feat(forms): ingest Section 16 (3/4/5) and Form 144 ownership filings

src/cli/groups/version.test.ts

@@ -44,13 +44,13 @@ describe("sec version CLI", () => {
       const status = await runCli(["version", "status", "--format", "json"], dir);
       expect(status.exitCode).toBe(0);
       const parsed = JSON.parse(status.stdout);
-      // PR2 wires bootstrapExtractorVersions() into db setup; expect the
-      // five extractor ids registered at 1.0.0 in the current slot.
+      // PR2 wires bootstrapExtractorVersions() into db setup; expect every
+      // extractor id registered at 1.0.0 in the current slot.
       const ids = parsed
         .filter((r: { component_kind: string }) => r.component_kind === "extractor")
         .map((r: { component_id: string }) => r.component_id)
         .sort();
-      expect(ids).toEqual(["1-A", "1-K", "1-Z", "C", "D"]);
+      expect(ids).toEqual(["1-A", "1-K", "1-Z", "144", "3", "4", "5", "C", "D"]);
       const extractorRows = parsed.filter(
         (r: { component_kind: string }) => r.component_kind === "extractor"
       );

src/cli/queries/DbStatus.ts

@@ -9,6 +9,16 @@ import { INVESTMENT_OFFERING_REPOSITORY_TOKEN } from "../../storage/investment-o
 import { PHONE_REPOSITORY_TOKEN } from "../../storage/phone/PhoneSchema";
 import { CROWDFUNDING_REPOSITORY_TOKEN } from "../../storage/portal/CrowdfundingSchema";
 import { PORTAL_REPOSITORY_TOKEN } from "../../storage/portal/PortalSchema";
+import {
+  SECTION16_FILING_REPOSITORY_TOKEN,
+  SECTION16_HOLDING_REPOSITORY_TOKEN,
+  SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+} from "../../storage/section16/Section16Schema";
+import {
+  FORM144_ACQUISITION_REPOSITORY_TOKEN,
+  FORM144_FILING_REPOSITORY_TOKEN,
+  FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+} from "../../storage/form144/Form144Schema";
 import { PROCESSED_FACTS_REPOSITORY_TOKEN } from "../../storage/processing/ProcessedFactsSchema";
 import { PROCESSED_SUBMISSIONS_REPOSITORY_TOKEN } from "../../storage/processing/ProcessedSubmissionsSchema";
 import { EXTRACTOR_RUN_REPOSITORY_TOKEN } from "../../storage/versioning/ExtractorRunSchema";
@@ -90,6 +100,12 @@ const TABLE_TOKENS: ReadonlyArray<{
   { table: "canonical_company", token: CANONICAL_COMPANY_REPOSITORY_TOKEN as any },
   { table: "person_identity_link", token: PERSON_IDENTITY_LINK_REPOSITORY_TOKEN as any },
   { table: "company_identity_link", token: COMPANY_IDENTITY_LINK_REPOSITORY_TOKEN as any },
+  { table: "section16_filings", token: SECTION16_FILING_REPOSITORY_TOKEN as any },
+  { table: "section16_transactions", token: SECTION16_TRANSACTION_REPOSITORY_TOKEN as any },
+  { table: "section16_holdings", token: SECTION16_HOLDING_REPOSITORY_TOKEN as any },
+  { table: "form144_filings", token: FORM144_FILING_REPOSITORY_TOKEN as any },
+  { table: "form144_acquisitions", token: FORM144_ACQUISITION_REPOSITORY_TOKEN as any },
+  { table: "form144_recent_sales", token: FORM144_RECENT_SALE_REPOSITORY_TOKEN as any },
 ];
 
 export async function getDbStats(): Promise<TableStat[]> {

src/config/DefaultDI.ts

@@ -104,6 +104,28 @@ import {
   PortalPrimaryKeyNames,
   PortalSchema,
 } from "../storage/portal/PortalSchema";
+import {
+  SECTION16_FILING_REPOSITORY_TOKEN,
+  SECTION16_HOLDING_REPOSITORY_TOKEN,
+  SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+  Section16FilingPrimaryKeyNames,
+  Section16FilingSchema,
+  Section16HoldingPrimaryKeyNames,
+  Section16HoldingSchema,
+  Section16TransactionPrimaryKeyNames,
+  Section16TransactionSchema,
+} from "../storage/section16/Section16Schema";
+import {
+  FORM144_ACQUISITION_REPOSITORY_TOKEN,
+  FORM144_FILING_REPOSITORY_TOKEN,
+  FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+  Form144AcquisitionPrimaryKeyNames,
+  Form144AcquisitionSchema,
+  Form144FilingPrimaryKeyNames,
+  Form144FilingSchema,
+  Form144RecentSalePrimaryKeyNames,
+  Form144RecentSaleSchema,
+} from "../storage/form144/Form144Schema";
 import {
   CIK_LAST_UPDATE_REPOSITORY_TOKEN,
   CikLastUpdatePrimaryKeyNames,
@@ -357,6 +379,56 @@ export const DefaultDI = () => {
     )
   );
 
