exam_service
This commit is contained in:
SpecialX
@@ -6,244 +6,244 @@ using System.IO; // 用于 XML 反序列化
|
||||
namespace TechHelper.Client.Exam
|
||||
{
|
||||
|
||||
[XmlRoot("EP")]
|
||||
public class StringsList
|
||||
{
|
||||
//[XmlRoot("EP")]
|
||||
//public class StringsList
|
||||
//{
|
||||
|
||||
[XmlElement("Q")]
|
||||
public List<string> Items { get; set; }
|
||||
}
|
||||
// [XmlElement("Q")]
|
||||
// public List<string> Items { get; set; }
|
||||
//}
|
||||
|
||||
// XML 根元素 <EP>
|
||||
[XmlRoot("EP")]
|
||||
public class ExamPaper
|
||||
{
|
||||
// XML 特性：<QGs> 包含 <QG> 列表
|
||||
[XmlArray("QGs")]
|
||||
[XmlArrayItem("QG")]
|
||||
[JsonProperty("QuestionGroups")]
|
||||
public List<QuestionGroup> QuestionGroups { get; set; } = new List<QuestionGroup>();
|
||||
}
|
||||
//// XML 根元素 <EP>
|
||||
//[XmlRoot("EP")]
|
||||
//public class ExamPaper
|
||||
//{
|
||||
// // XML 特性：<QGs> 包含 <QG> 列表
|
||||
// [XmlArray("QGs")]
|
||||
// [XmlArrayItem("QG")]
|
||||
// [JsonProperty("QuestionGroups")]
|
||||
// public List<QuestionGroup> QuestionGroups { get; set; } = new List<QuestionGroup>();
|
||||
//}
|
||||
|
||||
[XmlRoot("QG")]
|
||||
public class QuestionGroup
|
||||
{
|
||||
// JSON 特性
|
||||
[JsonProperty("题号")]
|
||||
// XML 特性：作为 <QG Id="X"> 属性
|
||||
[XmlAttribute("Id")]
|
||||
public byte Id { get; set; }
|
||||
//[XmlRoot("QG")]
|
||||
//public class QuestionGroup
|
||||
//{
|
||||
// // JSON 特性
|
||||
// [JsonProperty("题号")]
|
||||
// // XML 特性：作为 <QG Id="X"> 属性
|
||||
// [XmlAttribute("Id")]
|
||||
// public byte Id { get; set; }
|
||||
|
||||
[JsonProperty("标题")]
|
||||
[XmlElement("T")] // T for Title
|
||||
public string Title { get; set; }
|
||||
// [JsonProperty("标题")]
|
||||
// [XmlElement("T")] // T for Title
|
||||
// public string Title { get; set; }
|
||||
|
||||
[JsonProperty("分值")]
|
||||
[XmlAttribute("S")] // S for Score
|
||||
public int Score { get; set; }
|
||||
// [JsonProperty("分值")]
|
||||
// [XmlAttribute("S")] // S for Score
|
||||
// public int Score { get; set; }
|
||||
|
||||
[JsonProperty("题目引用")]
|
||||
[XmlElement("QR")] // QR for QuestionReference，作为 <QR> 元素
|
||||
public string QuestionReference { get; set; } = ""; // 初始化为空字符串
|
||||
// [JsonProperty("题目引用")]
|
||||
// [XmlElement("QR")] // QR for QuestionReference，作为 <QR> 元素
|
||||
// public string QuestionReference { get; set; } = ""; // 初始化为空字符串
|
||||
|
||||
[JsonProperty("子题目")]
|
||||
[XmlArray("SQs")] // SQs 包含 <SQ> 列表
|
||||
[XmlArrayItem("SQ")]
|
||||
public List<SubQuestion> SubQuestions { get; set; } = new List<SubQuestion>();
|
||||
// [JsonProperty("子题目")]
|
||||
// [XmlArray("SQs")] // SQs 包含 <SQ> 列表
|
||||
// [XmlArrayItem("SQ")]
|
||||
// public List<SubQuestion> SubQuestions { get; set; } = new List<SubQuestion>();
|
||||
|
||||
[JsonProperty("子题组")]
|
||||
[XmlArray("SQGs")] // SQGs 包含 <QG> 列表 (嵌套题组)
|
||||
[XmlArrayItem("QG")]
|
||||
public List<QuestionGroup> SubQuestionGroups { get; set; } = new List<QuestionGroup>();
|
||||
}
|
||||
// [JsonProperty("子题组")]
|
||||
// [XmlArray("SQGs")] // SQGs 包含 <QG> 列表 (嵌套题组)
|
||||
// [XmlArrayItem("QG")]
|
||||
// public List<QuestionGroup> SubQuestionGroups { get; set; } = new List<QuestionGroup>();
|
||||
//}
|
||||
|
||||
// 子题目类
|
||||
public class SubQuestion
|
||||
{
|
||||
//// 子题目类
|
||||
//public class SubQuestion
|
||||
//{
|
||||
|
||||
[JsonProperty("子题号")]
|
||||
[XmlAttribute("Id")] // Id for SubId
|
||||
public byte SubId { get; set; }
|
||||
// [JsonProperty("子题号")]
|
||||
// [XmlAttribute("Id")] // Id for SubId
|
||||
// public byte SubId { get; set; }
|
||||
|
||||
[JsonProperty("题干")]
|
||||
[XmlElement("T")] // T for Text (Stem)
|
||||
public string Stem { get; set; }
|
||||
// [JsonProperty("题干")]
|
||||
// [XmlElement("T")] // T for Text (Stem)
|
||||
// public string Stem { get; set; }
|
||||
|
||||
[JsonProperty("分值")]
|
||||
[XmlAttribute("S")] // S for Score
|
||||
public int Score { get; set; } // 分值通常为整数
|
||||
// [JsonProperty("分值")]
|
||||
// [XmlAttribute("S")] // S for Score
|
||||
// public int Score { get; set; } // 分值通常为整数
|
||||
|
||||
[JsonProperty("选项")]
|
||||
[XmlArray("Os")] // Os 包含 <O> 列表
|
||||
[XmlArrayItem("O")]
|
||||
public List<Option> Options { get; set; } = new List<Option>();
|
||||
// [JsonProperty("选项")]
|
||||
// [XmlArray("Os")] // Os 包含 <O> 列表
|
||||
// [XmlArrayItem("O")]
|
||||
// public List<Option> Options { get; set; } = new List<Option>();
|
||||
|
||||
[JsonProperty("示例答案")]
|
||||
[XmlElement("SA")] // SA for SampleAnswer
|
||||
public string SampleAnswer { get; set; } = "";
|
||||
}
|
||||
// [JsonProperty("示例答案")]
|
||||
// [XmlElement("SA")] // SA for SampleAnswer
|
||||
// public string SampleAnswer { get; set; } = "";
|
||||
//}
|
||||
|
||||
// 选项类，用于适配 <O V="X"/> 结构
|
||||
public class Option
|
||||
{
|
||||
// XML 特性：作为 <O V="X"> 属性
|
||||
[XmlAttribute("V")] // V for Value
|
||||
// JSON 特性：如果 JSON 中的选项是 {"Value": "A"} 这样的对象，则需要 JsonProperty("Value")
|
||||
// 但如果 JSON 选项只是 ["A", "B"] 这样的字符串数组，则此Option类不适合JSON Options
|
||||
// 需要明确你的JSON Options的结构。我假设你JSON Options是 List<string>
|
||||
// 如果是 List<string>，则Options属性在SubQuestion中直接是List<string>，Option类则不需要
|
||||
// 但根据你的精简XML需求，Option类是必要的。
|
||||
// 所以这里需要你自己根据实际JSON Options结构选择。
|
||||
// 为了兼容XML，我会保留Option类，但如果JSON是List<string>，Options属性会很复杂
|
||||
public string Value { get; set; }
|
||||
}
|
||||
//// 选项类，用于适配 <O V="X"/> 结构
|
||||
//public class Option
|
||||
//{
|
||||
// // XML 特性：作为 <O V="X"> 属性
|
||||
// [XmlAttribute("V")] // V for Value
|
||||
// // JSON 特性：如果 JSON 中的选项是 {"Value": "A"} 这样的对象，则需要 JsonProperty("Value")
|
||||
// // 但如果 JSON 选项只是 ["A", "B"] 这样的字符串数组，则此Option类不适合JSON Options
|
||||
// // 需要明确你的JSON Options的结构。我假设你JSON Options是 List<string>
|
||||
// // 如果是 List<string>，则Options属性在SubQuestion中直接是List<string>，Option类则不需要
|
||||
// // 但根据你的精简XML需求，Option类是必要的。
|
||||
// // 所以这里需要你自己根据实际JSON Options结构选择。
|
||||
// // 为了兼容XML，我会保留Option类，但如果JSON是List<string>，Options属性会很复杂
|
||||
// public string Value { get; set; }
|
||||
//}
|
||||
|
||||
// 独立的服务类来处理序列化和反序列化
|
||||
public static class ExamParser
|
||||
{
|
||||
// JSON 反序列化方法
|
||||
public static List<T> ParseExamJson<T>(string jsonContent)
|
||||
{
|
||||
string cleanedJson = jsonContent.Trim();
|
||||
//// 独立的服务类来处理序列化和反序列化
|
||||
//public static class ExamParser
|
||||
//{
|
||||
// // JSON 反序列化方法
|
||||
// public static List<T> ParseExamJson<T>(string jsonContent)
|
||||
// {
|
||||
// string cleanedJson = jsonContent.Trim();
|
||||
|
||||
// 移除可能存在的 Markdown 代码块标记
|
||||
if (cleanedJson.StartsWith("```json") && cleanedJson.EndsWith("```"))
|
||||
{
|
||||
cleanedJson = cleanedJson.Substring("```json".Length, cleanedJson.Length - "```json".Length - "```".Length).Trim();
|
||||
}
|
||||
// 移除可能存在的单引号包围（如果 AI 偶尔会这样输出）
|
||||
if (cleanedJson.StartsWith("'") && cleanedJson.EndsWith("'"))
|
||||
{
|
||||
cleanedJson = cleanedJson.Substring(1, cleanedJson.Length - 2).Trim();
|
||||
}
|
||||
// // 移除可能存在的 Markdown 代码块标记
|
||||
// if (cleanedJson.StartsWith("```json") && cleanedJson.EndsWith("```"))
|
||||
// {
|
||||
// cleanedJson = cleanedJson.Substring("```json".Length, cleanedJson.Length - "```json".Length - "```".Length).Trim();
|
||||
// }
|
||||
// // 移除可能存在的单引号包围（如果 AI 偶尔会这样输出）
|
||||
// if (cleanedJson.StartsWith("'") && cleanedJson.EndsWith("'"))
|
||||
// {
|
||||
// cleanedJson = cleanedJson.Substring(1, cleanedJson.Length - 2).Trim();
|
||||
// }
|
||||
|
||||
try
|
||||
{
|
||||
// 注意：这里假设你的 JSON 根直接是一个 QuestionGroup 列表
|
||||
// 如果你的 JSON 根是 { "QuestionGroups": [...] }，则需要先反序列化到 ExamPaper
|
||||
List<T> examQuestions = JsonConvert.DeserializeObject<List<T>>(cleanedJson);
|
||||
return examQuestions;
|
||||
}
|
||||
catch (JsonSerializationException ex)
|
||||
{
|
||||
Console.WriteLine($"JSON 反序列化错误: {ex.Message}");
|
||||
Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
return null;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
Console.WriteLine($"处理错误: {ex.Message}");
|
||||
return null;
|
||||
}
|
||||
}
|
||||
// try
|
||||
// {
|
||||
// // 注意：这里假设你的 JSON 根直接是一个 QuestionGroup 列表
|
||||
// // 如果你的 JSON 根是 { "QuestionGroups": [...] }，则需要先反序列化到 ExamPaper
|
||||
// List<T> examQuestions = JsonConvert.DeserializeObject<List<T>>(cleanedJson);
|
||||
// return examQuestions;
|
||||
// }
|
||||
// catch (JsonSerializationException ex)
|
||||
// {
|
||||
// Console.WriteLine($"JSON 反序列化错误: {ex.Message}");
|
||||
// Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
// return null;
|
||||
// }
|
||||
// catch (Exception ex)
|
||||
// {
|
||||
// Console.WriteLine($"处理错误: {ex.Message}");
|
||||
// return null;
|
||||
// }
|
||||
// }
|
||||
|
||||
|
||||
|
||||
#region TEST
|
||||
[XmlRoot("User")]
|
||||
public class User
|
||||
{
|
||||
[XmlAttribute("id")]
|
||||
public string Id { get; set; }
|
||||
// #region TEST
|
||||
// [XmlRoot("User")]
|
||||
// public class User
|
||||
// {
|
||||
// [XmlAttribute("id")]
|
||||
// public string Id { get; set; }
|
||||
|
||||
[XmlElement("PersonalInfo")]
|
||||
public PersonalInfo PersonalInfo { get; set; }
|
||||
// [XmlElement("PersonalInfo")]
|
||||
// public PersonalInfo PersonalInfo { get; set; }
|
||||
|
||||
[XmlArray("Roles")] // 包装元素 <Roles>
|
||||
[XmlArrayItem("Role")] // 集合中的每个项是 <Role>
|
||||
public List<Role> Roles { get; set; } = new List<Role>();
|
||||
// [XmlArray("Roles")] // 包装元素 <Roles>
|
||||
// [XmlArrayItem("Role")] // 集合中的每个项是 <Role>
|
||||
