indexer

LAYOUT & GENERAL

WORD CONTENT

TEMPLATES

FORMAT CONVERSION

DOCXPATH

DOCXUTILITIES

DOCXPATHUTILITIES

removeSection

PDFUTILITIES

DOCXCUSTOMIZER

customizeWordContent

PERFORMANCE

stream

ENCRYPT

encryptPDF

indexer

ADVANCED / PREMIUM

BASIC

Parses Word documents and return their contents.

Description

public Indexer(String source)

This class parses the content of DOCX documents and returns an array with these contents:

body
charts
comments
endnotes
fonts
footers
footnotes
headers
images
links
numberings
properties
sections
styles

Parameters

source

The path to the Word document to be parsed.

Return values

HashMap<String, IndexerElement>

Code samples

Example #1:

package examples.DOCXUtilities.indexer;

import java.util.HashMap;

import com.javadocx.Indexer;
import com.javadocx.Indexer.IndexerElement;

public class Sample1 {
    public static void main(String[] args) throws Exception {
        Indexer docx = new Indexer("document.docx");
        HashMap<String, IndexerElement> output = docx.getOutput();
        
        IndexerElement body = output.get("body");
        System.out.println(body.getText());
        System.out.println(body.getLinks());
        System.out.println(body.getImages());
        System.out.println(body.getSections());
        
        IndexerElement headers = output.get("headers");
        System.out.println(headers.getText());
        System.out.println(headers.getLinks());
        System.out.println(headers.getImages());
        
        IndexerElement footers = output.get("footers");
        System.out.println(footers.getText());
        System.out.println(footers.getLinks());
        System.out.println(footers.getImages());
        
        IndexerElement comments = output.get("comments");
        System.out.println(comments.getText());
        System.out.println(comments.getLinks());
        System.out.println(comments.getImages());
        
        IndexerElement endnotes = output.get("endnotes");
        System.out.println(endnotes.getText());
        System.out.println(endnotes.getLinks());
        System.out.println(endnotes.getImages());
        
        IndexerElement footnotes = output.get("footnotes");
        System.out.println(footnotes.getText());
        System.out.println(footnotes.getLinks());
        System.out.println(footnotes.getImages());
        
        IndexerElement fonts = output.get("fonts");
        System.out.println(fonts.getContents());
        
        IndexerElement properties = output.get("properties");
        System.out.println(properties.getCore());
        System.out.println(properties.getCustom());
        
        IndexerElement styles = output.get("styles");
        System.out.println(styles.getDocDefaults());
        System.out.println(styles.getStyles());
        System.out.println(styles.getNumberings());
    }
}