com.datatorrent.lib.logs.LineTokenizerKeyVal Maven / Gradle / Ivy

Go to download
/**
 * 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.
 */
package com.datatorrent.lib.logs;

import java.util.HashMap;

import com.datatorrent.api.DefaultOutputPort;
import com.datatorrent.api.annotation.OperatorAnnotation;
import com.datatorrent.api.annotation.Stateless;
import com.datatorrent.lib.util.BaseLineTokenizer;
import com.datatorrent.lib.util.UnifierHashMap;

/**
 * This operator splits lines into tokens, and tokens into sub-tokens. 
 * Emitted tuples are key value pairs where tokens are the keys and sub tokens are the values.
 * 
 * Useful to convert String (log lines) into a POJO (HashMap)
 * 
 * 
 * This module is a pass through

 * 

 * StateFull : No,  tokens are processed in current window. 

 * Partitions : Yes, output unifier. 

 * 

 * 

 * Ideal for applications like log processing

 * Ports:

 * data: expects String

 * tokens: emits HashMap<String,String>

 * 

 * Properties:

 * splitby: The characters used to split the line. Default is ";\t "

 * splittokenby: The characters used to split a token into key,val pair. Default is "", i.e. tokens are not
 * split, and key is set to token, and val is null

 * 

 * 
 * @displayName Line Tokenizer Key Value
 * @category Tuple Converters
 * @tags string, key value
 *
 * @since 0.3.2
 */
@Stateless
@OperatorAnnotation(partitionable = true)
public class LineTokenizerKeyVal extends BaseLineTokenizer
{
  /**
   * This output port emits key value pairs where the key is a token in an input string,
   * and the value is a sub token of the key token.
   */
  public final transient DefaultOutputPort> tokens = new DefaultOutputPort>()
  {
    @Override
    public Unifier> getUnifier()
    {
      return new UnifierHashMap();
    }
  };

  private transient HashMap map = null;
  private transient String skey = "";
  private transient String sval = "";

  /**
   * sets up the cache
   */
  @Override
  public void beginProcessTokens()
  {
    map = new HashMap();
  }

  /**
   * emits tokens on port "tokens", and clears the cache
   */
  @Override
  public void endProcessTokens()
  {
    if (map != null) {
      tokens.emit(map);
      map = null;
    }
  }

  /**
   * clears subtoken key,val pair
   */
  @Override
  public void beginProcessSubTokens()
  {
    skey = "";
    sval = "";
  }

  /**
   * inserts subtoken key,val pair in subtoken hash. If there are multiple keys with the same value
   * override this call and append values
   */
  @Override
  public void endProcessSubTokens()
  {
    if (!skey.isEmpty()) {
      map.put(skey, sval);
      skey = "";
      sval = "";
    }
  }

  /**
   * first subtoken is the key, the next is the val.
   * No error is flagged for third token as yet.
   * @param subtok
   */
  @Override
  public void processSubToken(String subtok)
  {
    if (skey.isEmpty()) {
      skey = subtok;
    } else if (sval.isEmpty()) {
      sval = subtok;
    }
  }
}