dschlueter/youtube_abschrift_korrigieren
Watch
1
0
Fork
You've already forked youtube_abschrift_korrigieren
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

chore: Glossare echter Beiträge nur noch lokal

Browse source 
*.glossar.txt enthält Namen realer Personen und Hörfehler realer
Beiträge und steht jetzt in .gitignore; versioniert bleibt nur das
Glossar der erfundenen Beispielrede (tests/daten/beispiel.glossar.txt).
Die Tests der echten Glossare laufen nur, wenn Reden und Glossare lokal
vorhanden sind; die URL-Tests nutzen ein eigenes Mini-Glossar.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-10-11 22:44:46 +02:00
commit 33869e5f3e
1 changed files with 39 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

20
tests/test_abschrift_korrigieren.py
View file

@ -132,10 +132,13 @@ SAMPLE_GLOSSARIES = [
]
# The real speeches are not in the repository (copyright); without them these skip
# Real speeches and their glossaries are not in the repository; without them these skip
needs_speeches = pytest.mark.skipif(
not all((SPEECHES / sample).is_file() for _, sample in SAMPLE_GLOSSARIES),
reason="echte Reden nur lokal in testdaten/",
not all(
(SPEECHES / sample).is_file() and (REPO / glossary).is_file()
for glossary, sample in SAMPLE_GLOSSARIES
) or not SHARED_GLOSSARY.is_file(),
reason="echte Reden (testdaten/) und ihre Glossare nur lokal",
)
@ -622,9 +625,16 @@ def from_url(fake_yt_dlp, yt_dlp_installed, monkeypatch):
monkeypatch.setattr(ak, "find_paragraph_starts", every_nth_start(5))
def kreml_glossary(folder):
"""The one glossary rule the fake video needs."""
path = folder / "kreml.glossar.txt"
path.write_text("Kremmel => Kreml\n", encoding="utf-8")
return path
def test_main_url_default_names(from_url, tmp_path, monkeypatch):
monkeypatch.chdir(tmp_path)
run_main(monkeypatch, "-u", URL, "-g", SHARED_GLOSSARY)
run_main(monkeypatch, "-u", URL, "-g", kreml_glossary(tmp_path))
raw = (tmp_path / "Kanal_Rede_2026-03-28.txt").read_text(encoding="utf-8")
assert raw == "Der Kremmel ist in Moskau.\nDas ist bekannt.\n"
@ -914,7 +924,7 @@ def test_main_url_several_ranges(fake_yt_dlp, yt_dlp_installed, tmp_path, monkey
monkeypatch.setattr(subprocess, "run", fake_yt_dlp(VIDEO, vtt=MULTI_VTT))
sent = chunk_recorder(monkeypatch)
monkeypatch.chdir(tmp_path)
run_main(monkeypatch, "-u", URL, "-z", "0:00:00-0:00:30 0:02", "-g", SHARED_GLOSSARY)
run_main(monkeypatch, "-u", URL, "-z", "0:00:00-0:00:30 0:02", "-g", kreml_glossary(tmp_path))
name = "Kanal_Rede_2026-03-28_bis_00-00-30+ab_00-02-00"
assert (tmp_path / f"{name}.txt").read_text(encoding="utf-8") == (