cpython/Lib/string.py

531 lines
16 KiB
Python
Raw Normal View History

"""A collection of string operations (most are no longer used).
1990-10-13 16:23:40 -03:00
Warning: most of the code you see here isn't normally used nowadays.
Beginning with Python 1.6, many of these functions are implemented as
methods on the standard string object. They used to be implemented by
a built-in module called strop, but strop is now obsolete itself.
Public module variables:
whitespace -- a string containing all characters considered whitespace
lowercase -- a string containing all characters considered lowercase letters
uppercase -- a string containing all characters considered uppercase letters
letters -- a string containing all characters considered letters
digits -- a string containing all characters considered decimal digits
hexdigits -- a string containing all characters considered hexadecimal digits
octdigits -- a string containing all characters considered octal digits
punctuation -- a string containing all characters considered punctuation
printable -- a string containing all characters considered printable
"""
1990-10-13 16:23:40 -03:00
# Some strings for ctype-style character classification
whitespace = ' \t\n\r\v\f'
1990-10-13 16:23:40 -03:00
lowercase = 'abcdefghijklmnopqrstuvwxyz'
uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
letters = lowercase + uppercase
ascii_lowercase = lowercase
ascii_uppercase = uppercase
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 + letters + punctuation + whitespace
1990-10-13 16:23:40 -03:00
# Case conversion helpers
# Use str to convert Unicode literal in case of -U
# Note that Cookie.py bogusly uses _idmap :(
l = map(chr, xrange(256))
_idmap = str('').join(l)
del l
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. Note that this replaces runs of whitespace characters by
a single space.
"""
return (sep or ' ').join([x.capitalize() for x in s.split(sep)])
# Construct a translation string
_idmapL = None
def maketrans(fromstr, tostr):
"""maketrans(frm, to) -> string
Return a translation table (a string of 256 bytes long)
suitable for use in string.translate. The strings frm and to
must be of the same length.
"""
if len(fromstr) != len(tostr):
raise ValueError, "maketrans arguments must have same length"
global _idmapL
if not _idmapL:
_idmapL = map(None, _idmap)
L = _idmapL[:]
fromstr = map(ord, fromstr)
for i in range(len(fromstr)):
L[fromstr[i]] = tostr[i]
return ''.join(L)
####################################################################
import re as _re
class _multimap:
"""Helper class for combining multiple mappings.
Used by .{safe_,}substitute() to combine the mapping and keyword
arguments.
"""
def __init__(self, primary, secondary):
self._primary = primary
self._secondary = secondary
def __getitem__(self, key):
try:
return self._primary[key]
except KeyError:
return self._secondary[key]
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, _re.IGNORECASE | _re.VERBOSE)
class Template:
"""A string class for supporting $-substitutions."""
__metaclass__ = _TemplateMetaclass
delimiter = '$'
idpattern = r'[_a-z][_a-z0-9]*'
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(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(self, *args, **kws):
if len(args) > 1:
raise TypeError('Too many positional arguments')
if not args:
mapping = kws
elif kws:
mapping = _multimap(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(self, *args, **kws):
if len(args) > 1:
raise TypeError('Too many positional arguments')
if not args:
mapping = kws
elif kws:
mapping = _multimap(kws, args[0])
else:
mapping = args[0]
# Helper function for .sub()
def convert(mo):
named = mo.group('named')
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 self.delimiter + named
braced = mo.group('braced')
if braced is not None:
try:
return '%s' % (mapping[braced],)
except KeyError:
return self.delimiter + '{' + braced + '}'
if mo.group('escaped') is not None:
return self.delimiter
if mo.group('invalid') is not None:
return self.delimiter
raise ValueError('Unrecognized named group in pattern',
self.pattern)
return self.pattern.sub(convert, self.template)
####################################################################
# NOTE: Everything below here is deprecated. Use string methods instead.
# This stuff will go away in Python 3.0.
# Backward compatible names for exceptions
index_error = ValueError
atoi_error = ValueError
atof_error = ValueError
atol_error = ValueError
1990-10-13 16:23:40 -03:00
# convert UPPER CASE letters to lower case
def lower(s):
"""lower(s) -> string
Return a copy of the string s converted to lowercase.
"""
return s.lower()
1990-10-13 16:23:40 -03:00
# Convert lower case letters to UPPER CASE
def upper(s):
"""upper(s) -> string
Return a copy of the string s converted to uppercase.
