inteligr8/SearchServices
1
0
Fork 0
mirror of https://github.com/Alfresco/SearchServices.git synced 2026-09-16 18:12:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use gzipped compressed streams to recover content text from repository.

Browse Source 
This modification will also require Tomcat / NGINX configuration in order to accept HTTP GZIP requests.
This commit is contained in:
Angel Borroy
2020-01-14 16:50:16 +01:00
parent 57cbe5d54e
commit d28f05b19b
2 changed files with 23 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
search-services/alfresco-search/src/main/java/org/alfresco/solr/SolrInformationServer.java
+6 -1
View File
@@ -81,6 +81,7 @@ import java.util.Map.Entry;
import java.util.concurrent.locks.ReentrantReadWriteLock;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.zip.GZIPInputStream;
import com.carrotsearch.hppc.IntArrayList;
@@ -2498,8 +2499,12 @@ public class SolrInformationServer implements InformationServer
response);
addContentPropertyMetadata(doc, propertyQName, AlfrescoSolrDataModel.ContentFieldType.TRANSFORMATION_TIME,
response);
InputStream ris = response.getContent();
if (null != response.getContentEncoding() && response.getContentEncoding().equals("gzip"))
{
ris = new GZIPInputStream(ris);
}
String textContent = "";
try
{
search-services/alfresco-solrclient-lib/src/main/java/org/alfresco/solr/client/SOLRAPIClient.java
+17 -7
View File
@@ -30,6 +30,7 @@ import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
import java.util.Date;
import java.util.HashMap;
@@ -73,6 +74,7 @@ import org.apache.commons.codec.EncoderException;
import org.apache.commons.codec.net.URLCodec;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.util.DateUtil;
import org.apache.commons.io.IOUtils;
import org.json.JSONArray;
import org.json.JSONException;
import org.json.JSONObject;
@@ -1118,20 +1120,21 @@ public class SOLRAPIClient
GetRequest req = new GetRequest(url.toString());
Map<String, String> headers = new HashMap<String, String>();
if(modifiedSince != null)
{
Map<String, String> headers = new HashMap<String, String>(1, 1.0f);
headers.put("If-Modified-Since", String.valueOf(DateUtil.formatDate(new Date(modifiedSince))));
req.setHeaders(headers);
}
headers.put("Accept-Encoding", "gzip");
req.setHeaders(headers);
Response response = repositoryHttpClient.sendRequest(req);
if(response.getStatus() != Status.STATUS_NOT_MODIFIED && response.getStatus() != Status.STATUS_NO_CONTENT && response.getStatus() != Status.STATUS_OK)
{
throw new AlfrescoRuntimeException("GetTextContentResponse return status is " + response.getStatus());
}
}
return new GetTextContentResponse(response);
}
@@ -1481,7 +1484,8 @@ public class SOLRAPIClient
private SolrApiContentStatus status;
private String transformException;
private String transformStatusStr;
private Long transformDuration;
private Long transformDuration;
private String contentEncoding;
public GetTextContentResponse(Response response) throws IOException
{
@@ -1491,7 +1495,8 @@ public class SOLRAPIClient
this.transformStatusStr = response.getHeader("X-Alfresco-transformStatus");
this.transformException = response.getHeader("X-Alfresco-transformException");
String tmp = response.getHeader("X-Alfresco-transformDuration");
this.transformDuration = (tmp != null ? Long.valueOf(tmp) : null);
this.transformDuration = (tmp != null ? Long.valueOf(tmp) : null);
this.contentEncoding = response.getHeader("Content-Encoding");
setStatus();
}
@@ -1557,6 +1562,11 @@ public class SOLRAPIClient
public Long getTransformDuration()
{
return transformDuration;
}
public String getContentEncoding()
{
return contentEncoding;
}
}