Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

Revert r63934 -- it was mixing two patches.

This commit is contained in:
Georg Brandl 2008-06-04 13:01:30 +00:00
parent f954c4b9fb
commit a26f8ca668
37 changed files with 1028 additions and 1188 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
Doc/c-api/unicode.rst
View File

@ -144,13 +144,6 @@ the Python configuration.
Return 1 or 0 depending on whether *ch* is an alphanumeric character.
.. cfunction:: int Py_UNICODE_ISPRINTABLE(Py_UNICODE ch)
Return 1 or 0 depending on whether *ch* is a printable character.
Characters defined in the Unicode character database as "Other"
or "Separator" other than ASCII space(0x20) are not considered
printable.
These APIs can be used for fast direct character conversions:
@ -235,9 +228,6 @@ APIs:
+===================+=====================+================================+
| :attr:`%%` | *n/a* | The literal % character. |
+-------------------+---------------------+--------------------------------+
| :attr:`%a` | PyObject\* | The result of calling |
| | | :func:`ascii`. |
+-------------------+---------------------+--------------------------------+
| :attr:`%c` | int | A single character, |
| | | represented as an C int. |
+-------------------+---------------------+--------------------------------+

8
Doc/library/functions.rst
View File

@ -91,14 +91,6 @@ are always available. They are listed here in alphabetical order.
return False
.. function:: ascii(object)
As :func:`repr`, return a string containing a printable
representation of an object. But unlike :func:`repr`, the non-ASCII
characters in the string returned by :func:`ascii`() are hex-escaped
to generate a same string as :func:`repr` in Python 2.
.. function:: bin(x)
Convert an integer number to a binary string. The result is a valid Python

8
Doc/library/stdtypes.rst
View File

@ -774,14 +774,6 @@ functions based on regular expressions.
least one cased character, false otherwise.
.. method:: str.isprintable()
Return true if all characters in the string are printable and there is at
least one character, false otherwise. Characters defined in the Unicode
character database as "Other" or "Separator" other than ASCII space(0x20) are
not considered printable.
.. method:: str.isspace()
Return true if there are only whitespace characters in the string and there is

2
Doc/library/sys.rst
View File

@ -231,6 +231,8 @@ always available.
+------------------------------+------------------------------------------+
| :const:`ignore_environment` | -E |
+------------------------------+------------------------------------------+
| :const:`tabcheck` | -t or -tt |
+------------------------------+------------------------------------------+
| :const:`verbose` | -v |
+------------------------------+------------------------------------------+
| :const:`unicode` | -U |

7
Doc/using/cmdline.rst
View File

@ -222,6 +222,13 @@ Miscellaneous options
manipulations of :data:`sys.path` that it entails.
.. cmdoption:: -t
Issue a warning when a source file mixes tabs and spaces for indentation in a
way that makes it depend on the worth of a tab expressed in spaces. Issue an
error when the option is given twice (:option:`-tt`).
.. cmdoption:: -u
Force stdin, stdout and stderr to be totally unbuffered. On systems where it

1
Include/pydebug.h
View File

@ -14,6 +14,7 @@ PyAPI_DATA(int) Py_NoSiteFlag;
PyAPI_DATA(int) Py_BytesWarningFlag;
PyAPI_DATA(int) Py_UseClassExceptionsFlag;
PyAPI_DATA(int) Py_FrozenFlag;
PyAPI_DATA(int) Py_TabcheckFlag;
PyAPI_DATA(int) Py_IgnoreEnvironmentFlag;
PyAPI_DATA(int) Py_DivisionWarningFlag;
PyAPI_DATA(int) Py_DontWriteBytecodeFlag;

8
Include/unicodeobject.h
View File

@ -217,7 +217,6 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
# define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak
# define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase
# define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric
# define _PyUnicode_IsPrintable _PyUnicodeUCS2_IsPrintable
# define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase
# define _PyUnicode_IsXidStart _PyUnicodeUCS2_IsXidStart
# define _PyUnicode_IsXidContinue _PyUnicodeUCS2_IsXidContinue
@ -312,7 +311,6 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
# define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak
# define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase
# define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric
# define _PyUnicode_IsPrintable _PyUnicodeUCS4_IsPrintable
# define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase
# define _PyUnicode_IsXidStart _PyUnicodeUCS4_IsXidStart
# define _PyUnicode_IsXidContinue _PyUnicodeUCS4_IsXidContinue
@ -353,7 +351,6 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
@ -384,7 +381,6 @@ extern const unsigned char _Py_ascii_whitespace[];
#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
@ -1503,10 +1499,6 @@ PyAPI_FUNC(int) _PyUnicode_IsNumeric(
Py_UNICODE ch /* Unicode character */
);
PyAPI_FUNC(int) _PyUnicode_IsPrintable(
Py_UNICODE ch /* Unicode character */
);
PyAPI_FUNC(int) _PyUnicode_IsAlpha(
Py_UNICODE ch /* Unicode character */
);

