XMLLightweightParser.java 9.33 KB
Newer Older
Gaston Dombiak's avatar
Gaston Dombiak committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372
/**
 * $RCSfile$
 * $Revision: $
 * $Date: $
 *
 * Copyright (C) 2006 Jive Software. All rights reserved.
 *
 * This software is published under the terms of the GNU Public License (GPL),
 * a copy of which is included in this distribution.
 */

package org.jivesoftware.wildfire.net;

import java.io.IOException;
import java.io.InputStream;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.channels.Channels;
import java.nio.channels.ReadableByteChannel;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.List;

/**
 * This is a Light-Weight XML Parser.
 * It read data from a channel and collect data until data are available in 
 * the channel.
 * When a message is complete you can retrieve messages invoking the method
 * getMsgs() and you can invoke the method areThereMsgs() to know if at least
 * an message is presents.
 * 
 * @author Daniele Piras
 *
 */
class XMLLightweightParser
{
  // Chars that rappresent CDATA section start
  protected static char[] CDATA_START = {'<','!','[','C','D','A','T','A','['};
  // Chars that rappresent CDATA section end
  protected static char[] CDATA_END = {']',']','>'};
  
  // Buffer with all data retrieved
  protected StringBuilder buffer = new StringBuilder();
  
  // ---- INTERNAL STATUS -------
  // Initial status
  protected static final int INIT = 0;
  // Status used when the first tag name is retrieved
  protected static final int HEAD = 2;
  // Status used when robot is inside the xml and it looking for the tag conclusion
  protected static final int INSIDE = 3;
  // Status used when a '<' is found and try to find the conclusion tag.
  protected static final int PRETAIL = 4;
  // Status used when the ending tag is equal to the head tag
  protected static final int TAIL = 5;
  // Status used when robot is inside the main tag and found an '/' to check '/>'.
  protected static final int VERIFY_CLOSE_TAG = 6;
  //  Status used when you are inside a parameter
  protected static final int INSIDE_PARAM_VALUE = 7;
  //  Status used when you are inside a cdata section
  protected static final int INSIDE_CDATA = 8;
  
  
  // Current robot status
  protected int status = INIT;
  
  // Index to looking for a CDATA section start or end.
  protected int cdataOffset = 0;
  
  // Number of chars that machs with the head tag. If the tailCount is equal to
  // the head length so a close tag is found.
  protected int tailCount = 0;
  // Indicate the starting point in the buffer for the next message.
  protected int startLastMsg = 0;
  // Flag used to discover tag in the form <tag />.
  protected boolean insideRootTag = false;
  // Object conteining the head tag
  protected StringBuilder head = new StringBuilder( 5 );
  // List with all finished messages found.
  protected List<String> msgs = new ArrayList<String>();

  
  private ReadableByteChannel inputChannel;
  byte[] rawByteBuffer;
  ByteBuffer byteBuffer;
  Charset encoder;
  
  public ReadableByteChannel getChannel()
  {
    return inputChannel;
  }
  
  public XMLLightweightParser( ReadableByteChannel channel, String charset )
  {
    rawByteBuffer = new byte[1024];
    byteBuffer = ByteBuffer.wrap( rawByteBuffer );
    setInput( channel, charset );
  }
  
  public XMLLightweightParser( InputStream is , String charset)
  {
    rawByteBuffer = new byte[1024];
    byteBuffer = ByteBuffer.wrap( rawByteBuffer );
    setInput( is, charset );
  }
  
  public void setInput( InputStream is, String charset )
  {
    inputChannel = Channels.newChannel( is );
    encoder = Charset.forName( charset );
    invalidateBuffer();
  }
  
  public void setInput( ReadableByteChannel channel, String charset )
  {
    inputChannel = channel;
    encoder = Charset.forName( charset );
    invalidateBuffer();
  }
  
  /*
   * true if the parser has found some complete xml message.
   */
  public boolean areThereMsgs()
  {
    return ( msgs.size() > 0 );
  }
  
  /*
   * @return an array with all messages found
   */
  public String[] getMsgs()
  {
    String[] res = new String[ msgs.size() ];
    for ( int i = 0; i < res.length; i++ )
    {
      res[ i ] = msgs.get( i );
    }
    msgs.clear();
    invalidateBuffer();
    return res;
  }
  
  /*
   * Method use to re-initialize the buffer 
   */
  protected void invalidateBuffer()
  {
    if ( buffer.length() > 0 )
    {
      String str = buffer.substring( startLastMsg ).toString().trim();
      buffer.delete( 0, buffer.length() );
      buffer.append( str );
      buffer.trimToSize();
    }
    startLastMsg = 0;
  }
  
