Merge pull request #3178 from lonvia/library-documentation

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

diff --git a/nominatim/tokenizer/base.py b/nominatim/tokenizer/base.py
index 6484ff6a06a798b206c9c8e54bf947cf2da4b1d4..061cff36b99f22273e55e350d410d4291c425b91 100644 (file)
--- a/nominatim/tokenizer/base.py
+++ b/nominatim/tokenizer/base.py
@@ -5,17 +5,17 @@
 # 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
+Abstract class definitions for tokenizers. These base classes are here
 mainly for documentation purposes.
 """
 from abc import ABC, abstractmethod
-from typing import List, Tuple, Dict, Any
+from typing import List, Tuple, Dict, Any, Optional, Iterable
 from pathlib import Path
 
-from typing_extensions import Protocol
-
 from nominatim.config import Configuration
+from nominatim.db.connection import Connection
 from nominatim.data.place_info import PlaceInfo
+from nominatim.typing import Protocol
 
 class AbstractAnalyzer(ABC):
     """ The analyzer provides the functions for analysing names and building
@@ -53,8 +53,8 @@ class AbstractAnalyzer(ABC):
 
             Returns:
                 The function returns the list of all tuples that could be
-                found for the given words. Each list entry is a tuple of
-                (original word, word token, word id).
+                    found for the given words. Each list entry is a tuple of
+                    (original word, word token, word id).
         """
 
 
@@ -81,7 +81,8 @@ class AbstractAnalyzer(ABC):
 
 
     @abstractmethod
-    def update_special_phrases(self, phrases: List[Tuple[str, str, str, str]],
+    def update_special_phrases(self,
+                               phrases: Iterable[Tuple[str, str, str, str]],
                                should_replace: bool) -> None:
         """ Update the tokenizer's special phrase tokens from the given
             list of special phrases.
@@ -113,11 +114,11 @@ class AbstractAnalyzer(ABC):
             the search index.
 
             Arguments:
-                place: Place information retrived from the database.
+                place: Place information retrieved from the database.
 
             Returns:
                 A JSON-serialisable structure that will be handed into
-                the database via the `token_info` field.
+                    the database via the `token_info` field.
         """
 
 
@@ -141,10 +142,8 @@ class AbstractTokenizer(ABC):
 
               init_db: When set to False, then initialisation of database
                 tables should be skipped. This option is only required for
-                migration purposes and can be savely ignored by custom
+                migration purposes and can be safely ignored by custom
                 tokenizers.
-
-            TODO: can we move the init_db parameter somewhere else?
         """
 
 
@@ -187,7 +186,7 @@ class AbstractTokenizer(ABC):
 
 
     @abstractmethod
-    def check_database(self, config: Configuration) -> str:
+    def check_database(self, config: Configuration) -> Optional[str]:
         """ Check that the database is set up correctly and ready for being
             queried.
 
@@ -196,8 +195,8 @@ class AbstractTokenizer(ABC):
 
             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. If everything is okay, return `None`.
+                  description of the issue as well as hints for the user on
+                  how to resolve the issue. If everything is okay, return `None`.
         """
 
 
@@ -233,6 +232,17 @@ class AbstractTokenizer(ABC):
         """
 
 
+    @abstractmethod
+    def most_frequent_words(self, conn: Connection, num: int) -> List[str]:
+        """ Return a list of the most frequent full words in the database.
+
+            Arguments:
+              conn: Open connection to the database which may be used to
+                    retrieve the words.
+              num: Maximum number of words to return.
+        """
+
+
 class TokenizerModule(Protocol):
     """ Interface that must be exported by modules that implement their
         own tokenizer.