mirror of
https://github.com/overcuriousity/autopsy-flatpak.git
synced 2025-07-17 10:17:41 +00:00
vik- 174 : added min string length to language detection
This commit is contained in:
parent
47ce10ad90
commit
6b7df1ae47
@ -13,12 +13,13 @@ import org.sleuthkit.datamodel.AbstractFile;
|
||||
public interface TextLanguageIdentifier {
|
||||
|
||||
/**
|
||||
* attempts to identify the language of the given String and add it to the black board for the given {@code AbstractFile}
|
||||
* as a TSK_TEXT_LANGUAGE attribute on a TSK_GEN_INFO artifact.
|
||||
* attempts to identify the language of the given String and add it to the
|
||||
* black board for the given {@code AbstractFile} as a TSK_TEXT_LANGUAGE
|
||||
* attribute on a TSK_GEN_INFO artifact.
|
||||
*
|
||||
* @param extracted the String whose language is to be identified
|
||||
* @param extracted the String whose language is to be identified
|
||||
* @param sourceFile the AbstractFile the string is extracted from.
|
||||
* @return
|
||||
*/
|
||||
public void addLanguageToBlackBoard(String extracted, AbstractFile sourceFile);
|
||||
public void addLanguageToBlackBoard(String extracted, AbstractFile sourceFile);
|
||||
}
|
||||
|
@ -12,59 +12,65 @@ import org.sleuthkit.datamodel.BlackboardAttribute;
|
||||
import org.sleuthkit.datamodel.TskCoreException;
|
||||
|
||||
/**
|
||||
*TextLanguageIdentifier implementation based on a wrapped Tike LanguageIdentifier
|
||||
*
|
||||
*
|
||||
* TextLanguageIdentifier implementation based on a wrapped Tike
|
||||
* LanguageIdentifier
|
||||
*
|
||||
*
|
||||
* @author jmillman
|
||||
*/
|
||||
public class TikaLanguageIdentifier implements TextLanguageIdentifier {
|
||||
|
||||
private static final Logger logger = Logger.getLogger(TikaLanguageIdentifier.class.getName());
|
||||
private static final int MIN_STRING_LENGTH = 1000;
|
||||
|
||||
@Override
|
||||
public void addLanguageToBlackBoard(String extracted, AbstractFile sourceFile) {
|
||||
if (extracted.length() > MIN_STRING_LENGTH) {
|
||||
org.apache.tika.language.LanguageIdentifier li = new org.apache.tika.language.LanguageIdentifier(extracted);
|
||||
|
||||
org.apache.tika.language.LanguageIdentifier li = new org.apache.tika.language.LanguageIdentifier(extracted);
|
||||
|
||||
logger.log(Level.INFO, sourceFile.getName() + " detected language: " + li.getLanguage()
|
||||
+ "with " + ((li.isReasonablyCertain()) ? "HIGH" : "LOW") + "confidence");
|
||||
|
||||
BlackboardArtifact genInfo;
|
||||
try {
|
||||
genInfo = sourceFile.newArtifact(BlackboardArtifact.ARTIFACT_TYPE.TSK_GEN_INFO);
|
||||
logger.log(Level.INFO, sourceFile.getName() + " detected language: " + li.getLanguage()
|
||||
+ " with " + ((li.isReasonablyCertain()) ? "HIGH" : "LOW") + " confidence");
|
||||
|
||||
BlackboardAttribute textLang = new BlackboardAttribute(
|
||||
BlackboardAttribute.ATTRIBUTE_TYPE.TSK_TEXT_LANGUAGE.getTypeID(),
|
||||
KeywordSearchIngestModule.MODULE_NAME, li.getLanguage());
|
||||
BlackboardArtifact genInfo;
|
||||
try {
|
||||
genInfo = sourceFile.newArtifact(BlackboardArtifact.ARTIFACT_TYPE.TSK_GEN_INFO);
|
||||
|
||||
BlackboardAttribute textLang = new BlackboardAttribute(
|
||||
BlackboardAttribute.ATTRIBUTE_TYPE.TSK_TEXT_LANGUAGE.getTypeID(),
|
||||
KeywordSearchIngestModule.MODULE_NAME, li.getLanguage());
|
||||
|
||||
|
||||
genInfo.addAttribute(textLang);
|
||||
genInfo.addAttribute(textLang);
|
||||
|
||||
} catch (TskCoreException ex) {
|
||||
logger.log(Level.WARNING, "failed to add TSK_TEXT_LANGUAGE attribute to TSK_GEN_INFO artifact for file: " + sourceFile.getName(), ex);
|
||||
} catch (TskCoreException ex) {
|
||||
logger.log(Level.WARNING, "failed to add TSK_TEXT_LANGUAGE attribute to TSK_GEN_INFO artifact for file: " + sourceFile.getName(), ex);
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
}else{
|
||||
logger.info("extracted text too short, skipping language detection on " + sourceFile.getName());
|
||||
}
|
||||
} /* //attempt to verify that artifact with attribute was created
|
||||
ArrayList<BlackboardArtifact> arts;
|
||||
|
||||
|
||||
try {
|
||||
arts = Case.getCurrentCase().getSleuthkitCase().getBlackboardArtifacts(BlackboardArtifact.ARTIFACT_TYPE.TSK_GEN_INFO, sourceFile.getId());
|
||||
|
||||
for (BlackboardArtifact art : arts) {
|
||||
|
||||
List<BlackboardAttribute> attrs = art.getAttributes();
|
||||
for (BlackboardAttribute attr : attrs) {
|
||||
if (attr.getAttributeTypeID() == BlackboardAttribute.ATTRIBUTE_TYPE.TSK_TEXT_LANGUAGE.getTypeID()) {
|
||||
logger.log(Level.INFO, "succesfully added " + attr.getValueString() + " to gen info for:" + sourceFile.getName());
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch (TskCoreException ex) {
|
||||
Exceptions.printStackTrace(ex);
|
||||
}*/
|
||||
|
||||
|
||||
|
||||
/* //attempt to verify that artifact with attribute was created
|
||||
ArrayList<BlackboardArtifact> arts;
|
||||
|
||||
|
||||
try {
|
||||
arts = Case.getCurrentCase().getSleuthkitCase().getBlackboardArtifacts(BlackboardArtifact.ARTIFACT_TYPE.TSK_GEN_INFO, sourceFile.getId());
|
||||
|
||||
for (BlackboardArtifact art : arts) {
|
||||
|
||||
List<BlackboardAttribute> attrs = art.getAttributes();
|
||||
for (BlackboardAttribute attr : attrs) {
|
||||
if (attr.getAttributeTypeID() == BlackboardAttribute.ATTRIBUTE_TYPE.TSK_TEXT_LANGUAGE.getTypeID()) {
|
||||
logger.log(Level.INFO, "succesfully added " + attr.getValueString() + " to gen info for:" + sourceFile.getName());
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch (TskCoreException ex) {
|
||||
Exceptions.printStackTrace(ex);
|
||||
}*/
|
||||
}
|
||||
}
|
||||
}
|
Loading…
x
Reference in New Issue
Block a user