383 lines
12 KiB
PHP
383 lines
12 KiB
PHP
<?php
|
|
|
|
/**
|
|
* @file
|
|
* Contains CSV Parser.
|
|
*
|
|
* Functions in this file are independent of the Feeds specific implementation.
|
|
* Thanks to jpetso http://drupal.org/user/56020 for most of the code in this
|
|
* file.
|
|
*/
|
|
|
|
/**
|
|
* Text lines from file iterator.
|
|
*/
|
|
class ParserCSVIterator implements Iterator {
|
|
private $handle;
|
|
private $currentLine;
|
|
private $currentPos;
|
|
|
|
public function __construct($filepath) {
|
|
$this->handle = fopen($filepath, 'r');
|
|
$this->currentLine = NULL;
|
|
$this->currentPos = NULL;
|
|
}
|
|
|
|
function __destruct() {
|
|
if ($this->handle) {
|
|
fclose($this->handle);
|
|
}
|
|
}
|
|
|
|
public function rewind($pos = 0) {
|
|
if ($this->handle) {
|
|
fseek($this->handle, $pos);
|
|
$this->next();
|
|
}
|
|
}
|
|
|
|
public function next() {
|
|
if ($this->handle) {
|
|
$this->currentLine = feof($this->handle) ? NULL : fgets($this->handle);
|
|
$this->currentPos = ftell($this->handle);
|
|
return $this->currentLine;
|
|
}
|
|
}
|
|
|
|
public function valid() {
|
|
return isset($this->currentLine);
|
|
}
|
|
|
|
public function current() {
|
|
return $this->currentLine;
|
|
}
|
|
|
|
public function currentPos() {
|
|
return $this->currentPos;
|
|
}
|
|
|
|
public function key() {
|
|
return 'line';
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Functionality to parse CSV files into a two dimensional array.
|
|
*/
|
|
class ParserCSV {
|
|
private $delimiter;
|
|
private $fromEncoding;
|
|
private $toEncoding;
|
|
private $skipFirstLine;
|
|
private $columnNames;
|
|
private $timeout;
|
|
private $timeoutReached;
|
|
private $startByte;
|
|
private $lineLimit;
|
|
private $lastLinePos;
|
|
private $useMbString;
|
|
|
|
public function __construct() {
|
|
$this->delimiter = ',';
|
|
$this->fromEncoding = 'UTF-8';
|
|
$this->toEncoding = 'UTF-8';
|
|
$this->skipFirstLine = FALSE;
|
|
$this->columnNames = FALSE;
|
|
$this->timeout = FALSE;
|
|
$this->timeoutReached = FALSE;
|
|
$this->startByte = 0;
|
|
$this->lineLimit = 0;
|
|
$this->lastLinePos = 0;
|
|
ini_set('auto_detect_line_endings', TRUE);
|
|
if (extension_loaded('mbstring') && variable_get('feeds_use_mbstring', TRUE)) {
|
|
$this->useMbString = TRUE;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Set the column delimiter string.
|
|
* By default, the comma (',') is used as delimiter.
|
|
*/
|
|
public function setDelimiter($delimiter) {
|
|
$this->delimiter = $delimiter;
|
|
}
|
|
|
|
/**
|
|
* Sets the source file encoding.
|
|
*
|
|
* By default, the encoding is UTF-8.
|
|
*
|
|
* @param string $encoding
|
|
* The encoding to set.
|
|
*/
|
|
public function setEncoding($encoding) {
|
|
$this->fromEncoding = $encoding;
|
|
}
|
|
|
|
/**
|
|
* Set this to TRUE if the parser should skip the first line of the CSV text,
|
|
* which might be desired if the first line contains the column names.
|
|
* By default, this is set to FALSE and the first line is not skipped.
|
|
*/
|
|
public function setSkipFirstLine($skipFirstLine) {
|
|
$this->skipFirstLine = $skipFirstLine;
|
|
}
|
|
|
|
/**
|
|
* Specify an array of column names if you know them in advance, or FALSE
|
|
* (which is the default) to unset any prior column names. If no column names
|
|
* are set, the parser will put each row into a simple numerically indexed
|
|
* array. If column names are given, the parser will create arrays with
|
|
* these column names as array keys instead.
|
|
*/
|
|
public function setColumnNames($columnNames) {
|
|
$this->columnNames = $columnNames;
|
|
}
|
|
|
|
/**
|
|
* Define the time (in milliseconds) after which the parser stops parsing,
|
|
* even if it has not yet finished processing the CSV data. If the timeout
|
|
* has been reached before parsing is done, the parse() method will return
|
|
* an incomplete list of rows - a single row will never be cut off in the
|
|
* middle, though. By default, no timeout (@p $timeout == FALSE) is defined.
