X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/5e477e3b5b99da6fc4e54749d4671a6fc8fdcd66..a87fe8d8bf2f4dd784fdb94031bc978b3f28b799:/nominatim/tokenizer/base.py diff --git a/nominatim/tokenizer/base.py b/nominatim/tokenizer/base.py index afbd1914..061cff36 100644 --- a/nominatim/tokenizer/base.py +++ b/nominatim/tokenizer/base.py @@ -13,6 +13,7 @@ from typing import List, Tuple, Dict, Any, Optional, Iterable from pathlib import Path from nominatim.config import Configuration +from nominatim.db.connection import Connection from nominatim.data.place_info import PlaceInfo from nominatim.typing import Protocol @@ -52,8 +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). """ @@ -117,7 +118,7 @@ class AbstractAnalyzer(ABC): Returns: A JSON-serialisable structure that will be handed into - the database via the `token_info` field. + the database via the `token_info` field. """ @@ -143,8 +144,6 @@ class AbstractTokenizer(ABC): tables should be skipped. This option is only required for migration purposes and can be safely ignored by custom tokenizers. - - TODO: can we move the init_db parameter somewhere else? """ @@ -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.