mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-08 22:29:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Greg DiCristofaro 2025-01-08 15:28:32 -05:00
parent 143b20794d
commit cfd3c4e28c
No known key found for this signature in database
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
Core/src/org/sleuthkit/autopsy/textextractors/TikaTextExtractor.java
View File

@ -49,7 +49,6 @@ import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser; import org.apache.tika.parser.Parser;
import org.apache.tika.parser.ParsingReader; import org.apache.tika.parser.ParsingReader;
import org.apache.tika.parser.microsoft.OfficeParserConfig; import org.apache.tika.parser.microsoft.OfficeParserConfig;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig; import org.apache.tika.parser.pdf.PDFParserConfig;
import org.openide.util.NbBundle; import org.openide.util.NbBundle;
import org.openide.modules.InstalledFileLocator; import org.openide.modules.InstalledFileLocator;
@ -77,6 +76,7 @@ import java.util.ArrayList;
import java.util.Set; import java.util.Set;
import org.apache.tika.config.TikaConfig; import org.apache.tika.config.TikaConfig;
import org.apache.tika.mime.MimeTypes; import org.apache.tika.mime.MimeTypes;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig.OCR_STRATEGY; import org.apache.tika.parser.pdf.PDFParserConfig.OCR_STRATEGY;
import org.sleuthkit.autopsy.coreutils.ExecUtil.HybridTerminator; import org.sleuthkit.autopsy.coreutils.ExecUtil.HybridTerminator;
import org.sleuthkit.autopsy.modules.filetypeid.FileTypeDetector; import org.sleuthkit.autopsy.modules.filetypeid.FileTypeDetector;
@ -283,7 +283,12 @@ final class TikaTextExtractor implements TextExtractor {
if (isOcrSupported()) { if (isOcrSupported()) {
// Configure OCR for Tika if it chooses to run OCR // Configure OCR for Tika if it chooses to run OCR
// during extraction // during extraction
TesseractOCRConfig ocrConfig = getTesseractConfig(); TesseractOCRConfig ocrConfig = new TesseractOCRConfig();
String tesseractFolder = TESSERACT_PATH.getParent();
// coming from https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=109454096#TikaOCR-OverridingDefaultConfiguration
ocrConfig.getOtherTesseractConfig().put("tessdataPath", PlatformUtil.getOcrLanguagePacksPath());
ocrConfig.getOtherTesseractConfig().put("tesseractPath", tesseractFolder);
ocrConfig.setLanguage(languagePacks);
parseContext.set(TesseractOCRConfig.class, ocrConfig); parseContext.set(TesseractOCRConfig.class, ocrConfig);
// Configure how Tika handles OCRing PDFs // Configure how Tika handles OCRing PDFs
@ -344,16 +349,6 @@ final class TikaTextExtractor implements TextExtractor {
future.cancel(true); future.cancel(true);
} }
} }
private TesseractOCRConfig getTesseractConfig() {
// GVDTODO look at this: https://tika.apache.org/3.0.0/configuring.html
// String tesseractFolder = TESSERACT_PATH.getParent();
// ocrConfig.setTesseractPath(tesseractFolder);
// ocrConfig.setLanguage(languagePacks);
// ocrConfig.setTessdataPath(PlatformUtil.getOcrLanguagePacksPath());
return null;
}
/** /**
* Run OCR and return the file stream produced by Tesseract. * Run OCR and return the file stream produced by Tesseract.