/config/configobj.py

Large files files are truncated, but you can click here to view the full file

# configobj.py
# A config file reader/writer that supports nested sections in config files.
# Copyright (C) 2005-2006 Michael Foord, Nicola Larosa
# E-mail: fuzzyman AT voidspace DOT org DOT uk
#         nico AT tekNico DOT net

# ConfigObj 4
# http://www.voidspace.org.uk/python/configobj.html

# Released subject to the BSD License
# Please see http://www.voidspace.org.uk/python/license.shtml

# Scripts maintained at http://www.voidspace.org.uk/python/index.shtml
# For information about bugfixes, updates and support, please join the
# ConfigObj mailing list:
# http://lists.sourceforge.net/lists/listinfo/configobj-develop
# Comments, suggestions and bug reports welcome.

from __future__ import generators

import sys
INTP_VER = sys.version_info[:2]
if INTP_VER < (2, 2):
    raise RuntimeError("Python v.2.2 or later needed")

import os, re
compiler = None
try:
    import compiler
except ImportError:
    # for IronPython
    pass
from types import StringTypes
from warnings import warn
try:
    from codecs import BOM_UTF8, BOM_UTF16, BOM_UTF16_BE, BOM_UTF16_LE
except ImportError:
    # Python 2.2 does not have these
    # UTF-8
    BOM_UTF8 = '\xef\xbb\xbf'
    # UTF-16, little endian
    BOM_UTF16_LE = '\xff\xfe'
    # UTF-16, big endian
    BOM_UTF16_BE = '\xfe\xff'
    if sys.byteorder == 'little':
        # UTF-16, native endianness
        BOM_UTF16 = BOM_UTF16_LE
    else:
        # UTF-16, native endianness
        BOM_UTF16 = BOM_UTF16_BE

# A dictionary mapping BOM to
# the encoding to decode with, and what to set the
# encoding attribute to.
BOMS = {
    BOM_UTF8: ('utf_8', None),
    BOM_UTF16_BE: ('utf16_be', 'utf_16'),
    BOM_UTF16_LE: ('utf16_le', 'utf_16'),
    BOM_UTF16: ('utf_16', 'utf_16'),
    }
# All legal variants of the BOM codecs.
# TODO: the list of aliases is not meant to be exhaustive, is there a
#   better way ?
BOM_LIST = {
    'utf_16': 'utf_16',
    'u16': 'utf_16',
    'utf16': 'utf_16',
    'utf-16': 'utf_16',
    'utf16_be': 'utf16_be',
    'utf_16_be': 'utf16_be',
    'utf-16be': 'utf16_be',
    'utf16_le': 'utf16_le',
    'utf_16_le': 'utf16_le',
    'utf-16le': 'utf16_le',
    'utf_8': 'utf_8',
    'u8': 'utf_8',
    'utf': 'utf_8',
    'utf8': 'utf_8',
    'utf-8': 'utf_8',
    }

# Map of encodings to the BOM to write.
BOM_SET = {
    'utf_8': BOM_UTF8,
    'utf_16': BOM_UTF16,
    'utf16_be': BOM_UTF16_BE,
    'utf16_le': BOM_UTF16_LE,
    None: BOM_UTF8
    }

try:
    from validate import VdtMissingValue
except ImportError:
    VdtMissingValue = None

try:
    enumerate
except NameError:
    def enumerate(obj):
        """enumerate for Python 2.2."""
        i = -1
        for item in obj:
            i += 1
            yield i, item

try:
    True, False
except NameError:
    True, False = 1, 0


__version__ = '4.4.0'

__revision__ = '$Id: configobj.py,v 3.5 2007/07/02 18:20:24 benjamin%smedbergs.us Exp $'

__docformat__ = "restructuredtext en"

__all__ = (
    '__version__',
    'DEFAULT_INDENT_TYPE',
    'DEFAULT_INTERPOLATION',
    'ConfigObjError',
    'NestingError',
    'ParseError',
    'DuplicateError',
    'ConfigspecError',
    'ConfigObj',
    'SimpleVal',
    'InterpolationError',
    'InterpolationLoopError',
    'MissingInterpolationOption',
    'RepeatSectionError',
    'UnreprError',
    'UnknownType',
    '__docformat__',
    'flatten_errors',
)

DEFAULT_INTERPOLATION = 'configparser'
DEFAULT_INDENT_TYPE = '    '
MAX_INTERPOL_DEPTH = 10

OPTION_DEFAULTS = {
    'interpolation': True,
    'raise_errors': False,
    'list_values': True,
    'create_empty': False,
    'file_error': False,
    'configspec': None,
    'stringify': True,
    # option may be set to one of ('', ' ', '\t')
    'indent_type': None,
    'encoding': None,
    'default_encoding': None,
    'unrepr': False,
    'write_empty_values': False,
}


def getObj(s):
    s = "a=" + s
    if compiler is None:
        raise ImportError('compiler module not available')
    p = compiler.parse(s)
    return p.getChildren()[1].getChildren()[0].getChildren()[1]

class UnknownType(Exception):
    pass

class Builder:
    
    def build(self, o):
        m = getattr(self, 'build_' + o.__class__.__name__, None)
        if m is None:
            raise UnknownType(o.__class__.__name__)
        return m(o)
    
    def build_List(self, o):
        return map(self.build, o.getChildren())
    
    def build_Const(self, o):
        return o.value
    
    def build_Dict(self, o):
        d = {}
        i = iter(map(self.build, o.getChildren()))
        for el in i:
            d[el] = i.next()
        return d
    
    def build_Tuple(self, o):
        return tuple(self.build_List(o))
    
    def build_Name(self, o):
        if o.name == 'None':
            return None
        if o.name == 'True':
            return True
        if o.name == 'False':
            return False
        
