10

我有下面的一段代码。我想用“NewText”替换文本“Text1”,这是可行的。但是当我将文本“Text1”放在表格中时,表格中的“Text1”不再适用。

我想在所有文档中进行此替换。

using (WordprocessingDocument doc = WordprocessingDocument.Open(String.Format("c:\\temp\\filename.docx"), true))
{
    var body = doc.MainDocumentPart.Document.Body;

    foreach (var para in body.Elements<Paragraph>())
    {
        foreach (var run in para.Elements<Run>())
        {
            foreach (var text in run.Elements<Text>())
            {
                if (text.Text.Contains("##Text1##"))
                    text.Text = text.Text.Replace("##Text1##", "NewText");
            }
        }
    }
}
4

3 回答 3

15

您的代码不起作用,因为表格元素 ( w:tbl) 不包含在段落元素 ( w:p) 中。有关详细信息,请参阅以下MSDN文章。

Text(序列化为w:t)通常表示Runword 文档中元素内的文字文本。因此,您可以简单地搜索所有w:t元素(类)并在文本元素( )包含您的标签Text时替换您的标签:w:t

using (WordprocessingDocument doc = WordprocessingDocument.Open("yourdoc.docx", true))
{
  var body = doc.MainDocumentPart.Document.Body;

  foreach (var text in body.Descendants<Text>())
  {
    if (text.Text.Contains("##Text1##"))
    {
      text.Text = text.Text.Replace("##Text1##", "NewText");
    }
  }
}
于 2013-09-30T17:23:56.687 回答
10

在各个地方借用其他一些答案,并且必须克服四个主要障碍:

  1. 从无法从 Word 读取的替换字符串中删除任何高级 Unicode 字符(来自错误的用户输入)
  2. 能够跨段落中的多个运行或文本元素搜索您的查找结果(Word 通常会将单个句子分解为多个文本运行)
  3. 能够在替换文本中包含换行符,以便在文档中插入多行文本。
  4. 能够传入任何节点作为搜索的起点,从而将搜索限制在文档的该部分(例如正文、页眉、页脚、特定表格、表格行或表格单元格)。

我确信诸如书签、复杂嵌套之类的高级场景需要对此进行更多修改,但它适用于我迄今为止遇到的基本 Word 文档类型,并且比完全忽略运行或使用整个文件上的正则表达式,无法针对特定的 TableCell 或 Document 部分(用于高级场景)。

示例用法:

 var body = document.MainDocumentPart.Document.Body;
 ReplaceText(body, replace, with);

编码:

using System;
using System.Collections.Generic;
using System.Linq;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

namespace My.Web.Api.OpenXml
{
    public static class WordTools
    {


/// <summary>
        /// Find/replace within the specified paragraph.
        /// </summary>
        /// <param name="paragraph"></param>
        /// <param name="find"></param>
        /// <param name="replaceWith"></param>
        public static void ReplaceText(Paragraph paragraph, string find, string replaceWith)
        {
            var texts = paragraph.Descendants<Text>();
            for (int t = 0; t < texts.Count(); t++)
            {   // figure out which Text element within the paragraph contains the starting point of the search string
                Text txt = texts.ElementAt(t);
                for (int c = 0; c < txt.Text.Length; c++)
                {
                    var match = IsMatch(texts, t, c, find);
                    if (match != null)
                    {   // now replace the text
                        string[] lines = replaceWith.Replace(Environment.NewLine, "\r").Split('\n', '\r'); // handle any lone n/r returns, plus newline.

                        int skip = lines[lines.Length - 1].Length - 1; // will jump to end of the replacement text, it has been processed.

