/// <summary>
/// Lemma操作
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
protected void lemmanew_Click(object sender, EventArgs e)
{
/********变量**********/
string titleStr; //标题
string nameStr; //用户名
string txtStr = txtcontent.Value.Trim(); //正文文本
//检验文本册次，单元，篇章属性选择完毕
if (!isSelected())
{
PageAlert("你尚未选择本次筛查的文章册次、单元或篇章！", this);
return;
}
if (string.IsNullOrEmpty(txtcontent.Value)) //处理的文本还未输入
{
PageAlert("你还未输入或导入需要处理的文本,请确认后再试！", this);
txtcontent.Focus();
lemmanew.Enabled = true;
return;
}
else
{
string regEx = @"((file|gopher|news|nntp|telnet|http|ftp|https|ftps|sftp)://)(([a-zA-Z0-9\._-]+\.[a-zA-Z]{2,6})|([0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}))(:[0-9]{1,4})*(/[a-zA-Z0-9\&%_\./-~-]*)?";
txtStr = Regex.Replace(txtcontent.Value, regEx, ";");//正则表达式排除文中的网址
}
/***********1、过滤文本判断是否包含有英文单词*************/
string ignoreWordsFile = GetDbPath() + "words/ignoreWords.txt";
string ordinalWordsFile = GetDbPath() + "words/OrdinalWords.txt";
string symbolFile = GetDbPath() + "words/symbol.txt";
var txtlist = TextInput.ArticleToList(txtStr, ignoreWordsFile, ordinalWordsFile, symbolFile);//文本转化为字符串数组,将需要处理的单词存到数组中
//PageAlert(timeRecord, this);
if (txtlist.Count == 0)//文本中不包含有英文单词
{
PageAlert("文本中不包含英文单词！", this);
txtcontent.Focus();
lemmanew.Enabled = true;
return;
}
string wordLevel = "";
int maxIndex = 0;
maxIndex = ddlBook.SelectedIndex + 4;
int selectIndex = ddlBook.SelectedIndex + ddlUnit.SelectedIndex + ddlText.SelectedIndex;
if (maxIndex == 0 || selectIndex < 3)
{
PageAlert("你还未选定课文对应的册、单元或篇目!", this);
lemmanew.Enabled = true;
return;
}
else
{
wordLevel = ddlBook.SelectedValue + ddlUnit.SelectedValue + ddlText.SelectedValue;
}
/*********2、查询是否已经处理过本篇课文************/
titleStr = ddlBook.SelectedItem.Text + ddlUnit.SelectedItem.Text + ddlText.SelectedItem.Text;
List <string[]> oldwordsList = new List <string[]>();
List <words> newWordsList = new List <words>();
oldwordsList = WordBLL.GetWordLookup(wordLevel);
if (oldwordsList.Count > 0)
{
PageAlert("“" + titleStr + "”课文已经处理过，系统将为您直接输出生词表！", this);
for (int i = 0; i < oldwordsList.Count; i++)
{
newWordsList.Add(new words(i + 1, oldwordsList[i][0].ToString(), oldwordsList[i][1].ToString()));
}
wordgv.DataSource = newWordsList;
wordgv.DataBind();
totalW.Text = "你所筛查的本篇课文共有 " + newWordsList.Count.ToString() + " 生词";
inputDiv.Visible = false;
outputDiv.Visible = true;
Titlelb.Text = "生词表输出";
}
else
{
oldwordsList = new List <string[]>();
/**********3、保存要处理的文本************/
SPUser currentUser = SPContext.Current.Web.CurrentUser;
nameStr = currentUser.Name;
titleStr = TextInput.FilterSpecial(titleStr, "");
string filePath = GetDbPath() + @"export/"; //txt文件保存的路径
string nowStr = string.Format("{0:yyyyMMddHHmmssffff}", DateTime.Now); //时间格式字符串：年月日时分秒4位毫秒
string fileTitle = titleStr + "(" + nameStr + ")" + nowStr + ".txt";; //文章标题+ _ + 处理人姓名 + 处理人所属院校（登录名）+ 当前时间
TextInput.FileWrite(fileTitle, txtStr, filePath); //将即将处理的文本保存到服务器上的指定目录中;
inputDiv.Visible = false;
/***************4、词汇与级别表筛查*******************/
string fileName = GetDbPath() + "words/AllWords.txt"; //包含原型与变型以及对应等级的词汇表文本
Dictionary <int, object> allwordsList = WordBLL.SearchWordsWithTxt(txtlist, fileName, 0);
DataTable wordsTable = (DataTable)allwordsList[1]; //包含要输出的单词的元词汇、级别、频次
if (wordsTable.Rows.Count > 0) //有生词
{
