Spaces:
Running
Running
unknown
Claude Opus 5.5
Add meaning check, Groq model fallback and subject test run; close guard gaps
689da70 | import detector as D | |
| def _blocks(*paras): | |
| return D.classify([D.Block(D._norm(p)) for p in paras], D.PASTE_MIN_WORDS) | |
| def test_split_keeps_every_character(): | |
| for s in ['He said "stop." Then left. The U.S. economy grew.', | |
| "The model (trained in 2020.) Was good. It won [3]. [4] shows more. (See Fig. 2.) Next one.", | |
| "It rose by 3.5 %. Then it fell (see Fig. 2). Smith et al. reported this."]: | |
| assert " ".join(D.split_sentences(s)) == s | |
| def test_windows_cover_every_sentence(): | |
| lengths = [12, 30, 8, 25, 40, 5, 18, 22, 350, 9] | |
| w = D.make_windows(lengths) | |
| covered = {k for a, b in w for k in range(a, b)} | |
| assert covered == set(range(len(lengths))) | |
| assert all(a < b for a, b in w) | |
| def test_analyse_and_summarise_with_a_fake_scorer(): | |
| paras = ["This sentence is written by a machine for sure. Another machine sentence follows it here.", | |
| "A human wrote this one on a slow afternoon. And this one too, with some care."] | |
| blocks = _blocks(*paras) | |
| D.analyse(blocks, scorer=lambda texts: [1.0 if "machine" in t and "human" not in t else 0.0 for t in texts]) | |
| stats = D.summarise(blocks, 0.8, 0.5) | |
| assert stats["analysed"] == sum(len(p.split()) for p in paras) | |
| assert 0 <= stats["pct"] <= 100 | |
| assert all(len(b.scores) == len(b.sents) for b in blocks if b.kind == "para") | |
| def test_score_cache_scores_each_text_once(monkeypatch): | |
| calls = [] | |
| def fake(texts): | |
| calls.append(list(texts)) | |
| return [len(t) / 100 for t in texts] | |
| monkeypatch.setattr(D, "_score_uncached", fake) | |
| monkeypatch.setattr(D, "_score_cache", {}) | |
| out = D.score_texts(["bbb", "a", "bbb", "cc"]) | |
| assert out == [0.03, 0.01, 0.03, 0.02] | |
| assert calls == [["a", "cc", "bbb"]] # unique, shortest first | |
| assert D.score_texts(["a", "dddd"]) == [0.01, 0.04] | |
| assert calls[-1] == ["dddd"] # only the new text reaches the model | |
| assert D.score_texts([]) == [] | |
| def test_names_and_case_citations_do_not_end_a_sentence(): | |
| import textparse as TP | |
| cases = { | |
| "The Court in Justice K.S. Puttaswamy v. Union of India (2017) recognised privacy. It shapes the law.": 2, | |
| "It grew in the U.S. The economy then slowed. In the U.K. it did not.": 3, | |
| "The dose for group A. Results were clear. Written by J. Smith and A. Kumar in 2020. Then done.": 4, | |
| "The fluid moves at velocity v. The pressure drops. See Roe v. Wade for more.": 3, | |
| } | |
| for text, n in cases.items(): | |
| assert len(TP.split_sentences(text)) == n, text | |
| assert D.split_sentences(text) == TP.split_sentences(text) | |