16
Lib/doctest.py
View File

@ -1441,13 +1441,6 @@ class OutputChecker:
and returns true if they match; and `output_difference`, which
returns a string describing the differences between two outputs.
"""
def _toAscii(self, s):
"""
Convert string to hex-escaped ASCII string.
"""
return str(s.encode('ASCII', 'backslashreplace'), "ASCII")
def check_output(self, want, got, optionflags):
"""
Return True iff the actual output from an example (`got`)
@ -1458,15 +1451,6 @@ class OutputChecker:
documentation for `TestRunner` for more information about
option flags.
"""
# If `want` contains hex-escaped character such as "\u1234",
# then `want` is a string of six characters(e.g. [\,u,1,2,3,4]).
# On the other hand, `got` could be an another sequence of
# characters such as [\u1234], so `want` and `got` should
# be folded to hex-escaped ASCII string to compare.
got = self._toAscii(got)
want = self._toAscii(want)
# Handle the common case first, for efficiency:
# if they're string-identical, always return true.
if got == want:

2
Lib/test/test_array.py
View File

@ -768,7 +768,7 @@ class UnicodeTest(StringTest):
a = array.array('u', s)
self.assertEqual(
repr(a),
"array('u', '\\x00=\"\\'a\\\\b\\x80\xff\\x00\\x01\u1234')")
"array('u', '\\x00=\"\\'a\\\\b\\x80\\xff\\x00\\x01\\u1234')")
self.assertRaises(TypeError, a.fromunicode)

3
Lib/test/test_builtin.py
View File

@ -159,9 +159,6 @@ class BuiltinTest(unittest.TestCase):
S = [10, 20, 30]
self.assertEqual(any(x > 42 for x in S), False)
def test_ascii(self):
self.assertEqual(ascii("\u0370"), "'\\u0370'")
def test_neg(self):
x = -sys.maxsize-1
self.assert_(isinstance(x, int))

8
Lib/test/test_exceptions.py
View File

@ -80,10 +80,10 @@ class ExceptionTests(unittest.TestCase):
self.raise_catch(IndentationError, "IndentationError")
self.raise_catch(TabError, "TabError")
try: compile("try:\n\t1/0\n \t1/0\nfinally:\n pass\n",
'<string>', 'exec')
except TabError: pass
else: self.fail("TabError not raised")
# can only be tested under -tt, and is the only test for -tt
#try: compile("try:\n\t1/0\n \t1/0\nfinally:\n pass\n", '<string>', 'exec')
#except TabError: pass
#else: self.fail("TabError not raised")
self.raise_catch(SystemError, "SystemError")

6
Lib/test/test_format.py
View File

@ -216,8 +216,6 @@ class FormatTest(unittest.TestCase):
testformat("%o", 0o42, "42")
testformat("%o", -0o42, "-42")
testformat("%o", float(0o42), "42")
testformat("%r", "\u0370", "'\u0370'")
testformat("%a", "\u0370", "'\\u0370'")
# Test exception for unknown format characters
if verbose:
print('Testing exceptions')
@ -237,8 +235,8 @@ class FormatTest(unittest.TestCase):
raise
else:
raise TestFailed('did not get expected exception: %s' % excmsg)
test_exc('abc %b', 1, ValueError,
"unsupported format character 'b' (0x62) at index 5")
test_exc('abc %a', 1, ValueError,
"unsupported format character 'a' (0x61) at index 5")
#test_exc(unicode('abc %\u3000','raw-unicode-escape'), 1, ValueError,
# "unsupported format character '?' (0x3000) at index 5")
test_exc('%d', '1', TypeError, "%d format: a number is required, not str")

2
Lib/test/test_pyexpat.py
View File

@ -131,7 +131,7 @@ class ParseTest(unittest.TestCase):
self.assertEquals(op[1], "Comment: ' comment data '")
self.assertEquals(op[2], "Notation declared: ('notation', None, 'notation.jpeg', None)")
self.assertEquals(op[3], "Unparsed entity decl: ('unparsed_entity', None, 'entity.file', None, 'notation')")
self.assertEquals(op[4], "Start element: 'root' {'attr1': 'value1', 'attr2': 'value2\u1f40'}")
self.assertEquals(op[4], "Start element: 'root' {'attr1': 'value1', 'attr2': 'value2\\u1f40'}")
self.assertEquals(op[5], "NS decl: 'myns' 'http://www.python.org/namespace'")
self.assertEquals(op[6], "Start element: 'http://www.python.org/namespace!subelement' {}")
self.assertEquals(op[7], "Character data: 'Contents of subelements'")

