def test_add_spelling():
schema = fields.Schema(text1=fields.TEXT, text2=fields.TEXT)
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text1=u("render zorro kaori postal"), text2=u("alfa"))
w.add_document(text1=u("reader zebra koala pastry"), text2=u("alpa"))
w.add_document(text1=u("leader libra ooala paster"), text2=u("alpha"))
w.add_document(text1=u("feeder lorry zoala baster"), text2=u("olfo"))
w.commit()
with ix.reader() as r:
assert not r.has_word_graph("text1")
assert not r.has_word_graph("text2")
from whoosh.writing import add_spelling
add_spelling(ix, ["text1", "text2"])
with ix.reader() as r:
assert r.has_word_graph("text1")
assert r.has_word_graph("text2")
sp = spelling.ReaderCorrector(r, "text1")
assert sp.suggest(u("kaola"), maxdist=1) == [u('koala')]
assert sp.suggest(u("kaola"), maxdist=2) == [
u('koala'), u('kaori'),
u('ooala'), u('zoala')
]
sp = spelling.ReaderCorrector(r, "text2")
assert sp.suggest(u("alfo"), maxdist=1) == [u("alfa"), u("olfo")]
def test_reader_corrector_nograph():
schema = fields.Schema(text=fields.TEXT)
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text=u("render zorro kaori postal"))
w.add_document(text=u("reader zebra koala pastry"))
w.add_document(text=u("leader libra ooala paster"))
w.add_document(text=u("feeder lorry zoala baster"))
w.commit()
with ix.reader() as r:
sp = spelling.ReaderCorrector(r, "text")
assert sp.suggest(u("kaola"), maxdist=1) == ['koala']
assert sp.suggest(u("kaola"),
maxdist=2) == ['koala', 'kaori', 'ooala', 'zoala']
def test_reader_corrector():
schema = fields.Schema(text=fields.TEXT())
with TempIndex(schema) as ix:
with ix.writer() as w:
w.add_document(text=u"render zorro kaori postal")
w.add_document(text=u"reader zebra koala pastry")
w.add_document(text=u"leader libra oola paster")
w.add_document(text=u"feeder lorry zoala baster")
with ix.reader() as r:
sp = spelling.ReaderCorrector(r, "text", schema["text"])
assert sp.suggest(u"koala", maxdist=1) == [u'koala', u"zoala"]
target = [u'kaori', u'koala', u'oola']
sugs = sp.suggest(u"kaola", maxdist=2)
assert sugs == target
def test_unicode_spelling():
schema = fields.Schema(text=fields.ID())
domain = [
u"\u0924\u092a\u093e\u0907\u0939\u0930\u0941",
u"\u65e5\u672c",
u"\uc774\uc124\ud76c",
]
with TempIndex(schema) as ix:
with ix.writer() as w:
for word in domain:
w.add_document(text=word)
with ix.reader() as r:
rc = spelling.ReaderCorrector(r, "text", schema["text"])
assert rc.suggest(u"\u65e5\u672e\u672c") == [u"\u65e5\u672c"]
def test_reader_corrector():
schema = fields.Schema(text=fields.TEXT(spelling=True))
ix = RamStorage().create_index(schema)
w = ix.writer()
w.add_document(text=u("render zorro kaori postal"))
w.add_document(text=u("reader zebra koala pastry"))
w.add_document(text=u("leader libra ooala paster"))
w.add_document(text=u("feeder lorry zoala baster"))
w.commit()
with ix.reader() as r:
assert r.has_word_graph("text")
sp = spelling.ReaderCorrector(r, "text")
assert_equal(sp.suggest(u("kaola"), maxdist=1), [u('koala')])
assert_equal(
sp.suggest(u("kaola"), maxdist=2),
[u('koala'), u('kaori'),
u('ooala'), u('zoala')])
def test_unicode_spelling():
schema = fields.Schema(text=fields.ID(spelling=True))
domain = [
u("\u0924\u092a\u093e\u0907\u0939\u0930\u0941"),
u("\u65e5\u672c"),
u("\uc774\uc124\ud76c"),
]
ix = RamStorage().create_index(schema)
with ix.writer() as w:
for word in domain:
w.add_document(text=word)
with ix.reader() as r:
assert r.has_word_graph("text")
c = r._get_graph().cursor("text")
assert list(c.flatten_strings()) == domain
assert list(r.word_graph("text").flatten_strings()) == domain
rc = spelling.ReaderCorrector(r, "text")
assert rc.suggest(u("\u65e5\u672e\u672c")) == [u("\u65e5\u672c")]