Костыль для автоматической перекодировки имен-путей ANSI>UTF8 и доменов в punycode.
Code: Select all
// version: 2
// Добавил перекодировку национальных доменов в punycode при добавлении закачки.
//http://upload.wikimedia.org/wikipedia/ru/8/8c/Берите_пример_со_знатного_коноплевода_Александра_Хрипунова_(плакат).jpg
//http://кудяплики.рф/uploads/images/00/00/02/2010/12/02/dc265c.jpg
// "var punycode = new function Punycode() {" не работает: "Имя задано неоднозначно"!
//http://stackoverflow.com/questions/183485/can-anyone-recommend-a-good-free-javascript-for-punycode-to-unicode-conversion
//Javascript Punycode converter derived from example in RFC3492.
//This implementation is created by some@domain.name and released into public domain
var punycode = new function() {
// This object converts to and from puny-code used in IDN
//
// punycode.ToASCII ( domain )
//
// Returns a puny coded representation of "domain".
// It only converts the part of the domain name that
// has non ASCII characters. I.e. it dosent matter if
// you call it with a domain that already is in ASCII.
//
// punycode.ToUnicode (domain)
//
// Converts a puny-coded domain name to unicode.
// It only converts the puny-coded parts of the domain name.
// I.e. it dosent matter if you call it on a string
// that already has been converted to unicode.
//
//
this.utf16 = {
// The utf16-class is necessary to convert from javascripts internal character representation to unicode and back.
decode:function(input){
var output = [], i=0, len=input.length,value,extra;
while (i < len) {
value = input.charCodeAt(i++);
if ((value & 0xF800) === 0xD800) {
extra = input.charCodeAt(i++);
if ( ((value & 0xFC00) !== 0xD800) || ((extra & 0xFC00) !== 0xDC00) ) {
throw new RangeError("UTF-16(decode): Illegal UTF-16 sequence");
}
value = ((value & 0x3FF) << 10) + (extra & 0x3FF) + 0x10000;
}
output.push(value);
}
return output;
},
encode:function(input){
var output = [], i=0, len=input.length,value;
while (i < len) {
value = input[i++];
if ( (value & 0xF800) === 0xD800 ) {
throw new RangeError("UTF-16(encode): Illegal UTF-16 value");
}
if (value > 0xFFFF) {
value -= 0x10000;
output.push(String.fromCharCode(((value >>>10) & 0x3FF) | 0xD800));
value = 0xDC00 | (value & 0x3FF);
}
output.push(String.fromCharCode(value));
}
return output.join("");
}
}
//Default parameters
var initial_n = 0x80;
var initial_bias = 72;
var delimiter = "\x2D";
var base = 36;
var damp = 700;
var tmin=1;
var tmax=26;
var skew=38;
var maxint = 0x7FFFFFFF;
// decode_digit(cp) returns the numeric value of a basic code
// point (for use in representing integers) in the range 0 to
// base-1, or base if cp is does not represent a value.
function decode_digit(cp) {
return cp - 48 < 10 ? cp - 22 : cp - 65 < 26 ? cp - 65 : cp - 97 < 26 ? cp - 97 : base;
}
// encode_digit(d,flag) returns the basic code point whose value
// (when used for representing integers) is d, which needs to be in
// the range 0 to base-1. The lowercase form is used unless flag is
// nonzero, in which case the uppercase form is used. The behavior
// is undefined if flag is nonzero and digit d has no uppercase form.
function encode_digit(d, flag) {
return d + 22 + 75 * (d < 26) - ((flag != 0) << 5);
// 0..25 map to ASCII a..z or A..Z
// 26..35 map to ASCII 0..9
}
//** Bias adaptation function **
function adapt(delta, numpoints, firsttime ) {
var k;
delta = firsttime ? Math.floor(delta / damp) : (delta >> 1);
delta += Math.floor(delta / numpoints);
for (k = 0; delta > (((base - tmin) * tmax) >> 1); k += base) {
delta = Math.floor(delta / ( base - tmin ));
}
return Math.floor(k + (base - tmin + 1) * delta / (delta + skew));
}
// encode_basic(bcp,flag) forces a basic code point to lowercase if flag is zero,
// uppercase if flag is nonzero, and returns the resulting code point.
// The code point is unchanged if it is caseless.
// The behavior is undefined if bcp is not a basic code point.
function encode_basic(bcp, flag) {
bcp -= (bcp - 97 < 26) << 5;
return bcp + ((!flag && (bcp - 65 < 26)) << 5);
}
// Main decode
this.decode=function(input,preserveCase) {
// Dont use utf16
var output=[];
var case_flags=[];
var input_length = input.length;
var n, out, i, bias, basic, j, ic, oldi, w, k, digit, t, len;
// Initialize the state:
n = initial_n;
i = 0;
bias = initial_bias;
// Handle the basic code points: Let basic be the number of input code
// points before the last delimiter, or 0 if there is none, then
// copy the first basic code points to the output.
