Adds sanitizer for preventing certain tags to enter search index based on parameters

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

diff --git a/nominatim/tokenizer/sanitizers/base.py b/nominatim/tokenizer/sanitizers/base.py
index f2e1bc41538fbed863c1d2c768c2cb3eeb520632..2de868c787cb6f47d75039a1b239ab385f9853af 100644 (file)
--- a/nominatim/tokenizer/sanitizers/base.py
+++ b/nominatim/tokenizer/sanitizers/base.py
@@ -7,73 +7,12 @@
 """
 Common data types and protocols for sanitizers.
 """
-from typing import Optional, Dict, List, Mapping, Callable
+from typing import Optional, List, Mapping, Callable
 
-from typing_extensions import Protocol, Final
 from nominatim.tokenizer.sanitizers.config import SanitizerConfig
 from nominatim.data.place_info import PlaceInfo
-
-class PlaceName:
-    """ A searchable name for a place together with properties.
-        Every name object saves the name proper and two basic properties:
-        * 'kind' describes the name of the OSM key used without any suffixes
-          (i.e. the part after the colon removed)
-        * 'suffix' contains the suffix of the OSM tag, if any. The suffix
-          is the part of the key after the first colon.
-        In addition to that, the name may have arbitrary additional attributes.
-        Which attributes are used, depends on the token analyser.
-    """
-
-    def __init__(self, name: str, kind: str, suffix: Optional[str]):
-        self.name = name
-        self.kind = kind
-        self.suffix = suffix
-        self.attr: Dict[str, str] = {}
-
-
-    def __repr__(self) -> str:
-        return f"PlaceName(name='{self.name}',kind='{self.kind}',suffix='{self.suffix}')"
-
-
-    def clone(self, name: Optional[str] = None,
-              kind: Optional[str] = None,
-              suffix: Optional[str] = None,
-              attr: Optional[Mapping[str, str]] = None) -> 'PlaceName':
-        """ Create a deep copy of the place name, optionally with the
-            given parameters replaced. In the attribute list only the given
-            keys are updated. The list is not replaced completely.
-            In particular, the function cannot to be used to remove an
-            attribute from a place name.
-        """
-        newobj = PlaceName(name or self.name,
-                           kind or self.kind,
-                           suffix or self.suffix)
-
-        newobj.attr.update(self.attr)
-        if attr:
-            newobj.attr.update(attr)
-
-        return newobj
-
-
-    def set_attr(self, key: str, value: str) -> None:
-        """ Add the given property to the name. If the property was already
-            set, then the value is overwritten.
-        """
-        self.attr[key] = value
-
-
-    def get_attr(self, key: str, default: Optional[str] = None) -> Optional[str]:
-        """ Return the given property or the value of 'default' if it
-            is not set.
-        """
-        return self.attr.get(key, default)
-
-
-    def has_attr(self, key: str) -> bool:
-        """ Check if the given attribute is set.
-        """
-        return key in self.attr
+from nominatim.data.place_name import PlaceName
+from nominatim.typing import Protocol, Final
 
 
 class ProcessInfo:
@@ -113,7 +52,13 @@ class SanitizerHandler(Protocol):
 
     def create(self, config: SanitizerConfig) -> Callable[[ProcessInfo], None]:
         """
-        A sanitizer must define a single function `create`. It takes the
-        dictionary with the configuration information for the sanitizer and
-        returns a function that transforms name and address.
+        Create a function for sanitizing a place.
+
+        Arguments:
+            config: A dictionary with the additional configuration options
+                    specified in the tokenizer configuration
+
+        Return:
+            The result must be a callable that takes a place description
+            and transforms name and address as reuqired.
         """