aboutsummaryrefslogtreecommitdiffstats
path: root/netinstall/6/nb/content/nwSearchFnt.js
blob: 133278679f0c9d2b0bd7845ef4a51950e93f639f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93<
Diffstat (limited to 'installer/4/cs/content')
0 files changed, 0 insertions, 0 deletions
2 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524
/*----------------------------------------------------------------------------
 * JavaScript for webhelp search
 *----------------------------------------------------------------------------
 This file is part of the webhelpsearch plugin for DocBook WebHelp
 Copyright (c) 2007-2008 NexWave Solutions All Rights Reserved.
 www.nexwave.biz Nadege Quaine
 http://kasunbg.blogspot.com/ Kasun Gajasinghe
 */

//string initialization
var htmlfileList = "htmlFileList.js";
var htmlfileinfoList = "htmlFileInfoList.js";
var useCJKTokenizing = false;

/* Cette fonction verifie la validite de la recherche entrre par l utilisateur */
function Verifie(ditaSearch_Form) {

    // Check browser compatibitily
    if (navigator.userAgent.indexOf("Konquerer") > -1) {

        alert(txt_browser_not_supported);
        return;
    }


    var expressionInput = document.ditaSearch_Form.textToSearch.value;
    //Set a cookie to store the searched keywords
    $.cookie('textToSearch', expressionInput);


    if (expressionInput.length < 1) {

        // expression is invalid
        alert(txt_enter_at_least_1_char);
        // reactive la fenetre de search (utile car cadres)
        document.ditaSearch_Form.textToSearch.focus();
    }
    else {

        // Effectuer la recherche
        Effectuer_recherche(expressionInput);

        // reactive la fenetre de search (utile car cadres)
        document.ditaSearch_Form.textToSearch.focus();
    }
}

var stemQueryMap = new Array();  // A hashtable which maps stems to query words

/* This function parses the search expression, loads the indices and displays the results*/
function Effectuer_recherche(expressionInput) {

    /* Display a waiting message */
    //DisplayWaitingMessage();

    /*data initialisation*/
    var searchFor = "";       // expression en lowercase et sans les caracte    res speciaux
    //w = new Object();  // hashtable, key=word, value = list of the index of the html files
    scriptLetterTab = new Scriptfirstchar(); // Array containing the first letter of each word to look for
    var wordsList = new Array(); // Array with the words to look for
    var finalWordsList = new Array(); // Array with the words to look for after removing spaces
    var linkTab = new Array();
    var fileAndWordList = new Array();
    var txt_wordsnotfound = "";


    /*nqu: expressionInput, la recherche est lower cased, plus remplacement des char speciaux*/
    searchFor = expressionInput.toLowerCase().replace(/<\//g, "_st_").replace(/\$_/g, "_di_").replace(/\.|%2C|%3B|%21|%3A|@|\/|\*/g, " ").replace(/(%20)+/g, " ").replace(/_st_/g, "</").replace(/_di_/g, "%24_");

    searchFor = searchFor.replace(/  +/g, " ");
    searchFor = searchFor.replace(/ $/, "").replace(/^ /, "");

    wordsList = searchFor.split(" ");
    wordsList.sort();

    //set the tokenizing method
    if(typeof indexerLanguage != "undefined" && (indexerLanguage=="zh" || indexerLanguage=="ja" ||indexerLanguage=="ko")){
        useCJKTokenizing=true;
    } else {
        useCJKTokenizing=false;
    }
    //If Lucene CJKTokenizer was used as the indexer, then useCJKTokenizing will be true. Else, do normal tokenizing.
    // 2-gram tokenizinghappens in CJKTokenizing,  
    if(useCJKTokenizing){
        finalWordsList = cjkTokenize(wordsList);
    } else { 
        finalWordsList = tokenize(wordsList);
    }

    //load the scripts with the indices: the following lines do not work on the server. To be corrected
    /*if (IEBrowser) {
     scriptsarray = loadTheIndexScripts (scriptLetterTab);
     } */

