com.apache.pdfbox.ocr.tesseract.BadScan.java Source code

Introduction

Here is the source code for com.apache.pdfbox.ocr.tesseract.BadScan.java

Source

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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.
 */

package com.apache.pdfbox.ocr.tesseract;

import static org.junit.Assert.assertEquals;
import org.junit.Test;
import org.junit.Ignore;

import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;

public class BadScan {
    @Test
    public void textBadScan() {
        try {
            PDDocument document = PDDocument.load(new File("src/test/resources/samples/scansmpl.pdf"));
            PDFRenderer renderer = new PDFRenderer(document);
            BufferedImage image = renderer.renderImage(0, 3);

            TessBaseAPI api = new TessBaseAPI();
            boolean init = api.init("eng");
            api.setBufferedImage(image);
            String text = api.getUTF8Text();
            System.out.println(text);
            api.end();
            assertEquals(init, true);
            document.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}