feat: 段落分割 split_paragraphs(通用空行分词)
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
from genesis.parsers.paragraph_splitter import split_paragraphs
|
||||
|
||||
|
||||
def test_empty_matrix():
|
||||
assert split_paragraphs([]) == []
|
||||
|
||||
|
||||
def test_single_paragraph_no_empty_rows():
|
||||
m = [["a", "b"], ["c", "d"]]
|
||||
assert split_paragraphs(m) == [(0, 1)]
|
||||
|
||||
|
||||
def test_split_on_middle_empty_row():
|
||||
m = [["a"], [], ["b"], ["c"], []]
|
||||
assert split_paragraphs(m) == [(0, 0), (2, 3)]
|
||||
|
||||
|
||||
def test_trailing_empty_rows_no_extra_paragraph():
|
||||
m = [["a"], [], [], []]
|
||||
assert split_paragraphs(m) == [(0, 0)]
|
||||
|
||||
|
||||
def test_leading_empty_rows_start_at_first_nonempty():
|
||||
m = [[], ["a"], [], ["b"]]
|
||||
assert split_paragraphs(m) == [(1, 1), (3, 3)]
|
||||
Reference in New Issue
Block a user