move PlaceName into the generic data module

docs/develop/ICU-Tokenizer-Modules.md

@@ -77,7 +77,7 @@ adding extra attributes) or completely replace the list with a different one.
 
 #### PlaceName - extended naming information
 
-::: nominatim.tokenizer.sanitizers.base.PlaceName
+::: nominatim.data.place_name.PlaceName
     rendering:
         show_source: no
         heading_level: 6
@@ -94,7 +94,7 @@ functions:
         heading_level: 6
 
 
-::: nominatim.tokenizer.token_analysis.base.Analyser
+::: nominatim.tokenizer.token_analysis.base.Analyzer
     rendering:
         show_source: no
         heading_level: 6

nominatim/data/place_name.py

@@ -0,0 +1,78 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2022 by the Nominatim developer community.
+# For a full list of authors see the git log.
+"""
+Data class for a single name of a place.
+"""
+from typing import Optional, Dict, Mapping
+
+class PlaceName:
+    """ Each name and address part of a place is encapsulated in an object of
+        this class. It saves not only the name proper but also describes the
+        kind of name with two 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, a name may have arbitrary additional attributes.
+        How attributes are used, depends on the sanatizers and token analysers.
+        The exception is is the 'analyzer' attribute. This attribute determines
+        which token analysis module will be used to finalize the treatment of
+        names.
+    """
+
+    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

nominatim/tokenizer/icu_tokenizer.py

@@ -23,7 +23,7 @@ from nominatim.db.sql_preprocessor import SQLPreprocessor
 from nominatim.data.place_info import PlaceInfo
 from nominatim.tokenizer.icu_rule_loader import ICURuleLoader
 from nominatim.tokenizer.place_sanitizer import PlaceSanitizer
-from nominatim.tokenizer.sanitizers.base import PlaceName
+from nominatim.data.place_name import PlaceName
 from nominatim.tokenizer.icu_token_analysis import ICUTokenAnalysis
 from nominatim.tokenizer.base import AbstractAnalyzer, AbstractTokenizer
 

nominatim/tokenizer/place_sanitizer.py

@@ -13,7 +13,8 @@ from typing import Optional, List, Mapping, Sequence, Callable, Any, Tuple
 from nominatim.errors import UsageError
 from nominatim.config import Configuration
 from nominatim.tokenizer.sanitizers.config import SanitizerConfig
-from nominatim.tokenizer.sanitizers.base import SanitizerHandler, ProcessInfo, PlaceName
+from nominatim.tokenizer.sanitizers.base import SanitizerHandler, ProcessInfo
+from nominatim.data.place_name import PlaceName
 from nominatim.data.place_info import PlaceInfo
 
 

nominatim/tokenizer/sanitizers/base.py

@@ -7,80 +7,13 @@
 """
 Common data types and protocols for sanitizers.
 """
-from typing import Optional, Dict, List, Mapping, Callable
+from typing import Optional, List, Mapping, Callable
 
 from nominatim.tokenizer.sanitizers.config import SanitizerConfig
 from nominatim.data.place_info import PlaceInfo
+from nominatim.data.place_name import PlaceName
 from nominatim.typing import Protocol, Final
 
-class PlaceName:
-    """ Each name and address part of a place is encapsulated in an object of
-        this class. It saves not only the name proper but also describes the
-        kind of name with two 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, a name may have arbitrary additional attributes.
-        How attributes are used, depends on the sanatizers and token analysers.
-        The exception is is the 'analyzer' attribute. This apptribute determines
-        which token analysis module will be used to finalize the treatment of
-        names.
-    """
-
-    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
-
 
 class ProcessInfo:
     """ Container class for information handed into to handler functions.

nominatim/tokenizer/sanitizers/clean_housenumbers.py

@@ -27,7 +27,8 @@ Arguments:
 from typing import Callable, Iterator, List
 import re
 
-from nominatim.tokenizer.sanitizers.base import ProcessInfo, PlaceName
+from nominatim.tokenizer.sanitizers.base import ProcessInfo
+from nominatim.data.place_name import PlaceName
 from nominatim.tokenizer.sanitizers.config import SanitizerConfig
 
 class _HousenumberSanitizer: