s0.add_successor('a', s1)
s0.add_successor('c', s1)
s0.add_successor('b', s3)
s0.add_successor('d', s5)
s1.add_successor('a', s2)
s3.add_successor('a', s4)
s3.add_successor('b', s4)
s5.add_successor('d', s6)
aut = Automaton(s0, set([s4,s6]))
aut = determinize(remove_lambdas(aut))
wt = automaton_to_wordtree(aut, 2)
#wt = remove_empty_subtrees(wt)
# >s0 -a,c> s1 -a> (s2)
# 4 1 1
# a:1/4 a:1
# c:1/4
# -b> s3 -a,b> (s4)
# 2 1
# b:1/2 a:1/2
# b:1/2
# aa -> 1/4
# ca -> 1/4
digi = '0123456789'
#punc = '@&"\'(§!)-$,;:=<#°_*%£?./+>{}€[]'
punc = '\'"()[]{}.,;:-@&'
text = text.lower()
a1 = text_to_automaton(text, lambda x: x.isalpha(), 0)
text = text.upper()
a2 = text_to_automaton(text, lambda x: x.isalpha(), 0)
regex = Choice(Automaton(a1), Automaton(a2))
wt3 = regex_to_wordtree(regex, 16)
text = text.lower() + text.upper()
a4 = determinize(
remove_lambdas(text_to_automaton(text, lambda x: x.isalpha(), 0)))
wt4 = automaton_to_wordtree(a4, 16)
words = ['hello', 'this', 'can', 'world', '']
for word in words:
print("a1 accepts '" + word + "' : " + str(a1.accepts(word)))
reg = Repeat(Concat(Automaton(a1), Concat(Range(digi), Range(digi))))
aut = regex_to_automaton(reg)
aut = determinize(remove_lambdas(aut))
wt = remove_empty_subtrees(automaton_to_wordtree(aut, 16))
print("wt can produce " + str(wt.wordscount) + " words.")
wt2 = automaton_to_wordtree(a1, 16)
print("wt2 can produce " + str(wt2.wordscount) + " words.")
# Checking acceptance
tests = [
'ab', 'ac', 'a', 'abcbc', 'accccc', 'abcc', 'cb', 'cac', 'acca',
'abcbbcac', 'abcd', 'abce', 'ebbbb', ''
]
for test in tests:
print('aut accepts \'' + test + '\' : ' + str(aut.accepts(test)))
# Check copy
autcopy = aut.copy()
for test in tests:
print('autcopy accepts \'' + test + '\' : ' + str(autcopy.accepts(test)))
autcopy = remove_lambdas(autcopy)
for test in tests:
print('autcopy without lambdas accepts \'' + test + '\' : ' +
str(autcopy.accepts(test)))
a1 = remove_lambdas(regex_to_automaton(Range('a')))
print("a1 accepts 'a' : " + str(a1.accepts('a')))
print("a1 accepts 'aa' : " + str(a1.accepts('aa')))
print("a1 accepts 'b' : " + str(a1.accepts('b')))
print("a1 accepts '' : " + str(a1.accepts('')))
a2 = remove_lambdas(regex_to_automaton(Concat(Range('a'), Range('b'))))
print("a2 accepts 'ab' : " + str(a2.accepts('ab')))
print("a2 accepts 'a' : " + str(a2.accepts('a')))
print("a2 accepts 'aa' : " + str(a2.accepts('aa')))
print("a2 accepts 'b' : " + str(a2.accepts('b')))
from mepgen.automaton.transformation import reject_short_words, remove_lambdas
from mepgen.regex.regex import *
from mepgen.regex.transformation import regex_to_automaton
reg = Repeat(Range('a'))
aut = regex_to_automaton(reg)
tests = ['', 'a', 'b', 'aa', 'ab', 'ba', 'aaa', 'aaaa', 'aaaaa']
for test in tests:
print("aut '{0}' : {1}".format(test, aut.accepts(test) and "accepting" or "not accepting"))
autrlw = reject_short_words(remove_lambdas(aut), 4)
for test in tests:
print("autrlw '{0}' : {1}".format(test, autrlw.accepts(test) and "accepting" or "not accepting"))
from mepgen.automaton.transformation import reject_short_words, remove_lambdas
from mepgen.regex.regex import *
from mepgen.regex.transformation import regex_to_automaton
reg = Repeat(Range('a'))
aut = regex_to_automaton(reg)
tests = ['', 'a', 'b', 'aa', 'ab', 'ba', 'aaa', 'aaaa', 'aaaaa']
for test in tests:
print("aut '{0}' : {1}".format(
test,
aut.accepts(test) and "accepting" or "not accepting"))
autrlw = reject_short_words(remove_lambdas(aut), 4)
for test in tests:
print("autrlw '{0}' : {1}".format(
test,
autrlw.accepts(test) and "accepting" or "not accepting"))
from mepgen.regex.regex import Range, Repeat, Choice, Concat, Automaton
from mepgen.regex.transformation import regex_to_automaton
from mepgen.automaton.transformation import remove_lambdas, determinize
regex = Repeat(Choice(Range(frozenset(['a'])), Range(frozenset(['b']))))
aut = regex_to_automaton(regex)
print("aut is deterministic :", aut.is_deterministic())
tests = ['', 'a', 'b', 'c', 'aa', 'ba', 'ca', 'aaa', 'aba', 'aab', 'abc']
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
aut = remove_lambdas(aut)
print("aut is deterministic :", aut.is_deterministic())
tests = ['', 'a', 'b', 'c', 'aa', 'ba', 'ca', 'aaa', 'aba', 'aab', 'abc']
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
aut = determinize(aut)
print("aut is deterministic :", aut.is_deterministic())
tests = ['', 'a', 'b', 'c', 'aa', 'ba', 'ca', 'aaa', 'aba', 'aab', 'abc']
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
from mepgen.regex.transformation import regex_to_automaton, regex_to_wordtree
f = open("lovecraft.txt", "r")
text = f.read()
f.close()
digi = '0123456789'
punc = '\'"()[]{}.,;:-@&'
alphafilter = lambda x: x.isalpha()
threshold = 0.05
minwordlen = 4
text = text.lower()
words = reject_short_words(
remove_lambdas(text_to_automaton(text, alphafilter, threshold)),
minwordlen)
text = text.upper()
WORDS = reject_short_words(
remove_lambdas(text_to_automaton(text, alphafilter, threshold)),
minwordlen)
allWords = Choice(Automaton(words), Automaton(WORDS))
sep = Choice(Range(punc), Choice(Range(digi), Concat(Range(digi),
Range(digi))))
regex = Concat(allWords, Repeat(Concat(sep, allWords)))
wordtree = regex_to_wordtree(regex, 16)
print("wordtree can produce " + str(wordtree.wordscount) + " words.")
