aboutsummaryrefslogtreecommitdiffstats
path: root/netinstall/6/zh_CN/content/search
diff options
context:
space:
mode:
Diffstat (limited to 'netinstall/6/zh_CN/content/search')
-rw-r--r--netinstall/6/zh_CN/content/search/default.props1
-rw-r--r--netinstall/6/zh_CN/content/search/en-us.props45
-rw-r--r--netinstall/6/zh_CN/content/search/es-es.props179
-rw-r--r--netinstall/6/zh_CN/content/search/htmlFileInfoList.js2
-rw-r--r--netinstall/6/zh_CN/content/search/htmlFileList.js3
-rw-r--r--netinstall/6/zh_CN/content/search/index-1.js66
-rw-r--r--netinstall/6/zh_CN/content/search/index-2.js65
-rw-r--r--netinstall/6/zh_CN/content/search/index-3.js62
-rw-r--r--netinstall/6/zh_CN/content/search/ja-jp.props1
-rw-r--r--netinstall/6/zh_CN/content/search/nwSearchFnt.js513
-rw-r--r--netinstall/6/zh_CN/content/search/punctuation.props31
-rw-r--r--netinstall/6/zh_CN/content/search/stemmers/de_stemmer.js247
-rw-r--r--netinstall/6/zh_CN/content/search/stemmers/en_stemmer.js187
-rw-r--r--netinstall/6/zh_CN/content/search/stemmers/fr_stemmer.js299
14 files changed, 1701 insertions, 0 deletions
diff --git a/netinstall/6/zh_CN/content/search/default.props b/netinstall/6/zh_CN/content/search/default.props
new file mode 100644
index 00000000..22edf439
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/default.props
@@ -0,0 +1 @@
+DEF01=a \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/en-us.props b/netinstall/6/zh_CN/content/search/en-us.props
new file mode 100644
index 00000000..da284ce5
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/en-us.props
@@ -0,0 +1,45 @@
+DEF01=this
+DEF02=is
+DEF03=the
+DEF04=in
+DEF05=i
+DEF06=on
+DEF07=a
+DEF08=about
+DEF09=an
+DEF10=are
+DEF11=as
+DEF12=at
+DEF13=be
+DEF14=by
+DEF15=com
+DEF16=de
+DEF17=en
+DEF18=for
+DEF19=from
+DEF20=how
+DEF21=it
+DEF22=la
+DEF23=of
+DEF24=on
+DEF25=or
+DEF26=that
+DEF27=to
+DEF28=was
+DEF29=what
+DEF30=when
+DEF31=where
+DEF32=who
+DEF33=will
+DEF34=with
+DEF35=und
+DEF36=Next
+DEF37=Prev
+DEF38=Home
+DEF39=Motive
+DEF40=Inc
+DEF41=Copyright
+DEF42=All
+DEF43=rights
+DEF44=reserved
+DEF45=Up \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/es-es.props b/netinstall/6/zh_CN/content/search/es-es.props
new file mode 100644
index 00000000..fb73bdcc
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/es-es.props
@@ -0,0 +1,179 @@
+DEF01=un
+DEF02=una
+DEF03=unas
+DEF04=unos
+DEF05=uno
+DEF06=sobre
+DEF07=todo
+DEF08=tambin
+DEF09=tras
+DEF10=otro
+DEF11=algn
+DEF12=alguno
+DEF13=alguna
+DEF14=algunos
+DEF15=algunas
+DEF16=ser
+DEF17=es
+DEF18=soy
+DEF19=eres
+DEF20=somos
+DEF21=sois
+DEF22=estoy
+DEF23=esta
+DEF24=estamos
+DEF25=estais
+DEF26=estan
+DEF27=como
+DEF28=en
+DEF29=para
+DEF30=atras
+DEF31=porque
+DEF32=por
+DEF33=estado
+DEF34=estaba
+DEF35=ante
+DEF36=antes
+DEF37=siendo
+DEF38=ambos
+DEF39=pero
+DEF40=por
+DEF41=poder
+DEF42=puede
+DEF43=puedo
+DEF44=podemos
+DEF45=podeis
+DEF46=pueden
+DEF47=fui
+DEF48=fue
+DEF49=fuimos
+DEF50=fueron
+DEF51=hacer
+DEF52=hago
+DEF53=hace
+DEF54=hacemos
+DEF55=haceis
+DEF56=hacen
+DEF57=cada
+DEF58=fin
+DEF59=incluso
+DEF60=primero
+DEF61=desde
+DEF62=conseguir
+DEF63=consigo
+DEF64=consigue
+DEF65=consigues
+DEF66=conseguimos
+DEF67=consiguen
+DEF68=ir
+DEF69=voy
+DEF70=va
+DEF71=vamos
+DEF72=vais
+DEF73=van
+DEF74=vaya
+DEF75=gueno
+DEF76=ha
+DEF77=tener
+DEF78=tengo
+DEF79=tiene
+DEF80=tenemos
+DEF81=teneis
+DEF82=tienen
+DEF83=el
+DEF84=la
+DEF85=lo
+DEF86=las
+DEF87=los
+DEF88=su
+DEF89=aqui
+DEF90=mio
+DEF91=tuyo
+DEF92=ellos
+DEF93=ellas
+DEF94=nos
+DEF95=nosotros
+DEF96=vosotros
+DEF97=vosotras