+  // ------------------------------ Section 16 (Forms 3/4/5) --------------------------------
+  globalServiceRegistry.registerInstance(
+    SECTION16_FILING_REPOSITORY_TOKEN,
+    createStorage("section16_filings", Section16FilingSchema, Section16FilingPrimaryKeyNames, [
+      ["issuer_cik"],
+      ["form"],
+    ])
+  );
+  globalServiceRegistry.registerInstance(
+    SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+    createStorage(
+      "section16_transactions",
+      Section16TransactionSchema,
+      Section16TransactionPrimaryKeyNames,
+      [["accession_number"], ["issuer_cik"]]
+    )
+  );
+  globalServiceRegistry.registerInstance(
+    SECTION16_HOLDING_REPOSITORY_TOKEN,
+    createStorage("section16_holdings", Section16HoldingSchema, Section16HoldingPrimaryKeyNames, [
+      ["accession_number"],
+      ["issuer_cik"],
+    ])
+  );
+
+  // ------------------------------ Form 144 --------------------------------
+  globalServiceRegistry.registerInstance(
+    FORM144_FILING_REPOSITORY_TOKEN,
+    createStorage("form144_filings", Form144FilingSchema, Form144FilingPrimaryKeyNames, [
+      ["issuer_cik"],
+      ["form"],
+    ])
+  );
+  globalServiceRegistry.registerInstance(
+    FORM144_ACQUISITION_REPOSITORY_TOKEN,
+    createStorage(
+      "form144_acquisitions",
+      Form144AcquisitionSchema,
+      Form144AcquisitionPrimaryKeyNames,
+      [["accession_number"], ["issuer_cik"]]
+    )
+  );
+  globalServiceRegistry.registerInstance(
+    FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+    createStorage("form144_recent_sales", Form144RecentSaleSchema, Form144RecentSalePrimaryKeyNames, [
+      ["accession_number"],
+      ["issuer_cik"],
+    ])
+  );
+
   // ------------------------------ Change Log --------------------------------
   globalServiceRegistry.registerInstance(
     CHANGE_LOG_REPOSITORY_TOKEN,

src/config/TestingDI.ts

@@ -102,6 +102,28 @@ import {
   PortalPrimaryKeyNames,
   PortalSchema,
 } from "../storage/portal/PortalSchema";
+import {
+  SECTION16_FILING_REPOSITORY_TOKEN,
+  SECTION16_HOLDING_REPOSITORY_TOKEN,
+  SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+  Section16FilingPrimaryKeyNames,
+  Section16FilingSchema,
+  Section16HoldingPrimaryKeyNames,
+  Section16HoldingSchema,
+  Section16TransactionPrimaryKeyNames,
+  Section16TransactionSchema,
+} from "../storage/section16/Section16Schema";
+import {
+  FORM144_ACQUISITION_REPOSITORY_TOKEN,
+  FORM144_FILING_REPOSITORY_TOKEN,
+  FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+  Form144AcquisitionPrimaryKeyNames,
+  Form144AcquisitionSchema,
+  Form144FilingPrimaryKeyNames,
+  Form144FilingSchema,
+  Form144RecentSalePrimaryKeyNames,
+  Form144RecentSaleSchema,
+} from "../storage/form144/Form144Schema";
 import {
   CIK_LAST_UPDATE_REPOSITORY_TOKEN,
   CikLastUpdatePrimaryKeyNames,
@@ -364,6 +386,53 @@ export function resetDependencyInjectionsForTesting() {
     ])
   );
 
+  // Initialize Section 16 (Forms 3/4/5) repositories
+  globalServiceRegistry.registerInstance(
+    SECTION16_FILING_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(Section16FilingSchema, Section16FilingPrimaryKeyNames, [
+      ["issuer_cik"],
+      ["form"],
+    ])
+  );
+  globalServiceRegistry.registerInstance(
+    SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(
+      Section16TransactionSchema,
+      Section16TransactionPrimaryKeyNames,
+      [["accession_number"], ["issuer_cik"]]
+    )
+  );
+  globalServiceRegistry.registerInstance(
+    SECTION16_HOLDING_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(Section16HoldingSchema, Section16HoldingPrimaryKeyNames, [
+      ["accession_number"],
+      ["issuer_cik"],
+    ])
+  );
+
+  // Initialize Form 144 repositories
+  globalServiceRegistry.registerInstance(
+    FORM144_FILING_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(Form144FilingSchema, Form144FilingPrimaryKeyNames, [
+      ["issuer_cik"],
+      ["form"],
+    ])
+  );
+  globalServiceRegistry.registerInstance(
+    FORM144_ACQUISITION_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(Form144AcquisitionSchema, Form144AcquisitionPrimaryKeyNames, [
+      ["accession_number"],
+      ["issuer_cik"],
+    ])
+  );
+  globalServiceRegistry.registerInstance(
+    FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+    new InMemoryTabularStorage(Form144RecentSaleSchema, Form144RecentSalePrimaryKeyNames, [
+      ["accession_number"],
+      ["issuer_cik"],
+    ])
+  );
+
   // Initialize Processing Tracking repositories
   globalServiceRegistry.registerInstance(
     CIK_LAST_UPDATE_REPOSITORY_TOKEN,