// public List<Role> Roles { get; set; } = new List<Role>();
|
||||
|
||||
// 构造函数，方便测试
|
||||
public User() { }
|
||||
}
|
||||
// // 构造函数，方便测试
|
||||
// public User() { }
|
||||
// }
|
||||
|
||||
public class PersonalInfo
|
||||
{
|
||||
[XmlElement("FullName")]
|
||||
public string FullName { get; set; }
|
||||
// public class PersonalInfo
|
||||
// {
|
||||
// [XmlElement("FullName")]
|
||||
// public string FullName { get; set; }
|
||||
|
||||
[XmlElement("EmailAddress")]
|
||||
public string EmailAddress { get; set; }
|
||||
// [XmlElement("EmailAddress")]
|
||||
// public string EmailAddress { get; set; }
|
||||
|
||||
// 构造函数，方便测试
|
||||
public PersonalInfo() { }
|
||||
}
|
||||
// // 构造函数，方便测试
|
||||
// public PersonalInfo() { }
|
||||
// }
|
||||
|
||||
public class Role
|
||||
{
|
||||
[XmlAttribute("type")]
|
||||
public string Type { get; set; }
|
||||
// public class Role
|
||||
// {
|
||||
// [XmlAttribute("type")]
|
||||
// public string Type { get; set; }
|
||||
|
||||
// 构造函数，方便测试
|
||||
public Role() { }
|
||||
}
|
||||
#endregion
|
||||
// // 构造函数，方便测试
|
||||
// public Role() { }
|
||||
// }
|
||||
// #endregion
|
||||
|
||||
// XML 反序列化方法
|
||||
public static T ParseExamXml<T>(string xmlContent)
|
||||
{
|
||||
string cleanedXml = xmlContent.Trim();
|
||||
if (cleanedXml.StartsWith("'") && cleanedXml.EndsWith("'"))
|
||||
{
|
||||
cleanedXml = cleanedXml.Substring(1, cleanedXml.Length - 2);
|
||||
}
|
||||
if (cleanedXml.StartsWith("```xml") && cleanedXml.EndsWith("```"))
|
||||
{
|
||||
cleanedXml = cleanedXml.Substring("```xml".Length, cleanedXml.Length - "```xml".Length - "```".Length).Trim();
|
||||
}
|
||||
// // XML 反序列化方法
|
||||
// public static T ParseExamXml<T>(string xmlContent)
|
||||
// {
|
||||
// string cleanedXml = xmlContent.Trim();
|
||||
// if (cleanedXml.StartsWith("'") && cleanedXml.EndsWith("'"))
|
||||
// {
|
||||
// cleanedXml = cleanedXml.Substring(1, cleanedXml.Length - 2);
|
||||
// }
|
||||
// if (cleanedXml.StartsWith("```xml") && cleanedXml.EndsWith("```"))
|
||||
// {
|
||||
// cleanedXml = cleanedXml.Substring("```xml".Length, cleanedXml.Length - "```xml".Length - "```".Length).Trim();
|
||||
// }
|
||||
|
||||
XmlSerializer serializer = new XmlSerializer(typeof(T));
|
||||
// XmlSerializer serializer = new XmlSerializer(typeof(T));
|
||||
|
||||
using (StringReader reader = new StringReader(cleanedXml))
|
||||
{
|
||||
try
|
||||
{
|
||||
T user = (T)serializer.Deserialize(reader);
|
||||
return user;
|
||||
}
|
||||
catch (InvalidOperationException ex)
|
||||
{
|
||||
Console.WriteLine($"XML 反序列化操作错误: {ex.Message}");
|
||||
Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
return default(T);
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
Console.WriteLine($"处理错误: {ex.Message}");
|
||||
return default(T);
|
||||
}
|
||||
}
|
||||
}
|
||||
// using (StringReader reader = new StringReader(cleanedXml))
|
||||
// {
|
||||
// try
|
||||
// {
|
||||
// T user = (T)serializer.Deserialize(reader);
|
||||
// return user;
|
||||
// }
|
||||
// catch (InvalidOperationException ex)
|
||||
// {
|
||||
// Console.WriteLine($"XML 反序列化操作错误: {ex.Message}");
|
||||
// Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
// return default(T);
|
||||
// }
|
||||
// catch (Exception ex)
|
||||
// {
|
||||
// Console.WriteLine($"处理错误: {ex.Message}");
|
||||
// return default(T);
|
||||
// }
|
||||
// }
|
||||
// }
|
||||
|
||||
public static List<QuestionGroup> ParseExamXmlFormQG(string xmlContent)
|
||||
{
|
||||
// 移除可能存在的 Markdown 代码块标记
|
||||
if (xmlContent.StartsWith("```xml") && xmlContent.EndsWith("```"))
|
||||
{
|
||||
xmlContent = xmlContent.Substring("```xml".Length, xmlContent.Length - "```xml".Length - "```".Length).Trim();
|
||||
}
|
||||
// public static List<QuestionGroup> ParseExamXmlFormQG(string xmlContent)
|
||||
// {
|
||||
// // 移除可能存在的 Markdown 代码块标记
|
||||
// if (xmlContent.StartsWith("```xml") && xmlContent.EndsWith("```"))
|
||||
// {
|
||||
// xmlContent = xmlContent.Substring("```xml".Length, xmlContent.Length - "```xml".Length - "```".Length).Trim();
|
||||
// }
|
||||
|
||||
var serializer = new XmlSerializer(typeof(List<QuestionGroup>), new XmlRootAttribute("QGs"));
|
||||
// var serializer = new XmlSerializer(typeof(List<QuestionGroup>), new XmlRootAttribute("QGs"));
|
||||
|
||||
using (StringReader reader = new StringReader(xmlContent))
|
||||
{
|
||||
try
|
||||
{
|
||||
List<QuestionGroup> questionGroups = (List<QuestionGroup>)serializer.Deserialize(reader);
|
||||
return questionGroups;
|
||||
}
|
||||
catch (InvalidOperationException ex)
|
||||
{
|
||||
Console.WriteLine($"XML 反序列化操作错误: {ex.Message}");
|
||||
Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
return null;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
Console.WriteLine($"处理错误: {ex.Message}");
|
||||
return null;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
// using (StringReader reader = new StringReader(xmlContent))
|
||||
// {
|
||||
// try
|
||||
// {
|
||||
// List<QuestionGroup> questionGroups = (List<QuestionGroup>)serializer.Deserialize(reader);
|
||||
// return questionGroups;
|
||||
// }
|
||||
// catch (InvalidOperationException ex)
|
||||
// {
|
||||
// Console.WriteLine($"XML 反序列化操作错误: {ex.Message}");
|
||||
// Console.WriteLine($"内部异常: {ex.InnerException?.Message}");
|
||||
// return null;
|
||||
// }
|
||||
// catch (Exception ex)
|
||||
// {
|
||||
// Console.WriteLine($"处理错误: {ex.Message}");
|
||||
// return null;
|
||||
// }
|
||||
// }
|
||||
// }
|
||||
//}
|
||||
}
|
||||
@@ -1,627 +0,0 @@
|
||||
using System.Text.RegularExpressions;
|
||||
|
||||
namespace TechHelper.Client.Exam.Parse
|
||||
{
|
||||
public class ExamPaper
|
||||
{
|
||||
public string Title { get; set; } = "未识别试卷标题";
|
||||
public string Descript { get; set; } = "未识别试卷描述";
|
||||
public string SubjectArea { get; set; } = "试卷类别";
|
||||
public List<MajorQuestionGroup> MajorQuestionGroups { get; set; } = new List<MajorQuestionGroup>();
|
||||
public List<Question> TopLevelQuestions { get; set; } = new List<Question>();
|
||||
}
|
||||
|
||||
public class MajorQuestionGroup
|
||||
{
|
||||
public string Title { get; set; } = string.Empty;
|
||||
public string Descript { get; set; } = string.Empty;
|
||||
public float Score { get; set; }
|
||||
public List<MajorQuestionGroup> SubMajorQuestionGroups { get; set; } = new List<MajorQuestionGroup>();
|
||||
public List<Question> Questions { get; set; } = new List<Question>();
|
||||
public int Priority { get; set; }
|
||||
}
|
||||
|
||||
public class Question
|
||||
{
|
||||
public string Number { get; set; } = string.Empty;
|
||||
public string Text { get; set; } = string.Empty;
|
||||
public float Score { get; set; }
|
||||
public List<Option> Options { get; set; } = new List<Option>();
|
||||
public List<Question> SubQuestions { get; set; } = new List<Question>();
|
||||
public int Priority { get; set; }
|
||||
}
|
||||
|
||||
public class Option
|
||||
{
|
||||
public string Label { get; set; } = string.Empty;
|
||||
public string Text { get; set; } = string.Empty;
|
||||
}
|
||||
|
||||
|
||||
/// <summary>
|
||||
/// 表示一个带有优先级的正则表达式配置
|
||||
/// </summary>
|
||||
public class RegexPatternConfig
|
||||
{
|
||||
public string Pattern { get; set; } // 正则表达式字符串
|
||||
public int Priority { get; set; } // 优先级，数字越小优先级越高
|
||||
public Regex Regex { get; private set; } // 编译后的Regex对象，用于性能优化
|
||||
|
||||
public RegexPatternConfig(string pattern, int priority)
|
||||
{
|
||||
Pattern = pattern;
|
||||
Priority = priority;
|
||||
Regex = new Regex(pattern, RegexOptions.Multiline | RegexOptions.Compiled); // 多行模式，编译以提高性能
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 试卷解析的配置类，包含所有正则表达式
|
||||
/// </summary>
|
||||
public class ExamParserConfig
|
||||
{
|
||||
public List<RegexPatternConfig> MajorQuestionGroupPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
public List<RegexPatternConfig> QuestionPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
public List<RegexPatternConfig> OptionPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
|
||||
public ExamParserConfig()
|
||||
{
|
||||
// --- 大题组模式 (MajorQuestionGroupPatterns) ---
|
||||
// 匹配格式: "一、选择题 (20分)" 或 "二、阅读理解"
|
||||
// Group 1: 大题组编号 (e.g., "一", "二")
|
||||
// Group 2: 大题组标题 (e.g., "选择题", "阅读理解")
|
||||
// Group 3: 整个分数部分 (e.g., "(20分)") - 可选
|
||||
// Group 4: 纯数字分数 (e.g., "20") - 可选
|
||||
MajorQuestionGroupPatterns.Add(new RegexPatternConfig(@"^([一二三四五六七八九十]+)[、\.]\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 1));
|
||||
|
||||
|
||||
// --- 题目模式 (QuestionPatterns) ---
|
||||
// 针对不同格式的题目编号，捕获题号、题干和可选的分数
|
||||
// Group 1: 题目编号 (e.g., "1", "(1)", "①")
|
||||
// Group 2: 题干内容 (不含分数)
|
||||
// Group 3: 整个分数部分 (e.g., "(5分)") - 可选
|
||||
// Group 4: 纯数字分数 (e.g., "5") - 可选
|
||||
|
||||
// 模式 1: "1. 这是一个题目 (5分)" 或 "1. 这是一个题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^(\d+)\.\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 1));
|
||||
|
||||
// 模式 2: "(1) 这是一个子题目 (3分)" 或 "(1) 这是一个子题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^\((\d+)\)\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 2));
|
||||
|
||||
// 模式 3: "① 这是一个更深层次的子题目 (2分)" 或 "① 这是一个更深层次的子题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^[①②③④⑤⑥⑦⑧⑨⑩]+\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 3));
|
||||
|
||||
|
||||
// --- 选项模式 (OptionPatterns) ---
|
||||
// 匹配格式: "A. 选项内容"
|
||||
// Group 1: 选项标签 (e.g., "A.")
