feat: 標註工具與試跑 (#5)

標籤白名單、標註指示、批次切分、合併與檢查、抽查清單，以及 100 句試跑結果。 Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-14 17:35:09 +00:00
parent 9cf8196a3e
commit c85e00a56e
6 changed files with 329 additions and 0 deletions
@@ -0,0 +1,63 @@
+import json
+import tempfile
+import unittest
+from pathlib import Path
+
+import make_batches
+import merge_labels
+
+
+def rec(i, vol=1, ch=1, speaker=None, conf=None):
+    return {"id": i, "volume": vol, "chapter": ch, "text": f"對白{i}", "before": "", "after": "", "prev_par": "",
+            "next_par": "", "candidates": [], "speaker": speaker, "confidence": conf}
+
+
+class Batches(unittest.TestCase):
+    def test_neighbors_stay_inside_the_chapter_and_hide_rule_speaker(self):
+        recs = [rec("a1"), rec("a2", speaker="asuna", conf="high"), rec("a3"), rec("b1", ch=2)]
+        nb = make_batches.with_neighbors(recs)
+        self.assertEqual([x["id"] for x in nb["a2"]["prev"]], ["a1"])
+        self.assertEqual([x["id"] for x in nb["a2"]["next"]], ["a3"])
+        self.assertEqual(nb["b1"], {"prev": [], "next": []})
+        self.assertNotIn("rule_speaker", nb["a2"]["prev"][0])
+
+    def test_pilot_sample_is_stratified_and_deterministic(self):
+        recs = [rec(f"u{i}") for i in range(50)] + [rec(f"m{i}", speaker="kirito", conf="medium") for i in range(50)] \
+            + [rec(f"h{i}", speaker="asuna", conf="high") for i in range(50)]
+        a = make_batches.pilot_sample(recs, 20, 1)
+        b = make_batches.pilot_sample(recs, 20, 1)
+        self.assertEqual([r["id"] for r in a], [r["id"] for r in b])
+        kinds = [r["id"][0] for r in a]
+        self.assertEqual((kinds.count("u"), kinds.count("m"), kinds.count("h")), (10, 5, 5))
+
+
+class Check(unittest.TestCase):
+    good = {"id": "x", "speaker": "asuna", "confidence": "high", "function": "tease", "emotion": "anger", "evidence": "前段"}
+
+    def test_valid(self):
+        self.assertEqual(merge_labels.check(self.good), [])
+
+    def test_unknown_function_rejected(self):
+        self.assertTrue(merge_labels.check({**self.good, "function": "flirt"}))
+
+    def test_unknown_emotion_rejected(self):
+        self.assertTrue(merge_labels.check({**self.good, "emotion": "rage"}))
+
+    def test_extra_or_missing_fields_rejected(self):
+        self.assertTrue(merge_labels.check({**self.good, "note": "hi"}))
+        self.assertTrue(merge_labels.check({k: v for k, v in self.good.items() if k != "evidence"}))
+
+    def test_bad_confidence_rejected(self):
+        self.assertTrue(merge_labels.check({**self.good, "confidence": "sure"}))
+
+    def test_none_speaker_is_valid_but_never_final(self):
+        self.assertEqual(merge_labels.check({**self.good, "speaker": "none", "function": "other", "emotion": "neutral"}), [])
+
+    def test_whitelist_matches_prompt(self):
+        prompt = (Path(__file__).with_name("label_prompt.md")).read_text(encoding="utf-8")
+        self.assertIn("tags.json", prompt)
+        self.assertIn("other", merge_labels.TAGS["functions"])
+
+
+if __name__ == "__main__":
+    unittest.main()