Skip to content

Feature/composite property fields #1795

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

Open
kwahlin wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

Feature/composite property fields #1795

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
823dbd9
Index all search-relevant hasTitle fields as nested
kwahlin Jun 3, 2026
162e828
Add hard-coded workaround to suppress excessive alternative paths gen…
kwahlin Jun 3, 2026
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
64 changes: 46 additions & 18 deletions librisxl-tools/elasticsearch/libris_config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,24 +191,6 @@
}
}
},
"hasTitle": {
"type": "nested",
"include_in_parent": true,
"properties": {
"@type": {"type": "keyword"},
"__mainTitle": {
"type": "text",
"analyzer": "softmatcher",
"copy_to": "_all",
"fields": {
"keyword": {
"type": "icu_collation_keyword",
"language": "sv"
}
}
}
}
},
"reverseLinks": {
"properties": {
"@type": {
Expand Down Expand Up @@ -408,8 +390,10 @@
"contribution",
"instanceOf.contribution",
"@reverse.instanceOf.contribution",

"hasPart.contribution",
"instanceOf.hasPart.contribution",

"relationship.entity.contribution",
"instanceOf.relationship.entity.contribution"
],
Expand All @@ -419,6 +403,50 @@
}
}
},
{
"hasTitle_template": {
"path_match": [
"hasTitle",
"instanceOf.hasTitle",
"@reverse.instanceOf.hasTitle",

"translationOf.hasTitle",
"instanceOf.translationOf.hasTitle",

"hasPart.hasTitle",
"instanceOf.hasPart.hasTitle",
"@reverse.instanceOf.hasPart.hasTitle",

"hasPart.translationOf.hasTitle",
"instanceOf.hasPart.translationOf.hasTitle",

"relationship.entity.hasTitle",
"instanceOf.relationship.entity.hasTitle",
"@reverse.instanceOf.relationship.entity.hasTitle",

"seriesMembership.inSeries.instanceOf.hasTitle",
"@reverse.instanceOf.seriesMembership.inSeries.instanceOf.hasTitle"
],
"mapping": {
"type": "nested",
"include_in_parent": true,
"properties": {
"@type": {"type": "keyword"},
"__mainTitle": {
"type": "text",
"analyzer": "softmatcher",
"copy_to": "_all",
"fields": {
"keyword": {
"type": "icu_collation_keyword",
"language": "sv"
}
}
}
}
}
}
},
{
"identifiedBy_template": {
"path_match": ["identifiedBy", "@reverse.instanceOf.identifiedBy"],
Expand Down
34 changes: 16 additions & 18 deletions whelk-core/src/main/groovy/whelk/search2/querytree/Path.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
import java.util.List;
import java.util.Map;
import java.util.Objects;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;

Expand Down Expand Up @@ -61,7 +62,7 @@ public List<Selector> getAltSelectors(JsonLd jsonLd, Collection<String> rdfSubje
altSelectors.add(new Path(l));
}
});
return excludeInverseIntegralRoundTrips(altSelectors);
return altSelectors;
}

private List<List<PathElement>> getAltPaths(List<? extends PathElement> tail, JsonLd jsonLd, Collection<String> rdfSubjectTypes, boolean allowIncompatible) {
Expand All @@ -71,27 +72,24 @@ private List<List<PathElement>> getAltPaths(List<? extends PathElement> tail, Js
var next = tail.getFirst();
var newTail = tail.subList(1, tail.size());
var nextAltSelectors = next.getAltSelectors(jsonLd, rdfSubjectTypes, allowIncompatible);

var shouldRecurse = (!newTail.isEmpty() && newTail.getFirst().isComposite())
|| (next instanceof Property p && "hasItem".equals(p.name()));

if (shouldRecurse) {
return nextAltSelectors.stream()
.flatMap(s -> getAltPaths(newTail, jsonLd, next.range(), allowIncompatible).stream()
.map(altPath -> concat(s.path(), altPath)))
.toList();
}

return nextAltSelectors.stream()
.flatMap(s -> getAltPaths(newTail, jsonLd, next.range(), allowIncompatible).stream()
.map(altPath -> Stream.concat(s.path().stream(), altPath.stream())))
.map(Stream::toList)
.map(s -> concat(s.path(), newTail))
.toList();
}

private List<Selector> excludeInverseIntegralRoundTrips(List<Selector> altSelectors) {
List<Selector> res = new ArrayList<>();
for (Selector s : altSelectors) {
List<Property.IntegralProperty> integralsInPath = s.path().stream()
.filter(Property.IntegralProperty.class::isInstance)
.map(Property.IntegralProperty.class::cast)
.toList();
boolean hasInversePair = integralsInPath.stream()
.anyMatch(integral -> integralsInPath.stream().anyMatch(integral::isInverseOf));
if (!hasInversePair) {
res.add(s);
}
}
return res;
private List<PathElement> concat(List<? extends PathElement> left, List<? extends PathElement> right) {
return Stream.concat(left.stream(), right.stream()).toList();
}

