[Office 2010 開發 ] 利用 OpenXML 來分析您的 Word 文件的格式有哪些

2010-05-19

[Office 2010 開發 ] 利用 OpenXML 來了解您的 Word 文件的格式有哪些

在本文中您將會知道/學到：

而在本文中將會主要介紹下方幾項實作內容：

>> 這是範本檔案內容。有段落、表格、粗體等….

>> 標題部份為標題1

>> 顯示表格。

>> 這是針對上述 Word 文件的分析結果統計。

☆ 程式部份

◇ 請先建立一個 Concole Application (主控台)

◇ 再把 Program.cs 檔更改成如下的程式碼

   1:  using System;

   2:  using System.Collections.Generic;

   3:  using System.Linq;

   4:  using System.Text;

   5:  using DocumentFormat.OpenXml.Packaging;

   6:  using DocumentFormat.OpenXml.Wordprocessing;

7:

   8:  namespace QueryContentBasedOnStyles

   9:  {

  10:      class Program

  11:      {

  12:          static void Main(string[] args)

  13:          {

  14:              // 宣告各個變數名稱。

  15:              string paraStyle = "heading 1";

  16:              string runStyle = "Intense Emphasis";

  17:              string tableStyle = "Light List Accent 1";

18:

  19:              // 開啟 Word 檔案

  20:              using (WordprocessingDocument myDoc =

  21:                  WordprocessingDocument.Open("input.docx", true))

  22:              {

  23:                  //把剛開啟的檑案指定成 MainDocumentPart

  24:                  MainDocumentPart mainPart = myDoc.MainDocumentPart;

25:

  26:                  //依序針對下方所指定的樣式進行處理

  27:                  Console.WriteLine("Number of paragraphs with "

  28:                      + paraStyle + " styles: "

  29:                      + mainPart.ParagraphsByStyleName(paraStyle)

  30:                      .Count());

  31:                  Console.WriteLine("Number of runs with "

  32:                      + runStyle + " styles: "

  33:                      + mainPart.RunsByStyleName(runStyle).Count());

  34:                  Console.WriteLine("Number of tables with "

  35:                      + tableStyle + " styles: "

  36:                      + mainPart.TablesByStyleName(tableStyle)

  37:                      .Count());

  38:              }

39:

  40:              Console.ReadKey();

  41:          }

42:

43:

  44:      }

  45:  }

◇ 新增一個 WordStyleExtensions.cs 檔做為本次的 Open XML SDK 的 Extension Methods (延伸方法)，其程式碼如下：

   1:  using System;

   2:  using System.Collections.Generic;

   3:  using System.Linq;

   4:  using System.Text;

   5:  using DocumentFormat.OpenXml.Packaging;

   6:  using DocumentFormat.OpenXml.Wordprocessing;

7:

   8:  namespace QueryContentBasedOnStyles

   9:  {

  10:      public static class WordStyleExtensions

  11:      {

  12:          // 取得樣式名稱

  13:          private static string GetStyleIdFromStyleName(

  14:              MainDocumentPart mainPart, string styleName)

  15:          {

  16:              StyleDefinitionsPart stylePart =

  17:                  mainPart.StyleDefinitionsPart;

18:

  19:              string styleId = stylePart.Styles

  20:                                  .Descendants<StyleName>()

  21:                                  .Where(s => s.Val.Value.Equals(styleName))

  22:                                  .Select(n => ((Style)n.Parent).StyleId)

  23:                                  .FirstOrDefault();

24:

  25:                 return styleId ?? styleName;

  26:          }

27:

  28:          // 段落

  29:          public static IEnumerable<Paragraph> ParagraphsByStyleName(

  30:              this MainDocumentPart mainPart, string styleName)

  31:          {

  32:              string styleId = GetStyleIdFromStyleName(mainPart, styleName);

33:

  34:              IEnumerable<Paragraph> paraList = mainPart.Document

  35:                          .Descendants<Paragraph>()

  36:                          .Where(p => IsParagraphInStyle(p, styleId));

37:

  38:              return paraList;

  39:          }

40:

  41:          //判斷是否為段落

  42:          private static bool IsParagraphInStyle(Paragraph p,

  43:              string styleId)

  44:          {

  45:              ParagraphProperties pPr = p

  46:                  .GetFirstChild<ParagraphProperties>();

47:

  48:              if (pPr != null)

  49:              {

  50:                  ParagraphStyleId paraStyle = pPr.ParagraphStyleId;

  51:                  if (paraStyle != null)

  52:                  {

  53:                      return paraStyle.Val.Value.Equals(styleId);

  54:                  }

  55:              }

  56:              return false;

  57:          }

58:

  59:          public static IEnumerable<Run> RunsByStyleName(

  60:              this MainDocumentPart mainPart, string styleName)

  61:          {

  62:              string styleId = GetStyleIdFromStyleName(mainPart, styleName);

63:

  64:              IEnumerable<Run> runList = mainPart.Document

  65:                      .Descendants<Run>()

  66:                      .Where(r => IsRunInStyle(r, styleId));

67:

  68:              return runList;

  69:          }

70:

  71:          private static bool IsRunInStyle(Run r, string styleId)

  72:          {

  73:              RunProperties rPr = r.GetFirstChild<RunProperties>();

74:

  75:              if (rPr != null)

  76:              {

  77:                  RunStyle runStyle = rPr.RunStyle;

  78:                  if (runStyle != null)

  79:                  {

  80:                      return runStyle.Val.Value.Equals(styleId);

  81:                  }

  82:              }

  83:              return false;

  84:          }

85:

  86:          //表格

  87:          public static IEnumerable<Table> TablesByStyleName(

  88:              this MainDocumentPart mainPart, string styleName)

  89:          {

  90:              string styleId = GetStyleIdFromStyleName(mainPart, styleName);

  91:              IEnumerable<Table> tableList = mainPart.Document

  92:                      .Descendants<Table>()

  93:                      .Where(t => IsTableInStyle(t, styleId));

94:

  95:              return tableList;

  96:          }

97:

  98:          //判斷是否為表格

  99:          private static bool IsTableInStyle(Table tbl, string styleId)

 100:          {

 101:              TableProperties tblPr = tbl.GetFirstChild<TableProperties>();

 102:

 103:              if (tblPr != null)

 104:              {

 105:                  TableStyle tblStyle = tblPr.TableStyle;

 106:                  if (tblStyle != null)

 107:                  {

 108:                      return tblStyle.Val.Value.Equals(styleId);

 109:                  }

 110:              }

 111:              return false;

 112:          }

 113:      }

 114:  }

---> 本文預設於 2010.05.20 登入「Office/Sharepoint 開發組」