22
Lib/test/test_unicode.py
View File

@ -94,14 +94,14 @@ class UnicodeTest(
"JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
"\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
"\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
"\\x9c\\x9d\\x9e\\x9f\\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9"
"\xaa\xab\xac\\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
"\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5"
"\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3"
"\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1"
"\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd"
"\xfe\xff'")
"\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
"\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
"\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
"\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
"\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
"\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
"\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
"\\xfe\\xff'")
testrepr = repr(''.join(map(chr, range(256))))
self.assertEqual(testrepr, latin1repr)
# Test repr works on wide unicode escapes without overflow.
@ -374,12 +374,6 @@ class UnicodeTest(
self.assertFalse("[".isidentifier())
self.assertFalse("©".isidentifier())
def test_isprintable(self):
self.assertTrue("abcdefg".isprintable())
self.assertFalse("abcdefg\n".isprintable())
self.assertTrue("\u0370".isprintable())
self.assertFalse("\ud800".isprintable())
def test_contains(self):
# Testing Unicode contains method
self.assert_('a' in 'abdb')

8
Mac/BuildScript/scripts/postflight.framework
View File

@ -6,22 +6,22 @@
PYVER="@PYVER@"
FWK="/Library/Frameworks/Python.framework/Versions/@PYVER@"
"${FWK}/bin/python" -Wi \
"${FWK}/bin/python" -Wi -tt \
"${FWK}/lib/python${PYVER}/compileall.py" \
-x badsyntax -x site-packages \
"${FWK}/lib/python${PYVER}"
"${FWK}/bin/python" -Wi -O \
"${FWK}/bin/python" -Wi -tt -O \
"${FWK}/lib/python${PYVER}/compileall.py" \
-x badsyntax -x site-packages \
"${FWK}/lib/python${PYVER}"
"${FWK}/bin/python" -Wi \
"${FWK}/bin/python" -Wi -tt \
"${FWK}/lib/python${PYVER}/compileall.py" \
-x badsyntax -x site-packages \
"${FWK}/Mac/Tools"
"${FWK}/bin/python" -Wi -O \
"${FWK}/bin/python" -Wi -tt -O \
"${FWK}/lib/python${PYVER}/compileall.py" \
-x badsyntax -x site-packages \
"${FWK}/Mac/Tools"

4
Mac/Makefile.in
View File

@ -226,8 +226,8 @@ installmacsubtree:
$(RUNSHARED) $(BUILDPYTHON) $(CACHERSRC) -v $(DESTDIR)$(MACLIBDEST) $(DESTDIR)$(MACTOOLSDEST)
$(RUNSHARED) $(BUILDPYTHON) -Wi $(compileall) -d $(MACTOOLSDEST) -x badsyntax $(DESTDIR)$(MACTOOLSDEST)
$(RUNSHARED) $(BUILDPYTHON) -O -Wi $(compileall) -d $(MACTOOLSDEST) -x badsyntax $(DESTDIR)$(MACTOOLSDEST)
$(RUNSHARED) $(BUILDPYTHON) -Wi -tt $(compileall) -d $(MACTOOLSDEST) -x badsyntax $(DESTDIR)$(MACTOOLSDEST)
$(RUNSHARED) $(BUILDPYTHON) -O -Wi -tt $(compileall) -d $(MACTOOLSDEST) -x badsyntax $(DESTDIR)$(MACTOOLSDEST)
$(INSTALLED_PYTHONAPP): install_Python