+DEF98=si
+DEF99=dentro
+DEF100=solo
+DEF101=solamente
+DEF102=saber
+DEF103=sabes
+DEF104=sabe
+DEF105=sabemos
+DEF106=sabeis
+DEF107=saben
+DEF108=ultimo
+DEF109=largo
+DEF110=bastante
+DEF111=haces
+DEF112=muchos
+DEF113=aquellos
+DEF114=aquellas
+DEF115=sus
+DEF116=entonces
+DEF117=tiempo
+DEF118=verdad
+DEF119=verdadero
+DEF120=verdadera
+DEF121=cierto
+DEF122=ciertos
+DEF123=cierta
+DEF124=ciertas
+DEF125=intentar
+DEF126=intento
+DEF127=intenta
+DEF128=intentas
+DEF129=intentamos
+DEF130=intentais
+DEF131=intentan
+DEF132=dos
+DEF133=bajo
+DEF134=arriba
+DEF135=encima
+DEF136=usar
+DEF137=uso
+DEF138=usas
+DEF139=usa
+DEF140=usamos
+DEF141=usais
+DEF142=usan
+DEF143=emplear
+DEF144=empleo
+DEF145=empleas
+DEF146=emplean
+DEF147=ampleamos
+DEF148=empleais
+DEF149=valor
+DEF150=muy
+DEF151=era
+DEF152=eras
+DEF153=eramos
+DEF154=eran
+DEF155=modo
+DEF156=bien
+DEF157=cual
+DEF158=cuando
+DEF159=donde
+DEF160=mientras
+DEF161=quien
+DEF162=con
+DEF163=entre
+DEF164=sin
+DEF165=trabajo
+DEF166=trabajar
+DEF167=trabajas
+DEF168=trabaja
+DEF169=trabajamos
+DEF170=trabajais
+DEF171=trabajan
+DEF172=podria
+DEF173=podrias
+DEF174=podriamos
+DEF175=podrian
+DEF176=podriais
+DEF177=yo
+DEF178=aquel
+DEF179=qu \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/htmlFileInfoList.js b/netinstall/6/zh_CN/content/search/htmlFileInfoList.js
new file mode 100644
index 00000000..4aad3b4f
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/htmlFileInfoList.js
@@ -0,0 +1,2 @@
+fil = new Array();
+fil["0"]= "SOME_UNIQUE_ID.html@@@使用微型引导镜像来安装@@@null";
diff --git a/netinstall/6/zh_CN/content/search/htmlFileList.js b/netinstall/6/zh_CN/content/search/htmlFileList.js
new file mode 100644
index 00000000..6b6ccc3e
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/htmlFileList.js
@@ -0,0 +1,3 @@
+//List of files which are indexed.
+fl = new Array();
+fl["0"]= "SOME_UNIQUE_ID.html";
diff --git a/netinstall/6/zh_CN/content/search/index-1.js b/netinstall/6/zh_CN/content/search/index-1.js
new file mode 100644
index 00000000..4c9ebc41
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/index-1.js
@@ -0,0 +1,66 @@
+var indexerLanguage="en";
+//Auto generated index for searching.
+w["-"]="0";
+w["-netinstall-"]="0";
+w["-netinstall-nonfree-"]="0";
+w["-sa"]="0";
+w["0"]="0";
+w["1"]="0";
+w["1，您需要输入相关参数"]="0";
+w["2"]="0";
+w["2："]="0";
+w["3"]="0";
+w["5"]="0";
+w["alt"]="0";
+w["bio"]="0";
+w["boot"]="0";
+w["boot-nonfre"]="0";
+w["cauldron"]="0";
+w["cc"]="0";
+w["cd"]="0";
+w["content"]="0";
+w["ctrl"]="0";
+w["del"]="0";
+w["del；按"]="0";
+w["dhcp"]="0";
+w["distrib"]="0";
+w["doc"]="0";
+w["drakx"]="0";
+w["dvd"]="0";
+w["f1"]="0";
+w["f2"]="0";
+w["f3"]="0";
+w["f7"]="0";
+w["ftp"]="0";
+w["here"]="0";
+w["html"]="0";
+w["http"]="0";
+w["i586"]="0";
+w["imag"]="0";
+w["instal"]="0";
+w["install，然后按"]="0";
+w["iso"]="0";
+w["iso（也叫"]="0";
+w["iso）包含了额外的私有驱动，用于您的网络设备"]="0";
+w["iso）是仅包含启动"]="0";
+w["linux"]="0";
+w["livecd"]="0";
+w["mageia"]="0";
+w["mageia-"]="0";
+w["mageia（不支持加密无线网或蓝牙网络）"]="0";
+w["mbr"]="0";
+w["mirror"]="0";
+w["n"]="0";
+w["n（从列表中选择一个镜像）"]="0";
+w["ok，然后按"]="0";
+w["org"]="0";
+w["pub"]="0";
+w["rsync"]="0";
+w["selectlanguag"]="0";
+w["stage"]="0";
+w["start"]="0";
+w["tab"]="0";
+w["tty2"]="0";
+w["u"]="0";
+w["uefi"]="0";
+
diff --git a/netinstall/6/zh_CN/content/search/index-2.js b/netinstall/6/zh_CN/content/search/index-2.js
new file mode 100644
index 00000000..318e474a
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/index-2.js
@@ -0,0 +1,65 @@
+//Auto generated index for searching.
