<?
 
/*************************************************************
   CONFIGURABLE PARAMETERS
**********************************************************/
 
/**
 * These can also be configured per-query below, if more granularity is needed
 */
$from_db_connection = array('localhost', 'username', 'password', 'db-instance');
$to_db_connection = array('localhost', 'username', 'password', 'db-instance');
 
/**
 * We either output by printing insert statements to the screen for testing(true),
 * or by running the insert queries directly on the target db(false-default). Set this
 * to false when you're ready to import for real
 */
$fake_inserts = false;
 
/**
 * Max rows allows you to only run a certain number of queries per table, for testing. Leave
 * this set to 0 for the real run
 */
$max_rows = 0;
 
/**
 * If true, script will exist on any failed insert query.
 * If false, will continue to run even if queries fail and insert the other records.
 */
$stop_on_failed_query = false;
 
/**
 * $tablemap is an array containing one entry for each table to be converted.
 * Note that tables don't necessarily have to be 1:1 to make this work, since
 * the source query can use whatever sort of joins needed to set up the source
 * fields. There must, of course, be exactly one output table.
 *
 * <p>Here are the fields for each conversion element:
 * <ul>
 *   <li>connection info - an array containin the source database and target database. It contains two
 *       elements, each is an array containing array( host, username, password, db_instance )
 *   <li>source_query - the query to be run against source db, set it up however you like, the field names should correspond with the 'fields' array's keys
 *   <li>fields - see below
 *   <li>defaults - default values to apply to any fields in target table, overwritten by values in 'fields'
 * </ul>
 *
 * <p>If you just want to create insert statements with the data, use dest_table. If you
 * need custom queries or updates to run, you can specify dest_query. Values for any output fields
 * can be substituted using {field_name} in the query.
 *
 * <p>The 'fields' element is an indexed array. The key is the source table's column name. The value is either a string indicating the name of hte column in the destination table, or an array containing exactly two elements: 1) a function to call, which will be passed the value from source table, 2) the destination column name
 *
 * <p>The function is passed a host of arguments, in order:
 * <ol>
 *  <li>value from originating column
 *  <li>entire data row
 *  <li>original column name
 *  <li>destination column name
 * </ol>
 *
 * <p>To list the same field twice (since the keys would be identical) you can use an array index which will be stripped from the column name before querying, such as "field_id[1]", "field_id[2]", which both refer to a column named "field_id"
 */
$tablemap = array();
 
/**
* This example is a simple, straight copy from one table to another
*/
$tablemap[] = array(
	 "connection_info" => array(
				    "source" => $from_db_connection,
				    "dest" => $to_db_connection
	 ),
	 "source_query" => 'select * from source_table',
	 "dest_table" => "destination_table",
	 'fields' => array(
            'source1' => 'dest1',
            'source2' => 'dest2',
			   'posted'  => array('toSqlDate', 'date'), // convert unix timestamp to sql date
			   'id[1]'   => 'id', // here we set two dest fields from "id", using array index
			   'id[2]'   => array('getParentId', 'parent') // another custom function
	 ),
	 'defaults' => array(
			   'dest3' => '0',
            'dest4' => ''
	 )
);
 
/*
 * This example runs a customized query instead of a normal insert
 */
 
$tablemap[] = array(
	 "connection_info" => array(
          "source" => $from_db_connection,
          "dest" => $to_db_connection
	 ),
	 "source_query" => '
         select 
            count(*) as src_total, category
         from 
            source_table_1 s1, source_table_2 s2
         where
            s1.id = s2.id AND s2.id > 100
         group by
            category',
	 "dest_query" => 'update dest_table set total = {dest_total} where catid = {cat}',
	 'fields' => array(
			   'category' => 'cat',
			   'src_total' => 'dest_total'
	 ),
	 'defaults' => array() // these are still applicable, just didn't need any
);
 
 
/*****************************************************************************
  USER FUNCTIONS (methods used by the 'fields' array to convert values)
***************************************************************************/
 
/**
 * Just an example function that creates a value by combining two cols from source table
 */
function getParentId($src_id, $data_row, $src_col_name, $dest_col_name) {
   if( $src_id > 0 ) {
      // if it exists, use it
      return $src_id;
   }
   // otherwise, create one
   return $data_row["number_1"] + $data_row["number_2"];
}
 
/**
 * Example function to create an incremental id for the result data
 */
function getIncrementalId() {
   global $currentIncId;
   return ++$currentIncId;
}
$currentIncId = 0;
 
/**
 * Converts a unix timestamp to a sql datetime
 */
function toSqlDate($utime) {
  return date("Y-m-d H:i:s", $utime);
}
 
?>

<?
/*********************************
 GO TO THIS FILE TO CONFIGURE
 ********************************/
  include("config.php");
 
/*********************************
 YOU WON'T NEED TO CHANGE ANYTHING BELOW HERE
 ********************************/
 
/**
 * Prints out contents and adds html chars if this isn't cli
 */
function printIt($txt) {
  $e = php_sapi_name() == "cli"? "\n" : "<br>\n";
  print $txt.$e;
}
 
/**
 * Generates a list of insertable values, escaped for sql
 */
function make_vals($row) {
  $s = '';
  foreach($row as $k=>$v) {
    if( $s ) { $s .= ", "; }
    $s .= fixMySquirrelVal($v);
  }
  return $s;
}
 
