function UTF8Utils::checkForIllegalCodepoints

Checks for Unicode code points that are not valid in a document.

Parameters

string $data A string to analyze:

Return value

array An array of (string) error messages produced by the scanning

2 calls to UTF8Utils::checkForIllegalCodepoints()

Scanner::__construct in vendor/masterminds/html5/src/HTML5/Parser/Scanner.php

Create a new Scanner.

StringInputStream::__construct in vendor/masterminds/html5/src/HTML5/Parser/StringInputStream.php

Create a new InputStream wrapper.

File

vendor/masterminds/html5/src/HTML5/Parser/UTF8Utils.php, line 135

Class

UTF8Utils

Namespace

Masterminds\HTML5\Parser

Code

public static function checkForIllegalCodepoints($data) {
    // Vestigal error handling.
    $errors = array();
    
    /*
     * All U+0000 null characters in the input must be replaced by U+FFFD REPLACEMENT CHARACTERs.
     * Any occurrences of such characters is a parse error.
     */
    for ($i = 0, $count = substr_count($data, "\x00"); $i < $count; ++$i) {
        $errors[] = 'null-character';
    }
    
    /*
     * Any occurrences of any characters in the ranges U+0001 to U+0008, U+000B, U+000E to U+001F, U+007F
     * to U+009F, U+D800 to U+DFFF , U+FDD0 to U+FDEF, and characters U+FFFE, U+FFFF, U+1FFFE, U+1FFFF,
     * U+2FFFE, U+2FFFF, U+3FFFE, U+3FFFF, U+4FFFE, U+4FFFF, U+5FFFE, U+5FFFF, U+6FFFE, U+6FFFF, U+7FFFE,
     * U+7FFFF, U+8FFFE, U+8FFFF, U+9FFFE, U+9FFFF, U+AFFFE, U+AFFFF, U+BFFFE, U+BFFFF, U+CFFFE, U+CFFFF,
     * U+DFFFE, U+DFFFF, U+EFFFE, U+EFFFF, U+FFFFE, U+FFFFF, U+10FFFE, and U+10FFFF are parse errors.
     * (These are all control characters or permanently undefined Unicode characters.)
     */
    // Check PCRE is loaded.
    $count = preg_match_all('/(?:
        [\\x01-\\x08\\x0B\\x0E-\\x1F\\x7F] # U+0001 to U+0008, U+000B,  U+000E to U+001F and U+007F
      |
        \\xC2[\\x80-\\x9F] # U+0080 to U+009F
      |
        \\xED(?:\\xA0[\\x80-\\xFF]|[\\xA1-\\xBE][\\x00-\\xFF]|\\xBF[\\x00-\\xBF]) # U+D800 to U+DFFFF
      |
        \\xEF\\xB7[\\x90-\\xAF] # U+FDD0 to U+FDEF
      |
        \\xEF\\xBF[\\xBE\\xBF] # U+FFFE and U+FFFF
      |
        [\\xF0-\\xF4][\\x8F-\\xBF]\\xBF[\\xBE\\xBF] # U+nFFFE and U+nFFFF (1 <= n <= 10_{16})
      )/x', $data, $matches);
    for ($i = 0; $i < $count; ++$i) {
        $errors[] = 'invalid-codepoint';
    }
    return $errors;
}