    /**
     * Compare with the indexed words (in the w[] array), and push words that are in it to tempTab.
     */
    var tempTab = new Array();
    for (var t in finalWordsList) {
        if (w[finalWordsList[t].toString()] == undefined) {
            txt_wordsnotfound += finalWordsList[t] + " ";
        } else {
            tempTab.push(finalWordsList[t]);
        }
    }
    finalWordsList = tempTab;
    
    if (!finalWordsList.length) {
        finalWordsList = wordsList;
    }
    
    fileAndWordList = SortResults(finalWordsList);

    if (fileAndWordList && fileAndWordList.length) {

        //search 'and' and 'or' one time
        //fileAndWordList = SortResults(finalWordsList);

        var cpt = fileAndWordList.length;
        for (var i = cpt - 1; i >= 0; i--) {
            if (fileAndWordList[i] != undefined) {
                linkTab.push("<p>" + txt_results_for + " " + "<span class=\"searchExpression\">" + fileAndWordList[i][0].motslisteDisplay + "</span>" + "</p>");

                linkTab.push("<ul class='searchresult'>");
                for (t in fileAndWordList[i]) {
                    //DEBUG: alert(": "+ fileAndWordList[i][t].filenb+" " +fileAndWordList[i][t].motsliste);
                    //linkTab.push("<li><a href=\"../"+fl[fileAndWordList[i][t].filenb]+"\">"+fl[fileAndWordList[i][t].filenb]+"</a></li>");
                    var tempInfo = fil[fileAndWordList[i][t].filenb];
                    var pos1 = tempInfo.indexOf("@@@");
                    var pos2 = tempInfo.lastIndexOf("@@@");
                    var tempPath = tempInfo.substring(0, pos1);
                    var tempTitle = tempInfo.substring(pos1 + 3, pos2);
                    var tempShortdesc = tempInfo.substring(pos2 + 3, tempInfo.length);

                    //file:///home/kasun/docbook/WEBHELP/webhelp-draft-output-format-idea/src/main/resources/web/webhelp/installation.html
                    var linkString = "<li><a href=" + tempPath + ">" + tempTitle + "</a>";
                    // var linkString = "<li><a href=\"installation.html\">" + tempTitle + "</a>";
                    if ((tempShortdesc != "null")) {
                        linkString += "\n<div class=\"shortdesclink\">" + tempShortdesc + "</div>";
                    }
                    linkString += "</li>";
                    linkTab.push(linkString);
                }
                linkTab.push("</ul>");
            }
        }
    }

    var results = "";
    if (linkTab.length > 0) { 
        /*writeln ("<p>" + txt_results_for + " " + "<span class=\"searchExpression\">"  + cleanwordsList + "</span>" + "<br/>"+"</p>");*/
        results = "<p>";
        //write("<ul class='searchresult'>");
        for (t in linkTab) {
            results += linkTab[t].toString();
        }
        results += "</p>";
    } else {
        results = "<p>" + txt_no_results_for + "<span class=\"searchExpression\">" + txt_wordsnotfound + "</span>" + "</p>";
    }
    //alert(results);
    document.getElementById('searchResults').innerHTML = results; 
}

function tokenize(wordsList){
    var stemmedWordsList = new Array(); // Array with the words to look for after removing spaces
    var cleanwordsList = new Array(); // Array with the words to look for
    for(var j in wordsList){
        var word = wordsList[j];
        if(typeof stemmer != "undefined" ){
            stemQueryMap[stemmer(word)] = word;
        } else {
            stemQueryMap[word] = word;
        }
    } 
     //stemmedWordsList is the stemmed list of words separated by spaces.
    for (var t in wordsList) {
        wordsList[t] = wordsList[t].replace(/(%22)|^-/g, "");
        if (wordsList[t] != "%20") {
            scriptLetterTab.add(wordsList[t].charAt(0));
            cleanwordsList.push(wordsList[t]);
        }
    }

    if(typeof stemmer != "undefined" ){
        //Do the stemming using Porter's stemming algorithm
        for (var i = 0; i < cleanwordsList.length; i++) {
            var stemWord = stemmer(cleanwordsList[i]);
            stemmedWordsList.push(stemWord);
        }
    } else {
        stemmedWordsList = cleanwordsList;
    }
    return stemmedWordsList;
}

//Invoker of CJKTokenizer class methods.
function cjkTokenize(wordsList){
    var allTokens= new Array();
    var notCJKTokens= new Array();
    var j=0;
    for(j=0;j<wordsList.length;j++){
        var word = wordsList[j];
        if(getAvgAsciiValue(word) < 127){
            notCJKTokens.push(word);
        } else { 
            var tokenizer = new CJKTokenizer(word);
            var tokensTmp = tokenizer.getAllTokens();
            allTokens = allTokens.concat(tokensTmp);
        }
    }
    allTokens = allTokens.concat(tokenize(notCJKTokens));
    return allTokens;
}

