LumeWeb
/
chardet
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #2 from spikying/master 

declared variable '''' confidence '''' before use, to make it work in 'strict mode' environment.
This commit is contained in:
Dmitry Shirokov 2015-11-30 08:46:40 +11:00
parent 17aebe7b28 0d1eec1776
commit 9609ab4a7a
1 changed files with 19 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
encoding/unicode.js
View File

@ -1,3 +1,4 @@
'use strict';
var util = require('util'), var util = require('util'),
Match = require ('../match'); Match = require ('../match');
@ -12,8 +13,10 @@ module.exports.UTF_16BE = function() {
this.match = function(det) { this.match = function(det) {
var input = det.fRawInput; var input = det.fRawInput;
if (input.length >= 2 && ((input[0] & 0xff) == 0xfe && (input[1] & 0xff) == 0xff)) if (input.length >= 2 && ((input[0] & 0xff) == 0xfe && (input[1] & 0xff) == 0xff)) {
return new Match(det, this, confidence = 100); var confidence = 100;
return new Match(det, this, confidence);
}
// TODO: Do some statistics to check for unsigned UTF-16BE // TODO: Do some statistics to check for unsigned UTF-16BE
return null; return null;
@ -29,11 +32,12 @@ module.exports.UTF_16LE = function() {
if (input.length >= 2 && ((input[0] & 0xff) == 0xff && (input[1] & 0xff) == 0xfe)) { if (input.length >= 2 && ((input[0] & 0xff) == 0xff && (input[1] & 0xff) == 0xfe)) {
// An LE BOM is present. // An LE BOM is present.
if (input.length >= 4 && input[2] == 0x00 && input[3] == 0x00) if (input.length >= 4 && input[2] == 0x00 && input[3] == 0x00) {
// It is probably UTF-32 LE, not UTF-16 // It is probably UTF-32 LE, not UTF-16
return null; return null;
}
return new Match(det, this, confidence = 100); var confidence = 100;
return new Match(det, this, confidence);
} }
// TODO: Do some statistics to check for unsigned UTF-16LE // TODO: Do some statistics to check for unsigned UTF-16LE
@ -50,20 +54,23 @@ UTF_32.prototype.match = function(det) {
hasBOM = false, hasBOM = false,
confidence = 0; confidence = 0;
if (limit == 0) if (limit == 0) {
return null; return null;
}
if (this.getChar(input, 0) == 0x0000FEFF) if (this.getChar(input, 0) == 0x0000FEFF) {
hasBOM = true; hasBOM = true;
}
for (var i = 0; i < limit; i += 4) { for (var i = 0; i < limit; i += 4) {
var ch = this.getChar(input, i); var ch = this.getChar(input, i);
if (ch < 0 || ch >= 0x10FFFF || (ch >= 0xD800 && ch <= 0xDFFF)) if (ch < 0 || ch >= 0x10FFFF || (ch >= 0xD800 && ch <= 0xDFFF)) {
numInvalid += 1; numInvalid += 1;
else } else {
numValid += 1; numValid += 1;
} }
}
// Cook up some sort of confidence score, based on presence of a BOM // Cook up some sort of confidence score, based on presence of a BOM
// and the existence of valid and/or invalid multi-byte sequences. // and the existence of valid and/or invalid multi-byte sequences.