+w["x86_64"]="0";
+w["zh_cn"]="0";
+w[" "]="0";
+w["©"]="0";
+w["上的"]="0";
+w["上；如果您希望使用"]="0";
+w["与从"]="0";
+w["中的描述相同"]="0";
+w["中选择了哪个服务器，它的目录结构都应该与"]="0";
+w["中，引导器不会向您的硬盘写入任何数据，所以您可以随时按下"]="0";
+w["为"]="0";
+w["之后，将会安装并启动"]="0";
+w["从硬盘安装"]="0";
+w["代理"]="0";
+w["以便继续和完成安装过程"]="0";
+w["以及相应的分区"]="0";
+w["使用"]="0";
+w["使用微型引导镜像来安装"]="0";
+w["使用方向键来上下移动至需要选择的项目"]="0";
+w["使用方向键来选择"]="0";
+w["光盘上的"]="0";
+w["其他镜像的目录结构可能稍有不同，下列截图给出了示例："]="0";
+w["分区格式）引导计算机"]="0";
+w["发行版，则应当如下："]="0";
+w["可以用于通过有线"]="0";
+w["可以返回到安装界面"]="0";
+w["同时用这两种模式引导计算机"]="0";
+w["和"]="0";
+w["回到安装界面"]="0";
+w["回车"]="0";
+w["回车键"]="0";
+w["在"]="0";
+w["在下载镜像之后，您可以将其刻录到"]="0";
+w["在开始前"]="0";
+w["在线软件源（或本地镜像）"]="0";
+w["在选择"]="0";
+w["如果您不知道如何设置：请将其留空，然后选择“ok”"]="0";
+w["如果您不知道如何选择"]="0";
+w["如果您不知道如何选择，请选择"]="0";
+w["如果您从硬盘或"]="0";
+w["如果您使用的不是美式键盘，可能会在输入时遇到麻烦"]="0";
+w["如果您在后续的安装过程中遇到大量依赖缺失的问题，请重启并改用其他镜像"]="0";
+w["如果您手动指定了镜像，则必须输入某个媒体的路径"]="0";
+w["如果您没有做出选择，引导起将会以默认设置启动系统"]="0";
+w["如果您选择"]="0";
+w["如果您需要重启，请按"]="0";
+w["安装"]="0";
+w["安装不同，在网络安装的第一步——"]="0";
+w["安装器所必须的文件的安装镜像，drakx"]="0";
+w["官方镜像中的“mageia”目录一致，即"]="0";
+w["对于"]="0";
+w["对于企业网络而言，ftp"]="0";
+w["将在启动后查找："]="0";
+w["局域网（本地网络）上的"]="0";
+w["布局，如果您需要输入名称和路径，这可能会造成一些麻烦"]="0";
+w["您也可以从"]="0";
+w["您可以在"]="0";
+w["您可以将其留空，或者指定目录名，这样便于您从安装器提供的文件列表中做出选择：只需使用方向键来上下移动"]="0";
+w["您可以按"]="0";
+w["您将会看到如下界面："]="0";
+w["或"]="0";
+w["所列出的镜像服务器中下载它们"]="0";
+w["手动指定镜像"]="0";
+
diff --git a/netinstall/6/zh_CN/content/search/index-3.js b/netinstall/6/zh_CN/content/search/index-3.js
new file mode 100644
index 00000000..f347f376
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/index-3.js
@@ -0,0 +1,62 @@
+//Auto generated index for searching.
+w["按"]="0";
+w["按回车键确认即可，如第二张截图所示"]="0";
+w["文件的存放位置"]="0";
+w["文件的文件名"]="0";
+w["无论您在列表"]="0";
+w["服务可能会被封锁，在这种情况下您最好使用"]="0";
+w["服务器"]="0";
+w["服务器后，您将会看到用于输入登录名和密码的界面（如果需要的话）"]="0";
+w["服务器："]="0";
+w["未加密无线网络来安装"]="0";
+w["本地"]="0";
+w["来安全退出这一阶段"]="0";
+w["来越多高级选项的帮助，然后按"]="0";
+w["来返回安装界面"]="0";
+w["来阅读引导日志，然后按"]="0";
+w["架构"]="0";
+w["概要"]="0";
+w["模式引导计算机"]="0";
+w["模式（也叫"]="0";
+w["此处"]="0";
+w["此时您的键盘将暂时处于"]="0";
+w["注意"]="0";
+w["然后指定目录或"]="0";
+w["版本"]="0";
+w["版本号"]="0";
+w["盘"]="0";
+w["盘安装系统，请看下面的内容"]="0";
+w["盘安装，您必须知道"]="0";
+w["盘来安装，请参考"]="0";
+w["盘）"]="0";
+w["目录”字段的正确格式应当如下："]="0";
+w["硬盘"]="0";
+w["磁盘控制器或其他设备"]="0";
+w["第一个界面中提示您“请选择需要使用的语言”，此时安装器尚未写入数据到您的硬盘"]="0";
+w["第一个窗口如下图所示"]="0";
+w["系统启动前，您可以按"]="0";
+w["终端，然后按"]="0";
+w["网络安装的渠道，请选择"]="0";
+w["美式键盘"]="0";
+w["若您不确定如何选择，请将其留空"]="0";
+w["若您有多个网卡，请从中选择合适的网卡"]="0";
+w["若要从硬盘或"]="0";
+w["警告"]="0";
+w["设置主机名和域名"]="0";
+w["请点击上述链接来继续阅读安装指南；您也可以将链接中的“5”替换成其他您需要了解的"]="0";
+w["转到"]="0";
+w["这一步也叫"]="0";
+w["这一阶段的安装与"]="0";
+w["这两种镜像"]="0";
+w["这是第二阶段安装的界面，请参见下面的"]="0";
+w["这里的“网络安装”分类下找到"]="0";
+w["选择“mageia”之后，您可以用方向键在列表中选择特定类型的引导项"]="0";
+w["选择一个媒体"]="0";
+w["选择安装方式"]="0";
+w["选择网络连接类型"]="0";
+w["键将焦点移动至"]="0";
+w["镜像"]="0";
+w["镜像文件位于"]="0";
+w["首先，请选择您的硬盘（或"]="0";
+w["（使用官方镜像时）“mageia"]="0";
+
diff --git a/netinstall/6/zh_CN/content/search/ja-jp.props b/netinstall/6/zh_CN/content/search/ja-jp.props
new file mode 100644
index 00000000..27568054
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/ja-jp.props
@@ -0,0 +1 @@
+J01=\\u306B \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/nwSearchFnt.js b/netinstall/6/zh_CN/content/search/nwSearchFnt.js
new file mode 100644
index 00000000..0111559c
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/nwSearchFnt.js
@@ -0,0 +1,513 @@
+/*----------------------------------------------------------------------------
+ * 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) {
+
+ //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>" + "Your search returned 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);
+ 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);
+} \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/punctuation.props b/netinstall/6/zh_CN/content/search/punctuation.props
new file mode 100644
index 00000000..d3e3fcd2
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/punctuation.props
@@ -0,0 +1,31 @@
+Punct01=\\u3002
+Punct02=\\u3003
+Punct03=\\u300C
+Punct04=\\u300D
+Punct05=\\u300E
+Punct06=\\u300F
+Punct07=\\u301D
+Punct08=\\u301E
+Punct09=\\u301F
+Punct10=\\u309B
+Punct11=\\u2018
+Punct12=\\u2019
+Punct13=\\u201A
+Punct14=\\u201C
+Punct15=\\u201D
+Punct16=\\u201E
+Punct17=\\u2032
+Punct18=\\u2033
+Punct19=\\u2035
+Punct20=\\u2039
+Punct21=\\u203A
+Punct22=\\u201E
+Punct23=\\u00BB
+Punct24=\\u00AB
+Punct25=
+Punct26=
+Punct27=\\u00A0
+Punct28=\\u2014
+
+
+
diff --git a/netinstall/6/zh_CN/content/search/stemmers/de_stemmer.js b/netinstall/6/zh_CN/content/search/stemmers/de_stemmer.js
new file mode 100644
index 00000000..7ff3822a
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/stemmers/de_stemmer.js
@@ -0,0 +1,247 @@
+/*
+ * Author: Joder Illi
+ *
+ * Copyright (c) 2010, FormBlitz AG
+ * All rights reserved.
