mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-29 05:05:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Merge p3yk branch with the trunk up to revision 45595. This breaks a fair

Browse source 
number of tests, all because of the codecs/_multibytecodecs issue described
here (it's not a Py3K issue, just something Py3K discovers):
http://mail.python.org/pipermail/python-dev/2006-April/064051.html

Hye-Shik Chang promised to look for a fix, so no need to fix it here. The
tests that are expected to break are:

test_codecencodings_cn
test_codecencodings_hk
test_codecencodings_jp
test_codecencodings_kr
test_codecencodings_tw
test_codecs
test_multibytecodec

This merge fixes an actual test failure (test_weakref) in this branch,
though, so I believe merging is the right thing to do anyway.
This commit is contained in:
Thomas Wouters 2006-04-21 10:40:58 +00:00
parent 9ada3d6e29
commit 49fd7fa443
640 changed files with 52240 additions and 18408 deletions
Download patch file Download diff file Expand all files Collapse all files

542
Tools/pybench/Unicode.py Normal file
View file

@ -0,0 +1,542 @@
try:
unicode
except NameError:
raise ImportError
from pybench import Test
from string import join
class ConcatUnicode(Test):
version = 0.1
operations = 10 * 5
rounds = 60000
def test(self):
# Make sure the strings are *not* interned
s = unicode(join(map(str,range(100))))
t = unicode(join(map(str,range(1,101))))
for i in xrange(self.rounds):
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
t + s
def calibrate(self):
s = unicode(join(map(str,range(100))))
t = unicode(join(map(str,range(1,101))))
for i in xrange(self.rounds):
pass
class CompareUnicode(Test):
version = 0.1
operations = 10 * 5
rounds = 150000
def test(self):
# Make sure the strings are *not* interned
s = unicode(join(map(str,range(10))))
t = unicode(join(map(str,range(10))) + "abc")
for i in xrange(self.rounds):
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
t < s
t > s
t == s
t > s
t < s
def calibrate(self):
s = unicode(join(map(str,range(10))))
t = unicode(join(map(str,range(10))) + "abc")
for i in xrange(self.rounds):
pass
class CreateUnicodeWithConcat(Test):
version = 0.1
operations = 10 * 5
rounds = 80000
def test(self):
for i in xrange(self.rounds):
s = u'om'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
s = s + u'xax'
s = s + u'xbx'
s = s + u'xcx'
s = s + u'xdx'
s = s + u'xex'
def calibrate(self):
for i in xrange(self.rounds):
pass
class UnicodeSlicing(Test):
version = 0.1
operations = 5 * 7
rounds = 100000
def test(self):
s = unicode(join(map(str,range(100))))
for i in xrange(self.rounds):
s[50:]
s[:25]
s[50:55]
s[-1:]
s[:1]
s[2:]
s[11:-11]
s[50:]
s[:25]
s[50:55]
s[-1:]
s[:1]
s[2:]
s[11:-11]
s[50:]
s[:25]
s[50:55]
s[-1:]
s[:1]
s[2:]
s[11:-11]
s[50:]
s[:25]
s[50:55]
s[-1:]
s[:1]
s[2:]
s[11:-11]
s[50:]
s[:25]
s[50:55]
s[-1:]
s[:1]
s[2:]
s[11:-11]
def calibrate(self):
s = unicode(join(map(str,range(100))))
for i in xrange(self.rounds):
pass
### String methods
class UnicodeMappings(Test):
version = 0.1
operations = 3 * (5 + 4 + 2 + 1)
rounds = 10000
def test(self):
s = join(map(unichr,range(20)),'')
t = join(map(unichr,range(100)),'')