14
Makefile.pre.in
View File

@ -664,7 +664,7 @@ $(LIBRARY_OBJS) $(MODOBJS) Modules/python.o: $(PYTHON_HEADERS)
TESTOPTS= -l $(EXTRATESTOPTS)
TESTPROG= $(srcdir)/Lib/test/regrtest.py
TESTPYTHON= $(RUNSHARED) ./$(BUILDPYTHON) -E -bb
TESTPYTHON= $(RUNSHARED) ./$(BUILDPYTHON) -E -tt -bb
test: all platform
-find $(srcdir)/Lib -name '*.py[co]' -print | xargs rm -f
-$(TESTPYTHON) $(TESTPROG) $(TESTOPTS)
@ -687,7 +687,7 @@ testuniversal: all platform
-find $(srcdir)/Lib -name '*.py[co]' -print | xargs rm -f
-$(TESTPYTHON) $(TESTPROG) $(TESTOPTS) -uall
$(TESTPYTHON) $(TESTPROG) $(TESTOPTS) -uall
$(RUNSHARED) /usr/libexec/oah/translate ./$(BUILDPYTHON) -E $(TESTPROG) $(TESTOPTS) -uall
$(RUNSHARED) /usr/libexec/oah/translate ./$(BUILDPYTHON) -E -tt $(TESTPROG) $(TESTOPTS) -uall
# Like testall, but with a single pass only
@ -872,23 +872,23 @@ libinstall: build_all $(srcdir)/Lib/$(PLATDIR)
done
$(INSTALL_DATA) $(srcdir)/LICENSE $(DESTDIR)$(LIBDEST)/LICENSE.txt
-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
./$(BUILDPYTHON) -Wi $(DESTDIR)$(LIBDEST)/compileall.py \
./$(BUILDPYTHON) -Wi -tt $(DESTDIR)$(LIBDEST)/compileall.py \
-d $(LIBDEST) -f \
-x 'bad_coding|badsyntax|site-packages' $(DESTDIR)$(LIBDEST)
-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
./$(BUILDPYTHON) -Wi -O $(DESTDIR)$(LIBDEST)/compileall.py \
./$(BUILDPYTHON) -Wi -tt -O $(DESTDIR)$(LIBDEST)/compileall.py \
-d $(LIBDEST) -f \
-x 'bad_coding|badsyntax|site-packages' $(DESTDIR)$(LIBDEST)
-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
./$(BUILDPYTHON) -Wi $(DESTDIR)$(LIBDEST)/compileall.py \
./$(BUILDPYTHON) -Wi -t $(DESTDIR)$(LIBDEST)/compileall.py \
-d $(LIBDEST)/site-packages -f \
-x badsyntax $(DESTDIR)$(LIBDEST)/site-packages
-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
./$(BUILDPYTHON) -Wi -O $(DESTDIR)$(LIBDEST)/compileall.py \
./$(BUILDPYTHON) -Wi -t -O $(DESTDIR)$(LIBDEST)/compileall.py \
-d $(LIBDEST)/site-packages -f \
-x badsyntax $(DESTDIR)$(LIBDEST)/site-packages
-PYTHONPATH=$(DESTDIR)$(LIBDEST) $(RUNSHARED) \
./$(BUILDPYTHON) -Wi -c "import lib2to3.pygram"
./$(BUILDPYTHON) -Wi -t -c "import lib2to3.pygram"
# Create the PLATDIR source directory, if one wasn't distributed..
$(srcdir)/Lib/$(PLATDIR):

2
Misc/NEWS
View File

@ -12,8 +12,6 @@ What's new in Python 3.0b1?
Core and Builtins
-----------------
- Removed the already-defunct ``-t`` option.
- Issue #2957: Corrected a ValueError "recursion limit exceeded", when
unmarshalling many code objects, which happens when importing a
large .pyc file (~1000 functions).

2
Misc/build.sh
View File

@ -59,7 +59,7 @@ RSYNC_OPTS="-aC -e ssh"
PYTHON=$INSTALL_DIR/bin/python
# Python options and regression test program that should always be run.
REGRTEST_ARGS="-E $INSTALL_DIR/lib/python3.0/test/regrtest.py"
REGRTEST_ARGS="-E -tt $INSTALL_DIR/lib/python3.0/test/regrtest.py"
REFLOG="build/reflog.txt.out"
# These tests are not stable and falsely report leaks sometimes.

1
Misc/cheatsheet
View File

@ -46,6 +46,7 @@ Option Effect
-OO remove doc-strings in addition to the -O optimizations
-Q arg division options: -Qold (default), -Qwarn, -Qwarnall, -Qnew
-S Don't perform 'import site' on initialization
-t Issue warnings about inconsistent tab usage (-tt: issue errors)
-u Unbuffered binary stdout and stderr (also PYTHONUNBUFFERED=x).
-v Verbose (trace import statements) (also PYTHONVERBOSE=x)
-W arg : warning control (arg is action:message:category:module:lineno)

8
Misc/python.man
View File

@ -35,6 +35,9 @@ python \- an interpreted, interactive, object-oriented programming language
.B \-S
]
[
.B \-t
]
[
.B \-u
]
.br
@ -141,6 +144,11 @@ and the site-dependent manipulations of
.I sys.path
that it entails.
.TP
.B \-t
Issue a warning when a source file mixes tabs and spaces for
indentation in a way that makes it depend on the worth of a tab
expressed in spaces. Issue an error when the option is given twice.
.TP
.B \-u
Force stdin, stdout and stderr to be totally unbuffered. On systems
where it matters, also put stdin, stdout and stderr in binary mode.

2
Misc/valgrind-python.supp
View File

@ -5,7 +5,7 @@
#
# cd python/dist/src
# valgrind --tool=memcheck --suppressions=Misc/valgrind-python.supp \
# ./python -E ./Lib/test/regrtest.py -u bsddb,network
# ./python -E -tt ./Lib/test/regrtest.py -u bsddb,network
#
# You must edit Objects/obmalloc.c and uncomment Py_USING_MEMORY_DEBUGGER
# to use the preferred suppressions with Py_ADDRESS_IN_RANGE.

