fix(ревью#2): db_docs→_db + classify_raw в MemRepo + try/except в build_classify_prompt

2026-06-28 09:40:00 +04:00
parent 8a804da494
commit d8e8b35092
4 changed files with 89 additions and 23 deletions
@@ -0,0 +1,62 @@
+"""Test classify_batch with MemRepository + FakeLLM."""
+from services.classify import classify_batch
+from services.llm_client import FakeLLMClient
+from repository import MemRepository
+
+
+class TestClassifyBatch:
+    def test_garbage_by_filename(self):
+        """Счёт-фактура отфильтровывается без LLM."""
+        repo = MemRepository()
+        llm = FakeLLMClient({"default": '{"doc_type":"contract"}'})
+        
+        repo.insert_document("счет-фактура №123.docx", "mime", "data", batch_id="b1")
+        
+        result = classify_batch("b1", llm_client=llm, repo=repo)
+        assert result["ok"] is True
+        assert result["garbage"] == 1
+        assert result["done"] == 1
+        assert len(llm.calls) == 0  # LLM не вызывался
+
+    def test_garbage_by_header(self):
+        """Акт сверки в тексте отфильтровывается."""
+        repo = MemRepository()
+        llm = FakeLLMClient({"default": '{"doc_type":"contract"}'})
+        
+        doc = repo.insert_document("документ.docx", "mime", "data", batch_id="b1")
+        repo.set_document_parsed(doc["id"], [
+            {"type": "paragraph", "text": "АКТ СВЕРКИ взаимных расчётов", "style": ""}
+        ])
+        
+        result = classify_batch("b1", llm_client=llm, repo=repo)
+        assert result["garbage"] == 1
+        assert len(llm.calls) == 0
+
+    def test_llm_classify(self):
+        """Договор классифицируется через LLM."""
+        repo = MemRepository()
+        llm = FakeLLMClient({
+            "default": '{"doc_type":"contract","own_number":"03700_1","doc_date":"2026-02-01","counterparty":"ЗАО XXX001"}'
+        })
+        
+        doc = repo.insert_document("договор-XXX001.docx", "mime", "data", batch_id="b1")
+        repo.set_document_parsed(doc["id"], [
+            {"type": "paragraph", "text": "ДОГОВОР № 03700_1", "style": ""}
+        ])
+        
+        result = classify_batch("b1", llm_client=llm, repo=repo)
+        assert result["done"] == 1, f"done={result['done']}, failed={result['failed']}, doc={repo.get_document(doc['id'])}"
+        assert result["garbage"] == 0
+        assert len(llm.calls) == 1
+        
+        updated = repo.get_document(doc["id"])
+        assert updated["doc_type"] == "contract"
+        assert updated["own_number"] == "03700_1"
+        assert updated["counterparty"] == "ЗАО XXX001"
+
+    def test_no_pending(self):
+        """Пустой батч."""
+        repo = MemRepository()
+        result = classify_batch("empty", llm_client=FakeLLMClient(), repo=repo)
+        assert result["ok"] is False
+        assert "no pending" in result["error"]