do not hide errors when importing tokenizer

Explicitly check for the tokenizer source file to check that
the name is correct. We can't use the import error for that
because it hides other import errors like a missing
library.

Fixes #2327.

diff --git a/nominatim/tokenizer/factory.py b/nominatim/tokenizer/factory.py
index e0c06293ff56e22b9d90938bb5af923b0e279bdb..069672d4a1fd4d9b874943b5d44a367d4f2ef9e8 100644 (file)
--- a/nominatim/tokenizer/factory.py
+++ b/nominatim/tokenizer/factory.py
@@ -15,6 +15,7 @@ normalizer module is installed, when the tokenizer is created.
 """
 import logging
 import importlib
+from pathlib import Path
 
 from ..errors import UsageError
 from ..db import properties
@@ -25,12 +26,13 @@ LOG = logging.getLogger()
 def _import_tokenizer(name):
     """ Load the tokenizer.py module from project directory.
     """
-    try:
-        return importlib.import_module('nominatim.tokenizer.' + name + '_tokenizer')
-    except ModuleNotFoundError as exp:
+    src_file = Path(__file__).parent / (name + '_tokenizer.py')
+    if not src_file.is_file():
         LOG.fatal("No tokenizer named '%s' available. "
                   "Check the setting of NOMINATIM_TOKENIZER.", name)
-        raise UsageError('Tokenizer not found') from exp
+        raise UsageError('Tokenizer not found')
+
+    return importlib.import_module('nominatim.tokenizer.' + name + '_tokenizer')
 
 
 def create_tokenizer(config, init_db=True, module_name=None):

diff --git a/test/python/conftest.py b/test/python/conftest.py
index 923e6876a9beaced058600e303c8fa5e874ecafb..a3249474c4ad3acfd56572eea63deeb5d5a51702 100644 (file)
--- a/test/python/conftest.py
+++ b/test/python/conftest.py
@@ -17,6 +17,7 @@ from nominatim.config import Configuration
 from nominatim.db import connection
 from nominatim.db.sql_preprocessor import SQLPreprocessor
 from nominatim.db import properties
+import nominatim.tokenizer.factory
 
 import dummy_tokenizer
 import mocks
@@ -273,7 +274,7 @@ def tokenizer_mock(monkeypatch, property_table, temp_db_conn, tmp_path):
     def _import_dummy(module, *args, **kwargs):
         return dummy_tokenizer
 
-    monkeypatch.setattr(importlib, "import_module", _import_dummy)
+    monkeypatch.setattr(nominatim.tokenizer.factory, "_import_tokenizer", _import_dummy)
     properties.set_property(temp_db_conn, 'tokenizer', 'dummy')
 
     def _create_tokenizer():