GoogleCloudPlatform · nicain · Sep 30, 2020 · Oct 19, 2020 · Oct 21, 2020 · Nov 11, 2020
@@ -43,6 +43,7 @@
 /dataproc/**/*                         @GoogleCloudPlatform/python-samples-reviewers
 /datastore/**/*                        @GoogleCloudPlatform/cloud-native-db-dpes @GoogleCloudPlatform/python-samples-reviewers
 /dns/**/*                              @GoogleCloudPlatform/python-samples-reviewers
+/documentai/**/*                       @GoogleCloudPlatform/dee-data-ai  @GoogleCloudPlatform/python-samples-reviewers
 /endpoints/**/*                        @GoogleCloudPlatform/python-samples-reviewers
 /eventarc/**/*                         @GoogleCloudPlatform/aap-dpes  @GoogleCloudPlatform/python-samples-reviewers
 /error_reporting/**/*                  @GoogleCloudPlatform/python-samples-reviewers

@@ -13,6 +13,10 @@
 # limitations under the License.
 
 assign_issues_by:
+- labels:
+  - 'api: documentai'
+  to:
+  - GoogleCloudPlatform/dee-data-ai
 - labels:
   - 'api: appengine'
   - 'api: eventarc'
@@ -188,6 +192,7 @@ assign_prs_by:
   to:
   - GoogleCloudPlatform/infra-db-dpes
 - labels:
+  - 'api: documentai'
   - 'api: retail'
   to: 
   - GoogleCloudPlatform/dee-data-ai

