stashing

KeywordSearch/ivy.xml

@@ -18,7 +18,8 @@
 	    <dependency conf="solr-war->default" org="org.apache.solr" name="solr" rev="4.10.4" transitive="false" /> <!-- the war file for embedded Solr 4 -->
         
         <dependency conf="solr-libs->default" name="solr-cell" rev="8.11.2" org="org.apache.solr"/>
-        
+        <!-- https://mvnrepository.com/artifact/org.apache.lucene/lucene-core -->
+        <!-- <dependency org="org.apache.lucene" name="lucene-core" rev="8.11.2"/> -->       
         <!-- Autopsy -->
         <dependency conf="autopsy->default" org="org.apache.solr" name="solr-solrj" rev="8.11.2"/>
         <dependency conf="autopsy->default" org="com.optimaize.languagedetector" name="language-detector" rev="0.6"/>       

KeywordSearch/nbproject/project.properties

@@ -44,6 +44,7 @@ file.reference.stax2-api-4.2.1.jar=release/modules/ext/stax2-api-4.2.1.jar
 file.reference.woodstox-core-6.2.4.jar=release/modules/ext/woodstox-core-6.2.4.jar
 file.reference.zookeeper-3.8.0.jar=release/modules/ext/zookeeper-3.8.0.jar
 file.reference.zookeeper-jute-3.8.0.jar=release/modules/ext/zookeeper-jute-3.8.0.jar
+file.reference.lucene-core-8.11.2.jar=release/modules/ext/lucene-core-8.11.2.jar
 javac.source=1.8
 javac.compilerargs=-Xlint -Xlint:-serial
 license.file=../LICENSE-2.0.txt

KeywordSearch/nbproject/project.xml

@@ -418,6 +418,10 @@
                 <runtime-relative-path>ext/zookeeper-jute-3.8.0.jar</runtime-relative-path>
                 <binary-origin>release/modules/ext/zookeeper-jute-3.8.0.jar</binary-origin>
             </class-path-extension>
+            <class-path-extension>
+                <runtime-relative-path>ext/lucene-core-8.11.2.jar</runtime-relative-path>
+                <binary-origin>release/modules/ext/lucene-core-8.11.2.jar</binary-origin>
+            </class-path-extension>
         </data>
     </configuration>
 </project>

KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/InlineSearcher.java

@@ -19,6 +19,7 @@
 package org.sleuthkit.autopsy.keywordsearch;
 
 import com.twelvemonkeys.lang.StringUtil;
+import java.io.IOException;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
@@ -27,6 +28,11 @@
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 import org.apache.commons.validator.routines.DomainValidator;
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.openide.util.Exceptions;
 import org.sleuthkit.autopsy.casemodule.Case;
 import org.sleuthkit.autopsy.casemodule.NoCurrentCaseException;
 import org.sleuthkit.autopsy.coreutils.Logger;
@@ -71,24 +77,24 @@ void searchChunk(Chunk chunk) throws TskCoreException {
 
                 List<KeywordHit> keywordHits = new ArrayList<>();
                 if (originalKeyword.searchTermIsLiteral()) {
-                    if (!originalKeyword.searchTermIsWholeWord()) {
+//                    if (!originalKeyword.searchTermIsWholeWord()) {
                         if (StringUtil.containsIgnoreCase(chunk.geLowerCasedChunk(), originalKeyword.getSearchTerm())) {
 
                             keywordHits.addAll(createKeywordHits(chunk, originalKeyword));
                         }
-                    } else {
-                        String REGEX_FIND_WORD="\\b\\W*%s\\W*\\b"; //"[\\w[\\.']]*%s[\\w[\\.']]*"; //"(?i).*?\\b%s\\b.*?";
-                        String regex=String.format(REGEX_FIND_WORD, Pattern.quote(originalKeyword.getSearchTerm().toLowerCase()));
+//                    } else {
+//                        String REGEX_FIND_WORD="\\b\\W*%s\\W*\\b"; //"[\\w[\\.']]*%s[\\w[\\.']]*"; //"(?i).*?\\b%s\\b.*?";
+//                        String regex=String.format(REGEX_FIND_WORD, Pattern.quote(originalKeyword.getSearchTerm().toLowerCase()));
 //                        if(chunk.geLowerCasedChunk().matches(regex)) {
 //                            keywordHits.addAll(createKeywordHits(chunk, originalKeyword));
 //                        }     
 
-                       Pattern pattern = Pattern.compile(regex, java.util.regex.Pattern.CASE_INSENSITIVE);
-                       Matcher matcher = pattern.matcher(chunk.geLowerCasedChunk());
-                       if (matcher.find()) {
-                            keywordHits.addAll(createKeywordHits(chunk, originalKeyword));
-                        }
-                    }
+//                       Pattern pattern = Pattern.compile(regex, java.util.regex.Pattern.CASE_INSENSITIVE);
+//                       Matcher matcher = pattern.matcher(chunk.geLowerCasedChunk());
+//                       if (matcher.find()) {
+//                            keywordHits.addAll(createKeywordHits(chunk, originalKeyword));
+//                        }
+//                    }
                 } else {
                     String regex = originalKeyword.getSearchTerm();
 
@@ -163,6 +169,7 @@ private List<KeywordHit> createKeywordHits(Chunk chunk, Keyword originalKeyword)
             } else {
                 String REGEX_FIND_WORD="\\b\\W*%s\\W*\\b"; 
                 searchPattern=String.format(REGEX_FIND_WORD, Pattern.quote(originalKeyword.getSearchTerm().toLowerCase()));
+                testingTokenizer(chunk, originalKeyword);
             }
         } else {
             searchPattern = keywordString;
@@ -353,4 +360,28 @@ void makeArtifacts(Content content, IngestJobContext context, long sourceID) {
             map.clear();
         }
     }
+    
+    private void testingTokenizer(Chunk chunk, Keyword originalKeyword) {
+        try {
+            List<String> tokens = analyze(chunk.geLowerCasedChunk(), new StandardAnalyzer());
+            for(String token: tokens) {
+                if(token.equals(originalKeyword.getSearchTerm())) {
+                    
+                }
+            }
+        } catch (IOException ex) {
+            Exceptions.printStackTrace(ex);
+        }
+    }
+    
+    public List<String> analyze(String text, Analyzer analyzer) throws IOException{
+        List<String> result = new ArrayList<>();
+        TokenStream tokenStream = analyzer.tokenStream("sampleName", text);
+        CharTermAttribute attr = tokenStream.addAttribute(CharTermAttribute.class);
+        tokenStream.reset();
+        while(tokenStream.incrementToken()) {
+           result.add(attr.toString());
+        }       
+        return result;
+    }
 }