feat: RapidOCR default OCR engine, office-only ocr_engine, drop operator toggle

tests/test_config_loader.py

@@ -49,7 +49,7 @@ def test_do_block_and_batch_default_mode(repo_config_path):
     assert cfg.do.photo_dir == "do_photos"
     assert cfg.do.max_photos_per_batch == 8
     assert cfg.do.zone_warn_seconds == 3
-    assert cfg.do.ocr.engine == "tesseract"
+    assert cfg.do.ocr.engine == "rapid"
 
 
 def test_do_block_missing_uses_defaults(tmp_path):
@@ -65,7 +65,7 @@ def test_do_block_missing_uses_defaults(tmp_path):
     cfg = load_config(p)
     assert cfg.batch.default_mode == "auto"
     assert cfg.do.enabled is True
-    assert cfg.do.ocr.engine == "tesseract"
+    assert cfg.do.ocr.engine == "rapid"
     assert cfg.do.retention_days == 7
 
 

tests/test_do_batch.py

@@ -116,6 +116,7 @@ def test_ocr_engine_validation():
     for e in OCR_ENGINES:
         assert is_valid_ocr_engine(e)
     assert not is_valid_ocr_engine("easyocr")
+    assert OCR_ENGINES[0] == "rapid"  # default engine
 
 
 def test_empty_do_settings_defaults():
@@ -123,7 +124,7 @@ def test_empty_do_settings_defaults():
     assert s["ocr_engine"] == "tesseract"
     assert s["require_do"] is True
     bad = empty_do_settings({"ocr_engine": "nope"})
-    assert bad["ocr_engine"] == "tesseract"
+    assert bad["ocr_engine"] == "rapid"
 
 
 def test_parse_fields_from_text():
@@ -145,6 +146,21 @@ def test_extract_do_fields_none_engine(tmp_path):
     assert out["engine"] == "none"
 
 
+def test_extract_do_fields_rapid_engine(tmp_path):
+    from src.do_ocr import extract_do_fields
+    Image = pytest.importorskip("PIL.Image")
+
+    p = tmp_path / "do.png"
+    Image.new("RGB", (200, 60), "white").save(p)
+    out = extract_do_fields(str(p), engine="rapid")
+    assert out["engine"] == "rapid"
+    if out["ocr_ok"]:
+        assert out["ocr_text"] == ""  # blank image → empty text, no crash
+    else:
+        # rapid missing → explicit error (never silent fallback)
+        assert "rapidocr" in out["ocr_error"].lower()
+
+
 # ---------------------------------------------------------------------------
 # Flask API auth tests — skipped when flask/openpyxl not installed (CI)
 # ---------------------------------------------------------------------------
@@ -213,17 +229,18 @@ def test_model_mode_post_operator_403(dash_client):
     assert res.status_code == 403
 
 
-def test_ocr_engine_post_both_ports(dash_client):
+def test_ocr_engine_post_office_only(dash_client):
     client, _, _, settings_path = dash_client
     res = client.post("/api/do/settings", json={"ocr_engine": "paddle"},
                       headers={"Host": "localhost:5000"})
+    assert res.status_code == 403
+    office = {"Host": f"localhost:{cd_office_port()}"}
+    res = client.post("/api/do/settings", json={"ocr_engine": "paddle"}, headers=office)
     assert res.status_code == 200
     assert res.get_json()["ocr_engine"] == "paddle"
-    res = client.post("/api/do/settings", json={"ocr_engine": "tesseract"},
-                      headers={"Host": f"localhost:{cd_office_port()}"})
+    res = client.post("/api/do/settings", json={"ocr_engine": "tesseract"}, headers=office)
     assert res.status_code == 200
-    res = client.post("/api/do/settings", json={"ocr_engine": "bogus"},
-                      headers={"Host": "localhost:5000"})
+    res = client.post("/api/do/settings", json={"ocr_engine": "bogus"}, headers=office)
     assert res.status_code == 400