+ * Implementation of the stemming algorithm from http://snowball.tartarus.org/algorithms/german/stemmer.html
+ * Copyright of the algorithm is: Copyright (c) 2001, Dr Martin Porter and can be found at http://snowball.tartarus.org/license.php
+ *
+ * Redistribution and use in source and binary forms, with or without modification, is covered by the standard BSD license.
+ *
+ */
+
+//var stemmer = function Stemmer() {
+ /*
+ German includes the following accented forms,
+ ä ö ü
+ and a special letter, ß, equivalent to double s.
+ The following letters are vowels:
+ a e i o u y ä ö ü
+ */
+
+ var stemmer = function(word) {
+ /*
+ Put u and y between vowels into upper case
+ */
+ word = word.replace(/([aeiouyäöü])u([aeiouyäöü])/g, '$1U$2');
+ word = word.replace(/([aeiouyäöü])y([aeiouyäöü])/g, '$1Y$2');
+
+ /*
+ and then do the following mappings,
+ (a) replace ß with ss,
+ (a) replace ae with ä, Not doing these, have trouble with diphtongs
+ (a) replace oe with ö, Not doing these, have trouble with diphtongs
+ (a) replace ue with ü unless preceded by q. Not doing these, have trouble with diphtongs
+ So in quelle, ue is not mapped to ü because it follows q, and in feuer it is not mapped because the first part of the rule changes it to feUer, so the u is not found.
+ */
+ word = word.replace(/ß/g, 'ss');
+ //word = word.replace(/ae/g, 'ä');
+ //word = word.replace(/oe/g, 'ö');
+ //word = word.replace(/([^q])ue/g, '$1ü');
+
+ /*
+ R1 and R2 are first set up in the standard way (see the note on R1 and R2), but then R1 is adjusted so that the region before it contains at least 3 letters.
+ R1 is the region after the first non-vowel following a vowel, or is the null region at the end of the word if there is no such non-vowel.
+ R2 is the region after the first non-vowel following a vowel in R1, or is the null region at the end of the word if there is no such non-vowel.
+ */
+
+ var r1Index = word.search(/[aeiouyäöü][^aeiouyäöü]/);
+ var r1 = '';
+ if (r1Index != -1) {
+ r1Index += 2;
+ r1 = word.substring(r1Index);
+ }
+
+ var r2Index = -1;
+ var r2 = '';
+
+ if (r1Index != -1) {
+ var r2Index = r1.search(/[aeiouyäöü][^aeiouyäöü]/);
+ if (r2Index != -1) {
+ r2Index += 2;
+ r2 = r1.substring(r2Index);
+ r2Index += r1Index;
+ } else {
+ r2 = '';
+ }
+ }
+
+ if (r1Index != -1 && r1Index < 3) {
+ r1Index = 3;
+ r1 = word.substring(r1Index);
+ }
+
+ /*
+ Define a valid s-ending as one of b, d, f, g, h, k, l, m, n, r or t.
+ Define a valid st-ending as the same list, excluding letter r.
+ */
+
+ /*
+ Do each of steps 1, 2 and 3.
+ */
+
+ /*
+ Step 1:
+ Search for the longest among the following suffixes,
+ (a) em ern er
+ (b) e en es
+ (c) s (preceded by a valid s-ending)
+ */
+ var a1Index = word.search(/(em|ern|er)$/g);
+ var b1Index = word.search(/(e|en|es)$/g);
+ var c1Index = word.search(/([bdfghklmnrt]s)$/g);
+ if (c1Index != -1) {
+ c1Index++;
+ }
+ var index1 = 10000;
+ var optionUsed1 = '';
+ if (a1Index != -1 && a1Index < index1) {
+ optionUsed1 = 'a';
+ index1 = a1Index;
+ }
+ if (b1Index != -1 && b1Index < index1) {
+ optionUsed1 = 'b';
+ index1 = b1Index;
+ }
+ if (c1Index != -1 && c1Index < index1) {
+ optionUsed1 = 'c';
+ index1 = c1Index;
+ }
+
+ /*
+ and delete if in R1. (Of course the letter of the valid s-ending is not necessarily in R1.) If an ending of group (b) is deleted, and the ending is preceded by niss, delete the final s.
