guess the encoding from buffer
Este script no debería instalarse directamente. Es una biblioteca que utilizan otros scripts mediante la meta-directiva de inclusión // @require https://update.greasyfork.org/scripts/462180/1163789/bufferEncoding.js
// ==UserScript==
// @name bufferEncoding
// @namespace http://tampermonkey.net/
// @version 0.1
// @description guess the encoding from buffer
// @author You
// @include *
// ==/UserScript==
(function(f){if(typeof exports==="object"&&typeof module!=="undefined"){module.exports=f()}else if(typeof define==="function"&&define.amd){define([],f)}else{var g;if(typeof window!=="undefined"){g=window}else if(typeof global!=="undefined"){g=global}else if(typeof self!=="undefined"){g=self}else{g=this}g.languageEncoding = f()}})(function(){var define,module,exports;return (function(){function r(e,n,t){function o(i,f){if(!n[i]){if(!e[i]){var c="function"==typeof require&&require;if(!f&&c)return c(i,!0);if(u)return u(i,!0);var a=new Error("Cannot find module '"+i+"'");throw a.code="MODULE_NOT_FOUND",a}var p=n[i]={exports:{}};e[i][0].call(p.exports,function(r){var n=e[i][1][r];return o(n||r)},p,p.exports,r,e,n,t)}return n[i].exports}for(var u="function"==typeof require&&require,i=0;i<t.length;i++)o(t[i]);return o}return r})()({1:[function(require,module,exports){
const byteOrderMarks = require("../config/byteOrderMarkObject.js");
module.exports = (uInt8Start) => {
for (const element of byteOrderMarks) {
if (element.regex.test(uInt8Start)) return element.encoding;
}
return null;
};
},{"../config/byteOrderMarkObject.js":6}],2:[function(require,module,exports){
module.exports = (content) => {
for (let b = 0; b < content.length; b++) {
// If ? is encountered it's definitely not utf8!
if (content[b] === "�") {
return false;
}
}
return true;
}
},{}],3:[function(require,module,exports){
const countAllMatches = require("./processing-content/countAllMatches.js");
const calculateConfidenceScore = require("./processing-content/calculateConfidenceScore.js");
const byteOrderMarkObject = require("../config/byteOrderMarkObject.js");
module.exports = (data, fileInfo) => {
data.languageArr = countAllMatches(data, fileInfo.encoding);
fileInfo.language = data.languageArr.reduce((acc, val) =>
acc.count > val.count ? acc : val
).name;
// "pos" gives us the position in the language array that has the most matches
data.pos = data.languageArr.findIndex(
(elem) => elem.name === fileInfo.language
);
// Determine the encoding
if (!fileInfo.encoding) {
fileInfo.encoding = data.languageArr[data.pos].encoding;
}
const calculations = calculateConfidenceScore(data, fileInfo);
if (fileInfo.confidence.encoding) {
fileInfo.confidence.language = calculations;
} else {
fileInfo.confidence.encoding = calculations;
fileInfo.confidence.language = calculations;
}
// Edge case, when no matches were found
if (!data.languageArr[data.pos].count) {
fileInfo.language = null;
fileInfo.confidence.language = null;
if (!byteOrderMarkObject.some(obj => obj.encoding === fileInfo.encoding)) {
fileInfo.encoding = null;
fileInfo.confidence.encoding = null;
}
}
return fileInfo;
};
},{"../config/byteOrderMarkObject.js":6,"./processing-content/calculateConfidenceScore.js":4,"./processing-content/countAllMatches.js":5}],4:[function(require,module,exports){
module.exports = (data, fileInfo) => {
const charRegex = new RegExp(
