2007-04-17 05:48:32 -03:00
|
|
|
"""A collection of string constants.
|
1997-12-29 15:26:28 -04:00
|
|
|
|
|
|
|
Public module variables:
|
|
|
|
|
2008-11-22 04:31:09 -04:00
|
|
|
whitespace -- a string containing all ASCII whitespace
|
|
|
|
ascii_lowercase -- a string containing all ASCII lowercase letters
|
|
|
|
ascii_uppercase -- a string containing all ASCII uppercase letters
|
|
|
|
ascii_letters -- a string containing all ASCII letters
|
|
|
|
digits -- a string containing all ASCII decimal digits
|
|
|
|
hexdigits -- a string containing all ASCII hexadecimal digits
|
|
|
|
octdigits -- a string containing all ASCII octal digits
|
|
|
|
punctuation -- a string containing all ASCII punctuation characters
|
|
|
|
printable -- a string containing all ASCII characters considered printable
|
1997-12-29 15:26:28 -04:00
|
|
|
|
|
|
|
"""
|
|
|
|
|
2010-10-14 04:04:07 -03:00
|
|
|
import _string
|
|
|
|
|
1990-10-13 16:23:40 -03:00
|
|
|
# Some strings for ctype-style character classification
|
1993-07-29 06:37:38 -03:00
|
|
|
whitespace = ' \t\n\r\v\f'
|
2007-08-14 06:23:10 -03:00
|
|
|
ascii_lowercase = 'abcdefghijklmnopqrstuvwxyz'
|
|
|
|
ascii_uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
|
2001-07-20 15:38:26 -03:00
|
|
|
ascii_letters = ascii_lowercase + ascii_uppercase
|
1990-10-13 16:23:40 -03:00
|
|
|
digits = '0123456789'
|
|
|
|
hexdigits = digits + 'abcdef' + 'ABCDEF'
|
|
|
|
octdigits = '01234567'
|
2001-01-14 21:36:40 -04:00
|
|
|
punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
|
2007-08-14 06:23:10 -03:00
|
|
|
printable = digits + ascii_letters + punctuation + whitespace
|
1990-10-13 16:23:40 -03:00
|
|
|
|
2004-08-24 23:22:30 -03:00
|
|
|
# Functions which aren't available as string methods.
|
|
|
|
|
|
|
|
# Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def".
|
|
|
|
def capwords(s, sep=None):
|
2009-09-26 09:33:22 -03:00
|
|
|
"""capwords(s [,sep]) -> string
|
2004-08-24 23:22:30 -03:00
|
|
|
|
|
|
|
Split the argument into words using split, capitalize each
|
|
|
|
word using capitalize, and join the capitalized words using
|
2009-09-26 09:33:22 -03:00
|
|
|
join. If the optional second argument sep is absent or None,
|
|
|
|
runs of whitespace characters are replaced by a single space
|
|
|
|
and leading and trailing whitespace are removed, otherwise
|
|
|
|
sep is used to split and join the words.
