), sublen + size + SUBSTR.rfind(_(' ')))
self.assertEquals(s.rfind(SUBSTR), sublen + size) self.assertEquals(s.rfind(SUBSTR), sublen + size)
self.assertEquals(s.rfind(' ', 0, size), SUBSTR.rfind(' ')) self.assertEquals(s.rfind(_(' '), 0, size), SUBSTR.rfind(_(' ')))
self.assertEquals(s.rfind(SUBSTR, 0, sublen + size), 0) self.assertEquals(s.rfind(SUBSTR, 0, sublen + size), 0)
self.assertEquals(s.rfind('i'), sublen + size + SUBSTR.rfind('i')) self.assertEquals(s.rfind(_('i')), sublen + size + SUBSTR.rfind(_('i')))
self.assertEquals(s.rfind('i', 0, sublen), SUBSTR.rfind('i')) self.assertEquals(s.rfind(_('i'), 0, sublen), SUBSTR.rfind(_('i')))
self.assertEquals(s.rfind('i', 0, sublen + size), self.assertEquals(s.rfind(_('i'), 0, sublen + size),
SUBSTR.rfind('i')) SUBSTR.rfind(_('i')))
self.assertEquals(s.rfind('j'), -1) self.assertEquals(s.rfind(_('j')), -1)
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_rindex(self, size): def test_rindex(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
sublen = len(SUBSTR) sublen = len(SUBSTR)
s = ''.join([SUBSTR, '-' * size, SUBSTR]) s = _('').join([SUBSTR, _('-') * size, SUBSTR])
self.assertEquals(s.rindex(' '), self.assertEquals(s.rindex(_(' ')),
sublen + size + SUBSTR.rindex(' ')) sublen + size + SUBSTR.rindex(_(' ')))
self.assertEquals(s.rindex(SUBSTR), sublen + size) self.assertEquals(s.rindex(SUBSTR), sublen + size)
self.assertEquals(s.rindex(' ', 0, sublen + size - 1), self.assertEquals(s.rindex(_(' '), 0, sublen + size - 1),
SUBSTR.rindex(' ')) SUBSTR.rindex(_(' ')))
self.assertEquals(s.rindex(SUBSTR, 0, sublen + size), 0) self.assertEquals(s.rindex(SUBSTR, 0, sublen + size), 0)
self.assertEquals(s.rindex('i'), self.assertEquals(s.rindex(_('i')),
sublen + size + SUBSTR.rindex('i')) sublen + size + SUBSTR.rindex(_('i')))
self.assertEquals(s.rindex('i', 0, sublen), SUBSTR.rindex('i')) self.assertEquals(s.rindex(_('i'), 0, sublen), SUBSTR.rindex(_('i')))
self.assertEquals(s.rindex('i', 0, sublen + size), self.assertEquals(s.rindex(_('i'), 0, sublen + size),
SUBSTR.rindex('i')) SUBSTR.rindex(_('i')))
self.assertRaises(ValueError, s.rindex, 'j') self.assertRaises(ValueError, s.rindex, _('j'))
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
def test_rjust(self, size): def test_rjust(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
s = SUBSTR.ljust(size) s = SUBSTR.ljust(size)
self.failUnless(s.startswith(SUBSTR + ' ')) self.failUnless(s.startswith(SUBSTR + _(' ')))
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.strip(), SUBSTR.strip()) self.assertEquals(s.strip(), SUBSTR.strip())
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
def test_rstrip(self, size): def test_rstrip(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
SUBSTR = _(' abc def ghi')
s = SUBSTR.ljust(size) s = SUBSTR.ljust(size)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.rstrip(), SUBSTR.rstrip()) self.assertEquals(s.rstrip(), SUBSTR.rstrip())
del s del s
s = SUBSTR.rjust(size) s = SUBSTR.rjust(size)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
# Type-specific optimization
if isinstance(s, (str, bytes)):
stripped = s.rstrip() stripped = s.rstrip()
self.failUnless(stripped is s) self.failUnless(stripped is s)
...@@ -353,18 +319,23 @@ class StrTest(unittest.TestCase): ...@@ -353,18 +319,23 @@ class StrTest(unittest.TestCase):
