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

cleanup

This commit is contained in:
Dmitry Shirokov 2013-08-12 12:10:06 +10:00
parent 199a24bad6
commit 9fd949edf3
1 changed files with 25 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
encoding/mbcs.js
View File

@ -27,8 +27,8 @@ function binarySearch(arr, searchValue) {
return find(arr, searchValue, 0, arr.length - 1); return find(arr, searchValue, 0, arr.length - 1);
}; };
// "Character" iterated character class. // 'Character' iterated character class.
// Recognizers for specific mbcs encodings make their "characters" available // Recognizers for specific mbcs encodings make their 'characters' available
// by providing a nextChar() function that fills in an instance of iteratedChar // by providing a nextChar() function that fills in an instance of iteratedChar
// with the next char from the input. // with the next char from the input.
// The returned characters are not converted to Unicode, but remain as the raw // The returned characters are not converted to Unicode, but remain as the raw
@ -116,7 +116,7 @@ mbcs.prototype.match = function(det) {
} }
} }
} }
if (badCharCount >= 2 && badCharCount*5 >= doubleByteCharCount) { if (badCharCount >= 2 && badCharCount * 5 >= doubleByteCharCount) {
// console.log('its here!') // console.log('its here!')
// Bail out early if the byte data is not matching the encoding scheme. // Bail out early if the byte data is not matching the encoding scheme.
break detectBlock; break detectBlock;
@ -143,7 +143,7 @@ mbcs.prototype.match = function(det) {
// No match if there are too many characters that don't fit the encoding scheme. // No match if there are too many characters that don't fit the encoding scheme.
// (should we have zero tolerance for these?) // (should we have zero tolerance for these?)
// //
if (doubleByteCharCount < 20*badCharCount) { if (doubleByteCharCount < 20 * badCharCount) {
confidence = 0; confidence = 0;
break detectBlock; break detectBlock;
} }
@ -152,7 +152,7 @@ mbcs.prototype.match = function(det) {
// We have no statistics on frequently occuring characters. // We have no statistics on frequently occuring characters.
// Assess confidence purely on having a reasonable number of // Assess confidence purely on having a reasonable number of
// multi-byte characters (the more the better // multi-byte characters (the more the better
confidence = 30 + doubleByteCharCount - 20*badCharCount; confidence = 30 + doubleByteCharCount - 20 * badCharCount;
if (confidence > 100) { if (confidence > 100) {
confidence = 100; confidence = 100;
} }
@ -162,7 +162,7 @@ mbcs.prototype.match = function(det) {
// //
var maxVal = Math.log(parseFloat(doubleByteCharCount) / 4); var maxVal = Math.log(parseFloat(doubleByteCharCount) / 4);
var scaleFactor = 90.0 / maxVal; var scaleFactor = 90.0 / maxVal;
confidence = Math.floor(Math.log(commonCharCount+1) * scaleFactor + 10); confidence = Math.floor(Math.log(commonCharCount + 1) * scaleFactor + 10);
confidence = Math.min(confidence, 100); confidence = Math.min(confidence, 100);
} }
} // end of detectBlock: } // end of detectBlock:
@ -177,7 +177,7 @@ mbcs.prototype.match = function(det) {
* *
* This function is not a method of class iteratedChar only because * This function is not a method of class iteratedChar only because
* that would require a lot of extra derived classes, which is awkward. * that would require a lot of extra derived classes, which is awkward.
* @param it The iteratedChar "struct" into which the returned char is placed. * @param it The iteratedChar 'struct' into which the returned char is placed.
* @param det The charset detector, which is needed to get at the input byte data * @param det The charset detector, which is needed to get at the input byte data
* being iterated over. * being iterated over.
* @return True if a character was returned, false at end of input. * @return True if a character was returned, false at end of input.
@ -192,10 +192,10 @@ mbcs.prototype.nextChar = function(iter, det) {};
*/ */
module.exports.sjis = function() { module.exports.sjis = function() {
this.name = function() { this.name = function() {
return "Shift-JIS"; return 'Shift-JIS';
}; };
this.language = function() { this.language = function() {
return "ja"; return 'ja';
}; };
