YaCy supports now the storage to remote solr indexes. More federated storage (and search) methods may follow. The remote index scheme is the same as produced by the SolrCell; see http://wiki.apache.org/solr/ExtractingRequestHandler Because this default scheme is used, the default example scheme can be used as solr configuration This is also the same scheme that solr uses if documents are imported with apache tika. federated solr storage is switched off by default. To use this, do the following: - set federated.service.solr.indexing.enabled = true - download solr from http://www.apache.org/dyn/closer.cgi/lucene/solr/ - extract the solr (3.1) package, 'cd example' and start solr with 'java -jar start.jar' - start yacy and then start a crawler. The crawler will fill both, YaCy and solr indexes. - to check whats in solr after indexing, open http://localhost:8983/solr/admin/ Until now it is not possible to use the solr index to search with YaCy in that solr index. This functionality is now available for two reasons: 1) to compare the functionality of Solr and YaCy and to compare the search speed 2) to use YaCy as a search appliance for people who need a crawler or other source harvesting methods that YaCy provides (like dublin core reading, wikimedia dump reading, rss feed reader etc) if people still want to use solr instead of YaCy. git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7654 6c8d7289-2bf4-0310-a012-ef5d649a1542pull/1/head
orbiter
14 years ago
parent
c17d102bd8
commit
19fd13d3bc
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
@ -0,0 +1,176 @@
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
@ -0,0 +1,21 @@
|
||||
Copyright (c) 2004-2008 QOS.ch
|
||||
All rights reserved.
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining
|
||||
a copy of this software and associated documentation files (the
|
||||
"Software"), to deal in the Software without restriction, including
|
||||
without limitation the rights to use, copy, modify, merge, publish,
|
||||
distribute, sublicense, and/or sell copies of the Software, and to
|
||||
permit persons to whom the Software is furnished to do so, subject to
|
||||
the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be
|
||||
included in all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
||||
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
||||
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
||||
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
||||
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
||||
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
Binary file not shown.
Binary file not shown.
@ -0,0 +1,590 @@
|
||||
/**
|
||||
* Licensed to the Apache Software Foundation (ASF) under one or more
|
||||
* contributor license agreements. See the NOTICE file distributed with
|
||||
* this work for additional information regarding copyright ownership.
|
||||
* The ASF licenses this file to You under the Apache License, Version 2.0
|
||||
* (the "License"); you may not use this file except in compliance with
|
||||
* the License. You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
/*
|
||||
* This file was part of the solrj package and used the apache http client 3.1
|
||||
* It was modified and adopted to work with the apache http client 4.1
|
||||
* using the net.yacy.cora connection package of YaCy
|
||||
* Code modifications (C) under Apache License 2.0 by Michael Christen, 14.4.2011
|
||||
*/
|
||||
|
||||
package net.yacy.cora.services.federated.solr;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.net.MalformedURLException;
|
||||
import java.net.URL;
|
||||
import java.nio.charset.Charset;
|
||||
import java.util.Collection;
|
||||
import java.util.HashMap;
|
||||
import java.util.Iterator;
|
||||
|
||||
import net.yacy.cora.protocol.http.HTTPClient;
|
||||
|
||||
import org.apache.http.entity.mime.content.ContentBody;
|
||||
import org.apache.http.entity.mime.content.InputStreamBody;
|
||||
import org.apache.http.entity.mime.content.StringBody;
|
||||
import org.apache.solr.client.solrj.ResponseParser;
|
||||
import org.apache.solr.client.solrj.SolrRequest;
|
||||
import org.apache.solr.client.solrj.SolrServer;
|
||||
import org.apache.solr.client.solrj.SolrServerException;
|
||||
import org.apache.solr.client.solrj.impl.BinaryResponseParser;
|
||||
import org.apache.solr.client.solrj.response.UpdateResponse;
|
||||
import org.apache.solr.client.solrj.request.RequestWriter;
|
||||
import org.apache.solr.client.solrj.request.UpdateRequest;
|
||||
import org.apache.solr.client.solrj.util.ClientUtils;
|
||||
import org.apache.solr.common.SolrInputDocument;
|
||||
import org.apache.solr.common.params.CommonParams;
|
||||
import org.apache.solr.common.params.DefaultSolrParams;
|
||||
import org.apache.solr.common.params.ModifiableSolrParams;
|
||||
import org.apache.solr.common.params.SolrParams;
|
||||
import org.apache.solr.common.util.ContentStream;
|
||||
import org.apache.solr.common.util.NamedList;
|
||||
|
||||
/**
|
||||
* The {@link SolrHTTPClient} uses the Apache Commons HTTP Client to connect to solr.
