spark-nlp 5.5.3__py2.py3-none-any.whl → 6.0.1__py2.py3-none-any.whl

sparknlp/internal/__init__.py

@@ -67,6 +67,15 @@ class _AlbertForZeroShotClassificationLoader(ExtendedJavaWrapper):
         )
 
 
+class _AlbertMultipleChoiceLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_AlbertMultipleChoiceLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.classifier.dl.AlbertForMultipleChoice.loadSavedModel",
+            path,
+            jspark,
+        )
+
+
 class _BertLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
         super(_BertLoader, self).__init__(
@@ -121,6 +130,15 @@ class _BertMultipleChoiceLoader(ExtendedJavaWrapper):
             jspark,
         )
 
+class _CoHereLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_CoHereLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.seq2seq.CoHereTransformer.loadSavedModel",
+            path,
+            jspark,
+            use_openvino,
+        )
+
 class _DeBERTaLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark):
         super(_DeBERTaLoader, self).__init__(
@@ -211,6 +229,15 @@ class _DistilBertQuestionAnsweringLoader(ExtendedJavaWrapper):
         )
 
 
+class _DistilBertMultipleChoiceLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_DistilBertMultipleChoiceLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.classifier.dl.DistilBertForMultipleChoice.loadSavedModel",
+            path,
+            jspark,
+        )
+
+
 class _ElmoLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark):
         super(_ElmoLoader, self).__init__(
@@ -245,6 +272,23 @@ class _GPT2Loader(ExtendedJavaWrapper):
             jspark,
         )
 
+class _Gemma3ForMultiModalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_Gemma3ForMultiModalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.Gemma3ForMultiModal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
+
+class _JanusForMultiModalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_JanusForMultiModalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.JanusForMultiModal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
 
 class _LLAMA2Loader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
@@ -299,6 +343,14 @@ class _LongformerQuestionAnsweringLoader(ExtendedJavaWrapper):
             jspark,
         )
 
+class _LLAVAForMultiModalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_LLAVAForMultiModalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.LLAVAForMultiModal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
 
 class _M2M100Loader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
@@ -318,6 +370,14 @@ class _MistralLoader(ExtendedJavaWrapper):
             use_openvino,
         )
 
+class _MLLamaForMultimodalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_MLLamaForMultimodalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.MLLamaForMultimodal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
 
 class _NLLBLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark,  use_openvino=False):
@@ -345,6 +405,10 @@ class _MPNetLoader(ExtendedJavaWrapper):
         )
 
 
+class _OLMoLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_OLMoLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.seq2seq.OLMoTransformer.loadSavedModel", path, jspark)
 class _Phi2Loader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
         super(_Phi2Loader, self).__init__(
@@ -363,6 +427,15 @@ class _Phi3Loader(ExtendedJavaWrapper):
             use_openvino,
         )
 
+class _Phi3VisionLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_Phi3VisionLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.Phi3Vision.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )
+
 class _RoBertaLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
         super(_RoBertaLoader, self).__init__(
@@ -409,6 +482,15 @@ class _RoBertaQuestionAnsweringLoader(ExtendedJavaWrapper):
         )
 
 
+class _RoBertaMultipleChoiceLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_RoBertaMultipleChoiceLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.classifier.dl.RoBertaForMultipleChoice.loadSavedModel",
+            path,
+            jspark,
+        )
+
+
 class _StarCoderLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark, use_openvino=False):
         super(_StarCoderLoader, self).__init__(
@@ -504,6 +586,15 @@ class _XlmRoBertaQuestionAnsweringLoader(ExtendedJavaWrapper):
         )
 
 
+class _XlmRoBertaMultipleChoiceLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark):
+        super(_XlmRoBertaMultipleChoiceLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.classifier.dl.XlmRoBertaForMultipleChoice.loadSavedModel",
+            path,
+            jspark,
+        )
+
+
 class _XlnetLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark):
         super(_XlnetLoader, self).__init__(
@@ -992,8 +1083,8 @@ class _AutoGGUFLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark):
         super(_AutoGGUFLoader, self).__init__(
             "com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFModel.loadSavedModel", path, jspark)
-        
-        
+
+
 class _MxbaiEmbeddingsLoader(ExtendedJavaWrapper):
     def __init__(self, path, jspark):
         super(_MxbaiEmbeddingsLoader, self).__init__(
@@ -1021,3 +1112,37 @@ class _BLIPForQuestionAnswering(ExtendedJavaWrapper):
             path,
             jspark,
         )
+
+
+class _AutoGGUFVisionLoader(ExtendedJavaWrapper):
+    def __init__(self, modelPath, mmprojPath, jspark):
+        super(_AutoGGUFVisionLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFVisionModel.loadSavedModel", modelPath, mmprojPath, jspark)
+        
+               
+class _Qwen2VLTransformerLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_Qwen2VLTransformerLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.Qwen2VLTransformer.loadSavedModel",
+            path,
+            jspark,
+            use_openvino,
+        )
+
+class _PaliGemmaForMultiModalLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_PaliGemmaForMultiModalLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.PaliGemmaForMultiModal.loadSavedModel",
+            path,
+            jspark,
+            use_openvino,
+        )
+
+class _SmolVLMTransformerLoader(ExtendedJavaWrapper):
+    def __init__(self, path, jspark, use_openvino=False):
+        super(_SmolVLMTransformerLoader, self).__init__(
+            "com.johnsnowlabs.nlp.annotators.cv.SmolVLMTransformer.loadSavedModel",
+            path,
+            jspark,
+            use_openvino
+        )

