Python nltk.parse_cfg函数代码示例

def contextFreeGrammar():
    print "page 298 Context-Free Grammar"
    print "=============== A Simple Grammar ==============="
    grammar1 = nltk.parse_cfg("""
        S -> NP VP
        VP -> V NP | V NP PP  
        PP -> P NP  
        V -> "saw" | "ate" | "walked"  
        NP -> "John" | "Mary" | "Bob" | Det N | Det N PP  
        Det -> "a" | "an" | "the" | "my"  
        N -> "man" | "dog" | "cat" | "telescope" | "park"  
        P -> "in" | "on" | "by" | "with"  
        """)
    sent = "Mary saw Bob".split()
    rd_parser = nltk.RecursiveDescentParser(grammar1)
    for tree in rd_parser.nbest_parse(sent):
        print tree

    print "=============== Writing Your Own Grammars ==============="
    grammar1 = nltk.data.load('file:mygrammar.cfg')
    sent = "Mary saw Bob".split()
    rd_parser = nltk.RecursiveDescentParser(grammar1)
    for tree in rd_parser.nbest_parse(sent):
        print tree

    print "=============== Recursion in Syntactic Structure ==============="
    grammar2 = nltk.parse_cfg("""  S  -> NP VP  NP -> Det Nom | PropN  Nom -> Adj Nom | N  VP -> V Adj | V NP | V S | V NP PP  PP -> P NP  PropN -> 'Buster' | 'Chatterer' | 'Joe'  Det -> 'the' | 'a'  N -> 'bear' | 'squirrel' | 'tree' | 'fish' | 'log'  Adj  -> 'angry' | 'frightened' |  'little' | 'tall'  V ->  'chased'  | 'saw' | 'said' | 'thought' | 'was' | 'put'  P -> 'on'  """)

def cfgMatch ( nlQuery ):
    terminalList = [ 'find','search','display','tell','faculty','student','staff','other' ]
    grammar = nltk.parse_cfg("""
                    S -> A B
                    A -> 'find'|'search'|'display'|'tell'
                    B -> 'faculty'|'student'|'staff'|'other'
                    """)
# Since grammar crashes if a non term not in grammar is used.
# We have to check and report error if such a word is used anywhere
##################################################################
# Check and errors reporting here
    tokenizedList = list( word_tokenize( nlQuery  ) )
    for word in tokenizedList:
        if word not in terminalList:
            print "ERROR"
            return -1
##################################################################
    parser = nltk.RecursiveDescentParser ( grammar )
    parseTree = parser.nbest_parse ( tokenizedList, 1 )

    for tree in parseTree:
        print tree
        for elem in tree:
            for i in tree.node:
                print i

def generate_grammar(sentence):
    grammar = "\n".join([r for r, freq in frequent_rules])
    for (word, pos_tag) in sentence:
        grammar += "%s -> '%s' \n" %(pos_tag, word)

    #print grammar
    return nltk.parse_cfg(grammar)

def demo():
    from nltk import Nonterminal, parse_cfg
    nonterminals = 'S VP NP PP P N Name V Det'
    (S, VP, NP, PP, P, N, Name, V, Det) = [Nonterminal(s)
                                           for s in nonterminals.split()]

    grammar = parse_cfg("""
    S -> NP VP
    PP -> P NP
    NP -> Det N
    NP -> NP PP
    VP -> V NP
    VP -> VP PP
    Det -> 'a'
    Det -> 'the'
    Det -> 'my'
    NP -> 'I'
    N -> 'dog'
    N -> 'man'
    N -> 'park'
    N -> 'statue'
    V -> 'saw'
    P -> 'in'
    P -> 'up'
    P -> 'over'
    P -> 'with'
    """)

    def cb(grammar): print(grammar)
    top = Tk()
    editor = CFGEditor(top, grammar, cb)
    Label(top, text='\nTesting CFG Editor\n').pack()
    Button(top, text='Quit', command=top.destroy).pack()
    top.mainloop()