|
||||
* <pre class="prettyprint" >SolrServer server = new CommonsHttpSolrServer( url );</pre>
|
||||
*
|
||||
* @version $Id: CommonsHttpSolrServer.java 1067552 2011-02-05 23:52:42Z koji $
|
||||
* @since solr 1.3
|
||||
*/
|
||||
public class SolrHTTPClient extends SolrServer {
|
||||
private static final long serialVersionUID = -4532572298724852268L;
|
||||
|
||||
/**
|
||||
* User-Agent String as identified by the HTTP request by the {@link
|
||||
* org.apache.commons.httpclient.HttpClient HttpClient} to the Solr
|
||||
* server from the client.
|
||||
*/
|
||||
public static final String AGENT = "Solr["+SolrHTTPClient.class.getName()+"] 1.0";
|
||||
|
||||
public final static Charset utf8;
|
||||
static {
|
||||
utf8 = Charset.forName("UTF-8");
|
||||
}
|
||||
|
||||
/**
|
||||
* The URL of the Solr server.
|
||||
*/
|
||||
protected String _baseURL;
|
||||
|
||||
/**
|
||||
* Default value: null / empty. <p/>
|
||||
* Parameters that are added to every request regardless. This may be a place to add
|
||||
* something like an authentication token.
|
||||
*/
|
||||
protected ModifiableSolrParams _invariantParams;
|
||||
|
||||
/**
|
||||
* Default response parser is BinaryResponseParser <p/>
|
||||
* This parser represents the default Response Parser chosen to
|
||||
* parse the response if the parser were not specified as part of
|
||||
* the request.
|
||||
* @see org.apache.solr.client.solrj.impl.BinaryResponseParser
|
||||
*/
|
||||
protected ResponseParser _parser;
|
||||
|
||||
/**
|
||||
* The RequestWriter used to write all requests to Solr
|
||||
* @see org.apache.solr.client.solrj.request.RequestWriter
|
||||
*/
|
||||
protected RequestWriter requestWriter = new RequestWriter();
|
||||
|
||||
/**
|
||||
* @param solrServerUrl The URL of the Solr server. For
|
||||
* example, "<code>http://localhost:8983/solr/</code>"
|
||||
* if you are using the standard distribution Solr webapp
|
||||
* on your local machine.
|
||||
*/
|
||||
public SolrHTTPClient(String solrServerUrl) throws MalformedURLException {
|
||||
this(new URL(solrServerUrl));
|
||||
}
|
||||
|
||||
/**
|
||||
* @param baseURL The URL of the Solr server. For example,
|
||||
* "<code>http://localhost:8983/solr/</code>" if you are using the
|
||||
* standard distribution Solr webapp on your local machine.
|
||||
*/
|
||||
public SolrHTTPClient(URL baseURL)
|
||||
{
|
||||
this(baseURL, new BinaryResponseParser());
|
||||
}
|
||||
|
||||
/**
|
||||
* @see #useMultiPartPost
|
||||
* @see #_parser
|
||||
*/
|
||||
public SolrHTTPClient(URL baseURL, ResponseParser parser) {
|
||||
_baseURL = baseURL.toExternalForm();
|
||||
if( _baseURL.endsWith( "/" ) ) {
|
||||
_baseURL = _baseURL.substring( 0, _baseURL.length()-1 );
|
||||
}
|
||||
if( _baseURL.indexOf( '?' ) >=0 ) {
|
||||
throw new RuntimeException( "Invalid base url for solrj. The base URL must not contain parameters: "+_baseURL );
|
||||
}
|
||||
_parser = parser;
|
||||
}
|
||||
|
||||
//------------------------------------------------------------------------
|
||||
//------------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Process the request. If {@link org.apache.solr.client.solrj.SolrRequest#getResponseParser()} is null, then use
|
||||
* {@link #getParser()}
|
||||
* @param request The {@link org.apache.solr.client.solrj.SolrRequest} to process
|
||||
* @return The {@link org.apache.solr.common.util.NamedList} result
|
||||
* @throws SolrServerException
|
||||
* @throws IOException
|
||||
*
|
||||
* @see #request(org.apache.solr.client.solrj.SolrRequest, org.apache.solr.client.solrj.ResponseParser)
|
||||
*/
|
||||
@Override
|
||||
public NamedList<Object> request( final SolrRequest request ) throws SolrServerException, IOException
|
||||
{
|
||||
ResponseParser responseParser = request.getResponseParser();
|
||||
if (responseParser == null) {
|
||||
responseParser = _parser;
|
||||
}
|
||||
return request(request, responseParser);
|
||||
}
|
||||
|
||||
|
||||
public NamedList<Object> request(final SolrRequest request, ResponseParser processor) throws SolrServerException, IOException {
|
||||
SolrParams params = request.getParams();
|
||||
Collection<ContentStream> streams = requestWriter.getContentStreams(request);
|
||||
String path = requestWriter.getPath(request);
|
||||
if( path == null || !path.startsWith( "/" ) ) {
|
||||
path = "/select";
|
||||
}
|
||||
|
||||
// The parser 'wt=' and 'version=' params are used instead of the original params
|
||||