        # An undefinted Name
        raise UnknownType('Undefined Name')
    
    def build_Add(self, o):
        real, imag = map(self.build_Const, o.getChildren())
        try:
            real = float(real)
        except TypeError:
            raise UnknownType('Add')
        if not isinstance(imag, complex) or imag.real != 0.0:
            raise UnknownType('Add')
        return real+imag
    
    def build_Getattr(self, o):
        parent = self.build(o.expr)
        return getattr(parent, o.attrname)
    
    def build_UnarySub(self, o):
        return -self.build_Const(o.getChildren()[0])
    
    def build_UnaryAdd(self, o):
        return self.build_Const(o.getChildren()[0])

def unrepr(s):
    if not s:
        return s
    return Builder().build(getObj(s))

def _splitlines(instring):
    """Split a string on lines, without losing line endings or truncating."""
    

class ConfigObjError(SyntaxError):
    """
    This is the base class for all errors that ConfigObj raises.
    It is a subclass of SyntaxError.
    """
    def __init__(self, message='', line_number=None, line=''):
        self.line = line
        self.line_number = line_number
        self.message = message
        SyntaxError.__init__(self, message)

class NestingError(ConfigObjError):
    """
    This error indicates a level of nesting that doesn't match.
    """

class ParseError(ConfigObjError):
    """
    This error indicates that a line is badly written.
    It is neither a valid ``key = value`` line,
    nor a valid section marker line.
    """

class DuplicateError(ConfigObjError):
    """
    The keyword or section specified already exists.
    """

class ConfigspecError(ConfigObjError):
    """
    An error occurred whilst parsing a configspec.
    """

class InterpolationError(ConfigObjError):
    """Base class for the two interpolation errors."""

class InterpolationLoopError(InterpolationError):
    """Maximum interpolation depth exceeded in string interpolation."""

    def __init__(self, option):
        InterpolationError.__init__(
            self,
            'interpolation loop detected in value "%s".' % option)

class RepeatSectionError(ConfigObjError):
    """
    This error indicates additional sections in a section with a
    ``__many__`` (repeated) section.
    """

class MissingInterpolationOption(InterpolationError):
    """A value specified for interpolation was missing."""

    def __init__(self, option):
        InterpolationError.__init__(
            self,
            'missing option "%s" in interpolation.' % option)

class UnreprError(ConfigObjError):
    """An error parsing in unrepr mode."""


class InterpolationEngine(object):
    """
    A helper class to help perform string interpolation.

    This class is an abstract base class; its descendants perform
    the actual work.
    """

    # compiled regexp to use in self.interpolate()
    _KEYCRE = re.compile(r"%\(([^)]*)\)s")

    def __init__(self, section):
        # the Section instance that "owns" this engine
        self.section = section

    def interpolate(self, key, value):
        def recursive_interpolate(key, value, section, backtrail):
            """The function that does the actual work.

            ``value``: the string we're trying to interpolate.
            ``section``: the section in which that string was found
            ``backtrail``: a dict to keep track of where we've been,
            to detect and prevent infinite recursion loops

            This is similar to a depth-first-search algorithm.
            """
            # Have we been here already?
            if backtrail.has_key((key, section.name)):
                # Yes - infinite loop detected
                raise InterpolationLoopError(key)
            # Place a marker on our backtrail so we won't come back here again
            backtrail[(key, section.name)] = 1

            # Now start the actual work
            match = self._KEYCRE.search(value)
            while match:
                # The actual parsing of the match is implementation-dependent,
                # so delegate to our helper function
                k, v, s = self._parse_match(match)
                if k is None:
                    # That's the signal that no further interpolation is needed
                    replacement = v
                else:
                    # Further interpolation may be needed to obtain final value
                    replacement = recursive_interpolate(k, v, s, backtrail)
                # Replace the matched string with its final value
                start, end = match.span()
                value = ''.join((value[:start], replacement, value[end:]))
                new_search_start = start + len(replacement)
                # Pick up the next interpolation key, if any, for next time
                # through the while loop
                match = self._KEYCRE.search(value, new_search_start)

            # Now safe to come back here again; remove marker from backtrail
            del backtrail[(key, section.name)]

            return value

        # Back in interpolate(), all we have to do is kick off the recursive
        # function with appropriate starting values
        value = recursive_interpolate(key, value, self.section, {})
        return value

    def _fetch(self, key):
        """Helper function to fetch values from owning section.

        Returns a 2-tuple: the value, and the section where it was found.
        """
        # switch off interpolation before we try and fetch anything !
        save_interp = self.section.main.interpolation
        self.section.main.interpolation = False

        # Start at section that "owns" this InterpolationEngine
        current_section = self.section
        while True:
            # try the current section first
            val = current_section.get(key)
            if val is not None:
                break
            # try "DEFAULT" next
            val = current_section.get('DEFAULT', {}).get(key)
            if val is not None:
                break
            # move up to parent and try again
            # top-level's parent is itself
            if current_section.parent is current_section:
                # reached top level, time to give up
                break
            current_section = current_section.parent

        # restore interpolation to previous value before returning
        self.section.main.interpolation = save_interp
        if val is None:
            raise MissingInterpolationOption(key)
        return val, current_section

    def _parse_match(self, match):
        """Implementation-dependent helper function.

