Merge pull request #2764 from dgrove727/2447_TikaTextExtractorLogging

2447 tika text extractor logging
This commit is contained in:
Richard Cordovano 2017-05-02 16:25:26 -04:00 committed by GitHub
commit b9f9028540
3 changed files with 11 additions and 5 deletions

View File

@ -1,7 +1,7 @@
/*
* Autopsy Forensic Browser
*
* Copyright 2011-2016 Basis Technology Corp.
* Copyright 2011-2017 Basis Technology Corp.
* Contact: carrier <at> sleuthkit <dot> org
*
* Licensed under the Apache License, Version 2.0 (the "License");
@ -25,6 +25,8 @@ import java.util.Arrays;
import java.util.List;
import java.util.logging.Level;
import net.htmlparser.jericho.Attributes;
import net.htmlparser.jericho.Config;
import static net.htmlparser.jericho.Config.LoggerProvider;
import net.htmlparser.jericho.Renderer;
import net.htmlparser.jericho.Source;
import net.htmlparser.jericho.StartTag;
@ -50,6 +52,11 @@ class HtmlTextExtractor extends FileTextExtractor {
"text/javascript" //NON-NLS
);
static {
// Disable Jericho HTML Parser log messages.
Config.LoggerProvider = LoggerProvider.DISABLED;
}
@Override
boolean isContentTypeSpecific() {
return true;

View File

@ -1,7 +1,7 @@
/*
* Autopsy Forensic Browser
*
* Copyright 2011-2016 Basis Technology Corp.
* Copyright 2011-2017 Basis Technology Corp.
* Contact: carrier <at> sleuthkit <dot> org
*
* Licensed under the Apache License, Version 2.0 (the "License");
@ -446,7 +446,7 @@ public final class KeywordSearchIngestModule implements FileIngestModule {
}
if (extractor == null) {
logger.log(Level.INFO, "No text extractor found for file id:{0}, name: {1}, detected format: {2}", new Object[]{aFile.getId(), aFile.getName(), detectedFormat}); //NON-NLS
// No text extractor found.
return false;
}
@ -561,7 +561,7 @@ public final class KeywordSearchIngestModule implements FileIngestModule {
return;
}
if (!extractTextAndIndex(aFile, fileType)) {
logger.log(Level.WARNING, "Text extractor not found for file. Extracting strings only. File: ''{0}'' (id:{1}).", new Object[]{aFile.getName(), aFile.getId()}); //NON-NLS
// Text extractor not found for file. Extract string only.
putIngestStatus(jobId, aFile.getId(), IngestStatus.SKIPPED_ERROR_TEXTEXTRACT);
} else {
putIngestStatus(jobId, aFile.getId(), IngestStatus.TEXT_INGESTED);

View File

@ -57,7 +57,6 @@ class TikaTextExtractor extends FileTextExtractor {
@Override
public void logWarning(final String msg, Exception ex) {
KeywordSearch.getTikaLogger().log(Level.WARNING, msg, ex);
logger.log(Level.WARNING, msg, ex); //NON-NLS }
}
@Override