3
Modules/main.c
View File

@ -72,6 +72,7 @@ static char *usage_2 = "\
-OO : remove doc-strings in addition to the -O optimizations\n\
-s : don't add user site directory to sys.path; also PYTHONNOUSERSITE\n\
-S : don't imply 'import site' on initialization\n\
-t : issue warnings about inconsistent tab usage (-tt: issue errors)\n\
";
static char *usage_3 = "\
-u : unbuffered binary stdout and stderr; also PYTHONUNBUFFERED=x\n\
@ -369,7 +370,7 @@ Py_Main(int argc, wchar_t **argv)
break;
case 't':
/* ignored for backwards compatibility */
Py_TabcheckFlag++;
break;
case 'u':

21
Objects/unicodectype.c
View File

@ -21,7 +21,6 @@
#define UPPER_MASK 0x80
#define XID_START_MASK 0x100
#define XID_CONTINUE_MASK 0x200
#define NONPRINTABLE_MASK 0x400
typedef struct {
const Py_UNICODE upper;
@ -676,26 +675,6 @@ int _PyUnicode_IsNumeric(Py_UNICODE ch)
return _PyUnicode_ToNumeric(ch) != -1.0;
}
/* Returns 1 for Unicode characters to be hex-escaped when repr()ed,
0 otherwise.
Characters defined in the Unicode character database as following
categories are not considered printable.
* Cc (Other, Control)
* Cf (Other, Format)
* Cs (Other, Surrogate)
* Co (Other, Private Use)
* Cn (Other, Not Assigned)
* Zl Separator, Line ('\u2028', LINE SEPARATOR)
* Zp Separator, Paragraph ('\u2029', PARAGRAPH SEPARATOR)
* Zs (Separator, Space) other than ASCII space('\x20').
*/
int _PyUnicode_IsPrintable(Py_UNICODE ch)
{
const _PyUnicode_TypeRecord *ctype = gettyperecord(ch);
return (ctype->flags & NONPRINTABLE_MASK) == 0;
}
#ifndef WANT_WCTYPE_FUNCTIONS
/* Returns 1 for Unicode characters having the bidirectional type