sparknlp/reader/enums.py

@@ -0,0 +1,19 @@
+#  Copyright 2017-2025 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 enum import Enum
+
+class TextStripperType(Enum):
+    """Text Stripper Type"""
+    PDF_TEXT_STRIPPER = "PDFTextStripper"
+    PDF_LAYOUT_TEXT_STRIPPER = "PDFLayoutTextStripper"

sparknlp/reader/pdf_to_text.py

@@ -0,0 +1,111 @@
+from pyspark import keyword_only
+from pyspark.ml.param import Param, Params, TypeConverters
+from pyspark.ml.param.shared import HasInputCol, HasOutputCol
+from pyspark.ml.util import JavaMLReadable, JavaMLWritable
+from pyspark.ml.wrapper import JavaTransformer
+
+from sparknlp.reader.enums import TextStripperType
+
+
+class PdfToText(JavaTransformer, HasInputCol, HasOutputCol,
+                JavaMLReadable, JavaMLWritable):
+    """
+    Extract text from Pdf document to single string or to several strings per each page.
+    Input is a column with binary representation of PDF document.
+    As output generate column with text and page number.
+    Explode each page as separate row if split to page enabled.
+    """
+    pageNumCol = Param(Params._dummy(), "pageNumCol",
+                       "Page number output column name.",
+                       typeConverter=TypeConverters.toString)
+
+    partitionNum = Param(Params._dummy(), "partitionNum",
+                         "Number of partitions.",
+                         typeConverter=TypeConverters.toInt)
+
+    storeSplittedPdf = Param(Params._dummy(), "storeSplittedPdf",
+                             "Force to store splitted pdf.",
+                             typeConverter=TypeConverters.toBoolean)
+
+    splitPage = Param(Params._dummy(), "splitPage",
+                      "Param for enable/disable splitting document per page",
+                      typeConverter=TypeConverters.toBoolean)
+
+    textStripper = Param(Params._dummy(), "textStripper",
+                         "Text stripper type used for output layout and formatting",
+                         typeConverter=TypeConverters.toString)
+
+    sort = Param(Params._dummy(), "sort",
+                 "Param for enable/disable sort lines",
+                 typeConverter=TypeConverters.toBoolean)
+
+    onlyPageNum = Param(Params._dummy(), "onlyPageNum",
+                        "Force to extract only number of pages",
+                        typeConverter=TypeConverters.toBoolean)
+
+    @keyword_only
+    def __init__(self):
+        """
+        __init__(self)
+        """
+        super(PdfToText, self).__init__()
+        self._java_obj = self._new_java_obj("com.johnsnowlabs.reader.PdfToText", self.uid)
+
+    def setInputCol(self, value):
+        """
+        Sets the value of :py:attr:`inputCol`.
+        """
+        return self._set(inputCol=value)
+
+    def setOutputCol(self, value):
+        """
+        Sets the value of :py:attr:`outputCol`.
+        """
+        return self._set(outputCol=value)
+
+    def setPageNumCol(self, value):
+        """
+        Sets the value of :py:attr:`pageNumCol`.
+        """
+        return self._set(pageNumCol=value)
+
+    def setPartitionNum(self, value):
+        """
+        Sets the value of :py:attr:`partitionNum`.
+        """
+        return self._set(partitionNum=value)
+
+    def setStoreSplittedPdf(self, value):
+        """
+        Sets the value of :py:attr:`storeSplittedPdf`.
+        """
+        return self._set(storeSplittedPdf=value)
+
+    def setSplitPage(self, value):
+        """
+        Sets the value of :py:attr:`splitPage`.
+        """
+        return self._set(splitPage=value)
+
+    def setOnlyPageNum(self, value):
+        """
+        Sets the value of :py:attr:`onlyPageNum`.
+        """
+        return self._set(onlyPageNum=value)
+
+    def setTextStripper(self, value):
+        """
+        Sets the value of :py:attr:`textStripper`.
+        """
+        if isinstance(value, TextStripperType):
+            value = value.value
+        if value not in [i.value for i in TextStripperType]:
+            type_value = type(value)
+            raise ValueError(f"Param textStripper must be a 'TextStripperType' enum but got {type_value}.")
+        return self._set(textStripper=str(value))
+
+    def setSort(self, value):
+        """
+        Sets the value of :py:attr:`sort`.
+        """
+        return self._set(sort=value)

sparknlp/reader/sparknlp_reader.py

@@ -15,19 +15,39 @@ 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"`).
+    """Instantiates class to read documents in various formats.
 
