Office文件的奥秘——.NET平台下不借助Office实现Word、Powerpoint等文件的解析(一)

#region 字段
private FileStream m_stream;
private BinaryReader m_reader;
private Int64 m_length;
private DirectoryEntry m_dirRootEntry;

#region 头部信息
private UInt32 m_sectorSize;//Sector大小
private UInt32 m_miniSectorSize;//Mini-Sector大小
private UInt32 m_fatCount;//FAT数量
private UInt32 m_dirStartSectorID;//Directory开始的SectorID
private UInt32 m_miniFatStartSectorID;//Mini-FAT开始的SectorID
private UInt32 m_miniFatCount;//Mini-FAT数量
private UInt32 m_difStartSectorID;//DIF开始的SectorID
private UInt32 m_difCount;//DIF数量
#endregion
#endregion

#region 读取头部信息
private void ReadHeader()
{
    if (this.m_reader == null)
    {
        return;
    }

    //先判断是否是Office文件格式
    Byte[] sig = (this.m_length > 512 ? this.m_reader.ReadBytes(8) : null);
    if (sig == null ||
        sig[0] != 0xD0 || sig[1] != 0xCF || sig[2] != 0x11 || sig[3] != 0xE0 ||
        sig[4] != 0xA1 || sig[5] != 0xB1 || sig[6] != 0x1A || sig[7] != 0xE1)
    {
        throw new Exception("该文件不是Office文件！");
    }

    //读取头部信息
    this.m_stream.Seek(22, SeekOrigin.Current);
    this.m_sectorSize = (UInt32)Math.Pow(2, this.m_reader.ReadUInt16());
    this.m_miniSectorSize = (UInt32)Math.Pow(2, this.m_reader.ReadUInt16());

    this.m_stream.Seek(10, SeekOrigin.Current);
    this.m_fatCount = this.m_reader.ReadUInt32();
    this.m_dirStartSectorID = this.m_reader.ReadUInt32();

    this.m_stream.Seek(8, SeekOrigin.Current);
    this.m_miniFatStartSectorID = this.m_reader.ReadUInt32();
    this.m_miniFatCount = this.m_reader.ReadUInt32();
    this.m_difStartSectorID = this.m_reader.ReadUInt32();
    this.m_difCount = this.m_reader.ReadUInt32();
}
#endregion

public enum DirectoryEntryType : byte
{
    Invalid = 0,
    Storage = 1,
    Stream = 2,
    LockBytes = 3,
    Property = 4,
    Root = 5
}

public class DirectoryEntry
{
    #region 字段
    private UInt32 m_entryID;
    private String m_entryName;
    private DirectoryEntryType m_entryType;
    private UInt32 m_sectorID;
    private UInt32 m_length;

    private DirectoryEntry m_parent;
    private List<DirectoryEntry> m_children;
    #endregion

    #region 属性
    /// <summary>
    /// 获取DirectoryEntry的EntryID
    /// </summary>
    public UInt32 EntryID
    {
        get { return this.m_entryID; }
    }

    /// <summary>
    /// 获取DirectoryEntry名称
    /// </summary>
    public String EntryName
    {
        get { return this.m_entryName; }
    }

    /// <summary>
    /// 获取DirectoryEntry类型
    /// </summary>
    public DirectoryEntryType EntryType
    {
        get { return this.m_entryType; }
    }

    /// <summary>
    /// 获取DirectoryEntry的SectorID
    /// </summary>
    public UInt32 SectorID
    {
        get { return this.m_sectorID; }
    }

    /// <summary>
    /// 获取DirectoryEntry的内容大小
    /// </summary>
    public UInt32 Length
    {
        get { return this.m_length; }
    }

    /// <summary>
    /// 获取DirectoryEntry的父节点
    /// </summary>
    public DirectoryEntry Parent
    {
        get { return this.m_parent; }
    }

    /// <summary>
    /// 获取DirectoryEntry的子节点
    /// </summary>
    public List<DirectoryEntry> Children
    {
        get { return this.m_children; }
    }
    #endregion

    #region 构造函数
    /// <summary>
    /// 初始化新的DirectoryEntry
    /// </summary>
    /// <param name="parent">父节点</param>
    /// <param name="entryID">DirectoryEntryID</param>
    /// <param name="entryName">DirectoryEntry名称</param>
    /// <param name="entryType">DirectoryEntry类型</param>
    /// <param name="sectorID">SectorID</param>
    /// <param name="length">内容大小</param>
    public DirectoryEntry(DirectoryEntry parent, UInt32 entryID, String entryName, DirectoryEntryType entryType, UInt32 sectorID, UInt32 length)
    {
        this.m_entryID = entryID;
        this.m_entryName = entryName;
        this.m_entryType = entryType;
        this.m_sectorID = sectorID;
        this.m_length = length;
        this.m_parent = parent;

        if (entryType == DirectoryEntryType.Root || entryType == DirectoryEntryType.Storage)
        {
            this.m_children = new List<DirectoryEntry>();
        }
    }
    #endregion

