Package org.springframework.ai.reader.tika

Class TikaDocumentReader

java.lang.Object

org.springframework.ai.reader.tika.TikaDocumentReader

All Implemented Interfaces:

Supplier<List<Document>>, DocumentReader

public class TikaDocumentReader
extends Object
implements DocumentReader

A document reader that leverages Apache Tika to extract text from a variety of document formats, such as PDF, DOC/DOCX, PPT/PPTX, and HTML. For a comprehensive list of supported formats, refer to: https://tika.apache.org/3.0.0-BETA2/formats.html. This reader directly provides the extracted text without any additional formatting. All extracted texts are encapsulated within a Document instance. If you require more specialized handling for PDFs, consider using the PagePdfDocumentReader or ParagraphPdfDocumentReader.

Author:

Christian Tzolov

Field Summary

Fields

Modifier and Type	Field	Description
static final String	METADATA_SOURCE	Metadata key representing the source of the document.

Constructor Summary

Constructors

Constructor	Description
TikaDocumentReader(String resourceUrl)	Constructor initializing the reader with a given resource URL.
TikaDocumentReader(String resourceUrl, ExtractedTextFormatter textFormatter)	Constructor initializing the reader with a given resource URL and a text formatter.
TikaDocumentReader(org.springframework.core.io.Resource resource)	Constructor initializing the reader with a resource.
TikaDocumentReader(org.springframework.core.io.Resource resource, ExtractedTextFormatter textFormatter)	Constructor initializing the reader with a resource and a text formatter.
TikaDocumentReader(org.springframework.core.io.Resource resource, ContentHandler contentHandler, ExtractedTextFormatter textFormatter)	Constructor initializing the reader with a resource, content handler, and a text formatter.

Method Summary

Modifier and Type	Method	Description
List<Document>	get()	Extracts and returns the list of documents from the resource.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.springframework.ai.document.DocumentReader

read

Field Details

METADATA_SOURCE

public static final String METADATA_SOURCE

Metadata key representing the source of the document.

See Also:

• Constant Field Values

Constructor Details

TikaDocumentReader

public TikaDocumentReader(String resourceUrl)

Constructor initializing the reader with a given resource URL.

Parameters:

resourceUrl - URL to the resource

TikaDocumentReader

public TikaDocumentReader(String resourceUrl,
 ExtractedTextFormatter textFormatter)

Constructor initializing the reader with a given resource URL and a text formatter.

Parameters:

resourceUrl - URL to the resource

textFormatter - Formatter for the extracted text

TikaDocumentReader

public TikaDocumentReader(org.springframework.core.io.Resource resource)

Constructor initializing the reader with a resource.

Parameters:

resource - Resource pointing to the document

TikaDocumentReader

public TikaDocumentReader(org.springframework.core.io.Resource resource,
 ExtractedTextFormatter textFormatter)

Constructor initializing the reader with a resource and a text formatter. This constructor will create a BodyContentHandler that allows for reading large PDFs (constrained only by memory)

Parameters:

resource - Resource pointing to the document

textFormatter - Formatter for the extracted text

TikaDocumentReader

public TikaDocumentReader(org.springframework.core.io.Resource resource,
 ContentHandler contentHandler,
 ExtractedTextFormatter textFormatter)

Constructor initializing the reader with a resource, content handler, and a text formatter.

Parameters:

resource - Resource pointing to the document

contentHandler - Handler to manage content extraction

textFormatter - Formatter for the extracted text

Method Details

get

public List<Document> get()

Extracts and returns the list of documents from the resource.

Specified by:

get in interface Supplier<List<Document>>

Returns:

List of extracted Document