spark-nlp 2.6.3rc1__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/__init__.py

@@ -0,0 +1,17 @@
+#  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 pretrained pipelines and resources."""
+from sparknlp.pretrained.pretrained_pipeline import *
+from sparknlp.pretrained.resource_downloader import *
+from sparknlp.pretrained.utils import *

sparknlp/pretrained/pretrained_pipeline.py

@@ -0,0 +1,158 @@
+#  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.
+"""Contains classes for the PretrainedPipeline."""
+
+from pyspark.ml import PipelineModel
+from pyspark.sql import DataFrame
+
+from sparknlp.base import LightPipeline
+from sparknlp.pretrained.resource_downloader import ResourceDownloader
+
+
+class PretrainedPipeline:
+    """Loads a Represents a fully constructed and trained Spark NLP pipeline,
+    ready to be used.
+
+    This way, a whole pipeline can be defined in 1 line. Additionally, the
+    :class:`.LightPipeline` version of the model can be retrieved with member
+    :attr:`.light_model`.
+
+    For more extended examples see the `Pipelines page
+    <https://sparknlp.org/docs/en/pipelines>`_ and our `Github Model
+    Repository <https://github.com/JohnSnowLabs/spark-nlp-models>`_  for
+    available pipeline models.
+
+    Parameters
+    ----------
+    name : str
+        Name of the PretrainedPipeline. These can be gathered from the Pipelines
+        Page.
+    lang : str, optional
+        Langauge of the model, by default 'en'
+    remote_loc : str, optional
+        Link to the remote location of the model (if it was already downloaded),
+        by default None
+    parse_embeddings : bool, optional
+        Whether to parse embeddings, by default False
+    disk_location : str , optional
+        Path to locally stored PretrainedPipeline, by default None
+    """
+
+    def __init__(self, name, lang='en', remote_loc=None, parse_embeddings=False, disk_location=None):
+        if not disk_location:
+            self.model = ResourceDownloader().downloadPipeline(name, lang, remote_loc)
+        else:
+            self.model = PipelineModel.load(disk_location)
+        self.light_model = LightPipeline(self.model, parse_embeddings)
+
+    @staticmethod
+    def from_disk(path, parse_embeddings=False):
+        return PretrainedPipeline(None, None, None, parse_embeddings, path)
+
+    def annotate(self, target, column=None):
+        """Annotates the data provided, extracting the results.
+
+        The data should be either a list or a str.
+
+        Parameters
+        ----------
+        target : list or str
+            The data to be annotated
+
+        Returns
+        -------
+        List[dict] or dict
+            The result of the annotation
+
+        Examples
+        --------
+        >>> from sparknlp.pretrained import PretrainedPipeline
+        >>> explain_document_pipeline = PretrainedPipeline("explain_document_dl")
+        >>> result = explain_document_pipeline.annotate('U.N. official Ekeus heads for Baghdad.')
+        >>> result.keys()
+        dict_keys(['entities', 'stem', 'checked', 'lemma', 'document', 'pos', 'token', 'ner', 'embeddings', 'sentence'])
+        >>> result["ner"]
+        ['B-ORG', 'O', 'O', 'B-PER', 'O', 'O', 'B-LOC', 'O']
+        """
+
+        annotations = self.light_model.annotate(target)
+        return annotations
+
+    def fullAnnotate(self, target, optional_target=""):
+        """Annotates the data provided into `Annotation` type results.
+
+        The data should be either a list or a str.
+
+        Parameters
+        ----------
+        target : list or str
+            The data to be annotated
+
+        Returns
+        -------
+        List[Annotation]
+            The result of the annotation
+
+        Examples
+        --------
+        >>> from sparknlp.pretrained import PretrainedPipeline
+        >>> explain_document_pipeline = PretrainedPipeline("explain_document_dl")
+        >>> result = explain_document_pipeline.fullAnnotate('U.N. official Ekeus heads for Baghdad.')
+        >>> result[0].keys()
+        dict_keys(['entities', 'stem', 'checked', 'lemma', 'document', 'pos', 'token', 'ner', 'embeddings', 'sentence'])
+        >>> result[0]["ner"]
+        [Annotation(named_entity, 0, 2, B-ORG, {'word': 'U.N'}),
+        Annotation(named_entity, 3, 3, O, {'word': '.'}),
+        Annotation(named_entity, 5, 12, O, {'word': 'official'}),
+        Annotation(named_entity, 14, 18, B-PER, {'word': 'Ekeus'}),
+        Annotation(named_entity, 20, 24, O, {'word': 'heads'}),
+        Annotation(named_entity, 26, 28, O, {'word': 'for'}),
+        Annotation(named_entity, 30, 36, B-LOC, {'word': 'Baghdad'}),
+        Annotation(named_entity, 37, 37, O, {'word': '.'})]
+        """
+        annotations = self.light_model.fullAnnotate(target, optional_target)
+        return annotations
+
+    def fullAnnotateImage(self, path_to_image):
+        """Annotates the data provided into `Annotation` type results.
+
+        The data should be either a list or a str.
+
+        Parameters
+        ----------
+        path_to_image : list or str
+            Source path of image, list of paths to images
+
+        Returns
+        -------
+        List[AnnotationImage]
+            The result of the annotation
+        """
+        pipeline = self.light_model
+        return pipeline.fullAnnotateImage(path_to_image)
+
+    def transform(self, data):
+        """Transforms the input dataset with Spark.
+
+        Parameters
+        ----------
+        data : :class:`pyspark.sql.DataFrame`
+            input dataset
+
+        Returns
+        -------
+        :class:`pyspark.sql.DataFrame`
+            transformed dataset
+        """
+        return self.model.transform(data)