|
||||
// Group 2: 选项内容
|
||||
OptionPatterns.Add(new RegexPatternConfig(@"^([A-Z]\.)\s*(.*)$", 1)); // 大写字母选项
|
||||
OptionPatterns.Add(new RegexPatternConfig(@"^([a-z]\.)\s*(.*)$", 2)); // 小写字母选项
|
||||
|
||||
|
||||
// --- 忽略模式 (IgnoredPatterns) ---
|
||||
// 匹配空行或只包含空格的行，避免干扰解析流程
|
||||
//IgnoredPatterns.Add(new RegexPatternConfig(@"^\s*$", 1));
|
||||
//// 匹配试卷结尾的常见字符，防止被错误解析
|
||||
//IgnoredPatterns.Add(new RegexPatternConfig(@"^\s*（试卷到此结束）\s*$", 1));
|
||||
//IgnoredPatterns.Add(new RegexPatternConfig(@"^\s*（本卷共[0-9]+页）\s*$", 1));
|
||||
// 标题和描述虽然你没要，但在实际解析中，这些模式有助于区分内容块，
|
||||
// 否则它们可能会被其他模式（如题目模式）错误匹配。
|
||||
// 建议你保留所有模式，但在本回复中，我只给出你要求的部分。
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
public class PotentialMatch
|
||||
{
|
||||
public int StartIndex { get; set; }
|
||||
public int EndIndex { get; set; } // 匹配到的结构在原始文本中的结束位置
|
||||
public string MatchedText { get; set; } // 匹配到的完整行或段落
|
||||
public Match RegexMatch { get; set; } // 原始的Regex.Match对象，方便获取捕获组
|
||||
public RegexPatternConfig PatternConfig { get; set; } // 匹配到的模式配置
|
||||
public MatchType Type { get; set; } // 枚举：MajorQuestionGroup, Question, Option, etc.
|
||||
}
|
||||
|
||||
public enum MatchType
|
||||
{
|
||||
MajorQuestionGroup,
|
||||
Question,
|
||||
Option,
|
||||
Other // 如果有其他需要识别的类型
|
||||
}
|
||||
|
||||
|
||||
/// <summary>
|
||||
/// 负责扫描原始文本，收集所有潜在的匹配项（题组、题目、选项）。
|
||||
/// 它只进行匹配，不进行结构化归属。
|
||||
/// </summary>
|
||||
public class ExamDocumentScanner
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
|
||||
public ExamDocumentScanner(ExamParserConfig config)
|
||||
{
|
||||
_config = config;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 扫描给定的文本，返回所有潜在的匹配项，并按起始位置排序。
|
||||
/// </summary>
|
||||
/// <param name="text">要扫描的文本</param>
|
||||
/// <returns>所有匹配到的 PotentialMatch 列表</returns>
|
||||
public List<PotentialMatch> Scan(string text)
|
||||
{
|
||||
var allPotentialMatches = new List<PotentialMatch>();
|
||||
|
||||
// 扫描所有题组模式
|
||||
foreach (var patternConfig in _config.MajorQuestionGroupPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.MajorQuestionGroup
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 扫描所有题目模式
|
||||
foreach (var patternConfig in _config.QuestionPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.Question
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 扫描所有选项模式
|
||||
foreach (var patternConfig in _config.OptionPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.Option
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 统一按起始位置排序
|
||||
return allPotentialMatches.OrderBy(pm => pm.StartIndex).ToList();
|
||||
}
|
||||
}
|
||||
|
||||
public class ExamStructureBuilder
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
|
||||
public ExamStructureBuilder(ExamParserConfig config)
|
||||
{
|
||||
_config = config ?? throw new ArgumentNullException(nameof(config), "ExamParserConfig cannot be null.");
|
||||
}
|
||||
|
||||
public ExamPaper BuildExamPaper(string fullExamText, List<PotentialMatch> allPotentialMatches)
|
||||
{
|
||||
if (string.IsNullOrWhiteSpace(fullExamText))
|
||||
{
|
||||
throw new ArgumentException("Full exam text cannot be null or empty.", nameof(fullExamText));
|
||||
}
|
||||
if (allPotentialMatches == null)
|
||||
{
|
||||
throw new ArgumentNullException(nameof(allPotentialMatches), "Potential matches list cannot be null.");
|
||||
}
|
||||
|
||||
var examPaper = new ExamPaper();
|
||||
try
|
||||
{
|
||||
examPaper.Title = GetExamTitle(fullExamText);
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException("Failed to extract exam title.", ex);
|
||||
}
|
||||
|
||||
var majorQGStack = new Stack<MajorQuestionGroup>();
|
||||
MajorQuestionGroup currentMajorQG = null;
|
||||
|
||||
var questionStack = new Stack<Question>();
|
||||
Question currentQuestion = null;
|
||||
|
||||
int currentContentStart = 0;
|
||||
|
||||
if (allPotentialMatches.Any() && allPotentialMatches[0].StartIndex > 0)
|
||||
{
|
||||
string introText = fullExamText.Substring(0, allPotentialMatches[0].StartIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(introText))
|
||||
{
|
||||
examPaper.Descript = introText;
|
||||
}
|
||||
}
|
||||
|
||||
for (int i = 0; i < allPotentialMatches.Count; i++)
|
||||
{
|
||||
var pm = allPotentialMatches[i];
|
||||
|
||||
try
|
||||
{
|
||||
// Validate potential match data
|
||||
if (pm.StartIndex < currentContentStart || pm.EndIndex > fullExamText.Length || pm.StartIndex > pm.EndIndex)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(
|
||||
$"PotentialMatch at index {i} has invalid start/end indices. Start: {pm.StartIndex}, End: {pm.EndIndex}, CurrentContentStart: {currentContentStart}, FullTextLength: {fullExamText.Length}");
|
||||
}
|
||||
if (pm.RegexMatch == null || pm.PatternConfig == null)
|
||||
{
|
||||
throw new InvalidOperationException($"PotentialMatch at index {i} is missing RegexMatch or PatternConfig.");
|
||||
}
|
||||
|
||||
string precedingText = fullExamText.Substring(currentContentStart, pm.StartIndex - currentContentStart).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(precedingText))
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
ProcessQuestionContent(currentQuestion, precedingText,
|
||||
GetSubMatchesForRange(allPotentialMatches, currentContentStart, pm.StartIndex));
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.Descript += (string.IsNullOrWhiteSpace(currentMajorQG.Descript) ? "" : "\n") + precedingText;
|
||||
}
|
||||
else
|
||||
{
|
||||
// Append to ExamPaper.Description if it's top-level descriptive text
|
||||
examPaper.Descript += (string.IsNullOrWhiteSpace(examPaper.Descript) ? "" : "\n") + precedingText;
|
||||
}
|
||||
}
|
||||
|
||||
if (pm.Type == MatchType.MajorQuestionGroup)
|
||||
{
|
||||
try
|
||||
{
|
||||
while (majorQGStack.Any() && pm.PatternConfig.Priority <= majorQGStack.Peek().Priority)
|
||||
{
|
||||
majorQGStack.Pop();
|
||||
}
|
||||
|
||||
// Check if regex match groups exist before accessing
|
||||
if (pm.RegexMatch.Groups.Count < 2)
|
||||
{
|
||||
throw new InvalidOperationException($"MajorQuestionGroup match at index {i} does not have enough regex groups for Title.");
|
||||
}
|
||||
|
||||
float score = 0;
|
||||
if (pm.RegexMatch.Groups.Count > 2 && pm.RegexMatch.Groups[2].Success)
|
||||
{
|
||||
if (!float.TryParse(pm.RegexMatch.Groups[2].Value, out score))
|
||||
{
|
||||
throw new FormatException($"Failed to parse score '{pm.RegexMatch.Groups[2].Value}' for MajorQuestionGroup at index {i}.");
|
||||
}
|
||||
}
|
||||
|
||||
MajorQuestionGroup newMajorQG = new MajorQuestionGroup
|
||||
{
|
||||
Title = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Score = score,
|
||||
Priority = pm.PatternConfig.Priority
|
||||
};
|
||||
|
||||
if (majorQGStack.Any())
|
||||
{
|
||||
majorQGStack.Peek().SubMajorQuestionGroups.Add(newMajorQG);
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.MajorQuestionGroups.Add(newMajorQG);
|
||||
}
|
||||
|
||||
majorQGStack.Push(newMajorQG);
|
||||
currentMajorQG = newMajorQG;
|
||||
questionStack.Clear();
|
||||
currentQuestion = null;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException($"Error processing MajorQuestionGroup at index {i} (MatchedText: '{pm.MatchedText}').", ex);
|
||||
}
|
||||
}
|
||||
else if (pm.Type == MatchType.Question)
|
||||
{
|
||||
try
|
||||
{
|
||||
while (questionStack.Any() && pm.PatternConfig.Priority <= questionStack.Peek().Priority)
|
||||
{
|
||||
questionStack.Pop();
|
||||
}
|
||||
|
||||
if (pm.RegexMatch.Groups.Count < 3)
|
||||
{
|
||||
throw new InvalidOperationException($"Question match at index {i} does not have enough regex groups for Number and Text.");
|
||||
}
|
||||
|
||||
Question newQuestion = new Question
|
||||
{
|
||||
Number = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Text = pm.RegexMatch.Groups[2].Value.Trim(),
|
||||
Priority = pm.PatternConfig.Priority
|
||||
};
|
||||
|
||||
if (pm.RegexMatch.Groups.Count > 3 && pm.RegexMatch.Groups[3].Success) // Assuming score is group 3 if available
|
||||
{
|
||||
float score = 0;
|
||||
if (!float.TryParse(pm.RegexMatch.Groups[3].Value, out score))
|
||||
{
|
||||
throw new FormatException($"Failed to parse score '{pm.RegexMatch.Groups[3].Value}' for Question at index {i}.");
|
||||
}
|
||||
newQuestion.Score = score;
|
||||
}
|
||||
|
||||
if (questionStack.Any())
|
||||
{
|
||||
questionStack.Peek().SubQuestions.Add(newQuestion);
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.Questions.Add(newQuestion);
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.TopLevelQuestions.Add(newQuestion);
|
||||
}
|
||||
|
||||
questionStack.Push(newQuestion);
|
||||
currentQuestion = newQuestion;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException($"Error processing Question at index {i} (MatchedText: '{pm.MatchedText}').", ex);
|
||||
}
|
||||
}
|
||||
else if (pm.Type == MatchType.Option)
|
||||
{
|
||||
try
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
if (pm.RegexMatch.Groups.Count < 3)
|
||||
{
|
||||
throw new InvalidOperationException($"Option match at index {i} does not have enough regex groups for Label and Text.");
|
||||
}
|
||||
|
||||
Option newOption = new Option
|
||||
{
|
||||
Label = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Text = pm.RegexMatch.Groups[2].Value.Trim()
|
||||
};
|
||||
currentQuestion.Options.Add(newOption);
|
||||
}
|
||||
else
|
||||
{
|
||||
// This indicates a structural issue in the exam text
|
||||
throw new InvalidOperationException($"Found isolated Option at index {i} (MatchedText: '{pm.MatchedText}'). Options must belong to a question.");
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException($"Error processing Option at index {i} (MatchedText: '{pm.MatchedText}').", ex);
|
||||
}
|
||||
}
|
||||
|
||||
currentContentStart = pm.EndIndex;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// Catch any unexpected errors during the main loop iteration
|
||||
throw new InvalidOperationException($"An unexpected error occurred during processing of PotentialMatch at index {i}.", ex);
|
||||
}
|
||||
}
|
||||
|
||||
// --- Step 4: Process remaining content after the last match ---
|
||||
if (currentContentStart < fullExamText.Length)
|
||||
{
|
||||
try
|
||||
{
|
||||
string remainingText = fullExamText.Substring(currentContentStart).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(remainingText))
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
ProcessQuestionContent(currentQuestion, remainingText,
|
||||
GetSubMatchesForRange(allPotentialMatches, currentContentStart, fullExamText.Length));
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.Descript += (string.IsNullOrWhiteSpace(currentMajorQG.Descript) ? "" : "\n") + remainingText;
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.Descript += (string.IsNullOrWhiteSpace(examPaper.Descript) ? "" : "\n") + remainingText;
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException("Error processing remaining text after all potential matches.", ex);
|
||||
}
|
||||
}
|
||||
|
||||
return examPaper;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Extracts the exam title (simple implementation)
|
||||
/// </summary>
|
||||
private string GetExamTitle(string examPaperText)
|
||||
{
|
||||
try
|
||||
{
|
||||
var firstLine = examPaperText.Split(new[] { '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries)
|
||||
.FirstOrDefault(line => !string.IsNullOrWhiteSpace(line));
|
||||
return firstLine ?? "未识别试卷标题";
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException("An error occurred while trying to extract the exam title from the text.", ex);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Gets a subset of the given PotentialMatch list within a specified range.
