[Python-checkins] python/nondist/sandbox/string/string __init__.py, NONE, 1.1 pep292.py, NONE, 1.1 safedict.py, NONE, 1.1 string.py, NONE, 1.1

[bwarsaw at users.sourceforge.net]

Update of /cvsroot/python/python/nondist/sandbox/string/string
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv27618/string

Added Files:
	__init__.py pep292.py safedict.py string.py 
Log Message:
Updated code and tests for PEP 292 proposal.  I still need to write some
documentation, and it's not clear we're agreed on the approach of making the
string module a backward compatible package.  But at least there's now a
strawman and some unit tests.


--- NEW FILE: __init__.py ---
# Copyright (C) 2004 Python Software Foundation
# Author: barry at python.org (Barry Warsaw)

__version__ = '1.0'

# __all__ either needs to be left out for blanket importation or needs to have
# something like ``__all__.extend([stuff
#                     for stuff from dir(sys.modules['string'])
#                         if not stuff.startswith('_')])``
#__all__ = [
#    'dstring', 'astring',
#    'safedict', 'nsdict',
#    ]

from pep292 import dstring, astring
from safedict import safedict, nsdict

from string import *

--- NEW FILE: pep292.py ---
# Copyright (C) 2004 Python Software Foundation
# Author: barry at python.org (Barry Warsaw)

"""A package supporting PEP 292 Simple String Substitutions.

See http://www.python.org/peps/pep-0292.html for full specification.

Two subclasses of the unicode type are provided:

dstring - PEP 292 'dollar' strings with the following substitution rules:

    1. $$ is an escape; it is replaced with a single $

    2. $identifier names a substitution placeholder matching a mapping
       key of "identifier".  "identifier" must be a Python identifier
       as defined in [2].  The first non-identifier character after
       the $ character terminates this placeholder specification.

    3. ${identifier} is equivalent to $identifier.  It is required for
       when valid identifier characters follow the placeholder but are
       not part of the placeholder, e.g. "${noun}ification".

    No other characters have special meaning.

    [2] Identifiers and Keywords
    http://www.python.org/doc/current/ref/identifiers.html

astring - like dstring, but allows dotted identifiers (i.e. attribute paths)
    as the substitution variables.

You can also derive your own classes from dstring to define different
identifier rules.  UTSL for details.

Examples:

>>> x = dstring('$who owes me $what')
>>> print x
$who owes me $what
>>> print x % {'who': 'Tim', 'what': 'a bag of ham'}
Tim owes me a bag of ham

>>> import re
>>> class mstring(dstring):
...    cre = re.compile(
...        r'(\${2})|\$(mm:[_a-z]\w*)|\$({mm:[_a-z]\w*})', re.IGNORECASE)
...
>>> x = mstring('$who owes me $mm:what')
>>> print x % {'who': 'Tim', 'mm:what', 'nothing'}
$who owes me nothing

See also the safedict.py module for subclasses of dict that provide useful
substitution semantics.
"""

__all__ = ['dstring', 'astring']

import re

# Search for $$, $identifier, or ${identifier}
dre = re.compile(r'(\${2})|\$([_a-z][_a-z0-9]*)|\$({[_a-z][_a-z0-9]*})',
                 re.IGNORECASE)
# Like dre, but allows dots after the first character
are = re.compile(r'(\${2})|\$([_a-z][_.a-z0-9]*)|\$({[_a-z][_.a-z0-9]*})',
                 re.IGNORECASE)

EMPTYSTRING = ''



class dstring(unicode):
    cre = dre

    """A string class for supporting $-substitutions."""

    def __init__(self, s, *args, **kws):
        s = s.replace('%', '%%')
        parts = self.cre.split(s)
        # Here's what the elements of parts looks like after the split:
        #
        # 0   - any text before the first match
        # i, i+1, i+2 - groups of 3 corresponding to the three capturing
        #       parentheses in the regular expression.  Only one of these
        #       three will not be None, since of course only one group will
        #       match.
        # i+3 - this will be all the non-matching text between this match and
        #       the next one, or the end of the string if this is the last
        #       match.
        #
        # The algorithm then is to figure out which of the three groups
        # matched, and replace it with the %()s equivalent syntax.
        for i in range(1, len(parts), 4):
            if parts[i] is not None:
                # This matched the escape pattern.  It can just be replaced
                # with a single dollar since that's not special to Python's
                # build-in string interpolation.
                parts[i] = '$'
            elif parts[i+1] is not None:
                # This matched $identifier.  The $ is not retained in the
                # capturing parenthesis group.
                parts[i+1] = '%(' + parts[i+1] + ')s'
            else:
                # This matched ${identifier}.  The $ is not retained in the
                # capturing parenthesis group, but the curly braces are.
                # Doing so is useful for the safedict.
                parts[i+2] = '%(' + parts[i+2] + ')s'
        # Cache Pythonically syntaxed substitution string
        self._modstr = EMPTYSTRING.join(filter(None, parts))
        super(unicode, self).__init__(s, *args, **kws)

