mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-17 10:17:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

much simpler version that also works for hits that are not single terms in the Solr index.

Browse Source
This commit is contained in:
millmanorama 2017-01-23 22:28:43 +01:00
parent bcb97180c4
commit c616b45b33
1 changed files with 8 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/LuceneQuery.java
View File

@ -30,7 +30,6 @@ 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.coreutils.EscapeUtil; import org.sleuthkit.autopsy.coreutils.EscapeUtil;
import org.sleuthkit.autopsy.coreutils.Logger; import org.sleuthkit.autopsy.coreutils.Logger;
import org.sleuthkit.autopsy.coreutils.Version; import org.sleuthkit.autopsy.coreutils.Version;
@ -203,11 +202,11 @@ 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();
final String strippedQueryString = StringUtils.strip(getQueryString(), "\"");
// cycle through results in sets of MAX_RESULTS // cycle through results in sets of MAX_RESULTS
for (int start = 0; !allMatchesFetched; start = start + MAX_RESULTS) { for (int start = 0; !allMatchesFetched; start = start + MAX_RESULTS) {
q.setStart(start); q.setStart(start);
@ -222,30 +221,20 @@ class LuceneQuery implements KeywordSearchQuery {
* will get picked up in the next one. */ * will get picked up in the next one. */
final String docId = resultDoc.getFieldValue(Server.Schema.ID.toString()).toString(); final String docId = resultDoc.getFieldValue(Server.Schema.ID.toString()).toString();
final Integer chunkSize = (Integer) resultDoc.getFieldValue(Server.Schema.CHUNK_SIZE.toString()); final Integer chunkSize = (Integer) resultDoc.getFieldValue(Server.Schema.CHUNK_SIZE.toString());
final String content_str = resultDoc.get(Server.Schema.CONTENT_STR.toString()).toString();
Integer startOffset = getFirstOffset(termVectors, docId); Integer firstOccurence = content_str.indexOf(strippedQueryString);
if (startOffset < chunkSize) { if (firstOccurence < chunkSize) {
matches.add(createKeywordtHit(highlightResponse, docId)); matches.add(createKeywordtHit(highlightResponse, docId));
} }
} catch (TskException ex) { } catch (TskException ex) {
return matches; return matches;
} }
} }
} }
return matches; return matches;
} }
private Integer getFirstOffset(SimpleOrderedMap<?> termVectors, final String docId) {
SimpleOrderedMap<?> docTermVector = (SimpleOrderedMap<?>) termVectors.get(docId);
SimpleOrderedMap<?> fieldVector = (field == null)
? (SimpleOrderedMap< ?>) docTermVector.get(Server.Schema.TEXT.toString())
: (SimpleOrderedMap<?>) docTermVector.get(field);
SimpleOrderedMap<?> termInfo = (SimpleOrderedMap<?>) fieldVector.get(StringUtils.strip(getQueryString().toLowerCase(), "\""));
SimpleOrderedMap<?> offsets = (SimpleOrderedMap<?>) termInfo.get("offsets");
return (Integer) offsets.get("start");
}
/** /**
* Create the query object for the stored keyword * Create the query object for the stored keyword
* *
@ -270,25 +259,14 @@ class LuceneQuery implements KeywordSearchQuery {
q.setQuery(theQueryStr); q.setQuery(theQueryStr);
q.setRows(MAX_RESULTS); q.setRows(MAX_RESULTS);
q.setFields(Server.Schema.ID.toString(),
Server.Schema.CHUNK_SIZE.toString(),
Server.Schema.CONTENT_STR.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());
} }
//use Term Vector Request Handler to get term vectors with offsets.
//They are used to exclude hits that start inside the chunk window.
q.setRequestHandler("/tvrh");
q.setParam("tv", true);
q.setParam("tv.df", false);
q.setParam("tv.offsets", true);
q.setParam("tv.positions", false);
q.setParam("tv.payloads", false);
q.setParam("tv.tf", false);
q.setParam("tv.tf_idf", false);
if (field != null) {
q.setParam("tv.fl", field);
}
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