     Parameters
     ----------
-    spark : SparkSession
-        The active Spark session.
+    params : spark
+        Spark session
     params : dict, optional
-        A dictionary with custom configurations.
+        Parameter with custom configuration
+
+    Notes
+    -----
+    This class can read HTML, email, PDF, MS Word, Excel, PowerPoint, and text files.
+
+    Examples
+    --------
+    >>> from sparknlp.reader import SparkNLPReader
+    >>> reader = SparkNLPReader(spark)
+
+    # Reading HTML
+    >>> html_df = reader.html("https://www.wikipedia.org")
+    >>> # Or with shorthand
+    >>> import sparknlp
+    >>> html_df = sparknlp.read().html("https://www.wikipedia.org")
+
+    # Reading PDF
+    >>> pdf_df = reader.pdf("home/user/pdfs-directory")
+    >>> # Or with shorthand
+    >>> pdf_df = sparknlp.read().pdf("home/user/pdfs-directory")
+
+    # Reading Email
+    >>> email_df = reader.email("home/user/emails-directory")
+    >>> # Or with shorthand
+    >>> email_df = sparknlp.read().email("home/user/emails-directory")
     """
 
     def __init__(self, spark, params=None):
@@ -59,11 +79,29 @@ class SparkNLPReader(ExtendedJavaWrapper):
         >>> 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)
         """
         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)
+        dataframe = self.getDataFrame(self.spark, jdf)
+        return dataframe
 
     def email(self, filePath):
         """Reads email files and returns a Spark DataFrame.
@@ -83,31 +121,201 @@ class SparkNLPReader(ExtendedJavaWrapper):
         >>> from sparknlp.reader import SparkNLPReader
         >>> email_df = SparkNLPReader(spark).email("home/user/emails-directory")
 
-        Using SparkNLP:
+        You can also use SparkNLP to simplify the process:
 
         >>> 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)
+
         """
         if not isinstance(filePath, str):
             raise TypeError("filePath must be a string")
         jdf = self._java_obj.email(filePath)
-        return self.getDataFrame(self.spark, jdf)
+        dataframe = self.getDataFrame(self.spark, jdf)
+        return dataframe
 
     def doc(self, docPath):
-        """Reads document files and returns a Spark DataFrame.
+        """Reads word document files and returns a Spark DataFrame.
 
         Parameters
         ----------
         docPath : str
-            Path to a document file.
+            Path to a word document file.
 
