feat: wiki 讀取與對白抽取腳本 (#4)

fetch_wiki.py 用 tea 讀取 wiki；extract_dialogues.py 抽出「」對白與前後文，
並用規則判定明確的說話者。原文與輸出放在 repo 之外。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

tools/corpus/test_extract_dialogues.py

@@ -0,0 +1,64 @@
+import unittest
+
+from extract_dialogues import attribute, cn_number, pick_subject
+
+
+class PickSubject(unittest.TestCase):
+    def test_single_candidate_with_cue_is_high(self):
+        self.assertEqual(pick_subject("亞絲娜一邊流淚一邊對我叫道"), ("亞絲娜", ["亞絲娜"], True))
+
+    def test_object_wo_is_not_speaker(self):
+        self.assertEqual(pick_subject("在我背後的亞絲娜同樣相當氣憤地反問")[0], "亞絲娜")
+
+    def test_narrator_is_wo(self):
+        self.assertEqual(pick_subject("我低聲說道")[0], "我")
+
+    def test_first_subject_wins_and_is_not_high(self):
+        who, cands, high = pick_subject("我關掉地圖，瞄了亞絲娜一眼，說道")
+        self.assertEqual((who, cands, high), ("我", ["我", "亞絲娜"], False))
+
+    def test_frame_clause_is_skipped(self):
+        self.assertEqual(pick_subject("面對桐人這種問題，莉法先是瞪了他一下後才繼續說道")[0], "莉法")
+
+    def test_wo_men_is_not_speaker(self):
+        self.assertIsNone(pick_subject("我們一起說道")[0])
+
+    def test_no_candidate(self):
+        self.assertEqual(pick_subject("她聳了聳肩後繼續說道"), (None, [], False))
+
+
+class Attribute(unittest.TestCase):
+    def test_lead_in_same_paragraph(self):
+        r = attribute("亞絲娜小聲說：", "", "")
+        self.assertEqual((r[0], r[2], r[3]), ("asuna", "high", "lead_in"))
+
+    def test_lead_in_previous_paragraph_even_with_inner_quote(self):
+        r = attribute("", "", "他喊著「回復！」。亞絲娜小聲對我說：")
+        self.assertEqual((r[0], r[3]), ("asuna", "lead_in_prev"))
+
+    def test_narrator_maps_to_kirito(self):
+        self.assertEqual(attribute("我低聲說道：", "", "")[0], "kirito")
+
+    def test_trail(self):
+        r = attribute("", "，亞絲娜低聲說。", "")
+        self.assertEqual((r[0], r[3]), ("asuna", "trail"))
+
+    def test_trail_without_cue_is_not_attributed(self):
+        self.assertIsNone(attribute("", "亞絲娜點了點頭。", "")[0])
+
+    def test_leafa_mode_from_alias(self):
+        from extract_dialogues import resolve
+        self.assertEqual(resolve("莉法"), ("suguha", "leafa"))
+        self.assertEqual(resolve("直葉"), ("suguha", "real"))
+
+    def test_unknown_when_nothing_matches(self):
+        self.assertEqual(attribute("", "", "")[0], None)
+
+
+class Numerals(unittest.TestCase):
+    def test_chapters(self):
+        self.assertEqual([cn_number(x) for x in ("一", "十", "十一", "二十", "二十五")], [1, 10, 11, 20, 25])
+
+
+if __name__ == "__main__":
+    unittest.main()