                        if (c > 0)
                            lines[0] = txt.Text.Substring(0, c) + lines[0];  // has a prefix
                        if (match.EndCharIndex + 1 < texts.ElementAt(match.EndElementIndex).Text.Length)
                            lines[lines.Length - 1] = lines[lines.Length - 1] + texts.ElementAt(match.EndElementIndex).Text.Substring(match.EndCharIndex + 1);

                        txt.Space = new EnumValue<SpaceProcessingModeValues>(SpaceProcessingModeValues.Preserve); // in case your value starts/ends with whitespace
                        txt.Text = lines[0];

                        // remove any extra texts.
                        for (int i = t + 1; i <= match.EndElementIndex; i++)
                        {
                            texts.ElementAt(i).Text = string.Empty; // clear the text
                        }

                        // if 'with' contained line breaks we need to add breaks back...
                        if (lines.Count() > 1)
                        {
                            OpenXmlElement currEl = txt;
                            Break br;

                            // append more lines
                            var run = txt.Parent as Run;
                            for (int i = 1; i < lines.Count(); i++)
                            {
                                br = new Break();
                                run.InsertAfter<Break>(br, currEl);
                                currEl = br;
                                txt = new Text(lines[i]);
                                run.InsertAfter<Text>(txt, currEl);
                                t++; // skip to this next text element
                                currEl = txt;
                            }
                            c = skip; // new line
                        }
                        else
                        {   // continue to process same line
                            c += skip;
                        }
                    }
                }
            }
        }



        /// <summary>
        /// Determine if the texts (starting at element t, char c) exactly contain the find text
        /// </summary>
        /// <param name="texts"></param>
        /// <param name="t"></param>
        /// <param name="c"></param>
        /// <param name="find"></param>
        /// <returns>null or the result info</returns>
        static Match IsMatch(IEnumerable<Text> texts, int t, int c, string find)
        {
            int ix = 0;
            for (int i = t; i < texts.Count(); i++)
            {
                for (int j = c; j < texts.ElementAt(i).Text.Length; j++)
                {
                    if (find[ix] != texts.ElementAt(i).Text[j])
                    {
                        return null; // element mismatch
                    }
                    ix++; // match; go to next character
                    if (ix == find.Length)
                        return new Match() { EndElementIndex = i, EndCharIndex = j }; // full match with no issues
                }
                c = 0; // reset char index for next text element
            }
            return null; // ran out of text, not a string match
        }

        /// <summary>
        /// Defines a match result
        /// </summary>
        class Match
        {
            /// <summary>
            /// Last matching element index containing part of the search text
            /// </summary>
            public int EndElementIndex { get; set; }
            /// <summary>
            /// Last matching char index of the search text in last matching element
            /// </summary>
            public int EndCharIndex { get; set; }
        }

     }   // class
}  // namespace


public static class OpenXmlTools
    {
        // filters control characters but allows only properly-formed surrogate sequences
        private static Regex _invalidXMLChars = new Regex(
            @"(?<![\uD800-\uDBFF])[\uDC00-\uDFFF]|[\uD800-\uDBFF](?![\uDC00-\uDFFF])|[\x00-\x08\x0B\x0C\x0E-\x1F\x7F-\x9F\uFEFF\uFFFE\uFFFF]",
            RegexOptions.Compiled);
        /// <summary>
        /// removes any unusual unicode characters that can't be encoded into XML which give exception on save
        /// </summary>
        public static string RemoveInvalidXMLChars(string text)
        {
            if (string.IsNullOrEmpty(text)) return "";
            return _invalidXMLChars.Replace(text, "");
        }
    }
于 2015-04-27T20:01:15.173 回答
6

也许这个解决方案更容易

using (WordprocessingDocument wordDoc = WordprocessingDocument.Open(document, true))
{
 string docText = null;
 //1. Copy all the file into a string
 using (StreamReader sr = new StreamReader(wordDoc.MainDocumentPart.GetStream()))
     docText = sr.ReadToEnd();

 //2. Use regular expression to replace all text
 Regex regexText = new Regex(find);
 docText = regexText.Replace(docText, replace);

 //3. Write the changed string into the file again
 using (StreamWriter sw = new StreamWriter(wordDoc.MainDocumentPart.GetStream(FileMode.Create)))
      sw.Write(docText);
于 2014-06-17T08:26:49.280 回答