Import normalizer: offline tool to normalize the raw archive spreadsheets #663

Merged
marcel merged 172 commits from docs/import-migration into main 2026-05-28 15:05:51 +02:00
Showing only changes of commit 151d6aa03f - Show all commits

View File

@@ -3,6 +3,7 @@ package org.raddatz.familienarchiv.importing;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.junit.jupiter.api.AfterEach;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import org.raddatz.familienarchiv.PostgresContainerConfig;
@@ -59,6 +60,22 @@ class CanonicalImportIntegrationTest {
ReflectionTestUtils.setField(orchestrator, "canonicalDir", artifactDir.toString());
}
/**
* The import commits through its own transactions (the orchestrator is not transactional),
* so this test cannot rely on {@code @Transactional} rollback for isolation. Delete the
* committed rows after each test — otherwise the last test's documents (dated 1888-02) and
* persons/tags leak into the shared Testcontainers Postgres and pollute other integration
* tests that assume a known seed (e.g. DocumentDensityIntegrationTest,
* DocumentSearchPagedIntegrationTest). Mirrors the @AfterEach deleteAll convention used by
* DocumentListItemIntegrationTest.
*/
@AfterEach
void cleanup() {
documentRepository.deleteAll();
personRepository.deleteAll();
tagRepository.deleteAll();
}
@Test
void reimport_isIdempotent_noDuplicatePersonsTagsOrDocuments() {
orchestrator.runImport();