        Will be passed a match object corresponding to the interpolation
        key we just found (e.g., "%(foo)s" or "$foo"). Should look up that
        key in the appropriate config file section (using the ``_fetch()``
        helper function) and return a 3-tuple: (key, value, section)

        ``key`` is the name of the key we're looking for
        ``value`` is the value found for that key
        ``section`` is a reference to the section where it was found

        ``key`` and ``section`` should be None if no further
        interpolation should be performed on the resulting value
        (e.g., if we interpolated "$$" and returned "$").
        """
        raise NotImplementedError
    

class ConfigParserInterpolation(InterpolationEngine):
    """Behaves like ConfigParser."""
    _KEYCRE = re.compile(r"%\(([^)]*)\)s")

    def _parse_match(self, match):
        key = match.group(1)
        value, section = self._fetch(key)
        return key, value, section


class TemplateInterpolation(InterpolationEngine):
    """Behaves like string.Template."""
    _delimiter = '$'
    _KEYCRE = re.compile(r"""
        \$(?:
          (?P<escaped>\$)              |   # Two $ signs
          (?P<named>[_a-z][_a-z0-9]*)  |   # $name format
          {(?P<braced>[^}]*)}              # ${name} format
        )
        """, re.IGNORECASE | re.VERBOSE)

    def _parse_match(self, match):
        # Valid name (in or out of braces): fetch value from section
        key = match.group('named') or match.group('braced')
        if key is not None:
            value, section = self._fetch(key)
            return key, value, section
        # Escaped delimiter (e.g., $$): return single delimiter
        if match.group('escaped') is not None:
            # Return None for key and section to indicate it's time to stop
            return None, self._delimiter, None
        # Anything else: ignore completely, just return it unchanged
        return None, match.group(), None

interpolation_engines = {
    'configparser': ConfigParserInterpolation,
    'template': TemplateInterpolation,
}

class Section(dict):
    """
    A dictionary-like object that represents a section in a config file.
    
    It does string interpolation if the 'interpolation' attribute
    of the 'main' object is set to True.
    
    Interpolation is tried first from this object, then from the 'DEFAULT'
    section of this object, next from the parent and its 'DEFAULT' section,
    and so on until the main object is reached.
    
    A Section will behave like an ordered dictionary - following the
    order of the ``scalars`` and ``sections`` attributes.
    You can use this to change the order of members.
    
    Iteration follows the order: scalars, then sections.
    """

    def __init__(self, parent, depth, main, indict=None, name=None):
        """
        * parent is the section above
        * depth is the depth level of this section
        * main is the main ConfigObj
        * indict is a dictionary to initialise the section with
        """
        if indict is None:
            indict = {}
        dict.__init__(self)
        # used for nesting level *and* interpolation
        self.parent = parent
        # used for the interpolation attribute
        self.main = main
        # level of nesting depth of this Section
        self.depth = depth
        # the sequence of scalar values in this Section
        self.scalars = []
        # the sequence of sections in this Section
        self.sections = []
        # purely for information
        self.name = name
        # for comments :-)
        self.comments = {}
        self.inline_comments = {}
        # for the configspec
        self.configspec = {}
        self._order = []
        self._configspec_comments = {}
        self._configspec_inline_comments = {}
        self._cs_section_comments = {}
        self._cs_section_inline_comments = {}
        # for defaults
        self.defaults = []
        #
        # we do this explicitly so that __setitem__ is used properly
        # (rather than just passing to ``dict.__init__``)
        for entry in indict:
            self[entry] = indict[entry]

    def _interpolate(self, key, value):
        try:
            # do we already have an interpolation engine?
            engine = self._interpolation_engine
        except AttributeError:
            # not yet: first time running _interpolate(), so pick the engine
            name = self.main.interpolation
            if name == True:  # note that "if name:" would be incorrect here
                # backwards-compatibility: interpolation=True means use default
                name = DEFAULT_INTERPOLATION
            name = name.lower()  # so that "Template", "template", etc. all work
            class_ = interpolation_engines.get(name, None)
            if class_ is None:
                # invalid value for self.main.interpolation
                self.main.interpolation = False
                return value
            else:
                # save reference to engine so we don't have to do this again
                engine = self._interpolation_engine = class_(self)
        # let the engine do the actual work
        return engine.interpolate(key, value)

    def __getitem__(self, key):
        """Fetch the item and do string interpolation."""
        val = dict.__getitem__(self, key)
        if self.main.interpolation and isinstance(val, StringTypes):
            return self._interpolate(key, val)
        return val

    def __setitem__(self, key, value, unrepr=False):
        """
        Correctly set a value.
        
        Making dictionary values Section instances.
        (We have to special case 'Section' instances - which are also dicts)
        
        Keys must be strings.
        Values need only be strings (or lists of strings) if
        ``main.stringify`` is set.
        
