""" Locale support.

    The module provides low-level access to the C lib's locale APIs

    and adds high level number formatting APIs as well as a locale

    aliasing engine to complement these.

    The aliasing engine includes support for many commonly used locale

    names and maps them to values suitable for passing to the C lib's

    setlocale() function. It also includes default encodings for all

    supported locale names.

"""

import sys, encodings, encodings.aliases

# Try importing the _locale module.

#

# If this fails, fall back on a basic 'C' locale emulation.

# Yuck:  LC_MESSAGES is non-standard:  can't tell whether it exists before

# trying the import.  So __all__ is also fiddled at the end of the file.

__all__ = ["getlocale", "getdefaultlocale", "getpreferredencoding", "Error",

           "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",

           "str", "atof", "atoi", "format", "format_string", "currency",

           "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",

           "LC_NUMERIC", "LC_ALL", "CHAR_MAX"]

try:

    from _locale import *

except ImportError:

    # Locale emulation

    CHAR_MAX = 127

    LC_ALL = 6

    LC_COLLATE = 3

    LC_CTYPE = 0

    LC_MESSAGES = 5

    LC_MONETARY = 4

    LC_NUMERIC = 1

    LC_TIME = 2

    Error = ValueError

    def localeconv():

        """ localeconv() -> dict.

            Returns numeric and monetary locale-specific parameters.

        """

        # 'C' locale default values

        return {'grouping': [127],

                'currency_symbol': '',

                'n_sign_posn': 127,

                'p_cs_precedes': 127,

                'n_cs_precedes': 127,

                'mon_grouping': [],

                'n_sep_by_space': 127,

                'decimal_point': '.',

                'negative_sign': '',

                'positive_sign': '',

                'p_sep_by_space': 127,

                'int_curr_symbol': '',

                'p_sign_posn': 127,

                'thousands_sep': '',

                'mon_thousands_sep': '',

                'frac_digits': 127,

                'mon_decimal_point': '',

                'int_frac_digits': 127}

    def setlocale(category, value=None):

        """ setlocale(integer,string=None) -> string.

            Activates/queries locale processing.

        """

        if value not in (None, '', 'C'):

            raise Error, '_locale emulation only supports "C" locale'

        return 'C'

    def strcoll(a,b):

        """ strcoll(string,string) -> int.

            Compares two strings according to the locale.

        """

        return cmp(a,b)

    def strxfrm(s):

        """ strxfrm(string) -> string.

            Returns a string that behaves for cmp locale-aware.

        """

        return s

### Number formatting APIs

# Author: Martin von Loewis

# improved by Georg Brandl

#perform the grouping from right to left

def _group(s, monetary=False):

    conv = localeconv()

    thousands_sep = conv[monetary and 'mon_thousands_sep' or 'thousands_sep']

    grouping = conv[monetary and 'mon_grouping' or 'grouping']

    if not grouping:

        return (s, 0)

    result = ""

    seps = 0

    spaces = ""

    if s[-1] == ' ':

        sp = s.find(' ')

        spaces = s[sp:]

        s = s[:sp]

    while s and grouping:

        # if grouping is -1, we are done

        if grouping[0] == CHAR_MAX:

            break

        # 0: re-use last group ad infinitum

        elif grouping[0] != 0:

            #process last group

            group = grouping[0]

            grouping = grouping[1:]

        if result:

            result = s[-group:] + thousands_sep + result

            seps += 1

        else:

            result = s[-group:]

        s = s[:-group]

        if s and s[-1] not in "0123456789":

            # the leading string is only spaces and signs

            return s + result + spaces, seps

    if not result:

        return s + spaces, seps

    if s:

        result = s + thousands_sep + result

        seps += 1

    return result + spaces, seps

def format(percent, value, grouping=False, monetary=False, *additional):

    """Returns the locale-aware substitution of a %? specifier

    (percent).

    additional is for format strings which contain one or more

    '*' modifiers."""

