benchmark/src/main/java/org/apache/pdfbox/benchmark/TextExtraction.java

/*
 * 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 org.apache.pdfbox.benchmark;

import java.io.File;
import java.io.IOException;
import java.util.concurrent.TimeUnit;

import org.apache.logging.log4j.Level;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.core.config.Configurator;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.openjdk.jmh.annotations.Benchmark;
import org.openjdk.jmh.annotations.BenchmarkMode;
import org.openjdk.jmh.annotations.Mode;
import org.openjdk.jmh.annotations.OutputTimeUnit;
import org.openjdk.jmh.infra.Blackhole;

public class TextExtraction {

    static final String PDF32000_2008 = "target/pdfs/PDF32000_2008.pdf";

    static {
        Configurator.setAllLevels(LogManager.getRootLogger().getName(), Level.OFF);
        java.util.logging.Logger.getLogger("org.apache").setLevel(java.util.logging.Level.OFF);
    }
    

    @Benchmark
    @OutputTimeUnit(TimeUnit.MILLISECONDS)
    @BenchmarkMode(Mode.AverageTime)
    public void extractPDFSpecUnsorted(Blackhole blackhole) throws IOException {
        try (PDDocument pdf = Loader.loadPDF(new File(PDF32000_2008)))
        {
            PDFTextStripper pdfStripper = new PDFTextStripper();
            pdfStripper.setSortByPosition(false);
            String parsedText = pdfStripper.getText(pdf);
            blackhole.consume(parsedText);
        }
    }

    @Benchmark
    @OutputTimeUnit(TimeUnit.MILLISECONDS)
    @BenchmarkMode(Mode.AverageTime)
    public void extractPDFSpecSorted(Blackhole blackhole) throws IOException {
        try (PDDocument pdf = Loader.loadPDF(new File(PDF32000_2008)))
        {
            PDFTextStripper pdfStripper = new PDFTextStripper();
            pdfStripper.setSortByPosition(true);
            String parsedText = pdfStripper.getText(pdf);
            blackhole.consume(parsedText);
        }
    }
}