SDGEN: This is the data generator for Bisque.
Author: Bingsheng He (saven@cs.ust.hk)

/*									tab:4
 * "Copyright (c) 2000-2003 The Regents of the University  of California.  
 * All rights reserved.
 *
 * Permission to use, copy, modify, and distribute this software and its
 * documentation for any purpose, without fee, and without written agreement is
 * hereby granted, provided that the above copyright notice, the following
 * two paragraphs and the author appear in all copies of this software.
 * 
 * IN NO EVENT SHALL THE UNIVERSITY OF CALIFORNIA BE LIABLE TO ANY PARTY FOR
 * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT
 * OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN IF THE UNIVERSITY OF
 * CALIFORNIA HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 * 
 * THE UNIVERSITY OF CALIFORNIA SPECIFICALLY DISCLAIMS ANY WARRANTIES,
 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
 * AND FITNESS FOR A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS
 * ON AN "AS IS" BASIS, AND THE UNIVERSITY OF CALIFORNIA HAS NO OBLIGATION TO
 * PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS."
 *
 * Copyright (c) 2002-2003 Intel Corporation
 * All rights reserved.
 *
 * This file is distributed under the terms in the attached INTEL-LICENSE     
 * file. If you do not find these files, copies can be found by writing to
 * Intel Research Berkeley, 2150 Shattuck Avenue, Suite 1300, Berkeley, CA, 
 * 94704.  Attention:  Intel License Inquiry.
 */
********************************************************************************

Copyright (c) 2004-2005, The Hong Kong University of Science and Technology (HKUST)
All rights reserved.

Redistribution and use in source and binary forms, with or without 
modification, are permitted provided that the following conditions 
  are met:
 
    * Redistributions of source code must retain the above copyright notice, 
      this list of conditions, the authors and the following disclaimer.
    * Redistributions in binary form must reproduce the above copyright notice,
      this list of conditions, the authors and the following disclaimer in
      the documentation and/or other materials provided with the distribution.
    * Neither the name of the university nor the names of its 
      contributors may be used to endorse or promote products derived from 
      this software without specific prior written permission.
 
  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 
  AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 
  IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 
  ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 
  LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 
  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 
  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 
  INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 
  CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 
  ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 
  POSSIBILITY OF SUCH DAMAGE.


********************************************************************************



README:


=========================================================================================

We have applied spatio-temporal interpolation to synthesize the data sets.
The input to SDGEN is a real-world data set and two configuration files.
The default real-world data set is Intel Lab data set.
The readings in the output data set files (including light, temperature) are ADC counts.

Here is the check lists of the files:
[java libs required]:
./xerces-2_6_2/
./kss-2.6.0.jar
./ksssci-0.4.0.jar
./numericalMethods.jar

[java path setting batch file]:
./SetPath.bat

[sample configuration files]:
./IntelFullInput.xml
./IntelFullOutput_25Xrun.xml
./IntelFullOutput_49Xrun.xml
./IntelFullOutput_9Xrun.xml
./sample_25.xrun
./sample_49.xrun
./sample_9.xrun

[java source]:
./DTable.java
./InputParser.java
./Misc.java
./MTS300.java
./MyInterp.java
./OutputParser.java
./SDAnalyzer.java
./SDGEN.java
./Topology.java

********************************************************************************


USAGE:
=========================================================================================

Requirement:
The input and output schema should be "ts,nodeid,attr1,attr2...".
That is to say, we start the interpolation from the third column and the first two column are fixed to be "ts,nodeid".
We use the "ts" instead of the "timestamp" in our schema specification, because "timestamp" is a reserved word in MS ACCESS.

To run the data set generator program, please do the following steps:
(1) run SetPath.bat;
(2) compile the program: javac *.java
(3) to run SDGEN, we use the command: java SDGEN -i <original.xml> -o <target.xml>
to run the examples:
java -Xmx400M SDGEN -i IntelFullInput.xml -o IntelFullOutput_9Xrun.xml

NOTE: We add "-Xmx400M" to avoid the OutOfMemory java expecetion.

To import new data sets, please do the following steps:
(1) run SetPath.bat;
(2) compile the program: javac *.java
(3) to run SDGEN, we use the command: java SDAnalyzer -tn <tableName> -source <Dataset> -schema <schema>
to run the examples:
java SDAnalyzer -tn myTable -source SampleDataSet.dat -schema "ts TIME, nodeid integer, temperature double, light double"

another command you may use is to delete an existing table using GDIAnalyzer, java GDIAnalyzer -del <table-to-delete>.
one example is: 
java SDAnalyzer -del myTable


