py/ai-job-search
1
0
Fork 0
mirror of https://github.com/MadsLorentzen/ai-job-search.git synced 2026-09-17 16:46:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(jobdanmark-search): accept a comma after the postcode in location extraction

Browse Source 
The location regex required whitespace after the 4-digit postcode, but
live companyAddress values frequently read "2670, Greve" - those results
emitted location: null (7/30 in the review's live sample; 1/30 after this
fix), leaving /scrape's geography filter nothing to act on. Extraction is
now a helper with a comma fallback that requires a non-digit city start,
so a 4-digit street number never wins over the real postcode, and the
captured city is trimmed. Review finding F2 (2026-08-19).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mads Lorentzen
2026-08-19 19:46:34 +02:00
co-authored by Claude Opus 5
parent b2545d5121
commit 7aba0b4a9d
3 changed files with 47 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/jobdanmark-search/cli/src/commands/search.ts
+13 -1
View File
@@ -39,6 +39,18 @@ function toContractDate(value: string | null): string | null {
return match ? `${match[3]}-${match[2]}-${match[1]}` : (value ?? null)
}
// Live companyAddress values put the city after the postcode either as
// "Lautruphoej 2, 2750 Ballerup" or "2670, Greve". The comma fallback
// requires a non-digit after the comma so a 4-digit street number
// ("Vejlevej 1234, 7100 Vejle") never wins over the real postcode.
function extractCity(address: string | null): string | null {
if (!address) return null
const city =
address.match(/\d{4}\s+(.+)$/)?.[1] ?? address.match(/\d{4}\s*,\s*([^\d,].*)$/)?.[1]
const trimmed = city?.trim()
return trimmed ? trimmed : null
}
export function normalizeItem(item: ApiSearchItem): Record<string, unknown> {
const relativeUrl = item.url
const fullUrl = relativeUrl.startsWith("http")
@@ -83,7 +95,7 @@ export function normalizeItem(item: ApiSearchItem): Record<string, unknown> {
coverImage,
silhouetteLogo: item.silhouetteLogo,
company: item.companyName,
location: item.companyAddress?.match(/\d{4}\s+(.+)$/)?.[1] ?? null,
location: extractCity(item.companyAddress),
date: toContractDate(item.publishedDate),
deadline: toContractDate(item.applicationDeadline),
}