retrieval: remove unnecessary decode-encode step

This should fix MemoryError on attempting encoding
globaldothealth · Feb 28, 2022 · 062d4b9 · 062d4b9
1 parent 9eb0de1
commit 062d4b9
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/ingestion/functions/retrieval/retrieval.py b/ingestion/functions/retrieval/retrieval.py
@@ -120,8 +120,8 @@ def raw_content(url: str, content: bytes, tempdir: str = TEMP_PATH) -> io.BytesI
                      if f.is_file()),
                     key=operator.itemgetter(1)
                 )[0]
-                with largest_file.open() as fp:
-                    content = fp.read().encode("utf-8")
+                with largest_file.open("rb") as fp:
+                    content = fp.read()
             except subprocess.CalledProcessError as e:
                 raise ValueError(f"Error in extracting zip file with exception:\n{e}")
         Path(f.name).unlink(missing_ok=True)