如何删除 Word 文档的最后作者和修订号

Question

我有以下代码来删除 Word 文档的最后作者和修订号

using Microsoft.Office.Core;
using Word = Microsoft.Office.Interop.Word;
using System.Reflection;
using System.IO;
...


Word.Application oWord;
Word._Document oDoc;

oWord = new Word.Application();
oWord.Visible = false;

List<string> lstDocFile = new List<string>();
//Add doc files here
List<string> g_lstCheck = new List<string>();
//Add list check here "Last Author" and "Revision Number"

foreach (string path in lstDocFile)
{
    oDoc = oWord.Documents.Open(path, ReadOnly: false);
    foreach (string chkItem in g_lstCheck)
    {
        strValue = oDoc.BuiltInDocumentProperties[chkItem].Value;
        if (!string.IsNullOrEmpty(strValue))
        {
            oDoc.BuiltInDocumentProperties[chkItem].Value = string.Empty);
        }
    }
    oDoc.Close(Word.WdSaveOptions.wdSaveChanges);
}
oWord.Quit(Word.WdSaveOptions.wdDoNotSaveChanges);

在代码运行之后，我希望最后作者和修订号为空字符串。但结果是 Last Author 变成了我，Revision Number 增加了 1。我知道发生这种情况是因为我使用以下代码来保存 word 文档

oDoc.Close(Word.WdSaveOptions.wdSaveChanges);

请帮我用 C# 删除最后作者和修订号。

Answer 1

*根据 this article，作者 Mr.Vivek Singh 为我们提供了一些有用的代码。

**我们还有来自 Microsoft 的 this library -Dsofile.dll。

这样走。

第 1 步：下载 Dsofile.dll 库 (**)，解压缩并获取文件 Interop。Dsofile.dll（检索日期 8/8/2017）

第 2 步：为您的 C# 项目添加对文件 Interop 的引用。Dsofile.dll。

第 3 步：使用此代码（我从文章 * 编辑 - 感谢 Vivek Singh，我只是删除 OleDocumentPropertiesClass 中的单词 Class 以防止构建错误，并稍微编辑一下解决这个问题）

        string fileName = "";//Add the full path of the Word file

        OleDocumentProperties myDSOOleDocument = new OleDocumentProperties();
        myDSOOleDocument.Open(fileName, false,
 DSOFile.dsoFileOpenOptions.dsoOptionOpenReadOnlyIfNoWriteAccess);

        myDSOOleDocument.SummaryProperties.LastSavedBy = string.Empty;
       //myDSOOleDocument.SummaryProperties.RevisionNumber = string.Empty; //This can't be edit -readonly

        myDSOOleDocument.Save();
        myDSOOleDocument.Close();

无论如何，我无法编辑 RevisionNumber，因为它是只读的。好吧，我只能满足于我能得到的。

Answer 2

对于.docx（打开Xml）文件，最简单的方法是使用官方Open XML SDK nuget package。有了这个，操作文档属性就非常容易了：

// open for read write
using (var package = WordprocessingDocument.Open("myfile.docx", true))
{
    // modify properties
    package.PackageProperties.Creator = null;
    package.PackageProperties.LastModifiedBy = null;
    package.PackageProperties.Revision = null;
}

对于 .doc（Word .97->2003）文件，这里有一个 C# 小方法可以删除属性（技术上存储 completely differently）：

RemoveProperties("myfile.doc", SummaryInformationFormatId, PIDSI_AUTHOR, PIDSI_REVNUMBER, PIDSI_LASTAUTHOR);

...