//A simple way to determine whether the query is in english or not.
function getAvgAsciiValue(word){
    var tmp = 0;
    var num = word.length < 5 ? word.length:5;
    for(var i=0;i<num;i++){
        if(i==5) break;
        tmp += word.charCodeAt(i);
    }
    return tmp/num;
}

//CJKTokenizer
function CJKTokenizer(input){
    this.input = input;
    this.offset=-1;
    this.tokens = new Array(); 
    this.incrementToken = incrementToken;
    this.tokenize = tokenize;
    this.getAllTokens = getAllTokens;
    this.unique = unique;

    function incrementToken(){
		if(this.input.length - 2 <= this.offset){
		//	console.log("false "+offset);
			return false;
		}
		else {
			this.offset+=1;
			return true;
		}
	}

	function tokenize(){
		//document.getElementById("content").innerHTML += x.substring(offset,offset+2)+"<br>";
		return this.input.substring(this.offset,this.offset+2);
	}

	function getAllTokens(){
		while(this.incrementToken()){
			var tmp = this.tokenize();
			this.tokens.push(tmp);
		}
        return this.unique(this.tokens);
//		document.getElementById("content").innerHTML += tokens+" ";
//		document.getElementById("content").innerHTML += "<br>dada"+sortedTokens+" ";
//		console.log(tokens.length+"dsdsds");
		/*for(i=0;i<tokens.length;i++){
			console.log(tokens[i]);
			var ss = tokens[i] == sortedTokens[i];

//			document.getElementById("content").innerHTML += "<br>dada"+un[i]+"- "+stems[i]+"&nbsp;&nbsp;&nbsp;"+ ss;
			document.getElementById("content").innerHTML += "<br>"+sortedTokens[i];
		}*/
	}

	function unique(a)
	{
	   var r = new Array();
	   o:for(var i = 0, n = a.length; i < n; i++)
	   {
	      for(var x = 0, y = r.length; x < y; x++)
	      {
		 if(r[x]==a[i]) continue o;
	      }
	      r[r.length] = a[i];
	   }
	   return r;
	} 
}


/* Scriptfirstchar: to gather the first letter of index js files to upload */
function Scriptfirstchar() {
    this.strLetters = "";
    this.add = addLettre;
}

function addLettre(caract) {

    if (this.strLetters == 'undefined') {
        this.strLetters = caract;
    } else if (this.strLetters.indexOf(caract) < 0) {
        this.strLetters += caract;
    }

    return 0;
}
/* end of scriptfirstchar */

/*main loader function*/
/*tab contains the first letters of each word looked for*/
function loadTheIndexScripts(tab) {

    //alert (tab.strLetters);
    var scriptsarray = new Array();

    for (var i = 0; i < tab.strLetters.length; i++) {

        scriptsarray[i] = "..\/search" + "\/" + tab.strLetters.charAt(i) + ".js";
    }
    // add the list of html files
    i++;
    scriptsarray[i] = "..\/search" + "\/" + htmlfileList;

    //debug
    for (var t in scriptsarray) {
        //alert (scriptsarray[t]);
    }

    tab = new ScriptLoader();
    for (t in scriptsarray) {
        tab.add(scriptsarray[t]);
    }
    tab.load();
    //alert ("scripts loaded");
    return (scriptsarray);
}

/* ScriptLoader: to load the scripts and wait that it's finished */
function ScriptLoader() {
    this.cpt = 0;
    this.scriptTab = new Array();
    this.add = addAScriptInTheList;
    this.load = loadTheScripts;
    this.onScriptLoaded = onScriptLoadedFunc;
}

function addAScriptInTheList(scriptPath) {
    this.scriptTab.push(scriptPath);
}

function loadTheScripts() {
    var script;
    var head;

    head = document.getElementsByTagName('head').item(0);

