fix: corrige 6 bugs mineurs (BUG-035 a BUG-040)

tests/test_pdf.py

@@ -275,6 +275,7 @@ class TestPdfIndexing:
         """When a vault directory is scanned with .pdf files, they appear in files list.
 
         Uses the public _scan_vault() helper directly — no global state needed.
+        BUG-040: text extraction is deferred, so the scan only carries metadata.
         """
         from backend.indexer import _scan_vault
 
@@ -286,10 +287,96 @@ class TestPdfIndexing:
         names = {f["path"] for f in result["files"]}
         assert "a.pdf" in names
         assert "b.pdf" in names
-        # The PDF content should have been extracted.
+        # The scan defers the expensive text extraction.
         a_file = next(f for f in result["files"] if f["path"] == "a.pdf")
-        assert "ObsiGate test PDF" in (a_file.get("content") or "")
-        assert "uniqueword0" in (a_file.get("content") or "")
+        assert a_file["content"] == ""
+        assert a_file["pdf_text_pending"] is True
+
+
+class TestPdfLazyEnrichment:
+    """BUG-040: PDF text is extracted in a deferred background pass."""
+
+    def test_scan_defers_pdf_text_extraction(self, pdf_dir: Path, tmp_path: Path):
+        from backend.indexer import _scan_vault
+
+        vault_root = tmp_path / "vault"
+        vault_root.mkdir()
+        shutil.copy2(pdf_dir / "simple.pdf", vault_root / "a.pdf")
+        result = _scan_vault("v", str(vault_root), {})
+        a_file = next(f for f in result["files"] if f["path"] == "a.pdf")
+        assert a_file["content"] == ""
+        assert a_file["content_preview"] == ""
+        assert a_file["pdf_text_pending"] is True
+
+    @pytest.mark.asyncio
+    async def test_enrich_pdf_texts_fills_content_and_clears_flag(
+        self, pdf_dir: Path, tmp_path: Path
+    ):
+        import backend.indexer as idx
+
+        vault_root = tmp_path / "vault"
+        vault_root.mkdir()
+        shutil.copy2(pdf_dir / "simple.pdf", vault_root / "a.pdf")
+        file_info = {
+            "path": "a.pdf",
+            "title": "a",
+            "tags": [],
+            "content": "",
+            "content_preview": "",
+            "size": 0,
+            "modified": "",
+            "extension": ".pdf",
+            "pdf_text_pending": True,
+        }
+        with idx._index_lock:
+            idx.index["LazyV"] = {
+                "files": [file_info],
+                "tags": {},
+                "path": str(vault_root),
+                "paths": [],
+            }
+        try:
+            count = await idx.enrich_pdf_texts("LazyV")
+            assert count == 1
+            assert "ObsiGate test PDF" in file_info["content"]
+            assert "uniqueword0" in file_info["content"]
+            assert file_info["content_preview"]
+            assert "pdf_text_pending" not in file_info
+        finally:
+            with idx._index_lock:
+                idx.index.pop("LazyV", None)
+
+    @pytest.mark.asyncio
+    async def test_enrich_pdf_texts_skips_other_vaults(self, pdf_dir: Path, tmp_path: Path):
+        import backend.indexer as idx
+
+        vault_root = tmp_path / "vault"
+        vault_root.mkdir()
+        shutil.copy2(pdf_dir / "simple.pdf", vault_root / "a.pdf")
+        file_info = {
+            "path": "a.pdf",
+            "title": "a",
+            "tags": [],
+            "content": "",
+            "content_preview": "",
+            "size": 0,
+            "modified": "",
+            "extension": ".pdf",
+            "pdf_text_pending": True,
+        }
+        with idx._index_lock:
+            idx.index["OtherV"] = {
+                "files": [file_info],
+                "tags": {},
+                "path": str(vault_root),
+                "paths": [],
+            }
+        try:
+            assert await idx.enrich_pdf_texts("LazyV") == 0
+            assert file_info["content"] == ""
+        finally:
+            with idx._index_lock:
+                idx.index.pop("OtherV", None)
 
 
 # ── Search filter `ext:` ───────────────────────────────────────────────────