"""
return s.upper()
1990-10-13 16:23:40 -03:00
# Swap lower case letters and UPPER CASE
def swapcase(s):
"""swapcase(s) -> string
Return a copy of the string s with upper case characters
converted to lowercase and vice versa.
"""
return s.swapcase()
1990-10-13 16:23:40 -03:00
# Strip leading and trailing tabs and spaces
def strip(s, chars=None):
"""strip(s [,chars]) -> string
Return a copy of the string s with leading and trailing
whitespace removed.
If chars is given and not None, remove characters in chars instead.
If chars is unicode, S will be converted to unicode before stripping.
"""
return s.strip(chars)
1990-10-13 16:23:40 -03:00
# Strip leading tabs and spaces
def lstrip(s, chars=None):
"""lstrip(s [,chars]) -> string
Return a copy of the string s with leading whitespace removed.
If chars is given and not None, remove characters in chars instead.
"""
return s.lstrip(chars)
# Strip trailing tabs and spaces
def rstrip(s, chars=None):
"""rstrip(s [,chars]) -> string
Return a copy of the string s with trailing whitespace removed.
If chars is given and not None, remove characters in chars instead.
"""
return s.rstrip(chars)
1990-10-13 16:23:40 -03:00
# Split a string into a list of space/tab-separated words
def split(s, sep=None, maxsplit=-1):
"""split(s [,sep [,maxsplit]]) -> list of strings
Return a list of the words in the string s, using sep as the
delimiter string. If maxsplit is given, splits at no more than
maxsplit places (resulting in at most maxsplit+1 words). If sep
is not specified or is None, any whitespace string is a separator.
(split and splitfields are synonymous)
"""
return s.split(sep, maxsplit)
splitfields = split
# Split a string into a list of space/tab-separated words
def rsplit(s, sep=None, maxsplit=-1):
"""rsplit(s [,sep [,maxsplit]]) -> list of strings
Return a list of the words in the string s, using sep as the
delimiter string, starting at the end of the string and working
to the front. If maxsplit is given, at most maxsplit splits are
done. If sep is not specified or is None, any whitespace string
is a separator.
"""
return s.rsplit(sep, maxsplit)
# Join fields with optional separator
def join(words, sep = ' '):
"""join(list [,sep]) -> string
Return a string composed of the words in list, with
intervening occurrences of sep. The default separator is a
single space.
(joinfields and join are synonymous)
"""
return sep.join(words)
joinfields = join
# Find substring, raise exception if not found
def index(s, *args):
"""index(s, sub [,start [,end]]) -> int
Like find but raises ValueError when the substring is not found.
"""
return s.index(*args)
# Find last substring, raise exception if not found
def rindex(s, *args):
"""rindex(s, sub [,start [,end]]) -> int
Like rfind but raises ValueError when the substring is not found.
"""
return s.rindex(*args)
# Count non-overlapping occurrences of substring
def count(s, *args):
"""count(s, sub[, start[,end]]) -> int
Return the number of occurrences of substring sub in string
s[start:end]. Optional arguments start and end are
interpreted as in slice notation.
"""
return s.count(*args)
# Find substring, return -1 if not found
def find(s, *args):
"""find(s, sub [,start [,end]]) -> in
Return the lowest index in s where substring sub is found,
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Return -1 on failure.
"""
return s.find(*args)
1990-10-13 16:23:40 -03:00
# Find last substring, return -1 if not found
def rfind(s, *args):
"""rfind(s, sub [,start [,end]]) -> int
Return the highest index in s where substring sub is found,
such that sub is contained within s[start,end]. Optional
arguments start and end are interpreted as in slice notation.
Return -1 on failure.
"""
return s.rfind(*args)
# for a bit of speed
_float = float
_int = int
_long = long
# Convert string to float
def atof(s):
"""atof(s) -> float
Return the floating point number represented by the string s.
"""
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).
2000-04-05 17:11:21 -03:00
return _float(s)
1990-10-13 16:23:40 -03:00
# Convert string to integer
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).
2000-04-05 17:11:21 -03:00
def atoi(s , base=10):
"""atoi(s [,base]) -> int
Return the integer represented by the string s in the given
base, which defaults to 10. The string s must consist of one
or more digits, possibly preceded by a sign. If base is 0, it
is chosen from the leading characters of s, 0 for octal, 0x or
0X for hexadecimal. If base is 16, a preceding 0x or 0X is
accepted.