|
2004-08-24 23:22:30 -03:00
|
|
|
|
|
|
|
"""
|
2009-09-26 09:33:22 -03:00
|
|
|
return (sep or ' ').join(x.capitalize() for x in s.split(sep))
|
2004-08-24 23:22:30 -03:00
|
|
|
|
|
|
|
|
2004-08-25 21:21:13 -03:00
|
|
|
####################################################################
|
2004-08-24 23:22:30 -03:00
|
|
|
import re as _re
|
2011-02-25 21:02:51 -04:00
|
|
|
from collections import ChainMap
|
2004-09-13 11:35:04 -03:00
|
|
|
|
2004-09-10 00:08:08 -03:00
|
|
|
class _TemplateMetaclass(type):
|
|
|
|
pattern = r"""
|
2004-09-26 15:56:44 -03:00
|
|
|
%(delim)s(?:
|
|
|
|
(?P<escaped>%(delim)s) | # Escape sequence of two delimiters
|
|
|
|
(?P<named>%(id)s) | # delimiter and a Python identifier
|
|
|
|
{(?P<braced>%(id)s)} | # delimiter and a braced identifier
|
|
|
|
(?P<invalid>) # Other ill-formed delimiter exprs
|
|
|
|
)
|
2004-09-10 00:08:08 -03:00
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(cls, name, bases, dct):
|
|
|
|
super(_TemplateMetaclass, cls).__init__(name, bases, dct)
|
|
|
|
if 'pattern' in dct:
|
|
|
|
pattern = cls.pattern
|
|
|
|
else:
|
|
|
|
pattern = _TemplateMetaclass.pattern % {
|
2004-09-17 21:06:34 -03:00
|
|
|
'delim' : _re.escape(cls.delimiter),
|
2004-09-10 00:08:08 -03:00
|
|
|
'id' : cls.idpattern,
|
|
|
|
}
|
2010-07-29 14:16:10 -03:00
|
|
|
cls.pattern = _re.compile(pattern, cls.flags | _re.VERBOSE)
|
2004-09-10 00:08:08 -03:00
|
|
|
|
|
|
|
|
2007-03-18 12:41:51 -03:00
|
|
|
class Template(metaclass=_TemplateMetaclass):
|
2004-08-24 23:22:30 -03:00
|
|
|
"""A string class for supporting $-substitutions."""
|
2004-09-10 00:08:08 -03:00
|
|
|
|
2004-09-17 21:06:34 -03:00
|
|
|
delimiter = '$'
|
2004-09-10 00:08:08 -03:00
|
|
|
idpattern = r'[_a-z][_a-z0-9]*'
|
2010-07-29 14:16:10 -03:00
|
|
|
flags = _re.IGNORECASE
|
2004-09-10 00:08:08 -03:00
|
|
|
|
|
|
|
def __init__(self, template):
|
|
|
|
self.template = template
|
2004-08-24 23:22:30 -03:00
|
|
|
|
|
|
|
# Search for $$, $identifier, ${identifier}, and any bare $'s
|
2004-09-10 00:08:08 -03:00
|
|
|
|
2004-09-13 17:52:50 -03:00
|
|
|
def _invalid(self, mo):
|
|
|
|
i = mo.start('invalid')
|
2011-09-28 11:37:55 -03:00
|
|
|
lines = self.template[:i].splitlines(keepends=True)
|
2004-09-10 00:08:08 -03:00
|
|
|
if not lines:
|
|
|
|
colno = 1
|
|
|
|
lineno = 1
|
|
|
|
else:
|
|
|
|
colno = i - len(''.join(lines[:-1]))
|
|
|
|
lineno = len(lines)
|
|
|
|
raise ValueError('Invalid placeholder in string: line %d, col %d' %
|
|
|
|
(lineno, colno))
|
|
|
|
|
2015-03-24 17:28:43 -03:00
|
|
|
def substitute(*args, **kws):
|
|
|
|
if not args:
|
|
|
|
raise TypeError("descriptor 'substitute' of 'Template' object "
|
|
|
|
"needs an argument")
|
|
|
|
self, *args = args # allow the "self" keyword be passed
|
2004-09-13 12:25:15 -03:00
|
|
|
if len(args) > 1:
|
|
|
|
raise TypeError('Too many positional arguments')
|
|
|
|
if not args:
|
|
|
|
mapping = kws
|
2004-09-13 11:35:04 -03:00
|
|
|
elif kws:
|
2011-02-25 21:02:51 -04:00
|
|
|
mapping = ChainMap(kws, args[0])
|
2004-09-13 12:25:15 -03:00
|
|
|
else:
|
|
|
|
mapping = args[0]
|
2004-09-13 11:35:04 -03:00
|
|
|
# Helper function for .sub()
|
2004-08-24 23:22:30 -03:00
|
|
|
def convert(mo):
|
2004-09-13 17:52:50 -03:00
|
|
|
# Check the most common path first.
|
|
|
|
named = mo.group('named') or mo.group('braced')
|
|
|
|
if named is not None:
|
2015-05-30 11:57:56 -03:00
|
|
|
val = mapping[named]
