mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-17 18:17:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

begin to parse termvectors in LuceneQuery

Browse Source
This commit is contained in:
millmanorama 2017-01-11 23:56:54 +01:00
parent 64b07cb4d2
commit c8c8f45687
1 changed files with 19 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/LuceneQuery.java
View File

@ -1,7 +1,7 @@
/* /*
* Autopsy Forensic Browser * Autopsy Forensic Browser
* *
* Copyright 2011-2015 Basis Technology Corp. * Copyright 2011-2016 Basis Technology Corp.
* Contact: carrier <at> sleuthkit <dot> org * Contact: carrier <at> sleuthkit <dot> org
* *
* Licensed under the Apache License, Version 2.0 (the "License"); * Licensed under the Apache License, Version 2.0 (the "License");
@ -20,18 +20,16 @@ package org.sleuthkit.autopsy.keywordsearch;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Collection; import java.util.Collection;
import java.util.Collections;
import java.util.Comparator; import java.util.Comparator;
import java.util.List; import java.util.List;
import java.util.Map; import java.util.Map;
import java.util.Set;
import java.util.TreeSet;
import java.util.logging.Level; import java.util.logging.Level;
import org.apache.solr.client.solrj.SolrQuery; import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrRequest.METHOD; import org.apache.solr.client.solrj.SolrRequest.METHOD;
import org.apache.solr.client.solrj.response.QueryResponse; import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.common.SolrDocument; import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrDocumentList; import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.util.SimpleOrderedMap;
import org.sleuthkit.autopsy.casemodule.Case; import org.sleuthkit.autopsy.casemodule.Case;
import org.sleuthkit.autopsy.coreutils.EscapeUtil; import org.sleuthkit.autopsy.coreutils.EscapeUtil;
import org.sleuthkit.autopsy.coreutils.Logger; import org.sleuthkit.autopsy.coreutils.Logger;
@ -206,6 +204,7 @@ class LuceneQuery implements KeywordSearchQuery {
response = solrServer.query(q, METHOD.POST); response = solrServer.query(q, METHOD.POST);
resultList = response.getResults(); resultList = response.getResults();
SimpleOrderedMap termVectors = (SimpleOrderedMap) response.getResponse().get("termVectors");
// objectId_chunk -> "text" -> List of previews // objectId_chunk -> "text" -> List of previews
highlightResponse = response.getHighlighting(); highlightResponse = response.getHighlighting();
@ -225,8 +224,9 @@ class LuceneQuery implements KeywordSearchQuery {
} }
for (SolrDocument resultDoc : resultList) { for (SolrDocument resultDoc : resultList) {
KeywordHit contentHit; KeywordHit contentHit;
try { try {
contentHit = createKeywordtHit(resultDoc, highlightResponse, sleuthkitCase); contentHit = createKeywordtHit(resultDoc, highlightResponse, termVectors, sleuthkitCase);
} catch (TskException ex) { } catch (TskException ex) {
return matches; return matches;
} }
@ -260,12 +260,19 @@ class LuceneQuery implements KeywordSearchQuery {
q.setQuery(theQueryStr); q.setQuery(theQueryStr);
q.setRows(MAX_RESULTS); q.setRows(MAX_RESULTS);
q.setFields(Server.Schema.ID.toString()); // q.setFields(Server.Schema.ID.toString());
q.addSort(Server.Schema.ID.toString(), SolrQuery.ORDER.asc); q.addSort(Server.Schema.ID.toString(), SolrQuery.ORDER.asc);
for (KeywordQueryFilter filter : filters) { for (KeywordQueryFilter filter : filters) {
q.addFilterQuery(filter.toString()); q.addFilterQuery(filter.toString());
} }
q.setRequestHandler("/tvrh");
q.setParam("tv", true);
if (field != null) {
q.setParam("tv.fl", field);
}
q.setParam("tv.all", true);
if (snippets) { if (snippets) {
q.addHighlightField(Server.Schema.TEXT.toString()); q.addHighlightField(Server.Schema.TEXT.toString());
//q.setHighlightSimplePre("&laquo;"); //original highlighter only //q.setHighlightSimplePre("&laquo;"); //original highlighter only
@ -290,12 +297,15 @@ class LuceneQuery implements KeywordSearchQuery {
return q; return q;
} }
private KeywordHit createKeywordtHit(SolrDocument solrDoc, Map<String, Map<String, List<String>>> highlightResponse, SleuthkitCase caseDb) throws TskException { private KeywordHit createKeywordtHit(SolrDocument solrDoc, Map<String, Map<String, List<String>>> highlightResponse, SimpleOrderedMap termVectors, SleuthkitCase caseDb) throws TskException {
/** /**
* Get the first snippet from the document if keyword search is * Get the first snippet from the document if keyword search is
* configured to use snippets. * configured to use snippets.
*/ */
final String docId = solrDoc.getFieldValue(Server.Schema.ID.toString()).toString(); final String docId = solrDoc.getFieldValue(Server.Schema.ID.toString()).toString();
SimpleOrderedMap<?> get = (SimpleOrderedMap<?>) termVectors.get(docId);
String snippet = ""; String snippet = "";
if (KeywordSearchSettings.getShowSnippets()) { if (KeywordSearchSettings.getShowSnippets()) {
List<String> snippetList = highlightResponse.get(docId).get(Server.Schema.TEXT.toString()); List<String> snippetList = highlightResponse.get(docId).get(Server.Schema.TEXT.toString());
@ -304,6 +314,7 @@ class LuceneQuery implements KeywordSearchQuery {
snippet = EscapeUtil.unEscapeHtml(snippetList.get(0)).trim(); snippet = EscapeUtil.unEscapeHtml(snippetList.get(0)).trim();
} }
} }
return new KeywordHit(docId, snippet); return new KeywordHit(docId, snippet);
} }