# hold sqrt(size) items. It's close but just over 2x size. # hold sqrt(size) items. It's close but just over 2x size.
@bigmemtest(minsize=_2G, memuse=2.1) @bigmemtest(minsize=_2G, memuse=2.1)
def test_split_small(self, size): def test_split_small(self, size):
_ = self.from_latin1
# Crudely calculate an estimate so that the result of s.split won't # Crudely calculate an estimate so that the result of s.split won't
# take up an inordinate amount of memory # take up an inordinate amount of memory
chunksize = int(size ** 0.5 + 2) chunksize = int(size ** 0.5 + 2)
SUBSTR = 'a' + ' ' * chunksize SUBSTR = _('a') + _(' ') * chunksize
s = SUBSTR * chunksize s = SUBSTR * chunksize
l = s.split() l = s.split()
self.assertEquals(len(l), chunksize) self.assertEquals(len(l), chunksize)
self.assertEquals(set(l), set(['a'])) expected = _('a')
for item in l:
self.assertEquals(item, expected)
del l del l
l = s.split('a') l = s.split(_('a'))
self.assertEquals(len(l), chunksize + 1) self.assertEquals(len(l), chunksize + 1)
self.assertEquals(set(l), set(['', ' ' * chunksize])) expected = _(' ') * chunksize
for item in filter(None, l):
self.assertEquals(item, expected)
# Allocates a string of twice size (and briefly two) and a list of # Allocates a string of twice size (and briefly two) and a list of
# size. Because of internal affairs, the s.split() call produces a # size. Because of internal affairs, the s.split() call produces a
...@@ -374,37 +345,43 @@ class StrTest(unittest.TestCase): ...@@ -374,37 +345,43 @@ class StrTest(unittest.TestCase):
# 8*size bytes. # 8*size bytes.
@bigmemtest(minsize=_2G + 5, memuse=10) @bigmemtest(minsize=_2G + 5, memuse=10)
def test_split_large(self, size): def test_split_large(self, size):
s = ' a' * size + ' ' _ = self.from_latin1
s = _(' a') * size + _(' ')
l = s.split() l = s.split()
self.assertEquals(len(l), size) self.assertEquals(len(l), size)
self.assertEquals(set(l), set(['a'])) self.assertEquals(set(l), set([_('a')]))
del l del l
l = s.split('a') l = s.split(_('a'))
self.assertEquals(len(l), size + 1) self.assertEquals(len(l), size + 1)
self.assertEquals(set(l), set([' '])) self.assertEquals(set(l), set([_(' ')]))
@bigmemtest(minsize=_2G, memuse=2.1) @bigmemtest(minsize=_2G, memuse=2.1)
def test_splitlines(self, size): def test_splitlines(self, size):
_ = self.from_latin1
# Crudely calculate an estimate so that the result of s.split won't # Crudely calculate an estimate so that the result of s.split won't
# take up an inordinate amount of memory # take up an inordinate amount of memory
chunksize = int(size ** 0.5 + 2) // 2 chunksize = int(size ** 0.5 + 2) // 2
SUBSTR = ' ' * chunksize + '\n' + ' ' * chunksize + '\r\n' SUBSTR = _(' ') * chunksize + _('\n') + _(' ') * chunksize + _('\r\n')
s = SUBSTR * chunksize s = SUBSTR * chunksize
l = s.splitlines() l = s.splitlines()
self.assertEquals(len(l), chunksize * 2) self.assertEquals(len(l), chunksize * 2)
self.assertEquals(set(l), set([' ' * chunksize])) expected = _(' ') * chunksize
for item in l:
self.assertEquals(item, expected)
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_startswith(self, size): def test_startswith(self, size):
SUBSTR = ' abc def ghi' _ = self.from_latin1
s = '-' * size + SUBSTR SUBSTR = _(' abc def ghi')
s = _('-') * size + SUBSTR
self.failUnless(s.startswith(s)) self.failUnless(s.startswith(s))
self.failUnless(s.startswith('-' * size)) self.failUnless(s.startswith(_('-') * size))
self.failIf(s.startswith(SUBSTR)) self.failIf(s.startswith(SUBSTR))
@bigmemtest(minsize=_2G, memuse=1) @bigmemtest(minsize=_2G, memuse=1)
def test_strip(self, size): def test_strip(self, size):
SUBSTR = ' abc def ghi ' _ = self.from_latin1
SUBSTR = _(' abc def ghi ')