        `unrepr`` must be set when setting a value to a dictionary, without
        creating a new sub-section.
        """
        if not isinstance(key, StringTypes):
            raise ValueError, 'The key "%s" is not a string.' % key
        # add the comment
        if not self.comments.has_key(key):
            self.comments[key] = []
            self.inline_comments[key] = ''
        # remove the entry from defaults
        if key in self.defaults:
            self.defaults.remove(key)
        #
        if isinstance(value, Section):
            if not self.has_key(key):
                self.sections.append(key)
            dict.__setitem__(self, key, value)
        elif isinstance(value, dict) and not unrepr:
            # First create the new depth level,
            # then create the section
            if not self.has_key(key):
                self.sections.append(key)
            new_depth = self.depth + 1
            dict.__setitem__(
                self,
                key,
                Section(
                    self,
                    new_depth,
                    self.main,
                    indict=value,
                    name=key))
        else:
            if not self.has_key(key):
                self.scalars.append(key)
            if not self.main.stringify:
                if isinstance(value, StringTypes):
                    pass
                elif isinstance(value, (list, tuple)):
                    for entry in value:
                        if not isinstance(entry, StringTypes):
                            raise TypeError, (
                                'Value is not a string "%s".' % entry)
                else:
                    raise TypeError, 'Value is not a string "%s".' % value
            dict.__setitem__(self, key, value)

    def __delitem__(self, key):
        """Remove items from the sequence when deleting."""
        dict. __delitem__(self, key)
        if key in self.scalars:
            self.scalars.remove(key)
        else:
            self.sections.remove(key)
        del self.comments[key]
        del self.inline_comments[key]

    def get(self, key, default=None):
        """A version of ``get`` that doesn't bypass string interpolation."""
        try:
            return self[key]
        except KeyError:
            return default

    def update(self, indict):
        """
        A version of update that uses our ``__setitem__``.
        """
        for entry in indict:
            self[entry] = indict[entry]

    def pop(self, key, *args):
        """ """
        val = dict.pop(self, key, *args)
        if key in self.scalars:
            del self.comments[key]
            del self.inline_comments[key]
            self.scalars.remove(key)
        elif key in self.sections:
            del self.comments[key]
            del self.inline_comments[key]
            self.sections.remove(key)
        if self.main.interpolation and isinstance(val, StringTypes):
            return self._interpolate(key, val)
        return val

    def popitem(self):
        """Pops the first (key,val)"""
        sequence = (self.scalars + self.sections)
        if not sequence:
            raise KeyError, ": 'popitem(): dictionary is empty'"
        key = sequence[0]
        val =  self[key]
        del self[key]
        return key, val

    def clear(self):
        """
        A version of clear that also affects scalars/sections
        Also clears comments and configspec.
        
        Leaves other attributes alone :
            depth/main/parent are not affected
        """
        dict.clear(self)
        self.scalars = []
        self.sections = []
        self.comments = {}
        self.inline_comments = {}
        self.configspec = {}

    def setdefault(self, key, default=None):
        """A version of setdefault that sets sequence if appropriate."""
        try:
            return self[key]
        except KeyError:
            self[key] = default
            return self[key]

    def items(self):
        """ """
        return zip((self.scalars + self.sections), self.values())

    def keys(self):
        """ """
        return (self.scalars + self.sections)

    def values(self):
        """ """
        return [self[key] for key in (self.scalars + self.sections)]

    def iteritems(self):
        """ """
        return iter(self.items())

    def iterkeys(self):
        """ """
        return iter((self.scalars + self.sections))

    __iter__ = iterkeys

    def itervalues(self):
        """ """
        return iter(self.values())

    def __repr__(self):
        return '{%s}' % ', '.join([('%s: %s' % (repr(key), repr(self[key])))
            for key in (self.scalars + self.sections)])

    __str__ = __repr__

    # Extra methods - not in a normal dictionary

    def dict(self):
        """
        Return a deepcopy of self as a dictionary.
        
        All members that are ``Section`` instances are recursively turned to
        ordinary dictionaries - by calling their ``dict`` method.
        
        >>> n = a.dict()
        >>> n == a
        1
        >>> n is a
        0
        """
        newdict = {}
        for entry in self:
            this_entry = self[entry]
            if isinstance(this_entry, Section):
                this_entry = this_entry.dict()
            elif isinstance(this_entry, list):
                # create a copy rather than a reference
                this_entry = list(this_entry)
            elif isinstance(this_entry, tuple):
                # create a copy rather than a reference
                this_entry = tuple(this_entry)
            newdict[entry] = this_entry
        return newdict

    def merge(self, indict):
        """
        A recursive update - useful for merging config files.
        
        >>> a = '''[section1]
        ...     option1 = True
        ...     [[subsection]]
        ...     more_options = False
        ...     # end of file'''.splitlines()
        >>> b = '''# File is user.ini
        ...     [section1]
        ...     option1 = False
        ...     # end of file'''.splitlines()
        >>> c1 = ConfigObj(b)
        >>> c2 = ConfigObj(a)
        >>> c2.merge(c1)
        >>> c2
        {'section1': {'option1': 'False', 'subsection': {'more_options': 'False'}}}
        """
        for key, val in indict.items():
            if (key in self and isinstance(self[key], dict) and
                                isinstance(val, dict)):
                self[key].merge(val)
            else:   
                self[key] = val

    def rename(self, oldkey, newkey):
        """
        Change a keyname to another, without changing position in sequence.
        
