def test_document_analysis_none_model(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key):
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key))
with self.assertRaises(ValueError):
client.begin_analyze_document_from_url(
model=None, document_url="https://badurl.jpg")
def test_document_analysis_none_model(self, **kwargs):
formrecognizer_test_endpoint = kwargs.pop(
"formrecognizer_test_endpoint")
formrecognizer_test_api_key = kwargs.pop("formrecognizer_test_api_key")
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key))
with pytest.raises(ValueError):
client.begin_analyze_document_from_url(
model=None, document_url="https://badurl.jpg")
def test_polling_interval(self, formrecognizer_test_endpoint, formrecognizer_test_api_key):
client = DocumentAnalysisClient(formrecognizer_test_endpoint, AzureKeyCredential(formrecognizer_test_api_key), polling_interval=7)
self.assertEqual(client._client._config.polling_interval, 7)
poller = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg, polling_interval=6)
poller.wait()
self.assertEqual(poller._polling_method._timeout, 6)
poller2 = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg)
poller2.wait()
self.assertEqual(poller2._polling_method._timeout, 7) # goes back to client default
def test_document_analysis_empty_model_id(self,
formrecognizer_test_endpoint,
formrecognizer_test_api_key,
**kwargs):
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key))
with pytest.raises(ValueError):
client.begin_analyze_document_from_url(
model="", document_url="https://badurl.jpg")
def test_polling_interval(self, formrecognizer_test_endpoint, formrecognizer_test_api_key, **kwargs):
# this can be reverted to set_bodiless_matcher() after tests are re-recorded and don't contain these headers
set_custom_default_matcher(
compare_bodies=False, excluded_headers="Authorization,Content-Length,x-ms-client-request-id,x-ms-request-id"
)
client = DocumentAnalysisClient(formrecognizer_test_endpoint, AzureKeyCredential(formrecognizer_test_api_key), polling_interval=7)
assert client._client._config.polling_interval == 7
poller = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg, polling_interval=6)
poller.wait()
assert poller._polling_method._timeout == 6
poller2 = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg)
poller2.wait()
assert poller2._polling_method._timeout == 7 # goes back to client default
def test_active_directory_auth(self):
token = self.generate_oauth_token()
endpoint = self.get_oauth_endpoint()
client = DocumentAnalysisClient(endpoint, token)
poller = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg)
result = poller.result()
assert result is not None
def test_receipt_url_auth_bad_key(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key):
client = DocumentAnalysisClient(formrecognizer_test_endpoint,
AzureKeyCredential("xxxx"))
with self.assertRaises(ClientAuthenticationError):
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
def test_mock_quota_exceeded_403(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key):
response = mock.Mock(status_code=403,
headers={
"Retry-After": 186688,
"Content-Type": "application/json"
},
reason="Bad Request")
response.text = lambda encoding=None: json.dumps({
"error": {
"code":
"403",
"message":
"Out of call volume quota for FormRecognizer F0 pricing tier. "
"Please retry after 1 day. To increase your call volume switch to a paid tier."
}
})
response.content_type = "application/json"
transport = mock.Mock(send=lambda request, **kwargs: response)
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key),
transport=transport)
with pytest.raises(HttpResponseError) as e:
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
assert e.value.status_code == 403
assert e.value.error.message == 'Out of call volume quota for FormRecognizer F0 pricing tier. Please retry after 1 day. To increase your call volume switch to a paid tier.'