src/config/setupAllDatabases.ts

@@ -32,6 +32,16 @@ import {
   CROWDFUNDING_REPOSITORY_TOKEN,
 } from "../storage/portal/CrowdfundingSchema";
 import { PORTAL_REPOSITORY_TOKEN } from "../storage/portal/PortalSchema";
+import {
+  SECTION16_FILING_REPOSITORY_TOKEN,
+  SECTION16_HOLDING_REPOSITORY_TOKEN,
+  SECTION16_TRANSACTION_REPOSITORY_TOKEN,
+} from "../storage/section16/Section16Schema";
+import {
+  FORM144_ACQUISITION_REPOSITORY_TOKEN,
+  FORM144_FILING_REPOSITORY_TOKEN,
+  FORM144_RECENT_SALE_REPOSITORY_TOKEN,
+} from "../storage/form144/Form144Schema";
 import { CIK_LAST_UPDATE_REPOSITORY_TOKEN } from "../storage/processing/CikLastUpdateSchema";
 import { PROCESSED_FACTS_REPOSITORY_TOKEN } from "../storage/processing/ProcessedFactsSchema";
 import { PROCESSED_SUBMISSIONS_REPOSITORY_TOKEN } from "../storage/processing/ProcessedSubmissionsSchema";
@@ -95,6 +105,12 @@ export async function setupAllDatabases(): Promise<void> {
   await globalServiceRegistry.get(CROWDFUNDING_OFFERINGS_REPOSITORY_TOKEN).setupDatabase();
   await globalServiceRegistry.get(CROWDFUNDING_REPORTS_REPOSITORY_TOKEN).setupDatabase();
   await globalServiceRegistry.get(CROWDFUNDING_HISTORY_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(SECTION16_FILING_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(SECTION16_TRANSACTION_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(SECTION16_HOLDING_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(FORM144_FILING_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(FORM144_ACQUISITION_REPOSITORY_TOKEN).setupDatabase();
+  await globalServiceRegistry.get(FORM144_RECENT_SALE_REPOSITORY_TOKEN).setupDatabase();
   await globalServiceRegistry.get(CHANGE_LOG_REPOSITORY_TOKEN).setupDatabase();
   await globalServiceRegistry.get(PORTAL_REPOSITORY_TOKEN).setupDatabase();
   await globalServiceRegistry.get(REGA_OFFERING_REPOSITORY_TOKEN).setupDatabase();

