Marc-Andre's third try at this bulk patch seems to work (except that
his copy of test_contains.py seems to be broken -- the lines he
deleted were already absent). Checkin messages:
New Unicode support for int(), float(), complex() and long().
- new APIs PyInt_FromUnicode() and PyLong_FromUnicode()
- added support for Unicode to PyFloat_FromString()
- new encoding API PyUnicode_EncodeDecimal() which converts
Unicode to a decimal char* string (used in the above new
APIs)
- shortcuts for calls like int(<int object>) and float(<float obj>)
- tests for all of the above
Unicode compares and contains checks:
- comparing Unicode and non-string types now works; TypeErrors
are masked, all other errors such as ValueError during
Unicode coercion are passed through (note that PyUnicode_Compare
does not implement the masking -- PyObject_Compare does this)
- contains now works for non-string types too; TypeErrors are
masked and 0 returned; all other errors are passed through
Better testing support for the standard codecs.
Misc minor enhancements, such as an alias dbcs for the mbcs codec.
Changes:
- PyLong_FromString() now applies the same error checks as
does PyInt_FromString(): trailing garbage is reported
as error and not longer silently ignored. The only characters
which may be trailing the digits are 'L' and 'l' -- these
are still silently ignored.
- string.ato?() now directly interface to int(), long() and
float(). The error strings are now a little different, but
the type still remains the same. These functions are now
ready to get declared obsolete ;-)
- PyNumber_Int() now also does a check for embedded NULL chars
in the input string; PyNumber_Long() already did this (and
still does)
Followed by:
Looks like I've gone a step too far there... (and test_contains.py
seem to have a bug too).
I've changed back to reporting all errors in PyUnicode_Contains()
and added a few more test cases to test_contains.py (plus corrected
the join() NameError).
diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
index cd5876e..fa3119a 100644
--- a/Lib/encodings/__init__.py
+++ b/Lib/encodings/__init__.py
@@ -4,8 +4,8 @@
directory.
Codec modules must have names corresponding to standard lower-case
- encoding names. Hyphens are automatically converted to
- underscores, e.g. 'utf-8' is looked up as module utf_8.
+ encoding names with hyphens mapped to underscores, e.g. 'utf-8' is
+ implemented by the module 'utf_8.py'.
Each codec module must export the following interface:
@@ -40,7 +40,7 @@
return entry
# Import the module
- modname = string.replace(encoding,'-','_')
+ modname = string.replace(encoding, '-', '_')
modname = aliases.aliases.get(modname,modname)
try:
mod = __import__(modname,globals(),locals(),'*')
diff --git a/Lib/encodings/aliases.py b/Lib/encodings/aliases.py
index d99b38e..1214cf9 100644
--- a/Lib/encodings/aliases.py
+++ b/Lib/encodings/aliases.py
@@ -54,4 +54,7 @@
'macroman': 'mac_roman',
'macturkish': 'mac_turkish',
+ # MBCS
+ 'dbcs': 'mbcs',
+
}
diff --git a/Lib/string.py b/Lib/string.py
index 5eb5697..5f90723 100644
--- a/Lib/string.py
+++ b/Lib/string.py
@@ -196,14 +196,11 @@
Return the floating point number represented by the string s.
"""
- if type(s) == _StringType:
- return _float(s)
- else:
- raise TypeError('argument 1: expected string, %s found' %
- type(s).__name__)
+ return _float(s)
+
# Convert string to integer
-def atoi(*args):
+def atoi(s , base=10):
"""atoi(s [,base]) -> int
Return the integer represented by the string s in the given
@@ -214,23 +211,11 @@
accepted.
"""
- try:
- s = args[0]
- except IndexError:
- raise TypeError('function requires at least 1 argument: %d given' %
- len(args))
- # Don't catch type error resulting from too many arguments to int(). The
- # error message isn't compatible but the error type is, and this function
- # is complicated enough already.
- if type(s) == _StringType:
- return _apply(_int, args)
- else:
- raise TypeError('argument 1: expected string, %s found' %
- type(s).__name__)
+ return _int(s, base)
# Convert string to long integer
-def atol(*args):
+def atol(s, base=10):
"""atol(s [,base]) -> long
Return the long integer represented by the string s in the
@@ -242,19 +227,7 @@
unless base is 0.
"""
- try:
- s = args[0]
- except IndexError:
- raise TypeError('function requires at least 1 argument: %d given' %
- len(args))
- # Don't catch type error resulting from too many arguments to long(). The
- # error message isn't compatible but the error type is, and this function
- # is complicated enough already.
