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

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>

.agents/skills/jobdanmark-search/cli/src/commands/search.ts

@@ -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),
   }

.agents/skills/jobdanmark-search/cli/tests/search-normalization.test.ts

@@ -44,6 +44,33 @@ describe("Jobdanmark search normalization", () => {
     expect(result.company).toBe("Statens It");
   });
 
+  test("extracts the city when a comma follows the postcode (live jobdanmark shape)", () => {
+    const result = normalizeItem({
+      ...item(),
+      companyAddress: "2670, Greve",
+    });
+
+    expect(result.location).toBe("Greve");
+  });
+
+  test("trims trailing whitespace from the extracted city", () => {
+    const result = normalizeItem({
+      ...item(),
+      companyAddress: "7100, Vejle ",
+    });
+
+    expect(result.location).toBe("Vejle");
+  });
+
+  test("does not mistake a 4-digit street number for the postcode", () => {
+    const result = normalizeItem({
+      ...item(),
+      companyAddress: "Vejlevej 1234, 7100 Vejle",
+    });
+
+    expect(result.location).toBe("Vejle");
+  });
+
   test("survives a null companyAddress from the API", () => {
     const result = normalizeItem({
       ...item(),

CHANGELOG.md

@@ -56,6 +56,13 @@ per-file diff commands.
 
 ### Fixed
 
+- **`jobdanmark-search` extracts the city when a comma follows the postcode** - the
+  `location` regex required whitespace after the 4-digit postcode, but live
+  `companyAddress` values frequently read `"2670, Greve"`; those results emitted
+  `location: null` (7 of 30 in a live sample), so `/scrape`'s geography/commute filter
+  (Rule 3) had nothing to act on. The extraction now accepts an optional comma, trims the
+  captured city, and still refuses to mistake a 4-digit street number for the postcode.
+  Pinned by three new cases in `tests/search-normalization.test.ts`.
 - **Example-CV bullets no longer swallowed as LaTeX optional labels** - every placeholder
   bullet written as `\item [text]` (11 in `cv/main_example.tex`, 3 in
   `06-cover-letter-templates.md`'s taught template) let LaTeX parse the bracketed text as