spark-nlp 6.0.5__py2.py3-none-any.whl → 6.1.1__py2.py3-none-any.whl

sparknlp/reader/reader2table.py

@@ -0,0 +1,163 @@
+#  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 TypeConverters, Params, Param
+
+from sparknlp.common import AnnotatorType
+from sparknlp.internal import AnnotatorTransformer
+from sparknlp.partition.partition_properties import *
+
+class Reader2Table(
+    AnnotatorTransformer,
+    HasEmailReaderProperties,
+    HasExcelReaderProperties,
+    HasHTMLReaderProperties,
+    HasPowerPointProperties,
+    HasTextReaderProperties
+):
+    name = 'Reader2Table'
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    contentPath = Param(
+        Params._dummy(),
+        "contentPath",
+        "contentPath path to files to read",
+        typeConverter=TypeConverters.toString
+    )
+
+    outputCol = Param(
+        Params._dummy(),
+        "outputCol",
+        "output column name",
+        typeConverter=TypeConverters.toString
+    )
+
+    contentType = Param(
+        Params._dummy(),
+        "contentType",
+        "Set the content type to load following MIME specification",
+        typeConverter=TypeConverters.toString
+    )
+
+    explodeDocs = Param(
+        Params._dummy(),
+        "explodeDocs",
+        "whether to explode the documents into separate rows",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    flattenOutput = Param(
+        Params._dummy(),
+        "flattenOutput",
+        "If true, output is flattened to plain text with minimal metadata",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    titleThreshold = Param(
+        Params._dummy(),
+        "titleThreshold",
+        "Minimum font size threshold for title detection in PDF docs",
+        typeConverter=TypeConverters.toFloat
+    )
+
+    outputFormat = Param(
+        Params._dummy(),
+        "outputFormat",
+        "Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.",
+        typeConverter=TypeConverters.toString
+    )
+
+    @keyword_only
+    def __init__(self):
+        super(Reader2Table, self).__init__(classname="com.johnsnowlabs.reader.Reader2Table")
+        self._setDefault(outputCol="document")
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)
+
+    def setContentPath(self, value):
+        """Sets content path.
+
+        Parameters
+        ----------
+        value : str
+            contentPath path to files to read
+        """
+        return self._set(contentPath=value)
+
+    def setContentType(self, value):
+        """
+        Set the content type to load following MIME specification
+
+        Parameters
+        ----------
+        value : str
+            content type to load following MIME specification
+        """
+        return self._set(contentType=value)
+
+    def setExplodeDocs(self, value):
+        """Sets whether to explode the documents into separate rows.
+
+
+        Parameters
+        ----------
+        value : boolean
+        Whether to explode the documents into separate rows
+        """
+        return self._set(explodeDocs=value)
+
+    def setOutputCol(self, value):
+        """Sets output column name.
+
+        Parameters
+        ----------
+        value : str
+            Name of the Output Column
+        """
+        return self._set(outputCol=value)
+
+    def setFlattenOutput(self, value):
+        """Sets whether to flatten the output to plain text with minimal metadata.
+
+        Parameters
+        ----------
+        value : bool
+            If true, output is flattened to plain text with minimal metadata
+        """
+        return self._set(flattenOutput=value)
+
+    def setTitleThreshold(self, value):
+        """Sets the minimum font size threshold for title detection in PDF documents.
+
+        Parameters
+        ----------
+        value : float
+            Minimum font size threshold for title detection in PDF docs
+        """
+        return self._set(titleThreshold=value)
+
+    def setOutputFormat(self, value):
+        """Sets the output format for the table content.
+
+        Parameters
+        ----------
+        value : str
+            Output format for the table content. Options are 'plain-text' or 'html-table'. Default is 'json-table'.
+        """
+        return self._set(outputFormat=value)

sparknlp/reader/sparknlp_reader.py

@@ -413,4 +413,49 @@ class SparkNLPReader(ExtendedJavaWrapper):
         if not isinstance(filePath, str):
             raise TypeError("filePath must be a string")
         jdf = self._java_obj.md(filePath)
+        return self.getDataFrame(self.spark, jdf)
+
+    def csv(self, csvPath):
+        """Reads CSV files and returns a Spark DataFrame.
+
+        Parameters
+        ----------
+        docPath : str
+            Path to an CSV file or a directory containing CSV files.
+
+        Returns
+        -------
+        pyspark.sql.DataFrame
+            A DataFrame containing parsed CSV content.
+
+        Examples
+        --------
+        >>> from sparknlp.reader import SparkNLPReader
+        >>> csv_df = SparkNLPReader(spark).csv("home/user/csv-directory")
+
+        You can use SparkNLP for one line of code
+
+        >>> import sparknlp
+        >>> csv_df = sparknlp.read().csv("home/user/csv-directory")
+        >>> csv_df.show(truncate=False)
+        +-----------------------------------------------------------------------------------------------------------------------------------------+
+        |csv                                                                                                                                      |
+        +-----------------------------------------------------------------------------------------------------------------------------------------+
+        |[{NarrativeText, Alice 100 Bob 95, {}}, {Table, <table><tr><td>Alice</td><td>100</td></tr><tr><td>Bob</td><td>95</td></tr></table>, {}}] |
+        +-----------------------------------------------------------------------------------------------------------------------------------------+
+
+        >>> csv_df.printSchema()
+        root
+         |-- path: string (nullable = true)
+         |-- csv: 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(csvPath, str):
+            raise TypeError("docPath must be a string")
+        jdf = self._java_obj.csv(csvPath)
         return self.getDataFrame(self.spark, jdf)