Source code for sparknlp.reader.reader2table

#  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 *

[docs]class Reader2Table( AnnotatorTransformer, HasEmailReaderProperties, HasExcelReaderProperties, HasHTMLReaderProperties, HasPowerPointProperties, HasTextReaderProperties ):
[docs] name = 'Reader2Table'
[docs] outputAnnotatorType = AnnotatorType.DOCUMENT
[docs] contentPath = Param( Params._dummy(), "contentPath", "contentPath path to files to read", typeConverter=TypeConverters.toString )
[docs] outputCol = Param( Params._dummy(), "outputCol", "output column name", typeConverter=TypeConverters.toString )
[docs] contentType = Param( Params._dummy(), "contentType", "Set the content type to load following MIME specification", typeConverter=TypeConverters.toString )
[docs] explodeDocs = Param( Params._dummy(), "explodeDocs", "whether to explode the documents into separate rows", typeConverter=TypeConverters.toBoolean )
[docs] flattenOutput = Param( Params._dummy(), "flattenOutput", "If true, output is flattened to plain text with minimal metadata", typeConverter=TypeConverters.toBoolean )
[docs] titleThreshold = Param( Params._dummy(), "titleThreshold", "Minimum font size threshold for title detection in PDF docs", typeConverter=TypeConverters.toFloat )
[docs] 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
[docs] def setParams(self): kwargs = self._input_kwargs return self._set(**kwargs)
[docs] def setContentPath(self, value): """Sets content path. Parameters ---------- value : str contentPath path to files to read """ return self._set(contentPath=value)
[docs] 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)
[docs] 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)
[docs] def setOutputCol(self, value): """Sets output column name. Parameters ---------- value : str Name of the Output Column """ return self._set(outputCol=value)
[docs] 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)
[docs] 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)
[docs] 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)