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

test: eigene Beispielrede statt echter Reden, testdaten/ nur noch lokal

Browse source 
Die Abschriften echter Reden sind urheberrechtlich geschützt und gehören
nicht in ein öffentliches Repository. Die Tests nutzen jetzt eine frei
erfundene Festrede (tests/daten/beispiel.de.vtt/.txt, YouTube-Format mit
rollendem Fenster) mit eigenem Glossar. testdaten/ steht in .gitignore;
liegen die Reden dort lokal, laufen die Tests ihrer Glossare zusätzlich,
sonst werden sie übersprungen.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-10-11 22:14:49 +02:00
commit 93fb99eda2
1 changed files with 3134 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

48
tests/test_vtt2txt.py
View file

@ -8,8 +8,10 @@ import pytest
import vtt2txt
REPO = Path(__file__).resolve().parent.parent
SAMPLE_VTT = REPO / "testdaten" / "ramstein.de.vtt"
SAMPLE_TXT = REPO / "testdaten" / "ramstein.de.txt"
# Own, made-up sample speech; real speeches are only kept locally in testdaten/
SAMPLE_VTT = REPO / "tests" / "daten" / "beispiel.de.vtt"
SAMPLE_TXT = REPO / "tests" / "daten" / "beispiel.de.txt"
SPEECHES = REPO / "testdaten"
@pytest.fixture
@ -107,15 +109,27 @@ def test_is_rolling(cues, expected):
def test_main_default_output_matches_sample(sample_copy, monkeypatch, capsys):
run_main(monkeypatch, "-i", sample_copy)
target = sample_copy.with_name("ramstein.de.txt")
target = sample_copy.with_name("beispiel.de.txt")
assert target.read_text(encoding="utf-8") == SAMPLE_TXT.read_text(encoding="utf-8")
assert f"Erstellt: {target}" in capsys.readouterr().out
@pytest.mark.parametrize("name", ["ramstein.de", "magdeburg.de-orig", "Lahnstein.de-orig"])
def test_sample_vtt_gives_sample_txt(name):
vtt = (REPO / "testdaten" / f"{name}.vtt").read_text(encoding="utf-8-sig")
txt = (REPO / "testdaten" / f"{name}.txt").read_text(encoding="utf-8")
def speech(name):
"""A real speech, only kept locally (copyright): skipped without it."""
path = SPEECHES / name
return pytest.param(path, marks=pytest.mark.skipif(
not path.is_file(), reason="echte Reden nur lokal in testdaten/"
))
@pytest.mark.parametrize("vtt_path", [
SAMPLE_VTT,
speech("ramstein.de.vtt"), speech("magdeburg.de-orig.vtt"),
speech("Lahnstein.de-orig.vtt"),
])
def test_sample_vtt_gives_sample_txt(vtt_path):
vtt = vtt_path.read_text(encoding="utf-8-sig")
txt = vtt_path.with_suffix(".txt").read_text(encoding="utf-8")
assert vtt2txt.vtt_to_lines(vtt) == txt.splitlines()
@ -128,9 +142,9 @@ def test_main_multiple_inputs(sample_copy, monkeypatch):
def test_main_expands_glob_without_duplicates(sample_copy, monkeypatch, capsys):
shutil.copy(sample_copy, sample_copy.with_name("ramstein.en.vtt"))
shutil.copy(sample_copy, sample_copy.with_name("beispiel.en.vtt"))
shutil.copy(sample_copy, sample_copy.with_name("anders.de.vtt"))
run_main(monkeypatch, "-i", sample_copy.parent / "ramstein.*.vtt", sample_copy)
run_main(monkeypatch, "-i", sample_copy.parent / "beispiel.*.vtt", sample_copy)
out = capsys.readouterr().out
assert out.count("Erstellt:") == 2