// TODO: This set of data comes from the character frequency- // TODO: This set of data comes from the character frequency-
@ -216,20 +216,18 @@ module.exports.sjis = function() {
var firstByte; var firstByte;
firstByte = iter.charValue = iter.nextByte(det); firstByte = iter.charValue = iter.nextByte(det);
if (firstByte < 0) { if (firstByte < 0)
return false; return false;
}
if (firstByte <= 0x7f || (firstByte>0xa0 && firstByte<=0xdf)) { if (firstByte <= 0x7f || (firstByte > 0xa0 && firstByte <= 0xdf))
return true; return true;
}
var secondByte = iter.nextByte(det); var secondByte = iter.nextByte(det);
if (secondByte < 0) { if (secondByte < 0)
return false; return false;
}
iter.charValue = (firstByte << 8) | secondByte; iter.charValue = (firstByte << 8) | secondByte;
if (! ((secondByte>=0x40 && secondByte<=0x7f) || (secondByte>=0x80 && secondByte<=0xff))) { if (! ((secondByte >= 0x40 && secondByte <= 0x7f) || (secondByte >= 0x80 && secondByte <= 0xff))) {
// Illegal second byte value. // Illegal second byte value.
iter.error = true; iter.error = true;
} }
@ -245,10 +243,10 @@ util.inherits(module.exports.sjis, mbcs);
*/ */
module.exports.big5 = function() { module.exports.big5 = function() {
this.name = function() { this.name = function() {
return "Big5"; return 'Big5';
}; };
this.language = function() { this.language = function() {
return "zh"; return 'zh';
}; };
// TODO: This set of data comes from the character frequency- // TODO: This set of data comes from the character frequency-
// of-occurence analysis tool. The data needs to be moved // of-occurence analysis tool. The data needs to be moved
@ -300,7 +298,7 @@ util.inherits(module.exports.big5, mbcs);
* and nested derived classes for EUC_KR, EUC_JP, EUC_CN. * and nested derived classes for EUC_KR, EUC_JP, EUC_CN.
* *
* Get the next character value for EUC based encodings. * Get the next character value for EUC based encodings.
* Character "value" is simply the raw bytes that make up the character * Character 'value' is simply the raw bytes that make up the character
* packed into an int. * packed into an int.
*/ */
function eucNextChar(iter, det) { function eucNextChar(iter, det) {
@ -363,10 +361,10 @@ function eucNextChar(iter, det) {
*/ */
module.exports.euc_jp = function() { module.exports.euc_jp = function() {
this.name = function() { this.name = function() {
return "EUC-JP"; return 'EUC-JP';
}; };
this.language = function() { this.language = function() {
return "ja"; return 'ja';
}; };
// TODO: This set of data comes from the character frequency- // TODO: This set of data comes from the character frequency-
@ -397,10 +395,10 @@ util.inherits(module.exports.euc_jp, mbcs);
*/ */
module.exports.euc_kr = function() { module.exports.euc_kr = function() {
this.name = function() { this.name = function() {
return "EUC-KR"; return 'EUC-KR';
}; };
this.language = function() { this.language = function() {
return "ko"; return 'ko';
}; };
// TODO: This set of data comes from the character frequency- // TODO: This set of data comes from the character frequency-
@ -430,15 +428,15 @@ util.inherits(module.exports.euc_kr, mbcs);
*/ */
module.exports.gb_18030 = function() { module.exports.gb_18030 = function() {
this.name = function() { this.name = function() {
return "GB18030"; return 'GB18030';
}; };
this.language = function() { this.language = function() {
return "zh"; return 'zh';
}; };
/* /*
* Get the next character value for EUC based encodings. * Get the next character value for EUC based encodings.
* Character "value" is simply the raw bytes that make up the character * Character 'value' is simply the raw bytes that make up the character
* packed into an int. * packed into an int.
*/ */
this.nextChar = function(iter, det) { this.nextChar = function(iter, det) {
@ -463,7 +461,7 @@ module.exports.gb_18030 = function() {
iter.charValue = (iter.charValue << 8) | secondByte; iter.charValue = (iter.charValue << 8) | secondByte;
if (firstByte >= 0x81 && firstByte <= 0xFE) { if (firstByte >= 0x81 && firstByte <= 0xFE) {
// Two byte Char // Two byte Char
if ((secondByte >= 0x40 && secondByte <= 0x7E) || (secondByte >=80 && secondByte <=0xFE)) { if ((secondByte >= 0x40 && secondByte <= 0x7E) || (secondByte >=80 && secondByte <= 0xFE)) {
break buildChar; break buildChar;
} }
// Four byte char // Four byte char