/**
 * Adds a data row to the dest table
 * @param resource $dbin the db connection
 * @param string $table dest table
 * @param array $row indexed array of (string)col => (mixed)value - do not escape these
 */
function addRow($dbin, $table, $row) {
  $vals = make_vals($row);
  $cols = '`'.join('`,`',array_keys($row)).'`';
  $query = "INSERT INTO `$table` ($cols) VALUES($vals)";
  return runMySquirrelQuery($dbin, $query);
}
 
/**
 * Runs a custom query rather than a simple insert
 * @param resource $dbin the db connection
 * @param string $query the custom query, with {field_name} anywhere the field vals will be substituted
 * @param array $row indexed array of (string)col => (mixed)value - do not escape these
 */
function customQuery($dbin, $query, $row) {
  // substitute our new vals
  foreach($row as $k=>$v) {
    $query = str_replace("{{$k}}", fixMySquirrelVal($v), $query);
  }
  // run query with custom vals
  return runMySquirrelQuery($dbin, $query);
}
 
function fixMySquirrelVal($v) {
  if(is_null($v)) {
    return "NULL";
  }
  return sprintf(" '%s' ", mysql_real_escape_string($v));
}
 
function runMySquirrelQuery($dbin, $query) {
  global $fake_inserts;
  global $stop_on_failed_query;
  if( $fake_inserts ) {
    printIt($query);
    return true;
  }
  else if( !mysql_query($query, $dbin) ) {
    printIt("!!ERROR!! Unable to insert record ($query): ".mysql_error());
    if( $stop_on_failed_query ) { exit; }
    return false;
  }
  return true;
}
 
/**
 * Given a row from the source table, converts field names and values
 * to be compatible for dest table
 * @param array $row indexed array of (string)col => (mixed)value - do not escape these
 * @param array $fields indexed array of (string)source_field => (mixed)dest_field
 * @param array $defaults indexed array of (string)dest_field => (mixed)value -- can be null
 * @return array indexed by column names for dest table
 */
function convertRow($row, $fields, $defaults) {
  // start by applying default values, these can be overwritten if fields contains same value
  $newrow = is_array($defaults)? $defaults : array();
  foreach($fields as $k=>$v) {
    // for multiple fields with same key, strips off the [n] from end
    $k = preg_replace("@\[[0-9]+\]$@", "", $k); 
    // run user functions as needed to modify values
    $key = is_array($v)? $v[1] : $v;
    $val = is_array($v)? call_user_func($v[0], $row[$k], $row, $k, $key) : $row[$k];
    if( !is_null($val) ) { 
      // create the new column in data row
      $newrow[$key] = $val;
    }
  }
  return $newrow;
}
 
function connectToDb($connection_info) {
  list($host, $user, $pass, $dbname) = $connection_info;
  $dbh = mysql_connect($host, $user, $pass);
 
  if (!$dbh) {
    printIt("Unable to connect to DB: " . mysql_error());
    exit;
  }
 
  if (!mysql_select_db($dbname, $dbh)) {
    printIt("Unable to select $dbname: " . mysql_error());
    exit;
  }
 
  return $dbh;
}
 
function convertTable($map) {
  global $max_rows;
 
  printIt('');
  printIt("-------------------------------------------------");
  if( !empty($map['dest_query']) ) {
    printIt("Running custom query: {$map['dest_query']}");
  }
  else {
    printIt("Migrating values to {$map['dest_table']}");
  }
  printIt("-------------------------------------------------");
  printIt('');
 
  // we call this each time because we can't just store a separate connection for the from instance
  // and to instance... chances are they point to the same server, so php/mysql will re-use the connection
  // and just switch the instance being operated on... this will cause our queries to go on the fritz
  // the upside is that it doesn't have to reconnect since it's reused, so there's no big cost to this approach
  $dbout = connectToDb( $map['connection_info']['source'] );
 
  // select the old data
  $result = mysql_query($map['source_query'], $dbout);
  if (!$result) {
    printIt("Unable to load source data ({$map['source_query']}): " . mysql_error());
    exit;
  }
 
  if (mysql_num_rows($result) == 0) {
    printIt("No rows found, that's weird so I'm exiting");
    exit;
  }
 
  // here again, we call this right before use, because we're going to switch instances, but
  // it's probably to the same mysql server, so connection will get reused
  $dbin = connectToDb( $map['connection_info']['dest'] );
 
  // While a row of data exists, put that row in $row as an associative array
  $i=0;
  $j=0;
  while ($row = mysql_fetch_assoc($result)) {
    $vals = convertRow($row, $map['fields'], $map['defaults']);
    if( !empty($map['dest_query']) ) {
      customQuery($dbin, $map['dest_query'], $vals) || $j++;
    }
    else {
      addRow($dbin, $map['dest_table'], $vals) || $j++;
    }
    $i++;
    if( $max_rows && $i > $max_rows ) { break; }
  }
 
  // recover query memory
  mysql_free_result($result);
 
  // show the user what we did
  printIt("Converted ".($i-$j)." rows");
  if( $j ) { printIt("!!!! $j errors !!!!!!"); }
}
 
// actually run the conversions
foreach($tablemap as $t) {
  convertTable($t);
}
 
printIt("Finished without blowing up the planet");
 
?>