def existsItem(self, text):
# print(str(time.clock()), "existsItem(self, text) - INIZIO")
text = text.lower()
text = self.normalizeInput(text)
if text in self.enamdict:
return True
katakanaText = romkan.hiragana_to_katakana(text)
query = """
select 1
from edict_lemmas l
where lemma = '{0}'
union all
select 1
from kotobank_lemmas kl
where lemmatitle = '{0}'
union all
select 1
from kotobank_lemmas kl
where lemmasubtitle = '{1}'
""".format(text.replace("'", "\'"), katakanaText.replace("'", "\'"))
output = len(self.connection.execute(query).fetchall()) > 0
# print(str(time.clock()), "existsItem(self, text) - FINE")
return output
def getTranslation(self, text):
# print(str(time.clock()), "getTranslation(self, text) - INIZIO")
# if text in self._translationsCache:
# return self._translationsCache[text]
if text.strip() == "":
return None
output = []
text = text.lower()
text = self.normalizeInput(text)
katakanaText = romkan.hiragana_to_katakana(text)
query = """
select ifnull((select group_concat(acc.base_form, '/')
from pitch_accents acc
where acc.kanji = l.uninflectedLemma), '') || ' ' || a.content,
1 as o
from edict_lemmas l
join edict_articles a on a.id = l.articleId
where l.lemma = '{text}'
union
select replace(
'<b>' || kl.lemmatitle || ' - ' || kl.lemmasubtitle
|| ' (' || ifnull((select group_concat(acc.base_form, '/')
from pitch_accents acc
where acc.kanji = kl.lemmatitle), '')
|| ')</b><br/>' || ka.content,
'()',
''),
2 as o
from kotobank_lemmas kl
join kotobank_rel_lemma_article rel on kl.id = rel.lemmaid
join kotobank_articles ka on ka.id = rel.articleId
where (kl.lemmatitle = '{text}'
or kl.lemmasubtitle = '{katakanaText}'
or kl.lemmatitle in (select el.uninflectedlemma from edict_lemmas el where el.lemma = '{text}')
or kl.lemmasubtitle in (select el.uninflectedlemma from edict_lemmas el where el.lemma = '{katakanaText}')
) and ka.dictionary = 'デジタル大辞泉の解説'
order by o
""".format(text = text.replace("'", "\'"), katakanaText = katakanaText.replace("'", "\'"))
for entry in self.connection.execute(query).fetchall():
entry = entry[0]
entry = entry.replace("</a>", "") \
.replace("</img>", "") \
.replace("</spellout>", "") \
.replace("</section>", "")
entry = re.sub("<(a|img|section|spellout) .*?>", "", entry) #remove links
# entry = re.sub("<img .*?>", "", entry) #remove images
output.append(entry)
# self._translationsCache[text] = output
# print(str(time.clock()), "getTranslation(self, text) - FINE")
if text in self.enamdict:
output += self.enamdict[text]
if output == []:
return None
else:
return output
