diff options
| author | amankumarsingh77 <amankumarsingh7702@gmail.com> | 2026-07-28 21:17:13 +0530 |
|---|---|---|
| committer | Aman Kumar <145339995+amankumarsingh77@users.noreply.github.com> | 2026-08-02 19:12:46 +0530 |
| commit | ea11182a0e8cb62d208b5b53a60c98c8bdef9e9a (patch) | |
| tree | 665fb355b902e5f067694d1e953039f6713e8245 /test/domains/serp-parser-test.ts | |
| parent | 91f5ad12fc04264e0423b37c4871c826bb98a66b (diff) | |
feat!: remove the deep-research feature
The harness ships browser tools; orchestrating a multi-agent research
workflow on top of them is the agent's job, not this extension's. Drops
the skill, the /deep-research command, and the web-search-researcher
subagent config.
browser_web_search and browser_read_page are untouched — the two tests
that covered their pure parsers move to test/domains/, where the test
glob still picks them up.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'test/domains/serp-parser-test.ts')
| -rw-r--r-- | test/domains/serp-parser-test.ts | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/test/domains/serp-parser-test.ts b/test/domains/serp-parser-test.ts new file mode 100644 index 0000000..433c650 --- /dev/null +++ b/test/domains/serp-parser-test.ts @@ -0,0 +1,60 @@ +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"; + +const fixture = (name: string): SerpExtraction => + JSON.parse(readFileSync(join(import.meta.dirname, "fixtures", name), "utf8")) as SerpExtraction; + +const ok = fixture("google-serp-ok.json"); +const captcha = fixture("google-serp-captcha.json"); +const empty = fixture("google-serp-empty.json"); + +describe("pure Google SERP parser", () => { + 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:"))); + }); + + 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); + }); + + 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"); + }); +}); |