ResponseParser parser = request.getResponseParser();
|
||||
if( parser == null ) {
|
||||
parser = _parser;
|
||||
}
|
||||
ModifiableSolrParams wparams = new ModifiableSolrParams();
|
||||
wparams.set( CommonParams.WT, parser.getWriterType() );
|
||||
wparams.set( CommonParams.VERSION, parser.getVersion());
|
||||
if( params == null ) {
|
||||
params = wparams;
|
||||
}
|
||||
else {
|
||||
params = new DefaultSolrParams( wparams, params );
|
||||
}
|
||||
|
||||
if( _invariantParams != null ) {
|
||||
params = new DefaultSolrParams( _invariantParams, params );
|
||||
}
|
||||
|
||||
|
||||
byte[] result = null;
|
||||
HTTPClient client = new HTTPClient();
|
||||
if (SolrRequest.METHOD.POST == request.getMethod()) {
|
||||
boolean isMultipart = ( streams != null && streams.size() > 1 );
|
||||
|
||||
if (streams == null || isMultipart) {
|
||||
String url = _baseURL + path;
|
||||
|
||||
HashMap<String, ContentBody> parts = new HashMap<String, ContentBody>();
|
||||
Iterator<String> iter = params.getParameterNamesIterator();
|
||||
while (iter.hasNext()) {
|
||||
String p = iter.next();
|
||||
String[] vals = params.getParams(p);
|
||||
if (vals != null) {
|
||||
for (String v : vals) {
|
||||
if (isMultipart) {
|
||||
parts.put(p, new StringBody(v, utf8));
|
||||
} else {
|
||||
if (url.indexOf('?') >= 0) url += "&" + p + "=" + v; else url += "?" + p + "=" + v;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (isMultipart) {
|
||||
for (ContentStream content : streams) {
|
||||
parts.put(content.getName(), new InputStreamBody(content.getStream(), content.getContentType(), null));
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
result = client.POSTbytes(url, parts, true);
|
||||
} finally {
|
||||
client.finish();
|
||||
}
|
||||
} else {
|
||||
String pstr = ClientUtils.toQueryString(params, false);
|
||||
String url = _baseURL + path + pstr;
|
||||
|
||||
// Single stream as body
|
||||
// Using a loop just to get the first one
|
||||
final ContentStream[] contentStream = new ContentStream[1];
|
||||
for (ContentStream content : streams) {
|
||||
contentStream[0] = content;
|
||||
break;
|
||||
}
|
||||
result = client.POSTbytes(url, contentStream[0].getStream(), contentStream[0].getStream().available());
|
||||
}
|
||||
} else if (SolrRequest.METHOD.GET == request.getMethod()) {
|
||||
result = client.GETbytes( _baseURL + path + ClientUtils.toQueryString( params, false ));
|
||||
} else {
|
||||
throw new SolrServerException("Unsupported method: "+request.getMethod() );
|
||||
}
|
||||
|
||||
int statusCode = client.getStatusCode();
|
||||
if (statusCode != 200) {
|
||||
throw new IOException("bad status code: " + statusCode + ", " + client.getHttpResponse().getStatusLine());
|
||||
}
|
||||
|
||||
// Read the contents
|
||||
//System.out.println("SOLR RESPONSE: " + UTF8.String(result));
|
||||
InputStream respBody = new ByteArrayInputStream(result);
|
||||
return processor.processResponse(respBody, "UTF-8");
|
||||
}
|
||||
|
||||
/*
|
||||
* The original code for the request method
|
||||
public NamedList<Object> request(final SolrRequest request, ResponseParser processor) throws SolrServerException, IOException {
|
||||
HttpMethod method = null;
|
||||
InputStream is = null;
|
||||
SolrParams params = request.getParams();
|
||||
Collection<ContentStream> streams = requestWriter.getContentStreams(request);
|
||||
String path = requestWriter.getPath(request);
|
||||
if( path == null || !path.startsWith( "/" ) ) {
|
||||
path = "/select";
|
||||
}
|
||||
|
||||
ResponseParser parser = request.getResponseParser();
|
||||
if( parser == null ) {
|
||||
parser = _parser;
|
||||
}
|
||||
|
||||
// The parser 'wt=' and 'version=' params are used instead of the original params
|
||||
ModifiableSolrParams wparams = new ModifiableSolrParams();
|
||||
wparams.set( CommonParams.WT, parser.getWriterType() );
|
||||
wparams.set( CommonParams.VERSION, parser.getVersion());
|
||||
if( params == null ) {
|
||||
params = wparams;
|
||||
}
|
||||
else {
|
||||
params = new DefaultSolrParams( wparams, params );
|
||||
}
|
||||
|
||||
if( _invariantParams != null ) {
|
||||
params = new DefaultSolrParams( _invariantParams, params );
|
||||
}
|
||||
|
||||
int tries = _maxRetries + 1;
|
||||
try {
|
||||
while( tries-- > 0 ) {
|
||||
// Note: since we aren't do intermittent time keeping
|
||||
// ourselves, the potential non-timeout latency could be as
|
||||
// much as tries-times (plus scheduling effects) the given
|
||||
// timeAllowed.
