[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer Cursor.java,1.9,1.10 Lexer.java,1.10,1.11 Page.
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer Cursor.java,1.9,1.10 Lexer.java,1.10,1.11 Page.java,1.16,1.17 PageIndex.java,1.9,1.10 Source.java,1.10,1.11
|
From: <der...@us...> - 2003-09-29 22:02:39
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1:/tmp/cvs-serv32344/lexer
Modified Files:
Cursor.java Lexer.java Page.java PageIndex.java Source.java
Log Message:
Fix broken serializability.
Index: Cursor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Cursor.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** Cursor.java 28 Sep 2003 15:33:57 -0000 1.9
--- Cursor.java 29 Sep 2003 00:00:38 -0000 1.10
***************
*** 33,36 ****
--- 33,37 ----
package org.htmlparser.lexer;
+ import java.io.Serializable;
import org.htmlparser.util.sort.Ordered;
***************
*** 39,43 ****
* This class remembers the page it came from and its position within the page.
*/
! public class Cursor implements Ordered, Cloneable
{
/**
--- 40,48 ----
* This class remembers the page it came from and its position within the page.
*/
! public class Cursor
! implements
! Serializable,
! Ordered,
! Cloneable
{
/**
Index: Lexer.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Lexer.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** Lexer.java 28 Sep 2003 15:33:57 -0000 1.10
--- Lexer.java 29 Sep 2003 00:00:38 -0000 1.11
***************
*** 34,37 ****
--- 34,38 ----
import java.io.IOException;
+ import java.io.Serializable;
import java.net.MalformedURLException;
import java.net.URL;
***************
*** 59,62 ****
--- 60,64 ----
public class Lexer
implements
+ Serializable,
NodeFactory
{
***************
*** 75,78 ****
--- 77,90 ----
*/
protected NodeFactory mFactory;
+
+ /**
+ * Creates a new instance of a Lexer.
+ */
+ public Lexer ()
+ {
+ setPage (new Page (""));
+ setCursor (new Cursor (getPage (), 0));
+ setNodeFactory (this);
+ }
/**
Index: Page.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Page.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** Page.java 28 Sep 2003 15:33:57 -0000 1.16
--- Page.java 29 Sep 2003 00:00:39 -0000 1.17
***************
*** 35,38 ****
--- 35,39 ----
import java.io.*;
import java.io.IOException;
+ import java.io.Serializable;
import java.lang.reflect.*;
import java.net.*;
***************
*** 46,49 ****
--- 47,52 ----
*/
public class Page
+ implements
+ Serializable
{
/**
***************
*** 75,79 ****
* The connection this page is coming from or <code>null</code>.
*/
! protected URLConnection mConnection;
/**
--- 78,82 ----
* The connection this page is coming from or <code>null</code>.
*/
! protected transient URLConnection mConnection;
/**
***************
*** 95,98 ****
--- 98,109 ----
/**
+ * Construct an empty page reading.
+ */
+ public Page ()
+ {
+ this ("");
+ }
+
+ /**
* Construct a page reading from a URL connection.
* @param connection A fully conditioned connection. The connect()
***************
*** 154,157 ****
--- 165,257 ----
}
+ //
+ // Serialization support
+ //
+
+ private void writeObject (ObjectOutputStream out)
+ throws
+ IOException
+ {
+ String href;
+ Source source;
+ PageIndex index;
+
+ // two cases, reading from a URL and not
+ if (null != getConnection ())
+ {
+ out.writeBoolean (true);
+ out.writeInt (mSource.offset ()); // need to preread this much
+ href = getUrl ();
+ out.writeObject (href);
+ setUrl (getConnection ().getURL ().toExternalForm ());
+ source = getSource ();
+ mSource = null; // don't serialize the source if we can avoid it
+ index = mIndex;
+ mIndex = null; // will get recreated; valid for the new page anyway?
