Package com.github.hakenadu.javalangchains.chains.data.reader

Class ReadDocumentsFromInMemoryPdfChain

java.lang.Object

com.github.hakenadu.javalangchains.chains.data.reader.ReadDocumentsFromPdfChainBase<ReadDocumentsFromInMemoryPdfChain.InMemoryPdf>

com.github.hakenadu.javalangchains.chains.data.reader.ReadDocumentsFromInMemoryPdfChain

All Implemented Interfaces:

Chain<ReadDocumentsFromInMemoryPdfChain.InMemoryPdf,Stream<Map<String,String>>>

public class ReadDocumentsFromInMemoryPdfChain
extends ReadDocumentsFromPdfChainBase<ReadDocumentsFromInMemoryPdfChain.InMemoryPdf>

Utilizes Apache PDFBox to read documents from a byte array

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ReadDocumentsFromInMemoryPdfChain.InMemoryPdf	wrapper for an in memory pdf (byte array + title)

Nested classes/interfaces inherited from class com.github.hakenadu.javalangchains.chains.data.reader.ReadDocumentsFromPdfChainBase

ReadDocumentsFromPdfChainBase.PdDocumentWrapper, ReadDocumentsFromPdfChainBase.PdfReadMode

Constructor Summary

Constructors

Constructor	Description
ReadDocumentsFromInMemoryPdfChain()	creates a ReadDocumentsFromInMemoryPdfChain which reads the whole pdf as a document
ReadDocumentsFromInMemoryPdfChain(ReadDocumentsFromPdfChainBase.PdfReadMode readMode)	creates a ReadDocumentsFromInMemoryPdfChain
ReadDocumentsFromInMemoryPdfChain(ReadDocumentsFromPdfChainBase.PdfReadMode readMode, boolean parallel)	creates a ReadDocumentsFromInMemoryPdfChain

Method Summary

Modifier and Type	Method	Description
protected Stream<ReadDocumentsFromPdfChainBase.PdDocumentWrapper>	loadPdDocuments(ReadDocumentsFromInMemoryPdfChain.InMemoryPdf input)	load a pdf from an input instance

Methods inherited from class com.github.hakenadu.javalangchains.chains.data.reader.ReadDocumentsFromPdfChainBase

run

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.github.hakenadu.javalangchains.chains.Chain

chain

Constructor Details

ReadDocumentsFromInMemoryPdfChain

public ReadDocumentsFromInMemoryPdfChain(ReadDocumentsFromPdfChainBase.PdfReadMode readMode, boolean parallel)

creates a ReadDocumentsFromInMemoryPdfChain

Parameters:

readMode - ReadDocumentsFromPdfChainBase.readMode

parallel - ReadDocumentsFromPdfChainBase.parallel

ReadDocumentsFromInMemoryPdfChain

public ReadDocumentsFromInMemoryPdfChain(ReadDocumentsFromPdfChainBase.PdfReadMode readMode)

creates a ReadDocumentsFromInMemoryPdfChain

Parameters:

readMode - ReadDocumentsFromPdfChainBase.readMode

ReadDocumentsFromInMemoryPdfChain

public ReadDocumentsFromInMemoryPdfChain()

creates a ReadDocumentsFromInMemoryPdfChain which reads the whole pdf as a document

Method Details

loadPdDocuments

protected Stream<ReadDocumentsFromPdfChainBase.PdDocumentWrapper> loadPdDocuments(ReadDocumentsFromInMemoryPdfChain.InMemoryPdf input) throws IOException

Description copied from class: ReadDocumentsFromPdfChainBase

load a pdf from an input instance

Specified by:

loadPdDocuments in class ReadDocumentsFromPdfChainBase<ReadDocumentsFromInMemoryPdfChain.InMemoryPdf>

Parameters:

input - input instance

Returns:

PDDocument

Throws:

IOException - on error loading pdf