LPTHW Exercise 49

lexicon.py

class LexiconC(object):
    def __init__(self):
        #constants
        # TODO: Can we make these as constants so they can be accessed from out side the class with just the class name ?
        self.C_DIRECTION_WORDS = "direction"
        self.C_VERBS = "verb"
        self.C_STOP_WORDS = "stop"
        self.C_NOUNS = "noun"
        self.C_NUMBER = "number"
        self.C_ERROR = "error"

        #lexicon
        self.direction_words = ['north', 'south', 'east', 'west', 'down', 'up', 'left', 'right', 'back']
        self.verbs = ['go', 'stop', 'kill', 'eat']
        self.stop_words = ['the', 'in', 'of', 'from', 'at', 'it']
        self.nouns = ['door', 'bear', 'princess', 'cabinet']
        
    def get_tuple(self, word):
        ret_val = None
        lword = word.lower()
        if(lword in self.direction_words):
            ret_val = (self.C_DIRECTION_WORDS, word)
        elif(lword in self.verbs):
            ret_val = (self.C_VERBS, word)
        elif(lword in self.stop_words):
            ret_val = (self.C_STOP_WORDS, word)
        elif(lword in self.nouns):
            ret_val = (self.C_NOUNS, word)
        elif(self.convert_number(lword) != None):
            ret_val = (self.C_NUMBER, self.convert_number(lword))
        else:
            ret_val = (self.C_ERROR, word)

        return ret_val

    def convert_number(self, text):
        try:
            return int(text)
        except ValueError:
            return None


def scan(line):
    the_lexicon = LexiconC()
    ret_val = []
    words = line.split()
    for word in words:
        the_tuple = the_lexicon.get_tuple(word)
        ret_val.append(the_tuple)

    return ret_val

lexicon_tests.py

from nose.tools import *
from ex49 import lexicon

def setup():
    print "SETUP!"

def teardown():
    print "TEAR DOWN!"

def test_directions():
    assert_equal(lexicon.scan("north"), [('direction', 'north')])
    result = lexicon.scan("north south east")
    assert_equal(result, [('direction', 'north'),
                          ('direction', 'south'),
                          ('direction', 'east')])

def test_verbs():
    assert_equal(lexicon.scan("go"), [('verb', 'go')])
    result = lexicon.scan("go kill eat")
    assert_equal(result, [('verb', 'go'),
                           ('verb', 'kill'),
                           ('verb', 'eat')])

def test_stops():
    assert_equal(lexicon.scan("the"), [('stop', 'the')])
    result = lexicon.scan("the in of")
    assert_equals(result, [('stop', 'the'),
                           ('stop', 'in'),
                           ('stop', 'of')])

def test_nouns():
    assert_equal(lexicon.scan("bear"), [('noun', 'bear')])
    result = lexicon.scan("bear princess")
    assert_equal(result, [('noun', 'bear'),
                          ('noun', 'princess')])

def test_numbers():
    assert_equal(lexicon.scan("1234"), [('number', 1234)])
    result = lexicon.scan("3 91234")
    assert_equal(result, [('number', 3),
                          ('number', 91234)])

def test_errors():
    assert_equal(lexicon.scan("ASDFADFA"), [('error', "ASDFADFA")])
    result = lexicon.scan("bear IAS princess")
    assert_equal(result, [('noun', 'bear'),
                          ('error', 'IAS'),
                          ('noun', 'princess')])

sentence.py

class ParseError(Exception):
    pass

class Sentence(object):
    def __init__(self, subject, verb, object):
        """ Each argument 'subject', 'verb', 'object' is a tuple containing the code and word"""
        self.subject = subject
        self.verb = verb
        self.object = object

def peek(word_list):
    """ 
    word_list is a list of tuples in the form (code, word).
    This method returns the code of the first tuple in the list
    """
    if(word_list):
        word = word_list[0]
        return word[0]
    else:
        return None

def match(word_list, expecting):
    """ 
    Returns the first word if it matches the expecting type, else returns None.
    In any case, the first word will be removed from the word_list
    """
    ret_val = None
    if(word_list):
        word_tuple = word_list.pop(0)
        if(word_tuple[0] == expecting):
            ret_val =  word_tuple
    
    return ret_val

def skip(word_list, word_type):
    if(word_list):
        while(peek(word_list) == word_type):
            match(word_list, word_type)

def parse_subject(word_list, subject):
    skip(word_list, 'stop')
    verb = match(word_list, 'verb')
    if(verb == None):
        raise ParseError("Expecting a verb")

    skip(word_list, 'stop')
    object = match(word_list, 'noun')
    if(object == None):
        raise ParseError("Expecting a noun")

    return Sentence(subject, verb, object)

def parse_sentence(word_list):
    """ Accepts a list of tuples, where each tuple contains (code, word)"""
    skip(word_list, 'stop')
    start = peek(word_list)
    if(start == 'noun'):
        subject = match(word_list, 'noun')
        return parse_subject(word_list, subject)
    elif(start == 'verb'):
        subject = ('noun', 'player')
        return parse_subject(word_list, subject)
    else:
        raise ParseError("Must start with either a noun or a verb ... not '%s'" % start)
    

sentence_tests.py

from nose.tools import *
from ex49 import sentence
from ex49 import lexicon

def setup():
    print "SETUP!"

def teardown():
    print "TEAR DOWN!"

def test_peek():
    #test a line with one word
    line1 = "princess"
    word_tuples1 = lexicon.scan(line1)
    word_type1 = sentence.peek(word_tuples1)
    assert_equal("noun", word_type1)

    #test a line with multiple words
    line2 = "princess ate the bear"
    word_tuples2 = lexicon.scan(line2)
    assert_equal("noun", sentence.peek(word_tuples2))

def test_match():
    #test a line with one word
    line1 = "princess"
    word_tuples1 = lexicon.scan(line1)
    assert_equal("princess", sentence.match(word_tuples1, 'noun')[1])
    #Here we should get a None for any type since there is nothing in the word_list
    assert_equal(None, sentence.match(word_tuples1, 'noun'))

    #test a line with multiple words
    line2 = "princess eat the bear"
    word_tuples2 = lexicon.scan(line2)
    assert_equals(4, len(word_tuples2))
    assert_equal("princess", sentence.match(word_tuples2, "noun")[1])
    assert_equal("eat", sentence.match(word_tuples2, "verb")[1])
    assert_equal("the", sentence.match(word_tuples2, 'stop')[1])
    assert_equal("bear", sentence.match(word_tuples2, 'noun')[1])

def test_skip():
    #test a line with one word
    line1 = "princess"
    word_tuples1 = lexicon.scan(line1)
    sentence.skip(word_tuples1, "verb")
    assert_equal(1, len(word_tuples1))
    sentence.skip(word_tuples1, 'noun')
    assert_equal(0, len(word_tuples1))

    #test a line with multiple words
    line2 = "princess eat the bear"
    word_tuples2 = lexicon.scan(line2)
    sentence.skip(word_tuples2, "verb")
    assert_equal(4, len(word_tuples2))
    sentence.skip(word_tuples2, "noun")
    assert_equal(3, len(word_tuples2))
    sentence.skip(word_tuples2, "verb")
    assert_equal(2, len(word_tuples2))
    
    
        

def test_parse_sentence():
    line = "princess eat the bear"
    word_list = lexicon.scan(line)
    parsed_sentence = sentence.parse_sentence(word_list)
    assert_equal("princess", parsed_sentence.subject[1])
    assert_equal("eat", parsed_sentence.verb[1])
    assert_equal("bear", parsed_sentence.object[1])