    //script = document.createElement('script');

    for (var el in this.scriptTab) {
        //alert (el+this.scriptTab[el]);
        script = document.createElement('script');
        script.src = this.scriptTab[el];
        script.type = 'text/javascript';
        script.defer = false;

        head.appendChild(script);
    }

}

function onScriptLoadedFunc(e) {
    e = e || window.event;
    var target = e.target || e.srcElement;
    var isComplete = true;
    if (typeof target.readyState != undefined) {

        isComplete = (target.readyState == "complete" || target.readyState == "loaded");
    }
    if (isComplete) {
        ScriptLoader.cpt++;
        if (ScriptLoader.cpt == ScriptLoader.scripts.length) {
            ScriptLoader.onLoadComplete();
        }
    }
}

/*
function onLoadComplete() {
    alert("loaded !!");
} */

/* End of scriptloader functions */
 
// Array.unique( strict ) - Remove duplicate values
function unique(tab) {
    var a = new Array();
    var i;
    var l = tab.length;

    if (tab[0] != undefined) {
        a[0] = tab[0];
    }
    else {
        return -1
    }

    for (i = 1; i < l; i++) {
        if (indexof(a, tab[i], 0) < 0) {
            a.push(tab[i]);
        }
    }
    return a;
}
function indexof(tab, element, begin) {
    for (var i = begin; i < tab.length; i++) {
        if (tab[i] == element) {
            return i;
        }
    }
    return -1;

}
/* end of Array functions */


/*
 Param: mots= list of words to look for.
 This function creates an hashtable:
 - The key is the index of a html file which contains a word to look for.
 - The value is the list of all words contained in the html file.

 Return value: the hashtable fileAndWordList
 */
function SortResults(mots) {

    var fileAndWordList = new Object();
    if (mots.length == 0) {
        return null;
    }

    for (var t in mots) {
        // get the list of the indices of the files.
        var listNumerosDesFicStr = w[mots[t].toString()];
        //alert ("listNumerosDesFicStr "+listNumerosDesFicStr);
        
        if (!listNumerosDesFicStr) {
            return;
        }
        
        var tab = listNumerosDesFicStr.split(",");

        //for each file (file's index):
        for (var t2 in tab) {
            var temp = tab[t2].toString();
            if (fileAndWordList[temp] == undefined) {

                fileAndWordList[temp] = "" + mots[t];
            } else {

                fileAndWordList[temp] += "," + mots[t];
            }
        }
    }

    var fileAndWordListValuesOnly = new Array();

    // sort results according to values
    var temptab = new Array();
    for (t in fileAndWordList) {
        tab = fileAndWordList[t].split(',');

        var tempDisplay = new Array();
        for (var x in tab) {
            if(stemQueryMap[tab[x]] != undefined){
                tempDisplay.push(stemQueryMap[tab[x]]); //get the original word from the stem word.
            } else {
                tempDisplay.push(tab[x]); //no stem is available. (probably a CJK language)
            }
        }
        var tempDispString = tempDisplay.join(", ");

        temptab.push(new resultPerFile(t, fileAndWordList[t], tab.length, tempDispString));
        fileAndWordListValuesOnly.push(fileAndWordList[t]);
    }


    //alert("t"+fileAndWordListValuesOnly.toString());

    fileAndWordListValuesOnly = unique(fileAndWordListValuesOnly);
    fileAndWordListValuesOnly = fileAndWordListValuesOnly.sort(compare_nbMots);
    //alert("t: "+fileAndWordListValuesOnly.join(';'));

    var listToOutput = new Array();

    for (var j in fileAndWordListValuesOnly) {
        for (t in temptab) {
            if (temptab[t].motsliste == fileAndWordListValuesOnly[j]) {
                if (listToOutput[j] == undefined) {
                    listToOutput[j] = new Array(temptab[t]);
                } else {
                    listToOutput[j].push(temptab[t]);
                }
            }
        }
    }
    return listToOutput;
}

function resultPerFile(filenb, motsliste, motsnb, motslisteDisplay) {
    this.filenb = filenb;
    this.motsliste = motsliste;
    this.motsnb = motsnb;
    this.motslisteDisplay= motslisteDisplay;
}

function compare_nbMots(s1, s2) {
    var t1 = s1.split(',');
    var t2 = s2.split(',');
    //alert ("s1:"+t1.length + " " +t2.length)
    if (t1.length == t2.length) {
        return 0;
    } else if (t1.length > t2.length) {
        return 1;
    } else {
        return -1;
    }
    //return t1.length - t2.length);
}