Hello.
I try to implemetnt full text search in file content, using embedded Oak
version 1.16.0.NodeStore in RDB MS SQL 2008r2
Tried to create index like it said in Oak documentation to index all
properties.
/oak:index/assetType
- jcr:primaryType = "oak:QueryIndexDefinition"
- type = "lucene"
- compatVersion = 2
- async = "async"
+ indexRules
- jcr:primaryType = "nt:unstructured"
+ nt:base
+ properties
- jcr:primaryType = "nt:unstructured"
+ allProps
- name = ".*"
- isRegexp = true
- nodeScopeIndex = true
//---------------------------------------------------
Create index. Tried different combinations of node types. Nothing work.
public static void createIndex(Repository repository) {
Session session = null;
try {
session = repository.login();
Node root = session.getRootNode();
Node index = root.getNode("oak:index");
Node lucineIndex =
index.addNode("assetType","oak:QueryIndexDefinition");
lucineIndex.setProperty("compatVersion", "2");
lucineIndex.setProperty("type", "lucene");
lucineIndex.setProperty("async", "async");
Node rules = lucineIndex.addNode("indexRules",
"nt:unstructured");
Node base = rules.addNode("nt:base");
Node properties = base.addNode("properties",
"nt:unstructured");
Node allProps = properties.addNode("allProps");
allProps.setProperty("jcr:content", ".*");
allProps.setProperty("isRegexp", true);
allProps.setProperty("nodeScopeIndex", true);
session.save();
} catch (LoginException e) {
e.printStackTrace();
} catch (RepositoryException e) {
e.printStackTrace();
} finally {
session.logout();
}
}
//---------------------------------------------------
Add some file
public static void saveFileIfNotExist(byte[] rawFile, String fileName,
String folderName, String mimeType, Repository repository) {
Session session = null;
try {
session = repository.login(new SimpleCredentials("admin",
"admin".toCharArray()));
Node root = session.getRootNode();
Binary binary = session.getValueFactory().createBinary(new
ByteArrayInputStream(rawFile));
if(!root.hasNode(folderName)) {
System.out.println("NO FOLDER");
Node folder = root.addNode(folderName, "nt:folder");
Node file = folder.addNode(fileName, "nt:file");
Node content = file.addNode("jcr:content", "nt:resource");
content.setProperty("jcr:mimeType", mimeType);
content.setProperty("jcr:data", binary);
} else {
System.out.println("FOLDER EXIST");
}
session.save();
}
catch (RepositoryException e) {
e.printStackTrace();
} finally {
session.logout();
}
}
//---------------------------------------------------
File content:
An implementation of the Value interface must override the inherited method
Object.equals(Object) so that, given Value instances V1 and V2,
V1.equals(V2) will return true if.
//---------------------------------------------------
Try to search file content
DocumentNodeStore rdb = new DocumentNodeStore(new
RDBDocumentNodeStoreBuilder().setRDBConnection(dataSource));
Repository repo = new Jcr(new Oak(rdb)).with(new
OpenSecurityProvider()).createRepository();
createIndex(repo);
byte[] rawFile = readBytes("D:\\file.txt");
saveFileIfNotExist(rawFile, "txt_folder", "text_file",
"text/plain", repo);
Session session = null;
try {
session = repo.login();
Node root = session.getRootNode();
Node index = root.getNode("oak:index");
QueryManager queryManager =
session.getWorkspace().getQueryManager();session.getWorkspace().getQueryManager();
Query query = queryManager.createQuery("SELECT * FROM
[nt:resource] AS s WHERE CONTAINS(s.*, 'must') option(traversal warn)",
Query.JCR_SQL2);
QueryResult result = query.execute();
RowIterator ri = result.getRows();
while (ri.hasNext()) {
Row row = ri.nextRow();
System.out.println("Row: " + row.toString());
}
} catch (RepositoryException e) {
e.printStackTrace();
}
finally {
session.logout();
((RepositoryImpl) repo).shutdown();
rdb.dispose();
}
//---------------------------------------------------
But nothing returns, and warns in log:
2019-10-03 11:54:46,054 [main] DEBUG QueryEngineImpl - Parsing JCR-SQL2
statement: SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must')
option(traversal warn)
2019-10-03 11:54:46,054 [main] DEBUG QueryEngineImpl - Parsing JCR-SQL2
statement: SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must')
option(traversal warn)
2019-10-03 11:54:46,070 [main] DEBUG QueryImpl - cost using filter
Filter(query=SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must')
option(traversal warn) fullText="must", path=*)
2019-10-03 11:54:46,070 [main] DEBUG QueryImpl - cost using filter
Filter(query=SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must')
option(traversal warn) fullText="must", path=*)
2019-10-03 11:54:46,073 [main] DEBUG QueryImpl - cost for UUIDDiffIndex is
Infinity
2019-10-03 11:54:46,073 [main] DEBUG QueryImpl - cost for UUIDDiffIndex is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for reference is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for reference is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for property is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for property is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for nodeType is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for nodeType is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for traverse is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - cost for traverse is
Infinity
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - no proper index was found
for filter Filter(query=SELECT * FROM [nt:resource] AS s WHERE
CONTAINS(s.*, 'must') option(traversal warn) fullText="must", path=*)
2019-10-03 11:54:46,076 [main] DEBUG QueryImpl - no proper index was found
for filter Filter(query=SELECT * FROM [nt:resource] AS s WHERE
CONTAINS(s.*, 'must') option(traversal warn) fullText="must", path=*)
2019-10-03 11:54:46,077 [main] WARN QueryImpl - Traversal query (query
without index): SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*,
'must') option(traversal warn); consider creating an index
2019-10-03 11:54:46,077 [main] WARN QueryImpl - Traversal query (query
without index): SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*,
'must') option(traversal warn); consider creating an index
2019-10-03 11:54:46,078 [main] DEBUG QueryRecorder - count: 1 query: SELECT
* FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'x') option(traversal warn)
2019-10-03 11:54:46,078 [main] DEBUG QueryRecorder - count: 1 query: SELECT
* FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'x') option(traversal warn)
2019-10-03 11:54:46,079 [main] DEBUG QueryManagerImpl - Executed query
[SELECT * FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must')
option(traversal warn)] in [35] ms
2019-10-03 11:54:46,081 [main] DEBUG QueryImpl - query execute SELECT *
FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must') option(traversal warn)
2019-10-03 11:54:46,081 [main] DEBUG QueryImpl - query execute SELECT *
FROM [nt:resource] AS s WHERE CONTAINS(s.*, 'must') option(traversal warn)
2019-10-03 11:54:46,082 [main] DEBUG QueryImpl - query plan [nt:resource]
as [s] /* traverse "*" where contains([s].[*], 'must') */
2019-10-03 11:54:46,082 [main] DEBUG QueryImpl - query plan [nt:resource]
as [s] /* traverse "*" where contains([s].[*], 'must') */
So, how to make proper index and make correct request to search in file
content?
How to search in pdf documents?
