diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Ingester.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Ingester.java
index 88eaffbed1c7d0070bf34daa9c51f2d04eb58d60..994dfb9161e828cac501a40287b46144a08e0616 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Ingester.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/Ingester.java
@@ -36,6 +36,8 @@
import org.sleuthkit.autopsy.healthmonitor.TimingMetric;
import org.sleuthkit.autopsy.ingest.IngestJobContext;
import org.sleuthkit.autopsy.keywordsearch.Chunker.Chunk;
+import org.sleuthkit.autopsy.textextractors.TextExtractor;
+import org.sleuthkit.autopsy.textextractors.TextExtractorFactory;
import org.sleuthkit.datamodel.AbstractFile;
import org.sleuthkit.datamodel.BlackboardArtifact;
import org.sleuthkit.datamodel.Content;
@@ -203,71 +205,69 @@ < T extends SleuthkitVisitableItem> boolean indexAndSearchStrings(Reader sourceR
// TODO (JIRA-3118): Cancelled text indexing does not propagate cancellation to clients
private < T extends SleuthkitVisitableItem> boolean indexTextAndSearch(Reader sourceReader, long sourceID, String sourceName, T source, IngestJobContext context, boolean doLanguageDetection, boolean indexIntoSolr, List<String> keywordListNames) throws Ingester.IngesterException {
int numChunks = 0; //unknown until chunking is done
-
+
Map<String, String> contentFields = Collections.unmodifiableMap(getContentFields(source));
Optional<Language> language = Optional.empty();
InlineSearcher searcher = new InlineSearcher(keywordListNames);
//Get a reader for the content of the given source
try (BufferedReader reader = new BufferedReader(sourceReader)) {
Chunker chunker = new Chunker(reader);
-
+
while (chunker.hasNext()) {
if (context != null && context.fileIngestIsCancelled()) {
logger.log(Level.INFO, "File ingest cancelled. Cancelling keyword search indexing of {0}", sourceName);
return false;
}
-
+
Chunk chunk = chunker.next();
+ String chunkId = "";
+ if (indexIntoSolr) {
+ Map<String, Object> fields = new HashMap<>(contentFields);
+ chunkId = Server.getChunkIdString(sourceID, numChunks + 1);
+ fields.put(Server.Schema.ID.toString(), chunkId);
+ fields.put(Server.Schema.CHUNK_SIZE.toString(), String.valueOf(chunk.getBaseChunkLength()));
+
+ if (doLanguageDetection) {
+ int size = Math.min(chunk.getBaseChunkLength(), LANGUAGE_DETECTION_STRING_SIZE);
+ language = languageSpecificContentIndexingHelper.detectLanguageIfNeeded(chunk.toString().substring(0, size));
+
+ // only do language detection on the first chunk of the document
+ doLanguageDetection = false;
+ }
+ language.ifPresent(lang -> languageSpecificContentIndexingHelper.updateLanguageSpecificFields(fields, chunk, lang));
+ try {
+ //add the chunk text to Solr index
+ indexChunk(chunk.toString(), chunk.geLowerCasedChunk(), sourceName, fields);
+ // add mini chunk when there's a language specific field
+ if (chunker.hasNext() && language.isPresent()) {
+ languageSpecificContentIndexingHelper.indexMiniChunk(chunk, sourceName, new HashMap<>(contentFields), chunkId, language.get());
+ }
+ numChunks++;
+ } catch (Ingester.IngesterException ingEx) {
+ logger.log(Level.WARNING, "Ingester had a problem with extracted string from file '" //NON-NLS
+ + sourceName + "' (id: " + sourceID + ").", ingEx);//NON-NLS
+
+ throw ingEx; //need to rethrow to signal error and move on
