Split a file by a set number of lines
March 4, 2012
Leave a comment
I had large files that I had to split into smaller files,
all the examples I found ran out of memory when running.
I created this class which can split 100 MB files easily and quickly.
Let me know if you find it useful.
class SplitFile {
/*
* @var Full path or relative path to where the output file will be created
*/
private $_dest_path;
/*
* __construct
*/
public function __construct($dest_path = '.')
{
$this->_dest_path = $dest_path;
}
/*
* Split the input (text) file into smaller files by number of lines
*
* @param string $source_file File path of the source text file
* @param string $output_prefix File prefix for the output files
* @param int $split_count Number of lines per split file
*/
public function split($source_file, $output_prefix = '', $split_count = '500000')
{
// File is less then split count so return file
if($this->_getFileLineCount($source_file) <= $split_count) {
return $this->_dest_path . '/' . $source_file;
}
$fileExtension = pathinfo($source_file,PATHINFO_EXTENSION);
if($output_prefix == '') {
$output_prefix = basename($source_file,'.'.$fileExtension);
}
$fileExtension = pathinfo($source_file,PATHINFO_EXTENSION);
// Open the file for reading
$handle = fopen($source_file, "r");
$lineCount = 0;
$split = 1;
// Loop through the file until you reach the last line
while(!feof($handle)) {
if ($lineCount == 0) {
$outfile = $this->_dest_path . '/' . $output_prefix . '-' . $split . ".$fileExtension";
$outHandle = fopen($outfile,'w+');
}
fwrite($outHandle, fgets($handle));
if($lineCount < $split_count) {
// Increment the counter
$lineCount++;
} else {
$split++;
$lineCount = 0;
}
}
// Release the file for access
fclose($handle);
unlink($source_file);
}
/**
* Get the line count of a file
*
* @param string $file The file name
* @return int The number of lines in a file
*/
private function _getFileLineCount($file)
{
// Open the file for reading
$handle = fopen($file, "r");
$lineCount = 0;
// Loop through the file until you reach the last line
while (fgets($handle) !== false) {
// Increment the counter
$lineCount++;
}
// Release the file for access
fclose($handle);
return $lineCount;
}
}
Categories: PHP, Programming
