voku / portable-utf8

        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;

          $mUcs4 = ($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

          $mUcs4 = ($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.

           */