[Zope-Checkins] CVS: Zope/lib/python/Products/PluginIndexes/TextIndexNG - defaultStopWords.py:1.1.2.1 StopWords.py:1.1.2.1

Andreas Jung andreas@zope.com
Sat, 5 Jan 2002 19:17:01 -0500


Update of /cvs-repository/Zope/lib/python/Products/PluginIndexes/TextIndexNG
In directory cvs.zope.org:/tmp/cvs-serv8579

Added Files:
      Tag: ajung-textindexng-branch
	defaultStopWords.py StopWords.py 
Log Message:
+ refactored StopWord functionality


=== Added File Zope/lib/python/Products/PluginIndexes/TextIndexNG/defaultStopWords.py ===
all = ['stop_word_dict']

stop_words=(
    'am', 'ii', 'iii', 'per', 'po', 're', 'a', 'about', 'above', 'across',
    'after', 'afterwards', 'again', 'against', 'all', 'almost', 'alone',
    'along', 'already', 'also', 'although', 'always', 'am', 'among',
    'amongst', 'amoungst', 'amount', 'an', 'and', 'another', 'any',
    'anyhow', 'anyone', 'anything', 'anyway', 'anywhere', 'are', 'around',
    'as', 'at', 'back', 'be', 'became', 'because', 'become', 'becomes',
    'becoming', 'been', 'before', 'beforehand', 'behind', 'being',
    'below', 'beside', 'besides', 'between', 'beyond', 'bill', 'both',
    'bottom', 'but', 'by', 'can', 'cannot', 'cant', 'con', 'could',
    'couldnt', 'cry', 'describe', 'detail', 'do', 'done', 'down', 'due',
    'during', 'each', 'eg', 'eight', 'either', 'eleven', 'else',
    'elsewhere', 'empty', 'enough', 'even', 'ever', 'every', 'everyone',
    'everything', 'everywhere', 'except', 'few', 'fifteen', 'fifty',
    'fill', 'find', 'fire', 'first', 'five', 'for', 'former', 'formerly',
    'forty', 'found', 'four', 'from', 'front', 'full', 'further', 'get',
    'give', 'go', 'had', 'has', 'hasnt', 'have', 'he', 'hence', 'her',
    'here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers',
    'herself', 'him', 'himself', 'his', 'how', 'however', 'hundred', 'i',
    'ie', 'if', 'in', 'inc', 'indeed', 'interest', 'into', 'is', 'it',
    'its', 'itself', 'keep', 'last', 'latter', 'latterly', 'least',
    'less', 'made', 'many', 'may', 'me', 'meanwhile', 'might', 'mill',
    'mine', 'more', 'moreover', 'most', 'mostly', 'move', 'much', 'must',
    'my', 'myself', 'name', 'namely', 'neither', 'never', 'nevertheless',
    'next', 'nine', 'no', 'nobody', 'none', 'noone', 'nor', 'not',
    'nothing', 'now', 'nowhere', 'of', 'off', 'often', 'on', 'once',
    'one', 'only', 'onto', 'or', 'other', 'others', 'otherwise', 'our',
    'ours', 'ourselves', 'out', 'over', 'own', 'per', 'perhaps',
    'please', 'pre', 'put', 'rather', 're', 'same', 'see', 'seem',
    'seemed', 'seeming', 'seems', 'serious', 'several', 'she', 'should',
    'show', 'side', 'since', 'sincere', 'six', 'sixty', 'so', 'some',
    'somehow', 'someone', 'something', 'sometime', 'sometimes',
    'somewhere', 'still', 'such', 'take', 'ten', 'than', 'that', 'the',
    'their', 'them', 'themselves', 'then', 'thence', 'there',
    'thereafter', 'thereby', 'therefore', 'therein', 'thereupon', 'these',
    'they', 'thick', 'thin', 'third', 'this', 'those', 'though', 'three',
    'through', 'throughout', 'thru', 'thus', 'to', 'together', 'too',
    'toward', 'towards', 'twelve', 'twenty', 'two', 'un', 'under',
    'until', 'up', 'upon', 'us', 'very', 'via', 'was', 'we', 'well',
    'were', 'what', 'whatever', 'when', 'whence', 'whenever', 'where',
    'whereafter', 'whereas', 'whereby', 'wherein', 'whereupon',
    'wherever', 'whether', 'which', 'while', 'whither', 'who', 'whoever',
    'whole', 'whom', 'whose', 'why', 'will', 'with', 'within', 'without',
    'would', 'yet', 'you', 'your', 'yours', 'yourself', 'yourselves',
    )

stop_word_dict={}
for word in stop_words: stop_word_dict[word]=None


=== Added File Zope/lib/python/Products/PluginIndexes/TextIndexNG/StopWords.py ===
##############################################################################
# 
# Copyright (c) 2001 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
# 
#############################################################################

from types import DictType, StringType
from defaultStopWords import stop_word_dict


class StopWords:

    def __init__(self, words=stop_word_dict):

        if isinstance(words,DictType):

            self._words = words.copy()

        elif isinstance(words,StringType):

            self._words = self.readStopWords(words)

        else: 
            raise ValueError

        self.keys   = self._words.keys
        self.values = self._words.values
        self.items  = self._words.items
        self.has_key= self._words.has_key
        self.get    = self._words.get


    def __len__(self):  return len(self._words)


    def readStopWords(self, fname):

        d = {}

        lines = open(fname).readlines()
        for l in lines: 
     
            l = l.strip()
            if l:
                d[ l ] = None

        return d.copy()




if __name__=='__main__':
    test()