|
|
|
|
# We use this idiom instead of str() because the latter will
|
|
|
|
# fail if val is a Unicode containing non-ASCII characters.
|
|
|
|
return '%s' % (val,)
|
2004-08-25 21:21:13 -03:00
|
|
|
if mo.group('escaped') is not None:
|
2004-09-17 21:06:34 -03:00
|
|
|
return self.delimiter
|
2004-09-13 17:52:50 -03:00
|
|
|
if mo.group('invalid') is not None:
|
|
|
|
self._invalid(mo)
|
2004-10-17 13:27:18 -03:00
|
|
|
raise ValueError('Unrecognized named group in pattern',
|
|
|
|
self.pattern)
|
2004-09-10 00:08:08 -03:00
|
|
|
return self.pattern.sub(convert, self.template)
|
2004-08-24 23:22:30 -03:00
|
|
|
|
2015-03-24 17:28:43 -03:00
|
|
|
def safe_substitute(*args, **kws):
|
|
|
|
if not args:
|
|
|
|
raise TypeError("descriptor 'safe_substitute' of 'Template' object "
|
|
|
|
"needs an argument")
|
|
|
|
self, *args = args # allow the "self" keyword be passed
|
2004-09-13 12:25:15 -03:00
|
|
|
if len(args) > 1:
|
|
|
|
raise TypeError('Too many positional arguments')
|
|
|
|
if not args:
|
|
|
|
mapping = kws
|
2004-09-13 11:35:04 -03:00
|
|
|
elif kws:
|
2011-02-25 21:02:51 -04:00
|
|
|
mapping = ChainMap(kws, args[0])
|
2004-09-13 12:25:15 -03:00
|
|
|
else:
|
|
|
|
mapping = args[0]
|
2004-09-13 11:35:04 -03:00
|
|
|
# Helper function for .sub()
|
2004-08-24 23:22:30 -03:00
|
|
|
def convert(mo):
|
2010-09-18 20:34:07 -03:00
|
|
|
named = mo.group('named') or mo.group('braced')
|
2004-08-24 23:22:30 -03:00
|
|
|
if named is not None:
|
|
|
|
try:
|
2015-05-30 11:57:56 -03:00
|
|
|
# We use this idiom instead of str() because the latter
|
|
|
|
# will fail if val is a Unicode containing non-ASCII
|
|
|
|
return '%s' % (mapping[named],)
|
2004-08-24 23:22:30 -03:00
|
|
|
except KeyError:
|
2010-09-18 20:34:07 -03:00
|
|
|
return mo.group()
|
2004-09-13 17:52:50 -03:00
|
|
|
if mo.group('escaped') is not None:
|
2004-09-17 21:06:34 -03:00
|
|
|
return self.delimiter
|
2004-09-13 17:52:50 -03:00
|
|
|
if mo.group('invalid') is not None:
|
2010-09-18 20:34:07 -03:00
|
|
|
return mo.group()
|
2004-10-17 13:27:18 -03:00
|
|
|
raise ValueError('Unrecognized named group in pattern',
|
|
|
|
self.pattern)
|
2004-09-10 00:08:08 -03:00
|
|
|
return self.pattern.sub(convert, self.template)
|
2007-08-24 23:26:07 -03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
########################################################################
|
|
|
|
# the Formatter class
|
|
|
|
# see PEP 3101 for details and purpose of this class
|
|
|
|
|
Merged revisions 67154,67157-67159,67175-67176,67189,67224-67227,67234 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/trunk
........
r67154 | hirokazu.yamamoto | 2008-11-07 21:46:17 -0600 (Fri, 07 Nov 2008) | 1 line
Issue #4071: ntpath.abspath returned an empty string for long unicode path.
........
r67157 | georg.brandl | 2008-11-08 05:47:44 -0600 (Sat, 08 Nov 2008) | 2 lines
Don't use "HOWTO" as the title for all howto .tex files.
........
r67158 | georg.brandl | 2008-11-08 05:48:20 -0600 (Sat, 08 Nov 2008) | 2 lines
Update "Documenting" a bit. Concentrate on Python-specifics.
........
r67159 | georg.brandl | 2008-11-08 06:52:25 -0600 (Sat, 08 Nov 2008) | 2 lines
Fix warning.
