[text analytics] Too many documents

sdk/textanalytics/azure-ai-textanalytics/azure/ai/textanalytics/_response_handlers.py

@@ -59,8 +59,27 @@ def order_results(response, combined):
 
 
 def prepare_result(func):
+    def _deal_with_too_many_documents(response, obj):
+        # special case for now if there are too many documents in the request
+        # they may change id to empty string, but currently it is "All"
+        too_many_documents_errors = [
+            error for error in obj.errors
+            if error.id == "All" and error.error.innererror.code == "InvalidDocumentBatch"
+        ]
+        if too_many_documents_errors:
+            too_many_documents_error = too_many_documents_errors[0]
+            response.status_code = 400
+            response.reason = "Bad Request"
+            raise HttpResponseError(
+                message="({}) {}".format(
+                    too_many_documents_error.error.innererror.code, too_many_documents_error.error.innererror.message
+                ),
+                response=response
+            )
+
     def wrapper(response, obj, response_headers):  # pylint: disable=unused-argument
         if obj.errors:
+            _deal_with_too_many_documents(response.http_response, obj)
             combined = obj.documents + obj.errors
             results = order_results(response, combined)
         else:

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_entities.test_too_many_documents.yaml

@@ -0,0 +1,49 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "One", "language": "en"}, {"id": "1",
+      "text": "Two", "language": "en"}, {"id": "2", "text": "Three", "language": "en"},
+      {"id": "3", "text": "Four", "language": "en"}, {"id": "4", "text": "Five", "language":
+      "en"}, {"id": "5", "text": "Six", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '295'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/1.0.0b5 Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+        Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/recognition/general?showStats=false
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[{"text":"One","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]},{"id":"1","entities":[{"text":"Two","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]},{"id":"2","entities":[{"text":"Three","category":"Quantity","subcategory":"Number","offset":0,"length":5,"confidenceScore":0.8}],"warnings":[]},{"id":"3","entities":[{"text":"Four","category":"Quantity","subcategory":"Number","offset":0,"length":4,"confidenceScore":0.8}],"warnings":[]},{"id":"4","entities":[{"text":"Five","category":"Quantity","subcategory":"Number","offset":0,"length":4,"confidenceScore":0.8}],"warnings":[]},{"id":"5","entities":[{"text":"Six","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]}],"errors":[{"id":"All","error":{"code":"InvalidArgument","message":"The
+        request contains a warning.","innererror":{"code":"InvalidDocumentBatch","message":"The
+        number of documents in the request have exceeded the data limitations. See
+        https://aka.ms/text-analytics-data-limits for additional information"}}}],"modelVersion":"2020-04-01"}'
+    headers:
+      apim-request-id:
+      - 3f938077-141a-48c0-a8dc-45158ca76ca6
+      content-type:
+      - application/json; charset=utf-8
+      csp-billing-usage:
+      - CognitiveServices.TextAnalytics.BatchScoring=6
+      date:
+      - Thu, 30 Apr 2020 18:38:28 GMT
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      transfer-encoding:
+      - chunked
+      x-content-type-options:
+      - nosniff
+      x-envoy-upstream-service-time:
+      - '87'
+    status:
+      code: 200
+      message: OK
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_entities_async.test_too_many_documents.yaml