176
Objects/unicodeobject.c
View File

@ -7149,36 +7149,6 @@ unicode_isidentifier(PyObject *self)
return PyBool_FromLong(PyUnicode_IsIdentifier(self));
}
PyDoc_STRVAR(isprintable__doc__,
"S.isprintable() -> bool\n\
\n\
Return True if all characters in S are considered\n\
printable in repr() and there is at least one character\n\
in S, False otherwise.");
static PyObject*
unicode_isprintable(PyObject *self)
{
register const Py_UNICODE *p = PyUnicode_AS_UNICODE(self);
register const Py_UNICODE *e;
/* Shortcut for single character strings */
if (PyUnicode_GET_SIZE(self) == 1 &&
Py_UNICODE_ISPRINTABLE(*p))
return PyBool_FromLong(1);
/* Special case for empty strings */
if (PyUnicode_GET_SIZE(self) == 0)
return PyBool_FromLong(0);
e = p + PyUnicode_GET_SIZE(self);
for (; p < e; p++) {
if (!Py_UNICODE_ISPRINTABLE(*p))
return PyBool_FromLong(0);
}
return PyBool_FromLong(1);
}
PyDoc_STRVAR(join__doc__,
"S.join(sequence) -> str\n\
\n\
@ -7556,8 +7526,61 @@ PyObject *unicode_repr(PyObject *unicode)
continue;
}
/* Map special whitespace to '\t', \n', '\r' */
if (ch == '\t') {
#ifdef Py_UNICODE_WIDE
/* Map 21-bit characters to '\U00xxxxxx' */
else if (ch >= 0x10000) {
*p++ = '\\';
*p++ = 'U';
*p++ = hexdigits[(ch >> 28) & 0x0000000F];
*p++ = hexdigits[(ch >> 24) & 0x0000000F];
*p++ = hexdigits[(ch >> 20) & 0x0000000F];
*p++ = hexdigits[(ch >> 16) & 0x0000000F];
*p++ = hexdigits[(ch >> 12) & 0x0000000F];
*p++ = hexdigits[(ch >> 8) & 0x0000000F];
*p++ = hexdigits[(ch >> 4) & 0x0000000F];
*p++ = hexdigits[ch & 0x0000000F];
continue;
}
#else
/* Map UTF-16 surrogate pairs to '\U00xxxxxx' */
else if (ch >= 0xD800 && ch < 0xDC00) {
Py_UNICODE ch2;
Py_UCS4 ucs;
ch2 = *s++;
size--;
if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
*p++ = '\\';
*p++ = 'U';
*p++ = hexdigits[(ucs >> 28) & 0x0000000F];
*p++ = hexdigits[(ucs >> 24) & 0x0000000F];
*p++ = hexdigits[(ucs >> 20) & 0x0000000F];
*p++ = hexdigits[(ucs >> 16) & 0x0000000F];
*p++ = hexdigits[(ucs >> 12) & 0x0000000F];
*p++ = hexdigits[(ucs >> 8) & 0x0000000F];
*p++ = hexdigits[(ucs >> 4) & 0x0000000F];
*p++ = hexdigits[ucs & 0x0000000F];
continue;
}
/* Fall through: isolated surrogates are copied as-is */
s--;
size++;
}
#endif
/* Map 16-bit characters to '\uxxxx' */
if (ch >= 256) {
*p++ = '\\';
*p++ = 'u';
*p++ = hexdigits[(ch >> 12) & 0x000F];
*p++ = hexdigits[(ch >> 8) & 0x000F];
*p++ = hexdigits[(ch >> 4) & 0x000F];
*p++ = hexdigits[ch & 0x000F];
}
/* Map special whitespace to '\t', \n', '\r' */
else if (ch == '\t') {
*p++ = '\\';
*p++ = 't';
}
@ -7571,79 +7594,16 @@ PyObject *unicode_repr(PyObject *unicode)
}
/* Map non-printable US ASCII to '\xhh' */
else if (ch < ' ' || ch == 0x7F) {
else if (ch < ' ' || ch >= 0x7F) {
*p++ = '\\';
*p++ = 'x';
*p++ = hexdigits[(ch >> 4) & 0x000F];
*p++ = hexdigits[ch & 0x000F];
}
/* Copy ASCII characters as-is */
else if (ch < 0x7F) {
*p++ = ch;
}
/* Non-ASCII characters */
else {
Py_UCS4 ucs = ch;
#ifndef Py_UNICODE_WIDE
Py_UNICODE ch2 = 0;
/* Get code point from surrogate pair */
if (size > 0) {
ch2 = *s;
if (ch >= 0xD800 && ch < 0xDC00 && ch2 >= 0xDC00
&& ch2 <= 0xDFFF) {
ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF))
+ 0x00010000;
s++;
size--;
}
}
#endif
/* Map Unicode whitespace and control characters
(categories Z* and C* except ASCII space)
*/
if (!Py_UNICODE_ISPRINTABLE(ucs)) {
/* Map 8-bit characters to '\xhh' */
if (ucs <= 0xff) {
*p++ = '\\';
*p++ = 'x';
*p++ = hexdigits[(ch >> 4) & 0x000F];
*p++ = hexdigits[ch & 0x000F];
}
/* Map 21-bit characters to '\U00xxxxxx' */
else if (ucs >= 0x10000) {
*p++ = '\\';
*p++ = 'U';
*p++ = hexdigits[(ucs >> 28) & 0x0000000F];
*p++ = hexdigits[(ucs >> 24) & 0x0000000F];
*p++ = hexdigits[(ucs >> 20) & 0x0000000F];
*p++ = hexdigits[(ucs >> 16) & 0x0000000F];
*p++ = hexdigits[(ucs >> 12) & 0x0000000F];
*p++ = hexdigits[(ucs >> 8) & 0x0000000F];
*p++ = hexdigits[(ucs >> 4) & 0x0000000F];
*p++ = hexdigits[ucs & 0x0000000F];
}
/* Map 16-bit characters to '\uxxxx' */
else {
*p++ = '\\';
*p++ = 'u';
*p++ = hexdigits[(ucs >> 12) & 0x000F];
*p++ = hexdigits[(ucs >> 8) & 0x000F];
*p++ = hexdigits[(ucs >> 4) & 0x000F];
*p++ = hexdigits[ucs & 0x000F];
}
}
/* Copy characters as-is */
else {
*p++ = ch;
#ifndef Py_UNICODE_WIDE
if (ucs >= 0x10000)
*p++ = ch2;
#endif
}
}
/* Copy everything else as-is */
else
*p++ = (char) ch;
}
/* Add quote */
*p++ = PyUnicode_AS_UNICODE(repr)[0];
@ -8308,7 +8268,6 @@ static PyMethodDef unicode_methods[] = {
{"isalpha", (PyCFunction) unicode_isalpha, METH_NOARGS, isalpha__doc__},
{"isalnum", (PyCFunction) unicode_isalnum, METH_NOARGS, isalnum__doc__},
{"isidentifier", (PyCFunction) unicode_isidentifier, METH_NOARGS, isidentifier__doc__},
{"isprintable", (PyCFunction) unicode_isprintable, METH_NOARGS, isprintable__doc__},
{"zfill", (PyCFunction) unicode_zfill, METH_VARARGS, zfill__doc__},
{"format", (PyCFunction) do_string_format, METH_VARARGS | METH_KEYWORDS, format__doc__},
{"__format__", (PyCFunction) unicode__format__, METH_VARARGS, p_format__doc__},
@ -8894,7 +8853,6 @@ PyObject *PyUnicode_Format(PyObject *format,
case 's':
case 'r':
case 'a':
if (PyUnicode_Check(v) && c == 's') {
temp = v;
Py_INCREF(temp);
@ -8914,22 +8872,6 @@ PyObject *PyUnicode_Format(PyObject *format,
"%s argument has non-string str()");
goto onError;
}
if (c == 'a') {
PyObject *ascii = PyUnicode_EncodeASCII(
PyUnicode_AS_UNICODE(temp),
PyUnicode_GET_SIZE(temp),
"backslashreplace");
Py_DECREF(temp);
if (ascii == NULL)
goto onError;
temp = PyUnicode_FromEncodedObject(ascii,
"ASCII", NULL);
Py_DECREF(ascii);
if (temp == NULL)
goto onError;
}
}
pbuf = PyUnicode_AS_UNICODE(temp);
len = PyUnicode_GET_SIZE(temp);

