terminated migration from apache httpclient-3.1 to 4.1:

- remove the library
- added two classes from the httpclient-3.1 library as source code to YaCy because these classes were used by the YaCy HTTP Server
- modified the added classes ChunkedInputStream and ContentLengthInputStream in such a way that:
 * there are no more dependencies to httpclient-3.1
 * these classes had been simplified to serve only the purpose for the YaCy httpd

git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7171 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
orbiter 15 years ago
parent 8da4eb5de6
commit 3552476fbe

@ -13,7 +13,6 @@
<classpathentry kind="src" path="htroot/api/bookmarks/xbel"/>
<classpathentry kind="src" path="htroot/api/bookmarks/tags"/>
<classpathentry kind="con" path="org.eclipse.jdt.launching.JRE_CONTAINER"/>
<classpathentry kind="lib" path="lib/commons-httpclient-3.1.jar" sourcepath="/commons-httpclient-3.1/src"/>
<classpathentry kind="lib" path="lib/commons-logging-1.1.1.jar"/>
<classpathentry kind="lib" path="lib/commons-io-1.4.jar"/>
<classpathentry kind="lib" path="lib/servlet-api.jar"/>

@ -41,7 +41,6 @@
<string>$JAVAROOT/lib/bzip2.jar</string>
<string>$JAVAROOT/lib/commons-codec-1.4.jar</string>
<string>$JAVAROOT/lib/commons-fileupload-1.2.2.jar</string>
<string>$JAVAROOT/lib/commons-httpclient-3.1.jar</string>
<string>$JAVAROOT/lib/commons-io-1.4.jar</string>
<string>$JAVAROOT/lib/commons-jxpath-1.3.jar</string>
<string>$JAVAROOT/lib/commons-logging-1.1.1.jar</string>

@ -185,7 +185,6 @@
<pathelement location="${lib}/bzip2.jar" />
<pathelement location="${lib}/commons-codec-1.4.jar" />
<pathelement location="${lib}/commons-fileupload-1.2.2.jar" />
<pathelement location="${lib}/commons-httpclient-3.1.jar" />
<pathelement location="${lib}/commons-io-1.4.jar" />
<pathelement location="${lib}/commons-jxpath-1.3.jar" />
<pathelement location="${lib}/commons-logging-1.1.1.jar" />

Binary file not shown.

@ -0,0 +1,461 @@
/* ====================================================================
*
* 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 software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*
*/
/*
* This file was imported from apache http client 3.1 library and modified
* to work for the YaCy http server when htto client library use was migrated
* to apache http components 4.0
* by Michael Christen, 20.09.2010
*/
package de.anomic.http.server;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
/**
* <p>Transparently coalesces chunks of a HTTP stream that uses
* Transfer-Encoding chunked.</p>
*
* <p>Note that this class NEVER closes the underlying stream, even when close
* gets called. Instead, it will read until the "end" of its chunking on close,
* which allows for the seamless invocation of subsequent HTTP 1.1 calls, while
* not requiring the client to remember to read the entire contents of the
* response.</p>
*
* @author Ortwin Glueck
* @author Sean C. Sullivan
* @author Martin Elwin
* @author Eric Johnson
* @author <a href="mailto:mbowler@GargoyleSoftware.com">Mike Bowler</a>
* @author Michael Becke
* @author <a href="mailto:oleg@ural.ru">Oleg Kalnichevski</a>
*
* @since 2.0
*
*/
public class ChunkedInputStream extends InputStream {
/** The inputstream that we're wrapping */
private InputStream in;
/** The chunk size */
private int chunkSize;
/** The current position within the current chunk */
private int pos;
/** True if we'are at the beginning of stream */
private boolean bof = true;
/** True if we've reached the end of stream */
private boolean eof = false;
/** True if this stream is closed */
private boolean closed = false;
/**
* ChunkedInputStream constructor
*
* @param in the raw input stream
*
* @throws IOException If an IO error occurs
*/
public ChunkedInputStream(final InputStream in) throws IOException {
if (in == null) {
throw new IllegalArgumentException("InputStream parameter may not be null");
}
this.in = in;
this.pos = 0;
}
/**
* <p> Returns all the data in a chunked stream in coalesced form. A chunk
* is followed by a CRLF. The method returns -1 as soon as a chunksize of 0
* is detected.</p>
*
* <p> Trailer headers are read automcatically at the end of the stream and
* can be obtained with the getResponseFooters() method.</p>
*
* @return -1 of the end of the stream has been reached or the next data
* byte
* @throws IOException If an IO problem occurs
*
* @see HttpMethod#getResponseFooters()
*/
public int read() throws IOException {
if (closed) {
throw new IOException("Attempted read from closed stream.");
}
if (eof) {
return -1;
}
if (pos >= chunkSize) {
nextChunk();
if (eof) {
return -1;
}
}
pos++;
return in.read();
}
/**
* Read some bytes from the stream.
* @param b The byte array that will hold the contents from the stream.
* @param off The offset into the byte array at which bytes will start to be
* placed.
* @param len the maximum number of bytes that can be returned.
* @return The number of bytes returned or -1 if the end of stream has been
* reached.
* @see java.io.InputStream#read(byte[], int, int)
* @throws IOException if an IO problem occurs.
*/
public int read (byte[] b, int off, int len) throws IOException {
if (closed) {
throw new IOException("Attempted read from closed stream.");
}
if (eof) {
return -1;
}
if (pos >= chunkSize) {
nextChunk();
if (eof) {
return -1;
}
}
len = Math.min(len, chunkSize - pos);
int count = in.read(b, off, len);
pos += count;
return count;
}
/**
* Read some bytes from the stream.
* @param b The byte array that will hold the contents from the stream.
* @return The number of bytes returned or -1 if the end of stream has been
* reached.
* @see java.io.InputStream#read(byte[])
* @throws IOException if an IO problem occurs.
*/
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 = in.read();
int lf = in.read();
if ((cr != '\r') || (lf != '\n')) {
throw new IOException(
"CRLF expected at end of chunk: " + cr + "/" + lf);
}
}
/**
* Read the next chunk.
* @throws IOException If an IO error occurs.
*/
private void nextChunk() throws IOException {
if (!bof) {
readCRLF();
}
chunkSize = getChunkSizeFromInputStream(in);
bof = false;
pos = 0;
if (chunkSize == 0) {
eof = true;
skipTrailerHeaders();
}
}
/**
* Expects the stream to start with a chunksize in hex with optional
* comments after a semicolon. The line must end with a CRLF: "a3; some
* comment\r\n" Positions the stream at the start of the next line.
*
* @param in The new input stream.
* @param required <tt>true<tt/> if a valid chunk must be present,
* <tt>false<tt/> otherwise.
*
* @return the chunk size as integer
*
* @throws IOException when the chunk size could not be parsed
*/
private static int getChunkSizeFromInputStream(final InputStream in)
throws IOException {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
// States: 0=normal, 1=\r was scanned, 2=inside quoted string, -1=end
int state = 0;
while (state != -1) {
int b = in.read();
if (b == -1) {
throw new IOException("chunked stream ended unexpectedly");
}
switch (state) {
case 0:
switch (b) {
case '\r':
state = 1;
break;
case '\"':
state = 2;
baos.write(b);
break;
default:
baos.write(b);
}
break;
case 1:
if (b == '\n') {
state = -1;
} else {
// this was not CRLF
throw new IOException("Protocol violation: Unexpected"
+ " single newline character in chunk size");
}
break;
case 2:
switch (b) {
case '\\':
b = in.read();
baos.write(b);
break;
case '\"':
state = 0;
baos.write(b);
break;
default:
baos.write(b);
}
break;
default: throw new RuntimeException("assertion failed");
}
}
//parse data
String dataString = getAsciiString(baos.toByteArray());
int separator = dataString.indexOf(';');
dataString = (separator > 0)
? dataString.substring(0, separator).trim()
: dataString.trim();
int result;
try {
result = Integer.parseInt(dataString.trim(), 16);
} catch (NumberFormatException e) {
throw new IOException ("Bad chunk size: " + dataString);
}
return result;
}
/**
* Converts the byte array of ASCII characters to a string. This method is
* to be used when decoding content of HTTP elements (such as response
* headers)
*
* @param data the byte array to be encoded
* @return The string representation of the byte array
*
* @since 3.0
*/
private static String getAsciiString(final byte[] data) throws IOException {
if (data == null) {
throw new IllegalArgumentException("Parameter may not be null");
}
try {
return new String(data, 0, data.length, "US-ASCII");
} catch (UnsupportedEncodingException e) {
throw new IOException("HttpClient requires ASCII support");
}
}
/**
* Reads and stores the Trailer headers.
* @throws IOException If an IO problem occurs
*/
private void skipTrailerHeaders() throws IOException {
for (; ;) {
String line = readLine(in, "US-ASCII");
if ((line == null) || (line.trim().length() < 1)) break;
}
}
/**
* Read up to <tt>"\n"</tt> from an (unchunked) input stream.
* If the stream ends before the line terminator is found,
* the last part of the string will still be returned.
* If no input data available, <code>null</code> is returned.
*
* @param inputStream the stream to read from
* @param charset charset of HTTP protocol elements
*
* @throws IOException if an I/O problem occurs
* @return a line from the stream
*
* @since 3.0
*/
private static String readLine(InputStream inputStream, String charset) throws IOException {
byte[] rawdata = readRawLine(inputStream);
if (rawdata == null) {
return null;
}
// strip CR and LF from the end
int len = rawdata.length;
int offset = 0;
if (len > 0) {
if (rawdata[len - 1] == '\n') {
offset++;
if (len > 1) {
if (rawdata[len - 2] == '\r') {
offset++;
}
}
}
}
final String result = getString(rawdata, 0, len - offset, charset);
return result;
}
/**
* Converts the byte array of HTTP content characters to a string. If
* the specified charset is not supported, default system encoding
* is used.
*
* @param data the byte array to be encoded
* @param offset the index of the first byte to encode
* @param length the number of bytes to encode
* @param charset the desired character encoding
* @return The result of the conversion.
*
* @since 3.0
*/
private static String getString(
final byte[] data,
int offset,
int length,
String charset
) {
if (data == null) {
throw new IllegalArgumentException("Parameter may not be null");
}
if (charset == null || charset.length() == 0) {
throw new IllegalArgumentException("charset may not be null or empty");
}
try {
return new String(data, offset, length, charset);
} catch (UnsupportedEncodingException e) {
return new String(data, offset, length);
}
}
/**
* Return byte array from an (unchunked) input stream.
* Stop reading when <tt>"\n"</tt> terminator encountered
* If the stream ends before the line terminator is found,
* the last part of the string will still be returned.
* If no input data available, <code>null</code> is returned.
*
* @param inputStream the stream to read from
*
* @throws IOException if an I/O problem occurs
* @return a byte array from the stream
*/
private static byte[] readRawLine(InputStream inputStream) throws IOException {
ByteArrayOutputStream buf = new ByteArrayOutputStream();
int ch;
while ((ch = inputStream.read()) >= 0) {
buf.write(ch);
if (ch == '\n') { // be tolerant (RFC-2616 Section 19.3)
break;
}
}
if (buf.size() == 0) {
return null;
}
return buf.toByteArray();
}
/**
* Upon close, this reads the remainder of the chunked message,
* leaving the underlying socket at a position to start reading the
* next response without scanning.
* @throws IOException If an IO problem occurs.
*/
public void close() throws IOException {
if (!closed) {
try {
if (!eof) {
exhaustInputStream(this);
}
} finally {
eof = true;
closed = true;
}
}
}
/**
* Exhaust an input stream, reading until EOF has been encountered.
*
* <p>Note that this function is intended as a non-public utility.
* This is a little weird, but it seemed silly to make a utility
* class for this one function, so instead it is just static and
* shared that way.</p>
*
* @param inStream The {@link InputStream} to exhaust.
* @throws IOException If an IO problem occurs
*/
static void exhaustInputStream(InputStream inStream) throws IOException {
// read and discard the remainder of the message
byte buffer[] = new byte[1024];
while (inStream.read(buffer) >= 0) {
;
}
}
}

@ -0,0 +1,210 @@
/*
* ====================================================================
*
* 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 software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*
*/
/*
* This file was imported from apache http client 3.1 library and modified
* to work for the YaCy http server when htto client library use was migrated
* to apache http components 4.0
* by Michael Christen, 20.09.2010
*/
package de.anomic.http.server;
import java.io.IOException;
import java.io.InputStream;
/**
* Cuts the wrapped InputStream off after a specified number of bytes.
*
* <p>Implementation note: Choices abound. One approach would pass
* through the {@link InputStream#mark} and {@link InputStream#reset} calls to
* the underlying stream. That's tricky, though, because you then have to
* start duplicating the work of keeping track of how much a reset rewinds.
* Further, you have to watch out for the "readLimit", and since the semantics
* for the readLimit leave room for differing implementations, you might get
* into a lot of trouble.</p>
*
* <p>Alternatively, you could make this class extend {@link java.io.BufferedInputStream}
* and then use the protected members of that class to avoid duplicated effort.
* That solution has the side effect of adding yet another possible layer of
* buffering.</p>
*
* <p>Then, there is the simple choice, which this takes - simply don't
* support {@link InputStream#mark} and {@link InputStream#reset}. That choice
* has the added benefit of keeping this class very simple.</p>
*
* @author Ortwin Glueck
* @author Eric Johnson
* @author <a href="mailto:mbowler@GargoyleSoftware.com">Mike Bowler</a>
* @since 2.0
*/
public class ContentLengthInputStream extends InputStream {
/**
* The maximum number of bytes that can be read from the stream. Subsequent
* read operations will return -1.
*/
private long contentLength;
/** The current position */
private long pos = 0;
/** True if the stream is closed. */
private boolean closed = false;
/**
* Wrapped input stream that all calls are delegated to.
*/
private InputStream wrappedStream = null;
/**
* Creates a new length limited stream
*
* @param in The stream to wrap
* @param contentLength The maximum number of bytes that can be read from
* the stream. Subsequent read operations will return -1.
*
* @since 3.0
*/
public ContentLengthInputStream(InputStream in, long contentLength) {
super();
this.wrappedStream = in;
this.contentLength = contentLength;
}
/**
* <p>Reads until the end of the known length of content.</p>
*
* <p>Does not close the underlying socket input, but instead leaves it
* primed to parse the next response.</p>
* @throws IOException If an IO problem occurs.
*/
public void close() throws IOException {
if (!closed) {
try {
ChunkedInputStream.exhaustInputStream(this);
} finally {
// close after above so that we don't throw an exception trying
// to read after closed!
closed = true;
}
}
}
/**
* Read the next byte from the stream
* @return The next byte or -1 if the end of stream has been reached.
* @throws IOException If an IO problem occurs
* @see java.io.InputStream#read()
*/
public int read() throws IOException {
if (closed) {
throw new IOException("Attempted read from closed stream.");
}
if (pos >= contentLength) {
return -1;
}
pos++;
return this.wrappedStream.read();
}
/**
* Does standard {@link InputStream#read(byte[], int, int)} behavior, but
* also notifies the watcher when the contents have been consumed.
*
* @param b The byte array to fill.
* @param off Start filling at this position.
* @param len The number of bytes to attempt to read.
* @return The number of bytes read, or -1 if the end of content has been
* reached.
*
* @throws java.io.IOException Should an error occur on the wrapped stream.
*/
public int read (byte[] b, int off, int len) throws java.io.IOException {
if (closed) {
throw new IOException("Attempted read from closed stream.");
}
if (pos >= contentLength) {
return -1;
}
if (pos + len > contentLength) {
len = (int) (contentLength - pos);
}
int count = this.wrappedStream.read(b, off, len);
pos += count;
return count;
}
/**
* Read more bytes from the stream.
* @param b The byte array to put the new data in.
* @return The number of bytes read into the buffer.
* @throws IOException If an IO problem occurs
* @see java.io.InputStream#read(byte[])
*/
public int read(byte[] b) throws IOException {
return read(b, 0, b.length);
}
/**
* Skips and discards a number of bytes from the input stream.
* @param n The number of bytes to skip.
* @return The actual number of bytes skipped. <= 0 if no bytes
* are skipped.
* @throws IOException If an error occurs while skipping bytes.
* @see InputStream#skip(long)
*/
public long skip(long n) throws IOException {
// make sure we don't skip more bytes than are
// still available
long length = Math.min(n, contentLength - pos);
// skip and keep track of the bytes actually skipped
length = this.wrappedStream.skip(length);
// only add the skipped bytes to the current position
// if bytes were actually skipped
if (length > 0) {
pos += length;
}
return length;
}
public int available() throws IOException {
if (this.closed) {
return 0;
}
int avail = this.wrappedStream.available();
if (this.pos + avail > this.contentLength ) {
avail = (int)(this.contentLength - this.pos);
}
return avail;
}
}

@ -71,8 +71,6 @@ import org.apache.commons.fileupload.FileUploadBase;
import org.apache.commons.fileupload.FileUploadException;
import org.apache.commons.fileupload.RequestContext;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.apache.commons.httpclient.ChunkedInputStream;
import org.apache.commons.httpclient.ContentLengthInputStream;
import de.anomic.data.userDB;
import de.anomic.search.Switchboard;

Loading…
Cancel
Save