        Implemented so that transformations can be made on keys,
        as well as on values. (used by encode and decode)
        
        Also renames comments.
        """
        if oldkey in self.scalars:
            the_list = self.scalars
        elif oldkey in self.sections:
            the_list = self.sections
        else:
            raise KeyError, 'Key "%s" not found.' % oldkey
        pos = the_list.index(oldkey)
        #
        val = self[oldkey]
        dict.__delitem__(self, oldkey)
        dict.__setitem__(self, newkey, val)
        the_list.remove(oldkey)
        the_list.insert(pos, newkey)
        comm = self.comments[oldkey]
        inline_comment = self.inline_comments[oldkey]
        del self.comments[oldkey]
        del self.inline_comments[oldkey]
        self.comments[newkey] = comm
        self.inline_comments[newkey] = inline_comment

    def walk(self, function, raise_errors=True,
            call_on_sections=False, **keywargs):
        """
        Walk every member and call a function on the keyword and value.
        
        Return a dictionary of the return values
        
        If the function raises an exception, raise the errror
        unless ``raise_errors=False``, in which case set the return value to
        ``False``.
        
        Any unrecognised keyword arguments you pass to walk, will be pased on
        to the function you pass in.
        
        Note: if ``call_on_sections`` is ``True`` then - on encountering a
        subsection, *first* the function is called for the *whole* subsection,
        and then recurses into its members. This means your function must be
        able to handle strings, dictionaries and lists. This allows you
        to change the key of subsections as well as for ordinary members. The
        return value when called on the whole subsection has to be discarded.
        
        See  the encode and decode methods for examples, including functions.
        
        .. caution::
        
            You can use ``walk`` to transform the names of members of a section
            but you mustn't add or delete members.
        
        >>> config = '''[XXXXsection]
        ... XXXXkey = XXXXvalue'''.splitlines()
        >>> cfg = ConfigObj(config)
        >>> cfg
        {'XXXXsection': {'XXXXkey': 'XXXXvalue'}}
        >>> def transform(section, key):
        ...     val = section[key]
        ...     newkey = key.replace('XXXX', 'CLIENT1')
        ...     section.rename(key, newkey)
        ...     if isinstance(val, (tuple, list, dict)):
        ...         pass
        ...     else:
        ...         val = val.replace('XXXX', 'CLIENT1')
        ...         section[newkey] = val
        >>> cfg.walk(transform, call_on_sections=True)
        {'CLIENT1section': {'CLIENT1key': None}}
        >>> cfg
        {'CLIENT1section': {'CLIENT1key': 'CLIENT1value'}}
        """
        out = {}
        # scalars first
        for i in range(len(self.scalars)):
            entry = self.scalars[i]
            try:
                val = function(self, entry, **keywargs)
                # bound again in case name has changed
                entry = self.scalars[i]
                out[entry] = val
            except Exception:
                if raise_errors:
                    raise
                else:
                    entry = self.scalars[i]
                    out[entry] = False
        # then sections
        for i in range(len(self.sections)):
            entry = self.sections[i]
            if call_on_sections:
                try:
                    function(self, entry, **keywargs)
                except Exception:
                    if raise_errors:
                        raise
                    else:
                        entry = self.sections[i]
                        out[entry] = False
                # bound again in case name has changed
                entry = self.sections[i]
            # previous result is discarded
            out[entry] = self[entry].walk(
                function,
                raise_errors=raise_errors,
                call_on_sections=call_on_sections,
                **keywargs)
        return out

    def decode(self, encoding):
        """
        Decode all strings and values to unicode, using the specified encoding.
        
        Works with subsections and list values.
        
        Uses the ``walk`` method.
        
        Testing ``encode`` and ``decode``.
        >>> m = ConfigObj(a)
        >>> m.decode('ascii')
        >>> def testuni(val):
        ...     for entry in val:
        ...         if not isinstance(entry, unicode):
        ...             print >> sys.stderr, type(entry)
        ...             raise AssertionError, 'decode failed.'
        ...         if isinstance(val[entry], dict):
        ...             testuni(val[entry])
        ...         elif not isinstance(val[entry], unicode):
        ...             raise AssertionError, 'decode failed.'
        >>> testuni(m)
        >>> m.encode('ascii')
        >>> a == m
        1
        """
        warn('use of ``decode`` is deprecated.', DeprecationWarning)
        def decode(section, key, encoding=encoding, warn=True):
            """ """
            val = section[key]
            if isinstance(val, (list, tuple)):
                newval = []
                for entry in val:
                    newval.append(entry.decode(encoding))
            elif isinstance(val, dict):
                newval = val
            else:
                newval = val.decode(encoding)
            newkey = key.decode(encoding)
            section.rename(key, newkey)
            section[newkey] = newval
        # using ``call_on_sections`` allows us to modify section names
        self.walk(decode, call_on_sections=True)

    def encode(self, encoding):
        """
        Encode all strings and values from unicode,
        using the specified encoding.
        
