mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-17 02:07:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use domain validator instead of list of file extensions to reduce email false positives.

Browse Source
This commit is contained in:
esaunders 2017-02-22 17:50:58 -05:00
parent da9b27d170
commit 5225a0e47d
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java
View File

@ -32,6 +32,7 @@ import java.util.logging.Level;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.commons.lang.StringUtils;
import org.apache.commons.validator.routines.DomainValidator;
import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrQuery.SortClause;
import org.apache.solr.client.solrj.SolrRequest;
@ -83,7 +84,6 @@ final class RegexQuery implements KeywordSearchQuery {
private String escapedQuery;
private final int MIN_EMAIL_ADDR_LENGTH = 8;
private final Pattern INVALID_EMAIL_PATTERN = Pattern.compile(".*\\.(dll|txt|exe|jpg|xml)$");
private final ListMultimap<Keyword, KeywordHit> hitsMultiMap = ArrayListMultimap.create();
@ -281,9 +281,10 @@ final class RegexQuery implements KeywordSearchQuery {
if (originalKeyword.getArtifactAttributeType() == BlackboardAttribute.ATTRIBUTE_TYPE.TSK_EMAIL) {
// Reduce false positives by eliminating email address hits that are either
// too short or end with well known file externsions.
if (hit.length() < MIN_EMAIL_ADDR_LENGTH || INVALID_EMAIL_PATTERN.matcher(hit).matches()) {
break;
// too short or are not for valid top level domains.
if (hit.length() < MIN_EMAIL_ADDR_LENGTH
|| !DomainValidator.getInstance(true).isValidTld(hit.substring(hit.lastIndexOf('.')))) {
continue;
}
}