    # this is only for one-percent-specifier strings and this should be checked

    if percent[0] != '%':

        raise ValueError("format() must be given exactly one %char "

                         "format specifier")

    if additional:

        formatted = percent % ((value,) + additional)

    else:

        formatted = percent % value

    # floats and decimal ints need special action!

    if percent[-1] in 'eEfFgG':

        seps = 0

        parts = formatted.split('.')

        if grouping:

            parts[0], seps = _group(parts[0], monetary=monetary)

        decimal_point = localeconv()[monetary and 'mon_decimal_point'

                                              or 'decimal_point']

        formatted = decimal_point.join(parts)

        while seps:

            sp = formatted.find(' ')

            if sp == -1: break

            formatted = formatted[:sp] + formatted[sp+1:]

            seps -= 1

    elif percent[-1] in 'diu':

        if grouping:

            formatted = _group(formatted, monetary=monetary)[0]

    return formatted

import re, operator

_percent_re = re.compile(r'%(?:\((?P<key>.*?)\))?'

                         r'(?P<modifiers>[-#0-9 +*.hlL]*?)[eEfFgGdiouxXcrs%]')

def format_string(f, val, grouping=False):

    """Formats a string in the same way that the % formatting would use,

    but takes the current locale into account.

    Grouping is applied if the third parameter is true."""

    percents = list(_percent_re.finditer(f))

    new_f = _percent_re.sub('%s', f)

    if isinstance(val, tuple):

        new_val = list(val)

        i = 0

        for perc in percents:

            starcount = perc.group('modifiers').count('*')

            new_val[i] = format(perc.group(), new_val[i], grouping, False, *new_val[i+1:i+1+starcount])

            del new_val[i+1:i+1+starcount]

            i += (1 + starcount)

        val = tuple(new_val)

    elif operator.isMappingType(val):

        for perc in percents:

            key = perc.group("key")

            val[key] = format(perc.group(), val[key], grouping)

    else:

        # val is a single value

        val = format(percents[0].group(), val, grouping)

    return new_f % val

def currency(val, symbol=True, grouping=False, international=False):

    """Formats val according to the currency settings

    in the current locale."""

    conv = localeconv()

    # check for illegal values

    digits = conv[international and 'int_frac_digits' or 'frac_digits']

    if digits == 127:

        raise ValueError("Currency formatting is not possible using "

                         "the 'C' locale.")

    s = format('%%.%if' % digits, abs(val), grouping, monetary=True)

    # '<' and '>' are markers if the sign must be inserted between symbol and value

    s = '<' + s + '>'

    if symbol:

        smb = conv[international and 'int_curr_symbol' or 'currency_symbol']

        precedes = conv[val<0 and 'n_cs_precedes' or 'p_cs_precedes']

        separated = conv[val<0 and 'n_sep_by_space' or 'p_sep_by_space']

        if precedes:

            s = smb + (separated and ' ' or '') + s

        else:

            s = s + (separated and ' ' or '') + smb

    sign_pos = conv[val<0 and 'n_sign_posn' or 'p_sign_posn']

    sign = conv[val<0 and 'negative_sign' or 'positive_sign']

    if sign_pos == 0:

        s = '(' + s + ')'

    elif sign_pos == 1:

        s = sign + s

    elif sign_pos == 2:

        s = s + sign

    elif sign_pos == 3:

        s = s.replace('<', sign)

    elif sign_pos == 4:

        s = s.replace('>', sign)

    else:

        # the default if nothing specified;

        # this should be the most fitting sign position

        s = sign + s

    return s.replace('<', '').replace('>', '')

def str(val):

    """Convert float to integer, taking the locale into account."""

    return format("%.12g", val)

def atof(string, func=float):

    "Parses a string as a float according to the locale settings."

    #First, get rid of the grouping

    ts = localeconv()['thousands_sep']

    if ts:

        string = string.replace(ts, '')

    #next, replace the decimal point with a dot

    dd = localeconv()['decimal_point']

    if dd:

        string = string.replace(dd, '.')

