【语言处理与Python】8.2文法有什么用？\8.3上下文无关文法\8.4上下文无关文法分析

grammar1= nltk.parse_cfg("""
S -> NPVP
VP-> VNP| VNPPP
PP-> P NP
V-> "saw" | "ate" | "walked"
NP-> "John" | "Mary" | "Bob" | DetN| DetNPP
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
(S (NP Mary)(VP (V saw) (NP Bob)))

>>>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

rd_parser =nltk.RecursiveDescentParser(grammar1, trace=2)

>>>rd_parser =nltk.RecursiveDescentParser(grammar1)
>>>sent = 'Mary saw a dog'.split()
>>>for t in rd_parser.nbest_parse(sent):
... print t
(S (NP Mary)(VP (V saw) (NP (Det a) (N dog))))

>>>sr_parse= nltk.ShiftReduceParser(grammar1)
>>>sent = 'Mary saw a dog'.split()
>>>print sr_parse.parse(sent)
(S (NP Mary)(VP (V saw) (NP (Det a) (N dog))))

grammar2= nltk.parse_cfg("""
S -> NP VP
NP-> Det Nom| PropN
Nom-> Adj Nom| N
VP-> V Adj| VNP| VS| VNPPP
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'
""")

>>>text = ['I', 'shot', 'an', 'elephant', 'in', 'my', 'pajamas']

def init_wfst(tokens, grammar):
    numtokens= len(tokens)
    wfst= [[None for i in range(numtokens+1)] for j in range(numtokens+1)]
    for i in range(numtokens):
        productions = grammar.productions(rhs=tokens[i])
        wfst[i][i+1]= productions[0].lhs()
    return wfst
def complete_wfst(wfst,tokens, grammar,trace=False):
    index = dict((p.rhs(),p.lhs()) for pin grammar.productions())
    numtokens= len(tokens)
    for span in range(2, numtokens+1):
        for start in range(numtokens+1-span):
        end = start + span
        for midin range(start+1, end):
            nt1,nt2 = wfst[start][mid],wfst[mid][end]
            if nt1 and nt2 and (nt1,nt2) in index:
                wfst[start][end]= index[(nt1,nt2)]
            if trace:
                    print "[%s] %3s[%s] %3s[%s] ==>[%s] %3s[%s]" %
                        \
                    (start, nt1, mid,nt2,end, start, index[(nt1,nt2)], end)
    return wfst

def display(wfst,tokens):
    print '\nWFST ' + ' '.join([("%-4d" %i) for i in range(1, len(wfst))])
    for i in range(len(wfst)-1):
        print "%d " %i,
    for j in range(1, len(wfst)):
        print "%-4s" %(wfst[i][j] or '.'),
    print
>>>tokens = "I shot an elephant in mypajamas".split()
>>>wfst0= init_wfst(tokens, groucho_grammar)
>>>display(wfst0,tokens)
WFST1 2 3 4 5 6 7
0 NP . . . . . .
1 . V . . . . .
2 . . Det . . . .
3 . . . N . . .
4 . . . . P . .
5 . . . . . Det .
6 . . . . . . N
>>>wfst1= complete_wfst(wfst0, tokens, groucho_grammar)
>>>display(wfst1,tokens)
WFST1 2 3 4 5 6 7
0 NP . . S . . S
1 . V . VP . . VP
2 . . Det NP . . .
3 . . . N . . .
4 . . . . P . PP
5 . . . . . Det NP
6 . . . . . . N

#对应的文法
>>> groucho_grammar= nltk.parse_cfg("""
S -> NP VP
PP -> P NP
NP -> Det N| DetN PP| 'I'
VP -> V NP| VP PP
Det -> 'an' | 'my'
N -> 'elephant' | 'pajamas'
V -> 'shot'
P ->'in'
""")
#文法的内容
>>> grammar,productions()
[S -> NP VP, PP -> P NP, NP -> Det N, NP -> DetN PP, NP -> 'I', VP -> V NP, VP -> VP PP, Det -> 'an', Det -> 'my', N -> 'elephant', N -> 'pajamas', V -> 'shot', P -> 'in']
#index的内容
pprint.pprint(dict((p.rhs(),p.lhs()) for p in groucho_grammar.productions()))
{(Det, N): NP,
 (DetN, PP): NP,
 (NP, VP): S,
 (P, NP): PP,
 (V, NP): VP,
 (VP, PP): VP,
 ('I',): NP,
 ('an',): Det,
 ('elephant',): N,
 ('in',): P,
 ('my',): Det,
 ('pajamas',): N,
 ('shot',): V}
>>>