- if type(s) == _StringType:
- return _apply(_long, args)
- else:
- raise TypeError('argument 1: expected string, %s found' %
- type(s).__name__)
+ return _long(s, base)
# Left-justify a string
diff --git a/Lib/test/output/test_unicode b/Lib/test/output/test_unicode
index 88e8624..15ffdc1 100644
--- a/Lib/test/output/test_unicode
+++ b/Lib/test/output/test_unicode
@@ -3,3 +3,4 @@
Testing Unicode contains method... done.
Testing Unicode formatting strings... done.
Testing builtin codecs... done.
+Testing standard mapping codecs... 0-127... 128-255... done.
diff --git a/Lib/test/test_b1.py b/Lib/test/test_b1.py
index d9c6320..6a89d22 100644
--- a/Lib/test/test_b1.py
+++ b/Lib/test/test_b1.py
@@ -95,6 +95,7 @@
if complex(0j, 3.14) <> 3.14j: raise TestFailed, 'complex(0j, 3.14)'
if complex(0.0, 3.14) <> 3.14j: raise TestFailed, 'complex(0.0, 3.14)'
if complex(" 3.14+J ") <> 3.14+1j: raise TestFailed, 'complex(" 3.14+J )"'
+if complex(u" 3.14+J ") <> 3.14+1j: raise TestFailed, 'complex(u" 3.14+J )"'
class Z:
def __complex__(self): return 3.14j
z = Z()
@@ -208,6 +209,9 @@
if float(314) <> 314.0: raise TestFailed, 'float(314)'
if float(314L) <> 314.0: raise TestFailed, 'float(314L)'
if float(" 3.14 ") <> 3.14: raise TestFailed, 'float(" 3.14 ")'
+if float(u" 3.14 ") <> 3.14: raise TestFailed, 'float(u" 3.14 ")'
+if float(u" \u0663.\u0661\u0664 ") <> 3.14:
+ raise TestFailed, 'float(u" \u0663.\u0661\u0664 ")'
print 'getattr'
import sys
@@ -254,6 +258,9 @@
if int(-3.9) <> -3: raise TestFailed, 'int(-3.9)'
if int(3.5) <> 3: raise TestFailed, 'int(3.5)'
if int(-3.5) <> -3: raise TestFailed, 'int(-3.5)'
+# Different base:
+if int("10",16) <> 16L: raise TestFailed, 'int("10",16)'
+if int(u"10",16) <> 16L: raise TestFailed, 'int(u"10",16)'
# Test conversion fron strings and various anomalies
L = [
('0', 0),
@@ -267,9 +274,28 @@
('314 ', 314),
(' \t\t 314 \t\t ', 314),
(`sys.maxint`, sys.maxint),
+ (' 1x', ValueError),
+ (' 1 ', 1),
+ (' 1\02 ', ValueError),
('', ValueError),
(' ', ValueError),
(' \t\t ', ValueError),
+ (u'0', 0),
+ (u'1', 1),
+ (u'9', 9),
+ (u'10', 10),
+ (u'99', 99),
+ (u'100', 100),
+ (u'314', 314),
+ (u' 314', 314),
+ (u'\u0663\u0661\u0664 ', 314),
+ (u' \t\t 314 \t\t ', 314),
+ (u' 1x', ValueError),
+ (u' 1 ', 1),
+ (u' 1\02 ', ValueError),
+ (u'', ValueError),
+ (u' ', ValueError),
+ (u' \t\t ', ValueError),
]
for s, v in L:
for sign in "", "+", "-":
@@ -349,10 +375,17 @@
if long(-3.9) <> -3L: raise TestFailed, 'long(-3.9)'
if long(3.5) <> 3L: raise TestFailed, 'long(3.5)'
if long(-3.5) <> -3L: raise TestFailed, 'long(-3.5)'
+if long("-3") <> -3L: raise TestFailed, 'long("-3")'
+if long(u"-3") <> -3L: raise TestFailed, 'long(u"-3")'
+# Different base:
+if long("10",16) <> 16L: raise TestFailed, 'long("10",16)'
+if long(u"10",16) <> 16L: raise TestFailed, 'long(u"10",16)'
# Check conversions from string (same test set as for int(), and then some)
LL = [
('1' + '0'*20, 10L**20),
('1' + '0'*100, 10L**100),
+ (u'1' + u'0'*20, 10L**20),
+ (u'1' + u'0'*100, 10L**100),
]
for s, v in L + LL:
for sign in "", "+", "-":
@@ -363,11 +396,11 @@
vv = -v
try:
if long(ss) != long(vv):
- raise TestFailed, "int(%s)" % `ss`
+ raise TestFailed, "long(%s)" % `ss`
except v:
pass
except ValueError, e:
- raise TestFailed, "int(%s) raised ValueError: %s" % (`ss`, e)
+ raise TestFailed, "long(%s) raised ValueError: %s" % (`ss`, e)
print 'map'
if map(None, 'hello world') <> ['h','e','l','l','o',' ','w','o','r','l','d']:
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index f90887a..5c0a063 100644
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -221,15 +221,23 @@
