root/coding.py

# coding: UTF-8
# Copyright (C) 2007, Stefan Schwarzer
#
# Permission is hereby granted, free of charge, to any person
# obtaining a copy of this software and associated documentation files
# (the "Software"), to deal in the Software without restriction,
# including without limitation the rights to use, copy, modify, merge,
# publish, distribute, sublicense, and/or sell copies of the Software,
# and to permit persons to whom the Software is furnished to do so,
# subject to the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

"""
Tools for converting between unicode strings and byte strings.
"""

# assume this encoding for all file names and their contents
DEFAULT_ENCODING = "UTF-8"

# the fallback encoding should be an 8-bit encoding
FALLBACK_ENCODING = "iso-8859-15"

def encode(unicode_string):
    r"""
    Return a byte string for the given `unicode_string`. Use the
    `DEFAULT_ENCODING`.

    >>> import unicodedata
    >>> encode(u"abc")
    'abc'
    >>> encode(unicodedata.lookup('LATIN SMALL LETTER A WITH DIAERESIS')
    ... + u"bc")
    '\xc3\xa4bc'
    """
    return unicode_string.encode(DEFAULT_ENCODING, 'replace')

def decode(byte_string):
    r"""
    Return a unicode string for the given `byte_string`. If the
    argument can't be decoded, decode with the `FALLBACK_ENCODING`
    instead.

    >>> import unicodedata
    >>> s = "\xc3\xa4bc"  # UTF-8, umlaut encoded in two bytes
    >>> u = decode(s)
    >>> len(u), unicodedata.name(u[0])
    (3, 'LATIN SMALL LETTER A WITH DIAERESIS')

    >>> s = "\xe4bc"  # ISO-8859-1, umlaut encoded in one byte
    >>> u = decode(s)
    >>> len(u), unicodedata.name(u[0])
    (3, 'LATIN SMALL LETTER A WITH DIAERESIS')
    """
    try:
        return byte_string.decode(DEFAULT_ENCODING)
    except UnicodeDecodeError:
        # 8-bit encoding, should always work
        return byte_string.decode(FALLBACK_ENCODING)