|
||||
/// This method helps ProcessQuestionContent by providing Options and SubQuestions within that range.
|
||||
/// </summary>
|
||||
private List<PotentialMatch> GetSubMatchesForRange(List<PotentialMatch> allMatches, int start, int end)
|
||||
{
|
||||
try
|
||||
{
|
||||
// Input validation for range
|
||||
if (start < 0 || end < start)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException($"Invalid range provided to GetSubMatchesForRange. Start: {start}, End: {end}");
|
||||
}
|
||||
// Ensure allMatches is not null before querying
|
||||
if (allMatches == null)
|
||||
{
|
||||
return new List<PotentialMatch>();
|
||||
}
|
||||
|
||||
return allMatches.Where(pm => pm.StartIndex >= start && pm.StartIndex < end).ToList();
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException($"Error getting sub-matches for range [{start}, {end}).", ex);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Processes the content of a Question, mainly for parsing Options and identifying unstructured text.
|
||||
/// </summary>
|
||||
private void ProcessQuestionContent(Question question, string contentText, List<PotentialMatch> potentialMatchesInScope)
|
||||
{
|
||||
if (question == null)
|
||||
{
|
||||
throw new ArgumentNullException(nameof(question), "Question cannot be null in ProcessQuestionContent.");
|
||||
}
|
||||
if (contentText == null) // contentText can be empty, but not null
|
||||
{
|
||||
throw new ArgumentNullException(nameof(contentText), "Content text cannot be null in ProcessQuestionContent.");
|
||||
}
|
||||
if (potentialMatchesInScope == null)
|
||||
{
|
||||
throw new ArgumentNullException(nameof(potentialMatchesInScope), "Potential matches in scope cannot be null.");
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
int lastOptionEndIndex = 0;
|
||||
|
||||
foreach (var pm in potentialMatchesInScope.OrderBy(p => p.StartIndex))
|
||||
{
|
||||
try
|
||||
{
|
||||
if (pm.Type == MatchType.Option)
|
||||
{
|
||||
// Check for valid indices
|
||||
if (pm.StartIndex < lastOptionEndIndex || pm.StartIndex > contentText.Length || pm.EndIndex > contentText.Length)
|
||||
{
|
||||
throw new ArgumentOutOfRangeException(
|
||||
$"Option match at index {pm.StartIndex} has invalid indices within content text. MatchedText: '{pm.MatchedText}'");
|
||||
}
|
||||
|
||||
if (pm.StartIndex > lastOptionEndIndex)
|
||||
{
|
||||
string textBeforeOption = contentText.Substring(lastOptionEndIndex, pm.StartIndex - lastOptionEndIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(textBeforeOption))
|
||||
{
|
||||
question.Text += (string.IsNullOrWhiteSpace(question.Text) ? "" : "\n") + textBeforeOption;
|
||||
}
|
||||
}
|
||||
|
||||
if (pm.RegexMatch.Groups.Count < 3)
|
||||
{
|
||||
throw new InvalidOperationException($"Option regex match '{pm.MatchedText}' does not have enough groups for label and text.");
|
||||
}
|
||||
|
||||
var newOption = new Option
|
||||
{
|
||||
Label = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Text = pm.RegexMatch.Groups[2].Value.Trim()
|
||||
};
|
||||
question.Options.Add(newOption);
|
||||
lastOptionEndIndex = pm.EndIndex;
|
||||
}
|
||||
// TODO: If there are SubQuestion types, they can be processed similarly here.
|
||||
}
|
||||
catch (Exception innerEx)
|
||||
{
|
||||
throw new InvalidOperationException($"Error processing a potential match ({pm.Type}) within question content (MatchedText: '{pm.MatchedText}').", innerEx);
|
||||
}
|
||||
}
|
||||
|
||||
// Process any remaining text after all options
|
||||
if (lastOptionEndIndex < contentText.Length)
|
||||
{
|
||||
string remainingContent = contentText.Substring(lastOptionEndIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(remainingContent))
|
||||
{
|
||||
question.Text += (string.IsNullOrWhiteSpace(question.Text) ? "" : "\n") + remainingContent;
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
throw new InvalidOperationException($"An error occurred while processing content for Question '{question.Number}'.", ex);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public class ExamParser
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
private readonly ExamDocumentScanner _scanner;
|
||||
private readonly ExamStructureBuilder _builder;
|
||||
|
||||
public ExamParser(ExamParserConfig config)
|
||||
{
|
||||
_config = config;
|
||||
_scanner = new ExamDocumentScanner(_config);
|
||||
_builder = new ExamStructureBuilder(_config);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 解析给定的试卷文本，返回结构化的 ExamPaper 对象。
|
||||
/// </summary>
|
||||
/// <param name="examPaperText">完整的试卷文本</param>
|
||||
/// <returns>解析后的 ExamPaper 对象</returns>
|
||||
public ExamPaper ParseExamPaper(string examPaperText)
|
||||
{
|
||||
// 1. 扫描：一次性扫描整个文本，收集所有潜在的匹配项
|
||||
List<PotentialMatch> allPotentialMatches = _scanner.Scan(examPaperText);
|
||||
|
||||
// 2. 构建：根据扫描结果和原始文本，线性遍历并构建层级结构
|
||||
ExamPaper parsedExam = _builder.BuildExamPaper(examPaperText, allPotentialMatches);
|
||||
|
||||
return parsedExam;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@@ -1,43 +0,0 @@
|
||||
@using TechHelper.Client.Exam.Parse
|
||||
|
||||
<MudCard Class="my-2 pa-2" Outlined="true" Elevation="1">
|
||||
<MudCardContent>
|
||||
<MudText Typo="Typo.subtitle1">
|
||||
<b>@Question.Number</b> @((MarkupString)Question.Text)
|
||||
@if (Question.Score > 0)
|
||||
{
|
||||
<MudText Typo="Typo.body2" Class="d-inline ml-2">(@Question.Score 分)</MudText>
|
||||
}
|
||||
</MudText>
|
||||
|
||||
@* 显示选项 - 不使用 MudList *@
|
||||
@if (Question.Options.Any())
|
||||
{
|
||||
<div class="mt-2">
|
||||
@* 使用普通的 div 容器，你可以添加自定义 CSS 类进行样式控制 *@
|
||||
@foreach (var option in Question.Options)
|
||||
{
|
||||
<MudText Typo="Typo.body2" Class="my-1">
|
||||
@* 为每个选项文本添加一些边距 *@
|
||||
<b>@option.Label</b> @((MarkupString)option.Text)
|
||||
</MudText>
|
||||
}
|
||||
</div>
|
||||
}
|
||||
|
||||
@* 递归显示子题目 *@
|
||||
@if (Question.SubQuestions.Any())
|
||||
{
|
||||
<MudText Typo="Typo.subtitle2" Class="my-2">子题目:</MudText>
|
||||
@foreach (var subQuestion in Question.SubQuestions)
|
||||
{
|
||||
<QuestionCard Question="subQuestion" />
|
||||
}
|
||||
}
|
||||
</MudCardContent>
|
||||
</MudCard>
|
||||
|
||||
@code {
|
||||
[Parameter]
|
||||
public Question Question { get; set; }
|
||||
}
|
||||
@@ -1,43 +0,0 @@
|
||||
@using TechHelper.Client.Exam.Parse
|
||||
@* SubMajorQuestionGroupDisplay.razor *@
|
||||
<MudExpansionPanels>
|
||||
@foreach (var majorQG in MajorQGList)
|
||||
{
|
||||
<MudExpansionPanel Text="@majorQG.Title" DisableRipple="true">
|
||||
<MudCard Class="mt-2" Outlined="true">
|
||||
<MudCardContent>
|
||||
@if (!string.IsNullOrWhiteSpace(majorQG.Descript))
|
||||
{
|
||||
<MudText Typo="Typo.body2"><b>描述:</b> @((MarkupString)majorQG.Descript)</MudText>
|
||||
}
|
||||
@if (majorQG.Score > 0)
|
||||
{
|
||||
<MudText Typo="Typo.body2"><b>总分:</b> @majorQG.Score 分</MudText>
|
||||
}
|
||||
|
||||
@* 显示当前子题组下的题目 *@
|
||||
@if (majorQG.Questions.Any())
|
||||
{
|
||||
<MudText Typo="Typo.subtitle1" Class="my-2">题目:</MudText>
|
||||
@foreach (var question in majorQG.Questions)
|
||||
{
|
||||
<QuestionCard Question="question" />
|
||||
}
|
||||
}
|
||||
|
||||
@* 递归显示更深层次的子题组 *@
|
||||
@if (majorQG.SubMajorQuestionGroups.Any())
|
||||
{
|
||||
<MudText Typo="Typo.subtitle1" Class="my-2">子题组:</MudText>
|
||||
<SubMajorQuestionGroupDisplay MajorQGList="majorQG.SubMajorQuestionGroups" />
|
||||
}
|
||||
</MudCardContent>
|
||||
</MudCard>
|
||||
</MudExpansionPanel>
|
||||
}
|
||||
</MudExpansionPanels>
|
||||
|
||||
@code {
|
||||
[Parameter]
|
||||
public List<MajorQuestionGroup> MajorQGList { get; set; }
|
||||
}
|
||||
220
TechHelper.Client/Exam/ExamPaperExtensions .cs
Normal file
220
TechHelper.Client/Exam/ExamPaperExtensions .cs
Normal file
@@ -0,0 +1,220 @@
|
||||
using Entities.DTO;
|
||||
using System.Text.Json.Serialization;
|
||||
using System.Text.Json;
|
||||
|
||||
namespace TechHelper.Client.Exam
|
||||
{
|
||||
public static class ExamPaperExtensions
|
||||
{
|
||||
