voku\helper\UTF8::is_utf8()

Complexity

Conditions	30
Paths	104

Size

Total Lines	146
Code Lines	80

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	66
CRAP Score	30.5202

Importance

Changes

0

<?php
  public static function is_utf8($str, bool $strict = false): bool
  {
    if (\is_array($str) === true) {
      foreach ($str as $k => $v) {
        if (false === self::is_utf8($v, $strict)) {
          return false;
        }
      }

      return true;
    }

    if ('' === $str) {
      return true;
    }

    if ($strict === true) {
      if (self::is_utf16($str) !== false) {
        return false;
      }

      if (self::is_utf32($str) !== false) {
        return false;
      }
    }

    if (self::pcre_utf8_support() !== true) {

      // If even just the first character can be matched, when the /u
      // modifier is used, then it's valid UTF-8. If the UTF-8 is somehow
      // invalid, nothing at all will match, even if the string contains
      // some valid sequences
      return (\preg_match('/^.{1}/us', $str, $ar) === 1);
    }

    $mState = 0; // cached expected number of octets after the current octet
    // until the beginning of the next UTF8 character sequence
    $mUcs4 = 0; // cached Unicode character
    $mBytes = 1; // cached expected number of octets in the current sequence

    if (!isset(self::$SUPPORT['already_checked_via_portable_utf8'])) {
      self::checkForSupport();
    }

    if (self::$ORD === null) {
      self::$ORD = self::getData('ord');

It seems like self::getData('ord') can also be of type false. However, the property $ORD is declared as type null|array. Maybe add an additional type check?

    }

    $len = self::strlen_in_byte((string)$str);
    /** @noinspection ForeachInvariantsInspection */
    for ($i = 0; $i < $len; $i++) {
      $in = self::$ORD[$str[$i]];
      if ($mState === 0) {
        // When mState is zero we expect either a US-ASCII character or a
        // multi-octet sequence.
        if (0 === (0x80 & $in)) {
          // US-ASCII, pass straight through.
          $mBytes = 1;
        } elseif (0xC0 === (0xE0 & $in)) {
          // First octet of 2 octet sequence.
          $mUcs4 = $in;
          $mUcs4 = ($mUcs4 & 0x1F) << 6;
          $mState = 1;
          $mBytes = 2;
        } elseif (0xE0 === (0xF0 & $in)) {
          // First octet of 3 octet sequence.
          $mUcs4 = $in;
          $mUcs4 = ($mUcs4 & 0x0F) << 12;
          $mState = 2;
          $mBytes = 3;
        } elseif (0xF0 === (0xF8 & $in)) {
          // First octet of 4 octet sequence.
          $mUcs4 = $in;
          $mUcs4 = ($mUcs4 & 0x07) << 18;
          $mState = 3;
          $mBytes = 4;
        } elseif (0xF8 === (0xFC & $in)) {
          /* First octet of 5 octet sequence.
          *
          * This is illegal because the encoded codepoint must be either
          * (a) not the shortest form or
          * (b) outside the Unicode range of 0-0x10FFFF.
          * Rather than trying to resynchronize, we will carry on until the end
          * of the sequence and let the later error handling code catch it.
          */
          $mUcs4 = $in;
          $mUcs4 = ($mUcs4 & 0x03) << 24;
          $mState = 4;
          $mBytes = 5;
        } elseif (0xFC === (0xFE & $in)) {
          // First octet of 6 octet sequence, see comments for 5 octet sequence.
          $mUcs4 = $in;
          $mUcs4 = ($mUcs4 & 1) << 30;
          $mState = 5;
          $mBytes = 6;
        } else {
          // Current octet is neither in the US-ASCII range nor a legal first
          // octet of a multi-octet sequence.
          return false;
        }
      } else {
        // When mState is non-zero, we expect a continuation of the multi-octet
        // sequence
        if (0x80 === (0xC0 & $in)) {
          // Legal continuation.
          $shift = ($mState - 1) * 6;
          $tmp = $in;
          $tmp = ($tmp & 0x0000003F) << $shift;
          $mUcs4 |= $tmp;
          // Prefix: End of the multi-octet sequence. mUcs4 now contains the final
          // Unicode code point to be output.
          if (0 === --$mState) {
            // Check for illegal sequences and code points.
            //
            // From Unicode 3.1, non-shortest form is illegal
            if (
                (2 === $mBytes && $mUcs4 < 0x0080)
                ||
                (3 === $mBytes && $mUcs4 < 0x0800)
                ||
                (4 === $mBytes && $mUcs4 < 0x10000)
                ||
                (4 < $mBytes)
                ||
                // From Unicode 3.2, surrogate characters are illegal.
                (($mUcs4 & 0xFFFFF800) === 0xD800)
                ||
                // Code points outside the Unicode range are illegal.
                ($mUcs4 > 0x10FFFF)
            ) {
              return false;
            }
            // initialize UTF8 cache
            $mState = 0;
            $mUcs4 = 0;
            $mBytes = 1;
          }
        } else {
          // ((0xC0 & (*in) != 0x80) && (mState != 0))
          // Incomplete multi-octet sequence.
          return false;
        }
      }
    }

    return true;
  }