/\d|\n|\s|\-|\.|\,|\:|\;|\?|\!|\<|\>|\[|\]|\{|\}|\&|\=|\|/,
"g"
);
const totalCharacters = data.content.replace(charRegex, "").length;
const langArr = data.languageArr;
const pos = data.pos;
const secondLanguage = langArr.reduce((acc, val) => {
if (acc.name === fileInfo.language) return val;
if (val.name === fileInfo.language) return acc;
return acc.count >= val.count ? acc : val;
});
const languageRatio =
langArr[pos].count / (secondLanguage.count + langArr[pos].count);
const characterWordRatio = langArr[pos].count / totalCharacters;
let lowerLimit = null;
let upperLimit = null;
const multiplier = 0.8;
if (fileInfo.encoding === "UTF-8" || fileInfo.encoding === "UTF-16LE") {
lowerLimit = langArr[pos].utfFrequency
? langArr[pos].utfFrequency.low * multiplier
: null;
upperLimit = langArr[pos].utfFrequency
? (langArr[pos].utfFrequency.low + langArr[pos].utfFrequency.high) / 2
: null;
} else {
lowerLimit = langArr[pos].isoFrequency
? langArr[pos].isoFrequency.low * multiplier
: null;
upperLimit = langArr[pos].isoFrequency
? (langArr[pos].isoFrequency.low + langArr[pos].isoFrequency.high) / 2
: null;
}
let confidenceScore;
if (!lowerLimit || !upperLimit) {
confidenceScore = null;
} else if (characterWordRatio >= upperLimit) {
confidenceScore = 1;
} else if (characterWordRatio > lowerLimit) {
const range = upperLimit - lowerLimit;
const surplus = characterWordRatio - lowerLimit;
const confidenceRaisePercentage = surplus / range;
const confidenceRaise = (1 - languageRatio) * confidenceRaisePercentage;
confidenceScore = Number((languageRatio + confidenceRaise).toFixed(2));
} else {
confidenceScore = Number(
(languageRatio * (characterWordRatio / lowerLimit)).toFixed(2)
);
}
return confidenceScore;
};
},{}],5:[function(require,module,exports){
const languageArr = require("../../config/languageObject.js");
module.exports = (data, encoding) => {
const newLanguageArr = [];
// Cloning the language array and making sure that "count" has no reference to "languageArr"!
languageArr.forEach((obj) => {
const updatedLangObj = {};
Object.keys(obj).forEach((key) => {
if (key !== "count") {
updatedLangObj[key] = obj[key];
} else {
updatedLangObj.count = 0;
}
});
newLanguageArr.push(updatedLangObj);
});
const regex = encoding ? "utfRegex" : "isoRegex";
// Populating the count property of the language array
newLanguageArr.forEach((lang) => {
if (lang[regex]) {
const matches = data.content.match(lang[regex]);
if (matches) lang.count = matches.length;
}
});
return newLanguageArr;
};
},{"../../config/languageObject.js":7}],6:[function(require,module,exports){
module.exports = [
{
encoding: "UTF-EBCDIC",
regex: new RegExp("221 115 102 115"),
},
{
encoding: "GB-18030",
regex: new RegExp("132 49 149 51"),
},
{
encoding: "UTF-32LE",
regex: new RegExp("255 254 0 0"),
},
{
encoding: "UTF-32BE",
regex: new RegExp("0 0 254 255"),
},
{
encoding: "UTF-8",
regex: new RegExp("239 187 191"),
},
{
encoding: "UTF-7",
regex: new RegExp("43 47 118"),
},
{
encoding: "UTF-1",
regex: new RegExp("247 100 76"),
},
{
encoding: "SCSU",
regex: new RegExp("14 254 255"),
},
{
encoding: "BOCU-1",
regex: new RegExp("251 238 40"),
},
{
encoding: "UTF-16BE",
regex: new RegExp("254 255"),
},
{
encoding: "UTF-16LE",
regex: new RegExp("255 254"),
},
];
},{}],7:[function(require,module,exports){
const flag = "gi";
const sharedRegex = {
