def test_parse(self):
# Assert parsed output with Penn Treebank II tags (slash-formatted).
# "il gatto nero" is a noun phrase, "sulla stuoia" is a prepositional noun phrase.
v = it.parser.parse(u"Il gatto nero seduto sulla stuoia.")
self.assertEqual(v,
u"Il/DT/B-NP/O gatto/NN/I-NP/O nero/JJ/I-NP/O " +
u"seduto/VB/B-VP/O " + \
u"sulla/IN/B-PP/B-PNP stuoia/NN/B-NP/I-PNP ././O/O"
)
# Assert the accuracy of the Italian tagger.
i, n = 0, 0
for sentence in open(
os.path.join(PATH, "corpora",
"tagged-it-wacky.txt")).readlines():
sentence = sentence.decode("utf-8").strip()
s1 = [w.split("/") for w in sentence.split(" ")]
s2 = [[w for w, pos in s1]]
s2 = it.parse(s2, tokenize=False)
s2 = [w.split("/") for w in s2.split(" ")]
for j in range(len(s1)):
t1 = s1[j][1]
t2 = s2[j][1]
# WaCKy test set tags plural nouns as "NN", pattern.it as "NNS".
# Some punctuation marks are also tagged differently,
# but these are not necessarily errors.
if t1 == t2 or (t1 == "NN" and
t2.startswith("NN")) or s1[j][0] in "\":;)-":
i += 1
n += 1
#print(float(i) / n)
self.assertTrue(float(i) / n > 0.92)
print("pattern.it.parser.parse()")
def test_parse(self):
# Assert parsed output with Penn Treebank II tags (slash-formatted).
# "il gatto nero" is a noun phrase, "sulla stuoia" is a prepositional noun phrase.
v = it.parser.parse(u"Il gatto nero seduto sulla stuoia.")
self.assertEqual(v,
u"Il/DT/B-NP/O gatto/NN/I-NP/O nero/JJ/I-NP/O " +
u"seduto/VB/B-VP/O " + \
u"sulla/IN/B-PP/B-PNP stuoia/NN/B-NP/I-PNP ././O/O"
)
# Assert the accuracy of the Italian tagger.
i, n = 0, 0
for sentence in open(os.path.join(PATH, "corpora", "tagged-it-wacky.txt")).readlines():
sentence = sentence.decode("utf-8").strip()
s1 = [w.split("/") for w in sentence.split(" ")]
s2 = [[w for w, pos in s1]]
s2 = it.parse(s2, tokenize=False)
s2 = [w.split("/") for w in s2.split(" ")]
for j in range(len(s1)):
t1 = s1[j][1]
t2 = s2[j][1]
# WaCKy test set tags plural nouns as "NN", pattern.it as "NNS".
# Some punctuation marks are also tagged differently,
# but these are not necessarily errors.
if t1 == t2 or (t1 == "NN" and t2 == "NNS") or s1[j][0] in "\":;)-":
i += 1
n += 1
#print float(i) / n
self.assertTrue(float(i) / n > 0.92)
print "pattern.it.parser.parse()"
def lemmatize_word(input_word):
in_word = input_word #.decode('utf-8')
word_it = parse(in_word,
tokenize=False,
tag=False,
chunk=False,
lemmata=True)
the_lemmatized_word = word_it.split()[0][0][4]
return the_lemmatized_word
def _getParse(word, language):
import pattern.en as pattern_en # @UnresolvedImport
import pattern.es as pattern_es # @UnresolvedImport
import pattern.fr as pattern_fr # @UnresolvedImport
import pattern.de as pattern_de # @UnresolvedImport
import pattern.it as pattern_it # @UnresolvedImport
if language == "es":
return pattern_es.parse(word)
elif language == "en":
return pattern_en.parse(word)
elif language == "it":
return pattern_it.parse(word)
elif language == "fr":
return pattern_fr.parse(word)
elif language == "de":
return pattern_de.parse(word)
else:
return pattern_en.parse(word)