Consistency related changes in form recognizer (#11467)

* page range + form field page number

* us receipt

* RecognizedReceipt

* Update sdk/formrecognizer/azure-ai-formrecognizer/CHANGELOG.md

* async

* comments

sdk/formrecognizer/azure-ai-formrecognizer/CHANGELOG.md

@@ -10,13 +10,16 @@
 - Removed `get_form_training_client` from `FormRecognizerClient`
 - Added `get_form_recognizer_client` to `FormTrainingClient`
 - A `HttpResponseError` is now raised if a model with `status=="invalid"` is returned from the `begin_train_model()` or `train_model()` methods
+- `PageRange` is renamed to `FormPageRange`
+- `FormField` does not have a page_number.
+- `begin_recognize_receipts` APIs now return `RecognizedReceipt` instead of `USReceipt`
+- `USReceiptType` is renamed to `ReceiptType`
 
 **New features**
 
 - Authentication using `azure-identity` credentials now supported
   - see the [Azure Identity documentation](https://github.com/Azure/azure-sdk-for-python/blob/master/sdk/identity/azure-identity/README.md) for more information
 
-
 ## 1.0.0b2 (2020-05-06)
 
 **Fixes and improvements**

sdk/formrecognizer/azure-ai-formrecognizer/README.md

@@ -123,7 +123,7 @@ See the full details regarding [authentication][cognitive_authentication] of cog
 
  - Recognizing form fields and content using custom models trained to recognize your custom forms. These values are returned in a collection of `RecognizedForm` objects.
  - Recognizing form content, including tables, lines and words, without the need to train a model. Form content is returned in a collection of `FormPage` objects.
- - Recognizing common fields from US receipts, using a pre-trained receipt model on the Form Recognizer service. These fields and meta-data are returned in a collection of `USReceipt` objects.
+ - Recognizing common fields from US receipts, using a pre-trained receipt model on the Form Recognizer service. These fields and meta-data are returned in a collection of `RecognizedReceipt` objects.
 
 ### FormTrainingClient
 `FormTrainingClient` provides operations for:

sdk/formrecognizer/azure-ai-formrecognizer/azure/ai/formrecognizer/__init__.py

@@ -15,7 +15,7 @@
     CustomFormModelStatus,
     FormContentType,
     USReceipt,
-    USReceiptType,
+    ReceiptType,
     USReceiptItem,
     FormTable,
     FormTableCell,
@@ -24,7 +24,7 @@
     CustomFormModelInfo,
     AccountProperties,
     Point,
-    PageRange,
+    FormPageRange,
     RecognizedForm,
     FormField,
     FieldText,
@@ -46,7 +46,7 @@
     'FormContentType',
     'FormContent',
     'USReceipt',
-    'USReceiptType',
+    'ReceiptType',
     'USReceiptItem',
     'FormTable',
     'FormTableCell',
@@ -55,7 +55,7 @@
     'CustomFormModelInfo',
     'AccountProperties',
     'Point',
-    'PageRange',
+    'FormPageRange',
     'RecognizedForm',
     'FormField',
     'FieldText',

sdk/formrecognizer/azure-ai-formrecognizer/azure/ai/formrecognizer/_form_recognizer_client.py

@@ -94,8 +94,8 @@ def begin_recognize_receipts(self, stream, **kwargs):
         :keyword int polling_interval: Waiting time between two polls for LRO operations
             if no Retry-After header is present. Defaults to 5 seconds.
         :return: An instance of an LROPoller. Call `result()` on the poller
-            object to return a list[:class:`~azure.ai.formrecognizer.USReceipt`].
-        :rtype: ~azure.core.polling.LROPoller[list[~azure.ai.formrecognizer.USReceipt]]
+            object to return a list[:class:`~azure.ai.formrecognizer.RecognizedReceipt`].
+        :rtype: ~azure.core.polling.LROPoller[list[~azure.ai.formrecognizer.RecognizedReceipt]]
         :raises ~azure.core.exceptions.HttpResponseError:
 
         .. admonition:: Example:
@@ -142,8 +142,8 @@ def begin_recognize_receipts_from_url(self, url, **kwargs):
         :keyword int polling_interval: Waiting time between two polls for LRO operations
             if no Retry-After header is present. Defaults to 5 seconds.
         :return: An instance of an LROPoller. Call `result()` on the poller
-            object to return a list[:class:`~azure.ai.formrecognizer.USReceipt`].
-        :rtype: ~azure.core.polling.LROPoller[list[~azure.ai.formrecognizer.USReceipt]]
+            object to return a list[:class:`~azure.ai.formrecognizer.RecognizedReceipt`].
+        :rtype: ~azure.core.polling.LROPoller[list[~azure.ai.formrecognizer.RecognizedReceipt]]
         :raises ~azure.core.exceptions.HttpResponseError:
 
