From 8b8c553bf2c7d46e6cc21ef6af6bd45220d5e68e Mon Sep 17 00:00:00 2001
From: adam-m <amalinowski@basistech.com>
Date: Thu, 24 Jan 2013 13:22:42 -0500
Subject: [PATCH] reenable processing of archive files (zip, tar, ...) by tika
 and string extractor, until after we have implemented the 7zip module

---
 .../autopsy/keywordsearch/AbstractFileStringExtract.java       | 3 ++-
 .../autopsy/keywordsearch/AbstractFileTikaTextExtract.java     | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileStringExtract.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileStringExtract.java
index f2f7318a32..72a9d7dadd 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileStringExtract.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileStringExtract.java
@@ -56,7 +56,8 @@ class AbstractFileStringExtract implements AbstractFileExtract {
     static final String[] UNSUPPORTED_EXTENSIONS = {
         //Archives 
         //Note: archive unpacker module will process these instead
-        "tar", "jar", "zip", "7z", "gzip", "bzip", "bzip2", "gz", "tgz", "cab", "rar", "arj", "dmg", "iso"};
+        //"tar", "jar", "zip", "7z", "gzip", "bzip", "bzip2", "gz", "tgz", "cab", "rar", "arj", "dmg", "iso"
+    };
 
     //disabled prepending of BOM
     //static {
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileTikaTextExtract.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileTikaTextExtract.java
index ed7d85eb96..e8f6f0ba42 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileTikaTextExtract.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/AbstractFileTikaTextExtract.java
@@ -69,6 +69,8 @@ public class AbstractFileTikaTextExtract implements AbstractFileExtract {
     // TODO: use type detection mechanism instead, and maintain supported MimeTypes, not extensions
     // supported extensions list from http://www.lucidimagination.com/devzone/technical-articles/content-extraction-tika
     static final String[] SUPPORTED_EXTENSIONS = {
+        //Archive (to be removed when we have archive module
+        "tar", "jar", "zip", "gzip", "bzip2", "gz", "tgz", "ar", "cpio", 
         //MS Office
         "doc", "dot", "docx", "docm", "dotx", "dotm",
         "xls", "xlw", "xlt", "xlsx", "xlsm", "xltx", "xltm",
-- 
GitLab