def demo2():
from nltk import Nonterminal, Production, 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()]
productions = (
# Syntactic Productions
Production(S, [NP, VP]),
Production(NP, [Det, N]),
Production(NP, [NP, PP]),
Production(VP, [VP, PP]),
Production(VP, [V, NP, PP]),
Production(VP, [V, NP]),
Production(PP, [P, NP]),
Production(PP, []),
Production(PP, ['up', 'over', NP]),
# Lexical Productions
Production(NP, ['I']), Production(Det, ['the']),
Production(Det, ['a']), Production(N, ['man']),
Production(V, ['saw']), Production(P, ['in']),
Production(P, ['with']), Production(N, ['park']),
Production(N, ['dog']), Production(N, ['statue']),
Production(Det, ['my']),
)
grammar = CFG(S, productions)
text = 'I saw a man in the park'.split()
d=CFGDemo(grammar, text)
d.mainloop()
######################################################################
# Old Demo
######################################################################
python类Nonterminal()的实例源码
def demo():
from nltk import Nonterminal, 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 = CFG.fromstring("""
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 _item_repr(self, item):
contents = []
contents.append(('%s\t' % item.lhs(), 'nonterminal'))
contents.append((self.ARROW, 'arrow'))
for elt in item.rhs():
if isinstance(elt, Nonterminal):
contents.append((' %s' % elt.symbol(), 'nonterminal'))
else:
contents.append((' %r' % elt, 'terminal'))
return contents
######################################################################
# CFG Editor
######################################################################
def _parse_productions(self):
"""
Parse the current contents of the textwidget buffer, to create
a list of productions.
"""
productions = []
# Get the text, normalize it, and split it into lines.
text = self._textwidget.get('1.0', 'end')
text = re.sub(self.ARROW, '->', text)
text = re.sub('\t', ' ', text)
lines = text.split('\n')
# Convert each line to a CFG production
for line in lines:
line = line.strip()
if line=='': continue
productions += _read_cfg_production(line)
#if line.strip() == '': continue
#if not CFGEditor._PRODUCTION_RE.match(line):
# raise ValueError('Bad production string %r' % line)
#
#(lhs_str, rhs_str) = line.split('->')
#lhs = Nonterminal(lhs_str.strip())
#rhs = []
#def parse_token(match, rhs=rhs):
# token = match.group()
# if token[0] in "'\"": rhs.append(token[1:-1])
# else: rhs.append(Nonterminal(token))
# return ''
#CFGEditor._TOKEN_RE.sub(parse_token, rhs_str)
#
#productions.append(Production(lhs, *rhs))
return productions
def _apply(self, *e):
productions = self._parse_productions()
start = Nonterminal(self._start.get())
cfg = CFG(start, productions)
if self._set_cfg_callback is not None:
self._set_cfg_callback(cfg)
def demo2():
from nltk import Nonterminal, Production, 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()]
productions = (
# Syntactic Productions
Production(S, [NP, VP]),
Production(NP, [Det, N]),
Production(NP, [NP, PP]),
Production(VP, [VP, PP]),
Production(VP, [V, NP, PP]),
Production(VP, [V, NP]),
Production(PP, [P, NP]),
Production(PP, []),
Production(PP, ['up', 'over', NP]),
# Lexical Productions
Production(NP, ['I']), Production(Det, ['the']),
Production(Det, ['a']), Production(N, ['man']),
Production(V, ['saw']), Production(P, ['in']),
Production(P, ['with']), Production(N, ['park']),
Production(N, ['dog']), Production(N, ['statue']),
Production(Det, ['my']),
)
grammar = CFG(S, productions)
text = 'I saw a man in the park'.split()
d=CFGDemo(grammar, text)
d.mainloop()
######################################################################
# Old Demo
######################################################################
def demo():
from nltk import Nonterminal, 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 = CFG.fromstring("""
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 _item_repr(self, item):
contents = []
contents.append(('%s\t' % item.lhs(), 'nonterminal'))
contents.append((self.ARROW, 'arrow'))
for elt in item.rhs():
if isinstance(elt, Nonterminal):
contents.append((' %s' % elt.symbol(), 'nonterminal'))
else:
contents.append((' %r' % elt, 'terminal'))
return contents
######################################################################
# CFG Editor
######################################################################
def _parse_productions(self):
"""
Parse the current contents of the textwidget buffer, to create
a list of productions.
"""
productions = []
