marcel/familienarchiv
1
0
Fork 0
Code Issues 111 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

feat(parser): widen GEB_PATTERN and extract maiden name in stripMaidenName

Browse Source 
Widen pattern from `\s+geb\.\s+\S+` to `,?\s*geb\.?\s+(.+)$` to
handle: optional comma, optional dot, multi-word maiden names.
stripMaidenName() now captures the maiden name instead of discarding
it. Handles all 5 input variants from the ODS data.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-08 12:51:32 +02:00
parent 1aabd9826c
commit c49cb345ca
2 changed files with 72 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
backend/src/main/java/org/raddatz/familienarchiv/service/PersonNameParser.java
View File

@@ -18,7 +18,7 @@ public class PersonNameParser {
static final List<String> KNOWN_LAST_NAMES = List.of(
"de Gruyter", "Dieckmann", "Gruber", "Müller", "Wolff", "Cram");
private static final Pattern GEB_PATTERN = Pattern.compile("\\s+geb\\.\\s+\\S+");
private static final Pattern GEB_PATTERN = Pattern.compile(",?\\s*geb\\.?\\s+(.+)$");
private static final Pattern PAREN_LAST_NAME = Pattern.compile("\\(([^)]+)\\)\\s*$");
private static final Pattern MULTI_SEPARATOR = Pattern.compile("\\s+(?:und|u)\\s+");
private static final Pattern SLASH_SEPARATOR = Pattern.compile("//");
@@ -153,10 +153,15 @@ public class PersonNameParser {
);
}
/** Strips "geb. Xxx" maiden-name annotations. Pass-through until #209. */
/** Strips geb annotations and extracts the maiden name. */
public static MaidenNameResult stripMaidenName(String input) {
String cleaned = GEB_PATTERN.matcher(input).replaceAll("").trim();
return new MaidenNameResult(cleaned, null);
Matcher m = GEB_PATTERN.matcher(input);
if (m.find()) {
String cleaned = input.substring(0, m.start()).trim();
String maidenName = m.group(1).trim();
return new MaidenNameResult(cleaned, maidenName);
}
return new MaidenNameResult(input, null);
}
/** Normalizes dot-compressed names: "Dr.Fr.Zarncke" → "Dr. Fr. Zarncke" */