def test_receipt_url_auth_bad_key(self, formrecognizer_test_endpoint,
**kwargs):
set_bodiless_matcher()
client = DocumentAnalysisClient(formrecognizer_test_endpoint,
AzureKeyCredential("xxxx"))
with pytest.raises(ClientAuthenticationError):
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
def test_receipt_url_bad_endpoint(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key):
with self.assertRaises(ServiceRequestError):
client = DocumentAnalysisClient(
"http://notreal.azure.com",
AzureKeyCredential(formrecognizer_test_api_key))
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
def test_receipt_url_auth_bad_key(self, formrecognizer_test_endpoint, **kwargs):
# this can be reverted to set_bodiless_matcher() after tests are re-recorded and don't contain these headers
set_custom_default_matcher(
compare_bodies=False, excluded_headers="Authorization,Content-Length,x-ms-client-request-id,x-ms-request-id"
)
client = DocumentAnalysisClient(formrecognizer_test_endpoint, AzureKeyCredential("xxxx"))
with pytest.raises(ClientAuthenticationError):
poller = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg)
def test_receipt_url_bad_endpoint(self, formrecognizer_test_api_key, **kwargs):
# this can be reverted to set_bodiless_matcher() after tests are re-recorded and don't contain these headers
set_custom_default_matcher(
compare_bodies=False, excluded_headers="Authorization,Content-Length,x-ms-client-request-id,x-ms-request-id"
)
with pytest.raises(ServiceRequestError):
client = DocumentAnalysisClient("http://notreal.azure.com", AzureKeyCredential(formrecognizer_test_api_key))
poller = client.begin_analyze_document_from_url("prebuilt-receipt", self.receipt_url_jpg)
def test_receipt_url_bad_endpoint(self, formrecognizer_test_api_key,
**kwargs):
set_bodiless_matcher()
with pytest.raises(ServiceRequestError):
client = DocumentAnalysisClient(
"http://notreal.azure.com",
AzureKeyCredential(formrecognizer_test_api_key))
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
def test_polling_interval(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key, **kwargs):
set_bodiless_matcher()
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key),
polling_interval=7)
assert client._client._config.polling_interval == 7
poller = client.begin_analyze_document_from_url("prebuilt-receipt",
self.receipt_url_jpg,
polling_interval=6)
poller.wait()
assert poller._polling_method._timeout == 6
poller2 = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
poller2.wait()
assert poller2._polling_method._timeout == 7 # goes back to client default
def authentication_with_api_key_credential_document_analysis_client():
# [START create_da_client_with_key]
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient
endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
document_analysis_client = DocumentAnalysisClient(endpoint, AzureKeyCredential(key))
# [END create_da_client_with_key]
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", url
)
result = poller.result()
def analyze_document(endpoint, key, data):
recordId = data['recordId']
formUrl = data["formUrl"] + data["formSasToken"]
model = data["model"]
document_analysis_client = DocumentAnalysisClient(
endpoint=endpoint, credential=AzureKeyCredential(key))
poller = document_analysis_client.begin_analyze_document_from_url(
model, formUrl)
result = poller.result()
output_record = {}
if model == "prebuilt-layout":
output_record = {
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-document":
output_record = {
"kvp": get_key_value_pairs(result),
"entities": get_entities(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-receipt":
output_record = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-idDocument":
output_record = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-invoice":
output_record = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
else:
output_record = {
"kvp": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
return output_record
def authentication_with_azure_active_directory_document_analysis_client():
# [START create_da_client_with_aad]
"""DefaultAzureCredential will use the values from these environment
variables: AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET
"""
from azure.ai.formrecognizer import DocumentAnalysisClient
from azure.identity import DefaultAzureCredential
endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
credential = DefaultAzureCredential()
document_analysis_client = DocumentAnalysisClient(endpoint, credential)
# [END create_da_client_with_aad]
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-layout", url
)
result = poller.result()
def test_logging_info_dac_client(self, formrecognizer_test_endpoint,
formrecognizer_test_api_key):
client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(formrecognizer_test_api_key))
mock_handler = MockHandler()
logger = logging.getLogger("azure")
logger.addHandler(mock_handler)
logger.setLevel(logging.INFO)
poller = client.begin_analyze_document_from_url(
"prebuilt-receipt", self.receipt_url_jpg)
result = poller.result()
for message in mock_handler.messages:
if message.levelname == "INFO":
# not able to use json.loads here. At INFO level only API key should be REDACTED
if message.message.find("Ocp-Apim-Subscription-Key") != -1:
assert message.message.find("REDACTED") != -1
else:
assert message.message.find("REDACTED") == -1
class AnalyzeDocumentFromUrlRequestPreparation(PerfStressTest):
def __init__(self, arguments):
super().__init__(arguments)
self.document_jpg_url = "https://raw.githubusercontent.com/Azure/azure-sdk-for-python/main/sdk/formrecognizer/azure-ai-formrecognizer/tests/sample_forms/forms/Form_1.jpg"
# read test related env vars
formrecognizer_test_endpoint = os.environ[
"FORMRECOGNIZER_TEST_ENDPOINT"]
form_recognizer_account_key = os.environ["FORMRECOGNIZER_TEST_API_KEY"]
# assign the clients that will be used in the perf tests
self.service_client = DocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(form_recognizer_account_key))
self.async_service_client = AsyncDocumentAnalysisClient(
formrecognizer_test_endpoint,
AzureKeyCredential(form_recognizer_account_key))
async def close(self):
"""This is run after cleanup."""
