From e83df642619512bc38ee460778bbc69d260425ad Mon Sep 17 00:00:00 2001
From: Colin Maudry <colin@maudry.com>
Date: Wed, 15 Apr 2026 16:07:41 +0200
Subject: [PATCH] Ajout de src.db.should_rebuild et ses tests

refs #71
---
 src/db.py        | 28 ++++++++++++++++++++
 tests/test_db.py | 67 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)
 create mode 100644 src/db.py
 create mode 100644 tests/test_db.py

diff --git a/src/db.py b/src/db.py
new file mode 100644
index 0000000..4dea532
--- /dev/null
+++ b/src/db.py
@@ -0,0 +1,28 @@
+import logging
+import os
+from pathlib import Path
+
+logger = logging.getLogger("decp.info")
+
+
+def should_rebuild(db_path: Path, parquet_path: Path) -> bool:
+    """Decide whether to rebuild the DuckDB database from the source Parquet.
+
+    Rules:
+      - Rebuild if the DuckDB file does not exist.
+      - Otherwise, rebuild only if the source Parquet is newer than the DB,
+        EXCEPT in development mode without REBUILD_DUCKDB=true (dev keeps
+        a stable DB across reloads unless explicitly opted in).
+    """
+    db_path = Path(db_path)
+    parquet_path = Path(parquet_path)
+
+    if not db_path.exists():
+        return True
+
+    dev = os.getenv("DEVELOPMENT", "False").lower() == "true"
+    force = os.getenv("REBUILD_DUCKDB", "False").lower() == "true"
+    if dev and not force:
+        return False
+
+    return parquet_path.stat().st_mtime > db_path.stat().st_mtime
diff --git a/tests/test_db.py b/tests/test_db.py
new file mode 100644
index 0000000..4343e08
--- /dev/null
+++ b/tests/test_db.py
@@ -0,0 +1,67 @@
+import time
+
+import pytest
+
+
+@pytest.fixture
+def parquet_and_db(tmp_path, monkeypatch):
+    parquet = tmp_path / "source.parquet"
+    db = tmp_path / "decp.duckdb"
+    parquet.write_bytes(b"fake parquet content")
+    monkeypatch.delenv("REBUILD_DUCKDB", raising=False)
+    monkeypatch.delenv("DEVELOPMENT", raising=False)
+    return parquet, db
+
+
+def test_should_rebuild_when_db_missing(parquet_and_db, monkeypatch):
+    from src.db import should_rebuild
+
+    parquet, db = parquet_and_db
+    monkeypatch.setenv("DEVELOPMENT", "true")
+    assert should_rebuild(db, parquet) is True
+
+
+def test_should_rebuild_prod_when_parquet_newer(parquet_and_db, monkeypatch):
+    from src.db import should_rebuild
+
+    parquet, db = parquet_and_db
+    db.write_bytes(b"x")
+    time.sleep(0.01)
+    parquet.touch()
+    monkeypatch.setenv("DEVELOPMENT", "false")
+    assert should_rebuild(db, parquet) is True
+
+
+def test_should_not_rebuild_prod_when_parquet_older(parquet_and_db, monkeypatch):
+    from src.db import should_rebuild
+
+    parquet, db = parquet_and_db
+    parquet.touch()
+    time.sleep(0.01)
+    db.write_bytes(b"x")
+    monkeypatch.setenv("DEVELOPMENT", "false")
+    assert should_rebuild(db, parquet) is False
+
+
+def test_should_not_rebuild_dev_even_when_parquet_newer(parquet_and_db, monkeypatch):
+    from src.db import should_rebuild
+
+    parquet, db = parquet_and_db
+    db.write_bytes(b"x")
+    time.sleep(0.01)
+    parquet.touch()
+    monkeypatch.setenv("DEVELOPMENT", "true")
+    monkeypatch.delenv("REBUILD_DUCKDB", raising=False)
+    assert should_rebuild(db, parquet) is False
+
+
+def test_should_rebuild_dev_when_rebuild_forced(parquet_and_db, monkeypatch):
+    from src.db import should_rebuild
+
+    parquet, db = parquet_and_db
+    db.write_bytes(b"x")
+    time.sleep(0.01)
+    parquet.touch()
+    monkeypatch.setenv("DEVELOPMENT", "true")
+    monkeypatch.setenv("REBUILD_DUCKDB", "true")
+    assert should_rebuild(db, parquet) is True