src/sec/forms/insider-trading/Form_144.schema.ts

@@ -0,0 +1,129 @@
+/**
+ * @license
+ * Copyright 2025 Steven Roussey <sroussey@gmail.com>
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+// Schema for the EDGAR Form 144 (and 144/A) "Notice of Proposed Sale of
+// Securities" XML. Since 2022 these are filed electronically under the
+// shared edgar/ownership namespace, with a `com:` common namespace for
+// address parts. The parser runs with removeNSPrefix, so `com:street1`
+// arrives as `street1`.
+//
+// Unlike the ownership forms (3/4/5), Form 144 leaves are plain text rather
+// than `{ value }` wrappers, and dates are US-format strings (MM/DD/YYYY),
+// stored verbatim rather than coerced to ISO.
+
+import { Static, Type } from "typebox";
+
+const ADDRESS_TYPE = Type.Object({
+  street1: Type.Optional(Type.String()),
+  street2: Type.Optional(Type.String()),
+  city: Type.Optional(Type.String()),
+  stateOrCountry: Type.Optional(Type.String()),
+  zipCode: Type.Optional(Type.String()),
+});
+
+const FILER_CREDENTIALS_TYPE = Type.Object({
+  cik: Type.Optional(Type.String()),
+  ccc: Type.Optional(Type.String()),
+});
+
+const FILER_INFO_TYPE = Type.Object({
+  filer: Type.Optional(
+    Type.Object({
+      filerCredentials: Type.Optional(FILER_CREDENTIALS_TYPE),
+    })
+  ),
+  liveTestFlag: Type.Optional(Type.String()),
+});
+
+const HEADER_DATA_TYPE = Type.Object({
+  submissionType: Type.Optional(Type.String()),
+  filerInfo: Type.Optional(FILER_INFO_TYPE),
+});
+
+const RELATIONSHIPS_TO_ISSUER_TYPE = Type.Object({
+  relationshipToIssuer: Type.Optional(Type.Array(Type.String())),
+});
+
+const ISSUER_INFO_TYPE = Type.Object({
+  issuerCik: Type.Optional(Type.String()),
+  issuerName: Type.Optional(Type.String()),
+  secFileNumber: Type.Optional(Type.String()),
+  issuerAddress: Type.Optional(ADDRESS_TYPE),
+  issuerContactPhone: Type.Optional(Type.String()),
+  nameOfPersonForWhoseAccountTheSecuritiesAreToBeSold: Type.Optional(Type.String()),
+  relationshipsToIssuer: Type.Optional(RELATIONSHIPS_TO_ISSUER_TYPE),
+});
+
+const BROKER_DETAILS_TYPE = Type.Object({
+  name: Type.Optional(Type.String()),
+  address: Type.Optional(ADDRESS_TYPE),
+});
+
+const SECURITIES_INFORMATION_TYPE = Type.Object({
+  securitiesClassTitle: Type.Optional(Type.String()),
+  brokerOrMarketmakerDetails: Type.Optional(BROKER_DETAILS_TYPE),
+  // Numeric leaves are kept as raw strings and coerced in storage. Typing them
+  // as Type.Number() would let Value.Convert turn an empty element ("") into a
+  // fabricated 0, indistinguishable from a real zero.
+  noOfUnitsSold: Type.Optional(Type.String()),
+  aggregateMarketValue: Type.Optional(Type.String()),
+  noOfUnitsOutstanding: Type.Optional(Type.String()),
+  approxSaleDate: Type.Optional(Type.String()),
+  securitiesExchangeName: Type.Optional(Type.String()),
+});
+
+const SECURITIES_TO_BE_SOLD_TYPE = Type.Object({
+  securitiesClassTitle: Type.Optional(Type.String()),
+  acquiredDate: Type.Optional(Type.String()),
+  natureOfAcquisitionTransaction: Type.Optional(Type.String()),
+  nameOfPersonfromWhomAcquired: Type.Optional(Type.String()),
+  isGiftTransaction: Type.Optional(Type.String()),
+  amountOfSecuritiesAcquired: Type.Optional(Type.String()),
+  paymentDate: Type.Optional(Type.String()),
+  natureOfPayment: Type.Optional(Type.String()),
+});
+
+const SELLER_DETAILS_TYPE = Type.Object({
+  name: Type.Optional(Type.String()),
+  address: Type.Optional(ADDRESS_TYPE),
+});
+
+const SECURITIES_SOLD_PAST_3_MONTHS_TYPE = Type.Object({
+  sellerDetails: Type.Optional(SELLER_DETAILS_TYPE),
+  securitiesClassTitle: Type.Optional(Type.String()),
+  saleDate: Type.Optional(Type.String()),
+  amountOfSecuritiesSold: Type.Optional(Type.String()),
+  grossProceeds: Type.Optional(Type.String()),
+});
+
+const NOTICE_SIGNATURE_TYPE = Type.Object({
+  noticeDate: Type.Optional(Type.String()),
+  signature: Type.Optional(Type.String()),
+});
+
+const FORM_DATA_TYPE = Type.Object({
+  issuerInfo: Type.Optional(ISSUER_INFO_TYPE),
+  securitiesInformation: Type.Optional(SECURITIES_INFORMATION_TYPE),
+  securitiesToBeSold: Type.Optional(Type.Array(SECURITIES_TO_BE_SOLD_TYPE)),
+  nothingToReportFlagOnSecuritiesSoldInPast3Months: Type.Optional(Type.String()),
+  securitiesSoldInPast3Months: Type.Optional(Type.Array(SECURITIES_SOLD_PAST_3_MONTHS_TYPE)),
+  noticeSignature: Type.Optional(NOTICE_SIGNATURE_TYPE),
+});
+
+export const Form144Schema = Type.Object({
+  headerData: Type.Optional(HEADER_DATA_TYPE),
+  formData: Type.Optional(FORM_DATA_TYPE),
+});
+
+export type Form144 = Static<typeof Form144Schema>;
+
+// Wrapper matching the XML root element so the parser's array-path detection
+// produces `edgarSubmission.*` jpaths.
+export const Form144SubmissionSchema = Type.Object({
+  edgarSubmission: Form144Schema,
+});
+
+export type Form144Submission = Static<typeof Form144SubmissionSchema>;