await self.async_service_client.close()
self.service_client.close()
await super().close()
def run_sync(self):
"""The synchronous perf test."""
poller = self.service_client.begin_analyze_document_from_url(
"prebuilt-document", self.document_jpg_url)
assert poller
async def run_async(self):
"""The asynchronous perf test."""
poller = await self.async_service_client.begin_analyze_document_from_url(
"prebuilt-document", self.document_jpg_url)
assert poller
def analyze_document(endpoint, key, recordId, data):
try:
formUrl = data["formUrl"] + data["formSasToken"]
model = data["model"]
logging.info("Model: " + model)
document_analysis_client = DocumentAnalysisClient(
endpoint=endpoint, credential=AzureKeyCredential(key)
)
poller = document_analysis_client.begin_analyze_document_from_url(
model, formUrl)
result = poller.result()
logging.info("Result from Form Recognizer before formatting: " + str(result))
output_record = {}
output_record_data = {}
if model == "prebuilt-layout":
output_record_data = {
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-document":
output_record_data = {
"kvp": get_key_value_pairs(result),
"entities" : get_entities(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-receipt":
output_record_data = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-idDocument":
output_record_data = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
elif model == "prebuilt-invoice":
output_record_data = {
"fields": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
else:
output_record_data = {
"kvp": get_fields(result),
"tables": get_tables(result),
"pages": get_pages(result)
}
output_record = {
"recordId": recordId,
"data": output_record_data
}
except Exception as error:
output_record = {
"recordId": recordId,
"errors": [ { "message": "Error: " + str(error) } ]
}
logging.info("Output record: " + json.dumps(output_record, ensure_ascii=False, cls=DateTimeEncoder))
return output_record
def analyze_receipts_from_url():
# [START analyze_receipts_from_url]
from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer import DocumentAnalysisClient
endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
document_analysis_client = DocumentAnalysisClient(
endpoint=endpoint, credential=AzureKeyCredential(key)
)
url = "https://raw.githubusercontent.com/Azure/azure-sdk-for-python/main/sdk/formrecognizer/azure-ai-formrecognizer/tests/sample_forms/receipt/contoso-receipt.png"
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-receipt", document_url=url
)
receipts = poller.result()
for idx, receipt in enumerate(receipts.documents):
print("--------Recognizing receipt #{}--------".format(idx + 1))
print("Receipt type: {}".format(receipt.doc_type or "N/A"))
merchant_name = receipt.fields.get("MerchantName")
if merchant_name:
print(
"Merchant Name: {} has confidence: {}".format(
merchant_name.value, merchant_name.confidence
)
)
transaction_date = receipt.fields.get("TransactionDate")
if transaction_date:
print(
"Transaction Date: {} has confidence: {}".format(
transaction_date.value, transaction_date.confidence
)
)
if receipt.fields.get("Items"):
print("Receipt items:")
for idx, item in enumerate(receipt.fields.get("Items").value):
print("...Item #{}".format(idx + 1))
item_name = item.value.get("Name")
if item_name:
print(
"......Item Name: {} has confidence: {}".format(
item_name.value, item_name.confidence
)
)
item_quantity = item.value.get("Quantity")
if item_quantity:
print(
"......Item Quantity: {} has confidence: {}".format(
item_quantity.value, item_quantity.confidence
)
)
item_price = item.value.get("Price")
if item_price:
print(
"......Individual Item Price: {} has confidence: {}".format(
item_price.value, item_price.confidence
)
)
item_total_price = item.value.get("TotalPrice")
if item_total_price:
print(
"......Total Item Price: {} has confidence: {}".format(
item_total_price.value, item_total_price.confidence
)
)
subtotal = receipt.fields.get("Subtotal")
if subtotal:
print(
"Subtotal: {} has confidence: {}".format(
subtotal.value, subtotal.confidence
)
)
tax = receipt.fields.get("Tax")
if tax:
print("Tax: {} has confidence: {}".format(tax.value, tax.confidence))
tip = receipt.fields.get("Tip")
if tip:
print("Tip: {} has confidence: {}".format(tip.value, tip.confidence))
total = receipt.fields.get("Total")
if total:
print("Total: {} has confidence: {}".format(total.value, total.confidence))
print("--------------------------------------")