Git-Mirrors/RetroShare
1
0
Fork 0
mirror of https://github.com/RetroShare/RetroShare.git synced 2025-05-19 14:30:43 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Implement deep indexing for files through Xapian

Browse source 
ATM it support extracting metadata only from OGG files.
The system has been designed to be easly extensible to more file formats
  registering more indexer functions which just need to extract metadata
  from a certain type of file and feed it to Xapian.
The system has been integrated into existent file search system to
  through generric search requests and results, it keep a good level of
  retro-compatibility due to some tricks.
The indexing system is released under AGPLv3  so when libretroshare is compiled
  with deep search enabled AGPLv3 must be honored instead of LGPLv3-or-later.
Cleaned up the debian copyright file using non-deprecated license
  code-names.
This commit is contained in:
Gioacchino Mazzurco 2019-06-20 17:24:18 +02:00
parent d46e3eb2b7
commit 3a26ccf6a5
No known key found for this signature in database
GPG key ID: A1FBCA3872E87051
25 changed files with 1364 additions and 438 deletions
Download patch file Download diff file Expand all files Collapse all files

143
libretroshare/src/deep_search/filesindex.cpp Normal file
View file

@ -0,0 +1,143 @@
/*******************************************************************************
* RetroShare full text indexing and search implementation based on Xapian *
* *
* Copyright (C) 2018-2019 Gioacchino Mazzurco <gio@eigenlab.org> *
* Copyright (C) 2019 Asociación Civil Altermundi <info@altermundi.net> *
* *
* This program is free software: you can redistribute it and/or modify *
* it under the terms of the GNU Affero General Public License version 3 as *
* published by the Free Software Foundation. *
* *
* This program is distributed in the hope that it will be useful, *
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
* GNU Affero General Public License for more details. *
* *
* You should have received a copy of the GNU Affero General Public License *
* along with this program. If not, see <https://www.gnu.org/licenses/>. *
* *
*******************************************************************************/
#include "deep_search/filesindex.hpp"
#include "deep_search/commonutils.hpp"
#include "util/rsdebug.h"
#include "retroshare/rsinit.h"
#include <utility>
/*static*/ std::multimap<int, DeepFilesIndex::IndexerFunType>
DeepFilesIndex::indexersRegister = {};
bool DeepFilesIndex::indexFile(
const std::string& path, const std::string& name,
const RsFileHash& hash )
{
auto dbPtr = DeepSearch::openWritableDatabase(
mDbPath, Xapian::DB_CREATE_OR_OPEN );
if(!dbPtr) return false;
Xapian::WritableDatabase& db(*dbPtr);
if(db.term_exists("Q" + hash.toStdString()))
{
Dbg3() << __PRETTY_FUNCTION__ << " skipping laready indexed file: "
<< hash << " " << name << std::endl;
return true;
}
// Set up a TermGenerator that we'll use in indexing.
Xapian::TermGenerator termgenerator;
//termgenerator.set_stemmer(Xapian::Stem("en"));
// We make a document and tell the term generator to use this.
Xapian::Document doc;
termgenerator.set_document(doc);
for(auto& indexerPair : indexersRegister)
if(indexerPair.second(path, name, termgenerator, doc) > 50)
break;
const std::string hashString = hash.toStdString();
const std::string idTerm("Q" + hashString);
doc.add_boolean_term(idTerm);
termgenerator.index_text(name, 1, "N");
termgenerator.index_text(name);
doc.add_value(FILE_HASH_VALUENO, hashString);
db.replace_document(idTerm, doc);
return true;
}
bool DeepFilesIndex::removeFileFromIndex(const RsFileHash& hash)
{
Dbg3() << __PRETTY_FUNCTION__ << " removing file from index: "
<< hash << std::endl;
std::unique_ptr<Xapian::WritableDatabase> db =
DeepSearch::openWritableDatabase(mDbPath, Xapian::DB_CREATE_OR_OPEN);
if(!db) return false;
db->delete_document("Q" + hash.toStdString());
return true;
}
/*static*/ std::string DeepFilesIndex::dbDefaultPath()
{ return RsAccounts::AccountDirectory() + "/deep_files_index_xapian_db"; }
/*static*/ bool DeepFilesIndex::registerIndexer(
int order, const DeepFilesIndex::IndexerFunType& indexerFun )
{
Dbg1() << __PRETTY_FUNCTION__ << " " << order << std::endl;
indexersRegister.insert(std::make_pair(order, indexerFun));
return true;
}
uint32_t DeepFilesIndex::search(
const std::string& queryStr,
std::vector<DeepFilesSearchResult>& results, uint32_t maxResults )
{
results.clear();
auto dbPtr = DeepSearch::openReadOnlyDatabase(mDbPath);
if(!dbPtr) return 0;
Xapian::Database& db(*dbPtr);
// Set up a QueryParser with a stemmer and suitable prefixes.
Xapian::QueryParser queryparser;
//queryparser.set_stemmer(Xapian::Stem("en"));
queryparser.set_stemming_strategy(queryparser.STEM_SOME);
// Start of prefix configuration.
//queryparser.add_prefix("title", "S");
//queryparser.add_prefix("description", "XD");
// End of prefix configuration.
// And parse the query.
Xapian::Query query = queryparser.parse_query(queryStr);
// Use an Enquire object on the database to run the query.
Xapian::Enquire enquire(db);
enquire.set_query(query);
Xapian::MSet mset = enquire.get_mset(
0, maxResults ? maxResults : db.get_doccount() );
for ( Xapian::MSetIterator m = mset.begin(); m != mset.end(); ++m )
{
const Xapian::Document& doc = m.get_document();
DeepFilesSearchResult s;
s.mFileHash = RsFileHash(doc.get_value(FILE_HASH_VALUENO));
s.mWeight = m.get_weight();
#if XAPIAN_AT_LEAST(1,3,5)
s.mSnippet = mset.snippet(doc.get_data());
#endif // XAPIAN_AT_LEAST(1,3,5)
results.push_back(s);
}
return static_cast<uint32_t>(results.size());
}
#ifdef RS_DEEP_FILES_INDEX_OGG
# include "deep_search/filesoggindexer.hpp"
static RsDeepOggFileIndexer oggFileIndexer;
#endif // def RS_DEEP_FILES_INDEX_OGG