marcel/familienarchiv
1
0
Fork 0
Code Issues 119 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

feat(repository): add bulk completion stats query to TranscriptionBlockRepository

Browse Source 
Adds findCompletionStatsForDocuments() returning reviewed-block percentage
per document in a single native SQL GROUP BY query. Needed for the new
DocumentSearchItem DTO in issue #281.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-19 23:00:20 +02:00
parent 70a2bbfaad
commit f197eb9752
3 changed files with 124 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
backend/src/main/java/org/raddatz/familienarchiv/repository/CompletionStatsRow.java Normal file
View File

@@ -0,0 +1,8 @@
package org.raddatz.familienarchiv.repository;
import java.util.UUID;
public interface CompletionStatsRow {
UUID getDocumentId();
int getCompletionPercentage();
}

12
backend/src/main/java/org/raddatz/familienarchiv/repository/TranscriptionBlockRepository.java
View File

@@ -5,12 +5,24 @@ import org.springframework.data.jpa.repository.JpaRepository;
import org.springframework.data.jpa.repository.Query;
import org.springframework.data.repository.query.Param;
import java.util.Collection;
import java.util.List;
import java.util.Optional;
import java.util.UUID;
public interface TranscriptionBlockRepository extends JpaRepository<TranscriptionBlock, UUID> {
@Query(value = """
SELECT
b.document_id AS documentId,
ROUND(COUNT(*) FILTER (WHERE b.reviewed = true) * 100.0 / COUNT(*))::int AS completionPercentage
FROM transcription_blocks b
WHERE b.document_id IN :documentIds
GROUP BY b.document_id
""", nativeQuery = true)
List<CompletionStatsRow> findCompletionStatsForDocuments(
@Param("documentIds") Collection<UUID> documentIds);
List<TranscriptionBlock> findByDocumentIdOrderBySortOrderAsc(UUID documentId);
Optional<TranscriptionBlock> findByIdAndDocumentId(UUID id, UUID documentId);

104
backend/src/test/java/org/raddatz/familienarchiv/repository/TranscriptionBlockRepositoryIntegrationTest.java Normal file
View File

@@ -0,0 +1,104 @@
package org.raddatz.familienarchiv.repository;
import org.junit.jupiter.api.Test;
import org.raddatz.familienarchiv.PostgresContainerConfig;
import org.raddatz.familienarchiv.config.FlywayConfig;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.data.jpa.test.autoconfigure.DataJpaTest;
import org.springframework.boot.jdbc.test.autoconfigure.AutoConfigureTestDatabase;
import org.springframework.context.annotation.Import;
import org.springframework.test.context.jdbc.Sql;
import java.util.List;
import java.util.Map;
import java.util.UUID;
import java.util.stream.Collectors;
import static org.assertj.core.api.Assertions.assertThat;
@DataJpaTest
@AutoConfigureTestDatabase(replace = AutoConfigureTestDatabase.Replace.NONE)
@Import({PostgresContainerConfig.class, FlywayConfig.class})
class TranscriptionBlockRepositoryIntegrationTest {
static final UUID DOC_A = UUID.fromString("aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa");
static final UUID DOC_B = UUID.fromString("bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb");
static final UUID ANN_A = UUID.fromString("cccccccc-cccc-cccc-cccc-cccccccccccc");
static final UUID ANN_B = UUID.fromString("dddddddd-dddd-dddd-dddd-dddddddddddd");
@Autowired TranscriptionBlockRepository repository;
@Test
@Sql(statements = {
"INSERT INTO documents (id, title, original_filename, status) VALUES ('aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 'Doc A', 'a.pdf', 'PLACEHOLDER')",
"INSERT INTO document_annotations (id, document_id, page_number, x, y, width, height, color) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, 0, 0, 1, 1, '#fff')",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 0, true)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, true)"
})
void findCompletionStats_returns_100_when_all_blocks_reviewed() {
List<CompletionStatsRow> rows = repository.findCompletionStatsForDocuments(List.of(DOC_A));
assertThat(rows).hasSize(1);
assertThat(rows.get(0).getDocumentId()).isEqualTo(DOC_A);
assertThat(rows.get(0).getCompletionPercentage()).isEqualTo(100);
}
@Test
@Sql(statements = {
"INSERT INTO documents (id, title, original_filename, status) VALUES ('aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 'Doc A', 'a.pdf', 'PLACEHOLDER')",
"INSERT INTO document_annotations (id, document_id, page_number, x, y, width, height, color) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, 0, 0, 1, 1, '#fff')",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 0, false)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, false)"
})
void findCompletionStats_returns_0_when_no_blocks_reviewed() {
List<CompletionStatsRow> rows = repository.findCompletionStatsForDocuments(List.of(DOC_A));
assertThat(rows).hasSize(1);
assertThat(rows.get(0).getCompletionPercentage()).isEqualTo(0);
}
@Test
@Sql(statements = {
"INSERT INTO documents (id, title, original_filename, status) VALUES ('aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 'Doc A', 'a.pdf', 'PLACEHOLDER')"
})
void findCompletionStats_returns_empty_when_document_has_no_blocks() {
List<CompletionStatsRow> rows = repository.findCompletionStatsForDocuments(List.of(DOC_A));
assertThat(rows).isEmpty();
}
@Test
@Sql(statements = {
"INSERT INTO documents (id, title, original_filename, status) VALUES ('aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 'Doc A', 'a.pdf', 'PLACEHOLDER')",
"INSERT INTO document_annotations (id, document_id, page_number, x, y, width, height, color) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, 0, 0, 1, 1, '#fff')",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 0, true)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, false)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 2, false)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 3, false)"
})
void findCompletionStats_rounds_partial_completion_correctly() {
List<CompletionStatsRow> rows = repository.findCompletionStatsForDocuments(List.of(DOC_A));
assertThat(rows).hasSize(1);
assertThat(rows.get(0).getCompletionPercentage()).isEqualTo(25);
}
@Test
@Sql(statements = {
"INSERT INTO documents (id, title, original_filename, status) VALUES ('aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 'Doc A', 'a.pdf', 'PLACEHOLDER')",
"INSERT INTO documents (id, title, original_filename, status) VALUES ('bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb', 'Doc B', 'b.pdf', 'PLACEHOLDER')",
"INSERT INTO document_annotations (id, document_id, page_number, x, y, width, height, color) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 1, 0, 0, 1, 1, '#fff')",
"INSERT INTO document_annotations (id, document_id, page_number, x, y, width, height, color) VALUES ('dddddddd-dddd-dddd-dddd-dddddddddddd', 'bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb', 1, 0, 0, 1, 1, '#fff')",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('cccccccc-cccc-cccc-cccc-cccccccccccc', 'aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa', 0, true)",
"INSERT INTO transcription_blocks (annotation_id, document_id, sort_order, reviewed) VALUES ('dddddddd-dddd-dddd-dddd-dddddddddddd', 'bbbbbbbb-bbbb-bbbb-bbbb-bbbbbbbbbbbb', 0, false)"
})
void findCompletionStats_handles_multiple_documents_in_one_call() {
List<CompletionStatsRow> rows = repository.findCompletionStatsForDocuments(List.of(DOC_A, DOC_B));
Map<UUID, Integer> byDoc = rows.stream()
.collect(Collectors.toMap(CompletionStatsRow::getDocumentId, CompletionStatsRow::getCompletionPercentage));
assertThat(byDoc).containsEntry(DOC_A, 100);
assertThat(byDoc).containsEntry(DOC_B, 0);
}
}