|
||||
try {
|
||||
if( SolrRequest.METHOD.GET == request.getMethod() ) {
|
||||
if( streams != null ) {
|
||||
throw new SolrException( SolrException.ErrorCode.BAD_REQUEST, "GET can't send streams!" );
|
||||
}
|
||||
method = new GetMethod( _baseURL + path + ClientUtils.toQueryString( params, false ) );
|
||||
}
|
||||
else if( SolrRequest.METHOD.POST == request.getMethod() ) {
|
||||
|
||||
String url = _baseURL + path;
|
||||
boolean isMultipart = ( streams != null && streams.size() > 1 );
|
||||
|
||||
if (streams == null || isMultipart) {
|
||||
PostMethod post = new PostMethod(url);
|
||||
post.getParams().setContentCharset("UTF-8");
|
||||
if (!this.useMultiPartPost && !isMultipart) {
|
||||
post.addRequestHeader("Content-Type",
|
||||
"application/x-www-form-urlencoded; charset=UTF-8");
|
||||
}
|
||||
|
||||
List<Part> parts = new LinkedList<Part>();
|
||||
Iterator<String> iter = params.getParameterNamesIterator();
|
||||
while (iter.hasNext()) {
|
||||
String p = iter.next();
|
||||
String[] vals = params.getParams(p);
|
||||
if (vals != null) {
|
||||
for (String v : vals) {
|
||||
if (this.useMultiPartPost || isMultipart) {
|
||||
parts.add(new StringPart(p, v, "UTF-8"));
|
||||
} else {
|
||||
post.addParameter(p, v);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (isMultipart) {
|
||||
int i = 0;
|
||||
for (ContentStream content : streams) {
|
||||
final ContentStream c = content;
|
||||
|
||||
String charSet = null;
|
||||
String transferEncoding = null;
|
||||
parts.add(new PartBase(c.getName(), c.getContentType(),
|
||||
charSet, transferEncoding) {
|
||||
@Override
|
||||
protected long lengthOfData() throws IOException {
|
||||
return c.getSize();
|
||||
}
|
||||
|
||||
@Override
|
||||
protected void sendData(OutputStream out)
|
||||
throws IOException {
|
||||
InputStream in = c.getStream();
|
||||
try {
|
||||
IOUtils.copy(in, out);
|
||||
} finally {
|
||||
in.close();
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
if (parts.size() > 0) {
|
||||
post.setRequestEntity(new MultipartRequestEntity(parts
|
||||
.toArray(new Part[parts.size()]), post.getParams()));
|
||||
}
|
||||
|
||||
method = post;
|
||||
}
|
||||
// It is has one stream, it is the post body, put the params in the URL
|
||||
else {
|
||||
String pstr = ClientUtils.toQueryString(params, false);
|
||||
PostMethod post = new PostMethod(url + pstr);
|
||||
|
||||
// Single stream as body
|
||||
// Using a loop just to get the first one
|
||||
final ContentStream[] contentStream = new ContentStream[1];
|
||||
for (ContentStream content : streams) {
|
||||
contentStream[0] = content;
|
||||
break;
|
||||
}
|
||||
if (contentStream[0] instanceof RequestWriter.LazyContentStream) {
|
||||
post.setRequestEntity(new RequestEntity() {
|
||||
public long getContentLength() {
|
||||
return -1;
|
||||
}
|
||||
|
||||
public String getContentType() {
|
||||
return contentStream[0].getContentType();
|
||||
}
|
||||
|
||||
public boolean isRepeatable() {
|
||||
return false;
|
||||
}
|
||||
|
||||
public void writeRequest(OutputStream outputStream) throws IOException {
|
||||
((RequestWriter.LazyContentStream) contentStream[0]).writeTo(outputStream);
|
||||
}
|
||||
}
|
||||
);
|
||||
|
||||
} else {
|
||||
is = contentStream[0].getStream();
|
||||
post.setRequestEntity(new InputStreamRequestEntity(is, contentStream[0].getContentType()));
|
||||
}
|
||||
method = post;
|
||||
}
|
||||
}
|
||||
else {
|
||||
throw new SolrServerException("Unsupported method: "+request.getMethod() );
|
||||
}
|
||||
}
|
||||
catch( NoHttpResponseException r ) {
|
||||
// This is generally safe to retry on
|
||||
method.releaseConnection();
|
||||
method = null;
|
||||
if(is != null) {
|
||||
is.close();
|
||||
}
|
||||
// If out of tries then just rethrow (as normal error).
