docs: fix typos

nominatim/tokenizer/base.py

@@ -5,7 +5,7 @@
 # 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
@@ -113,7 +113,7 @@ 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
@@ -141,7 +141,7 @@ 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?

nominatim/tokenizer/factory.py

@@ -9,11 +9,11 @@ Functions for creating a tokenizer or initialising the right one for an
 existing database.
 
 A tokenizer is something that is bound to the lifetime of a database. It
-can be choosen and configured before the intial import but then needs to
+can be chosen and configured before the initial import but then needs to
 be used consistently when querying and updating the database.
 
 This module provides the functions to create and configure a new tokenizer
-as well as instanciating the appropriate tokenizer for updating an existing
+as well as instantiating the appropriate tokenizer for updating an existing
 database.
 
 A tokenizer usually also includes PHP code for querying. The appropriate PHP

nominatim/tokenizer/icu_tokenizer.py

@@ -38,7 +38,7 @@ def create(dsn: str, data_dir: Path) -> 'ICUTokenizer':
 
 
 class ICUTokenizer(AbstractTokenizer):
-    """ This tokenizer uses libICU to covert names and queries to ASCII.
+    """ This tokenizer uses libICU to convert names and queries to ASCII.
         Otherwise it uses the same algorithms and data structures as the
         normalization routines in Nominatim 3.
     """
@@ -431,7 +431,7 @@ class ICUNameAnalyzer(AbstractAnalyzer):
     def _remove_special_phrases(self, cursor: Cursor,
                              new_phrases: Set[Tuple[str, str, str, str]],
                              existing_phrases: Set[Tuple[str, str, str, str]]) -> int:
-        """ Remove all phrases from the databse that are no longer in the
+        """ Remove all phrases from the database that are no longer in the
             new phrase list.
         """
         to_delete = existing_phrases - new_phrases
@@ -620,7 +620,7 @@ class ICUNameAnalyzer(AbstractAnalyzer):
 
     def _retrieve_full_tokens(self, name: str) -> List[int]:
         """ Get the full name token for the given name, if it exists.
-            The name is only retrived for the standard analyser.
+            The name is only retrieved for the standard analyser.
         """
         assert self.conn is not None
         norm_name = self._search_normalized(name)

nominatim/tokenizer/sanitizers/clean_postcodes.py

@@ -59,7 +59,7 @@ class _PostcodeSanitizer:
     def scan(self, postcode: str, country: Optional[str]) -> Optional[Tuple[str, str]]:
         """ Check the postcode for correct formatting and return the
             normalized version. Returns None if the postcode does not
-            correspond to the oficial format of the given country.
+            correspond to the official format of the given country.
         """
         match = self.matcher.match(country, postcode)
         if match is None:

nominatim/tokenizer/sanitizers/config.py

@@ -90,7 +90,7 @@ class SanitizerConfig(_BaseUserDict):
             True when the item passes the filter.
 
             If the parameter is empty, the filter lets all items pass. If the
-            paramter is a string, it is interpreted as a single regular expression
+            parameter is a string, it is interpreted as a single regular expression
             that must match the full kind string. If the parameter is a list then
             any of the regular expressions in the list must match to pass.
         """

nominatim/tokenizer/token_analysis/config_variants.py

@@ -58,7 +58,7 @@ def get_variant_config(in_rules: Any,
 
 
 class _VariantMaker:
-    """ Generater for all necessary ICUVariants from a single variant rule.
+    """ Generator for all necessary ICUVariants from a single variant rule.
 
         All text in rules is normalized to make sure the variants match later.
     """

nominatim/tokenizer/token_analysis/generic_mutation.py

@@ -23,7 +23,7 @@ def _zigzag(outer: Iterable[str], inner: Iterable[str]) -> Iterator[str]:
 class MutationVariantGenerator:
     """ Generates name variants by applying a regular expression to the name
         and replacing it with one or more variants. When the regular expression
-        matches more than once, each occurence is replaced with all replacement
+        matches more than once, each occurrence is replaced with all replacement
         patterns.
     """