+ out.defaultWriteObject ();
+ mSource = source;
+ mIndex = index;
+ }
+ else
+ {
+ out.writeBoolean (false);
+ href = getUrl ();
+ out.writeObject (href);
+ setUrl (null); // don't try and read a bogus URL
+ out.defaultWriteObject ();
+ setUrl (href);
+ }
+ }
+
+ private void readObject (ObjectInputStream in)
+ throws
+ IOException,
+ ClassNotFoundException
+ {
+ boolean fromurl;
+ int offset;
+ String href;
+ URL url;
+ Cursor cursor;
+
+ fromurl = in.readBoolean ();
+ if (fromurl)
+ {
+ offset = in.readInt ();
+ href = (String)in.readObject ();
+ in.defaultReadObject ();
+ // open the URL
+ if (null != getUrl ())
+ {
+ url = new URL (getUrl ());
+ try
+ {
+ setConnection (url.openConnection ());
+ }
+ catch (ParserException pe)
+ {
+ throw new IOException (pe.getMessage ());
+ }
+ }
+ cursor = new Cursor (this, 0);
+ for (int i = 0; i < offset; i++)
+ try
+ {
+ getCharacter (cursor);
+ }
+ catch (ParserException pe)
+ {
+ throw new IOException (pe.getMessage ());
+ }
+ setUrl (href);
+ }
+ else
+ {
+ href = (String)in.readObject ();
+ in.defaultReadObject ();
+ setUrl (href);
+ }
+ }
+
/**
* Reset the page by resetting the source of characters.
***************
*** 189,193 ****
- mUrl = null;
mConnection = connection;
try
--- 289,292 ----
***************
*** 232,235 ****
--- 331,335 ----
throw new ParserException (ioe.getMessage (), ioe);
}
+ mUrl = connection.getURL ().toExternalForm ();
mIndex = new PageIndex (this);
}
***************
*** 241,252 ****
public String getUrl ()
{
- URLConnection connection;
- if (null == mUrl)
- {
- connection = getConnection ();
- if (null != connection)
- mUrl = connection.getURL ().toExternalForm ();
- }
-
return (mUrl);
}
--- 341,344 ----
Index: PageIndex.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/PageIndex.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** PageIndex.java 22 Sep 2003 02:39:59 -0000 1.9
--- PageIndex.java 29 Sep 2003 00:00:39 -0000 1.10
***************
*** 33,36 ****
--- 33,37 ----
package org.htmlparser.lexer;
+ import java.io.Serializable;
import org.htmlparser.util.sort.Ordered;
import org.htmlparser.util.sort.Sort;
***************
*** 46,50 ****
* does not incur the overhead of an <code>Integer</code> object per element.
*/
! public class PageIndex implements Sortable
{
/**
--- 47,54 ----
* does not incur the overhead of an <code>Integer</code> object per element.
*/
! public class PageIndex
! implements
! Serializable,
! Sortable
{
/**
Index: Source.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Source.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** Source.java 28 Sep 2003 15:33:57 -0000 1.10
--- Source.java 29 Sep 2003 00:00:39 -0000 1.11
***************
*** 29,36 ****
--- 29,40 ----
package org.htmlparser.lexer;
+ import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
+ import java.io.ObjectInputStream;
+ import java.io.ObjectOutputStream;
import java.io.Reader;
+ import java.io.Serializable;
import java.io.UnsupportedEncodingException;
***************
*** 46,50 ****
*
*/
! public class Source extends Reader
{
/**
--- 50,58 ----
*
*/
! public class Source
! extends
! Reader
! implements
! Serializable
{
/**
***************
*** 61,65 ****
* The stream of bytes.
*/
! protected InputStream mStream;
/**
--- 69,73 ----
* The stream of bytes.
*/
! protected transient InputStream mStream;
/**
***************
*** 71,75 ****
* The converter from bytes to characters.
*/
! protected InputStreamReader mReader;
/**
--- 79,83 ----
* The converter from bytes to characters.
*/
! protected transient InputStreamReader mReader;
/**
***************
*** 143,146 ****
--- 151,189 ----
}
+ //
+ // Serialization support
+ //
+
+ private void writeObject (ObjectOutputStream out)
+ throws
+ IOException
+ {
+ int offset;
+ char[] buffer;
+
+ if (null != mStream)
+ {
+ // remember the offset, drain the input stream, restore the offset
+ offset = mOffset;
+ buffer = new char[4096];
+ while (-1 != read (buffer))
+ ;
+ mOffset = offset;
+ }
+
+ out.defaultWriteObject ();
+ }
+
+ private void readObject (ObjectInputStream in)
+ throws
+ IOException,
+ ClassNotFoundException
+ {
+ in.defaultReadObject ();
+ if (null != mBuffer) // buffer is null when destroy's been called
+ // pretend we're open, mStream goes null when exhausted
+ mStream = new ByteArrayInputStream (new byte[0]);
+ }
+
/**
* Get the input stream being used.
***************
*** 421,424 ****
--- 464,476 ----
mOffset = 0;
mMark = -1;
+ }
+
+ /**
+ * Get the position (in characters).
+ * @return The number of characters that have been read.
+ */
+ public int offset ()
+ {
+ return (mOffset);
}
|
