add samples for converting to and from dictionaries

sdk/formrecognizer/azure-ai-formrecognizer/samples/v3.2-beta/async_samples/sample_convert_to_and_from_dict_async.py

@@ -0,0 +1,128 @@
+# coding: utf-8
+
+# -------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License. See License.txt in the project root for
+# license information.
+# --------------------------------------------------------------------------
+
+"""
+FILE: sample_convert_to_and_from_dict_async.py
+
+DESCRIPTION:
+    This sample demonstrates how to convert models returned from an analyze operation
+    to and from a dictionary. The dictionary in this sample is then converted to a
+    JSON file, then the same dictionary is converted back to its original model.
+
+USAGE:
+    python sample_convert_to_and_from_dict_async.py
+
+    Set the environment variables with your own values before running the sample:
+    1) AZURE_FORM_RECOGNIZER_ENDPOINT - the endpoint to your Cognitive Services resource.
+    2) AZURE_FORM_RECOGNIZER_KEY - your Form Recognizer API key
+"""
+
+import os
+import json
+import asyncio
+
+async def convert_to_and_from_dict_async():
+    path_to_sample_documents = os.path.abspath(
+        os.path.join(
+            os.path.abspath(__file__),
+            "..",
+            "..",
+            "..",
+            "./sample_forms/forms/Form_1.jpg",
+        )
+    )
+
+    from azure.core.credentials import AzureKeyCredential
+    from azure.ai.formrecognizer.aio import DocumentAnalysisClient
+    from azure.ai.formrecognizer import AnalyzeResult
+
+    endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
+    key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
+
+    document_analysis_client = DocumentAnalysisClient(
+        endpoint=endpoint, credential=AzureKeyCredential(key)
+    )
+    async with document_analysis_client:
+        with open(path_to_sample_documents, "rb") as f:
+            poller = await document_analysis_client.begin_analyze_document(
+                "prebuilt-document", document=f
+            )
+        result = await poller.result()
+
+    # connvert the received model to a dictionary
+    d = result.to_dict()
+
+    # save the dictionary as a JSON content in a JSON file
+    with open('data.json', 'w') as f:
+        json.dump(d, f)
+
+    # convert the dictionary back to the original model
+    model = AnalyzeResult.from_dict(d)
+
+    # use the model as normal
+    for style in model.styles:
+        if style.is_handwritten:
+            print("Document contains handwritten content: ")
+            print(",".join([model.content[span.offset:span.offset + span.length] for span in style.spans]))
+
+    print("----Key-value pairs found in document----")
+    for kv_pair in model.key_value_pairs:
+        if kv_pair.key:
+            print(
+                    "Key '{}' found within '{}' bounding regions".format(
+                        kv_pair.key.content,
+                        kv_pair.key.bounding_regions,
+                    )
+                )
+        if kv_pair.value:
+            print(
+                    "Value '{}' found within '{}' bounding regions\n".format(
+                        kv_pair.value.content,
+                        kv_pair.value.bounding_regions,
+                    )
+                )
+
+    print("----Entities found in document----")
+    for entity in model.entities:
+        print("Entity of category '{}' with sub-category '{}'".format(entity.category, entity.sub_category))
+        print("...has content '{}'".format(entity.content))
+        print("...within '{}' bounding regions".format(entity.bounding_regions))
+        print("...with confidence {}\n".format(entity.confidence))
+
+    for table_idx, table in enumerate(model.tables):
+        print(
+            "Table # {} has {} rows and {} columns".format(
+                table_idx, table.row_count, table.column_count
+            )
+        )
+        for region in table.bounding_regions:
+            print(
+                "Table # {} location on page: {} is on {}".format(
+                    table_idx,
+                    region.page_number,
+                    region.bounding_box,
+                )
+            )
+        for cell in table.cells:
+            print(
+                "...Cell[{}][{}] has content '{}'".format(
+                    cell.row_index,
+                    cell.column_index,
+                    cell.content,
+                )
+            )
+    print("----------------------------------------")
+
+
+async def main():
+    await convert_to_and_from_dict_async()
+
+
+if __name__ == '__main__':
+    loop = asyncio.get_event_loop()
+    loop.run_until_complete(main())

sdk/formrecognizer/azure-ai-formrecognizer/samples/v3.2-beta/sample_convert_to_and_from_dict.py