DataRow[] drs = wordsTable.Select("[level]>'" + maxIndex + "'"); //生词词汇的原词、级别、频次
for (int i = 0; i < drs.Length; i++)
{
int level = (int)drs[i][1];
string signs = WordBLL.leveltoSigns(level);
string[] wds = new string[2] {
drs[i][0].ToString(), signs
};
oldwordsList.Add(wds);
}
oldwordsList = WordBLL.GetWordLookup(oldwordsList, wordLevel); //与动态词汇表对比筛查
/***************5、输出本文生词词汇表********************/
for (int i = 0; i < oldwordsList.Count; i++)
{
newWordsList.Add(new words(i + 1, oldwordsList[i][0].ToString(), oldwordsList[i][1].ToString()));
}
wordgv.DataSource = newWordsList;
wordgv.DataBind();
totalW.Text = "你所筛查的本篇课文共有 " + newWordsList.Count.ToString() + " 生词";
outputDiv.Visible = true;
Titlelb.Text = "生词表输出";
}
}
lemmanew.Enabled = true;
}
public static void Lemma(KeyValuePair <string, string> kv, string wordLevel, string dbpath)
{
/********变量**********/
string titleStr = kv.Key; //标题
string nameStr; //用户名
string regEx = @"((file|gopher|news|nntp|telnet|http|ftp|https|ftps|sftp)://)(([a-zA-Z0-9\._-]+\.[a-zA-Z]{2,6})|([0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}))(:[0-9]{1,4})*(/[a-zA-Z0-9\&%_\./-~-]*)?";
string txtStr = kv.Value;
txtStr = Regex.Replace(txtStr, regEx, ";");//正则表达式排除文中的网址
/***********1、过滤文本判断是否包含有英文单词*************/
string ignoreWordsFile = dbpath + "words/ignoreWords.txt";
string ordinalWordsFile = dbpath + "words/OrdinalWords.txt";
string symbolFile = dbpath + "words/symbol.txt";
var txtlist = TextInput.ArticleToList(txtStr, ignoreWordsFile, ordinalWordsFile, symbolFile);//文本转化为字符串数组,将需要处理的单词存到数组中
int maxIndex = 5;
List <string[]> oldwordsList = new List <string[]>();
List <words> newWordsList = new List <words>();
oldwordsList = WordBLL.GetWordLookup(wordLevel);
if (oldwordsList.Count > 0)
{
for (int i = 0; i < oldwordsList.Count; i++)
{
newWordsList.Add(new words(i + 1, oldwordsList[i][0].ToString(), oldwordsList[i][1].ToString()));
}
}
else
{
oldwordsList = new List <string[]>();
/**********3、保存要处理的文本************/
SPUser currentUser = SPContext.Current.Web.CurrentUser;
nameStr = currentUser.Name;
titleStr = TextInput.FilterSpecial(titleStr, "");
string filePath = dbpath + @"export/"; //txt文件保存的路径
string nowStr = string.Format("{0:yyyyMMddHHmmssffff}", DateTime.Now); //时间格式字符串：年月日时分秒4位毫秒
string fileTitle = titleStr + "(" + nameStr + ")" + nowStr + ".txt";; //文章标题+ _ + 处理人姓名 + 处理人所属院校（登录名）+ 当前时间
TextInput.FileWrite(fileTitle, txtStr, filePath); //将即将处理的文本保存到服务器上的指定目录中;
/***************4、词汇与级别表筛查*******************/
string fileName = dbpath + "words/AllWords.txt"; //包含原型与变型以及对应等级的词汇表文本
Dictionary <int, object> allwordsList = WordBLL.SearchWordsWithTxt(txtlist, fileName, 0);
DataTable wordsTable = (DataTable)allwordsList[1]; //包含要输出的单词的元词汇、级别、频次
if (wordsTable.Rows.Count > 0) //有生词
{
DataRow[] drs = wordsTable.Select("[level]>'" + maxIndex + "'"); //生词词汇的原词、级别、频次
for (int i = 0; i < drs.Length; i++)
{
int level = (int)drs[i][1];
string signs = WordBLL.leveltoSigns(level);
string[] wds = new string[2] {
drs[i][0].ToString(), signs
};
oldwordsList.Add(wds);
}
oldwordsList = WordBLL.GetWordLookup(oldwordsList, wordLevel); //与动态词汇表对比筛查
/***************5、输出本文生词词汇表********************/
for (int i = 0; i < oldwordsList.Count; i++)
{
newWordsList.Add(new words(i + 1, oldwordsList[i][0].ToString(), oldwordsList[i][1].ToString()));
}
}
}
}
