fix: migrate storage samples to use download_as_bytes() (GoogleCloudPlatform#9862)

kweinmeister · web-flow · commit d06561cc28de · 2023-05-03T10:21:33.000-07:00
diff --git a/data-science-onramp/data-ingestion/ingestion_test.py b/data-science-onramp/data-ingestion/ingestion_test.py
@@ -145,7 +145,7 @@ def get_dataproc_job_output(result):
     """Get the dataproc job logs in plain text"""
     output_location = result.driver_output_resource_uri + ".000000000"
     blob = get_blob_from_path(output_location)
-    return blob.download_as_string().decode("utf-8")
+    return blob.download_as_bytes().decode("utf-8")
 
 
 def assert_table_success_message(table_name, out):
diff --git a/data-science-onramp/data-processing/process_test.py b/data-science-onramp/data-processing/process_test.py
@@ -179,7 +179,7 @@ def test_process():
     # Get job output
     output_location = result.driver_output_resource_uri + ".000000000"
     blob = get_blob_from_path(output_location)
-    out = blob.download_as_string().decode("utf-8")
+    out = blob.download_as_bytes().decode("utf-8")
 
     # trip duration
     assert not is_in_table(r"\d*.\d* s", out)
diff --git a/dataproc/snippets/quickstart/quickstart.py b/dataproc/snippets/quickstart/quickstart.py
@@ -81,7 +81,7 @@ def quickstart(project_id, region, cluster_name, job_file_path):
         storage.Client()
         .get_bucket(matches.group(1))
         .blob(f"{matches.group(2)}.000000000")
-        .download_as_string()
+        .download_as_bytes().decode("utf-8")
     )
 
     print(f"Job finished successfully: {output}")
diff --git a/dataproc/snippets/submit_job.py b/dataproc/snippets/submit_job.py
@@ -63,7 +63,7 @@ def submit_job(project_id, region, cluster_name):
         storage.Client()
         .get_bucket(matches.group(1))
         .blob(f"{matches.group(2)}.000000000")
-        .download_as_string()
+        .download_as_bytes().decode("utf-8")
     )
 
     print(f"Job finished successfully: {output}")
diff --git a/dataproc/snippets/submit_job_to_cluster.py b/dataproc/snippets/submit_job_to_cluster.py
@@ -74,7 +74,7 @@ def download_output(project, cluster_id, output_bucket, job_id):
     output_blob = "google-cloud-dataproc-metainfo/{}/jobs/{}/driveroutput.000000000".format(
         cluster_id, job_id
     )
-    return bucket.blob(output_blob).download_as_string()
+    return bucket.blob(output_blob).download_as_bytes().decode("utf-8")
 
 
 # [START dataproc_create_cluster]
@@ -132,7 +132,7 @@ def quickstart(project_id, region, cluster_name, gcs_bucket, pyspark_file):
         storage.Client()
         .get_bucket(matches.group(1))
         .blob(f"{matches.group(2)}.000000000")
-        .download_as_string()
+        .download_as_bytes().decode("utf-8")
     )
 
     print(f"Job finished successfully: {output}\r\n")
diff --git a/vision/snippets/detect/beta_snippets.py b/vision/snippets/detect/beta_snippets.py
@@ -346,7 +346,7 @@ def async_batch_annotate_images_uri(input_image_uri, output_uri):
     # annotations for the first two annotate image requests.
     output = blob_list[0]
 
-    json_string = output.download_as_string()
+    json_string = output.download_as_bytes().decode("utf-8")
     response = vision.BatchAnnotateImagesResponse.from_json(json_string)
 
     # Prints the actual response for the first annotate image request.
diff --git a/vision/snippets/detect/detect.py b/vision/snippets/detect/detect.py
@@ -861,7 +861,7 @@ def async_detect_document(gcs_source_uri, gcs_destination_uri):
     # the first two pages of the input file.
     output = blob_list[0]
 
-    json_string = output.download_as_string()
+    json_string = output.download_as_bytes().decode("utf-8")
     response = json.loads(json_string)
 
     # The actual response for the first page of the input file.

Original file line number	Diff line number	Diff line change
`@@ -81,7 +81,7 @@ def quickstart(project_id, region, cluster_name, job_file_path):`
`81`	`81`	`storage.Client()`
`82`	`82`	`.get_bucket(matches.group(1))`
`83`	`83`	`.blob(f"{matches.group(2)}.000000000")`
`84`		`- .download_as_string()`
	`84`	`+ .download_as_bytes().decode("utf-8")`
`85`	`85`	`)`
`86`	`86`
`87`	`87`	`print(f"Job finished successfully: {output}")`
Original file line number	Diff line number	Diff line change
`@@ -63,7 +63,7 @@ def submit_job(project_id, region, cluster_name):`
`63`	`63`	`storage.Client()`
`64`	`64`	`.get_bucket(matches.group(1))`
`65`	`65`	`.blob(f"{matches.group(2)}.000000000")`
`66`		`- .download_as_string()`
	`66`	`+ .download_as_bytes().decode("utf-8")`
`67`	`67`	`)`
`68`	`68`
`69`	`69`	`print(f"Job finished successfully: {output}")`
Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,7 @@ def download_output(project, cluster_id, output_bucket, job_id):`
`74`	`74`	`output_blob = "google-cloud-dataproc-metainfo/{}/jobs/{}/driveroutput.000000000".format(`
`75`	`75`	`cluster_id, job_id`
`76`	`76`	`)`
`77`		`- return bucket.blob(output_blob).download_as_string()`
	`77`	`+ return bucket.blob(output_blob).download_as_bytes().decode("utf-8")`
`78`	`78`
`79`	`79`
`80`	`80`	`# [START dataproc_create_cluster]`
`@@ -132,7 +132,7 @@ def quickstart(project_id, region, cluster_name, gcs_bucket, pyspark_file):`
`132`	`132`	`storage.Client()`
`133`	`133`	`.get_bucket(matches.group(1))`
`134`	`134`	`.blob(f"{matches.group(2)}.000000000")`
`135`		`- .download_as_string()`
	`135`	`+ .download_as_bytes().decode("utf-8")`
`136`	`136`	`)`
`137`	`137`
`138`	`138`	`print(f"Job finished successfully: {output}\r\n")`