    #region 方法
    public void AddChild(DirectoryEntry entry)
    {
        if (this.m_children == null)
        {
            this.m_children = new List<DirectoryEntry>();
        }

        this.m_children.Add(entry);
    }

    public DirectoryEntry GetChild(String entryName)
    {
        for (Int32 i = 0; i < this.m_children.Count; i++)
        {
            if (String.Equals(this.m_children[i].EntryName, entryName))
            {
                return this.m_children[i];
            }
        }

        return null;
    }
    #endregion
}

#region 常量
private const UInt32 HeaderSize = 0x200;//512字节
private const UInt32 DirectoryEntrySize = 0x80;//128字节
#endregion

#region 读取目录信息
private void ReadDirectory()
{
    if (this.m_reader == null)
    {
        return;
    }

    UInt32 leftSiblingEntryID, rightSiblingEntryID, childEntryID;
    this.m_dirRootEntry = GetDirectoryEntry(0, null, out leftSiblingEntryID, out rightSiblingEntryID, out childEntryID);
    this.ReadDirectoryEntry(this.m_dirRootEntry, childEntryID);
}

private void ReadDirectoryEntry(DirectoryEntry rootEntry, UInt32 entryID)
{
    UInt32 leftSiblingEntryID, rightSiblingEntryID, childEntryID;
    DirectoryEntry entry = GetDirectoryEntry(entryID, rootEntry, out leftSiblingEntryID, out rightSiblingEntryID, out childEntryID);

    if (entry == null || entry.EntryType == DirectoryEntryType.Invalid)
    {
        return;
    }
    
    rootEntry.AddChild(entry);

    if (leftSiblingEntryID < UInt32.MaxValue)//有左兄弟节点
    {
        this.ReadDirectoryEntry(rootEntry, leftSiblingEntryID);
    }

    if (rightSiblingEntryID < UInt32.MaxValue)//有右兄弟节点
    {
        this.ReadDirectoryEntry(rootEntry, rightSiblingEntryID);
    }

    if (childEntryID < UInt32.MaxValue)//有孩子节点
    {
        this.ReadDirectoryEntry(entry, childEntryID);
    }
}

private DirectoryEntry GetDirectoryEntry(UInt32 entryID, DirectoryEntry parentEntry, out UInt32 leftSiblingEntryID, out UInt32 rightSiblingEntryID, out UInt32 childEntryID)
{
    leftSiblingEntryID = UInt16.MaxValue;
    rightSiblingEntryID = UInt16.MaxValue;
    childEntryID = UInt16.MaxValue;

    this.m_stream.Seek(GetDirectoryEntryOffset(entryID), SeekOrigin.Begin);

    if (this.m_stream.Position >= this.m_length)
    {
        return null;
    }

    StringBuilder temp = new StringBuilder();
    for (Int32 i = 0; i < 32; i++)
    {
        temp.Append((Char)this.m_reader.ReadUInt16());
    }

    UInt16 nameLen = this.m_reader.ReadUInt16();
    String name = (temp.ToString(0, (temp.Length < (nameLen / 2 - 1) ? temp.Length : nameLen / 2 - 1)));
    Byte type = this.m_reader.ReadByte();

    if (type > 5)
    {
        return null;
    }

    this.m_stream.Seek(1, SeekOrigin.Current);
    leftSiblingEntryID = this.m_reader.ReadUInt32();
    rightSiblingEntryID = this.m_reader.ReadUInt32();
    childEntryID = this.m_reader.ReadUInt32();

    this.m_stream.Seek(36, SeekOrigin.Current);
    UInt32 sectorID = this.m_reader.ReadUInt32();
    UInt32 length = this.m_reader.ReadUInt32();

    return new DirectoryEntry(parentEntry, entryID, name, (DirectoryEntryType)type, sectorID, length);
}
#endregion

#region 辅助方法
private Int64 GetSectorOffset(UInt32 sectorID)
{
    return HeaderSize + this.m_sectorSize * sectorID;
}

private Int64 GetDirectoryEntryOffset(UInt32 sectorID)
{
    return HeaderSize + this.m_sectorSize * this.m_dirStartSectorID + DirectoryEntrySize * sectorID;
}
#endregion