    def __mod__(self, other):
        return self._modstr % other


class astring(dstring):
    """Like string, but allow for dotted attribute paths."""
    cre = are

--- NEW FILE: safedict.py ---
# Copyright (C) 2004 Python Software Foundation
# Author: barry at python.org (Barry Warsaw)
# License: http://www.opensource.org/licenses/PythonSoftFoundation.php

"""Substitution dictionaries.

These work with $-string to provide foolproof substitutions.
"""

__all__ = ['safedict', 'nsdict']

import sys

_missing = object()



class safedict(dict):
    """Dictionary which returns a default value for unknown keys."""
    def __getitem__(self, key):
        if key.startswith('{') and key.endswith('}'):
            key = key[1:-1]
            fmt = '${%s}'
        else:
            fmt = '$%s'
        try:
            return super(safedict, self).__getitem__(key)
        except KeyError:
            return fmt % key



class nsdict(dict):
    # How many frames up from the caller of __getitem__() should we start
    # looking for locals and globals?  By default we look two frames up, since
    # the current frame will be our __getitem__() below, and the next frame up
    # will be dstring.__mod__() usually.  The frame up from that is the user's
    # code.  In Mailman, we'd set this to 3 since it's always called from the
    # mailman.i18n._() function which wraps the above frames.
    startframe = 2

    """Dictionary which substitutes in locals and globals."""
    def __getitem__(self, key):
        if key.startswith('{') and key.endswith('}'):
            key = key[1:-1]
            fmt = '${%s}'
        else:
            fmt = '$%s'
        # Split the key as if it were an attribute path
        parts = key.split('.')
        part0 = parts.pop(0)
        # Now search for the parts, starting with the locals and then trying
        # the globals, in the frame some number of call sites up. Note that
        # _getframe(0) would be nsdict.__getitem__().  You can start in
        # different frame locations by deriving from this class and overriding
        # startframe.  The default is to start at our caller.
        frame = sys._getframe(self.startframe)
        if part0 in frame.f_locals:
            obj = frame.f_locals[part0]
        elif part0 in frame.f_globals:
            obj = frame.f_globals[part0]
        else:
            return fmt % key
        while parts:
            attr = parts.pop(0)
            obj = getattr(obj, attr, _missing)
            if obj is _missing:
                return fmt % key
        return obj

--- NEW FILE: string.py ---
"""A collection of string operations (most are no longer used).

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

"""

# Some strings for ctype-style character classification
whitespace = ' \t\n\r\v\f'
lowercase = 'abcdefghijklmnopqrstuvwxyz'
uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
letters = lowercase + uppercase
ascii_lowercase = lowercase
ascii_uppercase = uppercase
ascii_letters = ascii_lowercase + ascii_uppercase
digits = '0123456789'
hexdigits = digits + 'abcdef' + 'ABCDEF'
octdigits = '01234567'
punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
printable = digits + letters + punctuation + whitespace

# Case conversion helpers
# Use str to convert Unicode literal in case of -U
l = map(chr, xrange(256))
_idmap = str('').join(l)
del l

# Backward compatible names for exceptions
index_error = ValueError
atoi_error = ValueError
atof_error = ValueError
atol_error = ValueError

# 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()

# 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()

# 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()

# 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)

# 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)


# 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, 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)

# 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.

    """
    return _float(s)


# Convert string to integer
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.

    """
    return _int(s, base)


# Convert string to long integer
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.

    """
    return _long(s, base)


# 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)

# 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)

# 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)

# 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)

# Expand tabs in a string.
# Doesn't take non-printing chars into account, but does understand \n.
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])

# 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()

# Capitalize the words in a string, e.g. " aBc  dEf " -> "Abc Def".
# See also regsub.capwords().
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 join(map(capitalize, s.split(sep)), sep or ' ')

# 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, "")

# 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