1798
Objects/unicodetype_db.h
View File

File diff suppressed because it is too large Load Diff

4
PC/VC6/rt.bat
View File

@ -31,11 +31,11 @@
@if "%_qmode%"=="yes" goto Qmode
@echo Deleting .pyc/.pyo files ...
@%_exe% rmpyc.py
%_exe% %_dashO% -E ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
%_exe% %_dashO% -E -tt ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
@echo About to run again without deleting .pyc/.pyo first:
@pause
:Qmode
%_exe% %_dashO% -E ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
%_exe% %_dashO% -E -tt ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
@set _exe=
@set _qmode=
@set _dashO=

2
PC/VS7.1/rt.bat
View File

@ -34,7 +34,7 @@ if "%1"=="-O" (set dashO=-O) & shift & goto CheckOpts
if "%1"=="-q" (set qmode=yes) & shift & goto CheckOpts
if "%1"=="-d" (set exe=python_d) & shift & goto CheckOpts
set cmd=%exe% %dashO% -E ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
set cmd=%exe% %dashO% -E -tt ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
if defined qmode goto Qmode
echo Deleting .pyc/.pyo files ...

2
PC/VS8.0/rt.bat
View File

@ -34,7 +34,7 @@ if "%1"=="-O" (set dashO=-O) & shift & goto CheckOpts
if "%1"=="-q" (set qmode=yes) & shift & goto CheckOpts
if "%1"=="-d" (set exe=python_d) & shift & goto CheckOpts
set cmd=%exe% %dashO% -E ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
set cmd=%exe% %dashO% -E -tt ../../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
if defined qmode goto Qmode
echo Deleting .pyc/.pyo files ...

4
PC/os2emx/Makefile
View File

@ -666,7 +666,7 @@ _ssl$(MODULE.EXT): $(OUT)_ssl$O $(OUT)_ssl_m.def $(PYTHON.IMPLIB)
# the test target
test:
-find ../../Lib -name "*.py[co]" -exec rm {} ";"
-./python -E ../../lib/test/regrtest.py -l -u "network"
./python -E ../../lib/test/regrtest.py -l -u "network"
-./python -E -tt ../../lib/test/regrtest.py -l -u "network"
./python -E -tt ../../lib/test/regrtest.py -l -u "network"
-include $(OUTBASE)python.dep

1
PC/os2emx/python26.def
View File

@ -49,6 +49,7 @@ EXPORTS
"PyParser_Delete"
; From python26_s.lib(parsetok)
"Py_TabcheckFlag"
"PyParser_ParseString"
"PyParser_ParseStringFlagsFilename"
"PyParser_ParseFile"

1
PC/os2vacpp/python.def
View File

@ -61,6 +61,7 @@ EXPORTS
Py_InteractiveFlag
Py_NoSiteFlag
Py_OptimizeFlag
Py_TabcheckFlag
Py_UseClassExceptionsFlag
Py_VerboseFlag
_PyImport_Filetab

2
PCbuild/rt.bat
View File

@ -40,7 +40,7 @@ if "%1"=="-x64" (set prefix=amd64) & (set tcltk=tcltk64) & shift & goto CheckOpt
PATH %PATH%;..\..\%tcltk%\bin
set exe=%prefix%\python%suffix%
set cmd=%exe% %dashO% -E ../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
set cmd=%exe% %dashO% -E -tt ../lib/test/regrtest.py %1 %2 %3 %4 %5 %6 %7 %8 %9
if defined qmode goto Qmode
echo Deleting .pyc/.pyo files ...

