【发布时间】:2010-12-15 10:41:44
【问题描述】:
有人有这个的 c# 变体吗?
这样我就可以获取一些 html 并显示它,而不会中断作为文章的摘要引导?
Truncate text containing HTML, ignoring tags
免得我重新发明轮子!
编辑
对不起,新来的,你的权利,应该更好地表达这个问题,这里有更多信息
我希望获取一个 html 字符串并将其截断为一定数量的单词(甚至是字符长度),这样我就可以将它的开头显示为摘要(然后引出主要文章)。我希望保留 html,以便在预览中显示链接等。
我必须解决的主要问题是,如果我们在 1 个或多个标签的中间截断,我们很可能会得到未闭合的 html 标签!
我对解决方案的想法是
首先将 html 截断为 N 个单词(单词更好,但字符可以)(确保不要停在标签中间并截断 require 属性)
在这个被截断的字符串中处理打开的 html 标记(也许我会一直把它们粘在堆栈上?)
然后处理结束标签并确保它们在我弹出它们时与堆栈上的标签匹配?
如果在此之后有任何打开的标签留在堆栈上,则将它们写入截断字符串的末尾,html 应该很好!!!!
2009 年 12 月 11 日编辑
- 到目前为止,这是我在 VS2008 中作为单元测试文件拼凑起来的内容,这“可能”对将来的某人有所帮助
- 我基于 Jan 代码的 hack 尝试在 char 版本 + word 版本的顶部(免责声明:这是肮脏的粗略代码!!就我而言)
- 我假设在所有情况下都使用“格式良好”的 HTML(但不一定是根据 XML 版本具有根节点的完整文档)
- Abels XML 版本处于底部,但还没有完全让测试在这个版本上运行(另外需要理解代码)...
- 我会在有机会改进时更新
- 发布代码时遇到问题?堆栈上没有上传工具吗?
感谢所有 cmets :)
using System;
using System.Collections.Generic;
using System.Text.RegularExpressions;
using System.Xml;
using System.Xml.XPath;
using Microsoft.VisualStudio.TestTools.UnitTesting;
namespace PINET40TestProject
{
[TestClass]
public class UtilityUnitTest
{
public static string TruncateHTMLSafeishChar(string text, int charCount)
{
bool inTag = false;
int cntr = 0;
int cntrContent = 0;
// loop through html, counting only viewable content
foreach (Char c in text)
{
if (cntrContent == charCount) break;
cntr++;
if (c == '<')
{
inTag = true;
continue;
}
if (c == '>')
{
inTag = false;
continue;
}
if (!inTag) cntrContent++;
}
string substr = text.Substring(0, cntr);
//search for nonclosed tags
MatchCollection openedTags = new Regex("<[^/](.|\n)*?>").Matches(substr);
MatchCollection closedTags = new Regex("<[/](.|\n)*?>").Matches(substr);
// create stack
Stack<string> opentagsStack = new Stack<string>();
Stack<string> closedtagsStack = new Stack<string>();
// to be honest, this seemed like a good idea then I got lost along the way
// so logic is probably hanging by a thread!!
foreach (Match tag in openedTags)
{
string openedtag = tag.Value.Substring(1, tag.Value.Length - 2);
// strip any attributes, sure we can use regex for this!