@Override
Expand Down
46 changes: 23 additions & 23 deletions whelk-core/src/test/groovy/whelk/search2/querytree/SelectorSpec.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,28 +30,28 @@ class SelectorSpec extends Specification {
p.getAltSelectors(jsonLd, types, true).collect { it.path().collect { it.toString() }.join(".") } == result

where:
_p | types | result
"p1" | [] | ["p1"]
"p1" | ["T1"] | ["instanceOf.p1", "p1"]
"p1" | ["T2"] | ["hasInstance.p1", "p1"]
"p1" | ["T1", "T2"] | ["hasInstance.p1", "instanceOf.p1", "p1"]
"p1" | ["T3"] | ["p1"]
"p7" | ["T1"] | ["p7"]
"p7" | ["T2"] | ["hasInstance.p7"]
"p7" | ["T1", "T2"] | ["hasInstance.p7", "p7"]
"p7" | ["T3"] | ["p7"]
"p8" | ["T1"] | ["instanceOf.p8"]
"p8" | ["T2"] | ["p8"]
"p8" | ["T1", "T2"] | ["instanceOf.p8", "p8"]
"p8" | ["T3"] | ["p8"]
"p9" | ["T1"] | ["p9"]
"p9" | ["T2"] | ["p9"]
"p9" | ["T1", "T2"] | ["p9"]
"p9" | ["T3"] | ["p9"]
"hasInstance.p7" | ["T2"] | ["hasInstance.p7"]
"type" | ["T2"] | ["rdf:type"]
"instanceOf.p8" | ["T1"] | ["instanceOf.p8"]
"type" | ["T1"] | ["rdf:type"]
"p7.p14" | ["T2"] | ["hasInstance.p7.hasComponent.p14", "hasInstance.p7.p14"]
_p | types | result
"p1" | [] | ["p1"]
"p1" | ["T1"] | ["instanceOf.p1", "p1"]
"p1" | ["T2"] | ["hasInstance.p1", "p1"]
"p1" | ["T1", "T2"] | ["hasInstance.p1", "instanceOf.p1", "p1"]
"p1" | ["T3"] | ["p1"]
"hasItem" | ["T1"] | ["hasItem"]
"hasItem" | ["T2"] | ["hasInstance.hasItem"]
"hasItem" | ["T1", "T2"] | ["hasInstance.hasItem", "hasItem"]
"hasItem" | ["T3"] | ["hasItem"]
"p8" | ["T1"] | ["instanceOf.p8"]
"p8" | ["T2"] | ["p8"]
"p8" | ["T1", "T2"] | ["instanceOf.p8", "p8"]
"p8" | ["T3"] | ["p8"]
"p9" | ["T1"] | ["p9"]
"p9" | ["T2"] | ["p9"]
"p9" | ["T1", "T2"] | ["p9"]
"p9" | ["T3"] | ["p9"]
"hasInstance.hasItem" | ["T2"] | ["hasInstance.hasItem"]
"type" | ["T2"] | ["rdf:type"]
"instanceOf.p8" | ["T1"] | ["instanceOf.p8"]
"type" | ["T1"] | ["rdf:type"]
"hasItem.p14" | ["T2"] | ["hasInstance.hasItem.hasComponent.p14", "hasInstance.hasItem.p14"]
}
}
7 changes: 7 additions & 0 deletions whelk-core/src/test/groovy/whelk/search2/querytree/TestData.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@ class TestData {
'rdf:type' : ['rdf:type'] as Set,
'instanceof' : ['instanceOf'] as Set,
'hasinstance' : ['hasInstance'] as Set,
'hasitem' : ['hasItem'] as Set,
'p' : ['p', 'p1'] as Set,
'plabel' : ['p2', 'p3'] as Set,
'pp' : ['p3', 'p4'] as Set,
Expand Down Expand Up @@ -227,6 +228,12 @@ class TestData {
'domain' : ['@id': 'T4'],
'range' : ['@id': 'T4']
],
[
'@id' : 'hasItem',
'@type' : 'DatatypeProperty',
'domain': [['@id': 'T1']],
'range' : [['@id': 'T4']]
],
[
'@id' : 'librissearch:workCategory',
'category' : ['@id': "https://id.kb.se/ns/librissearch/composite"],
Expand Down
Loading