s = SUBSTR.rjust(size) s = SUBSTR.rjust(size)
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.strip(), SUBSTR.strip()) self.assertEquals(s.strip(), SUBSTR.strip())
...@@ -415,7 +392,8 @@ class StrTest(unittest.TestCase): ...@@ -415,7 +392,8 @@ class StrTest(unittest.TestCase):
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_swapcase(self, size): def test_swapcase(self, size):
SUBSTR = "aBcDeFG12.'\xa9\x00" _ = self.from_latin1
SUBSTR = _("aBcDeFG12.'\xa9\x00")
sublen = len(SUBSTR) sublen = len(SUBSTR)
repeats = size // sublen + 2 repeats = size // sublen + 2
s = SUBSTR * repeats s = SUBSTR * repeats
...@@ -426,7 +404,8 @@ class StrTest(unittest.TestCase): ...@@ -426,7 +404,8 @@ class StrTest(unittest.TestCase):
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_title(self, size): def test_title(self, size):
SUBSTR = 'SpaaHAaaAaham' _ = self.from_latin1
SUBSTR = _('SpaaHAaaAaham')
s = SUBSTR * (size // len(SUBSTR) + 2) s = SUBSTR * (size // len(SUBSTR) + 2)
s = s.title() s = s.title()
self.failUnless(s.startswith((SUBSTR * 3).title())) self.failUnless(s.startswith((SUBSTR * 3).title()))
...@@ -434,8 +413,19 @@ class StrTest(unittest.TestCase): ...@@ -434,8 +413,19 @@ class StrTest(unittest.TestCase):
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_translate(self, size): def test_translate(self, size):
trans = {ord('.'):'-', ord('a'):'!', ord('Z'):'$'} _ = self.from_latin1
SUBSTR = 'aZz.z.Aaz.' trans = {
ord(_('.')): _('-'),
ord(_('a')): _('!'),
ord(_('Z')): _('$'),
}
SUBSTR = _('aZz.z.Aaz.')
if not isinstance(SUBSTR, str):
# Workaround the inexistence of bytes.maketrans()
chars = bytearray(range(256))
for k, v in trans.items():
chars[k] = ord(v)
trans = chars
sublen = len(SUBSTR) sublen = len(SUBSTR)
repeats = size // sublen + 2 repeats = size // sublen + 2
s = SUBSTR * repeats s = SUBSTR * repeats
...@@ -443,106 +433,54 @@ class StrTest(unittest.TestCase): ...@@ -443,106 +433,54 @@ class StrTest(unittest.TestCase):
self.assertEquals(len(s), repeats * sublen) self.assertEquals(len(s), repeats * sublen)
self.assertEquals(s[:sublen], SUBSTR.translate(trans)) self.assertEquals(s[:sublen], SUBSTR.translate(trans))
self.assertEquals(s[-sublen:], SUBSTR.translate(trans)) self.assertEquals(s[-sublen:], SUBSTR.translate(trans))
self.assertEquals(s.count('.'), 0) self.assertEquals(s.count(_('.')), 0)
self.assertEquals(s.count('!'), repeats * 2) self.assertEquals(s.count(_('!')), repeats * 2)
self.assertEquals(s.count('z'), repeats * 3) self.assertEquals(s.count(_('z')), repeats * 3)
@bigmemtest(minsize=_2G + 5, memuse=2) @bigmemtest(minsize=_2G + 5, memuse=2)
def test_upper(self, size): def test_upper(self, size):
s = 'a' * size _ = self.from_latin1
s = _('a') * size
s = s.upper() s = s.upper()
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.count('A'), size) self.assertEquals(s.count(_('A')), size)
@bigmemtest(minsize=_2G + 20, memuse=1) @bigmemtest(minsize=_2G + 20, memuse=1)
def test_zfill(self, size): def test_zfill(self, size):
SUBSTR = '-568324723598234' _ = self.from_latin1
SUBSTR = _('-568324723598234')
s = SUBSTR.zfill(size) s = SUBSTR.zfill(size)
self.failUnless(s.endswith('0' + SUBSTR[1:])) self.failUnless(s.endswith(_('0') + SUBSTR[1:]))
self.failUnless(s.startswith('-0')) self.failUnless(s.startswith(_('-0')))
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
self.assertEquals(s.count('0'), size - len(SUBSTR)) self.assertEquals(s.count(_('0')), size - len(SUBSTR))
@bigmemtest(minsize=_2G + 10, memuse=2)
def test_format(self, size):
s = '-' * size
sf = '%s' % (s,)
self.assertEqual(s, sf)
del sf
sf = '..%s..' % (s,)
self.assertEquals(len(sf), len(s) + 4)
self.failUnless(sf.startswith('..-'))
self.failUnless(sf.endswith('-..'))
