使用c#中的openxml sdk检测word文档中的粗体,下划线文本和标题

时间:2013-10-07 12:59:55

标签: c# .net ms-word openxml openxml-sdk

我想用C#中的openxml sdk检测选定word文档中的不同样式和标题。这就是我所拥有的:

 public string getWordDescription(string path)
        {
            string text = "";
            System.IO.Packaging.Package wordPackage = Package.Open(path, FileMode.Open, FileAccess.Read);
            using (WordprocessingDocument wordDocument =
WordprocessingDocument.Open(wordPackage))
            {              
                Body body = wordDocument.MainDocumentPart.Document.Body;
                if (body != null)
                {
                    foreach (Paragraph par in body.Descendants<Paragraph>())
                    {                                              
                        text += par.InnerText;
                        text += "<br />";                                              
                    }
                }
            }
            return text;
        }

因此,在循环段落时,我想以某种方式检测是否应用了某些样式或段落是否正在进行。

3 个答案:

答案 0 :(得分:4)

请记住,Paragraphs是块,块由运行组成。所以在你的foreach循环中,你需要一个内循环来遍历运行。运行元素容器RunProperty元素,用于描述内联格式。或者我相信你只能使用一个循环,如下面的

foreach (Run run in body.Descendants<Run>())
{
   RunProperties props = run.Descendants<RunProperties>();
   if(props.Descendants<Bold>().First() != null) 
   {
      //then do something
   }

   text += run.Text;
   text += "<br />";                                              
}

答案 1 :(得分:2)

试试这个

private RunStyles checkForEmphasis(Paragraph pTag)
    {

        bool isItalic = false;
        bool isBold = false;
        bool isUnderline = false;
        foreach (Run r in pTag.Descendants<Run>())
        {
            if (r.RunProperties != null)
            {
                RunProperties rProp = r.RunProperties;
                if (rProp.Italic != null)
                {
                    int x;

                    isItalic = true;
                }
                else
                {
                    isItalic = false;
                }
                if (rProp.Bold != null)
                {
                    isBold = true;
                }
                else
                {
                    isBold = false;
                }
                if (rProp.Underline != null)
                {
                    isUnderline = true;
                }
                else
                {
                    isUnderline = false;
                }
            }
            else
            {
                isItalic = false;
                isBold = false;
                isUnderline = false;
            }
        }
        if (isItalic && isBold && isUnderline)
        {
            return RunStyles.AllStyles;
        }
        else if (isBold && isItalic)
        {
            return RunStyles.BoldItalic;
        }
        else if (isBold && isUnderline)
        {
            return RunStyles.BoldUnderLine;
        }
        else if (isItalic && isUnderline)
        {
            return RunStyles.ItalicUnderLine;
        }
        else if (isItalic)
        {
            return RunStyles.Italic;
        }
        else if (isBold)
        {
            return RunStyles.Bold;
        }
        else if (isUnderline)
        {
            return RunStyles.UnderLine;
        }
        else
        {
            return RunStyles.NoStyle;
        }

    }

Enum RunStyles

enum RunStyles
{
    AllStyles = 1,
    BoldItalic = 2,
    BoldUnderLine = 3,
    ItalicUnderLine = 4,
    Italic = 5,
    Bold = 6,
    UnderLine = 7,
    NoStyle = 0
}

基于此,你可以做你的事情。这是完整的段落。

希望这有帮助。

答案 2 :(得分:0)