........
r67175 | benjamin.peterson | 2008-11-08 19:44:32 -0600 (Sat, 08 Nov 2008) | 1 line
update link
........
r67176 | benjamin.peterson | 2008-11-08 19:52:32 -0600 (Sat, 08 Nov 2008) | 1 line
fix comment
........
r67189 | benjamin.peterson | 2008-11-11 15:56:06 -0600 (Tue, 11 Nov 2008) | 1 line
use correct name
........
r67224 | georg.brandl | 2008-11-15 02:10:04 -0600 (Sat, 15 Nov 2008) | 2 lines
#4324: fix getlocale() argument.
........
r67225 | brett.cannon | 2008-11-15 16:33:25 -0600 (Sat, 15 Nov 2008) | 1 line
Clarify the docs for the 'strict' argument to httplib.HTTPConnection.
........
r67226 | brett.cannon | 2008-11-15 16:40:44 -0600 (Sat, 15 Nov 2008) | 4 lines
The docs for httplib.HTTPConnection.putheader() have claimed for quite a while
that their could be an arbitrary number of values passed in. Turns out the code
did not match that. The code now matches the docs.
........
r67227 | georg.brandl | 2008-11-16 02:00:17 -0600 (Sun, 16 Nov 2008) | 2 lines
#4316: fix configure.in markup problem.
........
r67234 | benjamin.peterson | 2008-11-16 11:54:55 -0600 (Sun, 16 Nov 2008) | 1 line
run autoconf
........
2008-11-16 14:33:53 -04:00
|
|
|
# The hard parts are reused from the C implementation. They're exposed as "_"
|
2010-09-06 17:27:55 -03:00
|
|
|
# prefixed methods of str.
|
2007-08-24 23:26:07 -03:00
|
|
|
|
2010-10-14 04:04:07 -03:00
|
|
|
# The overall parser is implemented in _string.formatter_parser.
|
|
|
|
# The field name parser is implemented in _string.formatter_field_name_split
|
2007-08-24 23:26:07 -03:00
|
|
|
|
|
|
|
class Formatter:
|
2015-03-24 17:28:43 -03:00
|
|
|
def format(*args, **kwargs):
|
|
|
|
if not args:
|
|
|
|
raise TypeError("descriptor 'format' of 'Formatter' object "
|
|
|
|
"needs an argument")
|
|
|
|
self, *args = args # allow the "self" keyword be passed
|
|
|
|
try:
|
|
|
|
format_string, *args = args # allow the "format_string" keyword be passed
|
|
|
|
except ValueError:
|
|
|
|
if 'format_string' in kwargs:
|
|
|
|
format_string = kwargs.pop('format_string')
|
2015-03-24 17:30:46 -03:00
|
|
|
import warnings
|
|
|
|
warnings.warn("Passing 'format_string' as keyword argument is "
|
|
|
|
"deprecated", DeprecationWarning, stacklevel=2)
|
2015-03-24 17:28:43 -03:00
|
|
|
else:
|
|
|
|
raise TypeError("format() missing 1 required positional "
|
|
|
|
"argument: 'format_string'") from None
|
2007-08-24 23:26:07 -03:00
|
|
|
return self.vformat(format_string, args, kwargs)
|
|
|
|
|
|
|
|
def vformat(self, format_string, args, kwargs):
|
2007-08-30 23:26:31 -03:00
|
|
|
used_args = set()
|
2015-09-29 11:27:38 -03:00
|
|
|
result, _ = self._vformat(format_string, args, kwargs, used_args, 2)
|
2007-09-04 20:04:22 -03:00
|
|
|
self.check_unused_args(used_args, args, kwargs)
|
|
|
|
return result
|
|
|
|
|
2014-04-14 17:43:50 -03:00
|
|
|
def _vformat(self, format_string, args, kwargs, used_args, recursion_depth,
|
|
|
|
auto_arg_index=0):
|
2007-09-04 20:04:22 -03:00
|
|
|
if recursion_depth < 0:
|
|
|
|
raise ValueError('Max string recursion exceeded')
|
2007-08-24 23:26:07 -03:00
|
|
|
result = []
|
2007-08-28 08:15:20 -03:00
|
|
|
for literal_text, field_name, format_spec, conversion in \
|
|
|
|
self.parse(format_string):
|
Modified parsing of format strings, so that we always return
a tuple (literal, field_name, format_spec, conversion).
literal will always be a string, but might be of zero length.
field_name will be None if there is no markup text
format_spec will be a (possibly zero length) string if
field_name is non-None
conversion will be a one character string, or None
This makes the Formatter class, and especially it's parse()
method, easier to understand.