|
||||
if( ( tries < 1 ) ) {
|
||||
throw r;
|
||||
}
|
||||
//log.warn( "Caught: " + r + ". Retrying..." );
|
||||
}
|
||||
}
|
||||
}
|
||||
catch( IOException ex ) {
|
||||
throw new SolrServerException("error reading streams", ex );
|
||||
}
|
||||
|
||||
method.setFollowRedirects( _followRedirects );
|
||||
method.addRequestHeader( "User-Agent", AGENT );
|
||||
if( _allowCompression ) {
|
||||
method.setRequestHeader( new Header( "Accept-Encoding", "gzip,deflate" ) );
|
||||
}
|
||||
|
||||
try {
|
||||
// Execute the method.
|
||||
//System.out.println( "EXECUTE:"+method.getURI() );
|
||||
|
||||
int statusCode = _httpClient.executeMethod(method);
|
||||
if (statusCode != HttpStatus.SC_OK) {
|
||||
StringBuilder msg = new StringBuilder();
|
||||
msg.append( method.getStatusLine().getReasonPhrase() );
|
||||
msg.append( "\n\n" );
|
||||
msg.append( method.getStatusText() );
|
||||
msg.append( "\n\n" );
|
||||
msg.append( "request: "+method.getURI() );
|
||||
throw new SolrException(statusCode, java.net.URLDecoder.decode(msg.toString(), "UTF-8") );
|
||||
}
|
||||
|
||||
// Read the contents
|
||||
String charset = "UTF-8";
|
||||
if( method instanceof HttpMethodBase ) {
|
||||
charset = ((HttpMethodBase)method).getResponseCharSet();
|
||||
}
|
||||
InputStream respBody = method.getResponseBodyAsStream();
|
||||
// Jakarta Commons HTTPClient doesn't handle any
|
||||
// compression natively. Handle gzip or deflate
|
||||
// here if applicable.
|
||||
if( _allowCompression ) {
|
||||
Header contentEncodingHeader = method.getResponseHeader( "Content-Encoding" );
|
||||
if( contentEncodingHeader != null ) {
|
||||
String contentEncoding = contentEncodingHeader.getValue();
|
||||
if( contentEncoding.contains( "gzip" ) ) {
|
||||
//log.debug( "wrapping response in GZIPInputStream" );
|
||||
respBody = new GZIPInputStream( respBody );
|
||||
}
|
||||
else if( contentEncoding.contains( "deflate" ) ) {
|
||||
//log.debug( "wrapping response in InflaterInputStream" );
|
||||
respBody = new InflaterInputStream(respBody);
|
||||
}
|
||||
}
|
||||
else {
|
||||
Header contentTypeHeader = method.getResponseHeader( "Content-Type" );
|
||||
if( contentTypeHeader != null ) {
|
||||
String contentType = contentTypeHeader.getValue();
|
||||
if( contentType != null ) {
|
||||
if( contentType.startsWith( "application/x-gzip-compressed" ) ) {
|
||||
//log.debug( "wrapping response in GZIPInputStream" );
|
||||
respBody = new GZIPInputStream( respBody );
|
||||
}
|
||||
else if ( contentType.startsWith("application/x-deflate") ) {
|
||||
//log.debug( "wrapping response in InflaterInputStream" );
|
||||
respBody = new InflaterInputStream(respBody);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return processor.processResponse(respBody, charset);
|
||||
}
|
||||
catch (HttpException e) {
|
||||
throw new SolrServerException( e );
|
||||
}
|
||||
catch (IOException e) {
|
||||
throw new SolrServerException( e );
|
||||
}
|
||||
finally {
|
||||
method.releaseConnection();
|
||||
if(is != null) {
|
||||
is.close();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
*/
|
||||
|
||||
//-------------------------------------------------------------------
|
||||
//-------------------------------------------------------------------
|
||||
|
||||
/**
|
||||
* Retrieve the default list of parameters are added to every request regardless.
|
||||
*
|
||||
* @see #_invariantParams
|
||||
*/
|
||||
public ModifiableSolrParams getInvariantParams()
|
||||
{
|
||||
return _invariantParams;
|
||||
}
|
||||
|
||||
public String getBaseURL() {
|
||||
return _baseURL;
|
||||
}
|
||||
|
||||
public void setBaseURL(String baseURL) {
|
||||
this._baseURL = baseURL;
|
||||
}
|
||||
|
||||
public ResponseParser getParser() {
|
||||
return _parser;
|
||||
}
|
||||
|
||||
/**
|
||||
* Note: This setter method is <b>not thread-safe</b>.