  
  /*
   * Method that add a message to the list and reinit parser.
   */
  protected void foundMsg( String msg )
  {
    // Add message to the complete message list
    if ( msg != null )
    {
      msgs.add( msg.trim() );
    }
    // Move the position into the buffer
    status = INIT;
    tailCount = 0;
    cdataOffset = 0;
    head.setLength( 0 );
    insideRootTag = false;
  }
  
  /*
   * Main reading method
   */
  public void read() throws Exception
  {
 
    // Reset buffer
    byteBuffer.limit( rawByteBuffer.length );
    byteBuffer.rewind();
    int readByte = inputChannel.read( byteBuffer );
    if ( readByte == -1 )
    {
      // ERROR ON SOCKET!!
      throw new IOException( "ReadByte == -1.Socket Close" );
    }
    else if ( readByte <= 0 )
    {
      return;
    }
    else if (  readByte == 1 && rawByteBuffer[ 0 ] == ' ' )
    {
      // Heart bit! Ignore it.
      return;
    }
    byteBuffer.flip();
    byte[] bhs = byteBuffer.array();
    byteBuffer.rewind();
    CharBuffer charBuffer = encoder.decode( byteBuffer );
    charBuffer.flip();
    char[] buf = charBuffer.array();

      buffer.append( buf );
    // Robot.
    char ch;
    for ( int i = 0; i < readByte; i++ )
    {
      //ch = rawByteBuffer[ i ];
      ch = buf[ i ];
      if ( status == TAIL )
      {
        // Looking for the close tag
        if ( ch == head.charAt( tailCount ) )
        {
          tailCount++;
          if ( tailCount == head.length() )
          {
            // Close tag found!
            // Calculate the correct start,end position of the message into the buffer
            int end = buffer.length() - readByte + ( i + 1 );
            String msg = buffer.substring( startLastMsg, end );
            // Add message to the list
            foundMsg( msg );
            startLastMsg = end;
          }
        }
        else
        {
          tailCount = 0;
          status = INSIDE;
        }
      }
      else if ( status == PRETAIL )
      {
        if ( ch == CDATA_START[ cdataOffset ] )
        {
          cdataOffset++;
          if ( cdataOffset == CDATA_START.length )
          {
            status = INSIDE_CDATA;
            cdataOffset = 0;
            continue;
          }
        }
        else
        {
          cdataOffset = 0;
          status = INSIDE;
        }
        if ( ch == '/' )
        {
          status = TAIL;
        }
      }
      else if ( status == VERIFY_CLOSE_TAG )
      {
        if ( ch == '>' )
        {
          // Found a tag in the form <tag />
          int end = buffer.length() - readByte + ( i + 1 );
          String msg = buffer.substring( startLastMsg, end );
          // Add message to the list
          foundMsg( msg );
          startLastMsg = end;
        }
        else
        {
          status = INSIDE;
        }
      }
      else if ( status == INSIDE_PARAM_VALUE )
      {
        
        if ( ch == '"' )
        {
          status = INSIDE;
          continue;
        }
      }
      else if ( status == INSIDE_CDATA )
      {
        if ( ch == CDATA_END[ cdataOffset ] )
        {
          cdataOffset++;
          if ( cdataOffset == CDATA_END.length )
          {
            status = INSIDE;
            cdataOffset = 0;
            continue;
          }
        }
        else
        {
          cdataOffset = 0;
        }
      }
      else if ( status == INSIDE )
      {
        if ( ch == CDATA_START[ cdataOffset ] )
        {
          cdataOffset++;
          if ( cdataOffset == CDATA_START.length )
          {
            status = INSIDE_CDATA;
            cdataOffset = 0;
            continue;
          }
        }
        else
        {
          cdataOffset = 0;
        }
        if ( ch == '"' )
        {
          status = INSIDE_PARAM_VALUE;
        }
        else if ( ch == '>' )
        {
          if ( insideRootTag && "stream:stream>".equals( head.toString() ) )
          {
            // Found closing stream:stream
            int end = buffer.length() - readByte + ( i + 1 );
            String msg = buffer.substring( startLastMsg, end );
            foundMsg( msg ); 
            startLastMsg = end;
          }
          insideRootTag = false;
        }
        else if ( ch == '<' )
        {
          status = PRETAIL;
        }
        else if ( ch == '/' && insideRootTag  )
        {
          status = VERIFY_CLOSE_TAG;
        }
      }
      else if ( status == HEAD )
      {
        if ( ch == ' ' || ch == '>' )
        {
          // Append > to head to facility the research of </tag>
          head.append( ">" );
          status = INSIDE;
          insideRootTag = true;
          continue;
        }
        head.append( (char)ch );
        
      }
      else if ( status == INIT )
      {
        if ( ch != ' ' && ch != '\r' && ch != '\n' && ch != '<' )
        {
          invalidateBuffer();
          return;
        }
        if ( ch == '<' )
        {
          status = HEAD;
        }
      }
    }
  }

}