czech: new RegExp(/jsem|jsi/, flag),
hungarian: new RegExp(/\snem\s/, flag),
slovak: new RegExp(/poriadku|myslím|\ssme\s/, flag),
slovenian: new RegExp(/\skaj\s|lahko|zdaj/, flag),
albanian: new RegExp(/nuk/, flag),
english: new RegExp(/ the /, flag),
french: new RegExp(/c'est/, flag),
portuguese: new RegExp(/ não /, flag),
spanish: new RegExp(/estaba|\smuy\s|siempre|ahora/, flag),
german: new RegExp(/\sdas\s/, flag),
italian: new RegExp(/\sche\s/, flag),
danish: new RegExp(/hvad|noget/, flag),
norwegian: new RegExp(/deg/, flag),
swedish: new RegExp(/ jag /, flag),
dutch: new RegExp(/ het /, flag),
finnish: new RegExp(/hän/, flag),
"serbo-croatian": new RegExp(/ sam | kako /, flag),
estonian: new RegExp(/\sseda\s|\spole\s|midagi/, flag),
icelandic: new RegExp(/Það/, flag),
"malay-indonesian": new RegExp(/tidak/, flag),
turkish: new RegExp(/ bir /, flag),
lithuanian: new RegExp(/taip|\stai\s/, flag),
bengali: new RegExp(/এটা/, flag),
hindi: new RegExp(/हैं/, flag),
urdu: new RegExp(/ایک/, flag),
vietnamese: new RegExp(/ không /, flag)
};
const sharedFrequency = {
polish: { low: 0.004355, high: 0.005102 },
czech: { low: 0.004433, high: 0.007324 },
hungarian: { low: 0.004994, high: 0.005183 },
romanian: { low: 0.003319, high: 0.004190 },
slovak: { low: 0.001736, high: 0.002557 },
slovenian: { low: 0.004111, high: 0.004959 },
albanian: { low: 0.003773, high: 0.007313 },
ukrainian: { low: 0.002933, high: 0.005389 },
english: { low: 0.004679, high: 0.007580 },
french: { low: 0.003016, high: 0.004825 },
portuguese: { low: 0.003406, high: 0.005032 },
spanish: { low: 0.002348, high: 0.002881 },
german: { low: 0.004044, high: 0.004391 },
italian: { low: 0.003889, high: 0.005175 },
danish: { low: 0.003630, high: 0.004189 },
norwegian: { low: 0.002410, high: 0.003918 },
swedish: { low: 0.004916, high: 0.007221 },
dutch: { low: 0.003501, high: 0.004150 },
finnish: { low: 0.003308, high: 0.005135 },
"serbo-croatian": { low: 0.002568, high: 0.005182 },
estonian: { low: 0.002892, high: 0.003963 },
icelandic: { low: 0.004366, high: 0.004366 },
"malay-indonesian": { low: 0.002825, high: 0.003932 },
greek: { low: 0.003440, high: 0.004862 },
turkish: { low: 0.002915, high: 0.004588 },
hebrew: { low: 0.003663, high: 0.004666 },
lithuanian: { low: 0.003277, high: 0.003768 },
bengali: { low: 0.003155, high: 0.005236 },
hindi: { low: 0.004159, high: 0.006478 },
urdu: { low: 0.004118, high: 0.005851 },
vietnamese: { low: 0.003387, high: 0.005191 }
};
module.exports = [
{
name: "polish",
count: 0,
utfRegex: new RegExp(/się/, flag),
isoRegex: new RegExp(/siê/, flag),
encoding: "CP1250",
utfFrequency: sharedFrequency.polish,
isoFrequency: sharedFrequency.polish
},
{
name: "czech",
count: 0,
utfRegex: sharedRegex.czech,
isoRegex: sharedRegex.czech,
encoding: "CP1250",
utfFrequency: sharedFrequency.czech,
isoFrequency: sharedFrequency.czech
},
{
name: "hungarian",
count: 0,
utfRegex: sharedRegex.hungarian,
isoRegex: sharedRegex.hungarian,
encoding: "CP1250",
utfFrequency: sharedFrequency.hungarian,
isoFrequency: sharedFrequency.hungarian
},
{
name: "romanian",
count: 0,
utfRegex: new RegExp(/sunt|eşti/, flag),
isoRegex: new RegExp(/sunt|eºti/, flag),
encoding: "CP1250",
utfFrequency: sharedFrequency.romanian,
isoFrequency: sharedFrequency.romanian
},
{
name: "slovak",
count: 0,
utfRegex: sharedRegex.slovak,
isoRegex: sharedRegex.slovak,