u = join(map(unichr,range(500)),'')
v = join(map(unichr,range(1000)),'')
for i in xrange(self.rounds):
s.lower()
s.lower()
s.lower()
s.lower()
s.lower()
s.upper()
s.upper()
s.upper()
s.upper()
s.upper()
s.title()
s.title()
s.title()
s.title()
s.title()
t.lower()
t.lower()
t.lower()
t.lower()
t.upper()
t.upper()
t.upper()
t.upper()
t.title()
t.title()
t.title()
t.title()
u.lower()
u.lower()
u.upper()
u.upper()
u.title()
u.title()
v.lower()
v.upper()
v.title()
def calibrate(self):
s = join(map(unichr,range(20)),'')
t = join(map(unichr,range(100)),'')
u = join(map(unichr,range(500)),'')
v = join(map(unichr,range(1000)),'')
for i in xrange(self.rounds):
pass
class UnicodePredicates(Test):
version = 0.1
operations = 5 * 9
rounds = 100000
def test(self):
data = (u'abc', u'123', u' ', u'\u1234\u2345\u3456', u'\uFFFF'*10)
len_data = len(data)
for i in xrange(self.rounds):
s = data[i % len_data]
s.isalnum()
s.isalpha()
s.isdecimal()
s.isdigit()
s.islower()
s.isnumeric()
s.isspace()
s.istitle()
s.isupper()
s.isalnum()
s.isalpha()
s.isdecimal()
s.isdigit()
s.islower()
s.isnumeric()
s.isspace()
s.istitle()
s.isupper()
s.isalnum()
s.isalpha()
s.isdecimal()
s.isdigit()
s.islower()
s.isnumeric()
s.isspace()
s.istitle()
s.isupper()
s.isalnum()
s.isalpha()
s.isdecimal()
s.isdigit()
s.islower()
s.isnumeric()
s.isspace()
s.istitle()
s.isupper()
s.isalnum()
s.isalpha()
s.isdecimal()
s.isdigit()
s.islower()
s.isnumeric()
s.isspace()
s.istitle()
s.isupper()
def calibrate(self):
data = (u'abc', u'123', u' ', u'\u1234\u2345\u3456', u'\uFFFF'*10)
len_data = len(data)
for i in xrange(self.rounds):
s = data[i % len_data]
try:
import unicodedata
except ImportError:
pass
else:
class UnicodeProperties(Test):
version = 0.1
operations = 5 * 8
rounds = 100000
def test(self):
data = (u'a', u'1', u' ', u'\u1234', u'\uFFFF')
len_data = len(data)
digit = unicodedata.digit
numeric = unicodedata.numeric
decimal = unicodedata.decimal
category = unicodedata.category
bidirectional = unicodedata.bidirectional
decomposition = unicodedata.decomposition
mirrored = unicodedata.mirrored
combining = unicodedata.combining
for i in xrange(self.rounds):
c = data[i % len_data]
digit(c, None)
numeric(c, None)
decimal(c, None)
category(c)
bidirectional(c)
decomposition(c)
mirrored(c)
combining(c)
digit(c, None)
numeric(c, None)
decimal(c, None)
category(c)
bidirectional(c)
decomposition(c)
mirrored(c)
combining(c)
digit(c, None)
numeric(c, None)
decimal(c, None)
category(c)
bidirectional(c)
decomposition(c)
mirrored(c)
combining(c)
digit(c, None)
numeric(c, None)
decimal(c, None)
category(c)
bidirectional(c)
decomposition(c)
mirrored(c)
combining(c)
digit(c, None)
numeric(c, None)
decimal(c, None)
category(c)
bidirectional(c)
decomposition(c)
mirrored(c)
combining(c)
def calibrate(self):
data = (u'a', u'1', u' ', u'\u1234', u'\uFFFF')
len_data = len(data)
digit = unicodedata.digit
numeric = unicodedata.numeric
decimal = unicodedata.decimal
category = unicodedata.category
bidirectional = unicodedata.bidirectional
decomposition = unicodedata.decomposition
mirrored = unicodedata.mirrored
combining = unicodedata.combining
for i in xrange(self.rounds):
c = data[i % len_data]