From c41f2fed2133668dc3179813261d39d3ff69cbdd Mon Sep 17 00:00:00 2001
From: Sarah Hoffmann <lonvia@denofr.de>
Date: Tue, 5 Dec 2023 16:07:56 +0100
Subject: [PATCH] simplify weigh_search() function

Use JSON arrays which can have mixed types and therefore have
a more logical structure than separate arrays. Avoid JSON dicts
because of their verboseness.
---
 lib-sql/functions/ranking.sql            | 14 ++++++--------
 nominatim/api/search/db_search_fields.py | 17 ++++++++++++-----
 nominatim/utils/json_writer.py           |  4 ++--
 3 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/lib-sql/functions/ranking.sql b/lib-sql/functions/ranking.sql
index 0b18954c..97a0cde3 100644
--- a/lib-sql/functions/ranking.sql
+++ b/lib-sql/functions/ranking.sql
@@ -287,21 +287,19 @@ LANGUAGE plpgsql IMMUTABLE;
 
 
 CREATE OR REPLACE FUNCTION weigh_search(search_vector INT[],
-                                        term_vectors TEXT[],
-                                        weight_vectors FLOAT[],
+                                        rankings TEXT,
                                         def_weight FLOAT)
   RETURNS FLOAT
   AS $$
 DECLARE
-  pos INT := 1;
-  terms TEXT;
+  rank JSON;
 BEGIN
-  FOREACH terms IN ARRAY term_vectors
+  FOR rank IN
+    SELECT * FROM json_array_elements(rankings::JSON)
   LOOP
-    IF search_vector @> terms::INTEGER[] THEN
-      RETURN weight_vectors[pos];
+    IF true = ALL(SELECT x::int = ANY(search_vector) FROM json_array_elements_text(rank->1) as x) THEN
+      RETURN (rank->>0)::float;
     END IF;
-    pos := pos + 1;
   END LOOP;
   RETURN def_weight;
 END;
diff --git a/nominatim/api/search/db_search_fields.py b/nominatim/api/search/db_search_fields.py
index 52693e95..324a7acc 100644
--- a/nominatim/api/search/db_search_fields.py
+++ b/nominatim/api/search/db_search_fields.py
@@ -14,6 +14,7 @@ import sqlalchemy as sa
 
 from nominatim.typing import SaFromClause, SaColumn, SaExpression
 from nominatim.api.search.query import Token
+from nominatim.utils.json_writer import JsonWriter
 
 @dataclasses.dataclass
 class WeightedStrings:
@@ -128,11 +129,17 @@ class FieldRanking:
         """
         assert self.rankings
 
-        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)
+        rout = JsonWriter().start_array()
+        for rank in self.rankings:
+            rout.start_array().value(rank.penalty).next()
+            rout.start_array()
+            for token in rank.tokens:
+                rout.value(token).next()
+            rout.end_array()
+            rout.end_array().next()
+        rout.end_array()
+
+        return sa.func.weigh_search(table.c[self.column], rout(), self.default)
 
 
 @dataclasses.dataclass
diff --git a/nominatim/utils/json_writer.py b/nominatim/utils/json_writer.py
index bb642233..fcc355d5 100644
--- a/nominatim/utils/json_writer.py
+++ b/nominatim/utils/json_writer.py
@@ -76,8 +76,8 @@ class JsonWriter:
     def end_array(self) -> 'JsonWriter':
         """ Write the closing bracket of a JSON array.
         """
-        assert self.pending in (',', '[', '')
-        if self.pending == '[':
+        assert self.pending in (',', '[', ']', ')', '')
+        if self.pending not in (',', ''):
             self.data.write(self.pending)
         self.pending = ']'
         return self