Generate a grammar sentence with a given number of terminals

Question

Say you have a toy grammar, for example: (updated, so the output looks more natural)

S -> ${NP} ${VP} | ${S} and ${S} | ${S}, after which ${S}

NP -> the ${N} | the ${A} ${N} | the ${A} ${A} ${N}

VP -> ${V} ${NP}

N -> dog | fish | bird | wizard

V -> kicks | meets | marries

A -> red | striped | spotted

for example, “the dog kicks the red wizard”, “the bird meets spotted fish, or the wizard marries the striped dog”

How can you make a sentence from this grammar in accordance with the restriction that it must contain a total of n Vs + As + Ns. Given an integer, a sentence should contain as many terminals. (note, of course, in this grammar the minimum possible n is 3).

Answer 1

Python . , , . , . 1 , n 0 0 . , , i, , . . , 1 , 1 0 . , . , , , 0. , . ,

S -> S S
S ->

: S = > , S = > S S = > , S = > S S = > S S S = > .. - . , 100 100 .

import collections
import random

class Grammar:
    def __init__(self):
        self.prods = collections.defaultdict(list)
        self.numsent = {}
        self.weight = {}

    def prod(self, lhs, *rhs):
        self.prods[lhs].append(rhs)
        self.numsent.clear()

    def countsent(self, rhs, n):
        if n < 0:
            return 0
        elif not rhs:
            return 1 if n == 0 else 0
        args = (rhs, n)
        if args not in self.numsent:
            sym = rhs[0]
            rest = rhs[1:]
            total = 0
            if sym in self.prods:
                for i in xrange(1, n + 1):
                    numrest = self.countsent(rest, n - i)
                    if numrest > 0:
                        for rhs1 in self.prods[sym]:
                            total += self.countsent(rhs1, i) * numrest
            else:
                total += self.countsent(rest, n - self.weight.get(sym, 1))
            self.numsent[args] = total
        return self.numsent[args]

    def getsent(self, rhs, n, j):
        assert 0 <= j < self.countsent(rhs, n)
        if not rhs:
            return ()
        sym = rhs[0]
        rest = rhs[1:]
        if sym in self.prods:
            for i in xrange(1, n + 1):
                numrest = self.countsent(rest, n - i)
                if numrest > 0:
                    for rhs1 in self.prods[sym]:
                        dj = self.countsent(rhs1, i) * numrest
                        if dj > j:
                            j1, j2 = divmod(j, numrest)
                            return self.getsent(rhs1, i, j1) + self.getsent(rest, n - i, j2)
                        j -= dj
            assert False
        else:
            return (sym,) + self.getsent(rest, n - self.weight.get(sym, 1), j)

    def randsent(self, sym, n):
        return self.getsent((sym,), n, random.randrange(self.countsent((sym,), n)))

if __name__ == '__main__':
    g = Grammar()
    g.prod('S', 'NP', 'VP')
    g.prod('S', 'S', 'and', 'S')
    g.prod('S', 'S', 'after', 'which', 'S')
    g.prod('NP', 'the', 'N')
    g.prod('NP', 'the', 'A', 'N')
    g.prod('NP', 'the', 'A', 'A', 'N')
    g.prod('VP', 'V', 'NP')
    g.prod('N', 'dog')
    g.prod('N', 'fish')
    g.prod('N', 'bird')
    g.prod('N', 'wizard')
    g.prod('V', 'kicks')
    g.prod('V', 'meets')
    g.prod('V', 'marries')
    g.prod('A', 'red')
    g.prod('A', 'striped')
    g.prod('A', 'spotted')
    g.weight.update({'and': 0, 'after': 0, 'which': 0, 'the': 0})
    for i in xrange(100):
        print ' '.join(g.randsent('S', 3))

Answer 2

, , , , . , , , .

, n = 3:

S → ($ {NP} ${VP}) → (($ {N}) ${VP}) → ((() ${VP}) → ... → (() (() ($ {NP})))) → ((() (() (()))))

(() (() ($ {N})))) → (() (() (()))))

...

((() ($ {V} ${N})) → ((() (() ${N}))) → ((() (( ) ())))

.

, , ( , ).

Answer 3

. , , , , .