diff --git a/lib/scripts/mtw.js b/lib/scripts/mtw.js
index f27d563..42bfb3a 100644
--- a/lib/scripts/mtw.js
+++ b/lib/scripts/mtw.js
@@ -149,7 +149,14 @@ export class ContentScript {
paragraphs = document.getElementsByTagName('p');
console.log('Getting words from all ' + paragraphs.length + ' paragraphs');
for (var i = 0; i < paragraphs.length; i++) {
- var words = paragraphs[i].innerText.split(/\s|,|[.()]|\d/g);
+ var words = paragraphs[i].innerText;
+ if(this.clkTest(words)){
+ words = words.replace(/\d|\s|[()]/g,'').split('').filter(v=>v!='');
+ }
+ else{
+ words = words.split(/\s|,|[.()]|\d/g);
+ }
+ // console.log(words);
for (var j = 0; j < words.length; j++) {
for (var b = ngramMin; b <= ngramMax; b++) {
var word = words.slice(j, j + b).join(' ');
@@ -179,11 +186,16 @@ export class ContentScript {
var blackListReg = new RegExp(userBlacklistedWords);
var punctuationReg = new RegExp(/[\.,\/#\!\$%\^&\*;:{}=\\\_`~()\?@\d\+\-]/g);
var countedWordsList = this.shuffle(this.toList(countedWords, (word, count) => {
- return !!word && word.length >= 2 && // no words that are too short
- word !== '' && !/\d/.test(word) && // no empty words
- word.charAt(0) !== word.charAt(0).toUpperCase() && // no proper nouns
- !blackListReg.test(word.toLowerCase()) && // no blacklisted words
- !punctuationReg.test(word.toLowerCase()); // no punctuation marks
+ if(this.clkTest(word))
+
+ return !!word && word !== '' && !/\d/.test(word) && // no empty words
+ !blackListReg.test(word.toLowerCase()) && // no blacklisted words
+ !punctuationReg.test(word.toLowerCase()); // no punctuation marksreturn !!word && word.length >= 2 && // no words that are too short
+ else
+ return word !== '' && !/\d/.test(word) && // no empty words
+ word.charAt(0) !== word.charAt(0).toUpperCase() && // no proper nouns
+ !blackListReg.test(word.toLowerCase()) && // no blacklisted words
+ !punctuationReg.test(word.toLowerCase()); // no punctuation marks
}));
var targetLength = Math.floor((Object.keys(countedWordsList).length * translationProbability) / 100);
return this.toMap(countedWordsList.slice(0, targetLength - 1));
@@ -280,7 +292,6 @@ export class ContentScript {
}
}
});
-
if (Object.keys(filteredTMap).length !== 0) {
var paragraphs = document.getElementsByTagName('p');
if (this.oneWordTranslation) {
@@ -294,6 +305,8 @@ export class ContentScript {
}
}
+ // console.log(filteredTMap);
+
// Add event listener to each word for toggle
var translatedWords = document.querySelectorAll('.mtwTranslatedWord, .mtwTranslatedWorde, .mtwTranslatedWordn, .mtwTranslatedWordh');
for (let i = 0; i < translatedWords.length; i++) {
@@ -395,11 +408,33 @@ export class ContentScript {
deepHTMLReplacement(node, tMap, iTMap) {
var badTags = ['TEXTAREA', 'INPUT', 'SCRIPT', 'CODE', 'A', 'SPAN'];
if (node.nodeType === Node.TEXT_NODE) {
- var newNodeValue = this.replaceAll(node.nodeValue, tMap);
+ var newNodeValue;
+ if(this.targetLanguage == "zh"){
+ newNodeValue = this.replaceAll(node.nodeValue, tMap);
+ }
+ else{
+ if(this.clkTest(node.nodeValue)){
+ newNodeValue = this.replaceAllClk(node.nodeValue, tMap);
+ }
+ else{
+ newNodeValue = this.replaceAll(node.nodeValue, tMap);
+ }
+ }
if (newNodeValue !== node.nodeValue) {
node.nodeValue = newNodeValue;
var parent = node.parentNode;
- parent.innerHTML = this.replaceAll(parent.innerHTML, iTMap);
+ if(this.targetLanguage == "zh"){
+ parent.innerHTML = this.replaceAll(parent.innerHTML, iTMap);
+ }
+ else{
+ if(this.clkTest(node.nodeValue)){
+ parent.innerHTML = this.replaceAllClk(parent.innerHTML, iTMap);
+ }
+ else{
+ parent.innerHTML = this.replaceAll(parent.innerHTML, iTMap);
+ }
+ }
+ // parent.innerHTML = this.replaceAll(parent.innerHTML, iTMap);
}
} else if (node.nodeType === Node.ELEMENT_NODE && badTags.indexOf(node.tagName) <= -1) {
var innerNodes = node.childNodes;
@@ -434,6 +469,40 @@ export class ContentScript {
return ' ' + m + ' ';
}
});
+
+ if (/^\s*$/.test(newText)) {
+ return text;
+ }
+ return newText;
+ }
+
+
+ /**
+ * Returns text replaced with translations (only for CLK Languages) (if any)
+ * otherwise returns the same text
+ * @param {string} text - source text
+ * @param {Object} translationMap - translations for source words
+ * @returns {string} text - text with translations
+ */
+ replaceAllClk(text, translationMap) {
+ var rExp = '';
+ var sortedSourceWords = Object.keys(translationMap)
+ .sort((w1, w2) => {
+ return w2.length - w1.length;
+ });
+ sortedSourceWords.forEach((sourceWord) => {
+ rExp += '(' + this.escapeRegExp(sourceWord) + ')|';
+ });
+ rExp = rExp.substring(0, rExp.length - 1);
+ var regExp = new RegExp(rExp, 'gm');
+ var newText = text.replace(regExp, (m) => {
+ if (translationMap[m] !== null) {
+ return ' ' + translationMap[m] + ' ';
+ } else {
+ return ' ' + m + ' ';
+ }
+ });
+
if (/^\s*$/.test(newText)) {
return text;
}
@@ -572,7 +641,7 @@ export class ContentScript {
sendError(message) {
if(message == '')
- message = 'Could Not Connect To Translator Service';
+ message = 'Could not connect to '+this.translator+' Service .\nIt may be temporarily unavailable or you may be experiencing internet connection problems ';
var date = new Date();
@@ -597,6 +666,15 @@ export class ContentScript {
});
}
+
+
+ clkTest(str){
+ var clk_main = new RegExp("[\u4E00-\u9FFF]");
+ var clk_extension = new RegExp("[\u3400-\u4DBF]");
+ var clk_strokes = new RegExp("[\u31C0-\u31EF]");
+ var clk_symbols_punctuation = new RegExp("[\u3000-\u303F]");
+ return (clk_main.test(str)||clk_extension.test(str)||clk_strokes.test(str)||clk_symbols_punctuation.test(str));
+ }
}
var MTWTranslator = new ContentScript();
diff --git a/lib/views/includes/troubleshooting.html b/lib/views/includes/troubleshooting.html
index 01a9a83..76496c2 100644
--- a/lib/views/includes/troubleshooting.html
+++ b/lib/views/includes/troubleshooting.html
@@ -1,3 +1,4 @@
+
@@ -20,7 +21,7 @@
{{logMessage.message}}
-
({{logMessage.url}})
+
({{logMessage.url}})
{{logMessage.date}}