spark-nlp 4.2.6__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/partition/partition_transformer.py

@@ -0,0 +1,200 @@
+#  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.
+"""Contains the PartitionTransformer class for reading various types of documents into chunks."""
+from sparknlp.common import *
+from sparknlp.partition.partition_properties import *
+
+
+class PartitionTransformer(
+    AnnotatorModel,
+    HasEmailReaderProperties,
+    HasExcelReaderProperties,
+    HasHTMLReaderProperties,
+    HasPowerPointProperties,
+    HasTextReaderProperties,
+    HasChunkerProperties
+):
+    """
+    The PartitionTransformer annotator allows you to use the Partition feature more smoothly
+    within existing Spark NLP workflows, enabling seamless reuse of your pipelines.
+
+    It supports reading from files, URLs, in-memory strings, or byte arrays, and works
+    within a Spark NLP pipeline.
+
+    Supported formats include:
+    - Plain text
+    - HTML
+    - Word (.doc/.docx)
+    - Excel (.xls/.xlsx)
+    - PowerPoint (.ppt/.pptx)
+    - Email files (.eml, .msg)
+    - PDFs
+
+    Parameters
+    ----------
+    inputCols : list of str
+        Names of input columns (typically from DocumentAssembler).
+    outputCol : str
+        Name of the column to store the output.
+    contentType : str
+        The type of content: e.g., "text", "url", "file", etc.
+    headers : dict, optional
+        Headers to be used if content type is a URL.
+
+    Examples
+    --------
+    >>> dataset = spark.createDataFrame([
+    ...     ("https://www.blizzard.com",),
+    ... ], ["text"])
+
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+
+    >>> partition = PartitionTransformer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("partition") \\
+    ...     .setContentType("url") \\
+    ...     .setHeaders({"Accept-Language": "es-ES"})
+
+    >>> pipeline = Pipeline(stages=[documentAssembler, partition])
+    >>> pipelineModel = pipeline.fit(dataset)
+    >>> resultDf = pipelineModel.transform(dataset)
+    >>> resultDf.show()
+    +--------------------+--------------------+--------------------+
+    |                text|            document|           partition|
+    +--------------------+--------------------+--------------------+
+    |https://www.blizz...|[{Title, Juegos d...|[{document, 0, 16...|
+    |https://www.googl...|[{Title, Gmail Im...|[{document, 0, 28...|
+    +--------------------+--------------------+--------------------+
+    """
+
+    name = "PartitionTransformer"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    contentPath = Param(
+        Params._dummy(),
+        "contentPath",
+        "Path to the content source",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setContentPath(self, value):
+        return self._set(contentPath=value)
+
+    def getContentPath(self):
+        return self.getOrDefault(self.contentPath)
+
+    contentType = Param(
+        Params._dummy(),
+        "contentType",
+        "Set the content type to load following MIME specification",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setContentType(self, value):
+        return self._set(contentType=value)
+
+    def getContentType(self):
+        return self.getOrDefault(self.contentType)
+
+    storeContent = Param(
+        Params._dummy(),
+        "storeContent",
+        "Whether to include the raw file content in the output DataFrame as a separate 'content' column, alongside the structured output.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setStoreContent(self, value):
+        return self._set(storeContent=value)
+
+    def getStoreContent(self):
+        return self.getOrDefault(self.storeContent)
+
+    titleFontSize = Param(
+        Params._dummy(),
+        "titleFontSize",
+        "Minimum font size threshold used as part of heuristic rules to detect title elements based on formatting (e.g., bold, centered, capitalized).",
+        typeConverter=TypeConverters.toInt
+    )
+
+    def setTitleFontSize(self, value):
+        return self._set(titleFontSize=value)
+
+    def getTitleFontSize(self):
+        return self.getOrDefault(self.titleFontSize)
+
+    inferTableStructure = Param(
+        Params._dummy(),
+        "inferTableStructure",
+        "Whether to generate an HTML table representation from structured table content. When enabled, a full <table> element is added alongside cell-level elements, based on row and column layout.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setInferTableStructure(self, value):
+        return self._set(inferTableStructure=value)
+
+    def getInferTableStructure(self):
+        return self.getOrDefault(self.inferTableStructure)
+
+    includePageBreaks = Param(
+        Params._dummy(),
+        "includePageBreaks",
+        "Whether to detect and tag content with page break metadata. In Word documents, this includes manual and section breaks. In Excel files, this includes page breaks based on column boundaries.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    def setIncludePageBreaks(self, value):
+        return self._set(includePageBreaks=value)
+
+    def getIncludePageBreaks(self):
+        return self.getOrDefault(self.includePageBreaks)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.partition.PartitionTransformer",
+                 java_model=None):
+        super(PartitionTransformer, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        DOUBLE_PARAGRAPH_PATTERN = r"(?:\s*\n\s*){2,}"
+
+        self._setDefault(
+            contentPath="",
+            contentType="text/plain",
+            storeContent=False,
+            titleFontSize = 9,
+            inferTableStructure=False,
+            includePageBreaks=False,
+            addAttachmentContent=False,
+            cellSeparator="\t",
+            appendCells=False,
+            timeout=0,
+            includeSlideNotes=False,
+            titleLengthSize=50,
+            groupBrokenParagraphs=False,
+            paragraphSplit=DOUBLE_PARAGRAPH_PATTERN,
+            shortLineWordThreshold=5,
+            maxLineCount=2000,
+            threshold=0.1,
+            chunkingStrategy="",
+            maxCharacters=100,
+            newAfterNChars=-1,
+            overlap=0,
+            combineTextUnderNChars=0,
+            overlapAll=False
+        )