del s, sf
size //= 2
edge = '-' * size
s = ''.join([edge, '%s', edge])
del edge
s = s % '...'
self.assertEquals(len(s), size * 2 + 3)
self.assertEquals(s.count('.'), 3)
self.assertEquals(s.count('-'), size * 2)
@bigmemtest(minsize=_2G + 10, memuse=2)
def test_repr_small(self, size):
s = '-' * size
s = repr(s)
self.assertEquals(len(s), size + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('-'), size)
del s
# repr() will create a string four times as large as this 'binary
# string', but we don't want to allocate much more than twice
# size in total. (We do extra testing in test_repr_large())
size = size // 5 * 2
s = '\x00' * size
s = repr(s)
self.assertEquals(len(s), size * 4 + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('\\'), size)
self.assertEquals(s.count('0'), size * 2)
@bigmemtest(minsize=_2G + 10, memuse=5)
def test_repr_large(self, size):
s = '\x00' * size
s = repr(s)
self.assertEquals(len(s), size * 4 + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('\\'), size)
self.assertEquals(s.count('0'), size * 2)
@bigmemtest(minsize=2**32 / 5, memuse=6+2)
def test_unicode_repr(self, size):
s = "\uAAAA" * size
self.failUnless(len(repr(s)) > size)
# This test is meaningful even with size < 2G, as long as the # This test is meaningful even with size < 2G, as long as the
# doubled string is > 2G (but it tests more if both are > 2G :) # doubled string is > 2G (but it tests more if both are > 2G :)
@bigmemtest(minsize=_1G + 2, memuse=3) @bigmemtest(minsize=_1G + 2, memuse=3)
def test_concat(self, size): def test_concat(self, size):
s = '.' * size _ = self.from_latin1
s = _('.') * size
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
s = s + s s = s + s
self.assertEquals(len(s), size * 2) self.assertEquals(len(s), size * 2)
self.assertEquals(s.count('.'), size * 2) self.assertEquals(s.count(_('.')), size * 2)
# This test is meaningful even with size < 2G, as long as the # This test is meaningful even with size < 2G, as long as the
# repeated string is > 2G (but it tests more if both are > 2G :) # repeated string is > 2G (but it tests more if both are > 2G :)
@bigmemtest(minsize=_1G + 2, memuse=3) @bigmemtest(minsize=_1G + 2, memuse=3)
def test_repeat(self, size): def test_repeat(self, size):
s = '.' * size _ = self.from_latin1
s = _('.') * size
self.assertEquals(len(s), size) self.assertEquals(len(s), size)
s = s * 2 s = s * 2
self.assertEquals(len(s), size * 2) self.assertEquals(len(s), size * 2)
self.assertEquals(s.count('.'), size * 2) self.assertEquals(s.count(_('.')), size * 2)
@bigmemtest(minsize=_2G + 20, memuse=1) @bigmemtest(minsize=_2G + 20, memuse=2)
def test_slice_and_getitem(self, size): def test_slice_and_getitem(self, size):
SUBSTR = '0123456789' _ = self.from_latin1
SUBSTR = _('0123456789')
sublen = len(SUBSTR) sublen = len(SUBSTR)
s = SUBSTR * (size // sublen) s = SUBSTR * (size // sublen)
stepsize = len(s) // 100 stepsize = len(s) // 100
...@@ -560,9 +498,9 @@ class StrTest(unittest.TestCase): ...@@ -560,9 +498,9 @@ class StrTest(unittest.TestCase):
self.assertEquals(s[-1], SUBSTR[-1]) self.assertEquals(s[-1], SUBSTR[-1])
self.assertEquals(s[len(s) - 10], SUBSTR[0]) self.assertEquals(s[len(s) - 10], SUBSTR[0])
self.assertEquals(s[-sublen], SUBSTR[0]) self.assertEquals(s[-sublen], SUBSTR[0])
self.assertEquals(s[len(s):], '') self.assertEquals(s[len(s):], _(''))
self.assertEquals(s[len(s) - 1:], SUBSTR[-1]) self.assertEquals(s[len(s) - 1:], SUBSTR[-1:])
self.assertEquals(s[-1:], SUBSTR[-1]) self.assertEquals(s[-1:], SUBSTR[-1:])
self.assertEquals(s[len(s) - sublen:], SUBSTR) self.assertEquals(s[len(s) - sublen:], SUBSTR)
self.assertEquals(s[-sublen:], SUBSTR) self.assertEquals(s[-sublen:], SUBSTR)
self.assertEquals(len(s[:]), len(s)) self.assertEquals(len(s[:]), len(s))
...@@ -575,27 +513,29 @@ class StrTest(unittest.TestCase): ...@@ -575,27 +513,29 @@ class StrTest(unittest.TestCase):