public static ExamDto ConvertToExamDTO(this ExamPaper examPaper)
|
||||
{
|
||||
ExamDto dto = new ExamDto();
|
||||
|
||||
dto.AssignmentTitle = examPaper.AssignmentTitle;
|
||||
dto.Description = examPaper.Description;
|
||||
dto.SubjectArea = examPaper.SubjectArea;
|
||||
dto.QuestionGroups.Title = examPaper.AssignmentTitle;
|
||||
dto.QuestionGroups.Descript = examPaper.Description;
|
||||
// 处理顶级 QuestionGroups
|
||||
foreach (var qg in examPaper.QuestionGroups)
|
||||
{
|
||||
var qgd = new QuestionGroupDto();
|
||||
// 顶级 QuestionGroup，其父组当然无效 (false)，所以 isParentGroupValidChain 为 false
|
||||
ParseMajorQuestionGroup(qg, qgd, false);
|
||||
dto.QuestionGroups.SubQuestionGroups.Add(qgd);
|
||||
}
|
||||
|
||||
// 处理 TopLevelQuestions
|
||||
foreach (var question in examPaper.TopLevelQuestions)
|
||||
{
|
||||
// 对于 TopLevelQuestions，它们没有父组，所以 isParentGroupValidChain 初始为 false
|
||||
// 如果顶级 Question 包含子问题，则将其视为一个 QuestionGroupDto
|
||||
if (question.SubQuestions != null && question.SubQuestions.Any())
|
||||
{
|
||||
var qgDto = new QuestionGroupDto
|
||||
{
|
||||
Title = question.Stem,
|
||||
Score = (int)question.Score,
|
||||
Descript = "", // 顶级 Question 默认无描述
|
||||
};
|
||||
// 判断当前组是否有效：如果有描述，则为有效组
|
||||
qgDto.ValidQuestionGroup = !string.IsNullOrEmpty(qgDto.Descript);
|
||||
|
||||
// 传递给子项的 isParentGroupValidChain 状态：如果当前组有效，则传递 true；否则继承父级状态 (此处为 false)
|
||||
ParseQuestionWithSubQuestions(question, qgDto, qgDto.ValidQuestionGroup);
|
||||
dto.QuestionGroups.SubQuestionGroups.Add(qgDto);
|
||||
}
|
||||
else // 如果顶级 Question 没有子问题，则它本身就是一个独立的 SubQuestionDto，放在一个容器 QuestionGroupDto 中
|
||||
{
|
||||
var qgDto = new QuestionGroupDto
|
||||
{
|
||||
Title = question.Stem,
|
||||
Score = (int)question.Score,
|
||||
Descript = "", // 独立题目的容器组通常无描述
|
||||
};
|
||||
// 独立题目的容器组，如果没有描述，则不是“有效组”
|
||||
qgDto.ValidQuestionGroup = !string.IsNullOrEmpty(qgDto.Descript);
|
||||
|
||||
var subQuestionDto = new SubQuestionDto();
|
||||
// 此时，qgDto.ValidQuestionGroup 为 false，所以传入 true，表示题目是有效的
|
||||
// 因为其父组链 (此处为自身) 不是有效组
|
||||
ParseSingleQuestion(question, subQuestionDto, !qgDto.ValidQuestionGroup);
|
||||
qgDto.SubQuestions.Add(subQuestionDto);
|
||||
dto.QuestionGroups.SubQuestionGroups.Add(qgDto);
|
||||
}
|
||||
}
|
||||
|
||||
return dto;
|
||||
}
|
||||
|
||||
// 解析 MajorQuestionGroup 及其子项
|
||||
// isParentGroupValidChain 参数表示从顶层到当前组的任一父组是否已经是“有效组”
|
||||
private static void ParseMajorQuestionGroup(MajorQuestionGroup qg, QuestionGroupDto qgd, bool isParentGroupValidChain)
|
||||
{
|
||||
qgd.Title = qg.Title;
|
||||
qgd.Score = (int)qg.Score;
|
||||
qgd.Descript = qg.Descript;
|
||||
|
||||
// 判断当前组是否有效：如果有描述，并且其父级链中没有任何一个组是有效组，则当前组有效
|
||||
qgd.ValidQuestionGroup = !string.IsNullOrEmpty(qg.Descript) && !isParentGroupValidChain;
|
||||
|
||||
// 更新传递给子项的 isParentGroupValidChain 状态：
|
||||
// 如果当前组是有效组 (即 qgd.ValidQuestionGroup 为 true)，那么子项的父级链就包含了有效组
|
||||
// 否则，子项的父级链有效性继承自其父级 (isParentGroupValidChain)
|
||||
bool nextIsParentGroupValidChain = qgd.ValidQuestionGroup || isParentGroupValidChain;
|
||||
|
||||
// 处理子 QuestionGroup
|
||||
if (qg.SubQuestionGroups != null)
|
||||
{
|
||||
qg.SubQuestionGroups.ForEach(sqg =>
|
||||
{
|
||||
var sqgd = new QuestionGroupDto();
|
||||
ParseMajorQuestionGroup(sqg, sqgd, nextIsParentGroupValidChain);
|
||||
qgd.SubQuestionGroups.Add(sqgd);
|
||||
});
|
||||
}
|
||||
|
||||
// 处理 MajorQuestionGroup 下的 SubQuestions
|
||||
if (qg.SubQuestions != null)
|
||||
{
|
||||
qg.SubQuestions.ForEach(sq =>
|
||||
{
|
||||
// 如果 MajorQuestionGroup 下的 Question 包含子问题，则转为 QuestionGroupDto
|
||||
if (sq.SubQuestions != null && sq.SubQuestions.Any())
|
||||
{
|
||||
var subQgd = new QuestionGroupDto
|
||||
{
|
||||
Title = sq.Stem,
|
||||
Score = (int)sq.Score,
|
||||
Descript = "" // 默认为空
|
||||
};
|
||||
// 判断当前组是否有效：如果有描述，并且其父级链中没有任何一个组是有效组，则当前组有效
|
||||
subQgd.ValidQuestionGroup = !string.IsNullOrEmpty(subQgd.Descript) && !nextIsParentGroupValidChain;
|
||||
|
||||
ParseQuestionWithSubQuestions(sq, subQgd, subQgd.ValidQuestionGroup || nextIsParentGroupValidChain);
|
||||
qgd.SubQuestionGroups.Add(subQgd);
|
||||
}
|
||||
else // 如果 MajorQuestionGroup 下的 Question 没有子问题，则转为 SubQuestionDto
|
||||
{
|
||||
var subQd = new SubQuestionDto();
|
||||
// 只有当所有父组（包括当前组）都不是有效组时，这个题目才有效
|
||||
ParseSingleQuestion(sq, subQd, !nextIsParentGroupValidChain);
|
||||
qgd.SubQuestions.Add(subQd);
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 解析包含子问题的 Question，将其转换为 QuestionGroupDto
|
||||
// isParentGroupValidChain 参数表示从顶层到当前组的任一父组是否已经是“有效组”
|
||||
private static void ParseQuestionWithSubQuestions(Question question, QuestionGroupDto qgd, bool isParentGroupValidChain)
|
||||
{
|
||||
qgd.Title = question.Stem;
|
||||
qgd.Score = (int)question.Score;
|
||||
qgd.Descript = ""; // 默认为空
|
||||
|
||||
// 判断当前组是否有效：如果有描述，并且其父级链中没有任何一个组是有效组，则当前组有效
|
||||
qgd.ValidQuestionGroup = !string.IsNullOrEmpty(qgd.Descript) && !isParentGroupValidChain;
|
||||
|
||||
// 更新传递给子项的 isParentGroupValidChain 状态
|
||||
bool nextIsParentGroupValidChain = qgd.ValidQuestionGroup || isParentGroupValidChain;
|
||||
|
||||
|
||||
if (question.SubQuestions != null)
|
||||
{
|
||||
question.SubQuestions.ForEach(subQ =>
|
||||
{
|
||||
// 如果子问题本身还有子问题（多层嵌套），则继续创建 QuestionGroupDto
|
||||
if (subQ.SubQuestions != null && subQ.SubQuestions.Any())
|
||||
{
|
||||
var nestedQgd = new QuestionGroupDto
|
||||
{
|
||||
Title = subQ.Stem,
|
||||
Score = (int)subQ.Score,
|
||||
Descript = "" // 默认为空
|
||||
};
|
||||
// 判断当前组是否有效：如果有描述，并且其父级链中没有任何一个组是有效组，则当前组有效
|
||||
nestedQgd.ValidQuestionGroup = !string.IsNullOrEmpty(nestedQgd.Descript) && !nextIsParentGroupValidChain;
|
||||
|
||||
ParseQuestionWithSubQuestions(subQ, nestedQgd, nestedQgd.ValidQuestionGroup || nextIsParentGroupValidChain);
|
||||
qgd.SubQuestionGroups.Add(nestedQgd);
|
||||
}
|
||||
else // 如果子问题没有子问题，则直接创建 SubQuestionDto
|
||||
{
|
||||
var subQd = new SubQuestionDto();
|
||||
// 只有当所有父组（包括当前组）都不是有效组时，这个题目才有效
|
||||
ParseSingleQuestion(subQ, subQd, !nextIsParentGroupValidChain);
|
||||
qgd.SubQuestions.Add(subQd);
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 解析单个 Question (没有子问题) 为 SubQuestionDto
|
||||
private static void ParseSingleQuestion(Question question, SubQuestionDto subQd, bool validQ)
|
||||
{
|
||||
subQd.Stem = question.Stem;
|
||||
subQd.Score = (int)question.Score;
|
||||
subQd.ValidQuestion = validQ; // 根据传入的 validQ 确定是否是“有效题目”
|
||||
subQd.SampleAnswer = question.SampleAnswer;
|
||||
subQd.QuestionType = question.QuestionType;
|
||||
// 注意：DifficultyLevel 在本地 Question 中没有，如果服务器需要，可能需要补充默认值或从其他地方获取
|
||||
// subQd.DifficultyLevel = ...;
|
||||
|
||||
if (question.Options != null)
|
||||
{
|
||||
question.Options.ForEach(o =>
|
||||
{
|
||||
subQd.Options.Add(new OptionDto { Value = o.Label + o.Text });
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
public static string SerializeExamDto(this ExamDto dto)
|
||||
{
|
||||
// 配置序列化选项（可选）
|
||||
var options = new JsonSerializerOptions
|
||||
{
|
||||
WriteIndented = true,
|
||||
PropertyNamingPolicy = JsonNamingPolicy.CamelCase,
|
||||
DefaultIgnoreCondition = JsonIgnoreCondition.WhenWritingNull
|
||||
};
|
||||
|
||||
return JsonSerializer.Serialize(dto, options);
|
||||
}
|
||||
|
||||
public static ExamDto DeserializeExamDto(string jsonString)
|
||||
{
|
||||
|
||||
var options = new JsonSerializerOptions
|
||||
{
|
||||
PropertyNamingPolicy = JsonNamingPolicy.CamelCase
|
||||
};
|
||||
|
||||
return JsonSerializer.Deserialize<ExamDto>(jsonString, options);
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
740
TechHelper.Client/Exam/ExamParse.cs
Normal file
740
TechHelper.Client/Exam/ExamParse.cs
Normal file
@@ -0,0 +1,740 @@
|
||||
using Entities.DTO;
|
||||
using System;
|
||||
using System.Collections.Generic;
|
||||
using System.Linq;
|
||||
using System.Text.RegularExpressions;
|
||||
|
||||
namespace TechHelper.Client.Exam
|
||||
{
|
||||
// --- 新增错误处理相关类 ---
|
||||
public class ParseError
|
||||
{
|
||||
public ParseErrorType Type { get; }
|
||||
public string Message { get; }