@@ -0,0 +1 @@
+See https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/AUTHORING_GUIDE.md
@@ -0,0 +1 @@
+See https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/CONTRIBUTING.md
@@ -0,0 +1,163 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+# [START documentai_batch_process_documents_processor_version]
+import re
+
+from google.api_core.client_options import ClientOptions
+from google.api_core.exceptions import InternalServerError
+from google.api_core.exceptions import RetryError
+from google.cloud import documentai
+from google.cloud import storage
+
+# TODO(developer): Uncomment these variables before running the sample.
+# project_id = 'YOUR_PROJECT_ID'
+# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
+# processor_id = 'YOUR_PROCESSOR_ID' # Example: aeb8cea219b7c272
+# processor_version_id = "YOUR_PROCESSOR_VERSION_ID" # Example: pretrained-ocr-v1.0-2020-09-23
+# gcs_input_uri = "YOUR_INPUT_URI" # Format: gs://bucket/directory/file.pdf
+# input_mime_type = "application/pdf"
+# gcs_output_bucket = "YOUR_OUTPUT_BUCKET_NAME" # Format: gs://bucket
+# gcs_output_uri_prefix = "YOUR_OUTPUT_URI_PREFIX" # Format: directory/subdirectory/
+# field_mask = "text,entities,pages.pageNumber"  # Optional. The fields to return in the Document object.
+
+
+def batch_process_documents_processor_version(
+    project_id: str,
+    location: str,
+    processor_id: str,
+    processor_version_id: str,
+    gcs_input_uri: str,
+    input_mime_type: str,
+    gcs_output_bucket: str,
+    gcs_output_uri_prefix: str,
+    field_mask: str = None,
+    timeout: int = 400,
+):
+
+    # You must set the api_endpoint if you use a location other than 'us'.
+    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
+
+    client = documentai.DocumentProcessorServiceClient(client_options=opts)
+
+    gcs_document = documentai.GcsDocument(
+        gcs_uri=gcs_input_uri, mime_type=input_mime_type
+    )
+
+    # Load GCS Input URI into a List of document files
+    gcs_documents = documentai.GcsDocuments(documents=[gcs_document])
+    input_config = documentai.BatchDocumentsInputConfig(gcs_documents=gcs_documents)
+
+    # NOTE: Alternatively, specify a GCS URI Prefix to process an entire directory
+    #
+    # gcs_input_uri = "gs://bucket/directory/"
+    # gcs_prefix = documentai.GcsPrefix(gcs_uri_prefix=gcs_input_uri)
+    # input_config = documentai.BatchDocumentsInputConfig(gcs_prefix=gcs_prefix)
+    #
+
+    # Cloud Storage URI for the Output Directory
+    # 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
+    )
+
+    # Where to write results
+    output_config = documentai.DocumentOutputConfig(gcs_output_config=gcs_output_config)
+
+    # The full resource name of the processor version
+    # e.g. projects/{project_id}/locations/{location}/processors/{processor_id}/processorVersions/{processor_version_id}
+    name = client.processor_version_path(
+        project_id, location, processor_id, processor_version_id
+    )
+
+    request = documentai.BatchProcessRequest(
+        name=name,
+        input_documents=input_config,
+        document_output_config=output_config,
+    )
+
+    # BatchProcess returns a Long Running Operation (LRO)
+    operation = client.batch_process_documents(request)
+
+    # Continually polls the operation until it is complete.
+    # This could take some time for larger files
+    # Format: projects/PROJECT_NUMBER/locations/LOCATION/operations/OPERATION_ID
+    try:
+        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, InternalServerError) as e:
+        print(e.message)
+
+    # NOTE: Can also use callbacks for asynchronous processing
+    #
+    # def my_callback(future):
+    #   result = future.result()
+    #
+    # operation.add_done_callback(my_callback)
+
+    # Once the operation is complete,
+    # get output document information from operation metadata
+    metadata = documentai.BatchProcessMetadata(operation.metadata)
+
+    if metadata.state != documentai.BatchProcessMetadata.State.SUCCEEDED:
+        raise ValueError(f"Batch Process Failed: {metadata.state_message}")
+
+    storage_client = storage.Client()
+
+    print("Output files:")
+    # One process per Input Document
+    for process in metadata.individual_process_statuses:
+        # output_gcs_destination format: gs://BUCKET/PREFIX/OPERATION_NUMBER/INPUT_FILE_NUMBER/
+        # The Cloud Storage API requires the bucket name and URI prefix separately
+        matches = re.match(r"gs://(.*?)/(.*)", process.output_gcs_destination)
+        if not matches:
+            print(
+                "Could not parse output GCS destination:",
+                process.output_gcs_destination,
+            )
+            continue
+
+        output_bucket, output_prefix = matches.groups()
+
+        # Get List of Document Objects from the Output Bucket
+        output_blobs = storage_client.list_blobs(output_bucket, prefix=output_prefix)
+
+        # Document AI may output multiple JSON files per source file
+        for blob in output_blobs:
+            # Document AI should only output JSON files to GCS
+            if ".json" not in blob.name:
+                print(
+                    f"Skipping non-supported file: {blob.name} - Mimetype: {blob.content_type}"
+                )
+                continue
+
+            # Download JSON File as bytes object and convert to Document Object
+            print(f"Fetching {blob.name}")
+            document = documentai.Document.from_json(
+                blob.download_as_bytes(), ignore_unknown_fields=True
+            )
+
+            # For a full list of Document object attributes, please reference this page:
+            # https://cloud.google.com/python/docs/reference/documentai/latest/google.cloud.documentai_v1.types.Document
+
+            # Read the text recognition output from the processor
+            print("The document contains the following text:")
+            print(document.text)
+
+
+# [END documentai_batch_process_documents_processor_version]
@@ -0,0 +1,49 @@
+# Copyright 2020 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import os
+from uuid import uuid4
+
+from documentai.snippets import \
+    batch_process_documents_processor_version_sample
+
+location = "us"
+project_id = os.environ["GOOGLE_CLOUD_PROJECT"]
+processor_id = "90484cfdedb024f6"
+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_bucket = "gs://document-ai-python"
+gcs_output_uri_prefix = f"{uuid4()}/"
+field_mask = "text,pages.pageNumber"
+
+
+def test_batch_process_documents_processor_version(capsys):
+    batch_process_documents_processor_version_sample.batch_process_documents_processor_version(
+        project_id=project_id,
+        location=location,
+        processor_id=processor_id,
+        processor_version_id=processor_version_id,
+        gcs_input_uri=gcs_input_uri,
+        input_mime_type=input_mime_type,
+        gcs_output_bucket=gcs_output_bucket,
+        gcs_output_uri_prefix=gcs_output_uri_prefix,
+        field_mask=field_mask,
+    )
+    out, _ = capsys.readouterr()
+
+    assert "operation" in out
+    assert "Fetching" in out
+    assert "text:" in out
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		See https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/AUTHORING_GUIDE.md