Merge pull request #1838 from MemPalace/fix/sqlite-ro-uri-encoding

fix: percent-encode sqlite read-only URIs for spaced/special-char paths

mempalace/backends/chroma.py

@@ -17,6 +17,7 @@ from typing import Any, Optional
 import chromadb
 from chromadb.errors import NotFoundError as _ChromaNotFoundError
 
+from ..config import sqlite_read_uri
 from ._sidecar import EMBEDDER_SIDECAR_FILENAME, read_embedder_sidecar, write_embedder_sidecar
 from .base import (
     BaseBackend,
@@ -457,7 +458,7 @@ def _vector_segment_id(palace_path: str, collection_name: str) -> Optional[str]:
     if not os.path.isfile(db_path):
         return None
     try:
-        conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
         try:
             row = conn.execute(
                 """
@@ -626,7 +627,7 @@ def _read_sync_threshold(palace_path: str, collection_name: str) -> int:
     if not os.path.isfile(db_path):
         return 1000
     try:
-        conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
         try:
             cur = conn.cursor()
             cur.execute(
@@ -746,7 +747,7 @@ def _sqlite_embedding_count(palace_path: str, collection_name: str) -> Optional[
     if not os.path.isfile(db_path):
         return None
     try:
-        conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
         try:
             row = conn.execute(
                 """
@@ -807,7 +808,7 @@ def _sqlite_wing_room_counts(
     if not os.path.isfile(db_path):
         return None
     try:
-        conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
         try:
             # Wait out a transient writer/checkpoint lock rather than falling
             # straight back to the expensive vector-index path (#1681).
@@ -1570,7 +1571,7 @@ class ChromaCollection(BaseCollection):
         # rowid, embedding_id is the user-facing drawer id.
         public_ids: dict[int, str] = {}
         try:
-            conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+            conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
             conn.row_factory = sqlite3.Row
         except sqlite3.Error:
             logger.debug("Chroma lexical sqlite open failed", exc_info=True)

mempalace/config.py

@@ -205,6 +205,21 @@ DEFAULT_BACKEND = "chroma"
 DEFAULT_MAX_BACKUPS = 10
 
 
+def sqlite_read_uri(db_path: str) -> str:
+    """Return a read-only ``file:`` URI for ``sqlite3.connect(..., uri=True)``.
+
+    A bare ``f"file:{db_path}?mode=ro"`` mis-parses paths containing spaces or
+    other URI-reserved characters — common in real home directories (a Windows
+    user folder like ``First Last``, many macOS paths). ``pathname2url``
+    percent-encodes the path and normalizes separators so the database opens on
+    every platform.
+    """
+    from urllib.request import pathname2url
+
+    db_path = os.fspath(db_path)
+    return f"file:{pathname2url(db_path)}?mode=ro"
+
+
 @lru_cache(maxsize=1)
 def get_configured_collection_name() -> str:
     """Return the configured drawer collection name without repeated config-file reads."""

mempalace/mcp_server.py

@@ -60,6 +60,7 @@ from .config import (  # noqa: E402
     sanitize_name,
     sanitize_content,
     sanitize_iso_temporal,
+    sqlite_read_uri,
     strip_lone_surrogates,
 )
 from .version import __version__  # noqa: E402
@@ -920,7 +921,7 @@ def _tool_status_via_sqlite() -> dict:
     rooms: dict = {}
     total = 0
     try:
-        conn = _sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = _sqlite3.connect(sqlite_read_uri(db_path), uri=True)
         try:
             row = conn.execute(
                 """

mempalace/repair.py

@@ -43,6 +43,7 @@ from typing import Callable, Iterator, Optional
 from chromadb.errors import NotFoundError as ChromaNotFoundError
 
 from .backends.chroma import ChromaBackend, hnsw_capacity_status
+from .config import sqlite_read_uri
 
 
 COLLECTION_NAME = "mempalace_drawers"
@@ -476,7 +477,7 @@ def sqlite_drawer_count(palace_path: str, collection_name: Optional[str] = None)
     try:
         import sqlite3
 
-        conn = sqlite3.connect(f"file:{sqlite_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(sqlite_path), uri=True)
         try:
             row = conn.execute(
                 """
@@ -516,7 +517,7 @@ def sqlite_integrity_errors(palace_path: str) -> list[str]:
         return []
 
     try:
-        with sqlite3.connect(f"file:{sqlite_path}?mode=ro", uri=True) as conn:
+        with sqlite3.connect(sqlite_read_uri(sqlite_path), uri=True) as conn:
             rows = conn.execute("PRAGMA quick_check").fetchall()
     except sqlite3.Error as e:
         return [f"PRAGMA quick_check failed: {e}"]
@@ -1013,7 +1014,7 @@ def extract_via_sqlite(palace_path: str, collection_name: str) -> Iterator[tuple
     if not os.path.isfile(sqlite_path):
         return
 
-    conn = sqlite3.connect(f"file:{sqlite_path}?mode=ro", uri=True)
+    conn = sqlite3.connect(sqlite_read_uri(sqlite_path), uri=True)
     try:
         seg_row = conn.execute(
             """

mempalace/searcher.py

@@ -23,6 +23,7 @@ from .backends import (
     PalaceNotFoundError,
     UnsupportedCapabilityError,
 )
+from .config import sqlite_read_uri
 from .palace import (
     _open_collection_or_explain,
     get_closets_collection,
@@ -533,7 +534,7 @@ def _bm25_only_via_sqlite(
         return "".join(clauses), params
 
     try:
-        conn = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
+        conn = sqlite3.connect(sqlite_read_uri(db_path), uri=True)
     except sqlite3.Error as e:
         return {"error": f"sqlite open failed: {e}"}
 

tests/test_config.py

@@ -1,5 +1,6 @@
 import os
 import json
+import sqlite3
 import tempfile
 
 import pytest
@@ -10,6 +11,7 @@ from mempalace.config import (
     sanitize_iso_temporal,
     sanitize_kg_value,
     sanitize_name,
+    sqlite_read_uri,
 )
 
 
@@ -148,6 +150,31 @@ def test_embedding_threads_invalid_falls_back_to_auto(tmp_path, monkeypatch):
     assert cfg.embedding_threads == 2
 
 
+def test_sqlite_read_uri_opens_path_with_spaces(tmp_path):
+    """sqlite_read_uri must open a read-only DB whose path contains spaces,
+    which a bare f"file:{path}?mode=ro" mis-parses (especially on Windows)."""
+    db_dir = tmp_path / "palace with spaces"
+    db_dir.mkdir()
+    db_path = db_dir / "chroma.sqlite3"
+    setup = sqlite3.connect(str(db_path))
+    setup.execute("CREATE TABLE t (x INTEGER)")
+    setup.execute("INSERT INTO t VALUES (42)")
+    setup.commit()
+    setup.close()
+
+    uri = sqlite_read_uri(str(db_path))
+    assert "%20" in uri  # the space is percent-encoded, not left raw
+
+    conn = sqlite3.connect(uri, uri=True)
+    try:
+        assert conn.execute("SELECT x FROM t").fetchone()[0] == 42
+        # mode=ro is still honored through the encoded URI
+        with pytest.raises(sqlite3.OperationalError):
+            conn.execute("INSERT INTO t VALUES (1)")
+    finally:
+        conn.close()
+
+
 def test_env_override():
     raw = "/env/palace"
     os.environ["MEMPALACE_PALACE_PATH"] = raw