if (openedtag.IndexOf(" ") >= 0)
{
openedtag = openedtag.Substring(0, openedtag.IndexOf(" "));
}
// ignore brs as self-closed
if (openedtag.Trim() != "br")
{
opentagsStack.Push(openedtag);
}
}
foreach (Match tag in closedTags)
{
string closedtag = tag.Value.Substring(2, tag.Value.Length - 3);
closedtagsStack.Push(closedtag);
}
if (closedtagsStack.Count < opentagsStack.Count)
{
while (opentagsStack.Count > 0)
{
string tagstr = opentagsStack.Pop();
if (closedtagsStack.Count == 0 || tagstr != closedtagsStack.Peek())
{
substr += "</" + tagstr + ">";
}
else
{
closedtagsStack.Pop();
}
}
}
return substr;
}
public static string TruncateHTMLSafeishWord(string text, int wordCount)
{
bool inTag = false;
int cntr = 0;
int cntrWords = 0;
Char lastc = ' ';
// loop through html, counting only viewable content
foreach (Char c in text)
{
if (cntrWords == wordCount) break;
cntr++;
if (c == '<')
{
inTag = true;
continue;
}
if (c == '>')
{
inTag = false;
continue;
}
if (!inTag)
{
// do not count double spaces, and a space not in a tag counts as a word
if (c == 32 && lastc != 32)
cntrWords++;
}
}
string substr = text.Substring(0, cntr) + " ...";
//search for nonclosed tags
MatchCollection openedTags = new Regex("<[^/](.|\n)*?>").Matches(substr);
MatchCollection closedTags = new Regex("<[/](.|\n)*?>").Matches(substr);
// create stack
Stack<string> opentagsStack = new Stack<string>();
Stack<string> closedtagsStack = new Stack<string>();
foreach (Match tag in openedTags)
{
string openedtag = tag.Value.Substring(1, tag.Value.Length - 2);
// strip any attributes, sure we can use regex for this!
if (openedtag.IndexOf(" ") >= 0)
{
openedtag = openedtag.Substring(0, openedtag.IndexOf(" "));
}
// ignore brs as self-closed
if (openedtag.Trim() != "br")
{
opentagsStack.Push(openedtag);
}
}
foreach (Match tag in closedTags)
{
string closedtag = tag.Value.Substring(2, tag.Value.Length - 3);
closedtagsStack.Push(closedtag);
}
if (closedtagsStack.Count < opentagsStack.Count)
{
while (opentagsStack.Count > 0)
{
string tagstr = opentagsStack.Pop();
if (closedtagsStack.Count == 0 || tagstr != closedtagsStack.Peek())
{
substr += "</" + tagstr + ">";
}
else
{
closedtagsStack.Pop();
}
}
}
return substr;
}
public static string TruncateHTMLSafeishCharXML(string text, int charCount)
{
// your data, probably comes from somewhere, or as params to a methodint
XmlDocument xml = new XmlDocument();
xml.LoadXml(text);
// create a navigator, this is our primary tool
XPathNavigator navigator = xml.CreateNavigator();
XPathNavigator breakPoint = null;
// find the text node we need:
while (navigator.MoveToFollowing(XPathNodeType.Text))
{
string lastText = navigator.Value.Substring(0, Math.Min(charCount, navigator.Value.Length));
charCount -= navigator.Value.Length;
if (charCount <= 0)
{
// truncate the last text. Here goes your "search word boundary" code:
navigator.SetValue(lastText);
breakPoint = navigator.Clone();
break;
}
}
// first remove text nodes, because Microsoft unfortunately merges them without asking
while (navigator.MoveToFollowing(XPathNodeType.Text))
{
if (navigator.ComparePosition(breakPoint) == XmlNodeOrder.After)
{
navigator.DeleteSelf();
}
}
// moves to parent, then move the rest
navigator.MoveTo(breakPoint);
while (navigator.MoveToFollowing(XPathNodeType.Element))
{
if (navigator.ComparePosition(breakPoint) == XmlNodeOrder.After)
{
navigator.DeleteSelf();
}
}
// moves to parent
// then remove *all* empty nodes to clean up (not necessary):
// TODO, add empty elements like <br />, <img /> as exclusion
navigator.MoveToRoot();
while (navigator.MoveToFollowing(XPathNodeType.Element))
{
while (!navigator.HasChildren && (navigator.Value ?? "").Trim() == "")
{
navigator.DeleteSelf();
}
}
// moves to parent
navigator.MoveToRoot();
return navigator.InnerXml;
}
[TestMethod]
public void TestTruncateHTMLSafeish()
{
// Case where we just make it to start of HREF (so effectively an empty link)
// 'simple' nested none attributed tags
Assert.AreEqual(@"<h1>1234</h1><b><i>56789</i>012</b>",
TruncateHTMLSafeishChar(
@"<h1>1234</h1><b><i>56789</i>012345</b>",
12));
// In middle of a!
