Improve Rolodex imports, display, and add repair script

tests/test_import_data.py

@@ -0,0 +1,130 @@
+"""Tests for Rolodex and Files CSV import helpers."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+from app.main import import_files_data, import_rolodex_data
+from app.models import Base, Case, Client
+
+
+def _make_engine(db_path: Path):
+    engine = create_engine(f"sqlite:///{db_path}")
+    Base.metadata.create_all(engine)
+    return engine
+
+
+@pytest.fixture()
+def session(tmp_path):
+    engine = _make_engine(tmp_path / "import-tests.db")
+    SessionLocal = sessionmaker(bind=engine)
+    db = SessionLocal()
+    try:
+        yield db
+    finally:
+        db.close()
+        engine.dispose()
+
+
+def _write_csv(path: Path, content: str) -> Path:
+    path.write_text(content, encoding="utf-8")
+    return path
+
+
+def test_import_rolodex_captures_email_and_memo(session, tmp_path):
+    csv_path = _write_csv(
+        tmp_path / "ROLODEX.csv",
+        "Id,Prefix,First,Middle,Last,Suffix,Title,A1,A2,A3,City,Abrev,St,Zip,Email,DOB,SS#,Legal_Status,Group,Memo\n"
+        "1001,,Ada,,Lovelace,,Countess,123 Main,,,London,,UK,12345,ada@example.com,12/10/1815,XXX-XX-1111,Active,VIP,Top client notes\n"
+        "1002,,Alan,,Turing,,,43 Park,,Bletchley,,UK,67890,,06/23/1912,XXX-XX-2222,Active,VIP,   \n",
+    )
+
+    result = import_rolodex_data(session, str(csv_path))
+
+    assert result["success"] == 2
+    assert result["email_imported"] == 1
+    assert result["email_missing"] == 1
+    assert result["memo_imported"] == 1
+    assert result["memo_missing"] == 1
+    assert not result["errors"]
+
+    clients = {c.rolodex_id: c for c in session.query(Client).all()}
+    assert clients["1001"].email == "ada@example.com"
+    assert clients["1001"].memo == "Top client notes"
+    assert clients["1002"].email is None
+    assert clients["1002"].memo is None
+
+
+def test_import_rolodex_handles_duplicates(session, tmp_path):
+    csv_path = _write_csv(
+        tmp_path / "ROLODEX.csv",
+        "Id,Prefix,First,Middle,Last,Suffix,Title,A1,A2,A3,City,Abrev,St,Zip,Email,DOB,SS#,Legal_Status,Group,Memo\n"
+        "3001,,Grace,,Hopper,,,,,Arlington,VA,Virginia,22202,grace@example.com,12/09/1906,XXX-XX-3333,Active,VIP,Notes\n"
+        "3001,,Grace,,Hopper,,,,,Arlington,VA,Virginia,22202,grace@example.com,12/09/1906,XXX-XX-3333,Active,VIP,Duplicate\n",
+    )
+
+    result = import_rolodex_data(session, str(csv_path))
+
+    assert result["success"] == 1
+    assert result["skipped_duplicates"] == 1
+    assert len(result["errors"]) == 0
+
+
+def test_import_files_links_clients_and_detects_missing(session, tmp_path):
+    _write_csv(
+        tmp_path / "ROLODEX.csv",
+        "Id,Prefix,First,Middle,Last,Suffix,Title,A1,A2,A3,City,Abrev,St,Zip,Email,DOB,SS#,Legal_Status,Group,Memo\n"
+        "2001,,Grace,,Hopper,,,,,Arlington,VA,Virginia,22202,grace@example.com,12/09/1906,XXX-XX-3333,Active,VIP,Notes\n",
+    )
+    import_rolodex_data(session, str(tmp_path / "ROLODEX.csv"))
+
+    files_path = _write_csv(
+        tmp_path / "FILES.csv",
+        "File_No,Id,File_Type,Regarding,Opened,Closed,Empl_Num,Rate_Per_Hour,Status,Footer_Code,Opposing,Hours,Hours_P,Trust_Bal,Trust_Bal_P,Hourly_Fees,Hourly_Fees_P,Flat_Fees,Flat_Fees_P,Disbursements,Disbursements_P,Credit_Bal,Credit_Bal_P,Total_Charges,Total_Charges_P,Amount_Owing,Amount_Owing_P,Transferable,Memo\n"
+        "F-001,2001,Divorce,Important matter,01/01/2020,,E1,175,Open,F1,,,0,0,0,0,0,0,0,0,0,0,0,0,0,0,No,Initial legacy memo\n"
+        "F-002,9999,Divorce,Missing client,01/01/2020,,E1,175,Open,F1,,,0,0,0,0,0,0,0,0,0,0,0,0,0,0,No,Should be skipped\n",
+    )
+
+    result = import_files_data(session, str(files_path))
+
+    assert result["success"] == 1
+    assert result["client_linked"] == 1
+    assert result["client_missing"] == 1
+    assert result["errors"], "Expected missing client to produce an error"
+
+    case = session.query(Case).filter(Case.file_no == "F-001").one()
+    assert case.client is not None
+    assert case.client.rolodex_id == "2001"
+
+    missing_case = session.query(Case).filter(Case.file_no == "F-002").first()
+    assert missing_case is None
+
+
+def test_import_files_respects_duplicates(session, tmp_path):
+    _write_csv(
+        tmp_path / "ROLODEX.csv",
+        "Id,Prefix,First,Middle,Last,Suffix,Title,A1,A2,A3,City,Abrev,St,Zip,Email,DOB,SS#,Legal_Status,Group,Memo\n"
+        "4001,,Marie,,Curie,,,,,Paris,,France,75000,marie@example.com,11/07/1867,XXX-XX-4444,Active,VIP,Notes\n",
+    )
+    import_rolodex_data(session, str(tmp_path / "ROLODEX.csv"))
+
+    files_csv = _write_csv(
+        tmp_path / "FILES.csv",
+        "File_No,Id,File_Type,Regarding,Opened,Closed,Empl_Num,Rate_Per_Hour,Status,Footer_Code,Opposing,Hours,Hours_P,Trust_Bal,Trust_Bal_P,Hourly_Fees,Hourly_Fees_P,Flat_Fees,Flat_Fees_P,Disbursements,Disbursements_P,Credit_Bal,Credit_Bal_P,Total_Charges,Total_Charges_P,Amount_Owing,Amount_Owing_P,Transferable,Memo\n"
+        "F-100,4001,Divorce,Legacy matter,01/01/2020,,E1,175,Open,F1,,,0,0,0,0,0,0,0,0,0,0,0,0,0,0,No,First import\n"
+        "F-100,4001,Divorce,Legacy matter,01/01/2020,,E1,175,Open,F1,,,0,0,0,0,0,0,0,0,0,0,0,0,0,0,No,Duplicate row\n",
+    )
+
+    first_result = import_files_data(session, str(files_csv))
+    assert first_result["success"] == 1
+    assert first_result["skipped_duplicates"] == 0
+
+    second_result = import_files_data(session, str(files_csv))
+    assert second_result["success"] == 0
+    assert second_result["skipped_duplicates"] == 1
+    assert not session.query(Case).filter(Case.file_no == "F-100").all()[1:]
+