+ (For example, äckern -> äck, ackers -> acker, armes -> arm, bedürfnissen -> bedürfnis)
+ */
+
+ if (index1 != 10000 && r1Index != -1) {
+ if (index1 >= r1Index) {
+ word = word.substring(0, index1);
+ if (optionUsed1 == 'b') {
+ if (word.search(/niss$/) != -1) {
+ word = word.substring(0, word.length -1);
+ }
+ }
+ }
+ }
+ /*
+ Step 2:
+ Search for the longest among the following suffixes,
+ (a) en er est
+ (b) st (preceded by a valid st-ending, itself preceded by at least 3 letters)
+ */
+
+ var a2Index = word.search(/(en|er|est)$/g);
+ var b2Index = word.search(/(.{3}[bdfghklmnt]st)$/g);
+ if (b2Index != -1) {
+ b2Index += 4;
+ }
+
+ var index2 = 10000;
+ var optionUsed2 = '';
+ if (a2Index != -1 && a2Index < index2) {
+ optionUsed2 = 'a';
+ index2 = a2Index;
+ }
+ if (b2Index != -1 && b2Index < index2) {
+ optionUsed2 = 'b';
+ index2 = b2Index;
+ }
+
+ /*
+ and delete if in R1.
+ (For example, derbsten -> derbst by step 1, and derbst -> derb by step 2, since b is a valid st-ending, and is preceded by just 3 letters)
+ */
+
+ if (index2 != 10000 && r1Index != -1) {
+ if (index2 >= r1Index) {
+ word = word.substring(0, index2);
+ }
+ }
+
+ /*
+ Step 3: d-suffixes (*)
+ Search for the longest among the following suffixes, and perform the action indicated.
+ end ung
+ delete if in R2
+ if preceded by ig, delete if in R2 and not preceded by e
+ ig ik isch
+ delete if in R2 and not preceded by e
+ lich heit
+ delete if in R2
+ if preceded by er or en, delete if in R1
+ keit
+ delete if in R2
+ if preceded by lich or ig, delete if in R2
+ */
+
+ var a3Index = word.search(/(end|ung)$/g);
+ var b3Index = word.search(/[^e](ig|ik|isch)$/g);
+ var c3Index = word.search(/(lich|heit)$/g);
+ var d3Index = word.search(/(keit)$/g);
+ if (b3Index != -1) {
+ b3Index ++;
+ }
+
+ var index3 = 10000;
+ var optionUsed3 = '';
+ if (a3Index != -1 && a3Index < index3) {
+ optionUsed3 = 'a';
+ index3 = a3Index;
+ }
+ if (b3Index != -1 && b3Index < index3) {
+ optionUsed3 = 'b';
+ index3 = b3Index;
+ }
+ if (c3Index != -1 && c3Index < index3) {
+ optionUsed3 = 'c';
+ index3 = c3Index;
+ }
+ if (d3Index != -1 && d3Index < index3) {
+ optionUsed3 = 'd';
+ index3 = d3Index;
+ }
+
+ if (index3 != 10000 && r2Index != -1) {
+ if (index3 >= r2Index) {
+ word = word.substring(0, index3);
+ var optionIndex = -1;
+ var optionSubsrt = '';
+ if (optionUsed3 == 'a') {
+ optionIndex = word.search(/[^e](ig)$/);
+ if (optionIndex != -1) {
+ optionIndex++;
+ if (optionIndex >= r2Index) {
+ word = word.substring(0, optionIndex);
+ }
+ }
+ } else if (optionUsed3 == 'c') {
+ optionIndex = word.search(/(er|en)$/);
+ if (optionIndex != -1) {
+ if (optionIndex >= r1Index) {
+ word = word.substring(0, optionIndex);
+ }
+ }
+ } else if (optionUsed3 == 'd') {
+ optionIndex = word.search(/(lich|ig)$/);
+ if (optionIndex != -1) {
+ if (optionIndex >= r2Index) {
+ word = word.substring(0, optionIndex);
+ }
+ }
+ }
+ }
+ }
+
+ /*
+ Finally,
+ turn U and Y back into lower case, and remove the umlaut accent from a, o and u.
+ */
+ word = word.replace(/U/g, 'u');
+ word = word.replace(/Y/g, 'y');
+ word = word.replace(/ä/g, 'a');
+ word = word.replace(/ö/g, 'o');
+ word = word.replace(/ü/g, 'u');
+
+ return word;
+ };
+//} \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/stemmers/en_stemmer.js b/netinstall/6/zh_CN/content/search/stemmers/en_stemmer.js
new file mode 100644
index 00000000..f58012f2
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/stemmers/en_stemmer.js
@@ -0,0 +1,187 @@
+// Porter stemmer in Javascript. Few comments, but it's easy to follow against the rules in the original
+// paper, in
+//
+// Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
+// no. 3, pp 130-137,
+//
+// see also http://www.tartarus.org/~martin/PorterStemmer
+
+// Release 1 be 'andargor', Jul 2004
+// Release 2 (substantially revised) by Christopher McKenzie, Aug 2009
+
+
+var stemmer = (function(){
+ var step2list = {
+ "ational" : "ate",
+ "tional" : "tion",
+ "enci" : "ence",
+ "anci" : "ance",
+ "izer" : "ize",
+ "bli" : "ble",
+ "alli" : "al",
+ "entli" : "ent",
+ "eli" : "e",
+ "ousli" : "ous",
+ "ization" : "ize",
+ "ation" : "ate",
+ "ator" : "ate",
+ "alism" : "al",
+ "iveness" : "ive",
+ "fulness" : "ful",
+ "ousness" : "ous",
+ "aliti" : "al",
+ "iviti" : "ive",
+ "biliti" : "ble",
+ "logi" : "log"
+ },
+
+ step3list = {
+ "icate" : "ic",
+ "ative" : "",
+ "alize" : "al",
+ "iciti" : "ic",
+ "ical" : "ic",
+ "ful" : "",
+ "ness" : ""
+ },
+
+ c = "[^aeiou]", // consonant
+ v = "[aeiouy]", // vowel
+ C = c + "[^aeiouy]*", // consonant sequence
+ V = v + "[aeiou]*", // vowel sequence
+
+ mgr0 = "^(" + C + ")?" + V + C, // [C]VC... is m>0
+ meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$", // [C]VC[V] is m=1
+ mgr1 = "^(" + C + ")?" + V + C + V + C, // [C]VCVC... is m>1