@@ -0,0 +1,38 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "One", "language": "en"}, {"id": "1",
+      "text": "Two", "language": "en"}, {"id": "2", "text": "Three", "language": "en"},
+      {"id": "3", "text": "Four", "language": "en"}, {"id": "4", "text": "Five", "language":
+      "en"}, {"id": "5", "text": "Six", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json
+      Content-Length:
+      - '295'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/1.0.0b5 Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+        Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/recognition/general?showStats=false
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[{"text":"One","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]},{"id":"1","entities":[{"text":"Two","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]},{"id":"2","entities":[{"text":"Three","category":"Quantity","subcategory":"Number","offset":0,"length":5,"confidenceScore":0.8}],"warnings":[]},{"id":"3","entities":[{"text":"Four","category":"Quantity","subcategory":"Number","offset":0,"length":4,"confidenceScore":0.8}],"warnings":[]},{"id":"4","entities":[{"text":"Five","category":"Quantity","subcategory":"Number","offset":0,"length":4,"confidenceScore":0.8}],"warnings":[]},{"id":"5","entities":[{"text":"Six","category":"Quantity","subcategory":"Number","offset":0,"length":3,"confidenceScore":0.8}],"warnings":[]}],"errors":[{"id":"All","error":{"code":"InvalidArgument","message":"The
+        request contains a warning.","innererror":{"code":"InvalidDocumentBatch","message":"The
+        number of documents in the request have exceeded the data limitations. See
+        https://aka.ms/text-analytics-data-limits for additional information"}}}],"modelVersion":"2020-04-01"}'
+    headers:
+      apim-request-id: 1dd2fff9-8681-43db-a4a2-550d2ce86329
+      content-type: application/json; charset=utf-8
+      csp-billing-usage: CognitiveServices.TextAnalytics.BatchScoring=6
+      date: Thu, 30 Apr 2020 18:38:29 GMT
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      transfer-encoding: chunked
+      x-content-type-options: nosniff
+      x-envoy-upstream-service-time: '74'
+    status:
+      code: 200
+      message: OK
+    url: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/recognition/general?showStats=false
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_linked_entities.test_too_many_documents.yaml

@@ -0,0 +1,49 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "One", "language": "en"}, {"id": "1",
+      "text": "Two", "language": "en"}, {"id": "2", "text": "Three", "language": "en"},
+      {"id": "3", "text": "Four", "language": "en"}, {"id": "4", "text": "Five", "language":
+      "en"}, {"id": "5", "text": "Six", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '295'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/1.0.0b5 Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+        Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/linking?showStats=false
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[],"warnings":[]},{"id":"1","entities":[],"warnings":[]},{"id":"2","entities":[],"warnings":[]},{"id":"3","entities":[],"warnings":[]},{"id":"4","entities":[],"warnings":[]},{"id":"5","entities":[],"warnings":[]}],"errors":[{"id":"All","error":{"code":"InvalidArgument","message":"The
+        request contains a warning.","innererror":{"code":"InvalidDocumentBatch","message":"The
+        number of documents in the request have exceeded the data limitations. See
+        https://aka.ms/text-analytics-data-limits for additional information"}}}],"modelVersion":"2020-02-01"}'
+    headers:
+      apim-request-id:
+      - d66bc012-b3ed-44be-80d2-d837abc671dd
+      content-type:
+      - application/json; charset=utf-8
+      csp-billing-usage:
+      - CognitiveServices.TextAnalytics.BatchScoring=6
+      date:
+      - Thu, 30 Apr 2020 18:38:29 GMT
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      transfer-encoding:
+      - chunked
+      x-content-type-options:
+      - nosniff
+      x-envoy-upstream-service-time:
+      - '21'
+    status:
+      code: 200
+      message: OK
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/recordings/test_recognize_linked_entities_async.test_too_many_documents.yaml

@@ -0,0 +1,38 @@
+interactions:
+- request:
+    body: '{"documents": [{"id": "0", "text": "One", "language": "en"}, {"id": "1",
+      "text": "Two", "language": "en"}, {"id": "2", "text": "Three", "language": "en"},
+      {"id": "3", "text": "Four", "language": "en"}, {"id": "4", "text": "Five", "language":
+      "en"}, {"id": "5", "text": "Six", "language": "en"}]}'
+    headers:
+      Accept:
+      - application/json
+      Content-Length:
+      - '295'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - azsdk-python-ai-textanalytics/1.0.0b5 Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+        Python/3.7.7 (Darwin-17.7.0-x86_64-i386-64bit)
+    method: POST
+    uri: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/linking?showStats=false
+  response:
+    body:
+      string: '{"documents":[{"id":"0","entities":[],"warnings":[]},{"id":"1","entities":[],"warnings":[]},{"id":"2","entities":[],"warnings":[]},{"id":"3","entities":[],"warnings":[]},{"id":"4","entities":[],"warnings":[]},{"id":"5","entities":[],"warnings":[]}],"errors":[{"id":"All","error":{"code":"InvalidArgument","message":"The
+        request contains a warning.","innererror":{"code":"InvalidDocumentBatch","message":"The
+        number of documents in the request have exceeded the data limitations. See
+        https://aka.ms/text-analytics-data-limits for additional information"}}}],"modelVersion":"2020-02-01"}'
+    headers:
+      apim-request-id: da8df0dd-8966-4c46-808e-7850f5efd6ad
+      content-type: application/json; charset=utf-8
+      csp-billing-usage: CognitiveServices.TextAnalytics.BatchScoring=6
+      date: Thu, 30 Apr 2020 18:38:29 GMT
+      strict-transport-security: max-age=31536000; includeSubDomains; preload
+      transfer-encoding: chunked
+      x-content-type-options: nosniff
+      x-envoy-upstream-service-time: '32'
+    status:
+      code: 200
+      message: OK
+    url: https://westus2.ppe.cognitiveservices.azure.com/text/analytics/v3.0/entities/linking?showStats=false
+version: 1

