refactor(pipeline): unify KS2 and KS4 legacy sources to same annual ZIPs

LegacyKS2Stream now auto-detects ZIP vs bare CSV — if the download is a ZIP
it extracts england_ks2final.csv; if it's a plain CSV file it reads directly.
This keeps backwards compatibility while allowing both streams to share the
same DfE annual archive URLs.

legacy_ks2_urls updated to point at the same 4 ZIPs as legacy_ks4_urls so
only one set of archives needs to be maintained going forward.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

pipeline/meltano.yml

@@ -31,10 +31,10 @@ plugins:
           description: "Year code → URL mapping for legacy KS4 ZIPs (england_ks4final.csv inside)"
       config:
         legacy_ks2_urls:
-          "201516": "http://10.0.1.224:8081/filebrowser/api/public/dl/R9jjXFWa?inline=true"
-          "201617": "http://10.0.1.224:8081/filebrowser/api/public/dl/tIwJPVQS?inline=true"
-          "201718": "http://10.0.1.224:8081/filebrowser/api/public/dl/GO7SKE0p?inline=true"
-          "201819": "http://10.0.1.224:8081/filebrowser/api/public/dl/jchDEHsv?inline=true"
+          "201516": "http://10.0.1.224:8081/filebrowser/api/public/dl/iaoSkg1v?inline=true"
+          "201617": "http://10.0.1.224:8081/filebrowser/api/public/dl/bqCMUcIH?inline=true"
+          "201718": "http://10.0.1.224:8081/filebrowser/api/public/dl/0L61fE_a?inline=true"
+          "201819": "http://10.0.1.224:8081/filebrowser/api/public/dl/XJGJ5lG1?inline=true"
         legacy_ks4_urls:
           "201516": "http://10.0.1.224:8081/filebrowser/api/public/dl/iaoSkg1v?inline=true"
           "201617": "http://10.0.1.224:8081/filebrowser/api/public/dl/bqCMUcIH?inline=true"

pipeline/plugins/extractors/tap-uk-ees/tap_uk_ees/tap.py

@@ -682,8 +682,31 @@ class LegacyKS2Stream(Stream):
                 self.logger.warning("Failed to download %s: %s", url, e)
                 continue
 
+            content = resp.content
+
+            # Auto-detect ZIP — the DfE annual archives contain both KS2 and KS4
+            # CSVs in one ZIP. If the download is a ZIP, extract england_ks2final.csv;
+            # otherwise treat the content as a bare CSV (legacy individual-file URLs).
+            csv_bytes = None
+            try:
+                zf = zipfile.ZipFile(io.BytesIO(content))
+                target = next(
+                    (n for n in zf.namelist() if "ks2final" in n.lower() and n.endswith(".csv")),
+                    None,
+                )
+                if target:
+                    with zf.open(target) as f:
+                        csv_bytes = f.read()
+                    self.logger.info("Extracted %s from ZIP for %s", target, year_code)
+                else:
+                    self.logger.warning("No ks2final CSV found in ZIP for %s", year_code)
+                    continue
+            except zipfile.BadZipFile:
+                # Not a ZIP — treat as a bare CSV file
+                csv_bytes = content
+
             df = pd.read_csv(
-                io.BytesIO(resp.content),
+                io.BytesIO(csv_bytes),
                 dtype=str,
                 keep_default_na=False,
                 encoding="latin-1",