spark-nlp 5.5.2__tar.gz → 5.5.3__tar.gz

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spark-nlp
-Version: 5.5.2
+Version: 5.5.3
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -95,7 +95,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==5.5.2 pyspark==3.3.1
+$ pip install spark-nlp==5.5.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +161,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *5.5.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *5.5.3* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -189,7 +189,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following runtimes:
+Spark NLP 5.5.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -206,7 +206,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following EMR releases:
+Spark NLP 5.5.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -237,7 +237,7 @@ deployed to Maven central. To add any of our packages as a dependency in your ap
 from our official documentation.
 
 If you are interested, there is a simple SBT project for Spark NLP to guide you on how to use it in your
-projects [Spark NLP SBT S5.5.2r](https://github.com/maziyarpanahi/spark-nlp-starter)
+projects [Spark NLP SBT S5.5.3r](https://github.com/maziyarpanahi/spark-nlp-starter)
 
 ### Python
 
@@ -282,7 +282,7 @@ In Spark NLP we can define S3 locations to:
 
 Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation.
 
-## Document5.5.2
+## Document5.5.3
 
 ### Examples
 
@@ -315,7 +315,7 @@ the Spark NLP library:
     keywords = {Spark, Natural language processing, Deep learning, Tensorflow, Cluster},
     abstract = {Spark NLP is a Natural Language Processing (NLP) library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines that can scale easily in a distributed environment. Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages. It supports nearly all the NLP tasks and modules that can be used seamlessly in a cluster. Downloaded more than 2.7 million times and experiencing 9x growth since January 2020, Spark NLP is used by 54% of healthcare organizations as the world’s most widely used NLP library in the enterprise.}
     }
-}5.5.2
+}5.5.3
 ```
 
 ## Community support

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/README.md

@@ -63,7 +63,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==5.5.2 pyspark==3.3.1
+$ pip install spark-nlp==5.5.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -129,7 +129,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *5.5.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *5.5.3* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -157,7 +157,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following runtimes:
+Spark NLP 5.5.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -174,7 +174,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following EMR releases:
+Spark NLP 5.5.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -205,7 +205,7 @@ deployed to Maven central. To add any of our packages as a dependency in your ap
 from our official documentation.
 
 If you are interested, there is a simple SBT project for Spark NLP to guide you on how to use it in your
-projects [Spark NLP SBT S5.5.2r](https://github.com/maziyarpanahi/spark-nlp-starter)
+projects [Spark NLP SBT S5.5.3r](https://github.com/maziyarpanahi/spark-nlp-starter)
 
 ### Python
 
@@ -250,7 +250,7 @@ In Spark NLP we can define S3 locations to:
 
 Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation.
 
-## Document5.5.2
+## Document5.5.3
 
 ### Examples
 
@@ -283,7 +283,7 @@ the Spark NLP library:
     keywords = {Spark, Natural language processing, Deep learning, Tensorflow, Cluster},
     abstract = {Spark NLP is a Natural Language Processing (NLP) library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines that can scale easily in a distributed environment. Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages. It supports nearly all the NLP tasks and modules that can be used seamlessly in a cluster. Downloaded more than 2.7 million times and experiencing 9x growth since January 2020, Spark NLP is used by 54% of healthcare organizations as the world’s most widely used NLP library in the enterprise.}
     }
-}5.5.2
+}5.5.3
 ```
 
 ## Community support

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='5.5.2',  # Required
+    version='5.5.3',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spark-nlp
-Version: 5.5.2
+Version: 5.5.3
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -95,7 +95,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==5.5.2 pyspark==3.3.1
+$ pip install spark-nlp==5.5.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -161,7 +161,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *5.5.2* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *5.5.3* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -189,7 +189,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following runtimes:
+Spark NLP 5.5.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -206,7 +206,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 5.5.2 has been tested and is compatible with the following EMR releases:
+Spark NLP 5.5.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|
@@ -237,7 +237,7 @@ deployed to Maven central. To add any of our packages as a dependency in your ap
 from our official documentation.
 