@bigmemtest(minsize=_2G, memuse=2) @bigmemtest(minsize=_2G, memuse=2)
def test_contains(self, size): def test_contains(self, size):
SUBSTR = '0123456789' _ = self.from_latin1
edge = '-' * (size // 2) SUBSTR = _('0123456789')
s = ''.join([edge, SUBSTR, edge]) edge = _('-') * (size // 2)
s = _('').join([edge, SUBSTR, edge])
del edge del edge
self.failUnless(SUBSTR in s) self.failUnless(SUBSTR in s)
self.failIf(SUBSTR * 2 in s) self.failIf(SUBSTR * 2 in s)
self.failUnless('-' in s) self.failUnless(_('-') in s)
self.failIf('a' in s) self.failIf(_('a') in s)
s += 'a' s += _('a')
self.failUnless('a' in s) self.failUnless(_('a') in s)
@bigmemtest(minsize=_2G + 10, memuse=2) @bigmemtest(minsize=_2G + 10, memuse=2)
def test_compare(self, size): def test_compare(self, size):
s1 = '-' * size _ = self.from_latin1
s2 = '-' * size s1 = _('-') * size
s2 = _('-') * size
self.assertEqual(s1, s2) self.assertEqual(s1, s2)
del s2 del s2
s2 = s1 + 'a' s2 = s1 + _('a')
self.failIf(s1 == s2) self.failIf(s1 == s2)
del s2 del s2
s2 = '.' * size s2 = _('.') * size
self.failIf(s1 == s2) self.failIf(s1 == s2)
@bigmemtest(minsize=_2G + 10, memuse=1) @bigmemtest(minsize=_2G + 10, memuse=1)
...@@ -606,12 +546,181 @@ class StrTest(unittest.TestCase): ...@@ -606,12 +546,181 @@ class StrTest(unittest.TestCase):
# test is dodgy (there's no *guarantee* that the two things should # test is dodgy (there's no *guarantee* that the two things should
# have a different hash, even if they, in the current # have a different hash, even if they, in the current
# implementation, almost always do.) # implementation, almost always do.)
s = '\x00' * size _ = self.from_latin1
s = _('\x00') * size
h1 = hash(s) h1 = hash(s)
del s del s
s = '\x00' * (size + 1) s = _('\x00') * (size + 1)
self.failIf(h1 == hash(s)) self.failIf(h1 == hash(s))
class StrTest(unittest.TestCase, BaseStrTest):
def from_latin1(self, s):
return s
def basic_encode_test(self, size, enc, c='.', expectedsize=None):
if expectedsize is None:
expectedsize = size
s = c * size
self.assertEquals(len(s.encode(enc)), expectedsize)
def setUp(self):
# HACK: adjust memory use of tests inherited from BaseStrTest
# according to character size.
self._adjusted = {}
for name in dir(BaseStrTest):
if not name.startswith('test_'):
continue
meth = getattr(type(self), name)
try:
memuse = meth.memuse
except AttributeError:
continue
meth.memuse = character_size * memuse
self._adjusted[name] = memuse
def tearDown(self):
for name, memuse in self._adjusted.items():
getattr(type(self), name).memuse = memuse
@bigmemtest(minsize=_2G + 2, memuse=character_size + 1)
def test_encode(self, size):
return self.basic_encode_test(size, 'utf-8')
@precisionbigmemtest(size=_4G // 6 + 2, memuse=character_size + 1)
def test_encode_raw_unicode_escape(self, size):
try:
return self.basic_encode_test(size, 'raw_unicode_escape')
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_4G // 5 + 70, memuse=character_size + 1)
def test_encode_utf7(self, size):
try:
return self.basic_encode_test(size, 'utf7')
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_4G // 4 + 5, memuse=character_size + 4)
def test_encode_utf32(self, size):
try:
return self.basic_encode_test(size, 'utf32', expectedsize=4*size+4)
except MemoryError:
pass # acceptable on 32-bit
@precisionbigmemtest(size=_2G - 1, memuse=character_size + 1)
def test_encode_ascii(self, size):
return self.basic_encode_test(size, 'ascii', c='A')
@precisionbigmemtest(size=_4G // 5, memuse=character_size * (6 + 1))
def test_unicode_repr_overflow(self, size):
try:
s = "\uAAAA"*size
r = repr(s)
except MemoryError:
pass # acceptable on 32-bit
else:
self.failUnless(s == eval(r))
@bigmemtest(minsize=_2G + 10, memuse=character_size * 2)
def test_format(self, size):
s = '-' * size
sf = '%s' % (s,)
self.assertEqual(s, sf)
del sf
sf = '..%s..' % (s,)
self.assertEquals(len(sf), len(s) + 4)
self.failUnless(sf.startswith('..-'))
self.failUnless(sf.endswith('-..'))