|
|
*
|
|
* You can check if the timeout has been reached by calling the
|
|
* timeoutReached() method after parse() has been called.
|
|
*/
|
|
public function setTimeout($timeout) {
|
|
$this->timeout = $timeout;
|
|
}
|
|
|
|
/**
|
|
* After calling the parse() method, determine if the timeout (set by the
|
|
* setTimeout() method) has been reached.
|
|
*
|
|
* @deprecated Use lastLinePos() instead to determine whether a file has
|
|
* finished parsing.
|
|
*/
|
|
public function timeoutReached() {
|
|
return $this->timeoutReached;
|
|
}
|
|
|
|
/**
|
|
* Define the number of lines to parse in one parsing operation.
|
|
*
|
|
* By default, all lines of a file are being parsed.
|
|
*/
|
|
public function setLineLimit($lines) {
|
|
$this->lineLimit = $lines;
|
|
}
|
|
|
|
/**
|
|
* Get the byte number where the parser left off after last parse() call.
|
|
*
|
|
* @return
|
|
* 0 if all lines or no line has been parsed, the byte position of where a
|
|
* timeout or the line limit has been reached otherwise. This position can be
|
|
* used to set the start byte for the next iteration after parse() has
|
|
* reached the timeout set with setTimeout() or the line limit set with
|
|
* setLineLimit().
|
|
*
|
|
* @see ParserCSV::setStartByte()
|
|
*/
|
|
public function lastLinePos() {
|
|
return $this->lastLinePos;
|
|
}
|
|
|
|
/**
|
|
* Set the byte where file should be started to read.
|
|
*
|
|
* Useful when parsing a file in batches.
|
|
*/
|
|
public function setStartByte($start) {
|
|
return $this->startByte = $start;
|
|
}
|
|
|
|
/**
|
|
* Parse CSV files into a two dimensional array.
|
|
*
|
|
* @param Iterator $lineIterator
|
|
* An Iterator object that yields line strings, e.g. ParserCSVIterator.
|
|
* @param $start
|
|
* The byte number from where to start parsing the file.
|
|
* @param $lines
|
|
* The number of lines to parse, 0 for all lines.
|
|
* @return
|
|
* Two dimensional array that contains the data in the CSV file.
|
|
*/
|
|
public function parse(Iterator $lineIterator) {
|
|
$skipLine = $this->skipFirstLine;
|
|
$rows = array();
|
|
|
|
$this->timeoutReached = FALSE;
|
|
$this->lastLinePos = 0;
|
|
$maxTime = empty($this->timeout) ? FALSE : (microtime() + $this->timeout);
|
|
$linesParsed = 0;
|
|
|
|
for ($lineIterator->rewind($this->startByte); $lineIterator->valid(); $lineIterator->next()) {
|
|
|
|
// Make really sure we've got lines without trailing newlines.
|
|
$line = trim($this->fixEncoding($lineIterator->current()), "\r\n");
|
|
|
|
// Skip empty lines.
|
|
if (empty($line)) {
|
|
continue;
|
|
}
|
|
// If the first line contains column names, skip it.
|
|
if ($skipLine) {
|
|
$skipLine = FALSE;
|
|
continue;
|
|
}
|
|
|
|
// The actual parser. explode() is unfortunately not suitable because the
|
|
// delimiter might be located inside a quoted field, and that would break
|
|
// the field and/or require additional effort to re-join the fields.
|
|
$quoted = FALSE;
|
|
$currentIndex = 0;
|
|
$currentField = '';
|
|
$fields = array();
|
|
|
|
// We must use strlen() as we're parsing byte by byte using strpos(), so
|
|
// drupal_strlen() will not work properly.
|
|
while ($currentIndex <= strlen($line)) {
|
|
if ($quoted) {
|
|
$nextQuoteIndex = strpos($line, '"', $currentIndex);
|
|
|
|
if ($nextQuoteIndex === FALSE) {
|
|
// There's a line break before the quote is closed, so fetch the
|
|
// next line and start from there.
|
|
$currentField .= substr($line, $currentIndex);
|
|
$lineIterator->next();
|
|
|
|
if (!$lineIterator->valid()) {
|
|
// Whoa, an unclosed quote! Well whatever, let's just ignore
|
|
// that shortcoming and record it nevertheless.
|
|
$fields[] = $currentField;
|
|
break;
|
|
}
|
|
// Ok, so, on with fetching the next line, as mentioned above.
|
|
$currentField .= "\n";
|
|
$line = trim($this->fixEncoding($lineIterator->current()), "\r\n");
|
|
$currentIndex = 0;
|
|
continue;
|
|
}
|
|
|
|
// There's actually another quote in this line...