|
||||
* @param processor Default Response Parser chosen to parse the response if the parser were not specified as part of the request.
|
||||
* @see org.apache.solr.client.solrj.SolrRequest#getResponseParser()
|
||||
*/
|
||||
public void setParser(ResponseParser processor) {
|
||||
_parser = processor;
|
||||
}
|
||||
|
||||
|
||||
public void setRequestWriter(RequestWriter requestWriter) {
|
||||
this.requestWriter = requestWriter;
|
||||
}
|
||||
|
||||
/**
|
||||
* Adds the documents supplied by the given iterator.
|
||||
*
|
||||
* @param docIterator the iterator which returns SolrInputDocument instances
|
||||
*
|
||||
* @return the response from the SolrServer
|
||||
*/
|
||||
public UpdateResponse add(Iterator<SolrInputDocument> docIterator)
|
||||
throws SolrServerException, IOException {
|
||||
UpdateRequest req = new UpdateRequest();
|
||||
req.setDocIterator(docIterator);
|
||||
return req.process(this);
|
||||
}
|
||||
|
||||
/**
|
||||
* Adds the beans supplied by the given iterator.
|
||||
*
|
||||
* @param beanIterator the iterator which returns Beans
|
||||
*
|
||||
* @return the response from the SolrServer
|
||||
*/
|
||||
public UpdateResponse addBeans(final Iterator<?> beanIterator)
|
||||
throws SolrServerException, IOException {
|
||||
UpdateRequest req = new UpdateRequest();
|
||||
req.setDocIterator(new Iterator<SolrInputDocument>() {
|
||||
|
||||
public boolean hasNext() {
|
||||
return beanIterator.hasNext();
|
||||
}
|
||||
|
||||
public SolrInputDocument next() {
|
||||
Object o = beanIterator.next();
|
||||
if (o == null) return null;
|
||||
return getBinder().toSolrInputDocument(o);
|
||||
}
|
||||
|
||||
public void remove() {
|
||||
beanIterator.remove();
|
||||
}
|
||||
});
|
||||
return req.process(this);
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,106 @@
|
||||
package net.yacy.cora.services.federated.solr;
|
||||
|
||||
|
||||
import net.yacy.cora.document.UTF8;
|
||||
import net.yacy.document.Document;
|
||||
import net.yacy.kelondro.data.meta.DigestURI;
|
||||
|
||||
import org.apache.solr.common.SolrInputDocument;
|
||||
|
||||
public enum SolrScheme {
|
||||
|
||||
SolrCell,
|
||||
DublinCore;
|
||||
|
||||
|
||||
public SolrInputDocument yacy2solr(String id, Document document) {
|
||||
if (this == SolrCell) return yacy2solrSolrCell(id, document);
|
||||
return null;
|
||||
}
|
||||
|
||||
public static SolrInputDocument yacy2solrSolrCell(String id, Document yacydoc) {
|
||||
// we user the SolrCell design as index scheme
|
||||
SolrInputDocument solrdoc = new SolrInputDocument();
|
||||
DigestURI digestURI = new DigestURI(yacydoc.dc_source());
|
||||
solrdoc.addField("id", id);
|
||||
solrdoc.addField("sku", digestURI.toNormalform(true, false), 3.0f);
|
||||
/*
|
||||
*
|
||||
private final MultiProtocolURI source; // the source url
|
||||
private final String mimeType; // mimeType as taken from http header
|
||||
private final String charset; // the charset of the document
|
||||
private final List<String> keywords; // most resources provide a keyword field
|
||||
private StringBuilder title; // a document title, taken from title or h1 tag; shall appear as headline of search result
|
||||
private final StringBuilder creator; // author or copyright
|
||||
private final String publisher; // publisher
|
||||
private final List<String> sections; // if present: more titles/headlines appearing in the document
|
||||
private final StringBuilder description; // an abstract, if present: short content description
|
||||
private Object text; // the clear text, all that is visible
|
||||
private final Map<MultiProtocolURI, String> anchors; // all links embedded as clickeable entities (anchor tags)
|
||||
private final Map<MultiProtocolURI, String> rss; // all embedded rss feeds
|
||||
private final Map<MultiProtocolURI, ImageEntry> images; // all visible pictures in document
|
||||
// the anchors and images - Maps are URL-to-EntityDescription mappings.
|
||||
// The EntityDescription appear either as visible text in anchors or as alternative
|
||||
// text in image tags.
