[Zope3-checkins] CVS: Zope3/src/zope/app/dublincore - dcsv.py:1.1

[Fred L. Drake, Jr.]

Update of /cvs-repository/Zope3/src/zope/app/dublincore
In directory cvs.zope.org:/tmp/cvs-serv9641

Added Files:
	dcsv.py 
Log Message:
preliminary support for Dublin Core Structured Values; need tests


=== Added File Zope3/src/zope/app/dublincore/dcsv.py ===
##############################################################################
#
# Copyright (c) 2003 Zope Corporation and Contributors.
# All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL).  A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE.
#
##############################################################################
"""Functions for working with Dublin Core Structured Value (DCSV) data.

DCSV is specified in 'DCMI DCSV: A syntax for writing a list of
labelled values in a text string', at:

http://dublincore.org/documents/dcmi-dcsv/

$Id: dcsv.py,v 1.1 2003/08/21 04:40:10 fdrake Exp $
"""

import re

__all__ = "encode", "decode"

try:
    basestring
except NameError:
    # define basestring in Python 2.2.x:
    try:
        unicode
    except NameError:
        basestring = str
    else:
        basestring = str, unicode


def encode(items):
    L = []
    for item in items:
        if isinstance(item, basestring):
            L.append(_encode_string(item) + ";")
        else:
            k, v = item
            if not isinstance(v, basestring):
                raise TypeError("values must be strings; found %r" % v)
            v = _encode_string(v)
            if k:
                if not isinstance(k, basestring):
                    raise TypeError("labels must be strings; found %r" % k)
                k = _encode_string(k)
                s = "%s=%s;" % (k, v)
            else:
                s = v + ";"
            L.append(s)
    return " ".join(L)

def _encode_string(s):
    return s.replace("\\", r"\\").replace(";", r"\;").replace("=", r"\=")


def decode(text):
    items = []
    text = text.strip()
    while text:
        m = _find_interesting(text)
        if m:
            prefix, char = m.group(1, 2)
            prefix = _decode_string(prefix).rstrip()
            if char == ";":
                items.append(('', prefix))
                text = text[m.end():].lstrip()
                continue
            else: # char == "="
                text = text[m.end():].lstrip()
            # else we have a label
            m = _find_value(text)
            if m:
                value = m.group(1)
                text = text[m.end():].rstrip()
            else:
                value = text
                text = ''
            items.append((prefix, _decode_string(value)))
        else:
            items.append(('', _decode_string(text)))
            break
    return items

_prefix = r"((?:[^;\\=]|\\[;\\=])*)"
_find_interesting = re.compile(_prefix + "([;=])").match
_find_value = re.compile(_prefix + ";").match

def _decode_string(s):
    if "\\" not in s:
        return s
    r = ""
    while s:
        c1 = s[0]
        if c1 == "\\":
            c2 = s[1:2]
            if not c2:
                return r + c1
            r += c2
            s = s[2:]
        else:
            r += c1
            s = s[1:]
    return r