+ s_v = "^(" + C + ")?" + v; // vowel in stem
+
+ return function (w) {
+ var stem,
+ suffix,
+ firstch,
+ re,
+ re2,
+ re3,
+ re4,
+ origword = w;
+
+ if (w.length < 3) { return w; }
+
+ firstch = w.substr(0,1);
+ if (firstch == "y") {
+ w = firstch.toUpperCase() + w.substr(1);
+ }
+
+ // Step 1a
+ re = /^(.+?)(ss|i)es$/;
+ re2 = /^(.+?)([^s])s$/;
+
+ if (re.test(w)) { w = w.replace(re,"$1$2"); }
+ else if (re2.test(w)) { w = w.replace(re2,"$1$2"); }
+
+ // Step 1b
+ re = /^(.+?)eed$/;
+ re2 = /^(.+?)(ed|ing)$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ re = new RegExp(mgr0);
+ if (re.test(fp[1])) {
+ re = /.$/;
+ w = w.replace(re,"");
+ }
+ } else if (re2.test(w)) {
+ var fp = re2.exec(w);
+ stem = fp[1];
+ re2 = new RegExp(s_v);
+ if (re2.test(stem)) {
+ w = stem;
+ re2 = /(at|bl|iz)$/;
+ re3 = new RegExp("([^aeiouylsz])\\1$");
+ re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
+ if (re2.test(w)) { w = w + "e"; }
+ else if (re3.test(w)) { re = /.$/; w = w.replace(re,""); }
+ else if (re4.test(w)) { w = w + "e"; }
+ }
+ }
+
+ // Step 1c
+ re = /^(.+?)y$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ stem = fp[1];
+ re = new RegExp(s_v);
+ if (re.test(stem)) { w = stem + "i"; }
+ }
+
+ // Step 2
+ re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ stem = fp[1];
+ suffix = fp[2];
+ re = new RegExp(mgr0);
+ if (re.test(stem)) {
+ w = stem + step2list[suffix];
+ }
+ }
+
+ // Step 3
+ re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ stem = fp[1];
+ suffix = fp[2];
+ re = new RegExp(mgr0);
+ if (re.test(stem)) {
+ w = stem + step3list[suffix];
+ }
+ }
+
+ // Step 4
+ re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
+ re2 = /^(.+?)(s|t)(ion)$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ stem = fp[1];
+ re = new RegExp(mgr1);
+ if (re.test(stem)) {
+ w = stem;
+ }
+ } else if (re2.test(w)) {
+ var fp = re2.exec(w);
+ stem = fp[1] + fp[2];
+ re2 = new RegExp(mgr1);
+ if (re2.test(stem)) {
+ w = stem;
+ }
+ }
+
+ // Step 5
+ re = /^(.+?)e$/;
+ if (re.test(w)) {
+ var fp = re.exec(w);
+ stem = fp[1];
+ re = new RegExp(mgr1);
+ re2 = new RegExp(meq1);
+ re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
+ if (re.test(stem) || (re2.test(stem) && !(re3.test(stem)))) {
+ w = stem;
+ }
+ }
+
+ re = /ll$/;
+ re2 = new RegExp(mgr1);
+ if (re.test(w) && re2.test(w)) {
+ re = /.$/;
+ w = w.replace(re,"");
+ }
+
+ // and turn initial Y back to y
+
+ if (firstch == "y") {
+ w = firstch.toLowerCase() + w.substr(1);
+ }
+
+ return w;
+ }
+})(); \ No newline at end of file
diff --git a/netinstall/6/zh_CN/content/search/stemmers/fr_stemmer.js b/netinstall/6/zh_CN/content/search/stemmers/fr_stemmer.js
new file mode 100644
index 00000000..34f97431
--- /dev/null
+++ b/netinstall/6/zh_CN/content/search/stemmers/fr_stemmer.js
@@ -0,0 +1,299 @@
+/*
+ * Author: Kasun Gajasinghe
+ * E-Mail: kasunbg AT gmail DOT com
+ * Date: 09.08.2010
+ *
+ * usage: stemmer(word);
+ * ex: var stem = stemmer(foobar);
+ * Implementation of the stemming algorithm from http://snowball.tartarus.org/algorithms/french/stemmer.html
+ *
+ * LICENSE:
+ *
+ * Copyright (c) 2010, Kasun Gajasinghe. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without modification,
+ * are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ *
+ * THIS SOFTWARE IS PROVIDED BY KASUN GAJASINGHE ''AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
+ * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL KASUN GAJASINGHE BE LIABLE FOR ANY DIRECT,
+ * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
+ * USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+var stemmer = function(word){
+// Letters in French include the following accented forms,
+// â à ç ë é ê è ï î ô û ù
+// The following letters are vowels:
+// a e i o u y â à ë é ê è ï î ô û ù
+
+ word = word.toLowerCase();
+ var oriWord = word;
+ word = word.replace(/qu/g, 'qU'); //have to perform first, as after the operation, capital U is not treated as a vowel
+ word = word.replace(/([aeiouyâàëéêèïîôûù])u([aeiouyâàëéêèïîôûù])/g, '$1U$2');
+ word = word.replace(/([aeiouyâàëéêèïîôûù])i([aeiouyâàëéêèïîôûù])/g, '$1I$2');
+ word = word.replace(/([aeiouyâàëéêèïîôûù])y/g, '$1Y');
+ word = word.replace(/y([aeiouyâàëéêèïîôûù])/g, 'Y$1');
+
+ var rv='';
+ var rvIndex = -1;
+ if(word.search(/^(par|col|tap)/) != -1 || word.search(/^[aeiouyâàëéêèïîôûù]{2}/) != -1){
+ rv = word.substring(3);
+ rvIndex = 3;
+ } else {
+ rvIndex = word.substring(1).search(/[aeiouyâàëéêèïîôûù]/);
+ if(rvIndex != -1){
+ rvIndex +=2; //+2 is to supplement the substring(1) used to find rvIndex
+ rv = word.substring(rvIndex);
+ } else {
+ rvIndex = word.length;
+ }
+ }
+
+// R1 is the region after the first non-vowel following a vowel, or the end of the word if there is no such non-vowel.
