def test_find_self():
wordlist = sorted(u("book bake bike bone").split())
st = RamStorage()
f = st.create_file("test")
spelling.wordlist_to_graph_file(wordlist, f)
gr = fst.GraphReader(st.open_file("test"))
gc = spelling.GraphCorrector(gr)
assert gc.suggest("book")[0] != "book"
assert gc.suggest("bake")[0] != "bake"
assert gc.suggest("bike")[0] != "bike"
assert gc.suggest("bone")[0] != "bone"
def test_insert_bytes():
# This test is only meaningful on Python 3
domain = [b("alfa"), b("bravo"), b("charlie")]
st = RamStorage()
gw = fst.GraphWriter(st.create_file("test"))
gw.start_field("test")
for key in domain:
gw.insert(key)
gw.close()
cur = fst.GraphReader(st.open_file("test")).cursor()
assert list(cur.flatten()) == domain
def __init__(self, word_file, graph_file):
dirname = os.path.dirname(graph_file)
st = FileStorage(dirname)
f = st.open_file(graph_file)
gr = fst.GraphReader(f)
self.graph = gr
self.dict = {}
with codecs.open(word_file,'r','utf-8') as file:
for line in file:
tokens = line.split(" ")
if len(tokens) >= 2:
self.dict[tokens[0].strip()] = int(tokens[1].strip())
def _fst_roundtrip(domain, t):
with TempStorage() as st:
f = st.create_file("test")
gw = fst.GraphWriter(f, vtype=t)
gw.start_field("_")
for key, value in domain:
gw.insert(key, value)
gw.finish_field()
gw.close()
f = st.open_file("test")
gr = fst.GraphReader(f, vtype=t)
cur = fst.Cursor(gr)
assert list(cur.flatten_v()) == domain
f.close()
def test_insert_unicode():
domain = [
u("\u280b\u2817\u2801\u281d\u2809\u2811"),
u("\u65e5\u672c"),
u("\uc774\uc124\ud76c"),
]
st = RamStorage()
gw = fst.GraphWriter(st.create_file("test"))
gw.start_field("test")
for key in domain:
gw.insert(key)
gw.close()
cur = fst.GraphReader(st.open_file("test")).cursor()
assert list(cur.flatten_strings()) == domain
def test_within_unicode():
domain = [
u("\u280b\u2817\u2801\u281d\u2809\u2811"),
u("\u65e5\u672c"),
u("\uc774\uc124\ud76c"),
]
st = RamStorage()
gw = fst.GraphWriter(st.create_file("test"))
gw.start_field("test")
for key in domain:
gw.insert(key)
gw.close()
gr = fst.GraphReader(st.open_file("test"))
s = list(fst.within(gr, u("\uc774.\ud76c")))
assert s == [u("\uc774\uc124\ud76c")]
def test_fields():
with TempStorage() as st:
f = st.create_file("test")
gw = fst.GraphWriter(f)
gw.start_field("f1")
gw.insert("a")
gw.insert("aa")
gw.insert("ab")
gw.finish_field()
gw.start_field("f2")
gw.insert("ba")
gw.insert("baa")
gw.insert("bab")
gw.close()
gr = fst.GraphReader(st.open_file("test"))
cur1 = fst.Cursor(gr, gr.root("f1"))
cur2 = fst.Cursor(gr, gr.root("f2"))
assert list(cur1.flatten_strings()) == ["a", "aa", "ab"]
assert list(cur2.flatten_strings()) == ["ba", "baa", "bab"]
gr.close()
def words_to_corrector(words):
st = RamStorage()
f = st.create_file("test")
spelling.wordlist_to_graph_file(words, f)
f = st.open_file("test")
return spelling.GraphCorrector(fst.GraphReader(f))
def greader(st):
return fst.GraphReader(st.open_file("test"))