refactor: remove hidden files indexing configuration and convert to UI-only display preference, eliminating includeHidden and hiddenWhitelist from vault config and indexing logic while adding hideHiddenFiles client-side filtering

This commit is contained in:
2026-03-26 19:53:40 -04:00
parent 34f4e41419
commit 2b69c49ed1
7 changed files with 98 additions and 340 deletions
+8 -59
View File
@@ -9,8 +9,6 @@ from typing import Dict, List, Optional, Any
import frontmatter
from backend.utils import should_include_path
logger = logging.getLogger("obsigate.indexer")
# Global in-memory index
@@ -61,16 +59,12 @@ def load_vault_config() -> Dict[str, Dict[str, Any]]:
Also reads optional configuration:
- VAULT_N_ATTACHMENTS_PATH: relative path to attachments folder
- VAULT_N_SCAN_ATTACHMENTS: "true"/"false" to enable/disable scanning
- VAULT_N_INCLUDE_HIDDEN: "true"/"false" to include all hidden files/folders
- VAULT_N_HIDDEN_WHITELIST: comma-separated list of hidden paths to include (e.g., ".obsidian,.github")
Returns:
Dict mapping vault names to configuration dicts with keys:
- path: filesystem path (required)
- attachmentsPath: relative attachments folder (optional)
- scanAttachmentsOnStartup: boolean (default True)
- includeHidden: boolean (default False) - include all hidden files/folders
- hiddenWhitelist: list of hidden paths to include even if includeHidden is False
- type: "VAULT" or "DIR"
"""
vaults: Dict[str, Dict[str, Any]] = {}
@@ -84,16 +78,11 @@ def load_vault_config() -> Dict[str, Dict[str, Any]]:
# Optional configuration
attachments_path = os.environ.get(f"VAULT_{n}_ATTACHMENTS_PATH")
scan_attachments = os.environ.get(f"VAULT_{n}_SCAN_ATTACHMENTS", "true").lower() == "true"
include_hidden = os.environ.get(f"VAULT_{n}_INCLUDE_HIDDEN", "false").lower() == "true"
hidden_whitelist_str = os.environ.get(f"VAULT_{n}_HIDDEN_WHITELIST", "")
hidden_whitelist = [item.strip() for item in hidden_whitelist_str.split(",") if item.strip()]
vaults[name] = {
"path": path,
"attachmentsPath": attachments_path,
"scanAttachmentsOnStartup": scan_attachments,
"includeHidden": include_hidden,
"hiddenWhitelist": hidden_whitelist,
"type": "VAULT"
}
n += 1
@@ -105,16 +94,10 @@ def load_vault_config() -> Dict[str, Dict[str, Any]]:
if not name or not path:
break
include_hidden = os.environ.get(f"DIR_{n}_INCLUDE_HIDDEN", "false").lower() == "true"
hidden_whitelist_str = os.environ.get(f"DIR_{n}_HIDDEN_WHITELIST", "")
hidden_whitelist = [item.strip() for item in hidden_whitelist_str.split(",") if item.strip()]
vaults[name] = {
"path": path,
"attachmentsPath": None,
"scanAttachmentsOnStartup": False,
"includeHidden": include_hidden,
"hiddenWhitelist": hidden_whitelist,
"type": "DIR"
}
n += 1
@@ -219,11 +202,13 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: Optional[Dict[str,
Walks the vault tree, reads supported files, extracts metadata
(tags, title, content preview) and stores a capped content snapshot
for in-memory full-text search.
All files and directories are indexed, including hidden files (starting with '.').
Args:
vault_name: Display name of the vault.
vault_path: Absolute filesystem path to the vault root.
vault_cfg: Optional vault configuration dict with hidden files settings.
vault_cfg: Optional vault configuration dict (unused for indexing, kept for compatibility).
Returns:
Dict with keys ``files`` (list), ``tags`` (counter dict), ``path`` (str), ``paths`` (list).