Suggestion was by Jim Jewett, inspired by the "tail" of an
elementtree node.
Also, fixed a reference leak in fieldnameiter_next.
2007-08-29 00:22:59 -03:00
|
|
|
|
|
|
|
# output the literal text
|
|
|
|
if literal_text:
|
|
|
|
result.append(literal_text)
|
|
|
|
|
|
|
|
# if there's a field, output it
|
|
|
|
if field_name is not None:
|
2007-08-28 08:15:20 -03:00
|
|
|
# this is some markup, find the object and do
|
|
|
|
# the formatting
|
2007-08-26 19:27:13 -03:00
|
|
|
|
2014-04-14 17:43:50 -03:00
|
|
|
# handle arg indexing when empty field_names are given.
|
|
|
|
if field_name == '':
|
|
|
|
if auto_arg_index is False:
|
|
|
|
raise ValueError('cannot switch from manual field '
|
|
|
|
'specification to automatic field '
|
|
|
|
'numbering')
|
|
|
|
field_name = str(auto_arg_index)
|
|
|
|
auto_arg_index += 1
|
|
|
|
elif field_name.isdigit():
|
|
|
|
if auto_arg_index:
|
|
|
|
raise ValueError('cannot switch from manual field '
|
|
|
|
'specification to automatic field '
|
|
|
|
'numbering')
|
|
|
|
# disable auto arg incrementing, if it gets
|
|
|
|
# used later on, then an exception will be raised
|
|
|
|
auto_arg_index = False
|
|
|
|
|
2007-08-28 08:15:20 -03:00
|
|
|
# given the field_name, find the object it references
|
2007-08-30 23:26:31 -03:00
|
|
|
# and the argument it came from
|
2007-09-02 12:33:26 -03:00
|
|
|
obj, arg_used = self.get_field(field_name, args, kwargs)
|
2007-08-30 23:26:31 -03:00
|
|
|
used_args.add(arg_used)
|
2007-08-26 19:27:13 -03:00
|
|
|
|
|
|
|
# do any conversion on the resulting object
|
2007-08-28 08:15:20 -03:00
|
|
|
obj = self.convert_field(obj, conversion)
|
2007-08-26 19:27:13 -03:00
|
|
|
|
2007-09-04 20:04:22 -03:00
|
|
|
# expand the format spec, if needed
|
2015-09-29 11:27:38 -03:00
|
|
|
format_spec, auto_arg_index = self._vformat(
|
|
|
|
format_spec, args, kwargs,
|
|
|
|
used_args, recursion_depth-1,
|
|
|
|
auto_arg_index=auto_arg_index)
|
2007-09-04 20:04:22 -03:00
|
|
|
|
2007-08-26 19:27:13 -03:00
|
|
|
# format the object and append to the result
|
|
|
|
result.append(self.format_field(obj, format_spec))
|
Modified parsing of format strings, so that we always return
a tuple (literal, field_name, format_spec, conversion).
literal will always be a string, but might be of zero length.
field_name will be None if there is no markup text
format_spec will be a (possibly zero length) string if
field_name is non-None
conversion will be a one character string, or None
This makes the Formatter class, and especially it's parse()
method, easier to understand.
Suggestion was by Jim Jewett, inspired by the "tail" of an
elementtree node.
Also, fixed a reference leak in fieldnameiter_next.
