From 2d5d12b544e4b3ae90eb09032f5cb2bff21dd458 Mon Sep 17 00:00:00 2001
From: kert <kert@rack.localdomain>
Date: Tue, 22 Sep 2026 16:29:27 -0400
Subject: [PATCH] =?UTF-8?q?fix(bls):=20upper-case=20the=20OEWS=20sheet=20h?=
 =?UTF-8?q?eaders=20=E2=80=94=20the=20May=202019=20release=20ships=20them?=
 =?UTF-8?q?=20lower-case,=20which=20loaded=200=20occupations=20(refs=20#69?=
 =?UTF-8?q?5)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 src/bls/oews.py        | 3 ++-
 tests/bls/test_oews.py | 8 ++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/src/bls/oews.py b/src/bls/oews.py
index 5a560d3..1c2e87a 100644
--- a/src/bls/oews.py
+++ b/src/bls/oews.py
@@ -129,7 +129,8 @@ def read_national(zip_path: Path, year: int) -> list[dict]:
         if ext == "xlsx"
         else pl.read_excel(io.BytesIO(raw), infer_schema_length=0, engine="calamine")
     )
-    return df.to_dicts()
+    # The 2019 release shipped lower-case headers; every other year is upper.
+    return df.rename({c: c.upper() for c in df.columns}).to_dicts()
 
 
 # ── rows ──────────────────────────────────────────────────────────────
diff --git a/tests/bls/test_oews.py b/tests/bls/test_oews.py
index de40d2f..8f9dd2e 100644
--- a/tests/bls/test_oews.py
+++ b/tests/bls/test_oews.py
@@ -271,6 +271,14 @@ class TestReadNational:
         recs = read_national(p, 2023)
         assert len(recs) == 2 and recs[0]["O_GROUP"] == "detailed"
 
+    def test_lower_case_headers_are_normalised(self, tmp_path):
+        # the May 2019 file is the one release with lower-case column names
+        p = tmp_path / "oesm19nat.zip"
+        p.write_bytes(_zip(2019, [c.lower() for c in NEW_COLS], NEW_ROWS))
+        recs = read_national(p, 2019)
+        assert recs[0]["OCC_CODE"] == "31-9092"
+        assert len(to_rows(2019, recs, item_key="K")) == 2
+
     def test_missing_member(self, tmp_path):
         p = tmp_path / "bad.zip"
         with zipfile.ZipFile(p, "w") as z: