c# - OpenXML Excel : throw error in any word after mail address

Question

我使用 OpenXml 读取 Excel 文件。一切正常，但如果电子表格包含一个单元格，其中有一个地址邮件，然后是一个空格和另一个单词，例如:

abc@abc.com abc

它在打开电子表格时立即抛出异常:

var _doc = SpreadsheetDocument.Open(_filePath, false); 

异常(exception):

DocumentFormat.OpenXml.Packaging.OpenXmlPackageException
Additional information:
Invalid Hyperlink: Malformed URI is embedded as a hyperlink in the document.

Answer 1

OpenXml 论坛上有一个与此问题相关的未解决问题:Malformed Hyperlink causes exception

在博文中，他们谈到了在 Word 文档中遇到格式错误的“mailto:”超链接的问题。

他们在这里提出了一个变通办法:Workaround for malformed hyperlink exception

解决方法本质上是一个小型控制台应用程序，它可以找到无效的 URL 并将其替换为硬编码值；这是他们进行替换的样本中的代码片段；您可以扩充此代码以尝试更正传递的 brokenUri:

private static Uri FixUri(string brokenUri)
{
    return new Uri("http://broken-link/");
}

我遇到的问题实际上是 Excel 文档(就像您一样)，它与格式错误的 http URL 有关；我惊喜地发现他们的代码与我的 Excel 文件一起工作得很好。

这是整个变通源代码，以防万一这些链接之一在将来消失:

 void Main(string[] args)
    {
        var fileName = @"C:\temp\corrupt.xlsx";
        var newFileName = @"c:\temp\Fixed.xlsx";
        var newFileInfo = new FileInfo(newFileName);

        if (newFileInfo.Exists)
            newFileInfo.Delete();

        File.Copy(fileName, newFileName);

        WordprocessingDocument wDoc;
        try
        {
            using (wDoc = WordprocessingDocument.Open(newFileName, true))
            {
                ProcessDocument(wDoc);
            }
        }
        catch (OpenXmlPackageException e)
        {
            e.Dump();
            if (e.ToString().Contains("The specified package is not valid."))
            {
                using (FileStream fs = new FileStream(newFileName, FileMode.OpenOrCreate, FileAccess.ReadWrite))
                {
                    UriFixer.FixInvalidUri(fs, brokenUri => FixUri(brokenUri));
                }               
            }
        }
    }

    private static Uri FixUri(string brokenUri)
    {
        brokenUri.Dump();
        return new Uri("http://broken-link/");
    }

    private static void ProcessDocument(WordprocessingDocument wDoc)
    {
        var elementCount = wDoc.MainDocumentPart.Document.Descendants().Count();
        Console.WriteLine(elementCount);
    }
}

public static class UriFixer
{
    public static void FixInvalidUri(Stream fs, Func<string, Uri> invalidUriHandler)
    {
        XNamespace relNs = "http://schemas.openxmlformats.org/package/2006/relationships";
        using (ZipArchive za = new ZipArchive(fs, ZipArchiveMode.Update))
        {
            foreach (var entry in za.Entries.ToList())
            {
                if (!entry.Name.EndsWith(".rels"))
                    continue;
                bool replaceEntry = false;
                XDocument entryXDoc = null;
                using (var entryStream = entry.Open())
                {
                    try
                    {
                        entryXDoc = XDocument.Load(entryStream);
                        if (entryXDoc.Root != null && entryXDoc.Root.Name.Namespace == relNs)
                        {
                            var urisToCheck = entryXDoc
                                .Descendants(relNs + "Relationship")
                                .Where(r => r.Attribute("TargetMode") != null && (string)r.Attribute("TargetMode") == "External");
                            foreach (var rel in urisToCheck)
                            {
                                var target = (string)rel.Attribute("Target");
                                if (target != null)
                                {
                                    try
                                    {
                                        Uri uri = new Uri(target);
                                    }
                                    catch (UriFormatException)
                                    {
                                        Uri newUri = invalidUriHandler(target);
                                        rel.Attribute("Target").Value = newUri.ToString();
                                        replaceEntry = true;
                                    }
                                }
                            }
                        }
                    }
                    catch (XmlException)
                    {
                        continue;
                    }
                }
                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);
                    }
                }
            }
        }
    }