         .. admonition:: Example:

sdk/formrecognizer/azure-ai-formrecognizer/azure/ai/formrecognizer/_models.py

@@ -120,17 +120,17 @@ def __new__(cls, x, y):
         return super(Point, cls).__new__(cls, x, y)
 
 
-class PageRange(namedtuple("PageRange", "first_page last_page")):
-    """The 1-based page range of the document.
+class FormPageRange(namedtuple("FormPageRange", "first_page last_page")):
+    """The 1-based page range of the form.
 
-    :ivar int first_page: The first page number of the document.
-    :ivar int last_page: The last page number of the document.
+    :ivar int first_page: The first page number of the form.
+    :ivar int last_page: The last page number of the form.
     """
 
     __slots__ = ()
 
     def __new__(cls, first_page, last_page):
-        return super(PageRange, cls).__new__(cls, first_page, last_page)
+        return super(FormPageRange, cls).__new__(cls, first_page, last_page)
 
 
 class FormContent(object):
@@ -162,7 +162,7 @@ class RecognizedForm(object):
         this is the training-time label of the field. For models trained
         without labels, a unique name is generated for each field.
     :vartype fields: dict[str, ~azure.ai.formrecognizer.FormField]
-    :ivar ~azure.ai.formrecognizer.PageRange page_range:
+    :ivar ~azure.ai.formrecognizer.FormPageRange page_range:
         The first and last page of the input form.
     :ivar list[~azure.ai.formrecognizer.FormPage] pages:
         A list of pages recognized from the input document. Contains lines,
@@ -179,8 +179,39 @@ def __repr__(self):
             self.form_type, repr(self.fields), repr(self.page_range), repr(self.pages)
         )[:1024]
 
+class RecognizedReceipt(RecognizedForm):
+    """Represents a receipt that has been recognized by a trained model.
 
-class USReceipt(object):  # pylint: disable=too-many-instance-attributes
+    :ivar str form_type:
+        The type of form the model identified the submitted form to be.
+    :ivar fields:
+        A dictionary of the fields found on the form. The fields dictionary
+        keys are the `name` of the field. For models trained with labels,
+        this is the training-time label of the field. For models trained
+        without labels, a unique name is generated for each field.
+    :vartype fields: dict[str, ~azure.ai.formrecognizer.FormField]
+    :ivar ~azure.ai.formrecognizer.FormPageRange page_range:
+        The first and last page of the input form.
+    :ivar list[~azure.ai.formrecognizer.FormPage] pages:
+        A list of pages recognized from the input document. Contains lines,
+        words, tables and page metadata.
+    :ivar ~azure.ai.formrecognizer.ReceiptType receipt_type:
+        The reciept type and confidence.
+    :ivar str receipt_locale: Defaults to "en-US".
+    """
+    def __init__(self, **kwargs):
+        super(RecognizedReceipt, self).__init__(**kwargs)
+        self.receipt_type = kwargs.get("receipt_type", None)
+        self.receipt_locale = kwargs.get("receipt_locale", "en-US")
+
+    def __repr__(self):
+        return "RecognizedReceipt(form_type={}, fields={}, page_range={}, pages={}, " \
+            "receipt_type={}, receipt_locale={})".format(
+            self.form_type, repr(self.fields), repr(self.page_range), repr(self.pages),
+            repr(self.receipt_type), self.receipt_locale
+        )[:1024]
+
+class USReceipt(RecognizedReceipt):  # pylint: disable=too-many-instance-attributes
     """Extracted fields found on the US sales receipt. Provides
     attributes for accessing common fields present in US sales receipts.
 
