New funders/funder_grants schema + ingest990pf monthly workflow: IRS BMF state file discovers NH private foundations (747), e-file index CSVs select their latest 990-PF filings, batch ZIPs stream through fflate (4/run cap, most-hits-first, deferred logged), grants-paid rows land in funder_grants, and funders with >=2 NH grants synthesize rolling grant rows (source irs_990pf, funder_ein linked) that flow through the existing embed+match pipeline. Scoring v2: funderPrecedentSubscore tiers repeated in-state giving (1/3/5/10 -> 8/15/20/25); easy win = >=65 total AND >=12 precedent (plan's precedent floor); scale is the full 0-100. Rolling deadlines pass the runway gate. Retrieval computes per-funder in-state counts and exposes funder_ein. Lead-quality gates from the first precedent run's failures: candidate orgs exclude NTEE T* grantmakers; self-matches gated by EIN + normalized name (NHDOJ registers foundations as charities, several without resolved EINs — the first run's top 'leads' were foundations matched to themselves). Live: ~6.5GB of IRS batches processed, 2,766 grants-paid rows, 123 synthesized foundation grants, 89 easy wins across 27 orgs, credible top-10 (AIDS Response-Seacoast -> Foundation for Seacoast Health, 25/25 precedent). 153 tests green. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
142 lines
3.5 KiB
TypeScript
142 lines
3.5 KiB
TypeScript
import { describe, expect, it } from 'vitest';
|
|
|
|
import { selectFilings } from './index-csv.js';
|
|
|
|
const HEADER =
|
|
'RETURN_ID,FILING_TYPE,EIN,TAX_PERIOD,SUB_DATE,TAXPAYER_NAME,RETURN_TYPE,DLN,OBJECT_ID,XML_BATCH_ID';
|
|
|
|
function row(fields: {
|
|
returnId?: string;
|
|
filingType?: string;
|
|
ein: string;
|
|
taxPeriod: string;
|
|
subDate?: string;
|
|
taxpayerName?: string;
|
|
returnType: string;
|
|
dln?: string;
|
|
objectId: string;
|
|
batchId: string;
|
|
}): string {
|
|
return [
|
|
fields.returnId ?? '1',
|
|
fields.filingType ?? 'EFILE',
|
|
fields.ein,
|
|
fields.taxPeriod,
|
|
fields.subDate ?? '20270301',
|
|
fields.taxpayerName ?? 'SOME FOUNDATION',
|
|
fields.returnType,
|
|
fields.dln ?? '93000000000000',
|
|
fields.objectId,
|
|
fields.batchId,
|
|
].join(',');
|
|
}
|
|
|
|
describe('selectFilings', () => {
|
|
it('keeps only RETURN_TYPE === "990PF" rows', () => {
|
|
const csv = [
|
|
HEADER,
|
|
row({
|
|
ein: '020123456',
|
|
taxPeriod: '202612',
|
|
returnType: '990PF',
|
|
objectId: '111',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
row({
|
|
ein: '020654321',
|
|
taxPeriod: '202612',
|
|
returnType: '990',
|
|
objectId: '222',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
].join('\n');
|
|
|
|
const targetEins = new Set(['020123456', '020654321']);
|
|
const filings = selectFilings(csv, targetEins);
|
|
expect(filings).toHaveLength(1);
|
|
expect(filings[0]?.ein).toBe('020123456');
|
|
});
|
|
|
|
it('filters to the target EIN set', () => {
|
|
const csv = [
|
|
HEADER,
|
|
row({
|
|
ein: '020999999',
|
|
taxPeriod: '202612',
|
|
returnType: '990PF',
|
|
objectId: '333',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
].join('\n');
|
|
|
|
expect(selectFilings(csv, new Set(['020123456']))).toEqual([]);
|
|
});
|
|
|
|
it('zero-pads a short EIN before matching against the target set', () => {
|
|
const csv = [
|
|
HEADER,
|
|
row({
|
|
ein: '20123456', // 8 digits
|
|
taxPeriod: '202612',
|
|
returnType: '990PF',
|
|
objectId: '444',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
].join('\n');
|
|
|
|
const filings = selectFilings(csv, new Set(['020123456']));
|
|
expect(filings).toHaveLength(1);
|
|
expect(filings[0]?.ein).toBe('020123456');
|
|
});
|
|
|
|
it('keeps only the LATEST TAX_PERIOD per EIN within the file', () => {
|
|
const csv = [
|
|
HEADER,
|
|
row({
|
|
ein: '020123456',
|
|
taxPeriod: '202512',
|
|
returnType: '990PF',
|
|
objectId: 'OLD',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
row({
|
|
ein: '020123456',
|
|
taxPeriod: '202612',
|
|
returnType: '990PF',
|
|
objectId: 'NEW',
|
|
batchId: 'BATCH2',
|
|
}),
|
|
].join('\n');
|
|
|
|
const filings = selectFilings(csv, new Set(['020123456']));
|
|
expect(filings).toHaveLength(1);
|
|
expect(filings[0]?.objectId).toBe('NEW');
|
|
expect(filings[0]?.batchId).toBe('BATCH2');
|
|
});
|
|
|
|
it('skips rows with a blank OBJECT_ID or XML_BATCH_ID', () => {
|
|
const csv = [
|
|
HEADER,
|
|
row({
|
|
ein: '020123456',
|
|
taxPeriod: '202612',
|
|
returnType: '990PF',
|
|
objectId: '',
|
|
batchId: 'BATCH1',
|
|
}),
|
|
].join('\n');
|
|
|
|
expect(selectFilings(csv, new Set(['020123456']))).toEqual([]);
|
|
});
|
|
|
|
it('returns an empty array for a header-only file', () => {
|
|
expect(selectFilings(HEADER, new Set(['020123456']))).toEqual([]);
|
|
});
|
|
|
|
it('throws when required columns are missing from the header', () => {
|
|
expect(() => selectFilings('FOO,BAR\n1,2', new Set(['020123456']))).toThrow(
|
|
/missing required column/i,
|
|
);
|
|
});
|
|
});
|