Merge pull request #911 from MemPalace/refactor/entity-detector-i18n

refactor(entity_detector): make multi-language extensible via i18n JSON

Author: igorls

mempalace/cli.py

@@ -73,12 +73,25 @@ def cmd_init(args):
     from .entity_detector import scan_for_detection, detect_entities, confirm_entities
     from .room_detector_local import detect_rooms_local
 
+    cfg = MempalaceConfig()
+
+    # Resolve entity-detection languages: --lang overrides config.
+    lang_arg = getattr(args, "lang", None)
+    if lang_arg:
+        languages = [s.strip() for s in lang_arg.split(",") if s.strip()] or ["en"]
+        cfg.set_entity_languages(languages)
+    else:
+        languages = cfg.entity_languages
+    languages_tuple = tuple(languages)
+
     # Pass 1: auto-detect people and projects from file content
     print(f"\n  Scanning for entities in: {args.dir}")
+    if languages_tuple != ("en",):
+        print(f"  Languages: {', '.join(languages_tuple)}")
     files = scan_for_detection(args.dir)
     if files:
         print(f"  Reading {len(files)} files...")
-        detected = detect_entities(files)
+        detected = detect_entities(files, languages=languages_tuple)
         total = len(detected["people"]) + len(detected["projects"]) + len(detected["uncertain"])
         if total > 0:
             confirmed = confirm_entities(detected, yes=getattr(args, "yes", False))
@@ -93,7 +106,7 @@ def cmd_init(args):
 
     # Pass 2: detect rooms from folder structure
     detect_rooms_local(project_dir=args.dir, yes=getattr(args, "yes", False))
-    MempalaceConfig().init()
+    cfg.init()
 
     # Pass 3: protect git repos from accidentally committing per-project files
     _ensure_mempalace_files_gitignored(args.dir)
@@ -478,6 +491,16 @@ def main():
         action="store_true",
         help="Auto-accept all detected entities (non-interactive)",
     )
+    p_init.add_argument(
+        "--lang",
+        default=None,
+        help=(
+            "Comma-separated language codes for entity detection "
+            "(e.g. 'en' or 'en,pt-br'). Defaults to value from config "
+            "(MEMPALACE_ENTITY_LANGUAGES env var or config.json), or 'en'. "
+            "When given, the value is also persisted to config.json."
+        ),
+    )
 
     # mine
     p_mine = sub.add_parser("mine", help="Mine files into the palace")

mempalace/config.py

@@ -197,6 +197,42 @@ def hall_keywords(self):
         """Mapping of hall names to keyword lists."""
         return self._file_config.get("hall_keywords", DEFAULT_HALL_KEYWORDS)
 
+    @property
+    def entity_languages(self):
+        """Languages whose entity-detection patterns should be applied.
+
+        Reads from env var ``MEMPALACE_ENTITY_LANGUAGES`` (comma-separated)
+        first, then the ``entity_languages`` field in ``config.json``,
+        defaulting to ``["en"]``.
+        """
+        env_val = os.environ.get("MEMPALACE_ENTITY_LANGUAGES") or os.environ.get(
+            "MEMPAL_ENTITY_LANGUAGES"
+        )
+        if env_val:
+            return [s.strip() for s in env_val.split(",") if s.strip()] or ["en"]
+        cfg = self._file_config.get("entity_languages")
+        if isinstance(cfg, list) and cfg:
+            return [str(s) for s in cfg]
+        return ["en"]
+
+    def set_entity_languages(self, languages):
+        """Persist the entity-detection language list to ``config.json``."""
+        normalized = [s.strip() for s in languages if s and s.strip()]
+        if not normalized:
+            normalized = ["en"]
+        self._file_config["entity_languages"] = normalized
+        self._config_dir.mkdir(parents=True, exist_ok=True)
+        try:
+            with open(self._config_file, "w", encoding="utf-8") as f:
+                json.dump(self._file_config, f, indent=2, ensure_ascii=False)
+        except OSError:
+            pass
+        try:
+            self._config_file.chmod(0o600)
+        except (OSError, NotImplementedError):
+            pass
+        return normalized
+
     @property
     def hook_silent_save(self):
         """Whether the stop hook saves directly (True) or blocks for MCP calls (False)."""