/// <summary>
/// 读取内容
/// </summary>
/// <param name="content"></param>
public void ReadContent(string content)
{
Framework.Text.Segment.IctclasSegment segment = Text.Segment.IctclasSegment.GetInstance();
//第一步：替换代词
string[] lines = content.Split(new[] { "\r\n", "\n", ".", "。" }, StringSplitOptions.RemoveEmptyEntries);
lines = ReplacePronouns(lines);
//第二步：信息抽取
ExtractByPattern(lines);
}
/// <summary>
/// 代词替换
/// </summary>
/// <param name="content"></param>
/// <param name="buildWithLast"></param>
/// <returns></returns>
public string[] ReplacePronouns(string[] content, bool buildWithLast = true)
{
List <string> lines = new List <string>();
Framework.Text.Segment.IctclasSegment segment = Text.Segment.IctclasSegment.GetInstance();
Tuple <string[], string[]> lastTuple = new Tuple <string[], string[]>(new string[0], new string[0]);
for (int i = 0; i < content.Length; i++)
{
Tuple <string[], string[]> currentTuple = segment.SplitToArray(content[i]);
lines.Add(ReplacePronouns(ref currentTuple, lastTuple));
if (buildWithLast)
{
lastTuple = currentTuple;
}
}
return(lines.ToArray());
}
public void Debug_TestReplace()
{
string context = File.ReadAllText("代词替换测试.txt", Encoding.UTF8);
Framework.Text.Segment.IctclasSegment segment = Text.Segment.IctclasSegment.GetInstance();
string[] content = context.Split(new[] { "\r\n", "\n", ",", ".", "。", "，" }, StringSplitOptions.RemoveEmptyEntries);
StringBuilder builder = new StringBuilder();
Tuple <string[], string[]> lastTuple = new Tuple <string[], string[]>(new string[0], new string[0]);
for (int i = 0; i < content.Length; i++)
{
Tuple <string[], string[]> currentTuple = segment.SplitToArray(content[i]);
builder.AppendLine(ReplacePronouns(ref currentTuple, lastTuple));
lastTuple = currentTuple;
}
File.WriteAllText("代词替换测试.txt", string.Join("\r\n", content));
File.WriteAllText("代词替换测试_result.txt", builder.ToString(), Encoding.UTF8);
}
/// <summary>
/// 获取含有代词的句子
/// </summary>
/// <param name="fileName"></param>
public void Debug_GetAllPronouns(string fileName)
{
Framework.Text.Segment.IctclasSegment segment = Text.Segment.IctclasSegment.GetInstance();
string[] allLines = File.ReadAllText(fileName, Encoding.UTF8).Split(new string[] { "\r\n", "\r", "\n", ".", "。", "!", "！" }, StringSplitOptions.RemoveEmptyEntries);
List <string> lines = new List <string>();
foreach (string line in allLines)
{
if (line.Trim().Length > 1)
{
Tuple <string[], string[]> tuple = segment.SplitToArray(line.Trim());
for (int i = 0; i < tuple.Item2.Length; i++)
{
if (tuple.Item2[i] == "rr" || tuple.Item2[i] == "rz" ||
tuple.Item2[i] == "rzt" || tuple.Item2[i] == "rzs" || tuple.Item2[i] == "rzv")
{
lines.Add(line);
break;
}
}
}
}
StringBuilder builder = new StringBuilder();
foreach (string line in lines)
{
//Tuple<string[], string[]> tuple = segment.SplitToArray(line);
//for (int i = 0; i < tuple.Item2.Length; i++)
//{
// builder.Append(tuple.Item1[i] + "/" + tuple.Item2[i] + " ");
//}
//builder.AppendLine("\r\n");
builder.AppendLine(line);
}
File.WriteAllText("代词替换测试_Pronouns.txt", builder.ToString(), Encoding.UTF8);
}
/// <summary>
/// 获取问题类型
/// </summary>
/// <param name="sentence"></param>
/// <returns></returns>
public List <string> GetQuestionTypes(string sentence)
{
List <string> qTypes = new List <string>();
bool isOther = false;
Framework.Text.Segment.IctclasSegment ictclasSegment = IctclasSegment.GetInstance();
string[] sentenceSemantic = ictclasSegment.SplitToArray(sentence).Item2;
if (sentenceSemantic != null && sentenceSemantic.Length > 0)
{
string text = string.Join(" ", sentenceSemantic);
// Regex regex;
foreach (DictionaryEntry dictionaryEntry in _questionRules)
{
//regex = new Regex(dictionaryEntry.Key.ToString());
if (dictionaryEntry.Key.ToString().Contains(text))
{
qTypes.AddRange(((Iveely.Framework.DataStructure.SortedList <string>)dictionaryEntry.Value).ToArray());
}
}
}
return(qTypes.Distinct().ToList());
}
