devtoolboxuk\soteria\voku\Resources\Utf8::isUtf8()

Complexity

Conditions	26
Paths	29

Size

Total Lines

133

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	702

Importance

Changes

0

<?php
    private function isUtf8($str)

This operation has 640 execution paths which exceeds the configured maximum of 200.

    {
        if (\is_array($str) === true) {
            foreach ($str as $v) {
                if ($this->isUtf8($v) === false) {
                    return false;
                }
            }

            return true;
        }

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

        if ($this->system->pcre_utf8_support() !== true) {

Blank line found at start of control structure

            // 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;

Avoid variables with short names like $ar. Configured minimum length is 3.

        }

        $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 ($this->ORD === null) {
            $this->ORD = $this->getData('ord');
        }

        $len = \strlen((string)$str);
        /** @noinspection ForeachInvariantsInspection */
        for ($i = 0; $i < $len; ++$i) {
            $in = $this->ORD[$str[$i]];

Avoid variables with short names like $in. Configured minimum length is 3.

            if ($mState === 0) {
                // When mState is zero we expect either a US-ASCII character or a
                // multi-octet sequence.
                if ((0x80 & $in) === 0) {
                    // US-ASCII, pass straight through.
                    $mBytes = 1;
                } elseif ((0xE0 & $in) === 0xC0) {
                    // First octet of 2 octet sequence.
                    $mUcs4 = $in;
                    $mUcs4 = ($mUcs4 & 0x1F) << 6;
                    $mState = 1;
                    $mBytes = 2;
                } elseif ((0xF0 & $in) === 0xE0) {
                    // First octet of 3 octet sequence.
                    $mUcs4 = $in;
                    $mUcs4 = ($mUcs4 & 0x0F) << 12;
                    $mState = 2;
                    $mBytes = 3;
                } elseif ((0xF8 & $in) === 0xF0) {
                    // First octet of 4 octet sequence.
                    $mUcs4 = $in;
                    $mUcs4 = ($mUcs4 & 0x07) << 18;
                    $mState = 3;
                    $mBytes = 4;
                } elseif ((0xFC & $in) === 0xF8) {
                    /* 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 ((0xFE & $in) === 0xFC) {
                    // First octet of 6 octet sequence, see comments for 5 octet sequence.
                    $mUcs4 = $in;
                    $mUcs4 = ($mUcs4 & 1) << 30;
                    $mState = 5;
                    $mBytes = 6;
                } else {

The method isUtf8 uses an else expression. Else is never necessary and you can simplify the code to work without else.

                    // Current octet is neither in the US-ASCII range nor a legal first
                    // octet of a multi-octet sequence.
                    return false;
                }
            } elseif ((0xC0 & $in) === 0x80) {

Blank line found at start of control structure

                // When mState is non-zero, we expect a continuation of the multi-octet
                // sequence

                // Legal continuation.
                $shift = ($mState - 1) * 6;
                $tmp = $in;
                $tmp = ($tmp & 0x0000003F) << $shift;
                $mUcs4 |= $tmp;
                // Prefix: End of the multi-octet sequence. mUcs4 now contains the final
                // Unicode code point to be output.
                if (--$mState === 0) {
                    // Check for illegal sequences and code points.
                    //
                    // From Unicode 3.1, non-shortest form is illegal
                    if (
                        ($mBytes === 2 && $mUcs4 < 0x0080)
                        ||
                        ($mBytes === 3 && $mUcs4 < 0x0800)
                        ||
                        ($mBytes === 4 && $mUcs4 < 0x10000)
                        ||
                        ($mBytes > 4)
                        ||
                        // 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 {

The method isUtf8 uses an else expression. Else is never necessary and you can simplify the code to work without else.

                // ((0xC0 & (*in) != 0x80) && (mState != 0))
                // Incomplete multi-octet sequence.
                return false;
            }
        }

        return true;
    }