Expand file type support beyond Markdown to include code, config, and build files with syntax highlighting and improved UI filtering

backend/indexer.py

@@ -15,6 +15,18 @@ index: Dict[str, Dict[str, Any]] = {}
 # Vault config: {name: path}
 vault_config: Dict[str, str] = {}
 
+# Supported text-based file extensions
+SUPPORTED_EXTENSIONS = {
+    ".md", ".txt", ".log", ".py", ".js", ".ts", ".jsx", ".tsx",
+    ".sh", ".bash", ".zsh", ".fish", ".bat", ".cmd", ".ps1",
+    ".json", ".yaml", ".yml", ".toml", ".xml", ".csv",
+    ".cfg", ".ini", ".conf", ".env",
+    ".html", ".css", ".scss", ".less",
+    ".java", ".c", ".cpp", ".h", ".hpp", ".cs", ".go", ".rs", ".rb",
+    ".php", ".sql", ".r", ".m", ".swift", ".kt",
+    ".dockerfile", ".makefile", ".cmake",
+}
+
 
 def load_vault_config() -> Dict[str, str]:
     """Read VAULT_N_NAME / VAULT_N_PATH env vars and return {name: path}."""
@@ -60,18 +72,34 @@ def _scan_vault(vault_name: str, vault_path: str) -> Dict[str, Any]:
         logger.warning(f"Vault path does not exist: {vault_path}")
         return {"files": [], "tags": {}, "path": vault_path}
 
-    for md_file in vault_root.rglob("*.md"):
+    for fpath in vault_root.rglob("*"):
+        if not fpath.is_file():
+            continue
+        # Skip hidden files and files inside hidden directories
+        rel_parts = fpath.relative_to(vault_root).parts
+        if any(part.startswith(".") for part in rel_parts):
+            continue
+        ext = fpath.suffix.lower()
+        # Also match extensionless files named like Dockerfile, Makefile
+        basename_lower = fpath.name.lower()
+        if ext not in SUPPORTED_EXTENSIONS and basename_lower not in ("dockerfile", "makefile", "cmakelists.txt"):
+            continue
         try:
-            relative = md_file.relative_to(vault_root)
-            stat = md_file.stat()
+            relative = fpath.relative_to(vault_root)
+            stat = fpath.stat()
             modified = datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat()
 
-            raw = md_file.read_text(encoding="utf-8", errors="replace")
-            post = frontmatter.loads(raw)
+            raw = fpath.read_text(encoding="utf-8", errors="replace")
 
-            tags = _extract_tags(post)
-            title = _extract_title(post, md_file)
-            content_preview = post.content[:200].strip()
+            tags: List[str] = []
+            title = fpath.stem.replace("-", " ").replace("_", " ")
+            content_preview = raw[:200].strip()
+
+            if ext == ".md":
+                post = frontmatter.loads(raw)
+                tags = _extract_tags(post)
+                title = _extract_title(post, fpath)
+                content_preview = post.content[:200].strip()
 
             files.append({
                 "path": str(relative).replace("\\", "/"),
@@ -80,13 +108,14 @@ def _scan_vault(vault_name: str, vault_path: str) -> Dict[str, Any]:
                 "content_preview": content_preview,
                 "size": stat.st_size,
                 "modified": modified,
+                "extension": ext,
             })
 
             for tag in tags:
                 tag_counts[tag] = tag_counts.get(tag, 0) + 1
 
         except Exception as e:
-            logger.error(f"Error indexing {md_file}: {e}")
+            logger.error(f"Error indexing {fpath}: {e}")
             continue
 
     logger.info(f"Vault '{vault_name}': indexed {len(files)} files, {len(tag_counts)} unique tags")