def parseSimile(tokensWithIndices):
    #The grammar used to check a simile
    grammar = nltk.parse_cfg("""
    S -> NP "like" NP | "ADJ" "like" "NP" | NP V "like" NP | "EX" "like" "NP" | NP "as" "ADJ" "as" NP | V "as" "ADJ" "as" NP |OTH
    NP -> N | "ADJ" N | "DET" NP 
    N -> "NP" | "PRO" | "N"
    V -> "VD" | "V" | "VG"
    OTH -> "OTH" "PUNC" "FW" "WH" "TO" "NUM" "ADV" "VD" "VG" "L" "VN" "N" "P" "S" "EX" "V" "CNJ" "UH" "PRO" "MOD"  
    """)  
    tokens = map(lambda i: i[0], tokensWithIndices)
    indices = map(lambda i: i[1], tokensWithIndices)
    parser = nltk.ChartParser(grammar)
    simile_indices = []
    start_token = 0
    while (start_token < len(tokens) - 2):
        end_token = start_token + 2 #can't have simile smaller than 4 words
        simile = False
        while ( (not simile) and (end_token <= len(tokens))):
            if (len(parser.nbest_parse(tokens[start_token:end_token])) > 0): #If a parse tree was formed
                simile_indices.extend(indices[start_token:end_token])
                start_token = end_token
                simile = True            
            else:    
                end_token += 1
        start_token += 1
    return simile_indices

def parse(wordlist, grammar, generator):
    """
    Parse this thang. Call off to nltk's chart parser (which is
    the only one fast enough to parse the massive grammar). Only
    use the top best tree. If no parse tree is found, the program
    dies. The pass along the tree for actual symantic analysis,
    and then print out the parse and we're done!
    """

    import nltk

    try:
        gr = nltk.parse_cfg(grammar)
        parts = [w.reduced() for w in wordlist]

        parser = nltk.BottomUpChartParser(gr)
        trees = parser.nbest_parse(parts)

        classifiers = ClassifierCollection(generator)
        ct = 0
        for tree in trees:
            rparse(tree, classifiers, False)
            ct += 1
            break

        if ct == 0:
            raise ParserException('No parse trees found')

        classifiers.finish()
        classifiers.pprint()

    except ValueError, e:
        raise ParserException(str(e))

	def test_returnRelevantTuples_2(self):
		# arrange
		testGrammar = """
S -> NP VP

VP -> VP PP
VP -> V NP
VP -> 'eats'

PP -> P NP

NP -> Det N
NP -> 'she'

V -> 'eats'

P -> 'with'

N -> 'fish'
N -> 'fork'

Det -> 'a'
"""
		grammar = nltk.parse_cfg(testGrammar)

		sent = ['she', 'eats', 'a', 'fish', 'with', 'a', 'fork']

		inst = cyk.Cyk(sent, grammar.productions())

		# act		
		inst.executeAlgorithm()

		# assert
		self.assertTrue(inst.isInGrammar())

	def __init__(self, cfgGrammar):
		self.pb = productionBuilder.ProductionBuilder()

		self.grammar = nltk.parse_cfg(cfgGrammar)
		self.terminalTransformProductions = []
		self.nonTerminalTransformProductions = []
		self.singleNonTerminalTransformProductions = []

    def __init__(self, blackboard, tense = "present", person = 1):
        super(SentenceExpert, self).__init__(blackboard, "Sentence Expert", tense, person,5)
        self.eva = ["be", "look", "feel"]
        self.atv = ["like", "hate", "love", "know", "need", "see"]