basic = input.lastIndexOf(delimiter);
if (basic < 0) basic = 0;
for (j = 0; j < basic; ++j) {
if(preserveCase) case_flags[output.length] = ( input.charCodeAt(j) -65 < 26);
if ( input.charCodeAt(j) >= 0x80) {
throw new RangeError("Illegal input >= 0x80");
}
output.push( input.charCodeAt(j) );
}
// Main decoding loop: Start just after the last delimiter if any
// basic code points were copied; start at the beginning otherwise.
for (ic = basic > 0 ? basic + 1 : 0; ic < input_length; ) {
// ic is the index of the next character to be consumed,
// Decode a generalized variable-length integer into delta,
// which gets added to i. The overflow checking is easier
// if we increase i as we go, then subtract off its starting
// value at the end to obtain delta.
for (oldi = i, w = 1, k = base; ; k += base) {
if (ic >= input_length) {
throw RangeError ("punycode_bad_input(1)");
}
digit = decode_digit(input.charCodeAt(ic++));
if (digit >= base) {
throw RangeError("punycode_bad_input(2)");
}
if (digit > Math.floor((maxint - i) / w)) {
throw RangeError ("punycode_overflow(1)");
}
i += digit * w;
t = k <= bias ? tmin : k >= bias + tmax ? tmax : k - bias;
if (digit < t) { break; }
if (w > Math.floor(maxint / (base - t))) {
throw RangeError("punycode_overflow(2)");
}
w *= (base - t);
}
out = output.length + 1;
bias = adapt(i - oldi, out, oldi === 0);
// i was supposed to wrap around from out to 0,
// incrementing n each time, so we'll fix that now:
if ( Math.floor(i / out) > maxint - n) {
throw RangeError("punycode_overflow(3)");
}
n += Math.floor( i / out ) ;
i %= out;
// Insert n at position i of the output:
// Case of last character determines uppercase flag:
if (preserveCase) { case_flags.splice(i, 0, input.charCodeAt(ic -1) -65 < 26);}
output.splice(i, 0, n);
i++;
}
if (preserveCase) {
for (i = 0, len = output.length; i < len; i++) {
if (case_flags[i]) {
output[i] = (String.fromCharCode(output[i]).toUpperCase()).charCodeAt(0);
}
}
}
return this.utf16.encode(output);
};
//** Main encode function **
this.encode = function (input,preserveCase) {
//** Bias adaptation function **
var n, delta, h, b, bias, j, m, q, k, t, ijv, case_flags;
if (preserveCase) {
// Preserve case, step1 of 2: Get a list of the unaltered string
case_flags = this.utf16.decode(input);
}
// Converts the input in UTF-16 to Unicode
input = this.utf16.decode(input.toLowerCase());
var input_length = input.length; // Cache the length
if (preserveCase) {
// Preserve case, step2 of 2: Modify the list to true/false
for (j=0; j < input_length; j++) {
case_flags[j] = input[j] != case_flags[j];
}
}
var output=[];
// Initialize the state:
n = initial_n;
delta = 0;
bias = initial_bias;
// Handle the basic code points:
for (j = 0; j < input_length; ++j) {
if ( input[j] < 0x80) {
output.push(
String.fromCharCode(
case_flags ? encode_basic(input[j], case_flags[j]) : input[j]
)
);
}
}
h = b = output.length;
// h is the number of code points that have been handled, b is the
// number of basic code points
if (b > 0) output.push(delimiter);
// Main encoding loop:
//
while (h < input_length) {
// All non-basic code points < n have been
// handled already. Find the next larger one:
for (m = maxint, j = 0; j < input_length; ++j) {
ijv = input[j];
if (ijv >= n && ijv < m) m = ijv;
}
// Increase delta enough to advance the decoder's
// <n,i> state to <m,0>, but guard against overflow:
if (m - n > Math.floor((maxint - delta) / (h + 1))) {
throw RangeError("punycode_overflow (1)");
}
delta += (m - n) * (h + 1);
n = m;
for (j = 0; j < input_length; ++j) {
ijv = input[j];
if (ijv < n ) {
if (++delta > maxint) return Error("punycode_overflow(2)");
}
if (ijv == n) {
// Represent delta as a generalized variable-length integer:
for (q = delta, k = base; ; k += base) {
t = k <= bias ? tmin : k >= bias + tmax ? tmax : k - bias;
if (q < t) break;
output.push( String.fromCharCode(encode_digit(t + (q - t) % (base - t), 0)) );
q = Math.floor( (q - t) / (base - t) );
}
output.push( String.fromCharCode(encode_digit(q, preserveCase && case_flags[j] ? 1:0 )));
bias = adapt(delta, h + 1, h == b);
delta = 0;
++h;
}
}
++delta, ++n;
}
return output.join("");
}
this.ToASCII = function ( domain ) {
var domain_array = domain.split(".");
var out = [];
for (var i=0; i < domain_array.length; ++i) {
var s = domain_array[i];
out.push(
s.match(/[^A-Za-z0-9-]/) ?