|
||||
private Map<MultiProtocolURI, String> hyperlinks, audiolinks, videolinks, applinks;
|
||||
private Map<String, String> emaillinks;
|
||||
private MultiProtocolURI favicon;
|
||||
private boolean resorted;
|
||||
private int inboundLinks, outboundLinks; // counters for inbound and outbound links, are counted after calling notifyWebStructure
|
||||
private Set<String> languages;
|
||||
private boolean indexingDenied;
|
||||
private float lon, lat;
|
||||
*/
|
||||
solrdoc.addField("title", yacydoc.dc_title());
|
||||
solrdoc.addField("author", yacydoc.dc_creator());
|
||||
solrdoc.addField("description", yacydoc.dc_description());
|
||||
solrdoc.addField("content_type", yacydoc.dc_format());
|
||||
solrdoc.addField("subject", yacydoc.dc_subject(' '));
|
||||
solrdoc.addField("text", UTF8.String(yacydoc.getTextBytes()));
|
||||
return solrdoc;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* standard solr scheme
|
||||
|
||||
<field name="id" type="string" indexed="true" stored="true" required="true" />
|
||||
<field name="sku" type="textTight" indexed="true" stored="true" omitNorms="true"/>
|
||||
<field name="name" type="textgen" indexed="true" stored="true"/>
|
||||
<field name="alphaNameSort" type="alphaOnlySort" indexed="true" stored="false"/>
|
||||
<field name="manu" type="textgen" indexed="true" stored="true" omitNorms="true"/>
|
||||
<field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="features" type="text" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="includes" type="text" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
|
||||
|
||||
<field name="weight" type="float" indexed="true" stored="true"/>
|
||||
<field name="price" type="float" indexed="true" stored="true"/>
|
||||
<field name="popularity" type="int" indexed="true" stored="true" />
|
||||
<field name="inStock" type="boolean" indexed="true" stored="true" />
|
||||
|
||||
<!-- Common metadata fields, named specifically to match up with
|
||||
SolrCell metadata when parsing rich documents such as Word, PDF.
|
||||
Some fields are multiValued only because Tika currently may return
|
||||
multiple values for them.
|
||||
-->
|
||||
<field name="title" type="text" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="subject" type="text" indexed="true" stored="true"/>
|
||||
<field name="description" type="text" indexed="true" stored="true"/>
|
||||
<field name="comments" type="text" indexed="true" stored="true"/>
|
||||
<field name="author" type="textgen" indexed="true" stored="true"/>
|
||||
<field name="keywords" type="textgen" indexed="true" stored="true"/>
|
||||
<field name="category" type="textgen" indexed="true" stored="true"/>
|
||||
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
<field name="last_modified" type="date" indexed="true" stored="true"/>
|
||||
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
|
||||
|
||||
<!-- catchall field, containing all other searchable text fields (implemented
|
||||
via copyField further on in this schema -->
|
||||
<field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
|
||||
|
||||
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
|
||||
leading wildcard queries. -->
|
||||
<field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>
|
||||
|
||||
*/
|
||||
}
|
||||
@ -0,0 +1,187 @@
|
||||
package net.yacy.cora.services.federated.solr;
|
||||
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.net.MalformedURLException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Collection;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.solr.client.solrj.SolrQuery;
|
||||
import org.apache.solr.client.solrj.SolrServer;
|
||||
import org.apache.solr.client.solrj.SolrServerException;
|
||||
import org.apache.solr.client.solrj.request.ContentStreamUpdateRequest;
|
||||
import org.apache.solr.client.solrj.response.QueryResponse;
|
||||
import org.apache.solr.common.SolrDocumentList;
|
||||
import org.apache.solr.common.SolrInputDocument;
|
||||
|
||||
import net.yacy.document.Document;
|
||||
|
||||
|
||||
public class SolrSingleConnector {
|
||||
|
||||
private String solrurl;
|
||||
private SolrServer server;
|
||||
private SolrScheme scheme;
|
||||
|
||||
public SolrSingleConnector(String url, SolrScheme scheme) throws IOException {
|
||||
this.solrurl = url;
|
||||
this.scheme = scheme;
|
||||
try {
|
||||
this.server = new SolrHTTPClient(this.solrurl);
|
||||
} catch (MalformedURLException e) {
|
||||
throw new IOException("bad connector url: " + this.solrurl);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* delete everything in the solr index
|
||||
* @throws IOException
|
||||
*/
|
||||
public void clear() throws IOException {
|
||||
try {
|
||||
server.deleteByQuery("*:*");
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
|
||||
public void delete(String id) throws IOException {
|
||||
try {
|
||||
server.deleteById(id);
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
|
||||
public void delete(List<String> ids) throws IOException {
|
||||
try {
|
||||
server.deleteById(ids);
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
|
||||
public void add(File file, String solrId) throws IOException {
|
||||
ContentStreamUpdateRequest up = new ContentStreamUpdateRequest("/update/extract");
|
||||
up.addFile(file);
|
||||
up.setParam("literal.id", solrId);
|
||||
up.setParam("uprefix", "attr_");
|
||||
up.setParam("fmap.content", "attr_content");
|
||||
//up.setAction(AbstractUpdateRequest.ACTION.COMMIT, true, true);
|
||||
try {
|
||||
server.request(up);
|
||||
server.commit();
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
public void addx(File file, String solrId) throws IOException {
|
||||
ContentStreamUpdateRequest up = new ContentStreamUpdateRequest("/update/extract");
|
||||
ModifiableSolrParams params = new ModifiableSolrParams();
|
||||
List<ContentStream> contentStreams = new ArrayList<ContentStream>();
|
||||
contentStreams.add(new ContentStreamBase.FileStream(file));
|
||||
params.set("literal.id", solrId);
|
||||
params.set("uprefix", "attr_");
|
||||
params.set("fmap.content", "attr_content");
|
||||
params.set( UpdateParams.COMMIT, "true" );
|
||||
params.set( UpdateParams.WAIT_FLUSH, String.valueOf(true));
|
||||
params.set( UpdateParams.WAIT_SEARCHER, String.valueOf(true));
|
||||
|
||||
try {
|
||||
server.