+ }
+ }
if(keywordListNames != null) {
searcher.searchChunk(chunk);
}
-
- if(!indexIntoSolr) {
- continue;
- }
-
- Map<String, Object> fields = new HashMap<>(contentFields);
- String chunkId = Server.getChunkIdString(sourceID, numChunks + 1);
- fields.put(Server.Schema.ID.toString(), chunkId);
- fields.put(Server.Schema.CHUNK_SIZE.toString(), String.valueOf(chunk.getBaseChunkLength()));
-
- if (doLanguageDetection) {
- int size = Math.min(chunk.getBaseChunkLength(), LANGUAGE_DETECTION_STRING_SIZE);
- language = languageSpecificContentIndexingHelper.detectLanguageIfNeeded(chunk.toString().substring(0, size));
-
- // only do language detection on the first chunk of the document
- doLanguageDetection = false;
- }
- language.ifPresent(lang -> languageSpecificContentIndexingHelper.updateLanguageSpecificFields(fields, chunk, lang));
- try {
- //add the chunk text to Solr index
- indexChunk(chunk.toString(), chunk.geLowerCasedChunk(), sourceName, fields);
- // add mini chunk when there's a language specific field
- if (chunker.hasNext() && language.isPresent()) {
- languageSpecificContentIndexingHelper.indexMiniChunk(chunk, sourceName, new HashMap<>(contentFields), chunkId, language.get());
- }
- numChunks++;
- } catch (Ingester.IngesterException ingEx) {
- logger.log(Level.WARNING, "Ingester had a problem with extracted string from file '" //NON-NLS
- + sourceName + "' (id: " + sourceID + ").", ingEx);//NON-NLS
-
- throw ingEx; //need to rethrow to signal error and move on
- }
}
if (chunker.hasException()) {
logger.log(Level.WARNING, "Error chunking content from " + sourceID + ": " + sourceName, chunker.getException());
return false;
- }
-
- searcher.makeArtifacts((Content)source, context, sourceID);
+ }
+
+ searcher.makeArtifacts((Content) source, context, sourceID);
} catch (Exception ex) {
logger.log(Level.WARNING, "Unexpected error, can't read content stream from " + sourceID + ": " + sourceName, ex);//NON-NLS
return false;
} finally {
if (context != null && context.fileIngestIsCancelled()) {
return false;
- } else if(indexIntoSolr){
+ } else if (indexIntoSolr) {
Map<String, Object> fields = new HashMap<>(contentFields);
//after all chunks, index just the meta data, including the numChunks, of the parent file
fields.put(Server.Schema.NUM_CHUNKS.toString(), Integer.toString(numChunks));
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/InlineSearcher.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/InlineSearcher.java
index f8313ace377c63788b5a463f3a67f3db5520dec0..9cfef448121497cf91966a9a93153fddeedf0045 100755
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/InlineSearcher.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/InlineSearcher.java
@@ -77,11 +77,17 @@ void searchChunk(Chunk chunk) throws TskCoreException {
keywordHits.addAll(createKeywordHits(chunk, originalKeyword));
}
} else {
- String REGEX_FIND_WORD="(?i).*?\\b%s\\b.*?";
+ 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)) {
+// 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));
- }
+ }
}
} else {
String regex = originalKeyword.getSearchTerm();
@@ -152,7 +158,12 @@ private List<KeywordHit> createKeywordHits(Chunk chunk, Keyword originalKeyword)
* and possessives (e.g. hacker's). This obviously works for English
* but is probably not sufficient for other languages.
