dschlueter
95bdc660ca
- „Bahrs“ → „Bahr’s“ ist jetzt eine Änderung; ’ ' ` gelten als gleich, Anführungszeichen am Wortrand zählen weiterhin nicht - Prüfmarken auch englisch: [check: …] - output/ (eigene Ergebnisse und Testläufe) in .gitignore Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
119 lines
4.4 KiB
Python
119 lines
4.4 KiB
Python
"""Tests for aenderungen.py (change report raw transcript -> corrected text)."""
|
||
import html
|
||
import re
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
import pytest
|
||
|
||
import aenderungen as ae
|
||
|
||
|
||
def changes(raw, corrected):
|
||
return [(tag, " ".join(old), " ".join(new))
|
||
for tag, old, new in ae.compare(raw, corrected).changes()]
|
||
|
||
|
||
def report_text(page):
|
||
"""Corrected text as shown in the report, without original/deleted words."""
|
||
body = page.split("<h2>Korrigierter Text</h2>")[1]
|
||
body = re.sub(r"<del[^>]*>.*?</del>|<span class=orig>.*?</span>", "", body)
|
||
return html.unescape(re.sub(r"<[^>]+>", " ", body)).split()
|
||
|
||
|
||
@pytest.mark.parametrize("raw, corrected", [
|
||
("das ist gut", "Das ist gut."), # case, punctuation
|
||
("all das zerstritten", "All das – zerstritten."), # dash only
|
||
("wie z.B. hier", "wie z. B. hier"), # split abbreviation
|
||
("eins zwei", "eins\n\nzwei"), # paragraph break
|
||
])
|
||
def test_expected_edits_are_no_changes(raw, corrected):
|
||
assert changes(raw, corrected) == []
|
||
|
||
|
||
@pytest.mark.parametrize("raw, corrected", [
|
||
("gibt's", "gibt’s"), # apostrophe variants
|
||
("er sagte Frieden", "Er sagte ‚Frieden‘."), # quotes at the edges
|
||
])
|
||
def test_apostrophes_and_quotes_unchanged(raw, corrected):
|
||
assert changes(raw, corrected) == []
|
||
|
||
|
||
def test_apostrophe_inside_word_is_a_change():
|
||
assert changes("Egon Bahrs Politik", "Egon Bahr’s Politik") == [
|
||
("replace", "Bahrs", "Bahr’s"),
|
||
]
|
||
|
||
|
||
def test_english_review_marks():
|
||
comparison = ae.compare("his name is Kocher", "His name is Kocher [check: Kocha].")
|
||
assert list(comparison.changes()) == []
|
||
assert sum(len(m) for m in comparison.marks.values()) == 1
|
||
|
||
|
||
def test_replace_insert_delete():
|
||
raw = "die gedeiliche Zusammenarbeit war das gut heute"
|
||
corrected = "die gedeihliche Zusammenarbeit war doch gut"
|
||
assert changes(raw, corrected) == [
|
||
("replace", "gedeiliche", "gedeihliche"),
|
||
("replace", "das", "doch"),
|
||
("delete", "heute", ""),
|
||
]
|
||
assert changes("ein Wort", "ein neues Wort") == [("insert", "", "neues")]
|
||
|
||
|
||
def test_change_summary_counts_and_sorts():
|
||
raw = "Kremmel und Kremmel und Bar"
|
||
corrected = "Kreml und Kreml und Bahr"
|
||
assert ae.change_summary(ae.compare(raw, corrected)) == [
|
||
("Kremmel", "Kreml", 2), ("Bar", "Bahr", 1),
|
||
]
|
||
|
||
|
||
def test_review_marks_are_not_changes_but_shown():
|
||
corrected = "Er heißt Gerhard [prüfen: Ghard] Kocher."
|
||
comparison = ae.compare("Er heißt Gerhard Kocher", corrected)
|
||
assert list(comparison.changes()) == []
|
||
page = ae.render_html(comparison, "t")
|
||
assert "<span class=check>[prüfen: Ghard]</span>" in page
|
||
assert "1 Prüfmarken" in page
|
||
|
||
|
||
def test_render_html_shows_text_original_and_paragraphs():
|
||
raw = "die gedeiliche Zusammenarbeit <b> ist gut heute neuer Absatz"
|
||
corrected = "Die gedeihliche Zusammenarbeit <b> ist gut.\n\nNeuer Absatz."
|
||
page = ae.render_html(ae.compare(raw, corrected), "Rede & Co")
|
||
|
||
assert report_text(page) == corrected.split()
|
||
assert "title='Original: gedeiliche'" in page
|
||
assert "<del title='gestrichen'>heute</del>" in page
|
||
assert "<b>" in page and "<b>" not in page.split("<body>")[1]
|
||
assert "Rede & Co" in page
|
||
assert page.split("<h2>Korrigierter Text</h2>")[1].count("<p>") == 2
|
||
|
||
|
||
def test_report_path():
|
||
assert ae.report_path(Path("a/rede.korrigiert.txt")) == Path("a/rede.aenderungen.html")
|
||
assert ae.report_path(Path("out.txt")) == Path("out.aenderungen.html")
|
||
|
||
|
||
def test_cli(tmp_path, monkeypatch, capsys):
|
||
raw = tmp_path / "rede.vtt"
|
||
raw.write_text(
|
||
"WEBVTT\n\n00:00:01.000 --> 00:00:02.000\ndas Kremmel heute\n", encoding="utf-8"
|
||
)
|
||
corrected = tmp_path / "rede.korrigiert.txt"
|
||
corrected.write_text("Das Kreml heute.\n", encoding="utf-8")
|
||
monkeypatch.setattr(sys, "argv", ["aenderungen.py", "-a", str(raw), "-b", str(corrected)])
|
||
ae.main()
|
||
|
||
assert (tmp_path / "rede.aenderungen.html").is_file()
|
||
out = capsys.readouterr().out
|
||
assert "1× „Kremmel“ → „Kreml“" in out
|
||
|
||
|
||
def test_cli_missing_file(tmp_path, monkeypatch, capsys):
|
||
monkeypatch.setattr(sys, "argv", ["aenderungen.py", "-a", "fehlt.txt", "-b", "fehlt.txt"])
|
||
with pytest.raises(SystemExit):
|
||
ae.main()
|
||
assert "Datei nicht gefunden" in capsys.readouterr().err
|