通过DocumentFormat.OpenXml解析PPTX文件时遇到异常:“\b”(十六进制值 0x08)是无效的字符,查看文件发现存在乱码,乱码的十六进制值刚好时异常中提到的0x08
网上有很多关于这类xml遇到无效字符异常的文章,其原因是xml中包含了不可打印的控制字符,解决办法是正则匹配替换这类字符。正则匹配的代码如下:
string r = "[\x00-\x08\x0B\x0C\x0E-\x1F\x26]";
return Regex.Replace(brokenXml, r, "", RegexOptions.Compiled);
原因和处理方式都有了,那么问题来了,加载PPTX文件的时候就抛出异常了,在什么时候替换xml中的控制字符呢?想起OpenXmlPowerTools的源码中关于处理文档中包含不合法的uri的代码,于是如法炮制,在加载页面slide的时候捕获XmlException类型的异常,在异常中修复xml内容
try
{
.......
}
catch (XmlException xe)
{
using (FileStream fs = new FileStream(filePath, FileMode.OpenOrCreate, FileAccess.ReadWrite))
{
XmlFixer.FixInvalidXml(fs, brokenXml =>
{
string r = "[\x00-\x08\x0B\x0C\x0E-\x1F\x26]";
return Regex.Replace(brokenXml, r, "", RegexOptions.Compiled);
});
}
return ReadPPTXText(filePath);
}
public static class XmlFixer
{
public static void FixInvalidXml(Stream fs,Func invalidXmlHandler)
{
using (ZipArchive za = new ZipArchive(fs, ZipArchiveMode.Update))
{
bool IsInvalidXml = false;
for (int i=0;i< za.Entries.Count;i++)
{
var entry = za.Entries[i];
if (!entry.Name.EndsWith(".xml"))
continue;
bool replaceEntry = false;
XDocument entryXDoc = null;
using (var entryStream = entry.Open())
{
try
{
if (IsInvalidXml)
{
string content;
using (StreamReader sr = new StreamReader(entryStream))
{
content = invalidXmlHandler(sr.ReadToEnd());
}
entryXDoc = XDocument.Parse(content);
IsInvalidXml = false;
replaceEntry = true;
}
else
{
entryXDoc = XDocument.Load(entryStream);
IsInvalidXml = false;
}
}
catch (XmlException xex)
{
i--;
IsInvalidXml = true;
}
}
if (replaceEntry)
{
var fullName = entry.FullName;
entry.Delete();
var newEntry = za.CreateEntry(fullName);
using (StreamWriter writer = new StreamWriter(newEntry.Open()))
using (XmlWriter xmlWriter = XmlWriter.Create(writer))
{
entryXDoc.WriteTo(xmlWriter);
}
}
}
}
}
}
手机扫一扫
移动阅读更方便
你可能感兴趣的文章