Esempio n. 1
0
def testRun():

    lukija = WordReader(["../Material/Grimm's Fairy Tales.txt"])

    lukija.readWords()


    punamusta = RedBlack(lukija)
    trie = Trie(lukija)

    print "Adding words from selected material..."
    intti = 0; setti = 0
    for word in lukija.words:
        trie.add(word[0], word[1:])
        punamusta.add(word[0], word[1:])
        intti = intti + 1
        if intti > lukija.wordcount / 100.0:
            setti = setti + 1
            print setti, '% of words added'
            intti = 0

    print "Searching for words in Grimm's Fairy tales and The Adventures of Tom Sawyer"

    word = raw_input( "Find a word (or its beginning) in the text: " ).rstrip( '\n' )

    positions, count, linecount = trie.find(word)
    print "Found", count, "instances (", linecount, "lines) @", positions
    RBpositions, RBcount, RBlinecount = punamusta.find(word)
    print "Found", RBcount, "instances (", RBlinecount, "lines) @", RBpositions
Esempio n. 2
0
class  PySearcherTestCases(unittest.TestCase):
    def setUp(self):
        self.reader = WordReader()
        self.finder = Trie(self.reader)
        self.searcher = Searcher(self.finder, '')

    def tearDown(self):
        self.reader = None
        self.finder = None
        self.searcher = None

    def testRandomWord(self):
       """ Tests that non-empty words are found and they are not the same """
       word1 = self.searcher.randomWord()
       word2 = self.searcher.randomWord()
       self.assertTrue(len(word1) > 1, 'Word length too short')
       self.assertTrue(len(word2) > 1, 'Word length too short')
       self.assertNotEqual(word1, word2, 'Found the same word')

    def testRandomWords(self):
       """ Tests that a set of random words do not contain the same words """
       words = self.searcher.randomWord(5)
       self.assertTrue(len(set(words)) == 5, 'Did not find 5 unique words')

    def testBinaryOperationsAreWorking(self):
        """
        Checks that operations are not identic and that correct number of hits
        is returned for every known result.
        """
        self.reader.addFileName(MaterialFilePath, readNow=True)
        self.finder.addFromReader()

        results = []
        for operation in operations:
            results.append(self.searcher.search(operations[operation],
                                                returnCount=True))
        self.assertTrue(len(set(results)) == 6, #i.e. operations are not identic
                        'Searcher failed binary operation check')
        for searchTerm in binaryOperationsSearch:
            self.assertEqual(self.searcher.search(searchTerm, returnCount=True),
                             binaryOperationsSearch[searchTerm],
                            'Searcher found wrong number of hits on some search')
Esempio n. 3
0
 def setUp(self):
     self.reader = WordReader()
     self.finder = Trie(self.reader)
     self.searcher = Searcher(self.finder, '')
Esempio n. 4
0

if __name__ == "__main__":
    print "Hello World"

    trieAddFile = openFile('trieAddToEmpty', 'w')
    punamustaAddFile = openFile('punamustaAddToEmpty', 'w')
    trieFindLengthFile = openFile('trieFindWordLength', 'w')
    punamustaFindLengthFile = openFile('punamustaFindWordLength', 'w')
    trieFindWordCountFile = openFile('trieFindWordCount', 'w')
    punamustaFindWordCountFile = openFile('punamustaFindWordCoun', 'w')

    lukija = WordReader(["../Material/Grimm's Fairy Tales.txt"])
    lukija.readWords()
    punamusta = RedBlack(lukija)
    trie = Trie(lukija)

    words = pickle.load( open( "randomWordList", "rb" ) ) # indexed by word len

    repeats = 100;
    runtimes = []
    for i in range(2,17):
        runtime = addWordsToEmptyList(trie, 2**i, repeats, '%25s\t%10d\t' % ('trie:add', 2**i), False)
        print '%25s\t%10d\t\t%14.3f ms' % ('trie:addToEmpty', 2**i, runtime)
        trieAddFile.write('%10d\t%8.3f\n' % (2**i, runtime))
        runtimes.append(findWords(trie, words[7], repeats, printout=False))
    for index, runtime in enumerate(runtimes):
        print '%25s\t%10d\t\t%14.3f ms' % ('trie:findWordCount', 2**(index+2), runtime)
        trieFindWordCountFile.write('%10d\t%14.3f\n' % (2**(index+2), runtime))

    runtimes = []