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

feat(import): parse generation column in PersonRegisterImporter (#689)

Browse Source 
Reads the optional `generation` cell by header name (REQUIRED_HEADERS is
not extended — REQ-IMP-001 backward-compat for older artifacts), parses
it through GENERATION_PATTERN (^\s*G?\s*(-?\d+)), and routes it into
PersonUpsertCommand.generation.

Out-of-range values (G 99, G -1) are skip-and-warned, never abort the
batch; the post-parse range guard mirrors the V70 CHECK constraint so
the DB never sees a value Bean Validation wouldn't accept.

Pinned with a parametrised CsvSource covering every shape from the
acceptance criteria plus a backward-compat test (artifact without a
generation column still imports, all upserts get generation=null).

Refs #689

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-05-28 15:30:31 +02:00
parent dcb5585c64
commit df0037cba2
2 changed files with 109 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
backend/src/main/java/org/raddatz/familienarchiv/importing/PersonRegisterImporter.java
View File

@@ -11,6 +11,8 @@ import java.io.File;
import java.time.LocalDate;
import java.time.format.DateTimeParseException;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* Loads {@code canonical-persons.xlsx} (the register) into the person domain via
@@ -25,6 +27,15 @@ public class PersonRegisterImporter {
static final List<String> REQUIRED_HEADERS = List.of("person_id", "last_name", "first_name", "provisional");
// Matches a leading optional G then a signed integer. Anchored at the
// start so noise can't slip in before the number, but tolerant of trailing
// commentary cells (e.g. "G 2 de Gruyter") since curated rows sometimes
// carry an inline note. Out-of-range values are caught by the post-parse
// range guard, not by the regex.
private static final Pattern GENERATION_PATTERN = Pattern.compile("^\\s*G?\\s*(-?\\d+)");
private static final int GENERATION_MIN = 0;
private static final int GENERATION_MAX = 10;
private final PersonService personService;
public int load(File artifact) {
@@ -49,11 +60,31 @@ public class PersonRegisterImporter {
.notes(blankToNull(row.get("notes")))
.birthYear(yearOf(row.get("birth_date")))
.deathYear(yearOf(row.get("death_date")))
.generation(parseGeneration(row.get("generation"), personId))
.personType(PersonType.PERSON)
.provisional(Boolean.parseBoolean(row.get("provisional")))
.build();
}
/**
* Parses an optional {@code G n} generation cell. Returns null for blanks,
* non-matching strings, and any value outside {@value #GENERATION_MIN}..{@value #GENERATION_MAX}
* (mirroring the V70 CHECK). Out-of-range values log a WARN but never abort
* the batch — REQ-IMP-001.
*/
static Integer parseGeneration(String raw, String personId) {
if (raw == null || raw.isBlank()) return null;
Matcher m = GENERATION_PATTERN.matcher(raw);
if (!m.find()) return null;
int parsed = Integer.parseInt(m.group(1));
if (parsed < GENERATION_MIN || parsed > GENERATION_MAX) {
log.warn("Skipping out-of-range generation '{}' for row {}", raw, personId);
return null;
}
log.debug("Parsed generation '{}' for person {}", raw, personId);
return parsed;
}
private static Integer yearOf(String isoDate) {
if (isoDate == null || isoDate.isBlank()) return null;
try {