Limnoria/src/utils.py

#!/usr/bin/env python

###
# Copyright (c) 2002, Jeremiah Fincher
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
#   * Redistributions of source code must retain the above copyright notice,
#     this list of conditions, and the following disclaimer.
#   * Redistributions in binary form must reproduce the above copyright notice,
#     this list of conditions, and the following disclaimer in the
#     documentation and/or other materials provided with the distribution.
#   * Neither the name of the author of this software nor the name of
#     contributors to this software may be used to endorse or promote products
#     derived from this software without specific prior written consent.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
###

"""
Simple utility functions.
"""

from fix import *

import sgmllib
import htmlentitydefs

class HtmlToText(sgmllib.SGMLParser):
    """Taken from some eff-bot code on c.l.p."""
    entitydefs = htmlentitydefs.entitydefs
    def __init__(self):
        self.data = []
        sgmllib.SGMLParser.__init__(self)

    def unknown_starttag(self, tag, attrib):
        self.data.append(" ")

    def unknown_endtag(self, tag):
        self.data.append(" ")

    def handle_data(self, data):
        self.data.append(data)

    def getText(self):
        text = ''.join(self.data).strip()
        return ' '.join(text.split()) # normalize whitespace

def htmlToText(s):
    x = HtmlToText()
    x.feed(s)
    return x.getText()

def eachSubstring(s):
    for i in range(1, len(s)+1):
        yield s[:i]

def abbrev(strings):
    d = {}
    for s in strings:
        for abbreviation in eachSubstring(s):
            if abbreviation not in d:
                d[abbreviation] = s
            else:
                d[abbreviation] = None
    removals = []
    for key in d:
        if d[key] is None:
            removals.append(key)
    for key in removals:
        del d[key]
    return d

# vim:set shiftwidth=4 tabstop=8 expandtab textwidth=78: