Check for assets with size of 0 bytes (explosion#10026)

ryndaniels · svlandeg · web-flow · commit 057b8c64c018 · 2022-01-12T10:34:23.000+01:00
* Check for assets with size of 0 bytes

* Update spacy/cli/project/assets.py

Co-authored-by: Sofie Van Landeghem &lt;svlandeg@users.noreply.github.com&gt;

Co-authored-by: Sofie Van Landeghem &lt;svlandeg@users.noreply.github.com&gt;
diff --git a/spacy/cli/project/assets.py b/spacy/cli/project/assets.py
@@ -1,6 +1,7 @@
 from typing import Any, Dict, Optional
 from pathlib import Path
 from wasabi import msg
+import os
 import re
 import shutil
 import requests
@@ -129,10 +130,17 @@ def fetch_asset(
         the asset failed.
     """
     dest_path = (project_path / dest).resolve()
-    if dest_path.exists() and checksum:
+    if dest_path.exists():
         # If there's already a file, check for checksum
-        if checksum == get_checksum(dest_path):
-            msg.good(f"Skipping download with matching checksum: {dest}")
+        if checksum:
+            if checksum == get_checksum(dest_path):
+                msg.good(f"Skipping download with matching checksum: {dest}")
+                return
+        else:
+            # If there's not a checksum, make sure the file is a possibly valid size
+            if os.path.getsize(dest_path) == 0:
+                msg.warn(f"Asset exists but with size of 0 bytes, deleting: {dest}")
+                os.remove(dest_path)
     # We might as well support the user here and create parent directories in
     # case the asset dir isn't listed as a dir to create in the project.yml
     if not dest_path.parent.exists():
