manyi/venv/Lib/site-packages/faker/utils/text.py

# coding=utf-8

import datetime
from decimal import Decimal
import re

import six
import unicodedata


_re_pattern = re.compile(r'[^\w\s-]', flags=re.U)
_re_pattern_allow_dots = re.compile(r'[^\.\w\s-]', flags=re.U)
_re_spaces = re.compile(r'[-\s]+', flags=re.U)


_PROTECTED_TYPES = six.integer_types + (
    type(None), float, Decimal,
    datetime.datetime, datetime.date, datetime.time,
)


def is_protected_type(obj):
    """Determine if the object instance is of a protected type.
    Objects of protected types are preserved as-is when passed to
    force_text(strings_only=True).
    """
    return isinstance(obj, _PROTECTED_TYPES)


def force_text(s, encoding='utf-8', strings_only=False, errors='strict'):
    """
    Similar to smart_text, except that lazy instances are resolved to
    strings, rather than kept as lazy objects.
    If strings_only is True, don't convert (some) non-string-like objects.
    """
    # Handle the common case first for performance reasons.
    if issubclass(type(s), six.text_type):
        return s
    if strings_only and is_protected_type(s):
        return s
    try:
        if not issubclass(type(s), six.string_types):
            if six.PY3:
                if isinstance(s, bytes):
                    s = six.text_type(s, encoding, errors)
                else:
                    s = six.text_type(s)
            elif hasattr(s, '__unicode__'):
                s = six.text_type(s)
            else:
                s = six.text_type(bytes(s), encoding, errors)
        else:
            # Note: We use .decode() here, instead of six.text_type(s, encoding,
            # errors), so that if s is a SafeBytes, it ends up being a
            # SafeText at the end.
            s = s.decode(encoding, errors)
    except UnicodeDecodeError as e:
        if not isinstance(s, Exception):
            raise ValueError(s, *e.args)
        else:
            # If we get to here, the caller has passed in an Exception
            # subclass populated with non-ASCII bytestring data without a
            # working unicode method. Try to handle this without raising a
            # further exception by individually forcing the exception args
            # to unicode.
            s = ' '.join(force_text(arg, encoding, strings_only, errors)
                         for arg in s)
    return s


def slugify(value, allow_dots=False, allow_unicode=False):
    """
    Converts to lowercase, removes non-word characters (alphanumerics and
    underscores) and converts spaces to hyphens. Also strips leading and
    trailing whitespace. Modified to optionally allow dots.

    Adapted from Django 1.9
    """
    if allow_dots:
        pattern = _re_pattern_allow_dots
    else:
        pattern = _re_pattern

    value = force_text(value)
    if allow_unicode:
        value = unicodedata.normalize('NFKC', value)
        value = pattern.sub('', value).strip().lower()
        return _re_spaces.sub('-', value)
    value = unicodedata.normalize('NFKD', value).encode(
        'ascii', 'ignore').decode('ascii')
    value = pattern.sub('', value).strip().lower()
    return _re_spaces.sub('-', value)