Office文件的奥秘——.NET平台下不借助Office实现Word、Powerpoint等文件的解析(二)

  1 #region 字段
  2 private UInt16 m_nFib;
  3 private Boolean m_isComplexFile;
  4 private Boolean m_hasPictures;
  5 private Boolean m_isEncrypted;
  6 private Boolean m_is1Table;
  7 
  8 private UInt16 m_lidFE;
  9 
 10 private Int32 m_cbMac;
 11 private Int32 m_ccpText;
 12 private Int32 m_ccpFtn;
 13 private Int32 m_ccpHdd;
 14 private Int32 m_ccpAtn;
 15 private Int32 m_ccpEdn;
 16 private Int32 m_ccpTxbx;
 17 private Int32 m_ccpHdrTxbx;
 18 
 19 private UInt32 m_fcClx;
 20 private UInt32 m_lcbClx;
 21 #endregion
 22 
 23 #region 读取WordDocument
 24 private void ReadWordDocument()
 25 {
 26     DirectoryEntry entry = this.m_dirRootEntry.GetChild("WordDocument");
 27 
 28     if (entry == null)
 29     {
 30         return;
 31     }
 32 
 33     Int64 entryStart = this.GetSectorOffset(entry.SectorID);
 34     this.m_stream.Seek(entryStart, SeekOrigin.Begin);
 35 
 36     this.ReadFileInformationBlock();
 37 }
 38 
 39 #region 读取FileInformationBlock
 40 private void ReadFileInformationBlock()
 41 {
 42     this.ReadFibBase();
 43     this.ReadFibRgW97();
 44     this.ReadFibRgLw97();
 45     this.ReadFibRgFcLcb();
 46     this.ReadFibRgCswNew();
 47 }
 48 
 49 #region FibBase
 50 private void ReadFibBase()
 51 {
 52     UInt16 wIdent = this.m_reader.ReadUInt16();
 53     if (wIdent != 0xA5EC)
 54     {
 55         throw new Exception("该文件不是Word文件！");
 56     }
 57 
 58     this.m_nFib = this.m_reader.ReadUInt16();
 59     this.m_reader.ReadUInt16();//unused
 60     this.m_reader.ReadUInt16();//lid
 61     this.m_reader.ReadUInt16();//pnNext
 62 
 63     UInt16 flags = this.m_reader.ReadUInt16();
 64     this.m_isComplexFile = this.GetBitFromInteger(flags, 2);
 65     this.m_hasPictures = this.GetBitFromInteger(flags, 3);
 66     this.m_isEncrypted = this.GetBitFromInteger(flags, 8);
 67     this.m_is1Table = this.GetBitFromInteger(flags, 9);
 68 
 69     if (this.m_isComplexFile)
 70     {
 71         throw new Exception("不支持复杂文件的读取！");
 72     }
 73 
 74     if (this.m_isEncrypted)
 75     {
 76         throw new Exception("不支持加密文件的读取！");
 77     }
 78 
 79     this.m_stream.Seek(32 - 12, SeekOrigin.Current);
 80 }
 81 #endregion
 82 
 83 #region FibRgW97
 84 private void ReadFibRgW97()
 85 {
 86     UInt16 count = this.m_reader.ReadUInt16();
 87 
 88     if (count != 0x000E)
 89     {
 90         throw new Exception("FibRgW97长度错误！");
 91     }
 92 
 93     this.m_stream.Seek(26, SeekOrigin.Current);
 94     this.m_lidFE = this.m_reader.ReadUInt16();
 95 }
 96 #endregion
 97 
 98 #region FibRgLw97
 99 private void ReadFibRgLw97()
100 {
101     UInt16 count = this.m_reader.ReadUInt16();
102 
103     if (count != 0x0016)
104     {
105         throw new Exception("FibRgLw97长度错误！");
106     }
107 
108     this.m_cbMac = this.m_reader.ReadInt32();
109     this.m_reader.ReadInt32();//reserved1
110     this.m_reader.ReadInt32();//reserved2
111     this.m_ccpText = this.m_reader.ReadInt32();
112     this.m_ccpFtn = this.m_reader.ReadInt32();
113     this.m_ccpHdd = this.m_reader.ReadInt32();
114     this.m_reader.ReadInt32();//reserved3
115     this.m_ccpAtn = this.m_reader.ReadInt32();
116     this.m_ccpEdn = this.m_reader.ReadInt32();
117     this.m_ccpTxbx = this.m_reader.ReadInt32();
118     this.m_ccpHdrTxbx = this.m_reader.ReadInt32();
119 
120     this.m_stream.Seek(44, SeekOrigin.Current);
121 }
122 #endregion
123 
124 #region FibRgFcLcb
125 private void ReadFibRgFcLcb()
126 {
127     UInt16 count = this.m_reader.ReadUInt16();
128     this.m_stream.Seek(66 * 4, SeekOrigin.Current);
129 
130     this.m_fcClx = this.m_reader.ReadUInt32();
131     this.m_lcbClx = this.m_reader.ReadUInt32();
132 
133     this.m_stream.Seek((count * 2 - 68) * 4, SeekOrigin.Current);
134 }
135 #endregion
136 
137 #region FibRgCswNew
138 private void ReadFibRgCswNew()
139 {
140     UInt16 count = this.m_reader.ReadUInt16();
141     this.m_nFib = this.m_reader.ReadUInt16();
142     this.m_stream.Seek((count - 1) * 2, SeekOrigin.Current);
143 }
144 #endregion
145 #endregion
146 #endregion
147 
148 private Boolean GetBitFromInteger(Int32 integer, Int32 bitIndex)
149 {
150     Int32 num = (Int32)Math.Pow(2, bitIndex);
151     return (integer & num) == num;
152 }