8
Parser/parsetok.c
View File

@ -10,6 +10,8 @@
#include "errcode.h"
#include "graminit.h"
int Py_TabcheckFlag;
/* Forward */
static node *parsetok(struct tok_state *, grammar *, int, perrdetail *, int *);
@ -55,6 +57,9 @@ PyParser_ParseStringFlagsFilenameEx(const char *s, const char *filename,
}
tok->filename = filename ? filename : "<string>";
if (Py_TabcheckFlag >= 3)
tok->alterror = 0;
return parsetok(tok, g, start, err_ret, flags);
}
@ -92,6 +97,9 @@ PyParser_ParseFileFlagsEx(FILE *fp, const char *filename,
return NULL;
}
tok->filename = filename;
if (Py_TabcheckFlag >= 3)
tok->alterror = 0;
return parsetok(tok, g, start, err_ret, flags);
}

33
Python/bltinmodule.c
View File

@ -265,38 +265,6 @@ PyDoc_STRVAR(any_doc,
\n\
Return True if bool(x) is True for any x in the iterable.");
static PyObject *
builtin_ascii(PyObject *self, PyObject *v)
{
PyObject *repr, *bytes, *ascii;
repr = PyObject_Repr(v);
if (!repr)
return NULL;
bytes = PyUnicode_EncodeASCII(
PyUnicode_AS_UNICODE(repr),
PyUnicode_GET_SIZE(repr),
"backslashreplace");
Py_DECREF(repr);
if (bytes == NULL)
return NULL;
ascii = PyUnicode_FromEncodedObject(bytes,
"ASCII", NULL);
Py_DECREF(bytes);
if (ascii == NULL)
return NULL;
return ascii;
}
PyDoc_STRVAR(ascii_doc,
"ascii(object) -> string\n\
\n\
Return the canonical string representation of the object as repr(),\n\
but non-ASCII characters in the string are hex-escaped");
static PyObject *
builtin_bin(PyObject *self, PyObject *v)
@ -2220,7 +2188,6 @@ static PyMethodDef builtin_methods[] = {
{"abs", builtin_abs, METH_O, abs_doc},
{"all", builtin_all, METH_O, all_doc},
{"any", builtin_any, METH_O, any_doc},
{"ascii", builtin_ascii, METH_O, ascii_doc},
{"bin", builtin_bin, METH_O, bin_doc},
{"chr", builtin_chr, METH_VARARGS, chr_doc},
{"cmp", builtin_cmp, METH_VARARGS, cmp_doc},

6
Python/sysmodule.c
View File

@ -1100,6 +1100,7 @@ static PyStructSequence_Field flags_fields[] = {
{"no_user_site", "-s"},
{"no_site", "-S"},
{"ignore_environment", "-E"},
{"tabcheck", "-t or -tt"},
{"verbose", "-v"},
#ifdef RISCOS
{"riscos_wimp", "???"},
@ -1115,9 +1116,9 @@ static PyStructSequence_Desc flags_desc = {
flags__doc__, /* doc */
flags_fields, /* fields */
#ifdef RISCOS
11
12
#else
10
11
#endif
};
@ -1143,6 +1144,7 @@ make_flags(void)
SetFlag(Py_NoUserSiteDirectory);
SetFlag(Py_NoSiteFlag);
SetFlag(Py_IgnoreEnvironmentFlag);
SetFlag(Py_TabcheckFlag);
SetFlag(Py_VerboseFlag);
#ifdef RISCOS
SetFlag(Py_RISCOSWimpFlag);

11
Tools/unicode/makeunicodedata.py
View File

@ -60,7 +60,6 @@ TITLE_MASK = 0x40
UPPER_MASK = 0x80
XID_START_MASK = 0x100
XID_CONTINUE_MASK = 0x200
NONPRINTABLE_MASK = 0x400
def maketables(trace=0):
@ -72,7 +71,7 @@ def maketables(trace=0):
EASTASIAN_WIDTH % version,
DERIVED_CORE_PROPERTIES % version)
print(len(list(filter(None, unicode.table))), "characters")
print(len(filter(None, unicode.table)), "characters")
for version in old_versions:
print("--- Reading", UNICODE_DATA % ("-"+version), "...")
@ -80,7 +79,7 @@ def maketables(trace=0):
COMPOSITION_EXCLUSIONS % ("-"+version),
EASTASIAN_WIDTH % ("-"+version),
DERIVED_CORE_PROPERTIES % ("-"+version))
print(len(list(filter(None, old_unicode.table))), "characters")
print(len(filter(None, old_unicode.table)), "characters")
merge_old_version(version, unicode, old_unicode)
makeunicodename(unicode, trace)
@ -372,10 +371,6 @@ def makeunicodetype(unicode, trace):
flags |= TITLE_MASK
if category == "Lu":
flags |= UPPER_MASK
if category[0] == "C":
flags |= NONPRINTABLE_MASK
if category[0] == "Z" and char != " ":
flags |= NONPRINTABLE_MASK
if "XID_Start" in properties:
flags |= XID_START_MASK
if "XID_Continue" in properties:
@ -470,7 +465,7 @@ def makeunicodename(unicode, trace):
if name and name[0] != "<":
names[char] = name + chr(0)
print(len(list(n for n in names if n is not None)), "distinct names")
print(len(n for n in names if n is not None), "distinct names")
# collect unique words from names (note that we differ between
# words inside a sentence, and words ending a sentence. the