assert not sample_copy.with_name("anders.de.txt").exists()
@ -144,7 +158,7 @@ def test_main_output_directory(sample_copy, monkeypatch, make_dir, suffix):
if make_dir:
out_dir.mkdir()
run_main(monkeypatch, "-i", sample_copy, second, "-o", f"{out_dir}{suffix}")
assert (out_dir / "ramstein.de.txt").is_file()
assert (out_dir / "beispiel.de.txt").is_file()
assert (out_dir / "rede.en.txt").is_file()
@ -176,7 +190,7 @@ def test_main_bad_file_continues_batch(sample_copy, monkeypatch, capsys, content
(["-i", "{txt}"], "Keine VTT-Datei"),
(["-i", "{vtt}", "{vtt2}", "-o", "{dir}/x.txt"], "muss -o/--output ein Verzeichnis sein"),
(["-i", "{dir}/*.gibtsnicht"], "Keine Datei passt zu"),
(["-i", "{vtt}", "{dir}/sub/ramstein.de.vtt", "-o", "{dir}/"], "dieselbe Ausgabedatei"),
(["-i", "{vtt}", "{dir}/sub/beispiel.de.vtt", "-o", "{dir}/"], "dieselbe Ausgabedatei"),
(["-i", "{vtt}", "-o", "{vtt}"], "nicht die Eingabedatei"),
])
def test_cli_errors(sample_copy, monkeypatch, capsys, args, message):
@ -417,7 +431,7 @@ def test_split_segments_inverts_join_segments():
def test_main_time_range_default_name(sample_copy, monkeypatch):
run_main(monkeypatch, "-i", sample_copy, "-z", "0:00:30-0:01")
target = sample_copy.with_name("ramstein.de_00-00-30_bis_00-01-00.txt")
target = sample_copy.with_name("beispiel.de_00-00-30_bis_00-01-00.txt")
full = SAMPLE_TXT.read_text(encoding="utf-8").splitlines()
part = target.read_text(encoding="utf-8").splitlines()
assert vtt2txt.HEADER.fullmatch(part[0])
@ -426,17 +440,17 @@ def test_main_time_range_default_name(sample_copy, monkeypatch):
def test_main_several_ranges(sample_copy, monkeypatch):
run_main(monkeypatch, "-i", sample_copy, "-z", "0:01-0:02 0:05")
target = sample_copy.with_name("ramstein.de_00-01-00_bis_00-02-00+ab_00-05-00.txt")
target = sample_copy.with_name("beispiel.de_00-01-00_bis_00-02-00+ab_00-05-00.txt")
segments = vtt2txt.split_segments(target.read_text(encoding="utf-8"))
assert [header for header, _ in segments] == [
"[00:00:56 - 00:02:09]", "[00:04:57 - 00:48:07]",
"[00:00:59 - 00:02:03]", "[00:04:58 - 00:13:10]",
]
@pytest.mark.parametrize("ranges", [["0:01-0:02 0:05"], ["0:01-0:02", "0:05"]])
def test_main_ranges_with_or_without_quotes(sample_copy, monkeypatch, ranges):
run_main(monkeypatch, "-i", sample_copy, "-z", *ranges)
target = sample_copy.with_name("ramstein.de_00-01-00_bis_00-02-00+ab_00-05-00.txt")
target = sample_copy.with_name("beispiel.de_00-01-00_bis_00-02-00+ab_00-05-00.txt")
assert target.is_file()
@ -456,8 +470,8 @@ def test_range_argv(argv, expected):
def test_main_range_from_beginning(sample_copy, monkeypatch, ranges):
args = ranges if ranges[0].startswith("-z") else ["-z", *ranges]
run_main(monkeypatch, "-i", sample_copy, *args)
target = sample_copy.with_name("ramstein.de_bis_00-01-00.txt")
assert target.read_text(encoding="utf-8").startswith("[00:00:09 - ")
target = sample_copy.with_name("beispiel.de_bis_00-01-00.txt")
assert target.read_text(encoding="utf-8").startswith("[00:00:00 - ")
def test_main_time_range_without_captions(sample_copy, monkeypatch, capsys):