yacy_search_server/source/de/anomic/http/httpChunkedInputStream.java
theli a2fa75e688 *) Asynchronous queuing of crawl job URLs (stackCrawl)
various checks like the blacklist check or the robots.txt disallow check are now
   done by a separate thread to unburden the indexer thread(s)
   TODO: maybe we have to introduce a threadpool here if it turn out that this single
         thread is a bottleneck because of the time consuming robots.txt downloads

*) improved index transfer
   The index selection and transmission is done in parallel now to improve index 
   transfer performance.
   TODO: maybe we could speed up performance by unsing multiple transmission threads in 
         parallel instead of only a single one.

*) gzip encoded post requests
   it is now configureable if a gzip encoded post request should be send on
   intex transfer/distribution

*) storage Peer (very experimentell and not optimized yet)
   Now it's possible to send the result of the yacy indexer thread to a remote peer 
   istead of storing the indexed words locally. 
   This could be done by setting the property "storagePeerHash" in the yacy config file
   - Please note that if the index transfer fails, the index ist stored locally.
   - TODO: currently this index transfer is done by the indexer thread. 
     To seedup the indexer
     a) this transmission should be done in parallel and
     b) multiple chunks should be bundled and transfered together


*) general performance improvements  
   - better memory cleanup after http request processing has finished
   - replacing some string concatenations with stringBuffers
   - replacing BufferedInputStreams with serverByteBuffer
   - replacing vectors with arraylists wherever possible
   - replacing hashtables with hashmaps wherever possible
   This was done because function calls to verctor or hashtable functions
   take 3 time longer than calls to functions of arraylists or hashmaps.
   TODO: we should take a look on the class serverObject which is inherited from hashmap
         Do we realy need a synchronization for this class?
   TODO: replace arraylists with linkedLists if random access to the list elements is not needed

*) Robots Parser supports if-modified-since downloads now
   If the downloaded robots.txt file is older than 7 days the robots parser tries to
   download the robots.txt with the if-modified-since header to avoid unnecessary downloads
   if the file was not changed. Additionally the ETag header is used to detect changes.

*) Crawler: better handling of unsupported mimeTypes + FileExtension

*) Bugfix: plasmaWordIndexEntity was not closed correctly in 
   - query.java
   - plasmaswitchboard.java

*) function minimizeUrlDB added to yacy.java 
   this function tests the current urlHashDB for unused urls
   ATTENTION: please don't use this function at the moment because
              it causes the wordIndexDB to flush all words into the
              word directory!

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@853 6c8d7289-2bf4-0310-a012-ef5d649a1542
2005-10-05 10:45:33 +00:00