*/
- searchPattern = "[\\w[\\.']]*" + java.util.regex.Pattern.quote(keywordString.toLowerCase()) + "[\\w[\\.']]*";
+ if(!originalKeyword.searchTermIsWholeWord()) {
+ searchPattern = "[\\w[\\.']]*" + java.util.regex.Pattern.quote(keywordString.toLowerCase()) + "[\\w[\\.']]*";
+ } else {
+ String REGEX_FIND_WORD="\\b\\W*%s\\W*\\b";
+ searchPattern=String.format(REGEX_FIND_WORD, Pattern.quote(originalKeyword.getSearchTerm().toLowerCase()));
+ }
} else {
searchPattern = keywordString;
}
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
index 7b0caa6c76d4013aebc782c46caae195802be65b..9dcd3984dd3f0fc74a084e8de0545aec841f8776 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchIngestModule.java
@@ -38,6 +38,7 @@
import java.util.logging.Level;
import java.util.stream.Collectors;
import org.apache.tika.mime.MimeTypes;
+import org.openide.util.Exceptions;
import org.openide.util.Lookup;
import org.openide.util.NbBundle;
import org.openide.util.NbBundle.Messages;
@@ -688,8 +689,7 @@ private boolean extractStringsAndIndex(AbstractFile aFile) {
if (context.fileIngestIsCancelled()) {
return true;
}
- TextExtractor stringsExtractor = TextExtractorFactory.getStringsExtractor(aFile, stringsExtractionContext);
- Reader extractedTextReader = stringsExtractor.getReader();
+ Reader extractedTextReader = KeywordSearchUtil.getReader(aFile, stringsExtractionContext);
if (Ingester.getDefault().indexAndSearchStrings(extractedTextReader, aFile.getId(), aFile.getName(), aFile, KeywordSearchIngestModule.this.context, settings.isIndexToSolrEnabled(), settings.getNamesOfEnabledKeyWordLists())) {
putIngestStatus(jobId, aFile.getId(), IngestStatus.STRINGS_INGESTED);
return true;
@@ -698,11 +698,11 @@ private boolean extractStringsAndIndex(AbstractFile aFile) {
putIngestStatus(jobId, aFile.getId(), IngestStatus.SKIPPED_ERROR_TEXTEXTRACT);
return false;
}
- } catch (IngesterException | TextExtractor.InitReaderException ex) {
+ } catch (IngesterException | TextExtractor.InitReaderException | TextExtractorFactory.NoTextExtractorFound ex) {
logger.log(Level.WARNING, "Failed to extract strings and ingest, file '" + aFile.getName() + "' (id: " + aFile.getId() + ").", ex); //NON-NLS
putIngestStatus(jobId, aFile.getId(), IngestStatus.SKIPPED_ERROR_INDEXING);
return false;
- }
+ }
}
/**
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchUtil.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchUtil.java
index d828f14585d0ee60f06ee0c142b9efeef847b5df..e5f39885a5416876735536e1c8d8e6481a169789 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchUtil.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KeywordSearchUtil.java
@@ -20,10 +20,18 @@
import java.awt.Component;
import java.io.File;
+import java.io.Reader;
import java.util.regex.Matcher;
import org.sleuthkit.autopsy.coreutils.Logger;
import javax.swing.JOptionPane;
+import org.openide.util.Lookup;
import org.openide.windows.WindowManager;
+import org.sleuthkit.autopsy.textextractors.TextExtractor;
+import org.sleuthkit.autopsy.textextractors.TextExtractorFactory;
+import org.sleuthkit.datamodel.AbstractFile;
+import org.sleuthkit.datamodel.BlackboardArtifact;
+import org.sleuthkit.datamodel.Content;
+import org.sleuthkit.datamodel.TskCoreException;
class KeywordSearchUtil {
@@ -181,4 +189,40 @@ static boolean isXMLList(String absPath) {
//TODO: make this more robust, if necessary
return new File(absPath).getName().endsWith(".xml"); //NON-NLS
}
+
+ static Reader getReader(Content content) throws TextExtractorFactory.NoTextExtractorFound, TextExtractor.InitReaderException{
+ return getReader(content, null);
+ }
+
+ static Reader getReader(Content content, Lookup stringsExtractionContext) throws TextExtractorFactory.NoTextExtractorFound, TextExtractor.InitReaderException{
+ Reader reader = null;
+ if (content instanceof BlackboardArtifact) {
+ BlackboardArtifact artifact = (BlackboardArtifact) content;
+ if (artifact.getArtifactID() > 0) {
+ /*
+ * Artifact indexing is only supported for artifacts that use
+ * negative artifact ids to avoid overlapping with the object
+ * ids of other types of Content.
