def test_concordance_slots_regions(germaparl):
corpus = get_corpus(germaparl)
query = (
r'[pos="NE"]? @1[pos="NE"] @2"\[" ([word="[A-Z]+"]+ "/"?)+ @3"\]"')
df_dump = corpus.query(query,
context=10,
context_break='s',
match_strategy='longest',
corrections={
2: +1,
3: -1
}).df
concordance = Concordance(corpus, df_dump)
lines = concordance.slots(df_dump, ['word'], slots=[['match', 1], [2, 3]])
assert (set(lines.columns) == {"word", "match..1_word", "2..3_word"})
def test_concordance_slots_singletons(germaparl):
corpus = get_corpus(germaparl)
query = (
r'[pos="NE"]? @1[pos="NE"] @2"\[" ([word="[A-Z]+"]+ "/"?)+ @3"\]"')
df_dump = corpus.query(query,
context=2,
context_break='s',
match_strategy='longest',
corrections={
2: +1,
3: -1
}).df
concordance = Concordance(corpus, df_dump)
lines = concordance.slots(df_dump, ['word', 'lemma'])
assert (set(lines.columns) == {
"word", "lemma", "1_word", "1_lemma", "2_word", "2_lemma", "3_word",
"3_lemma", "match..matchend_word", "match..matchend_lemma"
})