X-Git-Url: https://git.openstreetmap.org./nominatim.git/blobdiff_plain/c314a3092c5b51c7782015f6fa9ac093b46fa174..7c9002cae7f950a99f3045d3058ed61ef79fe044:/src/nominatim_db/tokenizer/base.py?ds=sidebyside

diff --git a/src/nominatim_db/tokenizer/base.py b/src/nominatim_db/tokenizer/base.py
index d3aeeaca..4b96cb23 100644
--- a/src/nominatim_db/tokenizer/base.py
+++ b/src/nominatim_db/tokenizer/base.py
@@ -17,6 +17,7 @@ from ..config import Configuration
 from ..db.connection import Connection
 from ..data.place_info import PlaceInfo
 
+
 class AbstractAnalyzer(ABC):
     """ The analyzer provides the functions for analysing names and building
         the token database.
@@ -28,17 +29,14 @@ class AbstractAnalyzer(ABC):
     def __enter__(self) -> 'AbstractAnalyzer':
         return self
 
-
     def __exit__(self, exc_type: Any, exc_value: Any, traceback: Any) -> None:
         self.close()
 
-
     @abstractmethod
     def close(self) -> None:
         """ Free all resources used by the analyzer.
         """
 
-
     @abstractmethod
     def get_word_token_info(self, words: List[str]) -> List[Tuple[str, str, int]]:
         """ Return token information for the given list of words.
@@ -57,7 +55,6 @@ class AbstractAnalyzer(ABC):
                     (original word, word token, word id).
         """
 
-
     @abstractmethod
     def normalize_postcode(self, postcode: str) -> str:
         """ Convert the postcode to its standardized form.
@@ -72,14 +69,12 @@ class AbstractAnalyzer(ABC):
                 The given postcode after normalization.
         """
 
-
     @abstractmethod
     def update_postcodes_from_db(self) -> None:
         """ Update the tokenizer's postcode tokens from the current content
             of the `location_postcode` table.
         """
 
-
     @abstractmethod
     def update_special_phrases(self,
                                phrases: Iterable[Tuple[str, str, str, str]],
@@ -95,7 +90,6 @@ class AbstractAnalyzer(ABC):
                                 ones that already exist.
         """
 
-
     @abstractmethod
     def add_country_names(self, country_code: str, names: Dict[str, str]) -> None:
         """ Add the given names to the tokenizer's list of country tokens.
@@ -106,7 +100,6 @@ class AbstractAnalyzer(ABC):
                 names: Dictionary of name type to name.
         """
 
-
     @abstractmethod
     def process_place(self, place: PlaceInfo) -> Any:
         """ Extract tokens for the given place and compute the
@@ -122,7 +115,6 @@ class AbstractAnalyzer(ABC):
         """
 
 
-
 class AbstractTokenizer(ABC):
     """ The tokenizer instance is the central instance of the tokenizer in
         the system. There will only be a single instance of the tokenizer
@@ -146,7 +138,6 @@ class AbstractTokenizer(ABC):
                 tokenizers.
         """
 
-
     @abstractmethod
     def init_from_project(self, config: Configuration) -> None:
         """ Initialise the tokenizer from an existing database setup.
@@ -158,7 +149,6 @@ class AbstractTokenizer(ABC):
               config: Read-only object with configuration options.
         """
 
-
     @abstractmethod
     def finalize_import(self, config: Configuration) -> None:
         """ This function is called at the very end of an import when all
@@ -170,7 +160,6 @@ class AbstractTokenizer(ABC):
               config: Read-only object with configuration options.
         """
 
-
     @abstractmethod
     def update_sql_functions(self, config: Configuration) -> None:
         """ Update the SQL part of the tokenizer. This function is called
@@ -184,7 +173,6 @@ class AbstractTokenizer(ABC):
               config: Read-only object with configuration options.
         """
 
-
     @abstractmethod
     def check_database(self, config: Configuration) -> Optional[str]:
         """ Check that the database is set up correctly and ready for being
@@ -199,7 +187,6 @@ class AbstractTokenizer(ABC):
                   how to resolve the issue. If everything is okay, return `None`.
         """
 
-
     @abstractmethod
     def update_statistics(self, config: Configuration, threads: int = 1) -> None:
         """ Recompute any tokenizer statistics necessary for efficient lookup.
@@ -208,14 +195,12 @@ class AbstractTokenizer(ABC):
             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.
         """
 
-
     @abstractmethod
     def name_analyzer(self) -> AbstractAnalyzer:
         """ Create a new analyzer for tokenizing names and queries
@@ -231,7 +216,6 @@ class AbstractTokenizer(ABC):
             call the close() function before destructing the analyzer.
         """
 
-
     @abstractmethod
     def most_frequent_words(self, conn: Connection, num: int) -> List[str]:
         """ Return a list of the most frequent full words in the database.