@@ -190,8 +221,6 @@ class USReceipt(object):  # pylint: disable=too-many-instance-attributes
         The name of the merchant.
     :ivar ~azure.ai.formrecognizer.FormField merchant_phone_number:
         The phone number associated with the merchant.
-    :ivar ~azure.ai.formrecognizer.USReceiptType receipt_type:
-        The reciept type and confidence.
     :ivar list[~azure.ai.formrecognizer.USReceiptItem] receipt_items:
         The purchased items found on the receipt.
     :ivar ~azure.ai.formrecognizer.FormField subtotal:
@@ -209,33 +238,27 @@ class USReceipt(object):  # pylint: disable=too-many-instance-attributes
     :ivar fields:
         A dictionary of the fields found on the receipt.
     :vartype fields: dict[str, ~azure.ai.formrecognizer.FormField]
-    :ivar ~azure.ai.formrecognizer.PageRange page_range:
+    :ivar ~azure.ai.formrecognizer.FormPageRange page_range:
         The first and last page of the input receipt.
     :ivar list[~azure.ai.formrecognizer.FormPage] pages:
         Contains page metadata such as page width, length, text angle, unit.
         If `include_text_content=True` is passed, contains a list
         of extracted text lines for each page in the input document.
     :ivar str form_type: The type of form.
-    :ivar str receipt_locale: Defaults to "en-US".
     """
 
     def __init__(self, **kwargs):
+        super(USReceipt, self).__init__(**kwargs)
         self.merchant_address = kwargs.get("merchant_address", None)
         self.merchant_name = kwargs.get("merchant_name", None)
         self.merchant_phone_number = kwargs.get("merchant_phone_number", None)
-        self.receipt_type = kwargs.get("receipt_type", None)
         self.receipt_items = kwargs.get("receipt_items", None)
         self.subtotal = kwargs.get("subtotal", None)
         self.tax = kwargs.get("tax", None)
         self.tip = kwargs.get("tip", None)
         self.total = kwargs.get("total", None)
         self.transaction_date = kwargs.get("transaction_date", None)
         self.transaction_time = kwargs.get("transaction_time", None)
-        self.fields = kwargs.get("fields", None)
-        self.page_range = kwargs.get("page_range", None)
-        self.pages = kwargs.get("pages", None)
-        self.form_type = kwargs.get("form_type", None)
-        self.receipt_locale = kwargs.get("receipt_locale", "en-US")
 
     def __repr__(self):
         return "USReceipt(merchant_address={}, merchant_name={}, merchant_phone_number={}, " \
@@ -264,8 +287,6 @@ class FormField(object):
         :class:`~azure.ai.formrecognizer.FormField`, or list[:class:`~azure.ai.formrecognizer.FormField`]
     :ivar float confidence:
         Measures the degree of certainty of the recognition result. Value is between [0.0, 1.0].
-    :ivar int page_number:
-        The 1-based number of the page in which this content is present.
     """
 
     def __init__(self, **kwargs):
@@ -274,7 +295,6 @@ def __init__(self, **kwargs):
         self.name = kwargs.get("name", None)
         self.value = kwargs.get("value", None)
         self.confidence = kwargs.get("confidence", None)
-        self.page_number = kwargs.get("page_number", None)
 
     @classmethod
     def _from_generated(cls, field, value, read_result):
@@ -284,7 +304,6 @@ def _from_generated(cls, field, value, read_result):
             value=get_field_value(field, value, read_result),
             name=field,
             confidence=adjust_confidence(value.confidence) if value else None,
-            page_number=value.page if value else None,
         )
 
 
@@ -296,12 +315,11 @@ def _from_generated_unlabeled(cls, field, idx, page, read_result):
             value=field.value.text,
             name="field-" + str(idx),
             confidence=adjust_confidence(field.confidence),
-            page_number=page,
         )
 
     def __repr__(self):
-        return "FormField(label_data={}, value_data={}, name={}, value={}, confidence={}, page_number={})".format(
-            repr(self.label_data), repr(self.value_data), self.name, repr(self.value), self.confidence, self.page_number
+        return "FormField(label_data={}, value_data={}, name={}, value={}, confidence={})".format(
+            repr(self.label_data), repr(self.value_data), self.name, repr(self.value), self.confidence
         )[:1024]
 
 
@@ -495,7 +513,7 @@ def __repr__(self):
         )[:1024]
 
 
-class USReceiptType(object):
+class ReceiptType(object):
     """The type of the analyzed US receipt and the confidence
     value of that type.
 
