Software: Apache/2.4.41 (Ubuntu). PHP/8.0.30 

uname -a: Linux apirnd 5.4.0-204-generic #224-Ubuntu SMP Thu Dec 5 13:38:28 UTC 2024 x86_64 

uid=33(www-data) gid=33(www-data) groups=33(www-data) 

Safe-mode: OFF (not secure)

/usr/local/lib/node_modules/strapi/node_modules/chardet/encoding/   drwxr-xr-x
Free 13.21 GB of 57.97 GB (22.79%)
                            Encoder    Tools    Proc.    FTP brute    Sec.    SQL    PHP-code    Update    Self remove    Logout    

Viewing file:     utf8.js (2.08 KB)      -rw-r--r--

var Match = require ('../match');

/**
 * Charset recognizer for UTF-8
 */
module.exports = function() {
  this.name = function() {
    return 'UTF-8';
  };
  this.match = function(det) {

    var hasBOM = false,
      numValid = 0,
      numInvalid = 0,
      input = det.fRawInput,
      trailBytes = 0,
      confidence;

    if (det.fRawLength >= 3 &&
      (input[0] & 0xff) == 0xef && (input[1] & 0xff) == 0xbb && (input[2] & 0xff) == 0xbf) {
      hasBOM = true;
    }

    // Scan for multi-byte sequences
    for (var i = 0; i < det.fRawLength; i++) {
      var b = input[i];
      if ((b & 0x80) == 0)
        continue; // ASCII

      // Hi bit on char found.  Figure out how long the sequence should be
      if ((b & 0x0e0) == 0x0c0) {
        trailBytes = 1;
      } else if ((b & 0x0f0) == 0x0e0) {
        trailBytes = 2;
      } else if ((b & 0x0f8) == 0xf0) {
        trailBytes = 3;
      } else {
        numInvalid++;
        if (numInvalid > 5)
          break;
        trailBytes = 0;
      }

      // Verify that we've got the right number of trail bytes in the sequence
      for (;;) {
        i++;
        if (i >= det.fRawLength)
          break;

        if ((input[i] & 0xc0) != 0x080) {
          numInvalid++;
          break;
        }
        if (--trailBytes == 0) {
          numValid++;
          break;
        }
      }
    }

    // Cook up some sort of confidence score, based on presense of a BOM
    //    and the existence of valid and/or invalid multi-byte sequences.
    confidence = 0;
    if (hasBOM && numInvalid == 0)
      confidence = 100;
    else if (hasBOM && numValid > numInvalid * 10)
      confidence = 80;
    else if (numValid > 3 && numInvalid == 0)
      confidence = 100;
    else if (numValid > 0 && numInvalid == 0)
      confidence = 80;
    else if (numValid == 0 && numInvalid == 0)
      // Plain ASCII.
      confidence = 10;
    else if (numValid > numInvalid * 10)
      // Probably corruput utf-8 data.  Valid sequences aren't likely by chance.
      confidence = 25;
    else
      return null

    return new Match(det, this, confidence);
  };
};