|
|
// find out whether it's escaped or not.
|
|
$currentField .= substr($line, $currentIndex, $nextQuoteIndex - $currentIndex);
|
|
|
|
if (isset($line[$nextQuoteIndex + 1]) && $line[$nextQuoteIndex + 1] === '"') {
|
|
// Escaped quote, add a single one to the field and proceed quoted.
|
|
$currentField .= '"';
|
|
$currentIndex = $nextQuoteIndex + 2;
|
|
}
|
|
else {
|
|
// End of the quoted section, close the quote and let the
|
|
// $quoted == FALSE block finalize the field.
|
|
$quoted = FALSE;
|
|
$currentIndex = $nextQuoteIndex + 1;
|
|
}
|
|
}
|
|
else { // $quoted == FALSE
|
|
// First, let's find out where the next character of interest is.
|
|
$nextQuoteIndex = strpos($line, '"', $currentIndex);
|
|
$nextDelimiterIndex = strpos($line, $this->delimiter, $currentIndex);
|
|
|
|
if ($nextQuoteIndex === FALSE) {
|
|
$nextIndex = $nextDelimiterIndex;
|
|
}
|
|
elseif ($nextDelimiterIndex === FALSE) {
|
|
$nextIndex = $nextQuoteIndex;
|
|
}
|
|
else {
|
|
$nextIndex = min($nextQuoteIndex, $nextDelimiterIndex);
|
|
}
|
|
|
|
if ($nextIndex === FALSE) {
|
|
// This line is done, add the rest of it as last field.
|
|
$currentField .= substr($line, $currentIndex);
|
|
$fields[] = $currentField;
|
|
break;
|
|
}
|
|
elseif ($line[$nextIndex] === $this->delimiter[0]) {
|
|
$length = ($nextIndex + strlen($this->delimiter) - 1) - $currentIndex;
|
|
$currentField .= substr($line, $currentIndex, $length);
|
|
$fields[] = $currentField;
|
|
$currentField = '';
|
|
$currentIndex += $length + 1;
|
|
// Continue with the next field.
|
|
}
|
|
else { // $line[$nextIndex] == '"'
|
|
$quoted = TRUE;
|
|
$currentField .= substr($line, $currentIndex, $nextIndex - $currentIndex);
|
|
$currentIndex = $nextIndex + 1;
|
|
// Continue this field in the $quoted == TRUE block.
|
|
}
|
|
}
|
|
}
|
|
// End of CSV parser. We've now got all the fields of the line as strings
|
|
// in the $fields array.
|
|
|
|
if (empty($this->columnNames)) {
|
|
$row = $fields;
|
|
}
|
|
else {
|
|
$row = array();
|
|
foreach ($this->columnNames as $columnName) {
|
|
$field = array_shift($fields);
|
|
$row[$columnName] = isset($field) ? $field : '';
|
|
}
|
|
}
|
|
$rows[] = $row;
|
|
|
|
// Quit parsing if timeout has been reached or requested lines have been
|
|
// reached.
|
|
if (!empty($maxTime) && microtime() > $maxTime) {
|
|
$this->timeoutReached = TRUE;
|
|
$this->lastLinePos = $lineIterator->currentPos();
|
|
break;
|
|
}
|
|
$linesParsed++;
|
|
if ($this->lineLimit && $linesParsed >= $this->lineLimit) {
|
|
$this->lastLinePos = $lineIterator->currentPos();
|
|
break;
|
|
}
|
|
}
|
|
return $rows;
|
|
}
|
|
|
|
/**
|
|
* Converts encoding of input data.
|
|
*
|
|
* @param string $data
|
|
* A chunk of data.
|
|
*
|
|
* @return string
|
|
* The encoded data.
|
|
*
|
|
* @throws ParserCSVEncodingException
|
|
* Thrown when a given encoding does not match.
|
|
*/
|
|
public function fixEncoding($data) {
|
|
if ($this->useMbString) {
|
|
if (mb_check_encoding($data, $this->fromEncoding)) {
|
|
if ($this->toEncoding != $this->fromEncoding) {
|
|
// Convert encoding. The conversion is to UTF-8 by default to prevent
|
|
// SQL errors.
|
|
$data = mb_convert_encoding($data, $this->toEncoding, $this->fromEncoding);
|
|
}
|
|
}
|
|
else {
|
|
throw new ParserCSVEncodingException(t('Source file is not in %encoding encoding.', array('%encoding' => $this->fromEncoding)));
|
|
}
|
|
}
|
|
|
|
return $data;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Exception thrown when an encoding error occurs during parsing.
|
|
*/
|
|
class ParserCSVEncodingException extends Exception {}
|