//using MS word introp object   

 public static List<KeyValuePair<string, string>> GetBoldItalicUnderline(string strfilename, int style)//style=1 is bold and style=2 is italic and style=3
        {
            Microsoft.Office.Interop.Word.Application Objword = new Microsoft.Office.Interop.Word.Application();
            List<KeyValuePair<string, string>> data = new List<KeyValuePair<string, string>>();
            //creating the object of document class  
            Document objdoc = new Document();
           // Document objdoc = Objword.Documents.Add();
            try
            {
                dynamic FilePath = strfilename;
                dynamic NA = System.Type.Missing;
                objdoc = Objword.Documents.Open
                              (ref FilePath, ref NA, ref NA, ref NA, ref NA,
                               ref NA, ref NA, ref NA, ref NA,
                               ref NA, ref NA, ref NA, ref NA,
                               ref NA, ref NA, ref NA
                               );
                if (style == 1)
                {
                    Microsoft.Office.Interop.Word.Range rng = objdoc.Content;
                    Microsoft.Office.Interop.Word.Find find = rng.Find;
                    find.Font.Bold = 1;
                    find.Format = true;
                    while (find.Execute())
                    {
                        data.Add(new KeyValuePair<string, string>(rng.Text, "Bold"));
                    }
                }
                if (style == 2)
                {
                    Microsoft.Office.Interop.Word.Range rngitalic = objdoc.Content;
                    Microsoft.Office.Interop.Word.Find finditalic = rngitalic.Find;
                    finditalic.Font.Italic = 1;
                    finditalic.Format = true;
                    while (finditalic.Execute())
                    {
                        data.Add(new KeyValuePair<string, string>(rngitalic.Text, "Italic"));
                    }
                }
                if (style == 3)
                {
                    //Simgle Underline
                    Microsoft.Office.Interop.Word.Range rngunderline = objdoc.Content;
                    Microsoft.Office.Interop.Word.Find findunderline = rngunderline.Find;
                    findunderline.Font.Underline = WdUnderline.wdUnderlineSingle;
                    findunderline.Format = true;
                    while (findunderline.Execute())
                    {
                        // data.Add(rngunderline.Text);
                        data.Add(new KeyValuePair<string, string>(rngunderline.Text, "wdUnderlineSingle"));
                    }
                    //Dash
                    Microsoft.Office.Interop.Word.Range rngunderlineDash = objdoc.Content;
                    Microsoft.Office.Interop.Word.Find findunderlineDash = rngunderlineDash.Find;
                    findunderlineDash.Font.Underline = WdUnderline.wdUnderlineDash;
                    findunderlineDash.Format = true;
                    while (findunderlineDash.Execute())
                    {
                        //data.Add(rngunderlineDash.Text);
                        data.Add(new KeyValuePair<string, string>(rngunderlineDash.Text, "wdUnderlineDash"));
                    }
                    //DashHeavy



Microsoft.Office.Interop.Word.Range rngunderlineDashHeavy = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDashHeavy = rngunderlineDashHeavy.Find;
                findunderlineDashHeavy.Font.Underline = WdUnderline.wdUnderlineDashHeavy;
                findunderlineDashHeavy.Format = true;
                while (findunderlineDashHeavy.Execute())
                {
                    //  data.Add(rngunderlineDashHeavy.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDashHeavy.Text, "wdUnderlineDashHeavy"));
                }
                //DashLong
                Microsoft.Office.Interop.Word.Range rngunderlineDashLong = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDashLong = rngunderlineDashLong.Find;
                findunderlineDashLong.Font.Underline = WdUnderline.wdUnderlineDashLong;
                findunderlineDashLong.Format = true;
                while (findunderlineDashLong.Execute())
                {
                    // data.Add(rngunderlineDashLong.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDashLong.Text, "wdUnderlineDashLong"));
                }
                //DashLongHeavy
                Microsoft.Office.Interop.Word.Range rngunderlineDashLonghv = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDashLonghv = rngunderlineDashLonghv.Find;
                findunderlineDashLonghv.Font.Underline = WdUnderline.wdUnderlineDashLongHeavy;
                findunderlineDashLonghv.Format = true;
                while (findunderlineDashLonghv.Execute())
                {
                    // data.Add(rngunderlineDashLonghv.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDashLonghv.Text, "wdUnderlineDashLongHeavy"));
                }
                //DotDash
                Microsoft.Office.Interop.Word.Range rngunderlineDotDash = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDotDash = rngunderlineDotDash.Find;
                findunderlineDotDash.Font.Underline = WdUnderline.wdUnderlineDotDash;
                findunderlineDotDash.Format = true;
                while (findunderlineDotDash.Execute())
                {
                    //data.Add(rngunderlineDotDash.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDotDash.Text, "wdUnderlineDotDash"));
                }
                //DotDashHeavy
                Microsoft.Office.Interop.Word.Range rngunderlineDotDashHv = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDotDashHv = rngunderlineDotDashHv.Find;
                findunderlineDotDashHv.Font.Underline = WdUnderline.wdUnderlineDotDashHeavy;
                findunderlineDotDashHv.Format = true;
                while (findunderlineDotDashHv.Execute())
                {
                    //data.Add(rngunderlineDotDashHv.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDotDashHv.Text, "wdUnderlineDotDashHeavy"));
                }
                //DotDotDash

                Microsoft.Office.Interop.Word.Range rngunderlineDotDotDash = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDotDotDash = rngunderlineDotDotDash.Find;
                findunderlineDotDotDash.Font.Underline = WdUnderline.wdUnderlineDotDotDash;
                findunderlineDotDotDash.Format = true;
                while (findunderlineDotDotDash.Execute())
                {
                    // data.Add(rngunderlineDotDotDash.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDotDotDash.Text, "wdUnderlineDotDotDash"));
                }