encoding: "CP1250",
utfFrequency: sharedFrequency.slovak,
isoFrequency: sharedFrequency.slovak
},
{
name: "slovenian",
count: 0,
utfRegex: sharedRegex.slovenian,
isoRegex: sharedRegex.slovenian,
encoding: "CP1250",
utfFrequency: sharedFrequency.slovenian,
isoFrequency: sharedFrequency.slovenian
},
{
name: "albanian",
count: 0,
utfRegex: sharedRegex.albanian,
isoRegex: sharedRegex.albanian,
encoding: "CP1250",
utfFrequency: sharedFrequency.albanian,
isoFrequency: sharedFrequency.albanian
},
{
name: "russian",
count: 0,
utfRegex: new RegExp(/что/, flag),
isoRegex: new RegExp(/÷òî/, flag),
encoding: "CP1251",
utfFrequency: { low: 0.004965, high: 0.005341 },
isoFrequency: { low: 0.003884, high: 0.003986 }
},
{
name: "ukrainian",
count: 0,
utfRegex: new RegExp(/він|але/, flag),
isoRegex: new RegExp(/â³í|àëå/, flag),
encoding: "CP1251",
utfFrequency: sharedFrequency.ukrainian,
isoFrequency: sharedFrequency.ukrainian
},
{
name: "bulgarian",
count: 0,
utfRegex: new RegExp(/това|какво/, flag),
isoRegex: new RegExp(/òîâà|äîáðå|êaêâo/, flag),
encoding: "CP1251",
utfFrequency: { low: 0.005225, high: 0.005628 },
isoFrequency: { low: 0.002767, high: 0.004951 }
},
{
name: "english",
count: 0,
utfRegex: sharedRegex.english,
isoRegex: sharedRegex.english,
encoding: "CP1252",
utfFrequency: sharedFrequency.english,
isoFrequency: sharedFrequency.english
},
{
name: "french",
count: 0,
utfRegex: sharedRegex.french,
isoRegex: sharedRegex.french,
encoding: "CP1252",
utfFrequency: sharedFrequency.french,
isoFrequency: sharedFrequency.french
},
{
name: "portuguese",
count: 0,
utfRegex: sharedRegex.portuguese,
isoRegex: sharedRegex.portuguese,
encoding: "CP1252",
utfFrequency: sharedFrequency.portuguese,
isoFrequency: sharedFrequency.portuguese
},
{
name: "spanish",
count: 0,
utfRegex: sharedRegex.spanish,
isoRegex: sharedRegex.spanish,
encoding: "CP1252",
utfFrequency: sharedFrequency.spanish,
isoFrequency: sharedFrequency.spanish
},
{
name: "german",
count: 0,
utfRegex: sharedRegex.german,
isoRegex: sharedRegex.german,
encoding: "CP1252",
utfFrequency: sharedFrequency.german,
isoFrequency: sharedFrequency.german
},
{
name: "italian",
count: 0,
utfRegex: sharedRegex.italian,
isoRegex: sharedRegex.italian,
encoding: "CP1252",
utfFrequency: sharedFrequency.italian,
isoFrequency: sharedFrequency.italian
},
{
name: "danish",
count: 0,
utfRegex: sharedRegex.danish,
isoRegex: sharedRegex.danish,
encoding: "CP1252",
utfFrequency: sharedFrequency.danish,
isoFrequency: sharedFrequency.danish
},
{
name: "norwegian",
count: 0,
utfRegex: sharedRegex.norwegian,
isoRegex: sharedRegex.norwegian,
encoding: "CP1252",
utfFrequency: sharedFrequency.norwegian,
isoFrequency: sharedFrequency.norwegian
},
{
name: "swedish",
count: 0,
utfRegex: sharedRegex.swedish,
isoRegex: sharedRegex.swedish,
encoding: "CP1252",
utfFrequency: sharedFrequency.swedish,
isoFrequency: sharedFrequency.swedish
},
{
name: "dutch",
count: 0,
utfRegex: sharedRegex.dutch,
isoRegex: sharedRegex.dutch,
encoding: "CP1252",
utfFrequency: sharedFrequency.dutch,
isoFrequency: sharedFrequency.dutch
},
{
name: "finnish",
count: 0,
utfRegex: sharedRegex.finnish,
isoRegex: sharedRegex.finnish,
encoding: "CP1252",
utfFrequency: sharedFrequency.finnish,
isoFrequency: sharedFrequency.finnish
},
{
name: "serbo-croatian",
count: 0,
utfRegex: sharedRegex["serbo-croatian"],