 1 public class PieceElement
 2 {
 3     #region 字段
 4     private UInt16 m_info;
 5     private UInt32 m_fc;
 6     private UInt16 m_prm;
 7     private Boolean m_isUnicode;
 8     #endregion
 9 
10     #region 属性
11     /// <summary>
12     /// 获取是否以Unicode形式存储文本
13     /// </summary>
14     public Boolean IsUnicode
15     {
16         get { return this.m_isUnicode; }
17     }
18 
19     /// <summary>
20     /// 获取文本偏移量
21     /// </summary>
22     public UInt32 Offset
23     {
24         get { return this.m_fc; }
25     }
26     #endregion
27 
28     #region 构造函数
29     public PieceElement(UInt16 info, UInt32 fcCompressed, UInt16 prm)
30     {
31         this.m_info = info;
32         this.m_fc = fcCompressed & 0x3FFFFFFF;//后30位
33         this.m_prm = prm;
34         this.m_isUnicode = (fcCompressed & 0x40000000) == 0;//第31位
35 
36         if (!this.m_isUnicode) this.m_fc = this.m_fc / 2;
37     }
38     #endregion
39 }

 1 private void ReadTableStream()
 2 {
 3     DirectoryEntry entry = this.m_dirRootEntry.GetChild((this.m_is1Table ? "1Table" : "0Table"));
 4 
 5     if (entry == null)
 6     {
 7         return;
 8     }
 9 
10     Int64 pieceTableStart = this.GetSectorOffset(entry.SectorID) + this.m_fcClx;
11     Int64 pieceTableEnd = pieceTableStart + this.m_lcbClx;
12     this.m_stream.Seek(pieceTableStart, SeekOrigin.Begin);
13 
14     Byte clxt = this.m_reader.ReadByte();
15     Int32 prcLen = 0;
16 
17     //判断如果是Prc不是Pcdt
18     while (clxt == 0x01 && this.m_stream.Position < pieceTableEnd)
19     {
20         this.m_stream.Seek(prcLen, SeekOrigin.Current);
21         clxt = this.m_reader.ReadByte();
22         prcLen = this.m_reader.ReadInt32();
23     }
24 
25     if (clxt != 0x02)
26     {
27         throw new Exception("该文件不存在内容！");
28     }
29 
30     UInt32 size = this.m_reader.ReadUInt32();
31     UInt32 count = (size - 4) / 12;
32 
33     this.m_lstPieceStartPosition = new List<UInt32>();
34     this.m_lstPieceEndPosition = new List<UInt32>();
35     this.m_lstPieceElement = new List<PieceElement>();
36 
37     for (Int32 i = 0; i < count; i++)
38     {
39         this.m_lstPieceStartPosition.Add(this.m_reader.ReadUInt32());
40         this.m_lstPieceEndPosition.Add(this.m_reader.ReadUInt32());
41         this.m_stream.Seek(-4, SeekOrigin.Current);
42     }
43 
44     this.m_stream.Seek(4, SeekOrigin.Current);
45 
46     for (Int32 i = 0; i < count; i++)
47     {
48         UInt16 info = this.m_reader.ReadUInt16();
49         UInt32 fcCompressed = this.m_reader.ReadUInt32();
50         UInt16 prm = this.m_reader.ReadUInt16();
51 
52         this.m_lstPieceElement.Add(new PieceElement(info, fcCompressed, prm));
53     }
54 }