diff options
| author | amankumarsingh77 <amankumarsingh7702@gmail.com> | 2026-07-27 00:27:08 +0530 |
|---|---|---|
| committer | Aman Kumar <145339995+amankumarsingh77@users.noreply.github.com> | 2026-08-02 19:12:46 +0530 |
| commit | 15a537a99efba614e6e108722462bcb78ec6c3c4 (patch) | |
| tree | 2ff20907fee8ace7a071470d491fe7808dce6a63 /test/deep-research/serp-parser-test.ts | |
| parent | ce5d808cb4cc3581d85b829656d1d478dc43e3a6 (diff) | |
test: port remaining suites to node:test
Mechanical port of the hand-rolled check() harness. Import-after-env
ordering preserved so suites still read their sandbox dirs.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'test/deep-research/serp-parser-test.ts')
| -rw-r--r-- | test/deep-research/serp-parser-test.ts | 97 |
1 files changed, 53 insertions, 44 deletions
diff --git a/test/deep-research/serp-parser-test.ts b/test/deep-research/serp-parser-test.ts index dabd72b..af5ac54 100644 --- a/test/deep-research/serp-parser-test.ts +++ b/test/deep-research/serp-parser-test.ts @@ -1,24 +1,14 @@ /** * Unit tests for the pure Google SERP parser — no browser required. * - * Run: npx tsx test/deep-research/serp-parser-test.ts + * Run: npm test */ +import { test, describe } from "node:test"; +import assert from "node:assert/strict"; import { readFileSync } from "node:fs"; import { join } from "node:path"; import { classifySerp, parseGoogleSerp, type SerpExtraction } from "../../src/domains/search/google-serp"; -let passed = 0; -let failed = 0; -const check = (cond: boolean, label: string): void => { - if (cond) { - passed++; - console.log(` ✓ ${label}`); - } else { - failed++; - console.error(` ✗ ${label}`); - } -}; - const fixture = (name: string): SerpExtraction => JSON.parse(readFileSync(join(import.meta.dirname, "fixtures", name), "utf8")) as SerpExtraction; @@ -26,34 +16,53 @@ const ok = fixture("google-serp-ok.json"); const captcha = fixture("google-serp-captcha.json"); const empty = fixture("google-serp-empty.json"); -// S1: redirect unwrapping + internal/javascript anchors dropped -{ - const results = parseGoogleSerp(ok.anchors, 10); - const urls = results.map((r) => r.url); - check(urls.includes("https://real.example/x"), "S1: /url?q= redirect is unwrapped to the real target"); - check(!urls.some((u) => u.includes("google.com")), "S1: google-internal anchors are dropped"); - check(!urls.some((u) => u.startsWith("javascript:")), "S1: javascript: anchors are dropped"); -} - -// S2: dedupe + rank + limit -{ - const results = parseGoogleSerp(ok.anchors, 10); - const realExampleCount = results.filter((r) => r.url.startsWith("https://real.example/x")).length; - check(realExampleCount === 1, "S2: trailing-slash duplicate collapses to one result"); - check( - results.every((r, i) => r.rank === i + 1), - "S2: rank runs 1..n in input order", - ); - const capped = parseGoogleSerp(ok.anchors, 2); - check(capped.length === 2 && capped[capped.length - 1]?.rank === 2, "S2: limit truncates and ranks stay 1..limit"); -} - -// S3: CAPTCHA / no-results classification -{ - check(classifySerp(ok.pageText, parseGoogleSerp(ok.anchors, 10).length) === "ok", "S3: populated SERP classifies as ok"); - check(classifySerp(captcha.pageText, 0) === "captcha", "S3: captcha page classifies as captcha"); - check(classifySerp(empty.pageText, 0) === "no_results", "S3: empty results classify as no_results"); -} - -console.log(`\n${passed} passed, ${failed} failed`); -if (failed > 0) process.exit(1); +describe("pure Google SERP parser", () => { + // S1: redirect unwrapping + internal/javascript anchors dropped + test("S1: /url?q= redirect is unwrapped to the real target", () => { + const results = parseGoogleSerp(ok.anchors, 10); + const urls = results.map((r) => r.url); + assert.ok(urls.includes("https://real.example/x")); + }); + + test("S1: google-internal anchors are dropped", () => { + const results = parseGoogleSerp(ok.anchors, 10); + const urls = results.map((r) => r.url); + assert.ok(!urls.some((u) => u.includes("google.com"))); + }); + + test("S1: javascript: anchors are dropped", () => { + const results = parseGoogleSerp(ok.anchors, 10); + const urls = results.map((r) => r.url); + assert.ok(!urls.some((u) => u.startsWith("javascript:"))); + }); + + // S2: dedupe + rank + limit + test("S2: trailing-slash duplicate collapses to one result", () => { + const results = parseGoogleSerp(ok.anchors, 10); + const realExampleCount = results.filter((r) => r.url.startsWith("https://real.example/x")).length; + assert.equal(realExampleCount, 1); + }); + + test("S2: rank runs 1..n in input order", () => { + const results = parseGoogleSerp(ok.anchors, 10); + assert.ok(results.every((r, i) => r.rank === i + 1)); + }); + + test("S2: limit truncates and ranks stay 1..limit", () => { + const capped = parseGoogleSerp(ok.anchors, 2); + assert.ok(capped.length === 2 && capped[capped.length - 1]?.rank === 2); + }); + + // S3: CAPTCHA / no-results classification + test("S3: populated SERP classifies as ok", () => { + assert.equal(classifySerp(ok.pageText, parseGoogleSerp(ok.anchors, 10).length), "ok"); + }); + + test("S3: captcha page classifies as captcha", () => { + assert.equal(classifySerp(captcha.pageText, 0), "captcha"); + }); + + test("S3: empty results classify as no_results", () => { + assert.equal(classifySerp(empty.pageText, 0), "no_results"); + }); +}); |
