2016-11-27 06:45:15 +00:00
|
|
|
<?php
|
|
|
|
|
|
2017-05-17 22:02:17 +00:00
|
|
|
use PhpOffice\PhpSpreadsheet\IOFactory;
|
|
|
|
|
use PhpOffice\PhpSpreadsheet\Reader\IReadFilter;
|
|
|
|
|
use PhpOffice\PhpSpreadsheet\Spreadsheet;
|
|
|
|
|
|
2017-03-24 13:09:32 +00:00
|
|
|
error_reporting(E_ALL);
|
|
|
|
|
set_time_limit(0);
|
|
|
|
|
|
|
|
|
|
date_default_timezone_set('Europe/London');
|
|
|
|
|
|
2016-11-27 06:45:15 +00:00
|
|
|
?>
|
|
|
|
|
<html>
|
|
|
|
|
<head>
|
|
|
|
|
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
|
|
|
|
|
|
2017-03-24 13:09:32 +00:00
|
|
|
<title>PhpSpreadsheet Reader Example #14</title>
|
2016-11-27 06:45:15 +00:00
|
|
|
|
|
|
|
|
</head>
|
|
|
|
|
<body>
|
|
|
|
|
|
2017-03-24 13:09:32 +00:00
|
|
|
<h1>PhpSpreadsheet Reader Example #14</h1>
|
2016-11-27 06:45:15 +00:00
|
|
|
<h2>Reading a Large CSV file in "Chunks" to split across multiple Worksheets</h2>
|
|
|
|
|
<?php
|
|
|
|
|
|
2017-03-24 13:09:32 +00:00
|
|
|
require_once __DIR__ . '/../../../src/Bootstrap.php';
|
2016-11-27 06:45:15 +00:00
|
|
|
|
2017-01-22 08:39:23 +00:00
|
|
|
$inputFileType = 'Csv';
|
2016-11-27 06:45:15 +00:00
|
|
|
$inputFileName = './sampleData/example2.csv';
|
|
|
|
|
|
2017-05-17 22:02:17 +00:00
|
|
|
/** Define a Read Filter class implementing IReadFilter */
|
|
|
|
|
class chunkReadFilter implements IReadFilter
|
2016-11-27 06:45:15 +00:00
|
|
|
{
|
|
|
|
|
private $_startRow = 0;
|
|
|
|
|
|
|
|
|
|
private $_endRow = 0;
|
|
|
|
|
|
2017-01-22 08:39:23 +00:00
|
|
|
/**
|
|
|
|
|
* Set the list of rows that we want to read.
|
|
|
|
|
*
|
|
|
|
|
* @param mixed $startRow
|
|
|
|
|
* @param mixed $chunkSize
|
|
|
|
|
*/
|
2016-11-27 06:45:15 +00:00
|
|
|
public function setRows($startRow, $chunkSize)
|
|
|
|
|
{
|
|
|
|
|
$this->_startRow = $startRow;
|
|
|
|
|
$this->_endRow = $startRow + $chunkSize;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
public function readCell($column, $row, $worksheetName = '')
|
|
|
|
|
{
|
|
|
|
|
// Only read the heading row, and the rows that are configured in $this->_startRow and $this->_endRow
|
|
|
|
|
if (($row == 1) || ($row >= $this->_startRow && $row < $this->_endRow)) {
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
echo 'Loading file ',pathinfo($inputFileName, PATHINFO_BASENAME),' using IOFactory with a defined reader type of ',$inputFileType,'<br />';
|
|
|
|
|
/* Create a new Reader of the type defined in $inputFileType **/
|
2017-05-17 22:02:17 +00:00
|
|
|
$reader = IOFactory::createReader($inputFileType);
|
2016-11-27 06:45:15 +00:00
|
|
|
|
|
|
|
|
echo '<hr />';
|
|
|
|
|
|
|
|
|
|
/* Define how many rows we want to read for each "chunk" **/
|
|
|
|
|
$chunkSize = 100;
|
|
|
|
|
/* Create a new Instance of our Read Filter **/
|
|
|
|
|
$chunkFilter = new chunkReadFilter();