# Get the text, normalize it, and split it into lines.
text = self._textwidget.get('1.0', 'end')
text = re.sub(self.ARROW, '->', text)
text = re.sub('\t', ' ', text)
lines = text.split('\n')
# Convert each line to a CFG production
for line in lines:
line = line.strip()
if line=='': continue
productions += _read_cfg_production(line)
#if line.strip() == '': continue
#if not CFGEditor._PRODUCTION_RE.match(line):
# raise ValueError('Bad production string %r' % line)
#
#(lhs_str, rhs_str) = line.split('->')
#lhs = Nonterminal(lhs_str.strip())
#rhs = []
#def parse_token(match, rhs=rhs):
# token = match.group()
# if token[0] in "'\"": rhs.append(token[1:-1])
# else: rhs.append(Nonterminal(token))
# return ''
#CFGEditor._TOKEN_RE.sub(parse_token, rhs_str)
#
#productions.append(Production(lhs, *rhs))
return productions
def _apply(self, *e):
productions = self._parse_productions()
start = Nonterminal(self._start.get())
cfg = CFG(start, productions)
if self._set_cfg_callback is not None:
self._set_cfg_callback(cfg)
def demo2():
from nltk import Nonterminal, Production, 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()]
productions = (
# Syntactic Productions
Production(S, [NP, VP]),
Production(NP, [Det, N]),
Production(NP, [NP, PP]),
Production(VP, [VP, PP]),
Production(VP, [V, NP, PP]),
Production(VP, [V, NP]),
Production(PP, [P, NP]),
Production(PP, []),
Production(PP, ['up', 'over', NP]),
# Lexical Productions
Production(NP, ['I']), Production(Det, ['the']),
Production(Det, ['a']), Production(N, ['man']),
Production(V, ['saw']), Production(P, ['in']),
Production(P, ['with']), Production(N, ['park']),
Production(N, ['dog']), Production(N, ['statue']),
Production(Det, ['my']),
)
grammar = CFG(S, productions)
text = 'I saw a man in the park'.split()
d=CFGDemo(grammar, text)
d.mainloop()
######################################################################
# Old Demo
######################################################################
def demo():
from nltk import Nonterminal, 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 = CFG.fromstring("""
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 _item_repr(self, item):
contents = []
contents.append(('%s\t' % item.lhs(), 'nonterminal'))
contents.append((self.ARROW, 'arrow'))
for elt in item.rhs():
if isinstance(elt, Nonterminal):
contents.append((' %s' % elt.symbol(), 'nonterminal'))
else:
contents.append((' %r' % elt, 'terminal'))
return contents
######################################################################
# CFG Editor
######################################################################
def _parse_productions(self):
"""
Parse the current contents of the textwidget buffer, to create
a list of productions.
"""
productions = []
# Get the text, normalize it, and split it into lines.
text = self._textwidget.get('1.0', 'end')
text = re.sub(self.ARROW, '->', text)
text = re.sub('\t', ' ', text)
lines = text.split('\n')
# Convert each line to a CFG production
for line in lines:
line = line.strip()
if line=='': continue
productions += _read_cfg_production(line)
#if line.strip() == '': continue
#if not CFGEditor._PRODUCTION_RE.match(line):
# raise ValueError('Bad production string %r' % line)
#
#(lhs_str, rhs_str) = line.split('->')
#lhs = Nonterminal(lhs_str.strip())
#rhs = []
#def parse_token(match, rhs=rhs):
# token = match.group()
# if token[0] in "'\"": rhs.append(token[1:-1])
# else: rhs.append(Nonterminal(token))
# return ''
#CFGEditor._TOKEN_RE.sub(parse_token, rhs_str)
#
#productions.append(Production(lhs, *rhs))
return productions
def _apply(self, *e):
productions = self._parse_productions()
start = Nonterminal(self._start.get())
cfg = CFG(start, productions)
if self._set_cfg_callback is not None:
self._set_cfg_callback(cfg)
def demo2():
from nltk import Nonterminal, Production, 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()]
productions = (
# Syntactic Productions
Production(S, [NP, VP]),
Production(NP, [Det, N]),
Production(NP, [NP, PP]),
Production(VP, [VP, PP]),
Production(VP, [V, NP, PP]),
Production(VP, [V, NP]),
Production(PP, [P, NP]),
Production(PP, []),
Production(PP, ['up', 'over', NP]),
# Lexical Productions
Production(NP, ['I']), Production(Det, ['the']),
Production(Det, ['a']), Production(N, ['man']),
Production(V, ['saw']), Production(P, ['in']),
Production(P, ['with']), Production(N, ['park']),
Production(N, ['dog']), Production(N, ['statue']),
Production(Det, ['my']),
)
grammar = CFG(S, productions)
text = 'I saw a man in the park'.split()
d=CFGDemo(grammar, text)
d.mainloop()
######################################################################
# Old Demo
######################################################################
def demo():
from nltk import Nonterminal, 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 = CFG.fromstring("""
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 _item_repr(self, item):
contents = []
contents.append(('%s\t' % item.lhs(), 'nonterminal'))
contents.append((self.ARROW, 'arrow'))
for elt in item.rhs():
if isinstance(elt, Nonterminal):
contents.append((' %s' % elt.symbol(), 'nonterminal'))
else:
contents.append((' %r' % elt, 'terminal'))
return contents
######################################################################
# CFG Editor
######################################################################
def _parse_productions(self):
"""
Parse the current contents of the textwidget buffer, to create
a list of productions.
"""
productions = []
# Get the text, normalize it, and split it into lines.
text = self._textwidget.get('1.0', 'end')
text = re.sub(self.ARROW, '->', text)
text = re.sub('\t', ' ', text)
lines = text.split('\n')
# Convert each line to a CFG production
for line in lines:
line = line.strip()
if line=='': continue
productions += _read_cfg_production(line)
#if line.strip() == '': continue
#if not CFGEditor._PRODUCTION_RE.match(line):
# raise ValueError('Bad production string %r' % line)
#
#(lhs_str, rhs_str) = line.split('->')
#lhs = Nonterminal(lhs_str.strip())
#rhs = []
#def parse_token(match, rhs=rhs):
# token = match.group()
# if token[0] in "'\"": rhs.append(token[1:-1])
# else: rhs.append(Nonterminal(token))
# return ''
#CFGEditor._TOKEN_RE.sub(parse_token, rhs_str)
#
#productions.append(Production(lhs, *rhs))
return productions
def _apply(self, *e):
productions = self._parse_productions()
start = Nonterminal(self._start.get())
cfg = CFG(start, productions)
if self._set_cfg_callback is not None:
self._set_cfg_callback(cfg)
