org.neo4j.commandline.dbms.CsvImporter Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of neo4j-dbms Show documentation
Show all versions of neo4j-dbms Show documentation
This component provides management functionality and product surface for Neo4j instances.
/*
* Copyright (c) 2002-2018 "Neo Technology,"
* Network Engine for Objects in Lund AB [http://neotechnology.com]
*
* This file is part of Neo4j.
*
* Neo4j is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see > nodesFiles, relationshipsFiles;
private final IdType idType;
private final Charset inputEncoding;
private final Config config;
private final Args args;
private final OutsideWorld outsideWorld;
private final String reportFileName;
public static String description()
{
return "--mode=csv\n" +
" Import a database from a collection of CSV files.\n" +
"--report-file=\n" +
" File name in which to store the report of the import.\n" +
" Defaults to " + ImportCommand.DEFAULT_REPORT_FILE_NAME + " in the current directory.\n" +
"--nodes[:Label1:Label2]=\",,...\"\n" +
" Node CSV header and data. Multiple files will be logically seen as\n" +
" one big file from the perspective of the importer. The first line\n" +
" must contain the header. Multiple data sources like these can be\n" +
" specified in one import, where each data source has its own header.\n" +
" Note that file groups must be enclosed in quotation marks.\n" +
"--relationships[:RELATIONSHIP_TYPE]=\",,...\"\n" +
" Relationship CSV header and data. Multiple files will be logically\n" +
" seen as one big file from the perspective of the importer. The first\n" +
" line must contain the header. Multiple data sources like these can be\n" +
" specified in one import, where each data source has its own header.\n" +
" Note that file groups must be enclosed in quotation marks.\n" +
"--id-type=\n" +
" Each node must provide a unique id. This is used to find the correct\n" +
" nodes when creating relationships. Must be one of:\n" +
" STRING: (default) arbitrary strings for identifying nodes.\n" +
" INTEGER: arbitrary integer values for identifying nodes.\n" +
" ACTUAL: (advanced) actual node ids. The default option is STRING.\n" +
" For more information on id handling, please see the Neo4j Manual:\n" +
" https://neo4j.com/docs/operations-manual/current/tools/import/\n" +
"--input-encoding \n" +
" Character set that input data is encoded in. Defaults to UTF-8.\n";
}
public static String arguments()
{
return "[--report-file=] " +
"[--nodes[:Label1:Label2]=\",,...\"] " +
"[--relationships[:RELATIONSHIP_TYPE]=\",,...\"] " +
"[--id-type=] " +
"[--input-encoding=] " +
"[--page-size=]";
}
CsvImporter( Args args, Config config, OutsideWorld outsideWorld ) throws IncorrectUsage
{
this.args = args;
this.outsideWorld = outsideWorld;
nodesFiles = extractInputFiles( args, "nodes", outsideWorld.errorStream() );
relationshipsFiles = extractInputFiles( args, "relationships", outsideWorld.errorStream() );
reportFileName =
args.interpretOption( "report-file", withDefault( ImportCommand.DEFAULT_REPORT_FILE_NAME ), s -> s );
try
{
validateInputFiles( nodesFiles, relationshipsFiles );
}
catch ( IllegalArgumentException e )
{
throw new IncorrectUsage( e.getMessage() );
}
idType = args.interpretOption( "id-type", withDefault( IdType.STRING ),
from -> IdType.valueOf( from.toUpperCase() ) );
inputEncoding = Charset.forName( args.get( "input-encoding", defaultCharset().name() ) );
this.config = config;
}
@Override
public void doImport() throws IOException
{
FileSystemAbstraction fs = outsideWorld.fileSystem();
File storeDir = config.get( DatabaseManagementSystemSettings.database_path );
File logsDir = config.get( GraphDatabaseSettings.logs_directory );
File reportFile = new File( reportFileName );
OutputStream badOutput = new BufferedOutputStream( fs.openAsOutputStream( reportFile, false ) );
Collector badCollector = badCollector( badOutput, 1000, collect( true, true, true ) );
Configuration configuration = importConfiguration( null, false, config );
CsvInput input = new CsvInput( nodeData( inputEncoding, nodesFiles ), defaultFormatNodeFileHeader(),
relationshipData( inputEncoding, relationshipsFiles ), defaultFormatRelationshipFileHeader(), idType,
csvConfiguration( args, false ), badCollector, configuration.maxNumberOfProcessors() );
ImportTool.doImport( outsideWorld.errorStream(), outsideWorld.errorStream(), storeDir, logsDir, reportFile, fs,
nodesFiles, relationshipsFiles, false, input, config, badOutput, configuration );
}
}