|
|
|
|
|
|
|
|
|
|
/* Tell the Reader that we want to use the Read Filter that we've Instantiated **/
|
|
|
|
|
/* and that we want to store it in contiguous rows/columns **/
|
2016-12-03 13:32:54 +00:00
|
|
|
$reader->setReadFilter($chunkFilter)
|
2016-11-27 06:45:15 +00:00
|
|
|
->setContiguous(true);
|
|
|
|
|
|
2017-03-24 13:09:32 +00:00
|
|
|
/* Instantiate a new PhpSpreadsheet object manually **/
|
2017-05-17 22:02:17 +00:00
|
|
|
$spreadsheet = new Spreadsheet();
|
2016-11-27 06:45:15 +00:00
|
|
|
|
|
|
|
|
/* Set a sheet index **/
|
|
|
|
|
$sheet = 0;
|
|
|
|
|
/* Loop to read our worksheet in "chunk size" blocks **/
|
|
|
|
|
/** $startRow is set to 2 initially because we always read the headings in row #1 **/
|
|
|
|
|
for ($startRow = 2; $startRow <= 240; $startRow += $chunkSize) {
|
2017-01-05 03:14:44 +00:00
|
|
|
echo 'Loading WorkSheet #', ($sheet + 1), ' using configurable filter for headings row 1 and for rows ', $startRow, ' to ', ($startRow + $chunkSize - 1), '<br />';
|
2016-11-27 06:45:15 +00:00
|
|
|
/* Tell the Read Filter, the limits on which rows we want to read this iteration **/
|
|
|
|
|
$chunkFilter->setRows($startRow, $chunkSize);
|
|
|
|
|
|
|
|
|
|
/* Increment the worksheet index pointer for the Reader **/
|
2016-12-03 13:32:54 +00:00
|
|
|
$reader->setSheetIndex($sheet);
|
2017-03-24 13:09:32 +00:00
|
|
|
/* Load only the rows that match our filter into a new worksheet in the PhpSpreadsheet Object **/
|
2016-12-03 13:32:54 +00:00
|
|
|
$reader->loadIntoExisting($inputFileName, $spreadsheet);
|
2016-11-27 06:45:15 +00:00
|
|
|
/* Set the worksheet title (to reference the "sheet" of data that we've loaded) **/
|
|
|
|
|
/* and increment the sheet index as well **/
|
2016-11-27 15:51:44 +00:00
|
|
|
$spreadsheet->getActiveSheet()->setTitle('Country Data #' . (++$sheet));
|
2016-11-27 06:45:15 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
echo '<hr />';
|
|
|
|
|
|
2017-01-05 03:14:44 +00:00
|
|
|
echo $spreadsheet->getSheetCount(), ' worksheet', (($spreadsheet->getSheetCount() == 1) ? '' : 's'), ' loaded<br /><br />';
|
2016-11-27 15:51:44 +00:00
|
|
|
$loadedSheetNames = $spreadsheet->getSheetNames();
|
2016-11-27 06:45:15 +00:00
|
|
|
foreach ($loadedSheetNames as $sheetIndex => $loadedSheetName) {
|
2017-01-05 03:14:44 +00:00
|
|
|
echo '<b>Worksheet #', $sheetIndex, ' -> ', $loadedSheetName, '</b><br />';
|
2016-11-27 15:51:44 +00:00
|
|
|
$spreadsheet->setActiveSheetIndexByName($loadedSheetName);
|
|
|
|
|
$sheetData = $spreadsheet->getActiveSheet()->toArray(null, false, false, true);
|
2016-11-27 06:45:15 +00:00
|
|
|
var_dump($sheetData);
|
|
|
|
|
echo '<br />';
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
?>
|
|
|
|
|
<body>
|
2010-10-20 11:30:09 +00:00
|
|
|
</html>
|
