feat(filename): support compound last names like de Gruyter
Some checks failed
CI / Unit & Component Tests (push) Has been cancelled
CI / Backend Unit Tests (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
CI / Unit & Component Tests (pull_request) Successful in 2m17s
CI / Backend Unit Tests (pull_request) Successful in 2m13s
CI / E2E Tests (pull_request) Failing after 25m0s
Some checks failed
CI / Unit & Component Tests (push) Has been cancelled
CI / Backend Unit Tests (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
CI / Unit & Component Tests (pull_request) Successful in 2m17s
CI / Backend Unit Tests (pull_request) Successful in 2m13s
CI / E2E Tests (pull_request) Failing after 25m0s
Replace the four fixed regexes with a split-based algorithm: - first segment = date → last segment = firstName, rest = lastName parts - last segment = date → second-to-last = firstName, rest = lastName parts 18881025_de_Gruyter_Walter.pdf now correctly yields "Walter de Gruyter". Simple two-segment names behave identically to before. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -2,8 +2,8 @@ import { describe, it, expect } from 'vitest';
|
||||
import { parseFilename, stripExtension } from './filename';
|
||||
|
||||
describe('parseFilename', () => {
|
||||
describe('YYYY-MM-DD_Lastname_Firstname pattern', () => {
|
||||
it('extracts date and name', () => {
|
||||
describe('date-first patterns', () => {
|
||||
it('YYYY-MM-DD_Lastname_Firstname', () => {
|
||||
expect(parseFilename('1965-03-12_Mueller_Hans.pdf')).toEqual({
|
||||
dateIso: '1965-03-12',
|
||||
personName: 'Hans Mueller',
|
||||
@@ -11,40 +11,52 @@ describe('parseFilename', () => {
|
||||
});
|
||||
});
|
||||
|
||||
it('YYYYMMDD_Lastname_Firstname', () => {
|
||||
expect(parseFilename('19650312_Mueller_Hans.pdf')).toEqual({
|
||||
dateIso: '1965-03-12',
|
||||
personName: 'Hans Mueller',
|
||||
suggestedTitle: 'Hans Mueller (12.03.1965)'
|
||||
});
|
||||
});
|
||||
|
||||
it('YYYYMMDD_compound_lastname_Firstname', () => {
|
||||
expect(parseFilename('18881025_de_Gruyter_Walter.pdf')).toEqual({
|
||||
dateIso: '1888-10-25',
|
||||
personName: 'Walter de Gruyter',
|
||||
suggestedTitle: 'Walter de Gruyter (25.10.1888)'
|
||||
});
|
||||
});
|
||||
|
||||
it('handles umlauts in names', () => {
|
||||
const result = parseFilename('2024-01-15_Müller_Jürgen.pdf');
|
||||
expect(result.personName).toBe('Jürgen Müller');
|
||||
});
|
||||
});
|
||||
|
||||
describe('YYYYMMDD_Lastname_Firstname pattern', () => {
|
||||
it('extracts date and name', () => {
|
||||
expect(parseFilename('19650312_Mueller_Hans.pdf')).toEqual({
|
||||
dateIso: '1965-03-12',
|
||||
personName: 'Hans Mueller',
|
||||
suggestedTitle: 'Hans Mueller (12.03.1965)'
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('Lastname_Firstname_YYYY-MM-DD pattern', () => {
|
||||
it('extracts date and name', () => {
|
||||
describe('date-last patterns', () => {
|
||||
it('Lastname_Firstname_YYYY-MM-DD', () => {
|
||||
expect(parseFilename('Mueller_Hans_1965-03-12.pdf')).toEqual({
|
||||
dateIso: '1965-03-12',
|
||||
personName: 'Hans Mueller',
|
||||
suggestedTitle: 'Hans Mueller (12.03.1965)'
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('Lastname_Firstname_YYYYMMDD pattern', () => {
|
||||
it('extracts date and name', () => {
|
||||
it('Lastname_Firstname_YYYYMMDD', () => {
|
||||
expect(parseFilename('Mueller_Hans_19650312.pdf')).toEqual({
|
||||
dateIso: '1965-03-12',
|
||||
personName: 'Hans Mueller',
|
||||
suggestedTitle: 'Hans Mueller (12.03.1965)'
|
||||
});
|
||||
});
|
||||
|
||||
it('compound_lastname_Firstname_YYYYMMDD', () => {
|
||||
expect(parseFilename('de_Gruyter_Walter_18881025.pdf')).toEqual({
|
||||
dateIso: '1888-10-25',
|
||||
personName: 'Walter de Gruyter',
|
||||
suggestedTitle: 'Walter de Gruyter (25.10.1888)'
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('non-matching filenames', () => {
|
||||
@@ -52,7 +64,7 @@ describe('parseFilename', () => {
|
||||
expect(parseFilename('1965-03-12.pdf')).toEqual({});
|
||||
});
|
||||
|
||||
it('returns empty for name-only filename', () => {
|
||||
it('returns empty for two segments with no date', () => {
|
||||
expect(parseFilename('Mueller_Hans.pdf')).toEqual({});
|
||||
});
|
||||
|
||||
@@ -60,13 +72,17 @@ describe('parseFilename', () => {
|
||||
expect(parseFilename('scan_001.pdf')).toEqual({});
|
||||
});
|
||||
|
||||
it('returns empty for three name segments without date', () => {
|
||||
it('returns empty for three name segments with no date', () => {
|
||||
expect(parseFilename('Mueller_Hans_Juergen.pdf')).toEqual({});
|
||||
});
|
||||
|
||||
it('returns empty for filename without extension', () => {
|
||||
expect(parseFilename('1965-03-12_Mueller_Hans')).toEqual({});
|
||||
});
|
||||
|
||||
it('rejects implausible date (month 13)', () => {
|
||||
expect(parseFilename('19651345_Mueller_Hans.pdf')).toEqual({});
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
Reference in New Issue
Block a user