        """ eva - emotional verb active
            evp - emotional verb passive
            ej - emotion adjective
            en - emotional noun
            atv - attitude verb
        """
        self.grammar = nltk.parse_cfg("""
            S -> P | EP | Person ATV NP
            P -> NP VP 
            EP -> Person EVA EJ | NP EVP Pron EJ | ENP VP
            ENP ->  EN OF NP 
            NP -> Det N | Det JJ N | Det EJ JJ N | Det EJ N | Det EN
            VP -> V | V ERB | ERB V
            Det -> 'the'
            N -> 'n'
            V -> 'v' 
            EVA -> 'eva'
            EVP -> 'makes' 
            EN -> 'en'
            EJ -> 'ej'
            JJ -> 'adj'
            ERB -> 'erb'
            ATV -> 'atv'
            Person -> 'person'
            Pron -> 'pron'
            OF -> 'of'
            CC -> 'and' | 'but' | 'because' | 'so'
            """)

    def build_grammar(self):
        '''Use the corpus data and return a NLTK grammar.'''

        grammer_def = self.build_grammar_text().getvalue()
        grammar = nltk.parse_cfg(grammer_def.encode('utf8'))

        return grammar

def Solution_parse(args):
  try:
    print "Parser option: %s " % args.parseOption
    gstring = open('solutiongrammar.cfg', 'r').read()
    grammar1 = nltk.parse_cfg(gstring)
    #print grammar1 , '\n'
    
    if (args.parseOption == 'rd'):
      parser = nltk.RecursiveDescentParser(grammar1)
    elif(args.parseOption == 'sr'):
      parser = nltk.ShiftReduceParser(grammar1)
    elif(args.parseOption == 'ec'):
      parser = nltk.parse.EarleyChartParser(grammar1)
    elif(args.parseOption == 'td'):
      parser = nltk.parse.TopDownChartParser(grammar1)
    elif(args.parseOption == 'bu'):
      parser = nltk.parse.BottomUpChartParser(grammar1)
    else:
      raise Exception("Unknown parseOption: %s" % args.parseOption)

    i = 0
    for line in open('inputfile.txt','r'):
      i += 1
      pass
      if i == 1:
        print line
        sent = wordpunct_tokenize(line)
        print sent , '\n'
        pp = parser.parse(sent)
        print pp, '\n'
        pass

  except Exception, err:
    sys.stderr.write('ERROR: %s\n' % str(err))
    raise

	def test_ctor(self):
		# arrange
		testGrammar = """
S -> NP VP

VP -> VP PP
VP -> V NP
VP -> 'eats'

PP -> P NP

NP -> Det N
NP -> 'she'

V -> 'eats'

P -> 'with'

N -> 'fish'
N -> 'fork'

Det -> 'a'
"""
		grammar = nltk.parse_cfg(testGrammar)

		sent = ['she', 'eats', 'a', 'fish', 'with', 'a', 'fork']

		# act
		inst = cyk.Cyk(sent, grammar.productions())

		# assert
		self.assertTrue(inst != None)
		self.assertTrue(inst.sentence == sent)

def demo():
    """
    A demonstration of the shift-reduce parser.
    """

    from nltk import parse, parse_cfg

    grammar = parse_cfg(
        """
    S -> NP VP
    NP -> Det N | Det N PP
    VP -> V NP | V NP PP
    PP -> P NP
    NP -> 'I'
    N -> 'man' | 'park' | 'telescope' | 'dog'
    Det -> 'the' | 'a'
    P -> 'in' | 'with'
    V -> 'saw'
    """
    )

    sent = "I saw a man in the park".split()

    parser = parse.ShiftReduceParser(grammar, trace=2)
    for p in parser.nbest_parse(sent):
        print p

def test():
  import nltk
	grammar1 = nltk.parse_cfg("""
	
	""")
	sr_parse = nltk.Shift Reduce Parser(grammar1)

	sent = "Lee ran away home".split()
	return sr_parse.parse(sent)

 def __init__(self, blackboard, tense = "present"):
     super(RhetoricalExpert, self).__init__(blackboard, "Rhetorical Expert", tense, 3)
     self.grammar = nltk.parse_cfg("""
         S -> WHAT BE Det NP | WHY BE Det N SO JJ
         NP -> JJ N | N
         JJ -> 'adj'
         N -> 'n'
         Det -> 'the'
         BE -> 'be'
         SO -> 'so'
         WHAT -> 'what'
         WHY -> 'why'
         """)