X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/5e5addcdbf20022b3fd76dc8c2275a1eecf12a3c..55b7edbab545346f7caa0cf9c708f18f74e16013:/nominatim/tokenizer/base.py?ds=sidebyside

diff --git a/nominatim/tokenizer/base.py b/nominatim/tokenizer/base.py
index e126507b..f81b3bc2 100644
--- a/nominatim/tokenizer/base.py
+++ b/nominatim/tokenizer/base.py
@@ -1,3 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
 """
 Abstract class defintions for tokenizers. These base classes are here
 mainly for documentation purposes.
@@ -30,7 +36,6 @@ class AbstractAnalyzer(ABC):
     def close(self) -> None:
         """ Free all resources used by the analyzer.
         """
-        pass
 
 
     @abstractmethod
@@ -50,7 +55,6 @@ class AbstractAnalyzer(ABC):
                 found for the given words. Each list entry is a tuple of
                 (original word, word token, word id).
         """
-        pass
 
 
     @abstractmethod
@@ -66,7 +70,6 @@ class AbstractAnalyzer(ABC):
             Returns:
                 The given postcode after normalization.
         """
-        pass
 
 
     @abstractmethod
@@ -74,7 +77,6 @@ class AbstractAnalyzer(ABC):
         """ Update the tokenizer's postcode tokens from the current content
             of the `location_postcode` table.
         """
-        pass
 
 
     @abstractmethod
@@ -90,7 +92,6 @@ class AbstractAnalyzer(ABC):
                                 When false, just add the given phrases to the
                                 ones that already exist.
         """
-        pass
 
 
     @abstractmethod
@@ -102,7 +103,6 @@ class AbstractAnalyzer(ABC):
                               refer to.
                 names: Dictionary of name type to name.
         """
-        pass
 
 
     @abstractmethod
@@ -145,17 +145,18 @@ class AbstractTokenizer(ABC):
 
             TODO: can we move the init_db parameter somewhere else?
         """
-        pass
 
 
     @abstractmethod
-    def init_from_project(self) -> None:
+    def init_from_project(self, config: Configuration) -> None:
         """ Initialise the tokenizer from an existing database setup.
 
             The function should load all previously saved configuration from
             the project directory and/or the property table.
+
+            Arguments:
+              config: Read-only object with configuration options.
         """
-        pass
 
 
     @abstractmethod
@@ -168,7 +169,6 @@ class AbstractTokenizer(ABC):
             Arguments:
               config: Read-only object with configuration options.
         """
-        pass
 
 
     @abstractmethod
@@ -183,22 +183,37 @@ class AbstractTokenizer(ABC):
             Arguments:
               config: Read-only object with configuration options.
         """
-        pass
 
 
     @abstractmethod
-    def check_database(self) -> str:
+    def check_database(self, config: Configuration) -> str:
         """ Check that the database is set up correctly and ready for being
             queried.
 
+            Arguments:
+              config: Read-only object with configuration options.
+
             Returns:
               If an issue was found, return an error message with the
               description of the issue as well as hints for the user on
-              how to resolve the issue.
+              how to resolve the issue. If everything is okay, return `None`.
+        """
 
-              Return `None`, if no issue was found.
+
+    @abstractmethod
+    def update_statistics(self) -> None:
+        """ Recompute any tokenizer statistics necessary for efficient lookup.
+            This function is meant to be called from time to time by the user
+            to improve performance. However, the tokenizer must not depend on
+            it to be called in order to work.
+        """
+
+
+    @abstractmethod
+    def update_word_tokens(self) -> None:
+        """ Do house-keeping on the tokenizers internal data structures.
+            Remove unused word tokens, resort data etc.
         """
-        pass
 
 
     @abstractmethod
@@ -215,4 +230,3 @@ class AbstractTokenizer(ABC):
             When used outside the with construct, the caller must ensure to
             call the close() function before destructing the analyzer.
         """
-        pass