public static void RemoveProperties(string filePath, Guid propertySet, params int[] ids)
{
    if (filePath == null)
        throw new ArgumentNullException(nameof(filePath));

    if (ids == null || ids.Length == 0)
        return;

    int hr = StgOpenStorageEx(filePath, STGM.STGM_DIRECT_SWMR | STGM.STGM_READWRITE | STGM.STGM_SHARE_DENY_WRITE, STGFMT.STGFMT_ANY, 0, IntPtr.Zero, IntPtr.Zero, typeof(IPropertySetStorage).GUID, out IPropertySetStorage setStorage);
    if (hr != 0)
        throw new Win32Exception(hr);

    try
    {
        hr = setStorage.Open(propertySet, STGM.STGM_READWRITE | STGM.STGM_SHARE_EXCLUSIVE, out IPropertyStorage storage);
        if (hr != 0)
        {
            const int STG_E_FILENOTFOUND = unchecked((int)0x80030002);
            if (hr == STG_E_FILENOTFOUND)
                return;

            throw new Win32Exception(hr);
        }

        var props = new List<PROPSPEC>();
        foreach (int id in ids)
        {
            var prop = new PROPSPEC();
            prop.ulKind = PRSPEC.PRSPEC_PROPID;
            prop.union.propid = id;
            props.Add(prop);
        }
        storage.DeleteMultiple(props.Count, props.ToArray());
        storage.Commit(0);
    }
    finally
    {
        Marshal.ReleaseComObject(setStorage);
    }
}

// "The Summary Information Property Set"
// https://msdn.microsoft.com/en-us/library/windows/desktop/aa380376.aspx
public static readonly Guid SummaryInformationFormatId = new Guid("F29F85E0-4FF9-1068-AB91-08002B27B3D9");
public const int PIDSI_AUTHOR = 4;
public const int PIDSI_LASTAUTHOR = 8;
public const int PIDSI_REVNUMBER = 9;

[Flags]
private enum STGM
{
    STGM_READ = 0x00000000,
    STGM_READWRITE = 0x00000002,
    STGM_SHARE_DENY_NONE = 0x00000040,
    STGM_SHARE_DENY_WRITE = 0x00000020,
    STGM_SHARE_EXCLUSIVE = 0x00000010,
    STGM_DIRECT_SWMR = 0x00400000
}

private enum STGFMT
{
    STGFMT_STORAGE = 0,
    STGFMT_FILE = 3,
    STGFMT_ANY = 4,
    STGFMT_DOCFILE = 5
}

[StructLayout(LayoutKind.Sequential)]
private struct PROPSPEC
{
    public PRSPEC ulKind;
    public PROPSPECunion union;
}

[StructLayout(LayoutKind.Explicit)]
private struct PROPSPECunion
{
    [FieldOffset(0)]
    public int propid;
    [FieldOffset(0)]
    public IntPtr lpwstr;
}

private enum PRSPEC
{
    PRSPEC_LPWSTR = 0,
    PRSPEC_PROPID = 1
}

[DllImport("ole32.dll")]
private static extern int StgOpenStorageEx([MarshalAs(UnmanagedType.LPWStr)] string pwcsName, STGM grfMode, STGFMT stgfmt, int grfAttrs, IntPtr pStgOptions, IntPtr reserved2, [MarshalAs(UnmanagedType.LPStruct)] Guid riid, out IPropertySetStorage ppObjectOpen);

[Guid("0000013A-0000-0000-C000-000000000046"), InterfaceTypeAttribute(ComInterfaceType.InterfaceIsIUnknown)]
private interface IPropertySetStorage
{
    void Unused1();
    [PreserveSig]
    int Open([MarshalAs(UnmanagedType.LPStruct)] Guid rfmtid, STGM grfMode, out IPropertyStorage storage);
}

[Guid("00000138-0000-0000-C000-000000000046"), InterfaceTypeAttribute(ComInterfaceType.InterfaceIsIUnknown)]
private interface IPropertyStorage
{
    void Unused1();
    void Unused2();
    void DeleteMultiple(int cpspec, [MarshalAs(UnmanagedType.LPArray, SizeParamIndex = 0)] PROPSPEC[] rgpspec);
    void Unused4();
    void Unused5();
    void Unused6();
    void Commit(uint grfCommitFlags);
    // rest ommited
}

如何删除 Word 文档的最后作者和修订号

How to remove Last Author and Revision Number of Word Document

c#

ms-word

office-interop

com-interop