        Works with subsections and list values.
        Uses the ``walk`` method.
        """
        warn('use of ``encode`` is deprecated.', DeprecationWarning)
        def encode(section, key, encoding=encoding):
            """ """
            val = section[key]
            if isinstance(val, (list, tuple)):
                newval = []
                for entry in val:
                    newval.append(entry.encode(encoding))
            elif isinstance(val, dict):
                newval = val
            else:
                newval = val.encode(encoding)
            newkey = key.encode(encoding)
            section.rename(key, newkey)
            section[newkey] = newval
        self.walk(encode, call_on_sections=True)

    def istrue(self, key):
        """A deprecated version of ``as_bool``."""
        warn('use of ``istrue`` is deprecated. Use ``as_bool`` method '
                'instead.', DeprecationWarning)
        return self.as_bool(key)

    def as_bool(self, key):
        """
        Accepts a key as input. The corresponding value must be a string or
        the objects (``True`` or 1) or (``False`` or 0). We allow 0 and 1 to
        retain compatibility with Python 2.2.
        
        If the string is one of  ``True``, ``On``, ``Yes``, or ``1`` it returns 
        ``True``.
        
        If the string is one of  ``False``, ``Off``, ``No``, or ``0`` it returns 
        ``False``.
        
        ``as_bool`` is not case sensitive.
        
        Any other input will raise a ``ValueError``.
        
        >>> a = ConfigObj()
        >>> a['a'] = 'fish'
        >>> a.as_bool('a')
        Traceback (most recent call last):
        ValueError: Value "fish" is neither True nor False
        >>> a['b'] = 'True'
        >>> a.as_bool('b')
        1
        >>> a['b'] = 'off'
        >>> a.as_bool('b')
        0
        """
        val = self[key]
        if val == True:
            return True
        elif val == False:
            return False
        else:
            try:
                if not isinstance(val, StringTypes):
                    raise KeyError
                else:
                    return self.main._bools[val.lower()]
            except KeyError:
                raise ValueError('Value "%s" is neither True nor False' % val)

    def as_int(self, key):
        """
        A convenience method which coerces the specified value to an integer.
        
        If the value is an invalid literal for ``int``, a ``ValueError`` will
        be raised.
        
        >>> a = ConfigObj()
        >>> a['a'] = 'fish'
        >>> a.as_int('a')
        Traceback (most recent call last):
        ValueError: invalid literal for int(): fish
        >>> a['b'] = '1'
        >>> a.as_int('b')
        1
        >>> a['b'] = '3.2'
        >>> a.as_int('b')
        Traceback (most recent call last):
        ValueError: invalid literal for int(): 3.2
        """
        return int(self[key])

    def as_float(self, key):
        """
        A convenience method which coerces the specified value to a float.
        
        If the value is an invalid literal for ``float``, a ``ValueError`` will
        be raised.
        
        >>> a = ConfigObj()
        >>> a['a'] = 'fish'
        >>> a.as_float('a')
        Traceback (most recent call last):
        ValueError: invalid literal for float(): fish
        >>> a['b'] = '1'
        >>> a.as_float('b')
        1.0
        >>> a['b'] = '3.2'
        >>> a.as_float('b')
        3.2000000000000002
        """
        return float(self[key])
    

class ConfigObj(Section):
    """An object to read, create, and write config files."""

    _keyword = re.compile(r'''^ # line start
        (\s*)                   # indentation
        (                       # keyword
            (?:".*?")|          # double quotes
            (?:'.*?')|          # single quotes
            (?:[^'"=].*?)       # no quotes
        )
        \s*=\s*                 # divider
        (.*)                    # value (including list values and comments)
        $   # line end
        ''',
        re.VERBOSE)

    _sectionmarker = re.compile(r'''^
        (\s*)                     # 1: indentation
        ((?:\[\s*)+)              # 2: section marker open
        (                         # 3: section name open
            (?:"\s*\S.*?\s*")|    # at least one non-space with double quotes
            (?:'\s*\S.*?\s*')|    # at least one non-space with single quotes
            (?:[^'"\s].*?)        # at least one non-space unquoted
        )                         # section name close
        ((?:\s*\])+)              # 4: section marker close
        \s*(\#.*)?                # 5: optional comment
        $''',
        re.VERBOSE)

    # this regexp pulls list values out as a single string
    # or single values and comments
    # FIXME: this regex adds a '' to the end of comma terminated lists
    #   workaround in ``_handle_value``
    _valueexp = re.compile(r'''^
        (?:
            (?:
                (
                    (?:
                        (?:
                            (?:".*?")|              # double quotes
                            (?:'.*?')|              # single quotes
                            (?:[^'",\#][^,\#]*?)    # unquoted
                        )
                        \s*,\s*                     # comma
                    )*      # match all list items ending in a comma (if any)
                )
                (
                    (?:".*?")|                      # double quotes
                    (?:'.*?')|                      # single quotes
                    (?:[^'",\#\s][^,]*?)|           # unquoted
                    (?:(?<!,))                      # Empty value
                )?          # last item in a list - or string value
            )|
            (,)             # alternatively a single comma - empty list
        )
        \s*(\#.*)?          # optional comment
        $''',
        re.VERBOSE)

    # use findall to get the members of a list value
    _listvalueexp = re.compile(r'''
        (
            (?:".*?")|          # double quotes
            (?:'.*?')|          # single quotes
            (?:[^'",\#].*?)       # unquoted
        )
        \s*,\s*                 # comma
        ''',
        re.VERBOSE)

    # this regexp is used for the value
    # when lists are switched off
    _nolistvalue = re.compile(r'''^
        (
            (?:".*?")|          # double quotes
            (?:'.*?')|          # single quotes
            (?:[^'"\#].*?)|     # unquoted
            (?:)                # Empty value
        )
        \s*(\#.*)?              # optional comment
        $''',
        re.VERBOSE)