del s, sf
size //= 2
edge = '-' * size
s = ''.join([edge, '%s', edge])
del edge
s = s % '...'
self.assertEquals(len(s), size * 2 + 3)
self.assertEquals(s.count('.'), 3)
self.assertEquals(s.count('-'), size * 2)
@bigmemtest(minsize=_2G + 10, memuse=character_size * 2)
def test_repr_small(self, size):
s = '-' * size
s = repr(s)
self.assertEquals(len(s), size + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('-'), size)
del s
# repr() will create a string four times as large as this 'binary
# string', but we don't want to allocate much more than twice
# size in total. (We do extra testing in test_repr_large())
size = size // 5 * 2
s = '\x00' * size
s = repr(s)
self.assertEquals(len(s), size * 4 + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('\\'), size)
self.assertEquals(s.count('0'), size * 2)
@bigmemtest(minsize=_2G + 10, memuse=character_size * 5)
def test_repr_large(self, size):
s = '\x00' * size
s = repr(s)
self.assertEquals(len(s), size * 4 + 2)
self.assertEquals(s[0], "'")
self.assertEquals(s[-1], "'")
self.assertEquals(s.count('\\'), size)
self.assertEquals(s.count('0'), size * 2)
@bigmemtest(minsize=2**32 / 5, memuse=character_size * 7)
def test_unicode_repr(self, size):
s = "\uAAAA" * size
for f in (repr, ascii):
r = f(s)
self.failUnless(len(r) > size)
self.failUnless(r.endswith(r"\uaaaa'"), r[-10:])
del r
# The character takes 4 bytes even in UCS-2 builds because it will
# be decomposed into surrogates.
@bigmemtest(minsize=2**32 / 5, memuse=4 + character_size * 9)
def test_unicode_repr_wide(self, size):
s = "\U0001AAAA" * size
for f in (repr, ascii):
r = f(s)
self.failUnless(len(r) > size)
self.failUnless(r.endswith(r"\U0001aaaa'"), r[-12:])
del r
class BytesTest(unittest.TestCase, BaseStrTest):
def from_latin1(self, s):
return s.encode("latin1")
@bigmemtest(minsize=_2G + 2, memuse=1 + character_size)
def test_decode(self, size):
s = self.from_latin1('.') * size
self.assertEquals(len(s.decode('utf-8')), size)
class BytearrayTest(unittest.TestCase, BaseStrTest):
def from_latin1(self, s):
return bytearray(s.encode("latin1"))
@bigmemtest(minsize=_2G + 2, memuse=1 + character_size)
def test_decode(self, size):
s = self.from_latin1('.') * size
self.assertEquals(len(s.decode('utf-8')), size)
test_hash = None
test_split_large = None
class TupleTest(unittest.TestCase): class TupleTest(unittest.TestCase):
# Tuples have a small, fixed-sized head and an array of pointers to # Tuples have a small, fixed-sized head and an array of pointers to
...@@ -1048,7 +1157,8 @@ class ListTest(unittest.TestCase): ...@@ -1048,7 +1157,8 @@ class ListTest(unittest.TestCase):
self.assertEquals(l[-10:], [5] * 10) self.assertEquals(l[-10:], [5] * 10)
def test_main(): def test_main():
support.run_unittest(StrTest, TupleTest, ListTest) support.run_unittest(StrTest, BytesTest, BytearrayTest,
TupleTest, ListTest)
if __name__ == '__main__': if __name__ == '__main__':
if len(sys.argv) > 1: if len(sys.argv) > 1:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment