def test_ngram(self):
self.assertJson(query.ngram("str"), '{"ngram":"str"}')
self.assertJson(query.ngram(["str0", "str1"]),
'{"ngram":["str0","str1"]}')
self.assertJson(query.ngram("str", min=2, max=3),
'{"max":3,"min":2,"ngram":"str"}')
self.assertJson(query.ngram(["str0", "str1"], min=2, max=3),
'{"max":3,"min":2,"ngram":["str0","str1"]}')
def test_ngram(self):
self.assertEqual(self._q(query.ngram("what")),
["w", "wh", "h", "ha", "a", "at", "t"])
self.assertEqual(self._q(query.ngram("what", min=2, max=3)),
["wh", "wha", "ha", "hat", "at"])
self.assertEqual(
self._q(query.ngram(["john", "doe"])),
["j", "jo", "o", "oh", "h", "hn", "n", "d", "do", "o", "oe", "e"])
self.assertEqual(self._q(query.ngram(["john", "doe"], min=3, max=4)),
["joh", "john", "ohn", "doe"])
def wordPartsGenerator(word):
return q.let(
{
"indexes":
q.map_(
# Reduce this array if you want less ngrams per word.
# Setting it to [ 0 ] would only create the word itself, Setting it to [0, 1] would result in the word itself
# and all ngrams that are one character shorter, etc..
lambda index: q.subtract(q.length(word), index),
maxNgrams),
"indexesFiltered":
q.filter_(
# left min parts length 3
lambda l: q.gte(l, 3),
q.var('indexes')),
"ngramsArray":
q.distinct(
q.union(
q.map_(lambda l: q.ngram(q.lowercase(word), l, l),
q.var('indexesFiltered'))))
},
q.var('ngramsArray'))