@@ -232,21 +217,12 @@ def _scan_vault(vault_name: str, vault_path: str, vault_cfg: Optional[Dict[str,
files: List[Dict[str, Any]] = []
tag_counts: Dict[str, int] = {}
paths: List[Dict[str, str]] = []
# Default config if not provided
if vault_cfg is None:
vault_cfg = {"includeHidden": False, "hiddenWhitelist": []}
if not vault_root.exists():
logger.warning(f"Vault path does not exist: {vault_path}")
return {"files": [], "tags": {}, "path": vault_path, "paths": []}
for fpath in vault_root.rglob("*"):
# Check if path should be included based on hidden files configuration
rel_parts = fpath.relative_to(vault_root).parts
if not should_include_path(rel_parts, vault_cfg):
continue
rel_path_str = str(fpath.relative_to(vault_root)).replace("\\", "/")
# Add all paths (files and directories) to path index
@@ -329,17 +305,8 @@ async def build_index(progress_callback=None) -> None:
vault_config.clear()
vault_config.update(load_vault_config())
# Merge vault_settings (from UI) with vault_config (from env vars)
from backend.vault_settings import get_all_vault_settings
saved_settings = get_all_vault_settings()
for vault_name, config in vault_config.items():
if vault_name in saved_settings:
settings = saved_settings[vault_name]
# Override with saved settings if present
if "includeHidden" in settings:
config["includeHidden"] = settings["includeHidden"]
if "hiddenWhitelist" in settings:
config["hiddenWhitelist"] = settings["hiddenWhitelist"]
# Note: vault_settings are now only used for UI display preferences (hideHiddenFiles)
# Indexing always includes all files regardless of settings
global _index_generation
with _index_lock:
@@ -443,22 +410,11 @@ async def reload_single_vault(vault_name: str) -> Dict[str, Any]:
# Reload vault config from env vars
vault_config.update(load_vault_config())
# Merge with saved settings
from backend.vault_settings import get_vault_setting
saved_settings = get_vault_setting(vault_name)
if vault_name not in vault_config:
raise ValueError(f"Vault '{vault_name}' not found in configuration")
config = vault_config[vault_name]
# Override with saved settings if present
if saved_settings:
if "includeHidden" in saved_settings:
config["includeHidden"] = saved_settings["includeHidden"]
if "hiddenWhitelist" in saved_settings:
config["hiddenWhitelist"] = saved_settings["hiddenWhitelist"]
# Remove old vault data from index structures
await remove_vault_from_index(vault_name)
@@ -520,12 +476,14 @@ def _get_async_lock() -> asyncio.Lock:
def _index_single_file_sync(vault_name: str, vault_path: str, file_path: str, vault_cfg: Optional[Dict[str, Any]] = None) -> Optional[Dict[str, Any]]:
"""Synchronously read and parse a single file for indexing.
All files are indexed, including hidden files (starting with '.').
Args:
vault_name: Name of the vault.
vault_path: Absolute path to vault root.
file_path: Absolute path to the file.
vault_cfg: Optional vault configuration dict with hidden files settings.
vault_cfg: Optional vault configuration dict (unused for indexing, kept for compatibility).
Returns:
File info dict or None if the file cannot be read.
@@ -538,13 +496,6 @@ def _index_single_file_sync(vault_name: str, vault_path: str, file_path: str, va
return None
relative = fpath.relative_to(vault_root)
rel_parts = relative.parts
# Check if path should be included based on hidden files configuration
if vault_cfg is None:
vault_cfg = {"includeHidden": False, "hiddenWhitelist": []}
if not should_include_path(rel_parts, vault_cfg):
return None
ext = fpath.suffix.lower()
basename_lower = fpath.name.lower()
@@ -815,8 +766,6 @@ async def add_vault_to_index(vault_name: str, vault_path: str) -> Dict[str, Any]
"path": vault_path,
"attachmentsPath": None,
"scanAttachmentsOnStartup": True,
"includeHidden": False,
"hiddenWhitelist": [],
}
loop = asyncio.get_event_loop()