    # regexes for finding triple quoted values on one line
    _single_line_single = re.compile(r"^'''(.*?)'''\s*(#.*)?$")
    _single_line_double = re.compile(r'^"""(.*?)"""\s*(#.*)?$')
    _multi_line_single = re.compile(r"^(.*?)'''\s*(#.*)?$")
    _multi_line_double = re.compile(r'^(.*?)"""\s*(#.*)?$')

    _triple_quote = {
        "'''": (_single_line_single, _multi_line_single),
        '"""': (_single_line_double, _multi_line_double),
    }

    # Used by the ``istrue`` Section method
    _bools = {
        'yes': True, 'no': False,
        'on': True, 'off': False,
        '1': True, '0': False,
        'true': True, 'false': False,
        }

    def __init__(self, infile=None, options=None, **kwargs):
        """
        Parse or create a config file object.
        
        ``ConfigObj(infile=None, options=None, **kwargs)``
        """
        if infile is None:
            infile = []
        if options is None:
            options = {}
        else:
            options = dict(options)
        # keyword arguments take precedence over an options dictionary
        options.update(kwargs)
        # init the superclass
        Section.__init__(self, self, 0, self)
        #
        defaults = OPTION_DEFAULTS.copy()
        for entry in options.keys():
            if entry not in defaults.keys():
                raise TypeError, 'Unrecognised option "%s".' % entry
        # TODO: check the values too.
        #
        # Add any explicit options to the defaults
        defaults.update(options)
        #
        # initialise a few variables
        self.filename = None
        self._errors = []
        self.raise_errors = defaults['raise_errors']
        self.interpolation = defaults['interpolation']
        self.list_values = defaults['list_values']
        self.create_empty = defaults['create_empty']
        self.file_error = defaults['file_error']
        self.stringify = defaults['stringify']
        self.indent_type = defaults['indent_type']
        self.encoding = defaults['encoding']
        self.default_encoding = defaults['default_encoding']
        self.BOM = False
        self.newlines = None
        self.write_empty_values = defaults['write_empty_values']
        self.unrepr = defaults['unrepr']
        #
        self.initial_comment = []
        self.final_comment = []
        #
        self._terminated = False
        #
        if isinstance(infile, StringTypes):
            self.filename = infile
            if os.path.isfile(infile):
                infile = open(infile).read() or []
            elif self.file_error:
                # raise an error if the file doesn't exist
                raise IOError, 'Config file not found: "%s".' % self.filename
            else:
                # file doesn't already exist
                if self.create_empty:
                    # this is a good test that the filename specified
                    # isn't impossible - like on a non existent device
                    h = open(infile, 'w')
                    h.write('')
                    h.close()
                infile = []
        elif isinstance(infile, (list, tuple)):
            infile = list(infile)
        elif isinstance(infile, dict):
            # initialise self
            # the Section class handles creating subsections
            if isinstance(infile, ConfigObj):
                # get a copy of our ConfigObj
                infile = infile.dict()
            for entry in infile:
                self[entry] = infile[entry]
            del self._errors
            if defaults['configspec'] is not None:
                self._handle_configspec(defaults['configspec'])
            else:
                self.configspec = None
            return
        elif hasattr(infile, 'read'):
            # This supports file like objects
            infile = infile.read() or []
            # needs splitting into lines - but needs doing *after* decoding
            # in case it's not an 8 bit encoding
        else:
            raise TypeError, ('infile must be a filename,'
                ' file like object, or list of lines.')
        #
        if infile:
            # don't do it for the empty ConfigObj
            infile = self._handle_bom(infile)
            # infile is now *always* a list
            #
            # Set the newlines attribute (first line ending it finds)
            # and strip trailing '\n' or '\r' from lines
            for line in infile:
                if (not line) or (line[-1] not in ('\r', '\n', '\r\n')):
                    continue
                for end in ('\r\n', '\n', '\r'):
                    if line.endswith(end):
                        self.newlines = end
                        break
                break
            if infile[-1] and infile[-1] in ('\r', '\n', '\r\n'):
                self._terminated = True
            infile = [line.rstrip('\r\n') for line in infile]
        #
        self._parse(infile)
        # if we had any errors, now is the time to raise them
        if self._errors:
            info = "at line %s." % self._errors[0].line_number
            if len(self._errors) > 1:
                msg = ("Parsing failed with several errors.\nFirst error %s" %
                    info)
                error = ConfigObjError(msg)
            else:
                error = self._errors[0]
            # set the errors attribute; it's a list of tuples:
            # (error_type, message, line_number)
            error.errors = self._errors
            # set the config attribute
            error.config = self
            raise error
        # delete private attributes
        del self._errors
        #
        if defaults['configspec'] is None:
            self.configspec = None
        else:
            self._handle_configspec(defaults['configspec'])
    
    def __repr__(self):
        return 'ConfigObj({%s})' % ', '.join(
            [('%s: %s' % (repr(key), repr(self[key]))) for key in
            (self.scalars + self.sections)])
    
    def _handle_bom(self, infile):
        """
        Handle any BOM, and decode if necessary.
        
        If an encoding is specified, that *must* be used - but the BOM should
        still be removed (and the BOM attribute set).
        