         Returns
         -------
         pyspark.sql.DataFrame
             A DataFrame containing parsed document content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> doc_df = SparkNLPReader().doc(spark, "home/user/word-directory")
+
+        You can use SparkNLP for one line of code
+        >>> import sparknlp
+        >>> doc_df = sparknlp.read().doc("home/user/word-directory")
+        >>> doc_df.show(truncate=False)
+
+        +----------------------------------------------------------------------------------------------------------------------------------------------------+
+        |doc                                                                                                                                                 |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+        +----------------------------------------------------------------------------------------------------------------------------------------------------+
+        |[{Table, Header Col 1, {}}, {Table, Header Col 2, {}}, {Table, Lorem ipsum, {}}, {Table, A Link example, {}}, {NarrativeText, Dolor sit amet, {}}]  |
+        +----------------------------------------------------------------------------------------------------------------------------------------------------+
+        >>> docsDf.printSchema()
+        root
+         |-- path: string (nullable = true)
+         |-- content: array (nullable = true)
+         |-- doc: 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)
+
         """
         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
+
+    def pdf(self, pdfPath):
+        if not isinstance(pdfPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.pdf(pdfPath)
+        dataframe = self.getDataFrame(self.spark, jdf)
+        return dataframe
+
+    def xls(self, docPath):
+        """Reads excel document files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to an excel document file.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed document content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> xlsDf = SparkNLPReader().xls(spark, "home/user/excel-directory")
+
+        You can use SparkNLP for one line of code
+        >>> import sparknlp
+        >>> xlsDf = sparknlp.read().xls("home/user/excel-directory")
+        >>> xlsDf.show(truncate=False)
+
+        +-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |xls                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+        +-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |[{Title, Financial performance, {SheetName -> Index}}, {Title, Topic\tPeriod\t\t\tPage, {SheetName -> Index}}, {NarrativeText, Quarterly revenue\tNine quarters to 30 June 2023\t\t\t1.0, {SheetName -> Index}}, {NarrativeText, Group financial performance\tFY 22\tFY 23\t\t2.0, {SheetName -> Index}}, {NarrativeText, Segmental results\tFY 22\tFY 23\t\t3.0, {SheetName -> Index}}, {NarrativeText, Segmental analysis\tFY 22\tFY 23\t\t4.0, {SheetName -> Index}}, {NarrativeText, Cash flow\tFY 22\tFY 23\t\t5.0, {SheetName -> Index}}, {Title, Operational metrics, {SheetName -> Index}}, {Title, Topic\tPeriod\t\t\tPage, {SheetName -> Index}}, {NarrativeText, Mobile customers\tNine quarters to 30 June 2023\t\t\t6.0, {SheetName -> Index}}, {NarrativeText, Fixed broadband customers\tNine quarters to 30 June 2023\t\t\t7.0, {SheetName -> Index}}, {NarrativeText, Marketable homes passed\tNine quarters to 30 June 2023\t\t\t8.0, {SheetName -> Index}}, {NarrativeText, TV customers\tNine quarters to 30 June 2023\t\t\t9.0, {SheetName -> Index}}, {NarrativeText, Converged customers\tNine quarters to 30 June 2023\t\t\t10.0, {SheetName -> Index}}, {NarrativeText, Mobile churn\tNine quarters to 30 June 2023\t\t\t11.0, {SheetName -> Index}}, {NarrativeText, Mobile data usage\tNine quarters to 30 June 2023\t\t\t12.0, {SheetName -> Index}}, {NarrativeText, Mobile ARPU\tNine quarters to 30 June 2023\t\t\t13.0, {SheetName -> Index}}, {Title, Other, {SheetName -> Index}}, {Title, Topic\tPeriod\t\t\tPage, {SheetName -> Index}}, {NarrativeText, Average foreign exchange rates\tNine quarters to 30 June 2023\t\t\t14.0, {SheetName -> Index}}, {NarrativeText, Guidance rates\tFY 23/24\t\t\t14.0, {SheetName -> Index}}]|
+        +-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+
+       >>> xlsDf.printSchema()
+       root
+        |-- path: string (nullable = true)
+        |-- content: binary (nullable = true)
+        |-- xls: 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)
+       """
+        if not isinstance(docPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.xls(docPath)
+        dataframe = self.getDataFrame(self.spark, jdf)
+        return dataframe
+
+    def ppt(self, docPath):
+        """
+        Reads power point document files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to an excel document file.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed document content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> pptDf = SparkNLPReader().ppt(spark, "home/user/powerpoint-directory")
+
+        You can use SparkNLP for one line of code
+        >>> import sparknlp
+        >>> pptDf = sparknlp.read().ppt("home/user/powerpoint-directory")
+        >>> pptDf.show(truncate=False)
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |ppt                                                                                                                                                                                                                                                                                                                      |
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |[{Title, Adding a Bullet Slide, {}}, {ListItem, • Find the bullet slide layout, {}}, {ListItem, – Use _TextFrame.text for first bullet, {}}, {ListItem, • Use _TextFrame.add_paragraph() for subsequent bullets, {}}, {NarrativeText, Here is a lot of text!, {}}, {NarrativeText, Here is some text in a text box!, {}}]|
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        """
+        if not isinstance(docPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.ppt(docPath)
+        dataframe = self.getDataFrame(self.spark, jdf)
+        return dataframe
+
+    def txt(self, docPath):
+        """Reads TXT files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to a TXT file.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed document content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> txtDf = SparkNLPReader().txt(spark, "home/user/txt/files")
+
+        You can use SparkNLP for one line of code
+        >>> import sparknlp
+        >>> txtDf = sparknlp.read().txt("home/user/txt/files")
+        >>> txtDf.show(truncate=False)
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |txt                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        |[{Title, BIG DATA ANALYTICS, {paragraph -> 0}}, {NarrativeText, Apache Spark is a fast and general-purpose cluster computing system.\nIt provides high-level APIs in Java, Scala, Python, and R., {paragraph -> 0}}, {Title, MACHINE LEARNING, {paragraph -> 1}}, {NarrativeText, Spark's MLlib provides scalable machine learning algorithms.\nIt includes tools for classification, regression, clustering, and more., {paragraph -> 1}}]|
+        +-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+        """
+        if not isinstance(docPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.txt(docPath)
         return self.getDataFrame(self.spark, jdf)

spark_nlp-5.5.3.dist-info/.uuid

@@ -1 +0,0 @@
-90f78083-0ee0-43e9-8240-7263731b6707