1.7.2 - 1.7.4 [FIX] mit Umlauten in Kommentaren-/Suche - Comments-/Search

[bildergallery]

nach mehreren offenen treads habe ich selber versucht, in einer frischen 4images installation
kommentare mit umlauten zu erstellen.

----------------------------------------------------------------------------------------------------------------------

ich benutze als testversion / testsystem
PHP Version 5.2.2 und Mysql 5.0.41

4images 1.7.4

Quelltext im Browser:
<title>4images - Image Gallery Management System</title>
<meta http-equiv="content-type" content="text/html; charset=iso-8859-1" />
<link rel="stylesheet" href="./templates/default/style.css" />

----------------------------------------------------------------------------------------------------------------------

folgende fehlermeldung kommt (siehe bild vorher.gif):
Das Feld Überschrift muss ausgefüllt werden!
Das Feld Kommentar muss ausgefüllt werden!

wenn die umlaute durch ae ue oe ersetzt werden, funktioniert dies (siehe bilder nachher.gif)

liebe programmierer, meldet euch 
damit die sache entgültig gelöst wird


UPDATE 28.08.2007
LÖSUNG/BUGFIX

suche/search in global.php

Code: [Select]

function clean_array($array) {
  $search = array(
    // Remove any attribute starting with "on" or xmlns
    '#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iUu',
    // Remove javascript: and vbscript: protocol
    '#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu',
    '#([a-z]*)[\x00-\x20]*=([\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu',
    //<span style="width: expression(alert('Ping!'));"></span>
    // Only works in ie...
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*expression[\x00-\x20]*\([^>]*>#iU',
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*behaviour[\x00-\x20]*\([^>]*>#iU',
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iUu'
  );

  $replace = array(
    "$1>",
    '$1=$2nojavascript...',
    '$1=$2novbscript...',
    "$1>",
    "$1>",
    "$1>"
  );

  // Remove all control (i.e. with ASCII value lower than 0x20 (space),
  // except of 0x0A (line feed) and 0x09 (tabulator)
  $search2 =
      "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
  $replace2 = //str_repeat("\r", strlen($search2));
      "\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D";

  foreach ($array as $key => $val) {
    if (is_array($val)) {
      $val = clean_array($val);
    } else {
      $val = preg_replace($search, $replace, $val);

      $val = str_replace("\r\n", "\n", $val);
      $val = str_replace("\r",   "\n", $val);
      $val = strtr($val, $search2, $replace2);
      $val = str_replace("\r", '', $val);  // \r === \x0D

      do {
        $oldval = $val;
        $val = preg_replace('#</*(applet|meta|xml|blink|link|style|script|embed|object|iframe|frame|frameset|ilayer|layer|bgsound|title|base)[^>]*>#i', "", $val);
      } while ($oldval != $val);
    }

    $array[$key] = $val;
  }

  return $array;
}
ersetze/replace

Code: [Select]

function clean_string($string) {
  $canCheckUTF8Error = defined('PREG_BAD_UTF8_ERROR') && function_exists('preg_last_error');

  // Remove any attribute starting with "on" or xmlns
  $tmp = preg_replace('#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iUu',"$1>",$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iU',"$1>",$string);
  }
  $string = $tmp;

  // Remove javascript: and vbscript: protocol
  $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu','$1=$2nojavascript...',$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iU','$1=$2nojavascript...',$string);
  }
  $string = $tmp;
  $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu','$1=$2novbscript...',$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iU','$1=$2novbscript...',$string);
  }
  $string = $tmp;

  // <span style="width: expression(alert('Ping!'));"></span>
  // only works in ie...
  $string = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*expression[\x00-\x20]*\([^>]*>#iU',"$1>",$string);
  $string = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*behaviour[\x00-\x20]*\([^>]*>#iU',"$1>",$string);
  $tmp = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iUu',"$1>",$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iU',"$1>",$string);
  }
  $string = $tmp;

  // Remove namespaced elements (we do not need them...)
  $string = preg_replace('#</*\w+:\w[^>]*>#i',"",$string);

  // Remove all control (i.e. with ASCII value lower than 0x20 (space),
  // except of 0x0A (line feed) and 0x09 (tabulator)
  $search =
    "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
  $replace = //str_repeat("\r", strlen($search2));
    "\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D";

  $string = str_replace("\r\n", "\n", $string);
  $string = str_replace("\r",   "\n", $string);
  $string = strtr($string, $search, $replace);
  $string = str_replace("\r", '', $string);  // \r === \x0D

  // Remove really unwanted tags
  do {
    $oldstring = $string;
    $string = preg_replace('#</*(applet|meta|xml|blink|link|style|script|embed|object|iframe|frame|frameset|ilayer|layer|bgsound|title|base)[^>]*>#i',"",$string);
  } while ($oldstring != $string);

  return $string;
}

function clean_array($array) {
  foreach ($array as $key => $val) {
    $key = clean_string($key);

    if (is_array($val)) {
      $val = clean_array($val);
    } else {
      $val = clean_string($val);
    }

    $array[$key] = $val;
  }

  return $array;
}

[mawenzi]

... habe Jan und Kai nochmals auf dieses Problem hingewiesen ...

[Jan]

Das wurde schon vor ziemlich langer Zeit gefixt (ziemlich am Anfang der global.php).

Jan

[Jan]

Hi,

wir sind leider hier im Büro seit 1 Woche offline 
Ich werde mich sobald es geht darum kümmern..

Jan

[Nicky]

auf meinem server laufen...

PHP Version 4.3.11
und
MySQL 5.0.22 (datenbank als utf8_general_ci)

an 4images 1.7.4 wurde nichts verändert.

das ist das ergebniss
http://www.nicky.net/4test/details.php?image_id=1

[mawenzi]

@Nicky
... du bist ja ein Sprachgenie ... 
... ich denke aber es dreht sich vorrangig um PHP Version 5.x.x ...

[Nicky]

LOOOOOOOOOL..

ich sollte echt mal die postings komplett lesen.. hab ja nur "5"-er gelesen und dachte auf mysql 5...
damit war mein post überflüssig.

sorry leutz...

[Nicky]

wieder ich
guckst du... (kann am server zwischen PHP4 und PHP5 wechseln)

PHP Version 5.1.1
MySQL 5.0.22 (datenbank als utf8_general_ci)

http://www.nicky.net/4test/details.php?image_id=1
user: test
pass: test

[Jan]

Mit register_globals hat das nichts zu tun. 4images war noch nie auf register_globals on angewiesen. Auch die neuen Superglobals können nicht das Problem sein weil wie gesagt schon lange ein Workaround besteht. Ich werde mir das mal in Ruhe anschauen...

Jan

[Jan]

Hi,

ich hab leider momentan nicht viel Zeit, ich kann den Fehler bei mir nicht nachvollziehen. Hier klappt alles ohne Probleme mit den Umlauten. Hast Du ne URL zu einer Installation bei der es nicht funktioniert?

Gruß Jan

[mawenzi]

... wenn in dieser Demo-Installation zwar nicht alles so richtig funktioniert, z.b. das captcha image nicht, so funktionieren zumindest die Umlaute in den Kommentaren ...

[mawenzi]

... Ivan, genauer lesen ...
... die Kommentare funktionieren dort mit Umlauten ... !
... also ist diese Installation ein schlechtes Beispiel für deine Umlaut-Probleme ...

[Jan]

Ok, der "Fehler" liegt in der Funktion clean_array() in global.php. Ein Workaround ist, folgende Zeile

Code: [Select]

'#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iUu'
in

Code: [Select]

'#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iU'
zu ändern. Also das kleine u am Ende zu entfernen.