isoRegex: sharedRegex["serbo-croatian"],
encoding: "CP1252",
utfFrequency: sharedFrequency["serbo-croatian"],
isoFrequency: sharedFrequency["serbo-croatian"]
},
{
name: "estonian",
count: 0,
utfRegex: sharedRegex.estonian,
isoRegex: sharedRegex.estonian,
encoding: "CP1252",
utfFrequency: sharedFrequency.estonian,
isoFrequency: sharedFrequency.estonian
},
{
name: "icelandic",
count: 0,
utfRegex: sharedRegex.icelandic,
isoRegex: sharedRegex.icelandic,
encoding: "CP1252",
utfFrequency: sharedFrequency.icelandic,
isoFrequency: sharedFrequency.icelandic
},
{
name: "malay-indonesian",
count: 0,
utfRegex: sharedRegex["malay-indonesian"],
isoRegex: sharedRegex["malay-indonesian"],
encoding: "CP1252",
utfFrequency: sharedFrequency["malay-indonesian"],
isoFrequency: sharedFrequency["malay-indonesian"]
},
{
name: "greek",
count: 0,
utfRegex: new RegExp(/είναι/, flag),
isoRegex: new RegExp(/åßíáé/, flag),
encoding: "CP1253",
utfFrequency: sharedFrequency.greek,
isoFrequency: sharedFrequency.greek
},
{
name: "turkish",
count: 0,
utfRegex: sharedRegex.turkish,
isoRegex: sharedRegex.turkish,
encoding: "CP1254",
utfFrequency: sharedFrequency.turkish,
isoFrequency: sharedFrequency.turkish
},
{
name: "hebrew",
count: 0,
utfRegex: new RegExp(/אתה/, flag),
isoRegex: new RegExp(/àúä/, flag),
encoding: "CP1255",
utfFrequency: sharedFrequency.hebrew,
isoFrequency: sharedFrequency.hebrew
},
{
name: "arabic",
count: 0,
utfRegex: new RegExp(/هذا/, flag),
isoRegex: new RegExp(/åðç/, flag),
encoding: "CP1256",
utfFrequency: { low: 0.003522, high: 0.004348 },
isoFrequency: { low: 0.003773, high: 0.005559 }
},
{
name: "farsi-persian",
count: 0,
utfRegex: new RegExp(/اون/, flag),
isoRegex: new RegExp(/çíä/, flag),
encoding: "CP1256",
utfFrequency: { low: 0.002761, high: 0.004856 },
isoFrequency: { low: 0.003010, high: 0.006646 }
},
{
name: "lithuanian",
count: 0,
utfRegex: sharedRegex.lithuanian,
isoRegex: sharedRegex.lithuanian,
encoding: "CP1257",
utfFrequency: sharedFrequency.lithuanian,
isoFrequency: sharedFrequency.lithuanian
},
{
name: "chinese-simplified",
count: 0,
utfRegex: new RegExp(/么/, flag),
isoRegex: new RegExp(/´ó|¶¯|Å®/, flag),
encoding: "GB18030",
utfFrequency: { low: 0.009567, high: 0.011502 },
isoFrequency: { low: 0.003137, high: 0.005009 }
},
{
name: "chinese-traditional",
count: 0,
utfRegex: new RegExp(/們/, flag),
isoRegex: new RegExp(/¦b/, flag),
encoding: "BIG5",
utfFrequency: { low: 0.012484, high: 0.014964 },
isoFrequency: { low: 0.005063, high: 0.005822 }
},
{
name: "japanese",
count: 0,
utfRegex: new RegExp(/ど/, flag),
isoRegex: new RegExp(/‚»|ÁÄ/, flag),
encoding: "Shift-JIS",
utfFrequency: { low: 0.004257, high: 0.006585 },
isoFrequency: { low: 0.004286, high: 0.004653 }
},
{
name: "korean",
count: 0,
utfRegex: new RegExp(/도/, flag),
isoRegex: new RegExp(/àö¾î|å¾ß|¡¼/, flag),
encoding: "EUC-KR",
utfFrequency: { low: 0.010910, high: 0.013670 },
isoFrequency: { low: 0.004118, high: 0.004961 }
},
{
name: "thai",
count: 0,
utfRegex: new RegExp(/แฮร์รี่|พอตเตอร์/, flag),
isoRegex: new RegExp(/áîãìãõè|¾íµàµíãì/, flag),
encoding: "TIS-620",
utfFrequency: { low: 0.003194, high: 0.003468 },
isoFrequency: { low: 0.002091, high: 0.002303 }
},
// The following languages don't seem to have their own encoding
// Subtitle files in these languages seem to almost exclusively use UTF encoding.