|
||||
public int? Index { get; } // 错误发生的文本索引或匹配项索引
|
||||
public string MatchedText { get; } // 如果与某个匹配项相关，记录其文本
|
||||
public Exception InnerException { get; } // 捕获到的原始异常
|
||||
|
||||
public ParseError(ParseErrorType type, string message, int? index = null, string matchedText = null, Exception innerException = null)
|
||||
{
|
||||
Type = type;
|
||||
Message = message;
|
||||
Index = index;
|
||||
MatchedText = matchedText;
|
||||
InnerException = innerException;
|
||||
}
|
||||
|
||||
public override string ToString()
|
||||
{
|
||||
var sb = new System.Text.StringBuilder();
|
||||
sb.Append($"[{Type}] {Message}");
|
||||
if (Index.HasValue) sb.Append($" (Index: {Index.Value})");
|
||||
if (!string.IsNullOrEmpty(MatchedText)) sb.Append($" (MatchedText: '{MatchedText}')");
|
||||
if (InnerException != null) sb.Append($" InnerException: {InnerException.Message}");
|
||||
return sb.ToString();
|
||||
}
|
||||
}
|
||||
|
||||
public enum ParseErrorType
|
||||
{
|
||||
Validation = 1, // 输入验证失败
|
||||
DataParsing = 2, // 数据解析失败（如数字转换）
|
||||
Structural = 3, // 结构性问题（如选项没有对应的问题）
|
||||
RegexMatchIssue = 4, // 正则表达式匹配结果不符合预期
|
||||
UnexpectedError = 5 // 未预料到的通用错误
|
||||
}
|
||||
|
||||
|
||||
public class ExamPaper
|
||||
{
|
||||
public string AssignmentTitle { get; set; } = "未识别试卷标题";
|
||||
public string Description { get; set; } = "未识别试卷描述";
|
||||
public string SubjectArea { get; set; } = "试卷类别";
|
||||
public List<MajorQuestionGroup> QuestionGroups { get; set; } = new List<MajorQuestionGroup>();
|
||||
public List<Question> TopLevelQuestions { get; set; } = new List<Question>();
|
||||
public List<ParseError> Errors { get; set; } = new List<ParseError>();
|
||||
}
|
||||
|
||||
public class MajorQuestionGroup
|
||||
{
|
||||
public string Title { get; set; } = string.Empty;
|
||||
public string Descript { get; set; } = string.Empty;
|
||||
public float Score { get; set; }
|
||||
public List<MajorQuestionGroup> SubQuestionGroups { get; set; } = new List<MajorQuestionGroup>();
|
||||
public List<Question> SubQuestions { get; set; } = new List<Question>();
|
||||
public int Priority { get; set; }
|
||||
}
|
||||
|
||||
public class Question
|
||||
{
|
||||
public string Number { get; set; } = string.Empty;
|
||||
public string Stem { get; set; } = string.Empty;
|
||||
public float Score { get; set; }
|
||||
public List<Option> Options { get; set; } = new List<Option>();
|
||||
public List<Question> SubQuestions { get; set; } = new List<Question>();
|
||||
public string SampleAnswer { get; set; } = string.Empty;
|
||||
public string QuestionType { get; set; } = string.Empty;
|
||||
public int Priority { get; set; }
|
||||
}
|
||||
|
||||
public class Option
|
||||
{
|
||||
public string Label { get; set; } = string.Empty;
|
||||
public string Text { get; set; } = string.Empty;
|
||||
}
|
||||
|
||||
|
||||
/// <summary>
|
||||
/// 表示一个带有优先级的正则表达式配置
|
||||
/// </summary>
|
||||
public class RegexPatternConfig
|
||||
{
|
||||
public string Pattern { get; set; } // 正则表达式字符串
|
||||
public int Priority { get; set; } // 优先级，数字越小优先级越高
|
||||
public Regex Regex { get; private set; } // 编译后的Regex对象，用于性能优化
|
||||
|
||||
public RegexPatternConfig(string pattern, int priority)
|
||||
{
|
||||
Pattern = pattern;
|
||||
Priority = priority;
|
||||
Regex = new Regex(pattern, RegexOptions.Multiline | RegexOptions.Compiled); // 多行模式，编译以提高性能
|
||||
}
|
||||
}
|
||||
|
||||
public enum ExamParserEnum
|
||||
{
|
||||
MajorQuestionGroupPatterns = 0,
|
||||
QuestionPatterns,
|
||||
OptionPatterns
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 试卷解析的配置类，包含所有正则表达式
|
||||
/// </summary>
|
||||
public class ExamParserConfig
|
||||
{
|
||||
public List<RegexPatternConfig> MajorQuestionGroupPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
public List<RegexPatternConfig> QuestionPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
public List<RegexPatternConfig> OptionPatterns { get; set; } = new List<RegexPatternConfig>();
|
||||
|
||||
public ExamParserConfig()
|
||||
{
|
||||
MajorQuestionGroupPatterns.Add(new RegexPatternConfig(@"^([一二三四五六七八九十]+)[、\.]\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 1));
|
||||
MajorQuestionGroupPatterns.Add(new RegexPatternConfig(@"^\(([一二三四五六七八九十]{1,2}|十[一二三四五六七八九])\)\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 2));
|
||||
|
||||
|
||||
// 模式 1: "1. 这是一个题目 (5分)" 或 "1. 这是一个题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^(\d+)\.\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 1));
|
||||
|
||||
// 模式 2: "(1) 这是一个子题目 (3分)" 或 "(1) 这是一个子题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^\((\d+)\)\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 2));
|
||||
|
||||
// 模式 3: "① 这是一个更深层次的子题目 (2分)" 或 "① 这是一个更深层次的子题目"
|
||||
QuestionPatterns.Add(new RegexPatternConfig(@"^[①②③④⑤⑥⑦⑧⑨⑩]+\s*(.+?)(?:\s*\(((\d+(?:\.\d+)?))\s*分\))?\s*$", 3));
|
||||
|
||||
|
||||
OptionPatterns.Add(new RegexPatternConfig(@"([A-Z]\.)\s*(.*?)(?=[A-Z]\.|$)", 1)); // 大写字母选项
|
||||
OptionPatterns.Add(new RegexPatternConfig(@"([a-z]\.)\s*(.*?)(?=[a-z]\.|$)", 1)); // 小写字母选项
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public class PotentialMatch
|
||||
{
|
||||
public int StartIndex { get; set; }
|
||||
public int EndIndex { get; set; } // 匹配到的结构在原始文本中的结束位置
|
||||
public string MatchedText { get; set; } // 匹配到的完整行或段落
|
||||
public Match RegexMatch { get; set; } // 原始的Regex.Match对象，方便获取捕获组
|
||||
public RegexPatternConfig PatternConfig { get; set; } // 匹配到的模式配置
|
||||
public MatchType Type { get; set; } // 枚举：MajorQuestionGroup, Question, Option, etc.
|
||||
}
|
||||
|
||||
public enum MatchType
|
||||
{
|
||||
MajorQuestionGroup,
|
||||
Question,
|
||||
Option,
|
||||
Other // 如果有其他需要识别的类型
|
||||
}
|
||||
|
||||
|
||||
/// <summary>
|
||||
/// 负责扫描原始文本，收集所有潜在的匹配项（题组、题目、选项）。
|
||||
/// 它只进行匹配，不进行结构化归属。
|
||||
/// </summary>
|
||||
public class ExamDocumentScanner
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
|
||||
public ExamDocumentScanner(ExamParserConfig config)
|
||||
{
|
||||
_config = config ?? throw new ArgumentNullException(nameof(config)); // 确保配置不为空
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 扫描给定的文本，返回所有潜在的匹配项，并按起始位置排序。
|
||||
/// </summary>
|
||||
/// <param name="text">要扫描的文本</param>
|
||||
/// <returns>所有匹配到的 PotentialMatch 列表</returns>
|
||||
public List<PotentialMatch> Scan(string text)
|
||||
{
|
||||
if (string.IsNullOrEmpty(text))
|
||||
{
|
||||
return new List<PotentialMatch>(); // 对于空文本，直接返回空列表
|
||||
}
|
||||
|
||||
var allPotentialMatches = new List<PotentialMatch>();
|
||||
|
||||
// 扫描所有题组模式
|
||||
foreach (var patternConfig in _config.MajorQuestionGroupPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.MajorQuestionGroup
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 扫描所有题目模式
|
||||
foreach (var patternConfig in _config.QuestionPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.Question
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 扫描所有选项模式
|
||||
foreach (var patternConfig in _config.OptionPatterns)
|
||||
{
|
||||
foreach (Match match in patternConfig.Regex.Matches(text))
|
||||
{
|
||||
allPotentialMatches.Add(new PotentialMatch
|
||||
{
|
||||
StartIndex = match.Index,
|
||||
EndIndex = match.Index + match.Length,
|
||||
MatchedText = match.Value,
|
||||
RegexMatch = match,
|
||||
PatternConfig = patternConfig,
|
||||
Type = MatchType.Option
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// 统一按起始位置排序
|
||||
return allPotentialMatches.OrderBy(pm => pm.StartIndex).ToList();
|
||||
}
|
||||
}
|
||||
|
||||
public class ExamStructureBuilder
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
|
||||
public ExamStructureBuilder(ExamParserConfig config)
|
||||
{
|
||||
_config = config ?? throw new ArgumentNullException(nameof(config), "ExamParserConfig cannot be null.");
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Builds the ExamPaper structure from raw text and potential matches.
|
||||
/// Collects and returns parsing errors encountered during the process.