                //DotDotDashHeavy
                Microsoft.Office.Interop.Word.Range rngunderlineDotDotDashHv = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDotDotDashHv = rngunderlineDotDotDashHv.Find;
                findunderlineDotDotDashHv.Font.Underline = WdUnderline.wdUnderlineDotDotDashHeavy;
                findunderlineDotDotDashHv.Format = true;
                while (findunderlineDotDotDashHv.Execute())
                {
                    //data.Add(rngunderlineDotDotDashHv.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDotDotDashHv.Text, "wdUnderlineDotDotDashHeavy"));
                }
                //Dotted
                Microsoft.Office.Interop.Word.Range rngunderlineDotted = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDotted = rngunderlineDotted.Find;
                findunderlineDotted.Font.Underline = WdUnderline.wdUnderlineDotted;
                findunderlineDotted.Format = true;
                while (findunderlineDotted.Execute())
                {
                    // data.Add(rngunderlineDotted.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDotted.Text, "wdUnderlineDotted"));
                }
                //DottedHeavy
                Microsoft.Office.Interop.Word.Range rngunderlineDottedHv = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDottedHv = rngunderlineDottedHv.Find;
                findunderlineDottedHv.Font.Underline = WdUnderline.wdUnderlineDottedHeavy;
                findunderlineDottedHv.Format = true;
                while (findunderlineDottedHv.Execute())
                {
                    //data.Add(rngunderlineDottedHv.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDottedHv.Text, "wdUnderlineDottedHeavy"));
                }
                //DoubleUnderline
                Microsoft.Office.Interop.Word.Range rngunderlineDouble = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineDouble = rngunderlineDouble.Find;
                findunderlineDouble.Font.Underline = WdUnderline.wdUnderlineDouble;
                findunderlineDouble.Format = true;
                while (findunderlineDouble.Execute())
                {
                    // data.Add(rngunderlineDouble.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineDouble.Text, "wdUnderlineDouble"));
                }
                //Thick
                Microsoft.Office.Interop.Word.Range rngunderlineThick = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineThick = rngunderlineThick.Find;
                findunderlineThick.Font.Underline = WdUnderline.wdUnderlineThick;
                findunderlineThick.Format = true;
                while (findunderlineThick.Execute())
                {
                    // data.Add(rngunderlineThick.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineThick.Text, "wdUnderlineThick"));
                }
                //Wavy
                Microsoft.Office.Interop.Word.Range rngunderlineWavy = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineWavy = rngunderlineWavy.Find;
                findunderlineWavy.Font.Underline = WdUnderline.wdUnderlineWavy;
                findunderlineWavy.Format = true;
                while (findunderlineWavy.Execute())
                {
                    // data.Add(rngunderlineWavy.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineWavy.Text, "wdUnderlineWavy"));
                }
                //wavyDouble
                Microsoft.Office.Interop.Word.Range rngunderlineWavyDbl = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineWavyDbl = rngunderlineWavyDbl.Find;
                findunderlineWavyDbl.Font.Underline = WdUnderline.wdUnderlineWavyDouble;
                findunderlineWavyDbl.Format = true;
                while (findunderlineWavyDbl.Execute())
                {
                    //data.Add(rngunderlineWavyDbl.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineWavyDbl.Text, "wdUnderlineWavyDouble"));
                }
                //WavyHeavy
                Microsoft.Office.Interop.Word.Range rngunderlineWavyHv = objdoc.Content;
                Microsoft.Office.Interop.Word.Find findunderlineWavyHv = rngunderlineWavyHv.Find;
                findunderlineWavyHv.Font.Underline = WdUnderline.wdUnderlineWavyHeavy;
                findunderlineWavyHv.Format = true;
                while (findunderlineWavyHv.Execute())
                {
                    //  data.Add(rngunderlineWavyHv.Text);
                    data.Add(new KeyValuePair<string, string>(rngunderlineWavyHv.Text, "wdUnderlineWavyHeavy"));
                }
            }
            return data;
        }
        catch (Exception ex)
        {
            throw ex;
        }
        finally
        {
            if (objdoc != null)
            {
                ((_Document)objdoc).Close();
                System.Runtime.InteropServices.Marshal.ReleaseComObject(objdoc);
                objdoc = null;
            }
            Process[] processes = Process.GetProcessesByName("winword");
            foreach (var process in processes)
            {
                process.Close();
            }
            GC.Collect();
            GC.WaitForPendingFinalizers();
        }
    }