{
name: "bengali",
count: 0,
utfRegex: sharedRegex.bengali,
isoRegex: sharedRegex.bengali,
utfFrequency: sharedFrequency.bengali,
isoFrequency: sharedFrequency.bengali
},
{
name: "hindi",
count: 0,
utfRegex: sharedRegex.hindi,
isoRegex: sharedRegex.hindi,
utfFrequency: sharedFrequency.hindi,
isoFrequency: sharedFrequency.hindi
},
{
name: "urdu",
count: 0,
utfRegex: sharedRegex.urdu,
isoRegex: sharedRegex.urdu,
utfFrequency: sharedFrequency.urdu,
isoFrequency: sharedFrequency.urdu
},
{
name: "vietnamese",
count: 0,
utfRegex: sharedRegex.vietnamese,
isoRegex: sharedRegex.vietnamese,
utfFrequency: sharedFrequency.vietnamese,
isoFrequency: sharedFrequency.vietnamese
},
];
},{}],8:[function(require,module,exports){
const checkUTF = require("./components/checkUTF.js");
const processContent = require("./components/processContent.js");
const checkByteOrderMark = require("./components/checkByteOrderMark.js");
module.exports = (buffer) => {
return new Promise((resolve, reject) => {
const bufferInfo = {
encoding: null,
language: null,
confidence: {
encoding: null,
language: null,
},
};
const data = {};
// Check the byte order mark!
const byteOrderMarkBuffer = new FileReader();
byteOrderMarkBuffer.onload = () => {
const uInt8String = new Uint8Array(byteOrderMarkBuffer.result).slice(0, 4).join(" ");
const byteOrderMark = checkByteOrderMark(uInt8String);
if (byteOrderMark) {
bufferInfo.encoding = byteOrderMark;
bufferInfo.confidence.encoding = 1;
const byteOrderMarkReader = new FileReader();
byteOrderMarkReader.onload = () => {
data.content = byteOrderMarkReader.result;
resolve(processContent(data, bufferInfo));
};
byteOrderMarkReader.onerror = (err) => {
reject(err);
};
byteOrderMarkReader.readAsArrayBuffer(buffer, bufferInfo.encoding);
} else {
// Read with UTF-8 first, then with ISO-8859-1
const utfReader = new FileReader();
utfReader.onload = () => {
const utfContent = utfReader.result;
const utf8 = checkUTF(utfContent);
if (utf8) {
bufferInfo.encoding = "UTF-8";
bufferInfo.confidence.encoding = 1;
}
if (utf8) {
data.content = utfContent;
resolve(processContent(data, bufferInfo));
} else {
const isoReader = new FileReader();
isoReader.onload = () => {
data.content = isoReader.result;
resolve(processContent(data, bufferInfo));
};
isoReader.readAsText(buffer, "ISO-8859-1");
}
};
utfReader.onerror = (err) => {
reject(err);
};
utfReader.readAsText(buffer, "UTF-8");
}
};
byteOrderMarkBuffer.onerror = (err) => {
reject(err);
};
byteOrderMarkBuffer.readAsArrayBuffer(buffer);
});
};
},{"./components/checkByteOrderMark.js":1,"./components/checkUTF.js":2,"./components/processContent.js":3}]},{},[8])(8)
});