Merge pull request #48 from CDCgov/ap66-file_ext_flexibility_update

Ap66-file_ext_flexibility_update

Author: cdc-ap66

.github/workflows/release.yaml

@@ -63,26 +63,14 @@ jobs:
         run: |
           poetry install --no-root --with dev
 
-      - name: Build Wheel
-        if: steps.is-release.outputs.should_continue == 'true'
-        run: |
-          poetry build
-
-      - name: Create Release
-        if: steps.is-release.outputs.should_continue == 'true'
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          gh release create ${{ github.ref }} dist/* --generate-notes --latest
-
       - name: Update pyproject.toml Version
         if: steps.is-release.outputs.should_continue == 'true'
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
           VERSION=${{ steps.get-version.outputs.version }}
 
-          sed -i.bak -E "s/^version\s*=\s*\"[^\"]+\"/version = \"${VERSION}\"/" pyproject.toml
+          sed -i.bak -E "s/^\s*version\s*=\s*\"[^\"]+\"/version = \"${VERSION}\"/" pyproject.toml
 
       - name: Update Change Log
         if: steps.is-release.outputs.should_continue == 'true'
@@ -105,6 +93,18 @@ jobs:
               { print $0 }
             ' changelog.md > temp.md && mv temp.md changelog.md
 
+      - name: Build Wheel
+        if: steps.is-release.outputs.should_continue == 'true'
+        run: |
+          poetry build
+
+      - name: Create Release
+        if: steps.is-release.outputs.should_continue == 'true'
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          gh release create ${{ github.ref }} dist/* --generate-notes --latest
+
       - name: Commit Change Log and pyproject.toml Updates
         if: steps.is-release.outputs.should_continue == 'true'
         env:

cfa/dataops/catalog.py

@@ -283,16 +283,18 @@ def get_versions(self) -> list:
             reverse=True,
         )
 
-    def get_file_ext(self) -> str:
+    def get_file_ext(self, version: str = "latest") -> str:
         """returns the file extension for handy routing of read byte types for
         DataFrame reading
 
+        Args:
+            version (str, optional): the version of the data to get.
         Returns:
             str: the file extension
         """
-        return self._get_version_blobs(print_version=False)[0]["name"].split(
-            "."
-        )[-1]
+        return self._get_version_blobs(version=version, print_version=False)[
+            0
+        ]["name"].split(".")[-1]
 
     def _get_version_blobs(
         self, version: str = "latest", newest=True, print_version=True
@@ -413,7 +415,7 @@ def get_dataframe(
                 f"Output {output} needs to be 'pandas', 'polars', 'pd, or 'pl'."
             )
         blobs = self.read_blobs(version, newest=newest)
-        file_ext = self.get_file_ext()
+        file_ext = self.get_file_ext(version=version)
         blob_bytes = [blob.content_as_bytes() for blob in blobs]
         blob_files = [BytesIO(pq) for pq in blob_bytes]
         if file_ext == "csv":

changelog.md

@@ -8,6 +8,12 @@ The versioning pattern is `YYYY.MM.DD.micro(a/b/{none if release})
 
 ---
 
+## [2025.12.10.0a]
+
+### Updated
+
+- Added version matching to `BlobEndpoint.get_file_ext()` method for greater flexibility to changing file types over time.
+
 ## [2025.12.08.1a]
 
 ### Fixed

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cfa.dataops"
-version = "2025.12.08.1a"
+version = "2025.12.10.0a"
 description = "Data cataloging, ETL, modeling, verification, and validation for CFA"
 authors = [
     { name = "Phil Rogers", email = "ap66@cdc.gov" },