2007-08-29 00:22:59 -03:00
|
|
|
|
2015-09-29 11:27:38 -03:00
|
|
|
return ''.join(result), auto_arg_index
|
2007-08-24 23:26:07 -03:00
|
|
|
|
2007-08-28 08:15:20 -03:00
|
|
|
|
2007-08-24 23:26:07 -03:00
|
|
|
def get_value(self, key, args, kwargs):
|
2007-08-26 19:27:13 -03:00
|
|
|
if isinstance(key, int):
|
|
|
|
return args[key]
|
|
|
|
else:
|
|
|
|
return kwargs[key]
|
2007-08-24 23:26:07 -03:00
|
|
|
|
2007-08-28 08:15:20 -03:00
|
|
|
|
2007-08-24 23:26:07 -03:00
|
|
|
def check_unused_args(self, used_args, args, kwargs):
|
|
|
|
pass
|
|
|
|
|
2007-08-28 08:15:20 -03:00
|
|
|
|
2007-08-24 23:26:07 -03:00
|
|
|
def format_field(self, value, format_spec):
|
2007-08-26 19:27:13 -03:00
|
|
|
return format(value, format_spec)
|
2007-08-28 08:15:20 -03:00
|
|
|
|
|
|
|
|
|
|
|
def convert_field(self, value, conversion):
|
|
|
|
# do any conversion on the resulting object
|
2012-08-19 18:26:34 -03:00
|
|
|
if conversion is None:
|
|
|
|
return value
|
2007-08-28 08:15:20 -03:00
|
|
|
elif conversion == 's':
|
|
|
|
return str(value)
|
2012-08-19 18:26:34 -03:00
|
|
|
elif conversion == 'r':
|
|
|
|
return repr(value)
|
|
|
|
elif conversion == 'a':
|
|
|
|
return ascii(value)
|
2010-09-06 17:27:55 -03:00
|
|
|
raise ValueError("Unknown conversion specifier {0!s}".format(conversion))
|
2007-08-28 08:15:20 -03:00
|
|
|
|
|
|
|
|
|
|
|
# returns an iterable that contains tuples of the form:
|
|
|
|
# (literal_text, field_name, format_spec, conversion)
|
Modified parsing of format strings, so that we always return
a tuple (literal, field_name, format_spec, conversion).
literal will always be a string, but might be of zero length.
field_name will be None if there is no markup text
format_spec will be a (possibly zero length) string if
field_name is non-None
conversion will be a one character string, or None
This makes the Formatter class, and especially it's parse()
method, easier to understand.
Suggestion was by Jim Jewett, inspired by the "tail" of an
elementtree node.
Also, fixed a reference leak in fieldnameiter_next.
2007-08-29 00:22:59 -03:00
|
|
|
# literal_text can be zero length
|
|
|
|
# field_name can be None, in which case there's no
|
|
|
|
# object to format and output
|
|
|
|
# if field_name is not None, it is looked up, formatted
|
|
|
|
# with format_spec and conversion and then used
|
2007-08-28 08:15:20 -03:00
|
|
|
def parse(self, format_string):
|
2010-10-14 04:04:07 -03:00
|
|
|
return _string.formatter_parser(format_string)
|
2007-08-28 08:15:20 -03:00
|
|
|
|
|
|
|
|
|
|
|
# given a field_name, find the object it references.
|
|
|
|
# field_name: the field being looked up, e.g. "0.name"
|
|
|
|
# or "lookup[3]"
|
|
|
|
# used_args: a set of which args have been used
|
|
|
|
# args, kwargs: as passed in to vformat
|
2007-09-02 12:33:26 -03:00
|
|
|
def get_field(self, field_name, args, kwargs):
|
2010-10-14 04:04:07 -03:00
|
|
|
first, rest = _string.formatter_field_name_split(field_name)
|
2007-08-28 08:15:20 -03:00
|
|
|
|
|
|
|
obj = self.get_value(first, args, kwargs)
|
|
|
|
|
|
|
|
# loop through the rest of the field_name, doing
|
|
|
|
# getattr or getitem as needed
|
|
|
|
for is_attr, i in rest:
|
|
|
|
if is_attr:
|
|
|
|
obj = getattr(obj, i)
|
|
|
|
else:
|
|
|
|
obj = obj[i]
|
|
|
|
|
2007-08-30 23:26:31 -03:00
|
|
|
return obj, first
|