"xn--" + punycode.encode(s) :
s
);
}
return out.join(".");
}
this.ToUnicode = function ( domain ) {
var domain_array = domain.split(".");
var out = [];
for (var i=0; i < domain_array.length; ++i) {
var s = domain_array[i];
out.push(
s.match(/^xn--/) ?
punycode.decode(s.slice(4)) :
s
);
}
return out.join(".");
}
}();
var WshShell = new ActiveXObject("WScript.Shell");
var ansiToUtf8 = {"Ё":"%D0%81","ё":"%D1%91","А":"%D0%90","Б":"%D0%91","В":"%D0%92","Г":"%D0%93","Д":"%D0%94","Е":"%D0%95","Ж":"%D0%96","З":"%D0%97","И":"%D0%98","Й":"%D0%99","К":"%D0%9A","Л":"%D0%9B","М":"%D0%9C","Н":"%D0%9D","О":"%D0%9E","П":"%D0%9F","Р":"%D0%A0","С":"%D0%A1","Т":"%D0%A2","У":"%D0%A3","Ф":"%D0%A4","Х":"%D0%A5","Ц":"%D0%A6","Ч":"%D0%A7","Ш":"%D0%A8","Щ":"%D0%A9","Ъ":"%D0%AA","Ы":"%D0%AB","Ь":"%D0%AC","Э":"%D0%AD","Ю":"%D0%AE","Я":"%D0%AF","а":"%D0%B0","б":"%D0%B1","в":"%D0%B2","г":"%D0%B3","д":"%D0%B4","е":"%D0%B5","ж":"%D0%B6","з":"%D0%B7","и":"%D0%B8","й":"%D0%B9","к":"%D0%BA","л":"%D0%BB","м":"%D0%BC","н":"%D0%BD","о":"%D0%BE","п":"%D0%BF","р":"%D1%80","с":"%D1%81","т":"%D1%82","у":"%D1%83","ф":"%D1%84","х":"%D1%85","ц":"%D1%86","ч":"%D1%87","ш":"%D1%88","щ":"%D1%89","ъ":"%D1%8A","ы":"%D1%8B","ь":"%D1%8C","э":"%D1%8D","ю":"%D1%8E","я":"%D1%8F"};
//1-протокол, логин-пароль; 2 - хост; 3 - остальное.
// 1 2 3
var parseUrl = /^((?:https?|ftp):\/\/(?:[\w\.-]+(?::[\w\.-]+)?@)?)([\w\.а-яЁё-]+)((?::\d+)?\/.*)?$/i;
// http://ru.wikipedia.org/wiki/URI#.D0.A0.D0.B0.D0.B7.D0.B1.D0.BE.D1.80_.D1.81.D1.82.D1.80.D1.83.D0.BA.D1.82.D1.83.D1.80.D1.8B_URI
function EventRaised(eType, eData)
{
var tmp=eData.split(' ');
var ID=tmp[0];
var dState=tmp[1];
if ( !(eType == 'dm_download_added') && !(eType == 'dm_download_state' && dState=='4') ) return;
var info = DM.DoAction('GetDownloadInfoByID', ID);
var url = info.match(/<url>(.*?)<\/url>/im)[1];
var newUrl = url.match(parseUrl);
newUrl[0] = '';
// перекодирую в utf-8 русские буквы в пути и имени файла
if (eType == 'dm_download_state' && dState=='4') { // dsError = 4
var descr = info.match(/<description>(.*?)<\/description>/im)[1];
if (descr.indexOf('[ansiToUtf8]')!=-1) {
tmp = DM.DoAction('AddStringToLog','<id>'+ID+'</id><type>3</type><logstring>[ansiToUtf8] label exists - aborting</logstring>');
return;
}
newUrl[3] = newUrl[3].replace(/[а-яЁё]/gi, function(i){ return ansiToUtf8[i]; });
newUrl=newUrl.join('');
if (newUrl == url) return;
var newData='<id>'+ID+'</id><mirror1>'+newUrl+'</mirror1><description>'+descr+' [ansiToUtf8]</description>';
tmp = DM.DoAction('SetDownloadInfoByID',newData);
tmp = DM.DoAction('AddStringToLog','<id>'+ID+'</id><type>2</type><logstring>[ansiToUtf8] mirror added - restarting</logstring>');
tmp = DM.DoAction('StartDownloads',ID);
}
// перекодирую хост в punycode - для русских доменов
else if (eType == 'dm_download_added') {
if (newUrl[2].search(/[^\da-z\.-]/i) == -1) return;
newUrl[2] = punycode.ToASCII(newUrl[2]);
newUrl=newUrl.join('');
if (newUrl == url) return;
var newData='<id>'+ID+'</id><url>'+newUrl+'</url>';
tmp = DM.DoAction('SetDownloadInfoByID',newData);
tmp = DM.DoAction('AddStringToLog','<id>'+ID+'</id><type>2</type><logstring>[ansiToUtf8] punycode: '+url+'</logstring>');
}
}
): скрипт "бегает" по html-страницам, переберает все линки на предмет соответствия заданному формату, и если все ОК - добавляет закачку.