Ldes · February 5, 2019 13:35
diff --git a/fix-corrupt-serialized-data.php b/fix-corrupt-serialized-data.php
 <?php

 /*
 * Regex/code to fix corrupt serialized PHP data
 *
 * Following snippet will attempt to read & parse recursively damaged serialized string (blob data).
 * For example if you stored into database column string too long and it got cut off.
 * Numeric primitives and bool are guaranteed to be valid, strings may be cut off and/or array keys may be missing.
 * The routine may be useful e.g. if recovering significant (not all) part of data is sufficient solution to you.
 * Via: https://stackoverflow.com/a/38708463/1723496
 */


 class Unserializer {
    /**
     * Parse blob string tolerating corrupted strings & arrays
     * @param string $str Corrupted blob string
     * @return array|string|int|float|bool|null
     */
    public static function parseCorruptedBlob(&$str) {
        
        // array pattern:    a:236:{...;}
        // integer pattern:  i:123;
        // double pattern:   d:329.0001122;
        // boolean pattern:  b:1; or b:0;
        // string pattern:   s:14:"date_departure";
        // null pattern:     N;
        // not supported: object O:{...}, reference R:{...}

        // Notes:
        // - primitive types (bool, int, float) except for string are guaranteed uncorrupted
        // - arrays are tolerant to corrupted keys/values
        // - references & objects are not supported
        // - we use single byte string length calculation (strlen rather than mb_strlen) since source string is ISO-8859-2, not utf-8

        // Usage:
        // $unserialized = Unserializer::parseCorruptedBlob($serializedString);
        
        if (preg_match('/^a:(\d+):{/', $str, $match)) {
            list($pattern, $cntItems) = $match;
            $str = substr($str, strlen($pattern));
            $array = [];
            for($i=0; $i<$cntItems; ++$i) {
                $key = self::parseCorruptedBlob($str);
                if(trim($key)!=='') { // hmm, we wont allow null and "" as keys..
                    $array[$key] = self::parseCorruptedBlob($str);
                }
            }
            $str = ltrim($str, '}'); // closing array bracket
            return $array;
        } elseif (preg_match('/^s:(\d+):/', $str, $match)) {
            list($pattern, $length) = $match;
            $str = substr($str, strlen($pattern));
            $val = substr($str, 0, $length + 2); // include also surrounding double quotes
            $str = substr($str, strlen($val) + 1); // include also semicolon
            $val = trim($val, '"'); // remove surrounding double quotes
            if (preg_match('/^a:(\d+):{/', $val)) {
                // parse instantly another serialized array
                return (array) self::parseCorruptedBlob($val);
            } else {
                return (string) $val;
            }
        } elseif (preg_match('/^i:(\d+);/', $str, $match)) {
            list($pattern, $val) = $match;
            $str = substr($str, strlen($pattern));
            return (int) $val;
        } elseif (preg_match('/^d:([\d.]+);/', $str, $match)) {
            list($pattern, $val) = $match;
            $str = substr($str, strlen($pattern));
            return (float) $val;
        } elseif (preg_match('/^b:(0|1);/', $str, $match)) {
            list($pattern, $val) = $match;
            $str = substr($str, strlen($pattern));
            return (bool) $val;
        } elseif (preg_match('/^N;/', $str, $match)) {
            $str = substr($str, strlen('N;'));
            return null;
        }
    }
 }
	<?php

	/*
	* Regex/code to fix corrupt serialized PHP data
	*
	* Following snippet will attempt to read & parse recursively damaged serialized string (blob data).
	* For example if you stored into database column string too long and it got cut off.
	* Numeric primitives and bool are guaranteed to be valid, strings may be cut off and/or array keys may be missing.
	* The routine may be useful e.g. if recovering significant (not all) part of data is sufficient solution to you.
	* Via: https://stackoverflow.com/a/38708463/1723496
	*/


	class Unserializer {
	/**
	* Parse blob string tolerating corrupted strings & arrays
	* @param string $str Corrupted blob string
	* @return array\|string\|int\|float\|bool\|null
	*/
	public static function parseCorruptedBlob(&$str) {

	// array pattern: a:236:{...;}
	// integer pattern: i:123;
	// double pattern: d:329.0001122;
	// boolean pattern: b:1; or b:0;
	// string pattern: s:14:"date_departure";
	// null pattern: N;
	// not supported: object O:{...}, reference R:{...}

	// Notes:
	// - primitive types (bool, int, float) except for string are guaranteed uncorrupted
	// - arrays are tolerant to corrupted keys/values
	// - references & objects are not supported
	// - we use single byte string length calculation (strlen rather than mb_strlen) since source string is ISO-8859-2, not utf-8

	// Usage:
	// $unserialized = Unserializer::parseCorruptedBlob($serializedString);

	if (preg_match('/^a:(\d+):{/', $str, $match)) {
	list($pattern, $cntItems) = $match;
	$str = substr($str, strlen($pattern));
	$array = [];
	for($i=0; $i<$cntItems; ++$i) {
	$key = self::parseCorruptedBlob($str);
	if(trim($key)!=='') { // hmm, we wont allow null and "" as keys..
	$array[$key] = self::parseCorruptedBlob($str);
	}
	}
	$str = ltrim($str, '}'); // closing array bracket
	return $array;
	} elseif (preg_match('/^s:(\d+):/', $str, $match)) {
	list($pattern, $length) = $match;
	$str = substr($str, strlen($pattern));
	$val = substr($str, 0, $length + 2); // include also surrounding double quotes
	$str = substr($str, strlen($val) + 1); // include also semicolon
	$val = trim($val, '"'); // remove surrounding double quotes
	if (preg_match('/^a:(\d+):{/', $val)) {
	// parse instantly another serialized array
	return (array) self::parseCorruptedBlob($val);
	} else {
	return (string) $val;
	}
	} elseif (preg_match('/^i:(\d+);/', $str, $match)) {
	list($pattern, $val) = $match;
	$str = substr($str, strlen($pattern));
	return (int) $val;
	} elseif (preg_match('/^d:([\d.]+);/', $str, $match)) {
	list($pattern, $val) = $match;
	$str = substr($str, strlen($pattern));
	return (float) $val;
	} elseif (preg_match('/^b:(0\|1);/', $str, $match)) {
	list($pattern, $val) = $match;
	$str = substr($str, strlen($pattern));
	return (bool) $val;
	} elseif (preg_match('/^N;/', $str, $match)) {
	$str = substr($str, strlen('N;'));
	return null;
	}
	}
	}