Merge pull request #3108 from mtmail/remove-legacy-wikipedia-tag-syntax

[nominatim.git] / nominatim / api / search / db_search_fields.py

diff --git a/nominatim/api/search/db_search_fields.py b/nominatim/api/search/db_search_fields.py
index 325e08df3559f9afd362242c69ec043c4ff617b0..59af826086db86027f2c808dee51824fb17e72ff 100644 (file)
--- a/nominatim/api/search/db_search_fields.py
+++ b/nominatim/api/search/db_search_fields.py
@@ -7,7 +7,7 @@
 """
 Data structures for more complex fields in abstract search descriptions.
 """
 """
 Data structures for more complex fields in abstract search descriptions.
 """

-from typing import List, Tuple, Iterator, cast
+from typing import List, Tuple, Iterator, cast, Dict

 import dataclasses
 
 import sqlalchemy as sa
 import dataclasses
 
 import sqlalchemy as sa


@@ -129,10 +129,11 @@ class FieldRanking:
         """
         assert self.rankings
 
         """
         assert self.rankings
 

-        col = table.c[self.column]
-
-        return sa.case(*((col.contains(r.tokens),r.penalty) for r in self.rankings),
-                       else_=self.default)
+        return sa.func.weigh_search(table.c[self.column],
+                                    [f"{{{','.join((str(s) for s in r.tokens))}}}"
+                                     for r in self.rankings],
+                                    [r.penalty for r in self.rankings],
+                                    self.default)

 
 
 @dataclasses.dataclass
 
 
 @dataclasses.dataclass


@@ -194,10 +195,17 @@ class SearchData:
         """ Set the qulaifier field from the given tokens.
         """
         if tokens:
         """ Set the qulaifier field from the given tokens.
         """
         if tokens:

-            min_penalty = min(t.penalty for t in tokens)
+            categories: Dict[Tuple[str, str], float] = {}
+            min_penalty = 1000.0
+            for t in tokens:
+                if t.penalty < min_penalty:
+                    min_penalty = t.penalty
+                cat = t.get_category()
+                if t.penalty < categories.get(cat, 1000.0):
+                    categories[cat] = t.penalty

             self.penalty += min_penalty
             self.penalty += min_penalty

-            self.qualifiers = WeightedCategories([t.get_category() for t in tokens],
-                                                 [t.penalty - min_penalty for t in tokens])
+            self.qualifiers = WeightedCategories(list(categories.keys()),
+                                                 list(categories.values()))

 
 
     def set_ranking(self, rankings: List[FieldRanking]) -> None:
 
 
     def set_ranking(self, rankings: List[FieldRanking]) -> None:


@@ -210,3 +218,35 @@ class SearchData:
                 self.rankings.append(ranking)
             else:
                 self.penalty += ranking.default
                 self.rankings.append(ranking)
             else:
                 self.penalty += ranking.default

+
+
+def lookup_by_names(name_tokens: List[int], addr_tokens: List[int]) -> List[FieldLookup]:
+    """ Create a lookup list where name tokens are looked up via index
+        and potential address tokens are used to restrict the search further.
+    """
+    lookup = [FieldLookup('name_vector', name_tokens, 'lookup_all')]
+    if addr_tokens:
+        lookup.append(FieldLookup('nameaddress_vector', addr_tokens, 'restrict'))
+
+    return lookup
+
+
+def lookup_by_any_name(name_tokens: List[int], addr_tokens: List[int],
+                       lookup_type: str) -> List[FieldLookup]:
+    """ Create a lookup list where name tokens are looked up via index
+        and only one of the name tokens must be present.
+        Potential address tokens are used to restrict the search further.
+    """
+    lookup = [FieldLookup('name_vector', name_tokens, 'lookup_any')]
+    if addr_tokens:
+        lookup.append(FieldLookup('nameaddress_vector', addr_tokens, lookup_type))
+
+    return lookup
+
+
+def lookup_by_addr(name_tokens: List[int], addr_tokens: List[int]) -> List[FieldLookup]:
+    """ Create a lookup list where address tokens are looked up via index
+        and the name tokens are only used to restrict the search further.
+    """
+    return [FieldLookup('name_vector', name_tokens, 'restrict'),
+            FieldLookup('nameaddress_vector', addr_tokens, 'lookup_all')]