Use a python script instead

Author: namannimmo10

.github/workflows/httomolibgpu_tests_run_iris.yml

@@ -33,41 +33,12 @@ jobs:
 
       - name: Download test data from Zenodo
         run: |
-          # Install required tools
-          dnf install -y epel-release
-          dnf install -y curl jq
+          chmod +x ./.scripts/download_zenodo.py
 
-          # Create a directory to store test data
-          mkdir -p tests/large_data_archive
-          cd tests/large_data_archive
+          ./.scripts/download_zenodo.py tests/large_data_archive
 
-          # Download and process all files from Zenodo
-          echo "Fetching files from Zenodo record 14338424..."
-          curl -s "https://zenodo.org/api/records/14338424" | \
-          jq -r '.files.entries[] | [.key, .links.content, .checksum] | @tsv' | \
-          while IFS=$'\t' read -r filename url checksum; do
-            echo "Downloading ${filename}..."
-            curl -L -o "${filename}" "${url}"
-            
-            # Extract MD5 from checksum string (removes 'md5:' prefix)
-            expected_md5=${checksum#md5:}
-            actual_md5=$(md5sum "${filename}" | cut -d' ' -f1)
-            
-            if [ "${actual_md5}" = "${expected_md5}" ]; then
-              echo "✓ Verified ${filename}"
-            else
-              echo "✗ Checksum verification failed for ${filename}"
-              echo "Expected: ${expected_md5}"
-              echo "Got: ${actual_md5}"
-              exit 1
-            fi
-          done
-
-          # Show downloaded files
           echo -e "\nDownloaded files:"
-          ls -lh
-
-          cd ../..
+          ls -lh tests/large_data_archive
 
       - name: Install httomolibgpu
         run: |

.scripts/download_zenodo.py

@@ -0,0 +1,66 @@
+#!/usr/bin/env python3
+
+import json
+import urllib.request
+import hashlib
+import sys
+import os
+from pathlib import Path
+
+
+def calculate_md5(filename):
+    """Calculate MD5 hash of a file."""
+    md5_hash = hashlib.md5()
+    with open(filename, "rb") as f:
+        for chunk in iter(lambda: f.read(4096), b""):
+            md5_hash.update(chunk)
+    return md5_hash.hexdigest()
+
+
+def download_zenodo_files(output_dir: Path):
+    """
+    Download all files from Zenodo record 14338424 and verify their checksums.
+    
+    Args:
+        output_dir: Directory where files should be downloaded
+    """
+    try:
+        print("Fetching files from Zenodo record 14338424...")
+        with urllib.request.urlopen("https://zenodo.org/api/records/14338424") as response:
+            data = json.loads(response.read())
+        
+        # Create output directory if it doesn't exist
+        output_dir.mkdir(parents=True, exist_ok=True)
+        
+        for filename, file_info in data["files"]["entries"].items():
+            output_file = output_dir / filename
+            print(f"Downloading {filename}...")
+            url = file_info["links"]["content"]
+            expected_md5 = file_info["checksum"].split(":")[1]
+            
+            # Download file
+            urllib.request.urlretrieve(url, output_file)
+            
+            # Verify checksum
+            actual_md5 = calculate_md5(output_file)
+            if actual_md5 == expected_md5:
+                print(f"✓ Verified {filename}")
+            else:
+                print(f"✗ Checksum verification failed for {filename}")
+                print(f"Expected: {expected_md5}")
+                print(f"Got: {actual_md5}")
+                sys.exit(1)
+                
+        print("\nAll files downloaded and verified successfully!")
+        
+    except Exception as e:
+        print(f"Error: {str(e)}", file=sys.stderr)
+        sys.exit(1)
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: download_zenodo.py <output_directory>")
+        sys.exit(1)
+        
+    output_dir = Path(sys.argv[1])
+    download_zenodo_files(output_dir)