sparknlp/pretrained/pretrained_pipeline.py

@@ -29,7 +29,7 @@ class PretrainedPipeline:
     :attr:`.light_model`.
 
     For more extended examples see the `Pipelines page
-    <https://nlp.johnsnowlabs.com/docs/en/pipelines>`_ and our `Github Model
+    <https://sparknlp.org/docs/en/pipelines>`_ and our `Github Model
     Repository <https://github.com/JohnSnowLabs/spark-nlp-models>`_  for
     available pipeline models.
 

sparknlp/pretrained/resource_downloader.py

@@ -24,9 +24,64 @@ from sparknlp.pretrained.utils import printProgress
 
 
 class ResourceDownloader(object):
+    """Downloads and manages resources, pretrained models/pipelines.
+
+    Usually you will not need to use this class directly. It is called by the
+    `pretrained()` function of annotators.
+
+    However, you can use this class to list the available pretrained resources.
+
+    Examples
+    --------
+    If you want to list all NerDLModels for the english language you can run:
+
+    >>> ResourceDownloader.showPublicModels("NerDLModel", "en")
+    +-------------+------+---------+
+    | Model       | lang | version |
+    +-------------+------+---------+
+    | onto_100    | en   | 2.1.0   |
+    | onto_300    | en   | 2.1.0   |
+    | ner_dl_bert | en   | 2.2.0   |
+    |  ...        | ...  | ...     |
+
+
+    Similarly for Pipelines:
+
+    >>> ResourceDownloader.showPublicPipelines("en")
+    +------------------+------+---------+
+    | Pipeline         | lang | version |
+    +------------------+------+---------+
+    | dependency_parse | en   | 2.0.2   |
+    | check_spelling   | en   | 2.1.0   |
+    | match_datetime   | en   | 2.1.0   |
+    |  ...             | ...  | ...     |
+
+    """
 
     @staticmethod
     def downloadModel(reader, name, language, remote_loc=None, j_dwn='PythonResourceDownloader'):
+        """Downloads and loads a model with the default downloader. Usually this method
+        does not need to be called directly, as it is called by the `pretrained()`
+        method of the annotator.
+
+        Parameters
+        ----------
+        reader : obj
+           Class to read the model for
+        name : str
+            Name of the pretrained model
+        language : str
+            Language of the model
+        remote_loc : str, optional
+            Directory of the Spark NLP Folder, by default None
+        j_dwn : str, optional
+            Which java downloader to use, by default 'PythonResourceDownloader'
+
+        Returns
+        -------
+        AnnotatorModel
+            Loaded pretrained annotator/pipeline
+        """
         print(name + " download started this may take some time.")
         file_size = _internal._GetResourceSize(name, language, remote_loc).apply()
         if file_size == "-1":
@@ -46,12 +101,42 @@ class ResourceDownloader(object):
                 t1.join()
 
             return reader(classname=None, java_model=j_obj)
+
     @staticmethod
-    def downloadModelDirectly(name, remote_loc="public/models"):
-        _internal._DownloadModelDirectly(name, remote_loc).apply()
+    def downloadModelDirectly(name, remote_loc="public/models", unzip=True):
+        """Downloads a model directly to the cache folder.
+        You can use to copy-paste the s3 URI from the model hub  and download the model.
+        For available s3 URI and models, please see the `Models Hub <https://sparknlp.org/models>`__.
+        Parameters
+        ----------
+        name : str
+            Name of the model or s3 URI
+        remote_loc : str, optional
+            Directory of the remote Spark NLP Folder, by default "public/models"
+        unzip : Bool, optional
+            Used to unzip model, by default 'True'
+        """
+        _internal._DownloadModelDirectly(name, remote_loc, unzip).apply()
+
 
     @staticmethod
     def downloadPipeline(name, language, remote_loc=None):
+        """Downloads and loads a pipeline with the default downloader.
+
+        Parameters
+        ----------
+        name : str
+            Name of the pipeline
+        language : str
+            Language of the pipeline
+        remote_loc : str, optional
+            Directory of the remote Spark NLP Folder, by default None
+
+        Returns
+        -------
+        PipelineModel
+            The loaded pipeline
+        """
         print(name + " download started this may take some time.")
         file_size = _internal._GetResourceSize(name, language, remote_loc).apply()
         if file_size == "-1":
@@ -72,21 +157,60 @@ class ResourceDownloader(object):
 
