always state encoding when opening files in text mode

Also applies to Path.write_text().

nominatim/config.py

@@ -187,7 +187,7 @@ class Configuration:
         if configfile.suffix in ('.yaml', '.yml'):
             result = self._load_from_yaml(configfile)
         elif configfile.suffix == '.json':
-            with configfile.open('r') as cfg:
+            with configfile.open('r', encoding='utf-8') as cfg:
                 result = json.load(cfg)
         else:
             raise UsageError(f"Config file '{configfile}' has unknown format.")

nominatim/tokenizer/icu_tokenizer.py

@@ -187,7 +187,7 @@ class LegacyICUTokenizer(AbstractTokenizer):
                 @define('CONST_Max_Word_Frequency', 10000000);
                 @define('CONST_Term_Normalization_Rules', "{self.loader.normalization_rules}");
                 @define('CONST_Transliteration', "{self.loader.get_search_rules()}");
-                require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""))
+                require_once('{phpdir}/tokenizer/icu_tokenizer.php');"""), encoding='utf-8')
 
 
     def _save_config(self):

nominatim/tokenizer/legacy_tokenizer.py

@@ -255,7 +255,7 @@ class LegacyTokenizer(AbstractTokenizer):
                 @define('CONST_Max_Word_Frequency', {0.MAX_WORD_FREQUENCY});
                 @define('CONST_Term_Normalization_Rules', "{0.TERM_NORMALIZATION}");
                 require_once('{0.lib_dir.php}/tokenizer/legacy_tokenizer.php');
-                """.format(config)))
+                """.format(config)), encoding='utf-8')
 
 
     def _init_db_tables(self, config):