</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox</artifactId>
			<version>${pdfbox.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>pdfbox-tools</artifactId>
			<version>${pdfbox.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.pdfbox</groupId>
			<artifactId>fontbox</artifactId>

- **License**: Apache 2.0
- **DI**: LastaFlute DI
- **Repo**: https://github.com/codelibs/fess-crawler

### Tech Stack

- **HTTP**: Apache HttpComponents 4.5+ and 5.x (switchable)
- **Extraction**: Apache Tika, POI, PDFBox
- **Testing**: JUnit 4, UTFlute, Mockito, Testcontainers
- **Storage**: In-memory (default), OpenSearch (optional)
- **Cloud**: AWS SDK v2 (S3), Google Cloud Storage

### Protocols

				max="${backup.max.history}" compressionLevel="9" />
		</RollingFile>
		<Rewrite name="AppFile">
			<AppenderRef ref="AppRollingFile" />
			<ErrorToWarnRewritePolicy loggers="org.apache.fontbox,org.apache.pdfbox,org.apache.poi" />
		</Rewrite>
		<RollingFile name="StatsFile" fileName="${log.file.basedir}/fess-urls.log"
			filePattern="${log.file.basedir}/fess-urls${backup.date.suffix}-%i.log.gz">
			<PatternLayout>

import org.apache.commons.lang3.time.DurationFormatUtils;
import org.apache.commons.text.StringEscapeUtils;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.apache.pdfbox.util.DateConverter;
import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.app.web.base.FessAdminAction;
import org.codelibs.fess.app.web.base.login.FessLoginAssist;

-Dlog4j.shutdownHookEnabled=false\n\
-Dlog4j2.formatMsgNoLookups=true\n\
-Dlog4j2.disable.jmx=true\n\
-Dlog4j.skipJansi=true\n\
-Dsun.java2d.cmm=sun.java2d.cmm.kcms.KcmsServiceProvider\n\
-Dorg.apache.pdfbox.rendering.UsePureJavaCMYKConversion=true\n\


jvm.suggest.options=\
-Djava.awt.headless=true\n\
-Dfile.encoding=UTF-8\n\
-Djna.nosys=true\n\
-Djdk.io.permissionsUseCanonicalPath=true\n\

     * -Dlog4j2.formatMsgNoLookups=true<br>
     * -Dlog4j2.disable.jmx=true<br>
     * -Dlog4j.skipJansi=true<br>
     * -Dsun.java2d.cmm=sun.java2d.cmm.kcms.KcmsServiceProvider<br>
     * -Dorg.apache.pdfbox.rendering.UsePureJavaCMYKConversion=true<br>
     *  */
    String JVM_CRAWLER_OPTIONS = "jvm.crawler.options";

    /** The key of the configuration. e.g. -Djava.awt.headless=true<br>
     * -Dfile.encoding=UTF-8<br>

            ownTmpDir = new File(tmpDir, "fessTmpDir_" + sessionId);
            if (ownTmpDir.mkdirs()) {
                cmdList.add("-Djava.io.tmpdir=" + ownTmpDir.getAbsolutePath());
                cmdList.add("-Dpdfbox.fontcache=" + ownTmpDir.getAbsolutePath());
            } else {
                ownTmpDir = null;
            }
        }

        cmdList.add(ComponentUtil.getThumbnailManager().getThumbnailPathOption());