Skip to content

Fixed Character Class and Ranges WildCardQuery Optimizations #126154

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Apr 3, 2025
Merged

Fixed Character Class and Ranges WildCardQuery Optimizations #126154

Changes from 4 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5b78223
fixed character class and ranges lacking optimizations after improvem…
john-wagster Apr 2, 2025
bdbb404
iter
john-wagster Apr 2, 2025
1903f44
spotless
john-wagster Apr 2, 2025
c8e4834
iter
john-wagster Apr 2, 2025
a958631
iter
john-wagster Apr 3, 2025
e622ec1
iter
john-wagster Apr 3, 2025
2ff7aa9
Merge branch 'lucene_snapshot' into wildcarfieldmapper_optimizations
john-wagster Apr 3, 2025
1567fd5
iter
john-wagster Apr 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 34 additions & 4 deletions ...n/wildcard/src/main/java/org/elasticsearch/xpack/wildcard/mapper/WildcardFieldMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -407,6 +407,10 @@ public Query regexpQuery(
public static Query toApproximationQuery(RegExp r) throws IllegalArgumentException {
Query result = null;
switch (r.kind) {
case REGEXP_CHAR_RANGE:
case REGEXP_CHAR_CLASS:
result = createCharacterClassQuery(r);
break;
case REGEXP_UNION:
result = createUnionQuery(r);
break;
Expand All @@ -426,7 +430,6 @@ public static Query toApproximationQuery(RegExp r) throws IllegalArgumentExcepti
// Repeat is zero or more times so zero matches = match all
result = new MatchAllDocsQuery();
break;

case REGEXP_REPEAT_MIN:
case REGEXP_REPEAT_MINMAX:
if (r.min > 0) {
Expand All @@ -453,8 +456,6 @@ public static Query toApproximationQuery(RegExp r) throws IllegalArgumentExcepti
case REGEXP_OPTIONAL:
case REGEXP_INTERSECTION:
case REGEXP_COMPLEMENT:
case REGEXP_CHAR_RANGE:
case REGEXP_CHAR_CLASS:
case REGEXP_ANYCHAR:
case REGEXP_INTERVAL:
case REGEXP_EMPTY:
Expand Down Expand Up @@ -497,11 +498,40 @@ private static Query createConcatenationQuery(RegExp r) {

}

private static Query createCharacterClassQuery(RegExp r) {
List<Query> queries = new ArrayList<>();
for (int i = 0; i < r.from.length; i++) {
if (r.from[i] == r.to[i]) {
String cs = Character.toString(r.from[i]);
String normalizedChar = toLowerCase(cs);
queries.add(new TermQuery(new Term("", normalizedChar)));
} else {
for (int j = r.from[i]; j <= r.to[i]; j++) {
String cs = Character.toString(j);
String normalizedChar = toLowerCase(cs);
queries.add(new TermQuery(new Term("", normalizedChar)));
if (queries.size() > MAX_CLAUSES_IN_APPROXIMATION_QUERY) {
break;
}
}
queries.add(new MatchAllDocsQuery());
}
if (queries.size() > MAX_CLAUSES_IN_APPROXIMATION_QUERY) {
break;
}
}
return formQuery(queries);
}

private static Query createUnionQuery(RegExp r) {
// Create an OR of clauses
ArrayList<Query> queries = new ArrayList<>();
List<Query> queries = new ArrayList<>();
findLeaves(r.exp1, org.apache.lucene.util.automaton.RegExp.Kind.REGEXP_UNION, queries);
findLeaves(r.exp2, org.apache.lucene.util.automaton.RegExp.Kind.REGEXP_UNION, queries);
return formQuery(queries);
}

private static Query formQuery(List<Query> queries) {
BooleanQuery.Builder bOr = new BooleanQuery.Builder();
HashSet<Query> uniqueClauses = new HashSet<>();
for (Query query : queries) {
Expand Down