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

backend/indexer.py

@@ -481,12 +481,18 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: dict[str, Any] | No
 
                 # PDF handling — special path (binary, uses pdf_reader)
                 tags: list[str] = []
+                pdf_text_pending = False
                 if ext == ".pdf":
-                    from backend.pdf_reader import extract_pdf_metadata, extract_pdf_text
-                    raw = extract_pdf_text(fpath, max_chars=100000)
+                    from backend.pdf_reader import extract_pdf_metadata
+                    # BUG-040: only the (cheap) metadata is read during the
+                    # scan. Full-text extraction is deferred to a background
+                    # pass (``enrich_pdf_texts``) so a vault with many/large
+                    # PDFs no longer blocks startup and index rebuilds.
                     pdf_meta = extract_pdf_metadata(fpath)
                     title = pdf_meta.get("title") or fpath.stem.replace("-", " ").replace("_", " ")
-                    content_preview = raw[:200].strip()
+                    raw = ""
+                    content_preview = ""
+                    pdf_text_pending = True
                 elif ext == ".excalidraw" or fpath.name.lower().endswith(".excalidraw.md"):
                     raw = fpath.read_text(encoding="utf-8", errors="replace")
                     raw = extract_excalidraw_indexable(raw)
@@ -510,7 +516,7 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: dict[str, Any] | No
                             title, post.content
                         )
 
-                files.append({
+                file_info = {
                     "path": str(relative).replace("\\", "/"),
                     "title": title,
                     "tags": tags,
@@ -519,7 +525,10 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: dict[str, Any] | No
                     "size": stat.st_size,
                     "modified": modified,
                     "extension": ext,
-                })
+                }
+                if pdf_text_pending:
+                    file_info["pdf_text_pending"] = True
+                files.append(file_info)
 
                 for tag in tags:
                     tag_counts[tag] = tag_counts.get(tag, 0) + 1
@@ -535,6 +544,60 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: dict[str, Any] | No
     return {"files": files, "tags": tag_counts, "path": vault_path, "paths": paths, "config": {}}
 
 
+async def enrich_pdf_texts(vault_name: str | None = None) -> int:
+    """Extract text from PDFs whose extraction was deferred during the scan (BUG-040).
+
+    ``_scan_vault`` only reads PDF metadata so a vault with many or large PDFs
+    starts serving immediately. This coroutine runs *after* the index (and the
+    inverted index) is ready, extracts the missing text off the event loop and
+    updates the in-memory entry plus the incremental index hooks.
+
+    Args:
+        vault_name: Restrict the pass to a single vault; ``None`` covers every
+            indexed vault.
+
+    Returns:
+        Number of deferred PDFs whose text extraction was attempted.
+    """
+    from backend.pdf_reader import extract_pdf_text
+
+    pending: list[tuple[str, dict[str, Any], Path]] = []
+    with _index_lock:
+        for name, vault_data in index.items():
+            if vault_name is not None and name != vault_name:
+                continue
+            vault_root = Path(vault_data.get("path", ""))
+            for file_info in vault_data.get("files", []):
+                if file_info.get("pdf_text_pending"):
+                    pending.append((name, file_info, vault_root / file_info["path"]))
+
+    if not pending:
+        return 0
+
+    loop = asyncio.get_running_loop()
+    enriched = 0
+    for name, file_info, file_path in pending:
+        try:
+            raw = await loop.run_in_executor(None, extract_pdf_text, file_path, 100000)
+        except Exception as exc:  # pragma: no cover - defensive
+            logger.warning("PDF enrichment failed for %s: %s", file_path, exc)
+            raw = ""
+        file_info["content"] = raw[:SEARCH_CONTENT_LIMIT]
+        file_info["content_preview"] = raw[:200].strip()
+        file_info.pop("pdf_text_pending", None)
+        enriched += 1
+        if _on_index_change:
+            try:
+                _on_index_change("add", name, file_info["path"], file_info)
+            except Exception as exc:  # pragma: no cover - defensive
+                logger.warning(
+                    "Index hook failed after PDF enrichment for %s: %s", file_path, exc
+                )
+
+    logger.info("PDF enrichment: extracted text for %d deferred PDF(s)", enriched)
+    return enriched
+
+
 async def build_index(progress_callback=None) -> None:
     """Build the full in-memory index for all configured vaults.
 
@@ -632,6 +695,8 @@ async def reload_index() -> dict[str, Any]:
         Dict mapping vault names to their file/tag counts.
     """
     await build_index()
+    # BUG-040: complete the deferred PDF extraction for the rebuilt index.
+    await enrich_pdf_texts()
     stats = {}
     for name, data in index.items():
         stats[name] = {"file_count": len(data["files"]), "tag_count": len(data["tags"])}
@@ -695,7 +760,10 @@ async def reload_single_vault(vault_name: str) -> dict[str, Any]:
     # Rebuild attachment index for this vault only
     from backend.attachment_indexer import build_attachment_index
     await build_attachment_index({vault_name: config})
-    
+
+    # BUG-040: complete the deferred PDF extraction for this vault.
+    await enrich_pdf_texts(vault_name)
+
     stats = {"file_count": len(vault_data["files"]), "tag_count": len(vault_data["tags"])}
     logger.info(f"Vault '{vault_name}' reindexed: {stats['file_count']} files, {stats['tag_count']} tags")
     return stats