Merge pull request #50642 from johanngan/regexptree-bad-opt

Revert invalid RegExpTreeDictionary optimization

src/Dictionaries/RegExpTreeDictionary.cpp

@@ -129,17 +129,6 @@ struct RegExpTreeDictionary::RegexTreeNode
         return searcher.Match(haystack, 0, size, re2_st::RE2::Anchor::UNANCHORED, nullptr, 0);
     }
 
-    /// check if this node can cover all the attributes from the query.
-    bool containsAll(const std::unordered_map<String, const DictionaryAttribute &> & matching_attributes) const
-    {
-        for (const auto & [key, value] : matching_attributes)
-        {
-            if (!attributes.contains(key))
-                return false;
-        }
-        return true;
-    }
-
     struct AttributeValue
     {
         Field field;
@@ -691,9 +680,6 @@ std::unordered_map<String, ColumnPtr> RegExpTreeDictionary::match(
             if (node_ptr->match(reinterpret_cast<const char *>(keys_data.data()) + offset, length))
             {
                 match_result.insertNodeID(node_ptr->id);
-                /// When this node is leaf and contains all the required attributes, it means a match.
-                if (node_ptr->containsAll(attributes) && node_ptr->children.empty())
-                    break;
             }
         }
 

tests/queries/0_stateless/02504_regexp_dictionary_yaml_source.reference

@@ -11,3 +11,19 @@
 (['ClickHouse Documentation','ClickHouse'],[0,1],['/en'],['ClickHouse'])
 (['Documentation','GitHub'],[2,3],[NULL],[])
 (['Documentation','GitHub'],[2,3],[NULL],[])
+ClickHouse
+['ClickHouse']
+ClickHouse Documentation
+['ClickHouse Documentation','ClickHouse','Documentation']
+GitHub Documentation
+['GitHub Documentation','GitHub']
+Documentation
+['Documentation']
+ClickHouse
+['ClickHouse']
+ClickHouse Documentation
+['ClickHouse Documentation','ClickHouse','Documentation']
+GitHub Documentation
+['GitHub Documentation','GitHub']
+Documentation
+['Documentation']

tests/queries/0_stateless/02504_regexp_dictionary_yaml_source.sh

@@ -175,6 +175,70 @@ select dictGetAll('regexp_dict3', ('tag', 'topological_index', 'captured', 'pare
 select dictGetAll('regexp_dict3', ('tag', 'topological_index', 'captured', 'parent'), 'github.com/clickhouse/tree/master/docs', 2);
 "
 
+# Test that things work the same for "simple" regexps that go through Hyperscan and "complex" regexps that go through RE2.
+# An easy way to force the use of RE2 is to disable Hyperscan.
+# This tree is constructed purposely so that text might (falsely) match leaf nodes without matching their corresponding parent nodes
+cat > "$yaml" <<EOL
+- regexp: 'clickhouse\.com'
+  tag: 'ClickHouse'
+  paths:
+    - regexp: 'docs'
+      tag: 'ClickHouse Documentation'
+
+- regexp: 'github\.com'
+  tag: 'GitHub'
+  paths:
+    - regexp: 'docs'
+      tag: 'GitHub Documentation'
+
+- regexp: '/docs(/|$)'
+  tag: 'Documentation'
+EOL
+
+$CLICKHOUSE_CLIENT -n --query="
+drop dictionary if exists regexp_dict3;
+create dictionary regexp_dict3
+(
+    regexp String,
+    tag String
+)
+PRIMARY KEY(regexp)
+SOURCE(YAMLRegExpTree(PATH '$yaml'))
+LIFETIME(0)
+LAYOUT(regexp_tree)
+SETTINGS(regexp_dict_allow_hyperscan = true);
+
+select dictGet('regexp_dict3', 'tag', 'clickhouse.com');
+select dictGetAll('regexp_dict3', 'tag', 'clickhouse.com');
+select dictGet('regexp_dict3', 'tag', 'clickhouse.com/docs');
+select dictGetAll('regexp_dict3', 'tag', 'clickhouse.com/docs');
+select dictGet('regexp_dict3', 'tag', 'docs.github.com');
+select dictGetAll('regexp_dict3', 'tag', 'docs.github.com');
+select dictGet('regexp_dict3', 'tag', '/docs');
+select dictGetAll('regexp_dict3', 'tag', '/docs');
+
+drop dictionary if exists regexp_dict3;
+create dictionary regexp_dict3
+(
+    regexp String,
+    tag String
+)
+PRIMARY KEY(regexp)
+SOURCE(YAMLRegExpTree(PATH '$yaml'))
+LIFETIME(0)
+LAYOUT(regexp_tree)
+SETTINGS(regexp_dict_allow_hyperscan = false);
+
+select dictGet('regexp_dict3', 'tag', 'clickhouse.com');
+select dictGetAll('regexp_dict3', 'tag', 'clickhouse.com');
+select dictGet('regexp_dict3', 'tag', 'clickhouse.com/docs');
+select dictGetAll('regexp_dict3', 'tag', 'clickhouse.com/docs');
+select dictGet('regexp_dict3', 'tag', 'docs.github.com');
+select dictGetAll('regexp_dict3', 'tag', 'docs.github.com');
+select dictGet('regexp_dict3', 'tag', '/docs');
+select dictGetAll('regexp_dict3', 'tag', '/docs');
+"
+
 $CLICKHOUSE_CLIENT -n --query="
 drop dictionary regexp_dict1;
 drop dictionary regexp_dict2;