feat(pdf): #74 au complet — fix auth 500 stream + endpoint pdf/info + HTTP Range 206 + indexation incrementale PDF + config taille/timeout

backend/indexer.py

@@ -546,19 +546,27 @@ def _index_single_file_sync(vault_name: str, vault_path: str, file_path: str, va
 
         stat = fpath.stat()
         modified = datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat()
-        raw = fpath.read_text(encoding="utf-8", errors="replace")
 
+        # PDF handling — binary, must go through pdf_reader (same as _scan_vault)
         tags: list[str] = []
         title = fpath.stem.replace("-", " ").replace("_", " ")
-        content_preview = raw[:200].strip()
+        if ext == ".pdf":
+            from backend.pdf_reader import extract_pdf_metadata, extract_pdf_text
+            raw = extract_pdf_text(fpath, max_chars=SEARCH_CONTENT_LIMIT)
+            pdf_meta = extract_pdf_metadata(fpath)
+            title = pdf_meta.get("title") or title
+            content_preview = raw[:200].strip()
+        else:
+            raw = fpath.read_text(encoding="utf-8", errors="replace")
+            content_preview = raw[:200].strip()
 
-        if ext == ".md":
-            post = parse_markdown_file(raw)
-            tags = _extract_tags(post)
-            inline_tags = _extract_inline_tags(post.content)
-            tags = list(set(tags) | set(inline_tags))
-            title = _extract_title(post, fpath)
-            content_preview = post.content[:200].strip()
+            if ext == ".md":
+                post = parse_markdown_file(raw)
+                tags = _extract_tags(post)
+                inline_tags = _extract_inline_tags(post.content)
+                tags = list(set(tags) | set(inline_tags))
+                title = _extract_title(post, fpath)
+                content_preview = post.content[:200].strip()
 
         return {
             "path": str(relative).replace("\\", "/"),