sdk/textanalytics/azure-ai-textanalytics/tests/test_analyze_sentiment.py

@@ -123,6 +123,16 @@ def test_input_with_all_errors(self, client):
         self.assertTrue(response[1].is_error)
         self.assertTrue(response[2].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = client.analyze_sentiment(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer()
     def test_document_warnings(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_analyze_sentiment_async.py

@@ -139,6 +139,16 @@ async def test_input_with_all_errors(self, client):
         self.assertTrue(response[1].is_error)
         self.assertTrue(response[2].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    async def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = await client.analyze_sentiment(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     async def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_detect_language.py

@@ -129,6 +129,16 @@ def test_input_with_all_errors(self, client):
         for resp in response:
             self.assertTrue(resp.is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = client.detect_language(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_detect_language_async.py

@@ -142,6 +142,16 @@ async def test_input_with_all_errors(self, client):
         for resp in response:
             self.assertTrue(resp.is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    async def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = await client.detect_language(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     async def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_extract_key_phrases.py

@@ -91,6 +91,16 @@ def test_input_with_all_errors(self, client):
         self.assertTrue(response[0].is_error)
         self.assertTrue(response[1].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = client.extract_key_phrases(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_extract_key_phrases_async.py

@@ -106,6 +106,16 @@ async def test_input_with_all_errors(self, client):
         self.assertTrue(response[0].is_error)
         self.assertTrue(response[1].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    @pytest.mark.xfail
+    async def test_too_many_documents(self, client):
+        # marking as xfail since the service hasn't added this error to this endpoint
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = await client.extract_key_phrases(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     async def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_entities.py

@@ -105,6 +105,14 @@ def test_input_with_all_errors(self, client):
         self.assertTrue(response[1].is_error)
         self.assertTrue(response[2].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    def test_too_many_documents(self, client):
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = client.recognize_entities(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_entities_async.py

@@ -121,6 +121,14 @@ async def test_input_with_all_errors(self, client):
         self.assertTrue(response[1].is_error)
         self.assertTrue(response[2].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    async def test_too_many_documents(self, client):
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = await client.recognize_entities(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     async def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_linked_entities.py

@@ -101,6 +101,14 @@ def test_input_with_all_errors(self, client):
         self.assertTrue(response[0].is_error)
         self.assertTrue(response[1].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    def test_too_many_documents(self, client):
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = client.recognize_linked_entities(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     def test_empty_credential_class(self, client):

sdk/textanalytics/azure-ai-textanalytics/tests/test_recognize_linked_entities_async.py

@@ -122,6 +122,14 @@ async def test_input_with_all_errors(self, client):
         self.assertTrue(response[0].is_error)
         self.assertTrue(response[1].is_error)
 
+    @GlobalTextAnalyticsAccountPreparer()
+    @TextAnalyticsClientPreparer()
+    async def test_too_many_documents(self, client):
+        docs = ["One", "Two", "Three", "Four", "Five", "Six"]
+
+        with self.assertRaises(HttpResponseError):
+            response = await client.recognize_linked_entities(docs)
+
     @GlobalTextAnalyticsAccountPreparer()
     @TextAnalyticsClientPreparer(client_kwargs={"text_analytics_account_key": ""})
     async def test_empty_credential_class(self, client):