    #finally, parse the string

    return func(string)

def atoi(str):

    "Converts a string to an integer according to the locale settings."

    return atof(str, int)

def _test():

    setlocale(LC_ALL, "")

    #do grouping

    s1 = format("%d", 123456789,1)

    print s1, "is", atoi(s1)

    #standard formatting

    s1 = str(3.14)

    print s1, "is", atof(s1)

### Locale name aliasing engine

# Author: Marc-Andre Lemburg, mal@lemburg.com

# Various tweaks by Fredrik Lundh <fredrik@pythonware.com>

# store away the low-level version of setlocale (it's

# overridden below)

_setlocale = setlocale

def normalize(localename):

    """ Returns a normalized locale code for the given locale

        name.

        The returned locale code is formatted for use with

        setlocale().

        If normalization fails, the original name is returned

        unchanged.

        If the given encoding is not known, the function defaults to

        the default encoding for the locale code just like setlocale()

        does.

    """

    # Normalize the locale name and extract the encoding

    fullname = localename.lower()

    if ':' in fullname:

        # ':' is sometimes used as encoding delimiter.

        fullname = fullname.replace(':', '.')

    if '.' in fullname:

        langname, encoding = fullname.split('.')[:2]

        fullname = langname + '.' + encoding

    else:

        langname = fullname

        encoding = ''

    # First lookup: fullname (possibly with encoding)

    norm_encoding = encoding.replace('-', '')

    norm_encoding = norm_encoding.replace('_', '')

    lookup_name = langname + '.' + encoding

    code = locale_alias.get(lookup_name, None)

    if code is not None:

        return code

    #print 'first lookup failed'

    # Second try: langname (without encoding)

    code = locale_alias.get(langname, None)

    if code is not None:

        #print 'langname lookup succeeded'

        if '.' in code:

            langname, defenc = code.split('.')

        else:

            langname = code

            defenc = ''

        if encoding:

            # Convert the encoding to a C lib compatible encoding string

            norm_encoding = encodings.normalize_encoding(encoding)

            #print 'norm encoding: %r' % norm_encoding

            norm_encoding = encodings.aliases.aliases.get(norm_encoding,

                                                          norm_encoding)

            #print 'aliased encoding: %r' % norm_encoding

            encoding = locale_encoding_alias.get(norm_encoding,

                                                 norm_encoding)

        else:

            encoding = defenc

        #print 'found encoding %r' % encoding

        if encoding:

            return langname + '.' + encoding

        else:

            return langname

    else:

        return localename

def _parse_localename(localename):

    """ Parses the locale code for localename and returns the

        result as tuple (language code, encoding).

        The localename is normalized and passed through the locale

        alias engine. A ValueError is raised in case the locale name

        cannot be parsed.

        The language code corresponds to RFC 1766.  code and encoding

        can be None in case the values cannot be determined or are

        unknown to this implementation.

    """

    code = normalize(localename)

    if '@' in code:

        # Deal with locale modifiers

        code, modifier = code.split('@')

        if modifier == 'euro' and '.' not in code:

            # Assume Latin-9 for @euro locales. This is bogus,

            # since some systems may use other encodings for these

            # locales. Also, we ignore other modifiers.

            return code, 'iso-8859-15'

    if '.' in code:

        return tuple(code.split('.')[:2])

    elif code == 'C':

        return None, None

    raise ValueError, 'unknown locale: %s' % localename

def _build_localename(localetuple):

    """ Builds a locale code from the given tuple (language code,

        encoding).

        No aliasing or normalizing takes place.

    """

    language, encoding = localetuple

    if language is None:

        language = 'C'

    if encoding is None:

        return language

    else:

        return language + '.' + encoding

def getdefaultlocale(envvars=('LC_ALL', 'LC_CTYPE', 'LANG', 'LANGUAGE')):

    """ Tries to determine the default locale settings and returns

        them as tuple (language code, encoding).