        (If the encoding is wrongly specified, then a BOM for an alternative
        encoding won't be discovered or removed.)
        
        If an encoding is not specified, UTF8 or UTF16 BOM will be detected and
        removed. The BOM attribute will be set. UTF16 will be decoded to
        unicode.
        
        NOTE: This method must not be called with an empty ``infile``.
        
        Specifying the *wrong* encoding is likely to cause a
        ``UnicodeDecodeError``.
        
        ``infile`` must always be returned as a list of lines, but may be
        passed in as a single string.
        """
        if ((self.encoding is not None) and
            (self.encoding.lower() not in BOM_LIST)):
            # No need to check for a BOM
            # the encoding specified doesn't have one
            # just decode
            return self._decode(infile, self.encoding)
        #
        if isinstance(infile, (list, tuple)):
            line = infile[0]
        else:
            line = infile
        if self.encoding is not None:
            # encoding explicitly supplied
            # And it could have an associated BOM
            # TODO: if encoding is just UTF16 - we ought to check for both
            # TODO: big endian and little endian versions.
            enc = BOM_LIST[self.encoding.lower()]
            if enc == 'utf_16':
                # For UTF16 we try big endian and little endian
                for BOM, (encoding, final_encoding) in BOMS.items():
                    if not final_encoding:
                        # skip UTF8
                        continue
                    if infile.startswith(BOM):
                        ### BOM discovered
                        ##self.BOM = True
                        # Don't need to remove BOM
                        return self._decode(infile, encoding)
                #
                # If we get this far, will *probably* raise a DecodeError
                # As it doesn't appear to start with a BOM
                return self._decode(infile, self.encoding)
            #
            # Must be UTF8
            BOM = BOM_SET[enc]
            if not line.startswith(BOM):
                return self._decode(infile, self.encoding)
            #
            newline = line[len(BOM):]
            #
            # BOM removed
            if isinstance(infile, (list, tuple)):
                infile[0] = newline
            else:
                infile = newline
            self.BOM = True
            return self._decode(infile, self.encoding)
        #
        # No encoding specified - so we need to check for UTF8/UTF16
        for BOM, (encoding, final_encoding) in BOMS.items():
            if not line.startswith(BOM):
                continue
            else:
                # BOM discovered
                self.encoding = final_encoding
                if not final_encoding:
                    self.BOM = True
                    # UTF8
                    # remove BOM
                    newline = line[len(BOM):]
                    if isinstance(infile, (list, tuple)):
                        infile[0] = newline
                    else:
                        infile = newline
                    # UTF8 - don't decode
                    if isinstance(infile, StringTypes):
                        return infile.splitlines(True)
                    else:
                        return infile
                # UTF16 - have to decode
                return self._decode(infile, encoding)
        #
        # No BOM discovered and no encoding specified, just return
        if isinstance(infile, StringTypes):
            # infile read from a file will be a single string
            return infile.splitlines(True)
        else:
            return infile

    def _a_to_u(self, aString):
        """Decode ASCII strings to unicode if a self.encoding is specified."""
        if self.encoding:
            return aString.decode('ascii')
        else:
            return aString

    def _decode(self, infile, encoding):
        """
        Decode infile to unicode. Using the specified encoding.
        
        if is a string, it also needs converting to a list.
        """
        if isinstance(infile, StringTypes):
            # can't be unicode
            # NOTE: Could raise a ``UnicodeDecodeError``
            return infile.decode(encoding).splitlines(True)
        for i, line in enumerate(infile):
            if not isinstance(line, unicode):
                # NOTE: The isinstance test here handles mixed lists of unicode/string
                # NOTE: But the decode will break on any non-string values
                # NOTE: Or could raise a ``UnicodeDecodeError``
                infile[i] = line.decode(encoding)
        return infile

    def _decode_element(self, line):
        """Decode element to unicode if necessary."""
        if not self.encoding:
            return line
        if isinstance(line, str) and self.default_encoding:
            return line.decode(self.default_encoding)
        return line

    def _str(self, value):
        """
        Used by ``stringify`` within validate, to turn non-string values
        into strings.
        """
        if not isinstance(value, StringTypes):
            return str(value)
        else:
            return value

    def _parse(self, infile):
        """Actually parse the config file."""
        temp_list_values = self.list_values
        if self.unrepr:
            self.list_values = False
        comment_list = []
        done_start = False
        this_section = self
        maxline = len(infile) - 1
        cur_index = -1
        reset_comment = False
        while cur_index < maxline:
            if reset_comment:
                comment_list = []
            cur_index += 1
            line = infile[cur_index]
            sline = line.strip()
            # do we have anything on the line ?
            if not sline or sline.startswith('#') or sline.startswith(';'):
                reset_comment = False
                comment_list.append(line)
                continue
            if not done_start:
                # preserve initial comment
                self.initial_comment = comment_list
                comment_list = []
                done_start = True
            reset_comment = True
            # first we check if it's a section marker
            mat = self._sectionmarker.match(line)
            if mat is not None:
                # is a section line
                (indent, sect_open, sect_name, sect_close, comment) = (
                    mat.groups())
                if indent and (self.indent_type is None):
                    self.indent_type = indent
                cur_depth = sect_open.count('[')
                if cur_depth != sect_close.count(']'):
                    self._handle_error(
                        "Cannot compute the section depth at …

Large files files are truncated, but you can click here to view the full file