fix(jobdanmark-search): emit the /scrape contract fields in search output (#340)

Adds additive normalization so jobdanmark search output carries the cross-portal contract fields: company from companyName, location as the city after the postal code in companyAddress (null-safe - a missing or null address yields null instead of crashing the search), and date/deadline converted from DD-MM-YYYY to YYYY-MM-DD with safe passthrough on unexpected formats. Native fields unchanged.

Co-authored-by: oscarbol09 <80536682+oscarbol09@users.noreply.github.com>
This commit is contained in:
Oscar Madera
2026-08-19 08:32:06 +02:00
committed by GitHub
parent 04186b9a37
commit 17bc698697
4 changed files with 89 additions and 4 deletions
@@ -148,7 +148,11 @@ bun run src/cli.ts search --text "sygeplejerske" --zip 8000 --limit 10
"url": "https://jobdanmark.dk/media/idvbnt4y/rah-service-as-billede.png",
"focalPoint": { "top": 0.488, "left": 0.499 }
},
"silhouetteLogo": false
"silhouetteLogo": false,
"company": "Rah Service A/S",
"location": "Ringkøbing",
"date": "2026-03-12",
"deadline": "2026-04-10"
}
]
}
@@ -161,6 +165,7 @@ bun run src/cli.ts search --text "sygeplejerske" --zip 8000 --limit 10
> - `companyLogo` can be `null`.
> - `publishedDate` format: `"DD-MM-YYYY"`.
> - `coverImage` can be `null`.
> - Every result also carries the cross-portal contract fields `company`, `location`, `date` and `deadline`, derived from `companyName`, the city after the postal code in `companyAddress`, and the day-first dates converted to `YYYY-MM-DD` — `/scrape` Step 2 expects search output to include title, company, location, date, and URL. Native fields are preserved unchanged.
---
@@ -2,7 +2,7 @@ import { defineCommand, option } from "@bunli/core"
import { z } from "zod"
import { apiPost, writeError, BASE_URL } from "../helpers.js"
interface ApiSearchItem {
export interface ApiSearchItem {
title: string
companyName: string
companyLogo: {
@@ -12,7 +12,7 @@ interface ApiSearchItem {
} | null
companyLogoSvgMarkup: string | null
overlayColor: string | null
companyAddress: string
companyAddress: string | null
jobTypes: string[]
boostJob: boolean
publishedDate: string
@@ -34,7 +34,12 @@ interface ApiSearchResponse {
totalPages: number
}
function normalizeItem(item: ApiSearchItem): Record<string, unknown> {
function toContractDate(value: string | null): string | null {
const match = value?.match(/^(\d{2})-(\d{2})-(\d{4})$/)
return match ? `${match[3]}-${match[2]}-${match[1]}` : (value ?? null)
}
export function normalizeItem(item: ApiSearchItem): Record<string, unknown> {
const relativeUrl = item.url
const fullUrl = relativeUrl.startsWith("http")
? relativeUrl
@@ -77,6 +82,10 @@ function normalizeItem(item: ApiSearchItem): Record<string, unknown> {
slug,
coverImage,
silhouetteLogo: item.silhouetteLogo,
company: item.companyName,
location: item.companyAddress?.match(/\d{4}\s+(.+)$/)?.[1] ?? null,
date: toContractDate(item.publishedDate),
deadline: toContractDate(item.applicationDeadline),
}
}
@@ -0,0 +1,64 @@
import { describe, expect, test } from "bun:test";
import { normalizeItem, type ApiSearchItem } from "../src/commands/search";
function item(): ApiSearchItem {
return {
title: "Softwareudvikler",
companyName: "Statens It",
companyLogo: null,
companyLogoSvgMarkup: null,
overlayColor: null,
companyAddress: "Lautruphøj 2, 2750 Ballerup",
jobTypes: ["fuldtid"],
boostJob: false,
publishedDate: "27-07-2026",
applicationDeadline: "17-08-2026",
url: "/job/softwareudvikler-til-statens-it",
coverImage: null,
silhouetteLogo: false,
};
}
describe("Jobdanmark search normalization", () => {
test("additively emits the /scrape contract fields (company, location, date, deadline)", () => {
const result = normalizeItem(item());
expect(result).toMatchObject({
company: "Statens It",
location: "Ballerup",
date: "2026-07-27",
deadline: "2026-08-17",
url: "https://jobdanmark.dk/job/softwareudvikler-til-statens-it",
});
});
test("maps a missing address zip and a null deadline to null", () => {
const result = normalizeItem({
...item(),
companyAddress: "Lautruphøj 2",
applicationDeadline: null,
});
expect(result.location).toBeNull();
expect(result.deadline).toBeNull();
expect(result.company).toBe("Statens It");
});
test("survives a null companyAddress from the API", () => {
const result = normalizeItem({
...item(),
companyAddress: null,
});
expect(result.location).toBeNull();
expect(result.company).toBe("Statens It");
});
test("keeps native fields unchanged (additive contract)", () => {
const result = normalizeItem(item());
expect(result.companyName).toBe("Statens It");
expect(result.publishedDate).toBe("27-07-2026");
expect(result.applicationDeadline).toBe("17-08-2026");
});
});
+7
View File
@@ -46,6 +46,13 @@ per-file diff commands.
### Fixed
- **`jobdanmark-search` search output now carries the `/scrape` contract fields** - the CLI
exposed the API-native schema (`companyName`, `publishedDate` in `DD-MM-YYYY`, …) with no
`company`, `location`, `date` or `deadline`, so every `/scrape` run flagged jobdanmark as
degraded and the `seen_jobs.json` dedupe lost the company. Search results now additively emit
`company`, `location` (city after the postal code in `companyAddress`), and `date`/`deadline`
in the `YYYY-MM-DD` convention, with null-safe handling of a missing address.
- **`jobnet-search` search output now carries the `/scrape` contract fields** - the CLI emitted
the raw Jobnet API schema (`jobAdId`, `hiringOrgName`, `publicationDate`, …) with no
`company`, `location`, `date` or `url`, so every `/scrape` run flagged jobnet as degraded