|
||||
/// </summary>
|
||||
/// <param name="fullExamText">The complete text of the exam paper.</param>
|
||||
/// <param name="allPotentialMatches">A list of all identified potential matches.</param>
|
||||
/// <returns>An ExamPaper object containing the parsed structure and a list of errors.</returns>
|
||||
/// <exception cref="ArgumentException">Thrown if fullExamText is null or empty.</exception>
|
||||
/// <exception cref="ArgumentNullException">Thrown if allPotentialMatches is null.</exception>
|
||||
public ExamPaper BuildExamPaper(string fullExamText, List<PotentialMatch> allPotentialMatches)
|
||||
{
|
||||
// 核心输入验证仍然是必要的，因为这些错误是无法恢复的
|
||||
if (string.IsNullOrWhiteSpace(fullExamText))
|
||||
{
|
||||
throw new ArgumentException("Full exam text cannot be null or empty.", nameof(fullExamText));
|
||||
}
|
||||
if (allPotentialMatches == null)
|
||||
{
|
||||
throw new ArgumentNullException(nameof(allPotentialMatches), "Potential matches list cannot be null.");
|
||||
}
|
||||
|
||||
var examPaper = new ExamPaper(); // ExamPaper 现在包含一个 Errors 列表
|
||||
|
||||
// 尝试获取试卷标题
|
||||
try
|
||||
{
|
||||
examPaper.AssignmentTitle = GetExamTitle(fullExamText);
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// 如果获取标题失败，记录错误而不是抛出致命异常
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError, "Failed to extract exam title.", innerException: ex));
|
||||
examPaper.AssignmentTitle = "未识别试卷标题"; // 提供默认值
|
||||
}
|
||||
|
||||
var majorQGStack = new Stack<MajorQuestionGroup>();
|
||||
MajorQuestionGroup currentMajorQG = null;
|
||||
|
||||
var questionStack = new Stack<Question>();
|
||||
Question currentQuestion = null;
|
||||
|
||||
int currentContentStart = 0;
|
||||
|
||||
// 处理试卷开头的描述性文本
|
||||
if (allPotentialMatches.Any() && allPotentialMatches[0].StartIndex > 0)
|
||||
{
|
||||
string introText = fullExamText.Substring(0, allPotentialMatches[0].StartIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(introText))
|
||||
{
|
||||
examPaper.Description += (string.IsNullOrWhiteSpace(examPaper.Description) ? "" : "\n") + introText;
|
||||
}
|
||||
}
|
||||
|
||||
currentContentStart = allPotentialMatches[0].StartIndex;
|
||||
|
||||
for (int i = 0; i < allPotentialMatches.Count; i++)
|
||||
{
|
||||
var pm = allPotentialMatches[i];
|
||||
|
||||
|
||||
try
|
||||
{
|
||||
// **数据验证：不再抛出，而是记录错误**
|
||||
if (pm.StartIndex < currentContentStart || pm.EndIndex > fullExamText.Length || pm.StartIndex > pm.EndIndex)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.Validation,
|
||||
$"PotentialMatch at index {i} has invalid start/end indices. Start: {pm.StartIndex}, End: {pm.EndIndex}, CurrentContentStart: {currentContentStart}, FullTextLength: {fullExamText.Length}",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
currentContentStart = Math.Max(currentContentStart, pm.EndIndex); // 尝试跳过这个损坏的匹配项
|
||||
continue; // 跳过当前循环迭代，处理下一个匹配项
|
||||
}
|
||||
if (pm.RegexMatch == null || pm.PatternConfig == null)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.Validation,
|
||||
$"PotentialMatch at index {i} is missing RegexMatch or PatternConfig.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
currentContentStart = Math.Max(currentContentStart, pm.EndIndex); // 尝试跳过这个损坏的匹配项
|
||||
continue; // 跳过当前循环迭代，处理下一个匹配项
|
||||
}
|
||||
|
||||
string precedingText = fullExamText.Substring(currentContentStart, pm.StartIndex - currentContentStart).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(precedingText))
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
// 将 examPaper.Errors 传递给 ProcessQuestionContent 收集错误
|
||||
ProcessQuestionContent(currentQuestion, precedingText,
|
||||
GetSubMatchesForRange(allPotentialMatches, currentContentStart, pm.StartIndex, examPaper.Errors),
|
||||
examPaper.Errors);
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.Descript += (string.IsNullOrWhiteSpace(currentMajorQG.Descript) ? "" : "\n") + precedingText;
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.Description += (string.IsNullOrWhiteSpace(examPaper.Description) ? "" : "\n") + precedingText;
|
||||
}
|
||||
}
|
||||
|
||||
if (pm.Type == MatchType.MajorQuestionGroup)
|
||||
{
|
||||
// 对 MajorQuestionGroup 的处理
|
||||
try
|
||||
{
|
||||
while (majorQGStack.Any() && pm.PatternConfig.Priority <= majorQGStack.Peek().Priority)
|
||||
{
|
||||
majorQGStack.Pop();
|
||||
}
|
||||
|
||||
// RegexMatch Groups 验证：不再抛出，记录错误
|
||||
if (pm.RegexMatch.Groups.Count < 2 || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[1].Value))
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.RegexMatchIssue,
|
||||
$"MajorQuestionGroup match at index {i} does not have enough regex groups or a valid title group (Group 1). Skipping this group.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
currentContentStart = pm.EndIndex; // 继续，尝试跳过此项
|
||||
continue;
|
||||
}
|
||||
|
||||
float score = 0;
|
||||
// 使用 float.TryParse 避免异常
|
||||
if (pm.RegexMatch.Groups.Count > 3 && pm.RegexMatch.Groups[4].Success) // 假设纯数字分数是 Group 4
|
||||
{
|
||||
if (!float.TryParse(pm.RegexMatch.Groups[4].Value, out score))
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.DataParsing,
|
||||
$"Failed to parse score '{pm.RegexMatch.Groups[4].Value}' for MajorQuestionGroup at index {i}. Defaulting to 0.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
}
|
||||
}
|
||||
|
||||
MajorQuestionGroup newMajorQG = new MajorQuestionGroup
|
||||
{
|
||||
Title = pm.RegexMatch.Groups[2].Value.Trim(), // 标题是 Group 2
|
||||
Score = score,
|
||||
Priority = pm.PatternConfig.Priority,
|
||||
};
|
||||
|
||||
if (majorQGStack.Any())
|
||||
{
|
||||
majorQGStack.Peek().SubQuestionGroups.Add(newMajorQG);
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.QuestionGroups.Add(newMajorQG);
|
||||
}
|
||||
|
||||
currentContentStart = pm.EndIndex;
|
||||
majorQGStack.Push(newMajorQG);
|
||||
currentMajorQG = newMajorQG;
|
||||
questionStack.Clear();
|
||||
currentQuestion = null;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred during processing MajorQuestionGroup at index {i}.",
|
||||
index: i, matchedText: pm.MatchedText, innerException: ex));
|
||||
currentContentStart = pm.EndIndex; // 尝试跳过此项
|
||||
continue;
|
||||
}
|
||||
}
|
||||
else if (pm.Type == MatchType.Question)
|
||||
{
|
||||
// 对 Question 的处理
|
||||
try
|
||||
{
|
||||
while (questionStack.Any() && pm.PatternConfig.Priority <= questionStack.Peek().Priority)
|
||||
{
|
||||
questionStack.Pop();
|
||||
}
|
||||
|
||||
// RegexMatch Groups 验证
|
||||
if (pm.RegexMatch.Groups.Count < 3 || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[1].Value) || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[2].Value))
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.RegexMatchIssue,
|
||||
$"Question match at index {i} does not have enough regex groups or valid number/text groups (Group 1/2). Skipping this question.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
currentContentStart = pm.EndIndex; // 尝试跳过此项
|
||||
continue;
|
||||
}
|
||||
|
||||
float score = 0;
|
||||
// 使用 float.TryParse 避免异常
|
||||
if (pm.RegexMatch.Groups.Count > 4 && pm.RegexMatch.Groups[4].Success) // 假设纯数字分数是 Group 4
|
||||
{
|
||||
if (!float.TryParse(pm.RegexMatch.Groups[4].Value, out score))
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.DataParsing,
|
||||
$"Failed to parse score '{pm.RegexMatch.Groups[4].Value}' for Question at index {i}. Defaulting to 0.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
}
|
||||
}
|
||||
|
||||
Question newQuestion = new Question
|
||||
{
|
||||
Number = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Stem = pm.RegexMatch.Groups[2].Value.Trim(),
|
||||
Priority = pm.PatternConfig.Priority,
|
||||
Score = score // 赋值解析到的分数
|
||||
};
|
||||
|
||||
if (questionStack.Any())
|
||||
{
|
||||
questionStack.Peek().SubQuestions.Add(newQuestion);
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.SubQuestions.Add(newQuestion);
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.TopLevelQuestions.Add(newQuestion);
|
||||
}
|
||||
|
||||
currentContentStart = pm.EndIndex;
|
||||
questionStack.Push(newQuestion);
|
||||
currentQuestion = newQuestion;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred during processing Question at index {i}.",
|
||||
index: i, matchedText: pm.MatchedText, innerException: ex));
|
||||
currentContentStart = pm.EndIndex; // 尝试跳过此项
|
||||
continue;
|
||||
}
|
||||
}
|
||||
else if (pm.Type == MatchType.Option)
|
||||
{
|
||||
// 对 Option 的处理
|
||||
try
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
// RegexMatch Groups 验证
|
||||
if (pm.RegexMatch.Groups.Count < 3 || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[1].Value) || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[2].Value))
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.RegexMatchIssue,
|
||||
$"Option match at index {i} does not have enough regex groups or valid label/text groups (Group 1/2). Skipping this option.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
currentContentStart = pm.EndIndex; // 尝试跳过此项
|
||||
continue;
|
||||
}
|
||||
|
||||
Option newOption = new Option
|
||||
{
|
||||
Label = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Text = pm.RegexMatch.Groups[2].Value.Trim()
|
||||
};
|
||||
currentQuestion.Options.Add(newOption);
|
||||
}
|
||||
else
|
||||
{
|
||||
// 结构性问题：找到孤立的选项，记录错误但继续
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.Structural,
|
||||
$"Found isolated Option at index {i}. Options must belong to a question. Ignoring this option.",
|
||||
index: i, matchedText: pm.MatchedText));
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred during processing Option at index {i}.",
|
||||
index: i, matchedText: pm.MatchedText, innerException: ex));
|
||||
// 这里不需要 `continue`，因为即使出错也可能只是该选项的问题，不影响后续处理
|
||||
}
|
||||
}
|
||||
|
||||
currentContentStart = pm.EndIndex; // 更新当前内容起点
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// 捕获任何在处理单个 PotentialMatch 过程中未被更具体 catch 块捕获的意外错误
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred during main loop processing of PotentialMatch at index {i}.",
|
||||
index: i, matchedText: pm.MatchedText, innerException: ex));
|
||||
currentContentStart = Math.Max(currentContentStart, pm.EndIndex); // 尝试跳过当前匹配项，继续下一项
|
||||
// 这里不 `continue` 是因为外层循环会推进 `i`，但确保 `currentContentStart` 更新以避免无限循环
|
||||
}
|
||||
}
|
||||
|
||||
// --- 处理所有匹配项之后的剩余内容 ---
|
||||
if (currentContentStart < fullExamText.Length)
|
||||
{
|
||||
try
|
||||
{
|
||||
string remainingText = fullExamText.Substring(currentContentStart).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(remainingText))
|
||||
{
|
||||
if (currentQuestion != null)
|
||||
{
|
||||
ProcessQuestionContent(currentQuestion, remainingText,
|
||||
GetSubMatchesForRange(allPotentialMatches, currentContentStart, fullExamText.Length, examPaper.Errors),
|
||||
examPaper.Errors);
|
||||
}
|
||||
else if (currentMajorQG != null)
|
||||
{
|
||||
currentMajorQG.Descript += (string.IsNullOrWhiteSpace(currentMajorQG.Descript) ? "" : "\n") + remainingText;
|
||||
}
|
||||
else
|
||||
{
|
||||
examPaper.Description += (string.IsNullOrWhiteSpace(examPaper.Description) ? "" : "\n") + remainingText;
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
examPaper.Errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
"An unexpected error occurred while processing remaining text after all potential matches.",
|
||||
innerException: ex));
|
||||
}
|
||||
}
|
||||
|
||||
return examPaper;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Extracts the exam title (simple implementation).
|
||||
/// Logs errors to the provided error list instead of throwing.
