/**
* @param $path string absolute path to file
* @param $closure \Closure
* @void
*/
public function parse($path, Closure $closure)
{
$config = new LexerConfig();
$config->setDelimiter($this->delimeter);
$config->setFromCharset($this->fromCharset);
$config->setToCharset($this->toCharset);
$lexer = new Lexer($config);
$interpreter = new Interpreter();
$interpreter->addObserver($closure);
$lexer->parse($path, $interpreter);
}
/**
* When import CSV file with data in Japanese (2 bytes character),
* data imported to database with error encoding
* @link https://github.com/goodby/csv/issues/5
*/
public function test_issue_5()
{
$csvFilename = CSVFiles::getIssue5CSV();
$csvContents = array();
$config = new LexerConfig();
$config->setToCharset('UTF-8')->setFromCharset('UTF-8');
$lexer = new Lexer($config);
$interpreter = new Interpreter();
$interpreter->addObserver(function (array $columns) use(&$csvContents) {
$csvContents[] = $columns;
});
$lexer->parse($csvFilename, $interpreter);
$this->assertSame(array(array("ID", "NAME", "MAKER"), array("1", "スティック型クリーナ", "*****@*****.**"), array("2", "bob", "*****@*****.**"), array("14", "スティック型クリーナ", "*****@*****.**"), array("16", "スティック型", "*****@*****.**")), $csvContents);
}
public function test_shift_jis_CSV()
{
$shiftJisCsv = CSVFiles::getShiftJisCsv();
$lines = array(array('あ', 'い', 'う', 'え', 'お'), array('日本語', '日本語', '日本語', '日本語', '日本語'), array('ぱ', 'ぴ', 'ぷ', 'ぺ', 'ぽ'), array('"quoted"', "a'quote'", 'a, b and c', '', ''));
$interpreter = $this->getMock('Goodby\\CSV\\Import\\Standard\\Interpreter', array('interpret'));
$interpreter->expects($this->at(0))->method('interpret')->with($lines[0]);
$interpreter->expects($this->at(1))->method('interpret')->with($lines[1]);
$interpreter->expects($this->at(2))->method('interpret')->with($lines[2]);
$interpreter->expects($this->at(3))->method('interpret')->with($lines[3]);
$config = new LexerConfig();
$config->setToCharset('UTF-8')->setFromCharset('SJIS-win');
$lexer = new Lexer($config);
$lexer->parse($shiftJisCsv, $interpreter);
}
public function testToCharset()
{
$config = new LexerConfig();
$this->assertSame(null, $config->getToCharset());
$this->assertSame('UTF-8', $config->setToCharset('UTF-8')->getToCharset());
}
/**
* CSV parser
*
* @param string $file Path of the file.
* @return array Returns the array from csv.
* @since 0.1.0
*/
public static function csv_parser($csv_file)
{
if (!is_file($csv_file)) {
return new WP_Error('error', 'The CSV file is not found.');
} elseif (!self::is_textfile($csv_file)) {
return new WP_Error('error', 'The file is not CSV.');
}
$csv = array();
/**
* Filter the CSV setting for the csv parser.
*
* @param array settings for the csv parser.
*/
$format = apply_filters('acsv_csv_format', array('from_charset' => 'UTF-8', 'to_charset' => 'UTF-8', 'delimiter' => ',', 'enclosure' => '"', 'escape' => '\\'));
$config = new LexerConfig();
$config->setFromCharset($format['from_charset']);
$config->setToCharset($format['to_charset']);
$config->setDelimiter($format['delimiter']);
$config->setEnclosure($format['enclosure']);
$config->setEscape($format['escape']);
$lexer = new Lexer($config);
$interpreter = new Interpreter();
$interpreter->unstrict();
$interpreter->addObserver(function (array $row) use(&$csv) {
$csv[] = $row;
});
$lexer->parse($csv_file, $interpreter);
return $csv;
}