+// R2 is the region after the first non-vowel following a vowel in R1, or the end of the word if there is no such non-vowel
+ var r1Index = word.search(/[aeiouyâàëéêèïîôûù][^aeiouyâàëéêèïîôûù]/);
+ var r1 = '';
+ if (r1Index != -1) {
+ r1Index += 2;
+ r1 = word.substring(r1Index);
+ } else {
+ r1Index = word.length;
+ }
+
+ var r2Index = -1;
+ var r2 = '';
+ if (r1Index != -1) {
+ r2Index = r1.search(/[aeiouyâàëéêèïîôûù][^aeiouyâàëéêèïîôûù]/);
+ if (r2Index != -1) {
+ r2Index += 2;
+ r2 = r1.substring(r2Index);
+ r2Index += r1Index;
+ } else {
+ r2 = '';
+ r2Index = word.length;
+ }
+ }
+ if (r1Index != -1 && r1Index < 3) {
+ r1Index = 3;
+ r1 = word.substring(r1Index);
+ }
+
+ /*
+ Step 1: Standard suffix removal
+ */
+ var a1Index = word.search(/(ance|iqUe|isme|able|iste|eux|ances|iqUes|ismes|ables|istes)$/);
+ var a2Index = word.search(/(atrice|ateur|ation|atrices|ateurs|ations)$/);
+ var a3Index = word.search(/(logie|logies)$/);
+ var a4Index = word.search(/(usion|ution|usions|utions)$/);
+ var a5Index = word.search(/(ence|ences)$/);
+ var a6Index = word.search(/(ement|ements)$/);
+ var a7Index = word.search(/(ité|ités)$/);
+ var a8Index = word.search(/(if|ive|ifs|ives)$/);
+ var a9Index = word.search(/(eaux)$/);
+ var a10Index = word.search(/(aux)$/);
+ var a11Index = word.search(/(euse|euses)$/);
+ var a12Index = word.search(/[^aeiouyâàëéêèïîôûù](issement|issements)$/);
+ var a13Index = word.search(/(amment)$/);
+ var a14Index = word.search(/(emment)$/);
+ var a15Index = word.search(/[aeiouyâàëéêèïîôûù](ment|ments)$/);
+
+ if(a1Index != -1 && a1Index >= r2Index){
+ word = word.substring(0,a1Index);
+ } else if(a2Index != -1 && a2Index >= r2Index){
+ word = word.substring(0,a2Index);
+ var a2Index2 = word.search(/(ic)$/);
+ if(a2Index2 != -1 && a2Index2 >= r2Index){
+ word = word.substring(0, a2Index2); //if preceded by ic, delete if in R2,
+ } else { //else replace by iqU
+ word = word.replace(/(ic)$/,'iqU');
+ }
+ } else if(a3Index != -1 && a3Index >= r2Index){
+ word = word.replace(/(logie|logies)$/,'log'); //replace with log if in R2
+ } else if(a4Index != -1 && a4Index >= r2Index){
+ word = word.replace(/(usion|ution|usions|utions)$/,'u'); //replace with u if in R2
+ } else if(a5Index != -1 && a5Index >= r2Index){
+ word = word.replace(/(ence|ences)$/,'ent'); //replace with ent if in R2
+ } else if(a6Index != -1 && a6Index >= rvIndex){
+ word = word.substring(0,a6Index);
+ if(word.search(/(iv)$/) >= r2Index){
+ word = word.replace(/(iv)$/, '');
+ if(word.search(/(at)$/) >= r2Index){
+ word = word.replace(/(at)$/, '');
+ }
+ } else if(word.search(/(eus)$/) != -1){
+ var a6Index2 = word.search(/(eus)$/);
+ if(a6Index2 >=r2Index){
+ word = word.substring(0, a6Index2);
+ } else if(a6Index2 >= r1Index){
+ word = word.substring(0,a6Index2)+"eux";
+ }
+ } else if(word.search(/(abl|iqU)$/) >= r2Index){
+ word = word.replace(/(abl|iqU)$/,''); //if preceded by abl or iqU, delete if in R2,
+ } else if(word.search(/(ièr|Ièr)$/) >= rvIndex){
+ word = word.replace(/(ièr|Ièr)$/,'i'); //if preceded by abl or iqU, delete if in R2,
+ }
+ } else if(a7Index != -1 && a7Index >= r2Index){
+ word = word.substring(0,a7Index); //delete if in R2
+ if(word.search(/(abil)$/) != -1){ //if preceded by abil, delete if in R2, else replace by abl, otherwise,
+ var a7Index2 = word.search(/(abil)$/);
+ if(a7Index2 >=r2Index){
+ word = word.substring(0, a7Index2);
+ } else {
+ word = word.substring(0,a7Index2)+"abl";
+ }
+ } else if(word.search(/(ic)$/) != -1){
+ var a7Index3 = word.search(/(ic)$/);
+ if(a7Index3 != -1 && a7Index3 >= r2Index){
+ word = word.substring(0, a7Index3); //if preceded by ic, delete if in R2,
+ } else { //else replace by iqU
+ word = word.replace(/(ic)$/,'iqU');
+ }
+ } else if(word.search(/(iv)$/) != r2Index){
+ word = word.replace(/(iv)$/,'');
+ }
+ } else if(a8Index != -1 && a8Index >= r2Index){
+ word = word.substring(0,a8Index);
+ if(word.search(/(at)$/) >= r2Index){
+ word = word.replace(/(at)$/, '');
+ if(word.search(/(ic)$/) >= r2Index){
+ word = word.replace(/(ic)$/, '');
+ } else { word = word.replace(/(ic)$/, 'iqU'); }
+ }
+ } else if(a9Index != -1){ word = word.replace(/(eaux)/,'eau')
+ } else if(a10Index >= r1Index){ word = word.replace(/(aux)/,'al')
+ } else if(a11Index != -1 ){
+ var a11Index2 = word.search(/(euse|euses)$/);
+ if(a11Index2 >=r2Index){