alph = list(wordtree.get_alphabet())
alph.sort()
'acca',
'abcbbcac',
'abcd',
'abce',
'ebbbb',
'' ]
for test in tests:
print('aut accepts \'' + test + '\' : ' + str(aut.accepts(test)))
# Check copy
autcopy = aut.copy()
for test in tests:
print('autcopy accepts \'' + test + '\' : ' + str(autcopy.accepts(test)))
autcopy = remove_lambdas(autcopy)
for test in tests:
print('autcopy without lambdas accepts \'' + test + '\' : ' + str(autcopy.accepts(test)))
a1 = remove_lambdas(regex_to_automaton(Range('a')))
print("a1 accepts 'a' : " + str(a1.accepts('a')))
print("a1 accepts 'aa' : " + str(a1.accepts('aa')))
print("a1 accepts 'b' : " + str(a1.accepts('b')))
print("a1 accepts '' : " + str(a1.accepts('')))
a2 = remove_lambdas(regex_to_automaton(Concat(Range('a'),Range('b'))))
print("a2 accepts 'ab' : " + str(a2.accepts('ab')))
print("a2 accepts 'a' : " + str(a2.accepts('a')))
print("a2 accepts 'aa' : " + str(a2.accepts('aa')))
print("a2 accepts 'b' : " + str(a2.accepts('b')))
print("a2 accepts '' : " + str(a2.accepts('')))
from mepgen.regex.regex import Range, Repeat, Choice, Concat, Automaton
from mepgen.regex.transformation import regex_to_automaton
from mepgen.automaton.transformation import remove_lambdas, determinize
regex = Repeat(Choice(Range(frozenset(["a"])), Range(frozenset(["b"]))))
aut = regex_to_automaton(regex)
print("aut is deterministic :", aut.is_deterministic())
tests = ["", "a", "b", "c", "aa", "ba", "ca", "aaa", "aba", "aab", "abc"]
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
aut = remove_lambdas(aut)
print("aut is deterministic :", aut.is_deterministic())
tests = ["", "a", "b", "c", "aa", "ba", "ca", "aaa", "aba", "aab", "abc"]
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
aut = determinize(aut)
print("aut is deterministic :", aut.is_deterministic())
tests = ["", "a", "b", "c", "aa", "ba", "ca", "aaa", "aba", "aab", "abc"]
for test in tests:
print("aut accepts '" + test + "' :", str(aut.accepts(test)))
f = open("lovecraft.txt", "r")
text = f.read()
f.close()
digi = '0123456789'
punc = '\'"()[]{}.,;:-@&'
alphafilter = lambda x : x.isalpha()
threshold = 0.05
minwordlen = 4
text = text.lower()
words = reject_short_words(
remove_lambdas(
text_to_automaton(text, alphafilter, threshold)
),
minwordlen
)
text = text.upper()
WORDS = reject_short_words(
remove_lambdas(
text_to_automaton(text, alphafilter, threshold)
),
minwordlen
)
allWords = Choice(Automaton(words), Automaton(WORDS))
sep = Choice(Range(punc), Choice(Range(digi), Concat(Range(digi), Range(digi))))
regex = Concat(allWords, Repeat(Concat(sep, allWords)))
#punc = '@&"\'(§!)-$,;:=<#°_*%£?./+>{}€[]'
punc = '\'"()[]{}.,;:-@&'
text = text.lower()
a1 = text_to_automaton(text, lambda x : x.isalpha(), 0)
text = text.upper()
a2 = text_to_automaton(text, lambda x : x.isalpha(), 0)
regex = Choice(Automaton(a1), Automaton(a2))
wt3 = regex_to_wordtree(regex, 16)
text = text.lower() + text.upper()
a4 = determinize(
remove_lambdas(
text_to_automaton(text, lambda x : x.isalpha(), 0)
)
)
wt4 = automaton_to_wordtree(a4, 16)
words = ['hello', 'this', 'can', 'world', '']
for word in words:
print("a1 accepts '" + word + "' : " + str(a1.accepts(word)))
reg = Repeat(Concat(Automaton(a1), Concat(Range(digi), Range(digi))))
aut = regex_to_automaton(reg)
aut = determinize(remove_lambdas(aut))
wt = remove_empty_subtrees(automaton_to_wordtree(aut, 16))
print("wt can produce " + str(wt.wordscount) + " words.")
