cpython/Lib/string.py

306 lines
11 KiB
Python
Raw Normal View History

"""A collection of string constants.
Public module variables:
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
"""
import _string
1990-10-13 16:23:40 -03:00
# Some strings for ctype-style character classification
whitespace = ' \t\n\r\v\f'
ascii_lowercase = 'abcdefghijklmnopqrstuvwxyz'
ascii_uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
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 = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
printable = digits + ascii_letters + punctuation + whitespace
1990-10-13 16:23:40 -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):
"""capwords(s [,sep]) -> string
Split the argument into words using split, capitalize each
word using capitalize, and join the capitalized words using
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.
"""
return (sep or ' ').join(x.capitalize() for x in s.split(sep))
####################################################################
import re as _re
from collections import ChainMap
class _TemplateMetaclass(type):
pattern = r"""
%(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
)
"""
def __init__(cls, name, bases, dct):
super(_TemplateMetaclass, cls).__init__(name, bases, dct)
if 'pattern' in dct:
pattern = cls.pattern
else:
pattern = _TemplateMetaclass.pattern % {
'delim' : _re.escape(cls.delimiter),
'id' : cls.idpattern,
}
cls.pattern = _re.compile(pattern, cls.flags | _re.VERBOSE)
class Template(metaclass=_TemplateMetaclass):
"""A string class for supporting $-substitutions."""
delimiter = '$'
idpattern = r'[_a-z][_a-z0-9]*'
flags = _re.IGNORECASE
def __init__(self, template):
self.template = template
# Search for $$, $identifier, ${identifier}, and any bare $'s
def _invalid(self, mo):
i = mo.start('invalid')
lines = self.template[:i].splitlines(keepends=True)
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))
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
if len(args) > 1:
raise TypeError('Too many positional arguments')
if not args:
mapping = kws
elif kws:
mapping = ChainMap(kws, args[0])
else:
mapping = args[0]
# Helper function for .sub()
def convert(mo):
# Check the most common path first.
named = mo.group('named') or mo.group('braced')
if named is not None:
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,)
if mo.group('escaped') is not None:
return self.delimiter
if mo.group('invalid') is not None:
self._invalid(mo)
raise ValueError('Unrecognized named group in pattern',
self.pattern)
return self.pattern.sub(convert, self.template)
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
if len(args) > 1:
raise TypeError('Too many positional arguments')
if not args:
mapping = kws
elif kws:
mapping = ChainMap(kws, args[0])
else:
mapping = args[0]
# Helper function for .sub()
def convert(mo):
named = mo.group('named') or mo.group('braced')
if named is not None:
try:
# We use this idiom instead of str() because the latter
# will fail if val is a Unicode containing non-ASCII
return '%s' % (mapping[named],)
except KeyError:
return mo.group()
if mo.group('escaped') is not None:
return self.delimiter
if mo.group('invalid') is not None:
return mo.group()
raise ValueError('Unrecognized named group in pattern',
self.pattern)
return self.pattern.sub(convert, self.template)
########################################################################
# 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.
# The overall parser is implemented in _string.formatter_parser.
# The field name parser is implemented in _string.formatter_field_name_split
class Formatter:
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')
import warnings
warnings.warn("Passing 'format_string' as keyword argument is "
"deprecated", DeprecationWarning, stacklevel=2)
else:
raise TypeError("format() missing 1 required positional "
"argument: 'format_string'") from None
return self.vformat(format_string, args, kwargs)
def vformat(self, format_string, args, kwargs):
used_args = set()
result = self._vformat(format_string, args, kwargs, used_args, 2)
self.check_unused_args(used_args, args, kwargs)
return result
def _vformat(self, format_string, args, kwargs, used_args, recursion_depth,
auto_arg_index=0):
if recursion_depth < 0:
raise ValueError('Max string recursion exceeded')
result = []
for literal_text, field_name, format_spec, conversion in \
self.parse(format_string):
# output the literal text
if literal_text:
result.append(literal_text)
# if there's a field, output it
if field_name is not None:
# this is some markup, find the object and do
# the formatting
# 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
# given the field_name, find the object it references
# and the argument it came from
obj, arg_used = self.get_field(field_name, args, kwargs)
used_args.add(arg_used)
# do any conversion on the resulting object
obj = self.convert_field(obj, conversion)
# expand the format spec, if needed
format_spec = self._vformat(format_spec, args, kwargs,
used_args, recursion_depth-1,
auto_arg_index=auto_arg_index)
# format the object and append to the result
result.append(self.format_field(obj, format_spec))
return ''.join(result)
def get_value(self, key, args, kwargs):
if isinstance(key, int):
return args[key]
else:
return kwargs[key]
def check_unused_args(self, used_args, args, kwargs):
pass
def format_field(self, value, format_spec):
return format(value, format_spec)
def convert_field(self, value, conversion):
# do any conversion on the resulting object
if conversion is None:
return value
elif conversion == 's':
return str(value)
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))
# returns an iterable that contains tuples of the form:
# (literal_text, field_name, format_spec, conversion)
# 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
def parse(self, format_string):
return _string.formatter_parser(format_string)
# 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
def get_field(self, field_name, args, kwargs):
first, rest = _string.formatter_field_name_split(field_name)
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]
return obj, first