Assert.AreEqual(@"<h1>1234</h1><a href=""testurl""><b>567</b></a>",
TruncateHTMLSafeishChar(
@"<h1>1234</h1><a href=""testurl""><b>5678</b></a><i><strong>some italic nested in string</strong></i>",
7));
// more
Assert.AreEqual(@"<div><b><i><strong>1</strong></i></b></div>",
TruncateHTMLSafeishChar(
@"<div><b><i><strong>12</strong></i></b></div>",
1));
// br
Assert.AreEqual(@"<h1>1 3 5</h1><br />6",
TruncateHTMLSafeishChar(
@"<h1>1 3 5</h1><br />678<br />",
6));
}
[TestMethod]
public void TestTruncateHTMLSafeishWord()
{
// zero case
Assert.AreEqual(@" ...",
TruncateHTMLSafeishWord(
@"",
5));
// 'simple' nested none attributed tags
Assert.AreEqual(@"<h1>one two <br /></h1><b><i>three ...</i></b>",
TruncateHTMLSafeishWord(
@"<h1>one two <br /></h1><b><i>three </i>four</b>",
3), "we have added ' ...' to end of summary");
// In middle of a!
Assert.AreEqual(@"<h1>one two three </h1><a href=""testurl""><b class=""mrclass"">four ...</b></a>",
TruncateHTMLSafeishWord(
@"<h1>one two three </h1><a href=""testurl""><b class=""mrclass"">four five </b></a><i><strong>some italic nested in string</strong></i>",
4));
// start of h1
Assert.AreEqual(@"<h1>one two three ...</h1>",
TruncateHTMLSafeishWord(
@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i>",
3));
// more than words available
Assert.AreEqual(@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i> ...",
TruncateHTMLSafeishWord(
@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i>",
99));
}
[TestMethod]
public void TestTruncateHTMLSafeishWordXML()
{
// zero case
Assert.AreEqual(@" ...",
TruncateHTMLSafeishWord(
@"",
5));
// 'simple' nested none attributed tags
string output = TruncateHTMLSafeishCharXML(
@"<body><h1>one two </h1><b><i>three </i>four</b></body>",
13);
Assert.AreEqual(@"<body>\r\n <h1>one two </h1>\r\n <b>\r\n <i>three</i>\r\n </b>\r\n</body>", output,
"XML version, no ... yet and addeds '\r\n + spaces?' to format document");
// In middle of a!
Assert.AreEqual(@"<h1>one two three </h1><a href=""testurl""><b class=""mrclass"">four ...</b></a>",
TruncateHTMLSafeishCharXML(
@"<body><h1>one two three </h1><a href=""testurl""><b class=""mrclass"">four five </b></a><i><strong>some italic nested in string</strong></i></body>",
4));
// start of h1
Assert.AreEqual(@"<h1>one two three ...</h1>",
TruncateHTMLSafeishCharXML(
@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i>",
3));
// more than words available
Assert.AreEqual(@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i> ...",
TruncateHTMLSafeishCharXML(
@"<h1>one two three </h1><a href=""testurl""><b>four five </b></a><i><strong>some italic nested in string</strong></i>",
99));
}
}
}
【问题讨论】:
-
如果有人编辑了您现在链接到的帖子怎么办? IMO,最好在您自己的帖子中尽可能准确地描述您的问题。
-
感谢您的更新,我将根据当前方法制定解决方案;-)
-
谢谢大家,我自己在这里尝试一些肮脏的方式,但不确定它有多少里程,如果我能找到一个体面的可行解决方案,我会发布
-
如果你厌倦了尝试肮脏的方式,我尝试了一种“干净的方式”算法,它提供了足够的扩展空间。它会正确地切割一个节点,不管它在哪里。使用 XML(与 XHTML 一样)的好处是,您犯的任何错误都会被系统捕获,但有一个很好的例外:早期退化原则。
-
感谢 Abel,尝试集成您的代码。