fix(samples): Fix Typos in Batch process & get processor Samples (#420)

Author: holtskinner

batch_process_documents_processor_version_sample.py

@@ -17,7 +17,7 @@
 import re
 
 from google.api_core.client_options import ClientOptions
-from google.api_core.exceptions import RetryError
+from google.api_core.exceptions import InternalServerError, RetryError
 from google.cloud import documentai, storage
 
 # TODO(developer): Uncomment these variables before running the sample.
@@ -66,7 +66,8 @@ def batch_process_documents_processor_version(
     #
 
     # Cloud Storage URI for the Output Directory
-    destination_uri = f"{gcs_output_bucket}/{gcs_output_uri_prefix}/"
+    # This must end with a trailing forward slash `/`
+    destination_uri = f"{gcs_output_bucket}/{gcs_output_uri_prefix}"
 
     gcs_output_config = documentai.DocumentOutputConfig.GcsOutputConfig(
         gcs_uri=destination_uri, field_mask=field_mask
@@ -97,7 +98,7 @@ def batch_process_documents_processor_version(
         print(f"Waiting for operation {operation.operation.name} to complete...")
         operation.result(timeout=timeout)
     # Catch exception when operation doesn't finish before timeout
-    except (RetryError) as e:
+    except (RetryError, InternalServerError) as e:
         print(e.message)
 
     # NOTE: Can also use callbacks for asynchronous processing

batch_process_documents_processor_version_sample_test.py

@@ -27,7 +27,7 @@
 processor_version_id = "pretrained-form-parser-v1.0-2020-09-23"
 gcs_input_uri = "gs://cloud-samples-data/documentai/invoice.pdf"
 input_mime_type = "application/pdf"
-gcs_output_uri_prefix = uuid4()
+gcs_output_uri_prefix = f"{uuid4()}/"
 field_mask = "text,pages.pageNumber"
 BUCKET_NAME = f"document-ai-python-{uuid4()}"
 

batch_process_documents_sample.py

@@ -17,7 +17,7 @@
 import re
 
 from google.api_core.client_options import ClientOptions
-from google.api_core.exceptions import RetryError
+from google.api_core.exceptions import InternalServerError, RetryError
 from google.cloud import documentai, storage
 
 # TODO(developer): Uncomment these variables before running the sample.
@@ -64,7 +64,8 @@ def batch_process_documents(
     #
 
     # Cloud Storage URI for the Output Directory
-    destination_uri = f"{gcs_output_bucket}/{gcs_output_uri_prefix}/"
+    # This must end with a trailing forward slash `/`
+    destination_uri = f"{gcs_output_bucket}/{gcs_output_uri_prefix}"
 
     gcs_output_config = documentai.DocumentOutputConfig.GcsOutputConfig(
         gcs_uri=destination_uri, field_mask=field_mask
@@ -93,7 +94,7 @@ def batch_process_documents(
         print(f"Waiting for operation {operation.operation.name} to complete...")
         operation.result(timeout=timeout)
     # Catch exception when operation doesn't finish before timeout
-    except (RetryError) as e:
+    except (RetryError, InternalServerError) as e:
         print(e.message)
 
     # NOTE: Can also use callbacks for asynchronous processing

batch_process_documents_sample_bad_input_test.py

@@ -16,6 +16,7 @@
 import os
 from uuid import uuid4
 
+from google.api_core.exceptions import InternalServerError, RetryError
 from samples.snippets import batch_process_documents_sample
 
 location = "us"
@@ -25,7 +26,7 @@
 input_mime_type = "application/pdf"
 # following bucket contains .csv file which will cause the sample to fail.
 gcs_output_full_uri_with_wrong_type = "gs://documentai-beta-samples"
-gcs_output_uri_prefix = "test"
+gcs_output_uri_prefix = "test/"
 BUCKET_NAME = f"document-ai-python-{uuid4()}"
 
 
@@ -41,7 +42,8 @@ def test_batch_process_documents_with_bad_input(capsys):
             gcs_output_uri_prefix=gcs_output_uri_prefix,
             timeout=450,
         )
+    except ValueError:
         out, _ = capsys.readouterr()
-        assert "Failed" in out
-    except Exception as e:
-        assert "Failed" in e.message
+        assert "Failed" in out or "error" in out
+    except (InternalServerError, RetryError) as e:
+        assert "error" in e.message

batch_process_documents_sample_test.py

@@ -26,7 +26,7 @@
 processor_id = "90484cfdedb024f6"
 gcs_input_uri = "gs://cloud-samples-data/documentai/invoice.pdf"
 input_mime_type = "application/pdf"
-gcs_output_uri_prefix = uuid4()
+gcs_output_uri_prefix = f"{uuid4()}/"
 field_mask = "text,pages.pageNumber"
 BUCKET_NAME = f"document-ai-python-{uuid4()}"
 

get_processor_sample.py

@@ -31,7 +31,7 @@ def get_processor_sample(project_id: str, location: str, processor_id: str):
     client = documentai.DocumentProcessorServiceClient(client_options=opts)
 
     # The full resource name of the processor, e.g.:
-    # projects/project_id/locations/location/processor/processor_id
+    # projects/{project_id}/locations/{location}/processors/{processor_id}
     name = client.processor_path(project_id, location, processor_id)
 
     # Make GetProcessor request