port legacy tokenizer to new postcode handling

[nominatim.git] / nominatim / tokenizer / legacy_tokenizer.py

diff --git a/nominatim/tokenizer/legacy_tokenizer.py b/nominatim/tokenizer/legacy_tokenizer.py
index 551b0536b88dbe77012a364015005a60cbe19548..36fd5722441a12e92d24434d5dc1317497dd27bc 100644 (file)
--- a/nominatim/tokenizer/legacy_tokenizer.py
+++ b/nominatim/tokenizer/legacy_tokenizer.py
@@ -74,10 +74,10 @@ def _check_module(module_dir, conn):
     with conn.cursor() as cur:
         try:
             cur.execute("""CREATE FUNCTION nominatim_test_import_func(text)
-                           RETURNS text AS '{}/nominatim.so', 'transliteration'
+                           RETURNS text AS %s, 'transliteration'
                            LANGUAGE c IMMUTABLE STRICT;
                            DROP FUNCTION nominatim_test_import_func(text)
-                        """.format(module_dir))
+                        """, (f'{module_dir}/nominatim.so', ))
         except psycopg2.DatabaseError as err:
             LOG.fatal("Error accessing database module: %s", err)
             raise UsageError("Database module cannot be accessed.") from err
@@ -107,7 +107,7 @@ class LegacyTokenizer(AbstractTokenizer):
 
         self.normalization = config.TERM_NORMALIZATION
 
-        self._install_php(config)
+        self._install_php(config, overwrite=True)
 
         with connect(self.dsn) as conn:
             _check_module(module_dir, conn)
@@ -119,12 +119,18 @@ class LegacyTokenizer(AbstractTokenizer):
             self._init_db_tables(config)
 
 
-    def init_from_project(self, _):
+    def init_from_project(self, config):
         """ Initialise the tokenizer from the project directory.
         """
         with connect(self.dsn) as conn:
             self.normalization = properties.get_property(conn, DBCFG_NORMALIZATION)
 
+        if not (config.project_dir / 'module' / 'nominatim.so').exists():
+            _install_module(config.DATABASE_MODULE_PATH,
+                            config.lib_dir.module,
+                            config.project_dir / 'module')
+
+        self._install_php(config, overwrite=False)
 
     def finalize_import(self, config):
         """ Do any required postprocessing to make the tokenizer data ready
@@ -211,6 +217,13 @@ class LegacyTokenizer(AbstractTokenizer):
                     cur.drop_table("word_frequencies")
             conn.commit()
 
+
+    def update_word_tokens(self):
+        """ No house-keeping implemented for the legacy tokenizer.
+        """
+        LOG.info("No tokenizer clean-up available.")
+
+
     def name_analyzer(self):
         """ Create a new analyzer for tokenizing names and queries
             using this tokinzer. Analyzers are context managers and should
@@ -231,16 +244,18 @@ class LegacyTokenizer(AbstractTokenizer):
         return LegacyNameAnalyzer(self.dsn, normalizer)
 
 
-    def _install_php(self, config):
+    def _install_php(self, config, overwrite=True):
         """ Install the php script for the tokenizer.
         """
         php_file = self.data_dir / "tokenizer.php"
-        php_file.write_text(dedent("""\
-            <?php
-            @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)))
+
+        if not php_file.exists() or overwrite:
+            php_file.write_text(dedent(f"""\
+                <?php
+                @define('CONST_Max_Word_Frequency', {config.MAX_WORD_FREQUENCY});
+                @define('CONST_Term_Normalization_Rules', "{config.TERM_NORMALIZATION}");
+                require_once('{config.lib_dir.php}/tokenizer/legacy_tokenizer.php');
+                """), encoding='utf-8')
 
 
     def _init_db_tables(self, config):
@@ -322,8 +337,7 @@ class LegacyNameAnalyzer(AbstractAnalyzer):
         return self.normalizer.transliterate(phrase)
 
 
-    @staticmethod
-    def normalize_postcode(postcode):
+    def normalize_postcode(self, postcode):
         """ Convert the postcode to a standardized form.
 
             This function must yield exactly the same result as the SQL function
@@ -453,15 +467,17 @@ class LegacyNameAnalyzer(AbstractAnalyzer):
             if key == 'postcode':
                 # Make sure the normalized postcode is present in the word table.
                 if re.search(r'[:,;]', value) is None:
-                    self._cache.add_postcode(self.conn,
-                                             self.normalize_postcode(value))
+                    norm_pc = self.normalize_postcode(value)
+                    token_info.set_postcode(norm_pc)
+                    self._cache.add_postcode(self.conn, norm_pc)
             elif key in ('housenumber', 'streetnumber', 'conscriptionnumber'):
                 hnrs.append(value)
             elif key == 'street':
                 token_info.add_street(self.conn, value)
             elif key == 'place':
                 token_info.add_place(self.conn, value)
-            elif not key.startswith('_') and key not in ('country', 'full'):
+            elif not key.startswith('_') \
+                 and key not in ('country', 'full', 'inclusion'):
                 addr_terms.append((key, value))
 
         if hnrs:
@@ -508,10 +524,15 @@ class _TokenInfo:
             simple_list = list(set(simple_list))
 
         with conn.cursor() as cur:
-            cur.execute("SELECT (create_housenumbers(%s)).* ", (simple_list, ))
+            cur.execute("SELECT * FROM create_housenumbers(%s)", (simple_list, ))
             self.data['hnr_tokens'], self.data['hnr'] = cur.fetchone()
 
 
+    def set_postcode(self, postcode):
+        """ Set or replace the postcode token with the given value.
+        """
+        self.data['postcode'] = postcode
+
     def add_street(self, conn, street):
         """ Add addr:street match terms.
         """