 If you are interested, there is a simple SBT project for Spark NLP to guide you on how to use it in your
-projects [Spark NLP SBT S5.5.2r](https://github.com/maziyarpanahi/spark-nlp-starter)
+projects [Spark NLP SBT S5.5.3r](https://github.com/maziyarpanahi/spark-nlp-starter)
 
 ### Python
 
@@ -282,7 +282,7 @@ In Spark NLP we can define S3 locations to:
 
 Please check [these instructions](https://sparknlp.org/docs/en/install#s3-integration) from our official documentation.
 
-## Document5.5.2
+## Document5.5.3
 
 ### Examples
 
@@ -315,7 +315,7 @@ the Spark NLP library:
     keywords = {Spark, Natural language processing, Deep learning, Tensorflow, Cluster},
     abstract = {Spark NLP is a Natural Language Processing (NLP) library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines that can scale easily in a distributed environment. Spark NLP comes with 1100+ pretrained pipelines and models in more than 192+ languages. It supports nearly all the NLP tasks and modules that can be used seamlessly in a cluster. Downloaded more than 2.7 million times and experiencing 9x growth since January 2020, Spark NLP is used by 54% of healthcare organizations as the world’s most widely used NLP library in the enterprise.}
     }
-}5.5.2
+}5.5.3
 ```
 
 ## Community support

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/sparknlp/__init__.py

@@ -132,7 +132,7 @@ def start(gpu=False,
         The initiated Spark session.
 
     """
-    current_version = "5.5.2"
+    current_version = "5.5.3"
 
     if params is None:
         params = {}
@@ -316,4 +316,4 @@ def version():
     str
         The current Spark NLP version.
     """
-    return '5.5.2'
+    return '5.5.3'

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/sparknlp/annotator/embeddings/bge_embeddings.py

@@ -21,7 +21,8 @@ class BGEEmbeddings(AnnotatorModel,
                     HasCaseSensitiveProperties,
                     HasStorageRef,
                     HasBatchedAnnotate,
-                    HasMaxSentenceLengthLimit):
+                    HasMaxSentenceLengthLimit,
+                    HasClsTokenProperties):
     """Sentence embeddings using BGE.
 
    BGE, or BAAI General Embeddings, a model that can map any text to a low-dimensional dense 
@@ -60,6 +61,8 @@ class BGEEmbeddings(AnnotatorModel,
         Max sentence length to process, by default 512
     configProtoBytes
         ConfigProto from tensorflow, serialized into byte array.
+    useCLSToken
+        Whether to use the CLS token for sentence embeddings, by default True
 
     References
     ----------
@@ -148,6 +151,7 @@ class BGEEmbeddings(AnnotatorModel,
             batchSize=8,
             maxSentenceLength=512,
             caseSensitive=False,
+            useCLSToken=True
         )
 
     @staticmethod
@@ -171,13 +175,13 @@ class BGEEmbeddings(AnnotatorModel,
         return BGEEmbeddings(java_model=jModel)
 
     @staticmethod
-    def pretrained(name="bge_base", lang="en", remote_loc=None):
+    def pretrained(name="bge_small_en_v1.5", lang="en", remote_loc=None):
         """Downloads and loads a pretrained model.
 
         Parameters
         ----------
         name : str, optional
-            Name of the pretrained model, by default "bge_base"
+            Name of the pretrained model, by default "bge_small_en_v1.5"
         lang : str, optional
             Language of the pretrained model, by default "en"
         remote_loc : str, optional

{spark-nlp-5.5.2 → spark-nlp-5.5.3}/sparknlp/common/properties.py

@@ -67,6 +67,33 @@ class HasCaseSensitiveProperties:
         return self.getOrDefault(self.caseSensitive)
 
 
+class HasClsTokenProperties:
+    useCLSToken = Param(Params._dummy(),
+                        "useCLSToken",
+                        "Whether to use CLS token for pooling (true) or attention-based average pooling (false)",
+                        typeConverter=TypeConverters.toBoolean)
+
+    def setUseCLSToken(self, value):
+        """Sets whether to ignore case in tokens for embeddings matching.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to use CLS token for pooling (true) or attention-based average pooling (false)
+        """
+        return self._set(useCLSToken=value)
+
+    def getUseCLSToken(self):
+        """Gets whether to use CLS token for pooling (true) or attention-based average pooling (false)
+
+        Returns
+        -------
+        bool
+            Whether to use CLS token for pooling (true) or attention-based average pooling (false)
+        """
+        return self.getOrDefault(self.useCLSToken)
+
+
 class HasClassifierActivationProperties:
