/// <summary>
/// 用于对TXT文件进行分章
/// </summary>
/// <param name="total">文本内容</param>
/// <param name="bookTitle">书籍标题</param>
/// <returns></returns>
private List <Chapter> GetTxtChapters(string total, string bookTitle = "")
{
int count = 0;
List <Chapter> chapters = new List <Chapter>();
int number = 1;
Chapter chapter = new Chapter();
chapter.Title = bookTitle;
chapter.Index = 0;
chapter.StartLength = 0;
chapters.Add(chapter);
StringBuilder builder = new StringBuilder();
int parseLength = 0;
foreach (var line in total.Split(Environment.NewLine))
{
if (string.IsNullOrEmpty(line.Trim()))
{
parseLength += line.Length + Environment.NewLine.Length;
continue;
}
if (number >= 1)
{
string title = "";
if (IsExtra(line))
{
title = line;
}
else if (IsTitle(line))
{
title = ChapterDivisionRegex.Match(line).Value;
}
if (!string.IsNullOrEmpty(title))
{
count++;
parseLength += builder.ToString().Length;
builder.Clear();
chapter = new Chapter(count, title, parseLength);
chapters.Add(chapter);
number = 0;
}
}
builder.Append(line);
parseLength += Environment.NewLine.Length;
number++;
if (number >= MAX_TXT_PARSE_LINES)
{
//为了避免某个文档一直没有匹配到新章节而不停的向StringBuilder中添加内容,导致内存溢出，这里对StringBuilder的大小进行了一定的限制
//即解析的行数达到一定的数目之后，即使没有匹配到新章节也将StringBuilder清空，同时更新parseLength。
//注意：这个数目的设定会影响到解析的时间，请谨慎设置!!!!
parseLength += builder.ToString().Length;
builder.Clear();
number = 1;
}
}
return(chapters);
}
private bool IsTitle(string line)
{
var numberRegex = new Regex("^[第]?[0-9零一二三四五六七八九十百千]+$");
string title = "";
bool result = false;
result = ChapterDivisionRegex.IsMatch(line);
title = ChapterDivisionRegex.Match(line).Value;
if (result)
{
if (title.Length > MAX_CHAPTER_LENGTH)
{
return(false);
}
int temp_index = line.IndexOf(title);
if (temp_index > 0)
{
string prev = line.Substring(0, temp_index);
// 此举是为了检测是否有类似章节名的内容
for (int i = 0; i < prev.Length; i++)
{
if (prev[i] >= 0x4e00 && prev[i] <= 0x9fbb)
{
return(false);
}
}
}
//int index = 0;
//for (int i = 0; i < title.Length; i++)
//{
// if (ChapterEndKey.Any(p => p == title[i].ToString()))
// {
// index = i;
// break;
// }
//}
//if (index <= temp_index)
// index = line.Length;
//string chapter = title.Substring(temp_index, index - 1).Trim();
//if (!numberRegex.IsMatch(chapter))
//{
// result = false;
//}
}
return(result);
}
/// <summary>
/// 用于对TXT文件进行分章
/// </summary>
/// <param name="book">TXT文件</param>
/// <returns></returns>
private async Task <List <Chapter> > GetTxtChapters(StorageFile book)
{
if (book == null)
{
throw new ArgumentNullException();
}
int count = 0;
List <Chapter> chapters = new List <Chapter>();
var total = await GetTxtContent(book);
int number = 1;
Chapter chapter = new Chapter();
chapter.Title = book.DisplayName.Replace(".txt", "", StringComparison.OrdinalIgnoreCase);
chapter.Index = 0;
chapter.StartLength = 0;
chapters.Add(chapter);
StringBuilder builder = new StringBuilder();
int parseLength = 0;
foreach (var line in total.Split(Environment.NewLine))
{
if (string.IsNullOrEmpty(line.Trim()))
{
parseLength += line.Length + Environment.NewLine.Length;
continue;
}
if (number >= 1)
{
string title = "";
if (IsExtra(line))
{
title = line;
}
else if (IsTitle(line))
{
title = ChapterDivisionRegex.Match(line).Value;
}
if (!string.IsNullOrEmpty(title))
{
count++;
parseLength += builder.ToString().Length;
builder.Clear();
chapter = new Chapter(count, title, parseLength);
chapters.Add(chapter);
number = 0;
}
}
builder.Append(line);
parseLength += Environment.NewLine.Length;
number++;
if (number >= MAX_TXT_PARSE_LINES)
{
//为了避免某个文档一直没有匹配到新章节而不停的向StringBuilder中添加内容,导致内存溢出，这里对StringBuilder的大小进行了一定的限制
//即解析的行数达到一定的数目之后，即使没有匹配到新章节也将StringBuilder清空，同时更新parseLength。
//注意：这个数目的设定会影响到解析的时间，请谨慎设置!!!!
parseLength += builder.ToString().Length;
builder.Clear();
number = 1;
}
}
return(chapters);
}
