new word table layout for icu tokenizer

The table now directly reflects the different token types.
Extra information is saved in a json structure that may be
dynamically extended in the future without affecting the
table layout.

nominatim/tokenizer/legacy_icu_tokenizer.py

@@ -152,7 +152,7 @@ class LegacyICUTokenizer:
         """
         with connect(self.dsn) as conn:
             sqlp = SQLPreprocessor(conn, config)
-            sqlp.run_sql_file(conn, 'tokenizer/legacy_tokenizer_tables.sql')
+            sqlp.run_sql_file(conn, 'tokenizer/icu_tokenizer_tables.sql')
             conn.commit()
 
             LOG.warning("Precomputing word tokens")