     activation = Param(Params._dummy(),
                        "activation",

spark-nlp-5.5.3/sparknlp/reader/sparknlp_reader.py

@@ -0,0 +1,113 @@
+#  Copyright 2017-2024 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+from sparknlp.internal import ExtendedJavaWrapper
+
+
+class SparkNLPReader(ExtendedJavaWrapper):
+    """Instantiates class to read HTML, email, and document files.
+
+    Two types of input paths are supported:
+
+    - `htmlPath`: A path to a directory of HTML files or a single HTML file (e.g., `"path/html/files"`).
+    - `url`: A single URL or a set of URLs (e.g., `"https://www.wikipedia.org"`).
+
+    Parameters
+    ----------
+    spark : SparkSession
+        The active Spark session.
+    params : dict, optional
+        A dictionary with custom configurations.
+    """
+
+    def __init__(self, spark, params=None):
+        if params is None:
+            params = {}
+        super(SparkNLPReader, self).__init__("com.johnsnowlabs.reader.SparkNLPReader", params)
+        self.spark = spark
+
+    def html(self, htmlPath):
+        """Reads HTML files or URLs and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        htmlPath : str or list of str
+            Path(s) to HTML file(s) or a list of URLs.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing the parsed HTML content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> html_df = SparkNLPReader(spark).html("https://www.wikipedia.org")
+
+        You can also use SparkNLP to simplify the process:
+
+        >>> import sparknlp
+        >>> html_df = sparknlp.read().html("https://www.wikipedia.org")
+        >>> html_df.show(truncate=False)
+        """
+        if not isinstance(htmlPath, (str, list)) or (isinstance(htmlPath, list) and not all(isinstance(item, str) for item in htmlPath)):
+            raise TypeError("htmlPath must be a string or a list of strings")
+        jdf = self._java_obj.html(htmlPath)
+        return self.getDataFrame(self.spark, jdf)
+
+    def email(self, filePath):
+        """Reads email files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        filePath : str
+            Path to an email file or a directory containing emails.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed email data.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> email_df = SparkNLPReader(spark).email("home/user/emails-directory")
+
+        Using SparkNLP:
+
+        >>> import sparknlp
+        >>> email_df = sparknlp.read().email("home/user/emails-directory")
+        >>> email_df.show(truncate=False)
+        """
+        if not isinstance(filePath, str):
+            raise TypeError("filePath must be a string")
+        jdf = self._java_obj.email(filePath)
+        return self.getDataFrame(self.spark, jdf)
+
+    def doc(self, docPath):
+        """Reads document files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to a document file.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed document content.
+        """
+        if not isinstance(docPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.doc(docPath)
+        return self.getDataFrame(self.spark, jdf)

spark-nlp-5.5.2/sparknlp/reader/sparknlp_reader.py

@@ -1,121 +0,0 @@
-#  Copyright 2017-2024 John Snow Labs
-#
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
-from sparknlp.internal import ExtendedJavaWrapper
-
-
-class SparkNLPReader(ExtendedJavaWrapper):
-    """Instantiates class to read HTML files.
-
-    Two types of input paths are supported,
-
-    htmlPath: this is a path to a directory of HTML files or a path to an HTML file
-    E.g. "path/html/files"
-
-    url: this is the URL or set of URLs of a website  . E.g., "https://www.wikipedia.org"
-
-    Parameters
-    ----------
-    params : spark
-        Spark session
-    params : dict, optional
-        Parameter with custom configuration
-
-    Examples
-    --------
-    >>> from sparknlp.reader import SparkNLPReader
-    >>> html_df = SparkNLPReader().html(spark, "https://www.wikipedia.org")
-
-    You can use SparkNLP for one line of code
-    >>> import sparknlp
-    >>> html_df = sparknlp.read().html("https://www.wikipedia.org")
-    >>> html_df.show(truncate=False)
-
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |url                 |html                                                                                                                                                                                                                                                                                                                            |
