TikaTextExtractor.java File Reference

import com.google.common.io.CharSource;
import com.google.common.util.concurrent.ThreadFactoryBuilder;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackReader;
import java.io.Reader;
import java.nio.file.Paths;
import java.util.HashMap;
import java.util.List;
import java.util.Objects;
import java.util.Map;
import java.util.concurrent.Callable;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import java.util.concurrent.ThreadFactory;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
import java.util.logging.Level;
import java.util.stream.Collectors;
import org.apache.tika.Tika;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ParsingReader;
import org.apache.tika.parser.microsoft.OfficeParserConfig;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.openide.util.NbBundle;
import org.openide.modules.InstalledFileLocator;
import org.openide.util.Lookup;
import org.sleuthkit.autopsy.casemodule.Case;
import org.sleuthkit.autopsy.casemodule.NoCurrentCaseException;
import org.sleuthkit.autopsy.coreutils.ExecUtil;
import org.sleuthkit.autopsy.coreutils.ExecUtil.ProcessTerminator;
import org.sleuthkit.autopsy.coreutils.FileUtil;
import org.sleuthkit.autopsy.coreutils.Logger;
import org.sleuthkit.autopsy.coreutils.PlatformUtil;
import org.sleuthkit.autopsy.textextractors.configs.ImageConfig;
import org.sleuthkit.autopsy.datamodel.ContentUtils;
import org.sleuthkit.datamodel.AbstractFile;
import org.sleuthkit.datamodel.Content;
import org.sleuthkit.datamodel.ReadContentInputStream;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import com.google.common.collect.ImmutableMap;
import com.google.common.collect.ImmutableSet;
import java.io.InputStreamReader;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Set;
import org.apache.tika.config.TikaConfig;
import org.apache.tika.mime.MimeTypes;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig.OCR_STRATEGY;
import org.sleuthkit.autopsy.coreutils.ExecUtil.HybridTerminator;
import org.sleuthkit.autopsy.modules.filetypeid.FileTypeDetector;

Go to the source code of this file.

Classes
class	org.sleuthkit.autopsy.textextractors.TikaTextExtractor.CleanUpStream
class	org.sleuthkit.autopsy.textextractors.TikaTextExtractor.GetTikaReader
class	org.sleuthkit.autopsy.textextractors.TikaTextExtractor.ReaderCharSource
class	org.sleuthkit.autopsy.textextractors.TikaTextExtractor

Packages
package	org.sleuthkit.autopsy.textextractors