+ */
+ return null;
+ }
+ TextExtractor blackboardExtractor = TextExtractorFactory.getExtractor(content, null);
+ reader = blackboardExtractor.getReader();
+
+ } else if (content instanceof AbstractFile) {
+ TextExtractor stringsExtractor = TextExtractorFactory.getStringsExtractor( content, stringsExtractionContext);
+ reader = stringsExtractor.getReader();
+ } else {
+ try {
+ TextExtractor contentExtractor = TextExtractorFactory.getExtractor(content, null);
+ reader = contentExtractor.getReader();
+ } catch (TextExtractorFactory.NoTextExtractorFound | TextExtractor.InitReaderException ex) {
+ // Try the StringsTextExtractor if Tika extractions fails.
+ TextExtractor stringsExtractor = TextExtractorFactory.getStringsExtractor(content, null);
+ reader = stringsExtractor.getReader();
+ }
+ }
+
+ return reader;
+ }
}
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsAnalysisResultIngestModule.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsAnalysisResultIngestModule.java
index 26ac0180675072fda932c925a395462a86af84b4..886b45b3a2cec346d6e6c70651b469edc826ac4e 100755
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsAnalysisResultIngestModule.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsAnalysisResultIngestModule.java
@@ -18,6 +18,7 @@
*/
package org.sleuthkit.autopsy.keywordsearch;
+import java.io.Reader;
import java.util.logging.Level;
import org.openide.util.Lookup;
import org.sleuthkit.autopsy.coreutils.Logger;
@@ -25,6 +26,8 @@
import org.sleuthkit.autopsy.ingest.IngestJobContext;
import org.sleuthkit.autopsy.ingest.IngestModule;
import org.sleuthkit.autopsy.keywordsearchservice.KeywordSearchService;
+import org.sleuthkit.autopsy.textextractors.TextExtractor;
+import org.sleuthkit.autopsy.textextractors.TextExtractorFactory;
import org.sleuthkit.datamodel.AnalysisResult;
import org.sleuthkit.datamodel.BlackboardArtifact;
import org.sleuthkit.datamodel.TskCoreException;
@@ -40,7 +43,6 @@ public class KwsAnalysisResultIngestModule implements AnalysisResultIngestModule
private static final Logger LOGGER = Logger.getLogger(KeywordSearchIngestModule.class.getName());
private static final int TSK_KEYWORD_HIT_TYPE_ID = BlackboardArtifact.Type.TSK_KEYWORD_HIT.getTypeID();
private IngestJobContext context;
- private KeywordSearchService searchService;
private final KeywordSearchJobSettings settings;
KwsAnalysisResultIngestModule(KeywordSearchJobSettings settings) {
@@ -50,16 +52,24 @@ public class KwsAnalysisResultIngestModule implements AnalysisResultIngestModule
@Override
public void startUp(IngestJobContext context) throws IngestModule.IngestModuleException {
this.context = context;
- searchService = Lookup.getDefault().lookup(KeywordSearchService.class);
}
@Override
public IngestModule.ProcessResult process(AnalysisResult result) {
try {
if (result.getType().getTypeID() != TSK_KEYWORD_HIT_TYPE_ID) {
- searchService.index(result);
+ Ingester ingester = Ingester.getDefault();
+ Reader blackboardExtractedTextReader = KeywordSearchUtil.getReader(result);
+ String sourceName = result.getDisplayName() + "_" + result.getArtifactID();
+ ingester.indexMetaDataOnly(result, sourceName);
+ ingester.indexTextAndSearch(blackboardExtractedTextReader,
+ result.getArtifactID(),
+ sourceName, result,
+ context,
+ settings.isIndexToSolrEnabled(),
+ settings.getNamesOfEnabledKeyWordLists());
}
- } catch (TskCoreException ex) {
+ } catch (TskCoreException | TextExtractorFactory.NoTextExtractorFound | TextExtractor.InitReaderException | Ingester.IngesterException ex) {
LOGGER.log(Level.SEVERE, String.format("Error indexing analysis result '%s' (job ID=%d)", result, context.getJobId()), ex); //NON-NLS
return IngestModule.ProcessResult.ERROR;
}