@@ -0,0 +1,119 @@
+# coding: utf-8
+
+# -------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License. See License.txt in the project root for
+# license information.
+# --------------------------------------------------------------------------
+
+"""
+FILE: sample_convert_to_and_from_dict.py
+
+DESCRIPTION:
+    This sample demonstrates how to convert models returned from an analyze operation
+    to and from a dictionary. The dictionary in this sample is then converted to a
+    JSON file, then the same dictionary is converted back to its original model.
+
+USAGE:
+    python sample_convert_to_and_from_dict.py
+
+    Set the environment variables with your own values before running the sample:
+    1) AZURE_FORM_RECOGNIZER_ENDPOINT - the endpoint to your Cognitive Services resource.
+    2) AZURE_FORM_RECOGNIZER_KEY - your Form Recognizer API key
+"""
+
+import os
+import json
+
+def convert_to_and_from_dict():
+    path_to_sample_documents = os.path.abspath(
+        os.path.join(
+            os.path.abspath(__file__),
+            "..",
+            "..",
+            "./sample_forms/forms/Form_1.jpg",
+        )
+    )
+
+    from azure.core.credentials import AzureKeyCredential
+    from azure.ai.formrecognizer import DocumentAnalysisClient, AnalyzeResult
+
+    endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
+    key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
+
+    document_analysis_client = DocumentAnalysisClient(
+        endpoint=endpoint, credential=AzureKeyCredential(key)
+    )
+    with open(path_to_sample_documents, "rb") as f:
+        poller = document_analysis_client.begin_analyze_document(
+            "prebuilt-document", document=f
+        )
+    result = poller.result()
+
+    # connvert the received model to a dictionary
+    d = result.to_dict()
+
+    # save the dictionary as a JSON content in a JSON file
+    with open('data.json', 'w') as f:
+        json.dump(d, f)
+
+    # convert the dictionary back to the original model
+    model = AnalyzeResult.from_dict(d)
+
+    # use the model as normal
+    for style in model.styles:
+        if style.is_handwritten:
+            print("Document contains handwritten content: ")
+            print(",".join([model.content[span.offset:span.offset + span.length] for span in style.spans]))
+
+    print("----Key-value pairs found in document----")
+    for kv_pair in model.key_value_pairs:
+        if kv_pair.key:
+            print(
+                    "Key '{}' found within '{}' bounding regions".format(
+                        kv_pair.key.content,
+                        kv_pair.key.bounding_regions,
+                    )
+                )
+        if kv_pair.value:
+            print(
+                    "Value '{}' found within '{}' bounding regions\n".format(
+                        kv_pair.value.content,
+                        kv_pair.value.bounding_regions,
+                    )
+                )
+
+    print("----Entities found in document----")
+    for entity in model.entities:
+        print("Entity of category '{}' with sub-category '{}'".format(entity.category, entity.sub_category))
+        print("...has content '{}'".format(entity.content))
+        print("...within '{}' bounding regions".format(entity.bounding_regions))
+        print("...with confidence {}\n".format(entity.confidence))
+
+    for table_idx, table in enumerate(model.tables):
+        print(
+            "Table # {} has {} rows and {} columns".format(
+                table_idx, table.row_count, table.column_count
+            )
+        )
+        for region in table.bounding_regions:
+            print(
+                "Table # {} location on page: {} is on {}".format(
+                    table_idx,
+                    region.page_number,
+                    region.bounding_box,
+                )
+            )
+        for cell in table.cells:
+            print(
+                "...Cell[{}][{}] has content '{}'".format(
+                    cell.row_index,
+                    cell.column_index,
+                    cell.content,
+                )
+            )
+    print("----------------------------------------")
+
+
+if __name__ == "__main__":
+    convert_to_and_from_dict()