     @staticmethod
     def clearCache(name, language, remote_loc=None):
+        """Clears the cache entry of a model.
+
+        Parameters
+        ----------
+        name : str
+            Name of the model
+        language : en
+            Language of the model
+        remote_loc : str, optional
+            Directory of the remote Spark NLP Folder, by default None
+        """
         _internal._ClearCache(name, language, remote_loc).apply()
 
     @staticmethod
     def showPublicModels(annotator=None, lang=None, version=None):
+        """Prints all pretrained models for a particular annotator model, that are
+        compatible with a version of Spark NLP. If any of the optional arguments are not
+        set, the filter is not considered.
+
+        Parameters
+        ----------
+        annotator : str, optional
+            Name of the annotator to filer, by default None
+        lang : str, optional
+            Language of the models to filter, by default None
+        version : str, optional
+            Version of Spark NLP to filter, by default None
+        """
         print(_internal._ShowPublicModels(annotator, lang, version).apply())
 
     @staticmethod
     def showPublicPipelines(lang=None, version=None):
+        """Prints all pretrained models for a particular annotator model, that are
+        compatible with a version of Spark NLP. If any of the optional arguments are not
+        set, the filter is not considered.
+
+        Parameters
+        ----------
+        lang : str, optional
+            Language of the models to filter, by default None
+        version : str, optional
+            Version of Spark NLP to filter, by default None
+        """
         print(_internal._ShowPublicPipelines(lang, version).apply())
 
     @staticmethod
     def showUnCategorizedResources():
+        """Shows models or pipelines in the metadata which has not been categorized yet.
+        """
         print(_internal._ShowUnCategorizedResources().apply())
 
     @staticmethod
     def showAvailableAnnotators():
+        """Shows all available annotators in Spark NLP.
+        """
         print(_internal._ShowAvailableAnnotators().apply())
 

sparknlp/reader/__init__.py

@@ -0,0 +1,15 @@
+#  Copyright 2017-2022 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.
+"""Module for reading different files types."""
+from sparknlp.reader.sparknlp_reader import *

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 +1,190 @@
+#  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 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 documents as either a single string or multiple strings per page.
+    Input is a column with binary content of PDF files. Output is a column with extracted text,
+    with options to include page numbers or split pages.
+
+    Parameters
+    ----------
+    pageNumCol : str, optional
+        Page number output column name.
+    partitionNum : int, optional
+        Number of partitions (default is 0).
+    storeSplittedPdf : bool, optional
+        Whether to store content of split PDFs (default is False).
+    splitPage : bool, optional
+        Enable/disable splitting per page (default is True).
+    onlyPageNum : bool, optional
+        Whether to extract only page numbers (default is False).
+    textStripper : str or TextStripperType, optional
+        Defines layout and formatting type.
+    sort : bool, optional
+        Enable/disable sorting content per page (default is False).
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.reader import *
+    >>> from pyspark.ml import Pipeline
+    >>> pdf_path = "Documents/files/pdf"
+    >>> data_frame = spark.read.format("binaryFile").load(pdf_path)
+    >>> pdf_to_text = PdfToText().setStoreSplittedPdf(True)
+    >>> pipeline = Pipeline(stages=[pdf_to_text])
+    >>> pipeline_model = pipeline.fit(data_frame)
+    >>> pdf_df = pipeline_model.transform(data_frame)
+    >>> pdf_df.show()
+    +--------------------+--------------------+
+    |                path|    modificationTime|
+    +--------------------+--------------------+
+    |file:/Users/paula...|2025-05-15 11:33:...|
+    |file:/Users/paula...|2025-05-15 11:33:...|
+    +--------------------+--------------------+
+    >>> pdf_df.printSchema()
+    root
+     |-- path: string (nullable = true)
+     |-- modificationTime: timestamp (nullable = true)
+     |-- length: long (nullable = true)
+     |-- text: string (nullable = true)
+     |-- height_dimension: integer (nullable = true)
+     |-- width_dimension: integer (nullable = true)
+     |-- content: binary (nullable = true)
+     |-- exception: string (nullable = true)
+     |-- pagenum: integer (nullable = true)
+    """
+    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)
+
+    extractCoordinates = Param(Params._dummy(), "extractCoordinates",
+                               "Force extract coordinates of text.",
+                               typeConverter=TypeConverters.toBoolean)
+
+    normalizeLigatures = Param(Params._dummy(), "normalizeLigatures",
+                               "Whether to convert ligature chars such as 'fl' into its corresponding chars (e.g., {'f', 'l'}).",
+                               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)
+
+    def setExtractCoordinates(self, value):
+        """
+        Sets the value of :py:attr:`extractCoordinates`.
+        """
+        return self._set(extractCoordinates=value)
+
+    def setNormalizeLigatures(self, value):
+        """
+        Sets the value of :py:attr:`normalizeLigatures`.
+        """
+        return self._set(normalizeLigatures=value)