@@ -516,7 +534,7 @@ def _from_generated(cls, item):
             confidence=adjust_confidence(item.confidence)) if item else None
 
     def __repr__(self):
-        return "USReceiptType(type={}, confidence={})".format(self.type, self.confidence)[:1024]
+        return "ReceiptType(type={}, confidence={})".format(self.type, self.confidence)[:1024]
 
 
 class USReceiptItem(object):

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

@@ -8,14 +8,14 @@
 
 from ._models import (
     USReceipt,
-    USReceiptType,
+    ReceiptType,
     FormField,
     USReceiptItem,
     FormPage,
     FormLine,
     FormTable,
     FormTableCell,
-    PageRange,
+    FormPageRange,
     RecognizedForm
 )
 
@@ -29,7 +29,7 @@ def prepare_us_receipt(response):
     for page in document_result:
         if page.fields is None:
             receipt = USReceipt(
-                page_range=PageRange(first_page=page.page_range[0], last_page=page.page_range[1]),
+                page_range=FormPageRange(first_page=page.page_range[0], last_page=page.page_range[1]),
                 pages=form_page[page.page_range[0]-1:page.page_range[1]],
                 form_type=page.doc_type,
             )
@@ -47,7 +47,7 @@ def prepare_us_receipt(response):
                 page.fields.get("MerchantPhoneNumber"),
                 read_result,
             ),
-            receipt_type=USReceiptType._from_generated(page.fields.get("ReceiptType")),
+            receipt_type=ReceiptType._from_generated(page.fields.get("ReceiptType")),
             receipt_items=USReceiptItem._from_generated(
                 page.fields.get("Items"), read_result
             ),
@@ -65,7 +65,7 @@ def prepare_us_receipt(response):
             transaction_time=FormField._from_generated(
                 "TransactionTime", page.fields.get("TransactionTime"), read_result
             ),
-            page_range=PageRange(
+            page_range=FormPageRange(
                 first_page=page.page_range[0], last_page=page.page_range[1]
             ),
             pages=form_page[page.page_range[0]-1:page.page_range[1]],
@@ -132,7 +132,7 @@ def prepare_unlabeled_result(response):
         if unlabeled_fields:
             unlabeled_fields = {field.name: field for field in unlabeled_fields}
         form = RecognizedForm(
-            page_range=PageRange(
+            page_range=FormPageRange(
                 first_page=page.page,
                 last_page=page.page
             ),
@@ -152,7 +152,7 @@ def prepare_labeled_result(response, model_id):
     result = []
     for doc in response.analyze_result.document_results:
         form = RecognizedForm(
-            page_range=PageRange(
+            page_range=FormPageRange(
                 first_page=doc.page_range[0],
                 last_page=doc.page_range[1]
             ),

sdk/formrecognizer/azure-ai-formrecognizer/azure/ai/formrecognizer/aio/_form_recognizer_client_async.py

@@ -29,7 +29,7 @@
     from azure.core.credentials import AzureKeyCredential
     from azure.core.credentials_async import AsyncTokenCredential
     from .._models import (
-        USReceipt,
+        RecognizedReceipt,
         FormPage,
         RecognizedForm
     )
@@ -91,7 +91,7 @@ async def recognize_receipts(
             self,
             stream: Union[bytes, IO[bytes]],
             **kwargs: Any
-    ) -> List["USReceipt"]:
+    ) -> List["RecognizedReceipt"]:
         """Extract field text and semantic values from a given US sales receipt.
         The input document must be of one of the supported content types - 'application/pdf',
         'image/jpeg', 'image/png' or 'image/tiff'.
@@ -106,8 +106,8 @@ async def recognize_receipts(
             see :class:`~azure.ai.formrecognizer.FormContentType`.
         :keyword int polling_interval: Waiting time between two polls for LRO operations
             if no Retry-After header is present. Defaults to 5 seconds.
-        :return: A list of USReceipt.
-        :rtype: list[~azure.ai.formrecognizer.USReceipt]
+        :return: A list of RecognizedReceipt.
+        :rtype: list[~azure.ai.formrecognizer.RecognizedReceipt]
         :raises ~azure.core.exceptions.HttpResponseError:
 
         .. admonition:: Example:
@@ -145,7 +145,7 @@ async def recognize_receipts_from_url(
             self,
             url: str,
             **kwargs: Any
-    ) -> List["USReceipt"]:
+    ) -> List["RecognizedReceipt"]:
         """Extract field text and semantic values from a given US sales receipt.
         The input document must be the location (Url) of the receipt to be analyzed.
 
@@ -156,8 +156,8 @@ async def recognize_receipts_from_url(
             Whether or not to include text elements such as lines and words in addition to form fields.
         :keyword int polling_interval: Waiting time between two polls for LRO operations
             if no Retry-After header is present. Defaults to 5 seconds.
-        :return: A list of USReceipt.
-        :rtype: list[~azure.ai.formrecognizer.USReceipt]
+        :return: A list of RecognizedReceipt.
+        :rtype: list[~azure.ai.formrecognizer.RecognizedReceipt]
         :raises ~azure.core.exceptions.HttpResponseError:
 
         .. admonition:: Example: