# Copyright (C) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See LICENSE in project root for information.
import sys
if sys.version >= '3':
basestring = str
from pyspark import SparkContext, SQLContext
from pyspark.sql import DataFrame
from pyspark.ml.param.shared import *
from pyspark import keyword_only
from pyspark.ml.util import JavaMLReadable, JavaMLWritable
from synapse.ml.core.platform import running_on_synapse_internal
from synapse.ml.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from synapse.ml.core.schema.Utils import *
from pyspark.ml.param import TypeConverters
from synapse.ml.core.schema.TypeConversionUtils import generateTypeConverter, complexTypeConverter
[docs]@inherit_doc
class AnalyzeDocument(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer):
"""
Args:
AADToken (object): AAD Token used for authentication
CustomAuthHeader (object): A Custom Value for Authorization Header
apiVersion (object): version of the api
backoffs (list): array of backoffs to use in the handler
concurrency (int): max number of concurrent calls
concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1
errorCol (str): column to hold http errors
imageBytes (object): bytestream of the image to use
imageUrl (object): the url of the image to use
initialPollingDelay (int): number of milliseconds to wait before first poll for result
locale (object): Locale of the receipt. Supported locales: en-AU, en-CA, en-GB, en-IN, en-US.
maxPollingRetries (int): number of times to poll
outputCol (str): The name of the output column
pages (object): The page selection only leveraged for multi-page PDF and TIFF documents. Accepted input include single pages (e.g.'1, 2' -> pages 1 and 2 will be processed), finite (e.g. '2-5' -> pages 2 to 5 will be processed) and open-ended ranges (e.g. '5-' -> all the pages from page 5 will be processed; e.g. '-10' -> pages 1 to 10 will be processed). All of these can be mixed together and ranges are allowed to overlap (eg. '-5, 1, 3, 5-10' - pages 1 to 10 will be processed). The service will accept the request if it can process at least one page of the document (e.g. using '5-100' on a 5 page document is a valid input where page 5 will be processed). If no page range is provided, the entire document will be processed.
pollingDelay (int): number of milliseconds to wait between polling
prebuiltModelId (object): Prebuilt Model identifier for Form Recognizer V3.0, supported modelId: prebuilt-read, prebuilt-layout,prebuilt-document, prebuilt-businessCard, prebuilt-idDocument, prebuilt-invoice, prebuilt-receipt,or your custom modelId
stringIndexType (object): Method used to compute string offset and length.
subscriptionKey (object): the API key to use
suppressMaxRetriesException (bool): set true to suppress the maxumimum retries exception and report in the error column
timeout (float): number of seconds to wait before closing the connection
url (str): Url of the service
"""
AADToken = Param(Params._dummy(), "AADToken", "ServiceParam: AAD Token used for authentication")
CustomAuthHeader = Param(Params._dummy(), "CustomAuthHeader", "ServiceParam: A Custom Value for Authorization Header")
apiVersion = Param(Params._dummy(), "apiVersion", "ServiceParam: version of the api")
backoffs = Param(Params._dummy(), "backoffs", "array of backoffs to use in the handler", typeConverter=TypeConverters.toListInt)
concurrency = Param(Params._dummy(), "concurrency", "max number of concurrent calls", typeConverter=TypeConverters.toInt)
concurrentTimeout = Param(Params._dummy(), "concurrentTimeout", "max number seconds to wait on futures if concurrency >= 1", typeConverter=TypeConverters.toFloat)
errorCol = Param(Params._dummy(), "errorCol", "column to hold http errors", typeConverter=TypeConverters.toString)
imageBytes = Param(Params._dummy(), "imageBytes", "ServiceParam: bytestream of the image to use")
imageUrl = Param(Params._dummy(), "imageUrl", "ServiceParam: the url of the image to use")
initialPollingDelay = Param(Params._dummy(), "initialPollingDelay", "number of milliseconds to wait before first poll for result", typeConverter=TypeConverters.toInt)
locale = Param(Params._dummy(), "locale", "ServiceParam: Locale of the receipt. Supported locales: en-AU, en-CA, en-GB, en-IN, en-US.")
maxPollingRetries = Param(Params._dummy(), "maxPollingRetries", "number of times to poll", typeConverter=TypeConverters.toInt)
outputCol = Param(Params._dummy(), "outputCol", "The name of the output column", typeConverter=TypeConverters.toString)
pages = Param(Params._dummy(), "pages", "ServiceParam: The page selection only leveraged for multi-page PDF and TIFF documents. Accepted input include single pages (e.g.'1, 2' -> pages 1 and 2 will be processed), finite (e.g. '2-5' -> pages 2 to 5 will be processed) and open-ended ranges (e.g. '5-' -> all the pages from page 5 will be processed; e.g. '-10' -> pages 1 to 10 will be processed). All of these can be mixed together and ranges are allowed to overlap (eg. '-5, 1, 3, 5-10' - pages 1 to 10 will be processed). The service will accept the request if it can process at least one page of the document (e.g. using '5-100' on a 5 page document is a valid input where page 5 will be processed). If no page range is provided, the entire document will be processed.")
pollingDelay = Param(Params._dummy(), "pollingDelay", "number of milliseconds to wait between polling", typeConverter=TypeConverters.toInt)
prebuiltModelId = Param(Params._dummy(), "prebuiltModelId", "ServiceParam: Prebuilt Model identifier for Form Recognizer V3.0, supported modelId: prebuilt-read, prebuilt-layout,prebuilt-document, prebuilt-businessCard, prebuilt-idDocument, prebuilt-invoice, prebuilt-receipt,or your custom modelId")
stringIndexType = Param(Params._dummy(), "stringIndexType", "ServiceParam: Method used to compute string offset and length.")
subscriptionKey = Param(Params._dummy(), "subscriptionKey", "ServiceParam: the API key to use")
suppressMaxRetriesException = Param(Params._dummy(), "suppressMaxRetriesException", "set true to suppress the maxumimum retries exception and report in the error column", typeConverter=TypeConverters.toBoolean)
timeout = Param(Params._dummy(), "timeout", "number of seconds to wait before closing the connection", typeConverter=TypeConverters.toFloat)
url = Param(Params._dummy(), "url", "Url of the service", typeConverter=TypeConverters.toString)
@keyword_only
def __init__(
self,
java_obj=None,
AADToken=None,
AADTokenCol=None,
CustomAuthHeader=None,
CustomAuthHeaderCol=None,
apiVersion=None,
apiVersionCol=None,
backoffs=[100,500,1000],
concurrency=1,
concurrentTimeout=None,
errorCol="AnalyzeDocument_e6fb69e1b1e7_error",
imageBytes=None,
imageBytesCol=None,
imageUrl=None,
imageUrlCol=None,
initialPollingDelay=300,
locale=None,
localeCol=None,
maxPollingRetries=1000,
outputCol="AnalyzeDocument_e6fb69e1b1e7_output",
pages=None,
pagesCol=None,
pollingDelay=300,
prebuiltModelId=None,
prebuiltModelIdCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
suppressMaxRetriesException=False,
timeout=60.0,
url=None
):
super(AnalyzeDocument, self).__init__()
if java_obj is None:
self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.services.form.AnalyzeDocument", self.uid)
else:
self._java_obj = java_obj
self._setDefault(backoffs=[100,500,1000])
self._setDefault(concurrency=1)
self._setDefault(errorCol="AnalyzeDocument_e6fb69e1b1e7_error")
self._setDefault(initialPollingDelay=300)
self._setDefault(maxPollingRetries=1000)
self._setDefault(outputCol="AnalyzeDocument_e6fb69e1b1e7_output")
self._setDefault(pollingDelay=300)
self._setDefault(suppressMaxRetriesException=False)
self._setDefault(timeout=60.0)
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
if java_obj is None:
for k,v in kwargs.items():
if v is not None:
getattr(self, "set" + k[0].upper() + k[1:])(v)
[docs] @keyword_only
def setParams(
self,
AADToken=None,
AADTokenCol=None,
CustomAuthHeader=None,
CustomAuthHeaderCol=None,
apiVersion=None,
apiVersionCol=None,
backoffs=[100,500,1000],
concurrency=1,
concurrentTimeout=None,
errorCol="AnalyzeDocument_e6fb69e1b1e7_error",
imageBytes=None,
imageBytesCol=None,
imageUrl=None,
imageUrlCol=None,
initialPollingDelay=300,
locale=None,
localeCol=None,
maxPollingRetries=1000,
outputCol="AnalyzeDocument_e6fb69e1b1e7_output",
pages=None,
pagesCol=None,
pollingDelay=300,
prebuiltModelId=None,
prebuiltModelIdCol=None,
stringIndexType=None,
stringIndexTypeCol=None,
subscriptionKey=None,
subscriptionKeyCol=None,
suppressMaxRetriesException=False,
timeout=60.0,
url=None
):
"""
Set the (keyword only) parameters
"""
if hasattr(self, "_input_kwargs"):
kwargs = self._input_kwargs
else:
kwargs = self.__init__._input_kwargs
return self._set(**kwargs)
[docs] @classmethod
def read(cls):
""" Returns an MLReader instance for this class. """
return JavaMMLReader(cls)
[docs] @staticmethod
def getJavaPackage():
""" Returns package name String. """
return "com.microsoft.azure.synapse.ml.services.form.AnalyzeDocument"
@staticmethod
def _from_java(java_stage):
module_name=AnalyzeDocument.__module__
module_name=module_name.rsplit(".", 1)[0] + ".AnalyzeDocument"
return from_java(java_stage, module_name)
[docs] def setAADToken(self, value):
"""
Args:
AADToken: AAD Token used for authentication
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setAADToken(value)
return self
[docs] def setAADTokenCol(self, value):
"""
Args:
AADToken: AAD Token used for authentication
"""
self._java_obj = self._java_obj.setAADTokenCol(value)
return self
[docs] def setApiVersion(self, value):
"""
Args:
apiVersion: version of the api
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setApiVersion(value)
return self
[docs] def setApiVersionCol(self, value):
"""
Args:
apiVersion: version of the api
"""
self._java_obj = self._java_obj.setApiVersionCol(value)
return self
[docs] def setBackoffs(self, value):
"""
Args:
backoffs: array of backoffs to use in the handler
"""
self._set(backoffs=value)
return self
[docs] def setConcurrency(self, value):
"""
Args:
concurrency: max number of concurrent calls
"""
self._set(concurrency=value)
return self
[docs] def setConcurrentTimeout(self, value):
"""
Args:
concurrentTimeout: max number seconds to wait on futures if concurrency >= 1
"""
self._set(concurrentTimeout=value)
return self
[docs] def setErrorCol(self, value):
"""
Args:
errorCol: column to hold http errors
"""
self._set(errorCol=value)
return self
[docs] def setImageBytes(self, value):
"""
Args:
imageBytes: bytestream of the image to use
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setImageBytes(value)
return self
[docs] def setImageBytesCol(self, value):
"""
Args:
imageBytes: bytestream of the image to use
"""
self._java_obj = self._java_obj.setImageBytesCol(value)
return self
[docs] def setImageUrl(self, value):
"""
Args:
imageUrl: the url of the image to use
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setImageUrl(value)
return self
[docs] def setImageUrlCol(self, value):
"""
Args:
imageUrl: the url of the image to use
"""
self._java_obj = self._java_obj.setImageUrlCol(value)
return self
[docs] def setInitialPollingDelay(self, value):
"""
Args:
initialPollingDelay: number of milliseconds to wait before first poll for result
"""
self._set(initialPollingDelay=value)
return self
[docs] def setLocale(self, value):
"""
Args:
locale: Locale of the receipt. Supported locales: en-AU, en-CA, en-GB, en-IN, en-US.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setLocale(value)
return self
[docs] def setLocaleCol(self, value):
"""
Args:
locale: Locale of the receipt. Supported locales: en-AU, en-CA, en-GB, en-IN, en-US.
"""
self._java_obj = self._java_obj.setLocaleCol(value)
return self
[docs] def setMaxPollingRetries(self, value):
"""
Args:
maxPollingRetries: number of times to poll
"""
self._set(maxPollingRetries=value)
return self
[docs] def setOutputCol(self, value):
"""
Args:
outputCol: The name of the output column
"""
self._set(outputCol=value)
return self
[docs] def setPages(self, value):
"""
Args:
pages: The page selection only leveraged for multi-page PDF and TIFF documents. Accepted input include single pages (e.g.'1, 2' -> pages 1 and 2 will be processed), finite (e.g. '2-5' -> pages 2 to 5 will be processed) and open-ended ranges (e.g. '5-' -> all the pages from page 5 will be processed; e.g. '-10' -> pages 1 to 10 will be processed). All of these can be mixed together and ranges are allowed to overlap (eg. '-5, 1, 3, 5-10' - pages 1 to 10 will be processed). The service will accept the request if it can process at least one page of the document (e.g. using '5-100' on a 5 page document is a valid input where page 5 will be processed). If no page range is provided, the entire document will be processed.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setPages(value)
return self
[docs] def setPagesCol(self, value):
"""
Args:
pages: The page selection only leveraged for multi-page PDF and TIFF documents. Accepted input include single pages (e.g.'1, 2' -> pages 1 and 2 will be processed), finite (e.g. '2-5' -> pages 2 to 5 will be processed) and open-ended ranges (e.g. '5-' -> all the pages from page 5 will be processed; e.g. '-10' -> pages 1 to 10 will be processed). All of these can be mixed together and ranges are allowed to overlap (eg. '-5, 1, 3, 5-10' - pages 1 to 10 will be processed). The service will accept the request if it can process at least one page of the document (e.g. using '5-100' on a 5 page document is a valid input where page 5 will be processed). If no page range is provided, the entire document will be processed.
"""
self._java_obj = self._java_obj.setPagesCol(value)
return self
[docs] def setPollingDelay(self, value):
"""
Args:
pollingDelay: number of milliseconds to wait between polling
"""
self._set(pollingDelay=value)
return self
[docs] def setPrebuiltModelId(self, value):
"""
Args:
prebuiltModelId: Prebuilt Model identifier for Form Recognizer V3.0, supported modelId: prebuilt-read, prebuilt-layout,prebuilt-document, prebuilt-businessCard, prebuilt-idDocument, prebuilt-invoice, prebuilt-receipt,or your custom modelId
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setPrebuiltModelId(value)
return self
[docs] def setPrebuiltModelIdCol(self, value):
"""
Args:
prebuiltModelId: Prebuilt Model identifier for Form Recognizer V3.0, supported modelId: prebuilt-read, prebuilt-layout,prebuilt-document, prebuilt-businessCard, prebuilt-idDocument, prebuilt-invoice, prebuilt-receipt,or your custom modelId
"""
self._java_obj = self._java_obj.setPrebuiltModelIdCol(value)
return self
[docs] def setStringIndexType(self, value):
"""
Args:
stringIndexType: Method used to compute string offset and length.
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setStringIndexType(value)
return self
[docs] def setStringIndexTypeCol(self, value):
"""
Args:
stringIndexType: Method used to compute string offset and length.
"""
self._java_obj = self._java_obj.setStringIndexTypeCol(value)
return self
[docs] def setSubscriptionKey(self, value):
"""
Args:
subscriptionKey: the API key to use
"""
if isinstance(value, list):
value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value)
self._java_obj = self._java_obj.setSubscriptionKey(value)
return self
[docs] def setSubscriptionKeyCol(self, value):
"""
Args:
subscriptionKey: the API key to use
"""
self._java_obj = self._java_obj.setSubscriptionKeyCol(value)
return self
[docs] def setSuppressMaxRetriesException(self, value):
"""
Args:
suppressMaxRetriesException: set true to suppress the maxumimum retries exception and report in the error column
"""
self._set(suppressMaxRetriesException=value)
return self
[docs] def setTimeout(self, value):
"""
Args:
timeout: number of seconds to wait before closing the connection
"""
self._set(timeout=value)
return self
[docs] def setUrl(self, value):
"""
Args:
url: Url of the service
"""
self._set(url=value)
return self
[docs] def getAADToken(self):
"""
Returns:
AADToken: AAD Token used for authentication
"""
return self._java_obj.getAADToken()
[docs] def getApiVersion(self):
"""
Returns:
apiVersion: version of the api
"""
return self._java_obj.getApiVersion()
[docs] def getBackoffs(self):
"""
Returns:
backoffs: array of backoffs to use in the handler
"""
return self.getOrDefault(self.backoffs)
[docs] def getConcurrency(self):
"""
Returns:
concurrency: max number of concurrent calls
"""
return self.getOrDefault(self.concurrency)
[docs] def getConcurrentTimeout(self):
"""
Returns:
concurrentTimeout: max number seconds to wait on futures if concurrency >= 1
"""
return self.getOrDefault(self.concurrentTimeout)
[docs] def getErrorCol(self):
"""
Returns:
errorCol: column to hold http errors
"""
return self.getOrDefault(self.errorCol)
[docs] def getImageBytes(self):
"""
Returns:
imageBytes: bytestream of the image to use
"""
return self._java_obj.getImageBytes()
[docs] def getImageUrl(self):
"""
Returns:
imageUrl: the url of the image to use
"""
return self._java_obj.getImageUrl()
[docs] def getInitialPollingDelay(self):
"""
Returns:
initialPollingDelay: number of milliseconds to wait before first poll for result
"""
return self.getOrDefault(self.initialPollingDelay)
[docs] def getLocale(self):
"""
Returns:
locale: Locale of the receipt. Supported locales: en-AU, en-CA, en-GB, en-IN, en-US.
"""
return self._java_obj.getLocale()
[docs] def getMaxPollingRetries(self):
"""
Returns:
maxPollingRetries: number of times to poll
"""
return self.getOrDefault(self.maxPollingRetries)
[docs] def getOutputCol(self):
"""
Returns:
outputCol: The name of the output column
"""
return self.getOrDefault(self.outputCol)
[docs] def getPages(self):
"""
Returns:
pages: The page selection only leveraged for multi-page PDF and TIFF documents. Accepted input include single pages (e.g.'1, 2' -> pages 1 and 2 will be processed), finite (e.g. '2-5' -> pages 2 to 5 will be processed) and open-ended ranges (e.g. '5-' -> all the pages from page 5 will be processed; e.g. '-10' -> pages 1 to 10 will be processed). All of these can be mixed together and ranges are allowed to overlap (eg. '-5, 1, 3, 5-10' - pages 1 to 10 will be processed). The service will accept the request if it can process at least one page of the document (e.g. using '5-100' on a 5 page document is a valid input where page 5 will be processed). If no page range is provided, the entire document will be processed.
"""
return self._java_obj.getPages()
[docs] def getPollingDelay(self):
"""
Returns:
pollingDelay: number of milliseconds to wait between polling
"""
return self.getOrDefault(self.pollingDelay)
[docs] def getPrebuiltModelId(self):
"""
Returns:
prebuiltModelId: Prebuilt Model identifier for Form Recognizer V3.0, supported modelId: prebuilt-read, prebuilt-layout,prebuilt-document, prebuilt-businessCard, prebuilt-idDocument, prebuilt-invoice, prebuilt-receipt,or your custom modelId
"""
return self._java_obj.getPrebuiltModelId()
[docs] def getStringIndexType(self):
"""
Returns:
stringIndexType: Method used to compute string offset and length.
"""
return self._java_obj.getStringIndexType()
[docs] def getSubscriptionKey(self):
"""
Returns:
subscriptionKey: the API key to use
"""
return self._java_obj.getSubscriptionKey()
[docs] def getSuppressMaxRetriesException(self):
"""
Returns:
suppressMaxRetriesException: set true to suppress the maxumimum retries exception and report in the error column
"""
return self.getOrDefault(self.suppressMaxRetriesException)
[docs] def getTimeout(self):
"""
Returns:
timeout: number of seconds to wait before closing the connection
"""
return self.getOrDefault(self.timeout)
[docs] def getUrl(self):
"""
Returns:
url: Url of the service
"""
return self.getOrDefault(self.url)
[docs] def setCustomServiceName(self, value):
self._java_obj = self._java_obj.setCustomServiceName(value)
return self
[docs] def setEndpoint(self, value):
self._java_obj = self._java_obj.setEndpoint(value)
return self
[docs] def setDefaultInternalEndpoint(self, value):
self._java_obj = self._java_obj.setDefaultInternalEndpoint(value)
return self
def _transform(self, dataset: DataFrame) -> DataFrame:
if running_on_synapse_internal():
try:
from synapse.ml.fabric.token_utils import TokenUtils
from synapse.ml.fabric.service_discovery import get_fabric_env_config
fabric_env_config = get_fabric_env_config().fabric_env_config
if self._java_obj.getInternalServiceType() != "openai":
self._java_obj.setDefaultAADToken(TokenUtils().get_aad_token())
else:
self._java_obj.setDefaultCustomAuthHeader(TokenUtils().get_openai_auth_header())
self.setDefaultInternalEndpoint(fabric_env_config.get_mlflow_workload_endpoint())
except ModuleNotFoundError as e:
pass
return super()._transform(dataset)
[docs] def setLocation(self, value):
self._java_obj = self._java_obj.setLocation(value)
return self
[docs] def setLinkedService(self, value):
self._java_obj = self._java_obj.setLinkedService(value)
return self