253 lines
8.8 KiB
Java

//httpChunkedInputStream.java
//-----------------------
//(C) by Michael Peter Christen; mc@anomic.de
//first published on http://www.anomic.de
//Frankfurt, Germany, 2004
//
// This file is contributed by Martin Thelian
// last major change: $LastChangedDate$ by $LastChangedBy$
// Revision: $LastChangedRevision$
//
//This program 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 2 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, write to the Free Software
//Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
//
//Using this software in any meaning (reading, learning, copying, compiling,
//running) means that you agree that the Author(s) is (are) not responsible
//for cost, loss of data or any harm that may be caused directly or indirectly
//by usage of this softare or this documentation. The usage of this software
//is on your own risk. The installation and usage (starting/running) of this
//software may allow other people or application to access your computer and
//any attached devices and is highly dependent on the configuration of the
//software which must be done by the user of the software; the author(s) is
//(are) also not responsible for proper configuration and usage of the
//software, even if provoked by documentation provided together with
//the software.
//
//Any changes to this file according to the GPL as documented in the file
//gpl.txt aside this file in the shipment you received can be done to the
//lines that follows this copyright notice here, but changes must not be
//done inside the copyright notive above. A re-distribution must contain
//the intact and unchanged copyright notice.
//Contributions and changes to the program code must be marked as such.
package de.anomic.http;
import java.io.BufferedReader;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import de.anomic.server.serverByteBuffer;
/**
* Some parts of this class code was copied from <a href="http://www.devdaily.com/java/jwarehouse/commons-httpclient-2.0/src/java/org/apache/commons/httpclient/ChunkedInputStream.shtml">Apache httpclient Project.</a>
* @author theli
*/
public final class httpChunkedInputStream extends InputStream {
private static final int READ_CHUNK_STATE_NORMAL = 0;
private static final int READ_CHUNK_STATE_CR_READ = 1;
private static final int READ_CHUNK_STATE_IN_EXT_CHUNK = 2;
private static final int READ_CHUNK_STATE_FINISHED = -1;
private static final char CR = '\r';
private static final char LF = '\n';
private final InputStream inputStream;
private int currPos;
private int currChunkSize;
private httpHeader httpTrailer;
private boolean beginningOfStream = true;
private boolean isEOF = false;
private boolean isClosed = false;
public httpChunkedInputStream(InputStream in) throws IOException {
if (in == null)throw new IllegalArgumentException("InputStream must not be null");
this.inputStream = in;
this.currPos = 0;
}
public int read() throws IOException {
if (this.isClosed) throw new IOException("Inputstream already closed.");
if (this.isEOF) return -1;
if (this.currPos >= this.currChunkSize) {
readNextChunk();
if (this.isEOF) return -1;
}
this.currPos++;
return this.inputStream.read();
}
public int read (byte[] b, int off, int len) throws IOException {
if (this.isClosed) throw new IOException("Inputstream already closed.");
if (this.isEOF) return -1;
if (this.currPos >= this.currChunkSize) {
readNextChunk();
if (this.isEOF) return -1;
}
len = Math.min(len, this.currChunkSize - this.currPos);
int count = this.inputStream.read(b, off, len);
this.currPos += count;
return count;
}
public int read (byte[] b) throws IOException {
return read(b, 0, b.length);
}
/**
* Read the CRLF terminator.
* @throws IOException If an IO error occurs.
*/
private void readCRLF() throws IOException {
int cr = this.inputStream.read();
int lf = this.inputStream.read();
if ((cr != CR) || (lf != LF)) {
throw new IOException("Malformed chunk. CRLF expected but '" + cr + lf + "' found");
}
}
private void readNextChunk() throws IOException {
if (!this.beginningOfStream) readCRLF();
this.currChunkSize = readChunkFromStream(this.inputStream);
this.beginningOfStream = false;
this.currPos = 0;
if (this.currChunkSize == 0) {
this.isEOF = true;
readTrailer();
}
}
private void readTrailer() throws IOException {
BufferedReader reader = null;
serverByteBuffer bout = null;
try {
bout = new serverByteBuffer();
do {
int ch;
while ((ch = this.inputStream.read()) >= 0) {
bout.write(ch);
if (ch == LF) {
break;
}
}
if (bout.length() <= 2) break;
} while(true);
ByteArrayInputStream bin = new ByteArrayInputStream(bout.toByteArray());
reader = new BufferedReader(new InputStreamReader(bin));
this.httpTrailer = httpHeader.readHttpHeader(reader);
} finally {
if (reader != null) try {reader.close();}catch(Exception e){}
if (bout != null) try {bout.close();}catch(Exception e){}
}
}
public httpHeader getTrailer() {
return this.httpTrailer;
}
private static int readChunkFromStream(final InputStream in)
throws IOException {
serverByteBuffer baos = new serverByteBuffer();
int state = 0;
while (state != READ_CHUNK_STATE_FINISHED) {
int b = in.read();
if (b == -1) throw new IOException("Malformed chunk. Unexpected end");
switch (state) {
case 0:
switch (b) {
case CR:
state = READ_CHUNK_STATE_CR_READ;
break;
case '\"':
case ';':
case ' ':
state = READ_CHUNK_STATE_IN_EXT_CHUNK;
break;
default:
baos.write(b);
}
break;
case 1:
if (b == LF) {
state = READ_CHUNK_STATE_FINISHED;
} else {
// this was not CRLF
throw new IOException("Malformed chunk. Unexpected enf of chunk. MIssing CR character.");
}
break;
case 2:
switch (b) {
case CR:
state = READ_CHUNK_STATE_CR_READ;
break;
default:
break;
}
break;
default: throw new RuntimeException("Malformed chunk. Illegal state.");
}
}
int result;
try {
result = Integer.parseInt(baos.toString().trim(), 16);
} catch (NumberFormatException e) {
throw new IOException ("Malformed chunk. Bad chunk size: " + baos.toString());
}
return result;
}
public void close() throws IOException {
if (!this.isClosed) {
try {
if (!this.isEOF) {
exhaustInputStream(this);
}
} finally {
this.isEOF = true;
this.isClosed = true;
}
}
}
static void exhaustInputStream(InputStream inStream) throws IOException {
byte buffer[] = new byte[1024];
while (inStream.read(buffer) >= 0) {
;
}
}
}