|
||||
server.request(up);
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
*/
|
||||
|
||||
public void add(String id, Document doc) throws IOException {
|
||||
add(id, doc, this.scheme);
|
||||
}
|
||||
|
||||
public void add(String id, Document doc, SolrScheme tempScheme) throws IOException {
|
||||
addSolr(tempScheme.yacy2solr(id, doc));
|
||||
}
|
||||
|
||||
protected void addSolr(SolrInputDocument doc) throws IOException {
|
||||
Collection<SolrInputDocument> docs = new ArrayList<SolrInputDocument>();
|
||||
docs.add(doc);
|
||||
addSolr(docs);
|
||||
}
|
||||
|
||||
protected void addSolr(Collection<SolrInputDocument> docs) throws IOException {
|
||||
try {
|
||||
server.add(docs);
|
||||
server.commit();
|
||||
/* To immediately commit after adding documents, you could use:
|
||||
UpdateRequest req = new UpdateRequest();
|
||||
req.setAction( UpdateRequest.ACTION.COMMIT, false, false );
|
||||
req.add( docs );
|
||||
UpdateResponse rsp = req.process( server );
|
||||
*/
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* get a query result from solr
|
||||
* to get all results set the query String to "*:*"
|
||||
* @param querystring
|
||||
* @throws IOException
|
||||
*/
|
||||
public SolrDocumentList get(String querystring, int offset, int count) throws IOException {
|
||||
// construct query
|
||||
SolrQuery query = new SolrQuery();
|
||||
query.setQuery(querystring);
|
||||
query.setRows(count);
|
||||
query.setStart(offset);
|
||||
query.addSortField( "price", SolrQuery.ORDER.asc );
|
||||
|
||||
// query the server
|
||||
//SearchResult result = new SearchResult(count);
|
||||
try {
|
||||
QueryResponse rsp = server.query( query );
|
||||
SolrDocumentList docs = rsp.getResults();
|
||||
return docs;
|
||||
// add the docs into the YaCy search result container
|
||||
/*
|
||||
for (SolrDocument doc: docs) {
|
||||
result.put(element)
|
||||
}
|
||||
*/
|
||||
} catch (SolrServerException e) {
|
||||
throw new IOException(e);
|
||||
}
|
||||
|
||||
//return result;
|
||||
}
|
||||
|
||||
public static void main(String args[]) {
|
||||
SolrSingleConnector solr;
|
||||
try {
|
||||
solr = new SolrSingleConnector("http://127.0.0.1:8983/solr", SolrScheme.SolrCell);
|
||||
solr.clear();
|
||||
File exampleDir = new File("/Data/workspace2/yacy/test/parsertest/");
|
||||
long t, t0, a = 0;
|
||||
int c = 0;
|
||||
for (String s: exampleDir.list()) {
|
||||
if (s.startsWith(".")) continue;
|
||||
t = System.currentTimeMillis();
|
||||
solr.add(new File(exampleDir, s), s);
|
||||
t0 = (System.currentTimeMillis() - t);
|
||||
a += t0;
|
||||
c++;
|
||||
System.out.println("pushed file " + s + " to solr, " + t0 + " milliseconds");
|
||||
}
|
||||
System.out.println("pushed " + c + " files in " + a + " milliseconds, " + (a / c) + " milliseconds average; " + (60000 / a * c) + " PPM");
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
Loading…
Reference in new issue