"""
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).
2000-04-05 17:11:21 -03:00
return _int(s, base)
1990-10-13 16:23:40 -03:00
# Convert string to long integer
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).
2000-04-05 17:11:21 -03:00
def atol(s, base=10):
"""atol(s [,base]) -> long
Return the long integer represented by the string s in the
given base, which defaults to 10. The string s must consist
of one or more digits, possibly preceded by a sign. If base
is 0, it is chosen from the leading characters of s, 0 for
octal, 0x or 0X for hexadecimal. If base is 16, a preceding
0x or 0X is accepted. A trailing L or l is not accepted,
unless base is 0.
"""
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).
2000-04-05 17:11:21 -03:00
return _long(s, base)
1990-10-13 16:23:40 -03:00
# Left-justify a string
def ljust(s, width, *args):
"""ljust(s, width[, fillchar]) -> string
Return a left-justified version of s, in a field of the
specified width, padded with spaces as needed. The string is
never truncated. If specified the fillchar is used instead of spaces.
"""
return s.ljust(width, *args)
1990-10-13 16:23:40 -03:00
# Right-justify a string
def rjust(s, width, *args):
"""rjust(s, width[, fillchar]) -> string
Return a right-justified version of s, in a field of the
specified width, padded with spaces as needed. The string is
never truncated. If specified the fillchar is used instead of spaces.
"""
return s.rjust(width, *args)
1990-10-13 16:23:40 -03:00
# Center a string
def center(s, width, *args):
"""center(s, width[, fillchar]) -> string
Return a center version of s, in a field of the specified
width. padded with spaces as needed. The string is never
truncated. If specified the fillchar is used instead of spaces.
"""
return s.center(width, *args)
1990-10-13 16:23:40 -03:00
# Zero-fill a number, e.g., (12, 3) --> '012' and (-3, 3) --> '-03'
# Decadent feature: the argument may be a string or a number
# (Use of this is deprecated; it should be a string as with ljust c.s.)
def zfill(x, width):
"""zfill(x, width) -> string
Pad a numeric string x with zeros on the left, to fill a field
of the specified width. The string x is never truncated.
"""
if not isinstance(x, basestring):
x = repr(x)
return x.zfill(width)
1992-03-27 11:13:31 -04:00
# Expand tabs in a string.
# Doesn't take non-printing chars into account, but does understand \n.
1995-08-10 16:42:05 -03:00
def expandtabs(s, tabsize=8):
"""expandtabs(s [,tabsize]) -> string
Return a copy of the string s with all tab characters replaced
by the appropriate number of spaces, depending on the current
column, and the tabsize (default 8).
"""
return s.expandtabs(tabsize)
# Character translation through look-up table.
def translate(s, table, deletions=""):
"""translate(s,table [,deletions]) -> string
Return a copy of the string s, where all characters occurring
in the optional argument deletions are removed, and the
remaining characters have been mapped through the given
translation table, which must be a string of length 256. The
deletions argument is not allowed for Unicode strings.
"""
if deletions:
return s.translate(table, deletions)
else:
# Add s[:0] so that if s is Unicode and table is an 8-bit string,
# table is converted to Unicode. This means that table *cannot*
# be a dictionary -- for that feature, use u.translate() directly.
return s.translate(table + s[:0])
1996-06-11 15:43:00 -03:00
# Capitalize a string, e.g. "aBc dEf" -> "Abc def".
def capitalize(s):
"""capitalize(s) -> string
Return a copy of the string s with only its first character
capitalized.
"""
return s.capitalize()
1996-06-11 15:43:00 -03:00
# Substring replacement (global)
def replace(s, old, new, maxsplit=-1):
"""replace (str, old, new[, maxsplit]) -> string
Return a copy of string str with all occurrences of substring
old replaced by new. If the optional argument maxsplit is
given, only the first maxsplit occurrences are replaced.
"""
return s.replace(old, new, maxsplit)
# Try importing optional built-in module "strop" -- if it exists,
# it redefines some string operations that are 100-1000 times faster.
# It also defines values for whitespace, lowercase and uppercase
# that match <ctype.h>'s definitions.
try:
from strop import maketrans, lowercase, uppercase, whitespace
letters = lowercase + uppercase
except ImportError:
pass # Use the original versions