+ word = word.substring(0, a11Index2);
+ } else if(a11Index2 >= r1Index){
+ word = word.substring(0, a11Index2)+"eux";
+ }
+ } else if(a12Index!=-1 && a12Index>=r1Index){
+ word = word.substring(0,a12Index+1); //+1- amendment to non-vowel
+ } else if(a13Index!=-1 && a13Index>=rvIndex){
+ word = word.replace(/(amment)$/,'ant');
+ } else if(a14Index!=-1 && a14Index>=rvIndex){
+ word = word.replace(/(emment)$/,'ent');
+ } else if(a15Index!=-1 && a15Index>=rvIndex){
+ word = word.substring(0,a15Index+1);
+ }
+
+ /* Step 2a: Verb suffixes beginning i*/
+ var wordStep1 = word;
+ var step2aDone = false;
+ if(oriWord == word.toLowerCase() || oriWord.search(/(amment|emment|ment|ments)$/) != -1){
+ step2aDone = true;
+ var b1Regex = /([^aeiouyâàëéêèïîôûù])(îmes|ît|îtes|i|ie|ies|ir|ira|irai|iraIent|irais|irait|iras|irent|irez|iriez|irions|irons|iront|is|issaIent|issais|issait|issant|issante|issantes|issants|isse|issent|isses|issez|issiez|issions|issons|it)$/i;
+ if(word.search(b1Regex) >= rvIndex){
+ word = word.replace(b1Regex,'$1');
+ }
+ }
+
+ /* Step 2b: Other verb suffixes*/
+ if (step2aDone && wordStep1 == word) {
+ if (word.search(/(ions)$/) >= r2Index) {
+ word = word.replace(/(ions)$/, '');
+ } else {
+ var b2Regex = /(é|ée|ées|és|èrent|er|era|erai|eraIent|erais|erait|eras|erez|eriez|erions|erons|eront|ez|iez)$/i;
+ if (word.search(b2Regex) >= rvIndex) {
+ word = word.replace(b2Regex, '');
+ } else {
+ var b3Regex = /e(âmes|ât|âtes|a|ai|aIent|ais|ait|ant|ante|antes|ants|as|asse|assent|asses|assiez|assions)$/i;
+ if (word.search(b3Regex) >= rvIndex) {
+ word = word.replace(b3Regex, '');
+ } else {
+ var b3Regex2 = /(âmes|ât|âtes|a|ai|aIent|ais|ait|ant|ante|antes|ants|as|asse|assent|asses|assiez|assions)$/i;
+ if (word.search(b3Regex2) >= rvIndex) {
+ word = word.replace(b3Regex2, '');
+ }
+ }
+ }
+ }
+ }
+
+ if(oriWord != word.toLowerCase()){
+ /* Step 3 */
+ var rep = '';
+ if(word.search(/Y$/) != -1) {
+ word = word.replace(/Y$/, 'i');
+ } else if(word.search(/ç$/) != -1){
+ word = word.replace(/ç$/, 'c');
+ }
+ } else {
+ /* Step 4 */
+ //If the word ends s, not preceded by a, i, o, u, è or s, delete it.
+ if (word.search(/([^aiouès])s$/) >= rvIndex) {
+ word = word.replace(/([^aiouès])s$/, '$1');
+ }
+ var e1Index = word.search(/ion$/);
+ if (e1Index >= r2Index && word.search(/[st]ion$/) >= rvIndex) {
+ word = word.substring(0, e1Index);
+ } else {
+ var e2Index = word.search(/(ier|ière|Ier|Ière)$/);
+ if (e2Index != -1 && e2Index >= rvIndex) {
+ word = word.substring(0, e2Index) + "i";
+ } else {
+ if (word.search(/e$/) >= rvIndex) {
+ word = word.replace(/e$/, ''); //delete last e
+ } else if (word.search(/guë$/) >= rvIndex) {
+ word = word.replace(/guë$/, 'gu');
+ }
+ }
+ }
+ }
+
+ /* Step 5: Undouble */
+ //word = word.replace(/(en|on|et|el|eil)(n|t|l)$/,'$1');
+ word = word.replace(/(en|on)(n)$/,'$1');
+ word = word.replace(/(ett)$/,'et');
+ word = word.replace(/(el|eil)(l)$/,'$1');
+
+ /* Step 6: Un-accent */
+ word = word.replace(/[éè]([^aeiouyâàëéêèïîôûù]+)$/,'e$1');
+ word = word.toLowerCase();
+ return word;
+};
+
+var eqOut = new Array();
+var noteqOut = new Array();
+var eqCount = 0;
+/*
+To test the stemming, create two arrays named "voc" and "COut" which are for vocabualary and the stemmed output.
+Then add the vocabulary strings and output strings. This method will generate the stemmed output for "voc" and will
+compare the output with COut.
+ (I used porter's voc and out files and did a regex to convert them to js objects. regex: /");\nvoc.push("/g . This
+ will add strings to voc array such that output would look like: voc.push("foobar"); ) drop me an email for any help.
+ */
+function testFr(){
+ var start = new Date().getTime(); //execution time
+ eqCount = 0;
+ eqOut = new Array();
+ noteqOut = new Array();
+ for(var k=0;k<voc.length;k++){
+ if(COut[k]==stemmer(voc[k])){
+ eqCount++;
+ eqOut.push("v: "+voc[k]+" c: "+COut[k]);
+ } else {
+ noteqOut.push(voc[k]+", c: "+COut[k]+" s:"+stemmer(voc[k]));
+ }
+ }
+ var end = new Date().getTime(); //execution time
+ var time = end-start;
+ alert("equal count= "+eqCount+" out of "+voc.length+" words. time= "+time+" ms");
+ //console.log("equal count= "+eqCount+" out of "+voc.length+" words. time= "+time+" ms");
+}
+
+
generated by cgit v1.2.1 (git 2.21.0) at 2024-05-15 05:47:40 +0000