[Jan]

global.php

  das ist der Fix /  here the fix:

  Die komplette Funktion /  complete function

Code: [Select]

function clean_array($array) {
  $search = array(
    // Remove any attribute starting with "on" or xmlns
    '#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iUu',
    // Remove javascript: and vbscript: protocol
    '#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu',
    '#([a-z]*)[\x00-\x20]*=([\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu',
    //<span style="width: expression(alert('Ping!'));"></span>
    // Only works in ie...
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*expression[\x00-\x20]*\([^>]*>#iU',
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*behaviour[\x00-\x20]*\([^>]*>#iU',
    '#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iUu'
  );

  $replace = array(
    "$1>",
    '$1=$2nojavascript...',
    '$1=$2novbscript...',
    "$1>",
    "$1>",
    "$1>"
  );

  // Remove all control (i.e. with ASCII value lower than 0x20 (space),
  // except of 0x0A (line feed) and 0x09 (tabulator)
  $search2 =
      "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
  $replace2 = //str_repeat("\r", strlen($search2));
      "\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D";

  foreach ($array as $key => $val) {
    if (is_array($val)) {
      $val = clean_array($val);
    } else {
      $val = preg_replace($search, $replace, $val);

      $val = str_replace("\r\n", "\n", $val);
      $val = str_replace("\r",   "\n", $val);
      $val = strtr($val, $search2, $replace2);
      $val = str_replace("\r", '', $val);  // \r === \x0D

      do {
        $oldval = $val;
        $val = preg_replace('#</*(applet|meta|xml|blink|link|style|script|embed|object|iframe|frame|frameset|ilayer|layer|bgsound|title|base)[^>]*>#i', "", $val);
      } while ($oldval != $val);
    }

    $array[$key] = $val;
  }

  return $array;
}

  durch /  replace with

Code: [Select]

function clean_string($string) {
  $canCheckUTF8Error = defined('PREG_BAD_UTF8_ERROR') && function_exists('preg_last_error');

  // Remove any attribute starting with "on" or xmlns
  $tmp = preg_replace('#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iUu',"$1>",$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#(<[^>]+[\x00-\x20\"\'])(on|xmlns)[^>]*>#iU',"$1>",$string);
  }
  $string = $tmp;

  // Remove javascript: and vbscript: protocol
  $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu','$1=$2nojavascript...',$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iU','$1=$2nojavascript...',$string);
  }
  $string = $tmp;
  $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iUu','$1=$2novbscript...',$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iU','$1=$2novbscript...',$string);
  }
  $string = $tmp;

  // <span style="width: expression(alert('Ping!'));"></span>
  // only works in ie...
  $string = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*expression[\x00-\x20]*\([^>]*>#iU',"$1>",$string);
  $string = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*behaviour[\x00-\x20]*\([^>]*>#iU',"$1>",$string);
  $tmp = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iUu',"$1>",$string);
  if ($canCheckUTF8Error && (PREG_BAD_UTF8_ERROR == preg_last_error())) {
      $tmp = preg_replace('#(<[^>]+)style[\x00-\x20]*=[\x00-\x20]*([\`\'\"]*).*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*>#iU',"$1>",$string);
  }
  $string = $tmp;

  // Remove namespaced elements (we do not need them...)
  $string = preg_replace('#</*\w+:\w[^>]*>#i',"",$string);

  // Remove all control (i.e. with ASCII value lower than 0x20 (space),
  // except of 0x0A (line feed) and 0x09 (tabulator)
  $search =
    "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0B\x0C\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F";
  $replace = //str_repeat("\r", strlen($search2));
    "\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D\x0D";

  $string = str_replace("\r\n", "\n", $string);
  $string = str_replace("\r",   "\n", $string);
  $string = strtr($string, $search, $replace);
  $string = str_replace("\r", '', $string);  // \r === \x0D

  // Remove really unwanted tags
  do {
    $oldstring = $string;
    $string = preg_replace('#</*(applet|meta|xml|blink|link|style|script|embed|object|iframe|frame|frameset|ilayer|layer|bgsound|title|base)[^>]*>#i',"",$string);
  } while ($oldstring != $string);

  return $string;
}

function clean_array($array) {
  foreach ($array as $key => $val) {
    $key = clean_string($key);

    if (is_array($val)) {
      $val = clean_array($val);
    } else {
      $val = clean_string($val);
    }

    $array[$key] = $val;
  }

  return $array;
}
  ersetzen.

[Nicky]

dies ist aber schon offtopic

nee, scherz bei seite.. dieser fehler ist bekannt.