|
||||
/// </summary>
|
||||
private string GetExamTitle(string examPaperText)
|
||||
{
|
||||
// 内部不再直接抛出异常，而是让外部的 try-catch 负责
|
||||
var firstLine = examPaperText.Split(new[] { '\r', '\n' }, StringSplitOptions.RemoveEmptyEntries)
|
||||
.FirstOrDefault(line => !string.IsNullOrWhiteSpace(line));
|
||||
return firstLine ?? "未识别试卷标题";
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Gets a subset of the given PotentialMatch list within a specified range.
|
||||
/// Logs errors to the provided error list instead of throwing.
|
||||
/// </summary>
|
||||
private List<PotentialMatch> GetSubMatchesForRange(List<PotentialMatch> allMatches, int start, int end, List<ParseError> errors)
|
||||
{
|
||||
// 输入验证，如果输入错误，记录错误并返回空列表
|
||||
if (start < 0 || end < start)
|
||||
{
|
||||
errors.Add(new ParseError(ParseErrorType.Validation,
|
||||
$"Invalid range provided to GetSubMatchesForRange. Start: {start}, End: {end}.",
|
||||
index: start)); // 使用 start 作为大概索引
|
||||
return new List<PotentialMatch>();
|
||||
}
|
||||
// allMatches 为 null 的情况已经在 BuildExamPaper 顶部处理，这里为了方法的健壮性可以再加一次检查
|
||||
if (allMatches == null)
|
||||
{
|
||||
return new List<PotentialMatch>();
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
return allMatches.Where(pm => pm.StartIndex >= start && pm.StartIndex < end).ToList();
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred getting sub-matches for range [{start}, {end}).",
|
||||
innerException: ex));
|
||||
return new List<PotentialMatch>(); // 出错时返回空列表
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Processes the content of a Question, mainly for parsing Options and identifying unstructured text.
|
||||
/// Logs errors to the provided error list instead of throwing.
|
||||
/// </summary>
|
||||
private void ProcessQuestionContent(Question question, string contentText, List<PotentialMatch> potentialMatchesInScope, List<ParseError> errors)
|
||||
{
|
||||
// 参数验证，这些是内部方法的契约，如果违反则直接抛出，因为这意味着调用者有错
|
||||
if (question == null) throw new ArgumentNullException(nameof(question), "Question cannot be null in ProcessQuestionContent.");
|
||||
if (contentText == null) throw new ArgumentNullException(nameof(contentText), "Content text cannot be null in ProcessQuestionContent.");
|
||||
if (potentialMatchesInScope == null) throw new ArgumentNullException(nameof(potentialMatchesInScope), "Potential matches in scope cannot be null.");
|
||||
|
||||
|
||||
try
|
||||
{
|
||||
int lastOptionEndIndex = 0;
|
||||
|
||||
foreach (var pm in potentialMatchesInScope.OrderBy(p => p.StartIndex))
|
||||
{
|
||||
// 对每个匹配项的内部处理，记录错误但继续
|
||||
try
|
||||
{
|
||||
if (pm.Type == MatchType.Option)
|
||||
{
|
||||
// 验证索引，记录错误但继续
|
||||
if (pm.StartIndex < lastOptionEndIndex || pm.StartIndex > contentText.Length || pm.EndIndex > contentText.Length)
|
||||
{
|
||||
errors.Add(new ParseError(ParseErrorType.Validation,
|
||||
$"Option match at index {pm.StartIndex} has invalid indices within content text. MatchedText: '{pm.MatchedText}'. Skipping.",
|
||||
index: pm.StartIndex, matchedText: pm.MatchedText));
|
||||
continue; // 跳过当前选项
|
||||
}
|
||||
|
||||
// 处理选项前的文本
|
||||
if (pm.StartIndex > lastOptionEndIndex)
|
||||
{
|
||||
string textBeforeOption = contentText.Substring(lastOptionEndIndex, pm.StartIndex - lastOptionEndIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(textBeforeOption))
|
||||
{
|
||||
question.Stem += (string.IsNullOrWhiteSpace(question.Stem) ? "" : "\n") + textBeforeOption;
|
||||
}
|
||||
}
|
||||
|
||||
// RegexMatch Groups 验证，记录错误但继续
|
||||
if (pm.RegexMatch.Groups.Count < 3 || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[1].Value) || string.IsNullOrWhiteSpace(pm.RegexMatch.Groups[2].Value))
|
||||
{
|
||||
errors.Add(new ParseError(ParseErrorType.RegexMatchIssue,
|
||||
$"Option regex match '{pm.MatchedText}' does not have enough groups (expected 3) for label and text. Skipping option.",
|
||||
index: pm.StartIndex, matchedText: pm.MatchedText));
|
||||
lastOptionEndIndex = pm.EndIndex; // 更新索引，避免卡死
|
||||
continue; // 跳过当前选项
|
||||
}
|
||||
|
||||
var newOption = new Option
|
||||
{
|
||||
Label = pm.RegexMatch.Groups[1].Value.Trim(),
|
||||
Text = pm.RegexMatch.Groups[2].Value.Trim()
|
||||
};
|
||||
question.Options.Add(newOption);
|
||||
lastOptionEndIndex = pm.EndIndex;
|
||||
}
|
||||
// TODO: If there are SubQuestion types, they can be processed similarly here.
|
||||
// 你可以在此处添加对子问题的处理逻辑，同样需要小心处理其内容和嵌套。
|
||||
}
|
||||
catch (Exception innerEx)
|
||||
{
|
||||
errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred during processing a potential match ({pm.Type}) within question content.",
|
||||
index: pm.StartIndex, matchedText: pm.MatchedText, innerException: innerEx));
|
||||
lastOptionEndIndex = pm.EndIndex; // 尝试更新索引，避免无限循环
|
||||
continue; // 尝试继续下一个匹配项
|
||||
}
|
||||
}
|
||||
|
||||
// 处理所有选项之后的剩余文本
|
||||
if (lastOptionEndIndex < contentText.Length)
|
||||
{
|
||||
string remainingContent = contentText.Substring(lastOptionEndIndex).Trim();
|
||||
if (!string.IsNullOrWhiteSpace(remainingContent))
|
||||
{
|
||||
question.Stem += (string.IsNullOrWhiteSpace(question.Stem) ? "" : "\n") + remainingContent;
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// 捕获 ProcessQuestionContent 整个方法内部的意外错误
|
||||
errors.Add(new ParseError(ParseErrorType.UnexpectedError,
|
||||
$"An unexpected error occurred while processing content for Question '{question.Number}'.",
|
||||
innerException: ex));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public class ExamParser
|
||||
{
|
||||
private readonly ExamParserConfig _config;
|
||||
private readonly ExamDocumentScanner _scanner;
|
||||
private readonly ExamStructureBuilder _builder;
|
||||
|
||||
public ExamParser(ExamParserConfig config)
|
||||
{
|
||||
_config = config ?? throw new ArgumentNullException(nameof(config));
|
||||
_scanner = new ExamDocumentScanner(_config);
|
||||
_builder = new ExamStructureBuilder(_config);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// 解析给定的试卷文本，返回结构化的 ExamPaper 对象。
|
||||
/// </summary>
|
||||
/// <param name="examPaperText">完整的试卷文本</param>
|
||||
/// <returns>解析后的 ExamPaper 对象</returns>
|
||||
public ExamPaper ParseExamPaper(string examPaperText)
|
||||
{
|
||||
// 1. 扫描：一次性扫描整个文本，收集所有潜在的匹配项
|
||||
// Scan 方法现在已经优化为不抛出 ArgumentNullException
|
||||
List<PotentialMatch> allPotentialMatches = _scanner.Scan(examPaperText);
|
||||
|
||||
// 2. 构建：根据扫描结果和原始文本，线性遍历并构建层级结构
|
||||
// BuildExamPaper 现在会返回一个包含错误列表的 ExamPaper 对象
|
||||
// 外部不再需要捕获内部解析异常，只需检查 ExamPaper.Errors 列表
|
||||
return _builder.BuildExamPaper(examPaperText, allPotentialMatches);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2,6 +2,9 @@
|
||||
using TechHelper.Client.AI;
|
||||
using TechHelper.Services;
|
||||
using Entities.DTO;
|
||||
using System.Net.Http.Json;
|
||||
using Newtonsoft.Json;
|
||||
using TechHelper.Client.Pages.Exam;
|
||||
|
||||
|
||||
namespace TechHelper.Client.Exam
|
||||
@@ -9,10 +12,13 @@ namespace TechHelper.Client.Exam
|
||||
public class ExamService : IExamService
|
||||
{
|
||||
private IAIService aIService;
|
||||
private IHttpClientFactory httpClientFactory;
|
||||
|
||||
public ExamService(IAIService aIService)
|
||||
public ExamService(IAIService aIService,
|
||||
IHttpClientFactory httpClientFactory)
|
||||
{
|
||||
this.aIService = aIService;
|
||||
this.httpClientFactory = httpClientFactory;
|
||||
}
|
||||
|
||||
public ApiResponse ConvertToXML<T>(string xmlContent)
|
||||
@@ -86,7 +92,7 @@ namespace TechHelper.Client.Exam
|
||||
{
|
||||
Status = false,
|
||||
Result = null,
|
||||
Message = $"处理试题分割时发生内部错误: {ex.Message}"
|
||||
Message = $"处理试题分割时发生内部错误: {ex.Message}"
|
||||
};
|
||||
}
|
||||
}
|
||||
@@ -127,6 +133,31 @@ namespace TechHelper.Client.Exam
|
||||
}
|
||||
}
|
||||
|
||||
public async Task<ApiResponse> GetAllExam(string user)
|
||||
{
|
||||
using (var client = httpClientFactory.CreateClient("Default"))
|
||||
{
|
||||
var response = await client.GetAsync($"exam/getAllPreview?user={user}");
|
||||
|
||||
|
||||
if (response.IsSuccessStatusCode)
|
||||
{
|
||||
var content = await response.Content.ReadAsStringAsync();
|
||||
var result = JsonConvert.DeserializeObject<List<ExamDto>>(content);
|
||||
return ApiResponse.Success(result: result);
|
||||
}
|
||||
else
|
||||
{
|
||||
return ApiResponse.Error(await response.Content.ReadAsStringAsync());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
public async Task<ApiResponse> GetExam(Guid guid)
|
||||
{
|
||||
return ApiResponse.Success("HELLO");
|
||||
}
|
||||
|
||||
public async Task<ApiResponse> ParseSingleQuestionGroup(string examContent)
|
||||
{
|
||||
try
|
||||
@@ -163,9 +194,19 @@ namespace TechHelper.Client.Exam
|
||||
}
|
||||
}
|
||||
|
||||
public Task<ApiResponse> SaveParsedExam(ExamDto examDto)
|
||||
public async Task<ApiResponse> SaveParsedExam(ExamDto examDto)
|
||||
{
|
||||
throw new NotImplementedException();
|
||||
using (var client = httpClientFactory.CreateClient("Default"))
|
||||
{
|
||||
var respont = await client.PostAsJsonAsync("exam/add",
|
||||
examDto);
|
||||
|
||||
if (respont.StatusCode == System.Net.HttpStatusCode.OK)
|
||||
{
|
||||
return new ApiResponse(true, "ok");
|
||||
}
|
||||
return new ApiResponse("false");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -10,5 +10,8 @@ namespace TechHelper.Client.Exam
|
||||
public Task<ApiResponse> SaveParsedExam(ExamDto examDto);
|
||||
public Task<ApiResponse> ParseSingleQuestionGroup(string examContent);
|
||||
public ApiResponse ConvertToXML<T>(string xmlContent);
|
||||
|
||||
public Task<ApiResponse> GetAllExam(string user);
|
||||
public Task<ApiResponse> GetExam(Guid guid);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user