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |https://example.com/|[{Title, Example Domain, {pageNumber -> 1}}, {NarrativeText, 0, This domain is for use in illustrative examples in documents. You may use this domain in literature without prior coordination or asking for permission., {pageNumber -> 1}}, {NarrativeText, 0, More information... More information..., {pageNumber -> 1}}]   |
-    +--------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    >>> html_df.printSchema()
-
-    root
-     |-- url: string (nullable = true)
-     |-- html: array (nullable = true)
-     |    |-- element: struct (containsNull = true)
-     |    |    |-- elementType: string (nullable = true)
-     |    |    |-- content: string (nullable = true)
-     |    |    |-- metadata: map (nullable = true)
-     |    |    |    |-- key: string
-     |    |    |    |-- value: string (valueContainsNull = true)
-
-
-
-    Instantiates class to read email files.
-
-    emailPath: this is a path to a directory of HTML files or a path to an HTML file E.g.
-    "path/html/emails"
-
-    Examples
-    --------
-    >>> from sparknlp.reader import SparkNLPReader
-    >>> email_df = SparkNLPReader().email(spark, "home/user/emails-directory")
-
-    You can use SparkNLP for one line of code
-    >>> import sparknlp
-    >>> email_df = sparknlp.read().email("home/user/emails-directory")
-    >>> email_df.show(truncate=False)
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |email                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    |[{Title, Email Text Attachments, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>}}, {NarrativeText, Email  test with two text attachments\r\n\r\nCheers,\r\n\r\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}, {NarrativeText, <html>\r\n<head>\r\n<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">\r\n<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>\r\n</head>\r\n<body dir="ltr">\r\n<span style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">Email&nbsp; test with two text attachments</span>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\n<br>\r\n</div>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\nCheers,</div>\r\n<div class="elementToProof" style="font-family: Aptos, Aptos_EmbeddedFont, Aptos_MSFontService, Calibri, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">\r\n<br>\r\n</div>\r\n</body>\r\n</html>\r\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/html}}, {Attachment, filename.txt, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, contentType -> text/plain; name="filename.txt"}}, {NarrativeText, This is the content of the file.\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}, {Attachment, filename2.txt, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, contentType -> text/plain; name="filename2.txt"}}, {NarrativeText, This is an additional content file.\n, {sent_to -> Danilo Burbano <danilo@johnsnowlabs.com>, sent_from -> Danilo Burbano <danilo@johnsnowlabs.com>, mimeType -> text/plain}}]|
-    +--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
-    email_df.printSchema()
-    root
-     |-- path: string (nullable = true)
-     |-- content: array (nullable = true)
-     |-- email: array (nullable = true)
-     |    |-- element: struct (containsNull = true)
-     |    |    |-- elementType: string (nullable = true)
-     |    |    |-- content: string (nullable = true)
-     |    |    |-- metadata: map (nullable = true)
-     |    |    |    |-- key: string
-     |    |    |    |-- value: string (valueContainsNull = true)
-
-    """
-
-    def __init__(self, spark, params=None):
-        if params is None:
-            params = {}
-        super(SparkNLPReader, self).__init__("com.johnsnowlabs.reader.SparkNLPReader", params)
-        self.spark = spark
-
-    def html(self, htmlPath):
-        if not isinstance(htmlPath, (str, list)) or (isinstance(htmlPath, list) and not all(isinstance(item, str) for item in htmlPath)):
-            raise TypeError("htmlPath must be a string or a list of strings")
-        jdf = self._java_obj.html(htmlPath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe
-
-    def email(self, filePath):
-        if not isinstance(filePath, str):
-            raise TypeError("filePath must be a string")
-        jdf = self._java_obj.email(filePath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe
-
-    def doc(self, docPath):
-        if not isinstance(docPath, str):
-            raise TypeError("docPath must be a string")
-        jdf = self._java_obj.doc(docPath)
-        dataframe = self.getDataFrame(self.spark, jdf)
-        return dataframe