sparknlp/pretrained/resource_downloader.py

@@ -0,0 +1,216 @@
+#  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.
+"""Contains classes for the ResourceDownloader."""
+
+import sys
+import threading
+
+from py4j.protocol import Py4JJavaError
+from pyspark.ml import PipelineModel
+
+import sparknlp.internal as _internal
+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":
+            print("Can not find the model to download please check the name!")
+        else:
+            print("Approximate size to download " + file_size)
+            stop_threads = False
+            t1 = threading.Thread(target=printProgress, args=(lambda: stop_threads,))
+            t1.start()
+            try:
+                j_obj = _internal._DownloadModel(reader.name, name, language, remote_loc, j_dwn).apply()
+            except Py4JJavaError as e:
+                sys.stdout.write("\n" + str(e))
+                raise e
+            finally:
+                stop_threads = True
+                t1.join()
+
+            return reader(classname=None, java_model=j_obj)
+
+    @staticmethod
+    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":
+            print("Can not find the model to download please check the name!")
+        else:
+            print("Approx size to download " + file_size)
+            stop_threads = False
+            t1 = threading.Thread(target=printProgress, args=(lambda: stop_threads,))
+            t1.start()
+            try:
+                j_obj = _internal._DownloadPipeline(name, language, remote_loc).apply()
+                jmodel = PipelineModel._from_java(j_obj)
+            finally:
+                stop_threads = True
+                t1.join()
+
+            return jmodel
+
+    @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/pretrained/utils.py

@@ -0,0 +1,35 @@
+#  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.
+"""Contains utilities for pretrained annotators and pipelines."""
+
+import sys
+import time
+
+
+def printProgress(stop):
+    states = [' | ', ' / ', ' — ', ' \\ ']
+    nextc = 0
+    while True:
+        sys.stdout.write('\r[{}]'.format(states[nextc]))
+        sys.stdout.flush()
+        time.sleep(2.5)
+        nextc = nextc + 1 if nextc < 3 else 0
+        if stop():
+            sys.stdout.write('\r[{}]'.format('OK!'))
+            sys.stdout.flush()
+            break
+
+    sys.stdout.write('\n')
+    return
+

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"