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsDataArtifactIngestModule.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsDataArtifactIngestModule.java
index 74e81801f618844730fccee753602b3a4fa23d77..4f0659b0e99a579d3202cd0337f22e1fbcddfb45 100755
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsDataArtifactIngestModule.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/KwsDataArtifactIngestModule.java
@@ -18,12 +18,16 @@
*/
package org.sleuthkit.autopsy.keywordsearch;
+import java.io.Reader;
import java.util.logging.Level;
+import org.openide.util.Exceptions;
import org.openide.util.Lookup;
import org.sleuthkit.autopsy.coreutils.Logger;
import org.sleuthkit.autopsy.ingest.DataArtifactIngestModule;
import org.sleuthkit.autopsy.ingest.IngestJobContext;
import org.sleuthkit.autopsy.keywordsearchservice.KeywordSearchService;
+import org.sleuthkit.autopsy.textextractors.TextExtractor;
+import org.sleuthkit.autopsy.textextractors.TextExtractorFactory;
import org.sleuthkit.datamodel.BlackboardArtifact;
import org.sleuthkit.datamodel.DataArtifact;
import org.sleuthkit.datamodel.TskCoreException;
@@ -39,7 +43,6 @@ public class KwsDataArtifactIngestModule implements DataArtifactIngestModule {
private static final Logger LOGGER = Logger.getLogger(KeywordSearchIngestModule.class.getName());
private static final int TSK_ASSOCIATED_OBJECT_TYPE_ID = BlackboardArtifact.Type.TSK_ASSOCIATED_OBJECT.getTypeID();
private IngestJobContext context;
- private KeywordSearchService searchService;
private final KeywordSearchJobSettings settings;
KwsDataArtifactIngestModule(KeywordSearchJobSettings settings) {
@@ -49,19 +52,27 @@ public class KwsDataArtifactIngestModule implements DataArtifactIngestModule {
@Override
public void startUp(IngestJobContext context) throws IngestModuleException {
this.context = context;
- searchService = Lookup.getDefault().lookup(KeywordSearchService.class);
}
@Override
public ProcessResult process(DataArtifact artifact) {
try {
if (artifact.getType().getTypeID() != TSK_ASSOCIATED_OBJECT_TYPE_ID) {
- searchService.index(artifact);
+ Ingester ingester = Ingester.getDefault();
+ Reader blackboardExtractedTextReader = KeywordSearchUtil.getReader(artifact);
+ String sourceName = artifact.getDisplayName() + "_" + artifact.getArtifactID();
+ ingester.indexMetaDataOnly(artifact, sourceName);
+ ingester.indexTextAndSearch(blackboardExtractedTextReader,
+ artifact.getArtifactID(),
+ sourceName, artifact,
+ context,
+ settings.isIndexToSolrEnabled(),
+ settings.getNamesOfEnabledKeyWordLists());
}
- } catch (TskCoreException ex) {
+ } catch (TskCoreException | TextExtractorFactory.NoTextExtractorFound | TextExtractor.InitReaderException | Ingester.IngesterException ex) {
LOGGER.log(Level.SEVERE, String.format("Error indexing data artifact '%s' (job ID=%d)", artifact, context.getJobId()), ex); //NON-NLS
return ProcessResult.ERROR;
- }
+ }
return ProcessResult.OK;
}
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java
index b68bb7d82e24f928407fe4355e41d0a40b139ada..3d830489cca7384daa5063608a33f8e023e184fe 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java
@@ -589,7 +589,11 @@ public static BlackboardArtifact createKeywordHitArtifact(Content content, Keyw
);
if (originalKW.searchTermIsLiteral()) {
- attributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_KEYWORD_SEARCH_TYPE, MODULE_NAME, KeywordSearch.QueryType.SUBSTRING.ordinal()));
+ if(!originalKW.searchTermIsWholeWord()) {
+ attributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_KEYWORD_SEARCH_TYPE, MODULE_NAME, KeywordSearch.QueryType.SUBSTRING.ordinal()));
+ } else {
+ attributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_KEYWORD_SEARCH_TYPE, MODULE_NAME, KeywordSearch.QueryType.LITERAL.ordinal()));
+ }
} else {
attributes.add(new BlackboardAttribute(ATTRIBUTE_TYPE.TSK_KEYWORD_SEARCH_TYPE, MODULE_NAME, KeywordSearch.QueryType.REGEX.ordinal()));
}
diff --git a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrSearchService.java b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrSearchService.java
index 2d56a938df19973c2c8d0665da59aff8e96eb023..7613538764c418b686fc40e123fbe804ef93795c 100644
--- a/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrSearchService.java
+++ b/KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/SolrSearchService.java
@@ -93,8 +93,7 @@ public void index(Content content) throws TskCoreException {
return;
}
try {
- TextExtractor blackboardExtractor = TextExtractorFactory.getExtractor(content, null);
- Reader blackboardExtractedTextReader = blackboardExtractor.getReader();
+ Reader blackboardExtractedTextReader = KeywordSearchUtil.getReader(content);
String sourceName = artifact.getDisplayName() + "_" + artifact.getArtifactID();
ingester.indexMetaDataOnly(artifact, sourceName);
ingester.indexTextAndSearch(blackboardExtractedTextReader, artifact.getArtifactID(), sourceName, content, null, true, null);
@@ -103,18 +102,11 @@ public void index(Content content) throws TskCoreException {
}
} else {
try {
- TextExtractor contentExtractor = TextExtractorFactory.getExtractor(content, null);
- Reader contentExtractedTextReader = contentExtractor.getReader();
- ingester.indexTextAndSearch(contentExtractedTextReader, content.getId(), content.getName(), content, null, true, null);
+
+ Reader reader = KeywordSearchUtil.getReader(content);
+ ingester.indexTextAndSearch(reader, content.getId(), content.getName(), content, null, true, null);
} catch (TextExtractorFactory.NoTextExtractorFound | Ingester.IngesterException | TextExtractor.InitReaderException ex) {
- try {
- // Try the StringsTextExtractor if Tika extractions fails.
- TextExtractor stringsExtractor = TextExtractorFactory.getStringsExtractor(content, null);
- Reader stringsExtractedTextReader = stringsExtractor.getReader();
- ingester.indexStrings(stringsExtractedTextReader, content.getId(), content.getName(), content, null, true);
- } catch (Ingester.IngesterException | TextExtractor.InitReaderException ex1) {
- throw new TskCoreException("Error indexing content", ex1);
- }
+ throw new TskCoreException("Error indexing content", ex);
}
// only do a Solr commit if ingest is not running. If ingest is running, the changes will
// be committed via a periodic commit or via final commit after the ingest job has finished.
diff --git a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractRegistry.java b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractRegistry.java
index 088af9f4b2e876262c86ecabdb341493d9020aeb..4dfcdd2193fc35b68785b9e634436c4a08081438 100644
--- a/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractRegistry.java
+++ b/RecentActivity/src/org/sleuthkit/autopsy/recentactivity/ExtractRegistry.java
@@ -422,13 +422,13 @@ private void analyzeRegistryFiles(long ingestJobId) {
"RegRipper " + regFile.getUniquePath(), regFile); //NON-NLS
// Index the report content so that it will be available for keyword search.
- KeywordSearchService searchService = Lookup.getDefault().lookup(KeywordSearchService.class);
- if (null == searchService) {
- logger.log(Level.WARNING, "Keyword search service not found. Report will not be indexed");
- } else {
- searchService.index(report);
- report.close();
- }
+// KeywordSearchService searchService = Lookup.getDefault().lookup(KeywordSearchService.class);
+// if (null == searchService) {
+// logger.log(Level.WARNING, "Keyword search service not found. Report will not be indexed");
+// } else {
+// searchService.index(report);
+// report.close();
+// }
} catch (TskCoreException e) {
this.addErrorMessage("Error adding regripper output as Autopsy report: " + e.getLocalizedMessage()); //NON-NLS
}