Dockerfile for bucket listing

bucketListing/Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11.6-slim
+
+WORKDIR /usr/src/app
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN groupadd -g 999 appuser && \
+    useradd -r -u 999 -g appuser appuser
+USER appuser
+
+COPY . .
+
+ENTRYPOINT [ "python", "./createBucketListing.py"]
+

bucketListing/createBucketListing.py

@@ -0,0 +1,28 @@
+from google.cloud import storage
+import base64
+import binascii
+import argparse
+
+
+def createBucketListing(project, bucket):
+
+    gcsPrefix = "https://storage.neonscience.org/"
+    gcsBucketName = bucket
+    storage_client = storage.Client(project)
+    blobs = storage_client.list_blobs(gcsBucketName)
+    listing = 'object,last_modified,etag' + '\n'
+    for blob in blobs:
+        checksum = binascii.hexlify(base64.urlsafe_b64decode(blob.md5_hash)).decode()
+        listing += gcsPrefix + gcsBucketName + "/" + blob.name + ',' + blob.updated.strftime("%Y-%m-%d %H:%M:%S") + ',' + checksum + '\n' 
+
+    gcsBucket = storage_client.bucket(gcsBucketName)
+    listingBlob = gcsBucket.blob("listing.csv")
+    listingBlob.upload_from_string(listing)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--project')
+    parser.add_argument('--bucket')
+    args=parser.parse_args()
+    createBucketListing(args.project, args.bucket)

bucketListing/requirements.txt

@@ -0,0 +1,17 @@
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+google-api-core==2.14.0
+google-auth==2.23.4
+google-cloud-core==2.3.3
+google-cloud-storage==2.13.0
+google-crc32c==1.5.0
+google-resumable-media==2.6.0
+googleapis-common-protos==1.61.0
+idna==3.6
+protobuf==4.25.1
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+requests==2.31.0
+rsa==4.9
+urllib3==2.1.0