# Contains:
print 'Testing Unicode contains method...',
-assert ('a' in 'abdb') == 1
-assert ('a' in 'bdab') == 1
-assert ('a' in 'bdaba') == 1
-assert ('a' in 'bdba') == 1
+assert ('a' in u'abdb') == 1
+assert ('a' in u'bdab') == 1
+assert ('a' in u'bdaba') == 1
+assert ('a' in u'bdba') == 1
assert ('a' in u'bdba') == 1
assert (u'a' in u'bdba') == 1
assert (u'a' in u'bdb') == 0
assert (u'a' in 'bdb') == 0
assert (u'a' in 'bdba') == 1
+assert (u'a' in ('a',1,None)) == 1
+assert (u'a' in (1,None,'a')) == 1
+assert (u'a' in (1,None,u'a')) == 1
+assert ('a' in ('a',1,None)) == 1
+assert ('a' in (1,None,'a')) == 1
+assert ('a' in (1,None,u'a')) == 1
+assert ('a' in ('x',1,u'y')) == 0
+assert ('a' in ('x',1,None)) == 0
print 'done.'
# Formatting:
@@ -270,11 +278,88 @@
assert unicode(u.encode(encoding),encoding) == u
u = u''.join(map(unichr, range(256)))
-for encoding in ('latin-1',):
- assert unicode(u.encode(encoding),encoding) == u
+for encoding in (
+ 'latin-1',
+ ):
+ try:
+ assert unicode(u.encode(encoding),encoding) == u
+ except AssertionError:
+ print '*** codec "%s" failed round-trip' % encoding
+ except ValueError,why:
+ print '*** codec for "%s" failed: %s' % (encoding, why)
u = u''.join(map(unichr, range(128)))
-for encoding in ('ascii',):
- assert unicode(u.encode(encoding),encoding) == u
+for encoding in (
+ 'ascii',
+ ):
+ try:
+ assert unicode(u.encode(encoding),encoding) == u
+ except AssertionError:
+ print '*** codec "%s" failed round-trip' % encoding
+ except ValueError,why:
+ print '*** codec for "%s" failed: %s' % (encoding, why)
+
+print 'done.'
+
+print 'Testing standard mapping codecs...',
+
+print '0-127...',
+s = ''.join(map(chr, range(128)))
+for encoding in (
+ 'cp037', 'cp1026',
+ 'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
+ 'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
+ 'cp863', 'cp865', 'cp866',
+ 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
+ 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
+ 'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
+ 'mac_cyrillic', 'mac_latin2',
+
+ 'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
+ 'cp1256', 'cp1257', 'cp1258',
+ 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
+
+ 'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
+ 'cp1006', 'cp875', 'iso8859_8',
+
+ ### These have undefined mappings:
+ #'cp424',
+
+ ):
+ try:
+ assert unicode(s,encoding).encode(encoding) == s
+ except AssertionError:
+ print '*** codec "%s" failed round-trip' % encoding
+ except ValueError,why:
+ print '*** codec for "%s" failed: %s' % (encoding, why)
+
+print '128-255...',
+s = ''.join(map(chr, range(128,256)))
+for encoding in (
+ 'cp037', 'cp1026',
+ 'cp437', 'cp500', 'cp737', 'cp775', 'cp850',
+ 'cp852', 'cp855', 'cp860', 'cp861', 'cp862',
+ 'cp863', 'cp865', 'cp866',
+ 'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
+ 'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
+ 'iso8859_7', 'iso8859_9', 'koi8_r', 'latin_1',
+ 'mac_cyrillic', 'mac_latin2',
+
+ ### These have undefined mappings:
+ #'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
+ #'cp1256', 'cp1257', 'cp1258',
+ #'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
+ #'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
+
+ ### These fail the round-trip:
+ #'cp1006', 'cp875', 'iso8859_8',
+
+ ):
+ try:
+ assert unicode(s,encoding).encode(encoding) == s
+ except AssertionError:
+ print '*** codec "%s" failed round-trip' % encoding
+ except ValueError,why:
+ print '*** codec for "%s" failed: %s' % (encoding, why)
print 'done.'