Auto-Registering Extractor System (#223)

* initial commit? * Address PR feedback on extractor discovery and startup resilience * Address latest PR review comments * fix city resolution fallback when input parses empty * address PR feedback on extractor registry and pipeline validation * address copilot comments on manifests and registry startup * fix extractor discovery export handling and env isolation in tests * enforce duplicate manifest id failures in strict mode * Fix remaining extractor registry and runtime review comments * docs * docs * test all, logic remains in extractors * Address PR review feedback on extractor registry and validation * Revert extractor moduleResolution to bundler * Enforce shared city filtering across all discovery sources * Deduplicate extractor strict city post-filtering
2026-02-21 17:44:07 +00:00
parent cc7cacd7f5
commit 82e142a8a8
52 changed files with 2207 additions and 1515 deletions
@@ -0,0 +1,72 @@
+import { describe, expect, it } from "vitest";
+import { parseUkVisaJobsProgressLine } from "../src/run";
+
+describe("parseUkVisaJobsProgressLine", () => {
+  it("parses init events", () => {
+    const event = parseUkVisaJobsProgressLine(
+      'JOBOPS_PROGRESS {"event":"init","maxPages":4,"maxJobs":50,"searchKeyword":"engineer"}',
+    );
+
+    expect(event).toEqual({
+      type: "init",
+      maxPages: 4,
+      maxJobs: 50,
+      searchKeyword: "engineer",
+    });
+  });
+
+  it("parses page_fetched events", () => {
+    const event = parseUkVisaJobsProgressLine(
+      'JOBOPS_PROGRESS {"event":"page_fetched","pageNo":2,"maxPages":4,"jobsOnPage":15,"totalCollected":28,"totalAvailable":105}',
+    );
+
+    expect(event).toEqual({
+      type: "page_fetched",
+      pageNo: 2,
+      maxPages: 4,
+      jobsOnPage: 15,
+      totalCollected: 28,
+      totalAvailable: 105,
+    });
+  });
+
+  it("parses terminal and error events", () => {
+    expect(
+      parseUkVisaJobsProgressLine(
+        'JOBOPS_PROGRESS {"event":"empty_page","pageNo":3,"maxPages":4,"totalCollected":28}',
+      ),
+    ).toEqual({
+      type: "empty_page",
+      pageNo: 3,
+      maxPages: 4,
+      totalCollected: 28,
+    });
+
+    expect(
+      parseUkVisaJobsProgressLine(
+        'JOBOPS_PROGRESS {"event":"done","maxPages":4,"totalCollected":42,"totalAvailable":105}',
+      ),
+    ).toEqual({
+      type: "done",
+      maxPages: 4,
+      totalCollected: 42,
+      totalAvailable: 105,
+    });
+
+    expect(
+      parseUkVisaJobsProgressLine(
+        'JOBOPS_PROGRESS {"event":"error","message":"boom","pageNo":2,"status":500}',
+      ),
+    ).toEqual({
+      type: "error",
+      message: "boom",
+      pageNo: 2,
+      status: 500,
+    });
+  });
+
+  it("ignores malformed or unrelated lines", () => {
+    expect(parseUkVisaJobsProgressLine("JOBOPS_PROGRESS {bad")).toBeNull();
+    expect(parseUkVisaJobsProgressLine("normal log line")).toBeNull();
+  });
+});