qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-12 21:29:59 +02:00
Code Issues Releases Wiki Activity

🐛 Update tests for ExtractedText

Browse source 
In PR gh-72, @maxbachmann introduced a new argument for ExtractedText(). Update the
corresponding tests.
This commit is contained in:
Gerber, Mike 2023-01-27 19:13:45 +01:00
parent f48e305347
commit a18b25b163
1 changed files with 19 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

31
qurator/dinglehopper/tests/extracted_text_test.py
View file

@ -13,12 +13,13 @@ def test_text():
test1 = ExtractedText(
None,
[
ExtractedText("s0", None, None, "foo"),
ExtractedText("s1", None, None, "bar"),
ExtractedText("s2", None, None, "bazinga"),
ExtractedText("s0", None, None, "foo", grapheme_clusters("foo")),
ExtractedText("s1", None, None, "bar", grapheme_clusters("bar")),
ExtractedText("s2", None, None, "bazinga", grapheme_clusters("bazinga")),
],
" ",
None,
None,
)
assert test1.text == "foo bar bazinga"
@ -29,8 +30,12 @@ def test_text():
def test_normalization_check():
with pytest.raises(ValueError, match=r".*is not in NFC.*"):
ExtractedText("foo", None, None, unicodedata.normalize("NFD", "Schlyñ"))
assert ExtractedText("foo", None, None, unicodedata.normalize("NFC", "Schlyñ"))
ExtractedText("foo", None, None,
unicodedata.normalize("NFD", "Schlyñ"),
grapheme_clusters(unicodedata.normalize("NFD", "Schlyñ")))
assert ExtractedText("foo", None, None,
unicodedata.normalize("NFC", "Schlyñ"),
grapheme_clusters(unicodedata.normalize("NFC", "Schlyñ")))
AlignmentElement = namedtuple("AlignmentElement", "left right left_id right_id")
@ -47,25 +52,27 @@ def test_align():
test1 = ExtractedText(
None,
[
ExtractedText("s0", None, None, "foo"),
ExtractedText("s1", None, None, "bar"),
ExtractedText("s2", None, None, "batzinga"),
ExtractedText("s0", None, None, "foo", grapheme_clusters("foo")),
ExtractedText("s1", None, None, "bar", grapheme_clusters("bar")),
ExtractedText("s2", None, None, "batzinga", grapheme_clusters("batzinga")),
],
" ",
None,
None,
)
test2 = ExtractedText(
None,
[
ExtractedText("x0", None, None, "foo"),
ExtractedText("x1", None, None, "bar"),
ExtractedText("x0", None, None, "foo", grapheme_clusters("foo")),
ExtractedText("x1", None, None, "bar", grapheme_clusters("bar")),
# extra .
ExtractedText("x2", None, None, "."),
ExtractedText("x2", None, None, ".", grapheme_clusters(".")),
# deletion + different grapheme cluster, m̃ also is two Python characters
ExtractedText("x3", None, None, "bazim̃ga"),
ExtractedText("x3", None, None, "bazim̃ga", grapheme_clusters("bazim̃ga")),
],
" ",
None,
None,
)
left_pos = 0