        According to POSIX, a program which has not called

        setlocale(LC_ALL, "") runs using the portable 'C' locale.

        Calling setlocale(LC_ALL, "") lets it use the default locale as

        defined by the LANG variable. Since we don't want to interfere

        with the current locale setting we thus emulate the behavior

        in the way described above.

        To maintain compatibility with other platforms, not only the

        LANG variable is tested, but a list of variables given as

        envvars parameter. The first found to be defined will be

        used. envvars defaults to the search path used in GNU gettext;

        it must always contain the variable name 'LANG'.

        Except for the code 'C', the language code corresponds to RFC

        1766.  code and encoding can be None in case the values cannot

        be determined.

    """

    try:

        # check if it's supported by the _locale module

        import _locale

        code, encoding = _locale._getdefaultlocale()

    except (ImportError, AttributeError):

        pass

    else:

        # make sure the code/encoding values are valid

        if sys.platform == "win32" and code and code[:2] == "0x":

            # map windows language identifier to language name

            code = windows_locale.get(int(code, 0))

        # ...add other platform-specific processing here, if

        # necessary...

        return code, encoding

    # fall back on POSIX behaviour

    import os

    lookup = os.environ.get

    for variable in envvars:

        localename = lookup(variable,None)

        if localename:

            if variable == 'LANGUAGE':

                localename = localename.split(':')[0]

            break

    else:

        localename = 'C'

    return _parse_localename(localename)

def getlocale(category=LC_CTYPE):

    """ Returns the current setting for the given locale category as

        tuple (language code, encoding).

        category may be one of the LC_* value except LC_ALL. It

        defaults to LC_CTYPE.

        Except for the code 'C', the language code corresponds to RFC

        1766.  code and encoding can be None in case the values cannot

        be determined.

    """

    localename = _setlocale(category)

    if category == LC_ALL and ';' in localename:

        raise TypeError, 'category LC_ALL is not supported'

    return _parse_localename(localename)

def setlocale(category, locale=None):

    """ Set the locale for the given category.  The locale can be

        a string, a locale tuple (language code, encoding), or None.

        Locale tuples are converted to strings the locale aliasing

        engine.  Locale strings are passed directly to the C lib.

        category may be given as one of the LC_* values.

    """

    if locale and type(locale) is not type(""):

        # convert to string

        locale = normalize(_build_localename(locale))

    return _setlocale(category, locale)

def resetlocale(category=LC_ALL):

    """ Sets the locale for category to the default setting.

        The default setting is determined by calling

        getdefaultlocale(). category defaults to LC_ALL.

    """

    _setlocale(category, _build_localename(getdefaultlocale()))

if sys.platform in ('win32', 'darwin', 'mac'):

    # On Win32, this will return the ANSI code page

    # On the Mac, it should return the system encoding;

    # it might return "ascii" instead

    def getpreferredencoding(do_setlocale = True):

        """Return the charset that the user is likely using."""

        import _locale

        return _locale._getdefaultlocale()[1]

else:

    # On Unix, if CODESET is available, use that.

    try:

        CODESET

    except NameError:

        # Fall back to parsing environment variables :-(

        def getpreferredencoding(do_setlocale = True):

            """Return the charset that the user is likely using,

            by looking at environment variables."""

            return getdefaultlocale()[1]

    else:

        def getpreferredencoding(do_setlocale = True):

            """Return the charset that the user is likely using,

            according to the system configuration."""

            if do_setlocale:

                oldloc = setlocale(LC_CTYPE)

                setlocale(LC_CTYPE, "")

                result = nl_langinfo(CODESET)

                setlocale(LC_CTYPE, oldloc)

                return result

            else:

                return nl_langinfo(CODESET)

### Database

#

# The following data was extracted from the locale.alias file which

# comes with X11 and then hand edited removing the explicit encoding

# definitions and adding some more aliases. The file is usually

# available as /usr/lib/X11/locale/locale.alias.

#