mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-17 18:17:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #4026 from wschaeferB/4088-TextFileExtractorFix-4.8

Browse Source 
4088 text file extractor fix 4.8
This commit is contained in:
Richard Cordovano 2018-08-07 14:32:48 -04:00 committed by GitHub
commit 9078338963
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
View File

@ -570,7 +570,9 @@ public final class KeywordSearchIngestModule implements FileIngestModule {
putIngestStatus(jobId, aFile.getId(), IngestStatus.SKIPPED_ERROR_TEXTEXTRACT); putIngestStatus(jobId, aFile.getId(), IngestStatus.SKIPPED_ERROR_TEXTEXTRACT);
} }
if ((wasTextAdded == false) && (aFile.getNameExtension().equalsIgnoreCase("txt"))) { if ((wasTextAdded == false) && (aFile.getNameExtension().equalsIgnoreCase("txt") && !(aFile.getType().equals(TskData.TSK_DB_FILES_TYPE_ENUM.CARVED)))) {
//Carved Files should be the only type of unallocated files capable of a txt extension and
//should be ignored by the TextFileExtractor because they may contain more than one text encoding
try { try {
if (Ingester.getDefault().indexText(txtFileExtractor, aFile, context)) { if (Ingester.getDefault().indexText(txtFileExtractor, aFile, context)) {
putIngestStatus(jobId, aFile.getId(), IngestStatus.TEXT_INGESTED); putIngestStatus(jobId, aFile.getId(), IngestStatus.TEXT_INGESTED);

10
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/TextFileExtractor.java
View File

@ -17,8 +17,9 @@
* limitations under the License. * limitations under the License.
*/ */
package org.sleuthkit.autopsy.keywordsearch; package org.sleuthkit.autopsy.keywordsearch;
import java.io.IOException; import java.io.IOException;
import java.io.InputStream;
import java.io.BufferedInputStream;
import java.io.Reader; import java.io.Reader;
import java.util.logging.Level; import java.util.logging.Level;
import org.apache.tika.parser.txt.CharsetDetector; import org.apache.tika.parser.txt.CharsetDetector;
@ -53,15 +54,16 @@ final class TextFileExtractor extends ContentTextExtractor {
@Override @Override
public Reader getReader(Content source) throws TextExtractorException { public Reader getReader(Content source) throws TextExtractorException {
CharsetDetector detector = new CharsetDetector(); CharsetDetector detector = new CharsetDetector();
ReadContentInputStream stream = new ReadContentInputStream(source); //wrap stream in a BufferedInputStream so that it supports the mark/reset methods necessary for the CharsetDetector
InputStream stream = new BufferedInputStream(new ReadContentInputStream(source));
try { try {
detector.setText(stream); detector.setText(stream);
} catch (IOException ex) { } catch (IOException ex) {
throw new TextExtractorException("Unable to get string from detected text in UnicodeTextExtractor", ex); throw new TextExtractorException("Unable to get string from detected text in TextFileExtractor", ex);
} }
CharsetMatch match = detector.detect(); CharsetMatch match = detector.detect();
if (match.getConfidence() < MIN_MATCH_CONFIDENCE) { if (match.getConfidence() < MIN_MATCH_CONFIDENCE) {
throw new TextExtractorException("Text does not match any character set with a high enough confidence for UnicodeTextExtractor"); throw new TextExtractorException("Text does not match any character set with a high enough confidence for TextFileExtractor");
} }
return match.getReader(); return match.getReader();