1.需求描述

需要将多个Word文档一键合并成一个新的word文档，同时保留原先多个word文档的格式、样式、及图片。

2.实现过程

/// <summary>
        /// 合并文档,合并后的word文档，图片会丢失
        /// </summary>
        /// <param name="paths">word文档路径集合</param>
        /// <param name="breakNewPage">是否新页面</param>
        /// <returns></returns>
        public static byte[] MergeWordFiles1(string[] paths, bool breakNewPage = true)
        {
            using (var stream = new MemoryStream())
            {
                using (WordprocessingDocument mergedDocument = WordprocessingDocument.Create(stream, WordprocessingDocumentType.Document))
                {
                    MainDocumentPart mainPart = mergedDocument.AddMainDocumentPart();
                    mainPart.Document = new Document();
                    mainPart.Document.AppendChild(new Body());

                    for (int i = 0; i < paths.Length; i++)
                    {
                        var path = paths[i];
                        if (!File.Exists(path)) continue;

                        using (WordprocessingDocument document = WordprocessingDocument.Open(path, false))
                        {
                            foreach (var element in document.MainDocumentPart.Document.Body.Elements())
                            {
                                mergedDocument.MainDocumentPart.Document.Body.AppendChild(element.CloneNode(true));
                            }
                        }
                        //如果需要换新页面
                        if (breakNewPage && i < paths.Length - 1)
                        {
                            mergedDocument.MainDocumentPart.Document.Body.Append(new Paragraph(new Run(new Break() { Type = BreakValues.Page })));
                        }
                    }

                    mergedDocument.Save();
                }

                return stream.ToArray();
            }
        }

通过以上代码，可以顺利合并文档，但当打开合并后的文档时发现存在一些问题，比如表格的边框没有了、图片也不存在了。

原先文档如下

合并后文档

继续查看官方文档，发现有个方法叫AltChunk，可以通过AltChunk这种方式实现文档合并，同时保留完整样式，于是调整代码如下

/// <summary>
        /// 合并文档，合并后的文档图片正常
        /// </summary>
        /// <param name="paths">word文档路径集合</param>
        /// <param name="breakNewPage">是否新页面</param>
        /// <returns></returns>
        public static byte[] MergeWordFiles2(string[] paths, bool breakNewPage = true)
        {
            using (var stream = new MemoryStream())
            {
                using (WordprocessingDocument mergedDocument = WordprocessingDocument.Create(stream, WordprocessingDocumentType.Document))
                {
                    var mainPart = mergedDocument.AddMainDocumentPart();
                    mainPart.Document = new Document();
                    mainPart.Document.AppendChild(new Body());

                    for (var i = 0; i < paths.Length; i++)
                    {
                        var altChunkId = "cid_" + Guid.NewGuid().ToString().Replace("-", "");
                        var chunk = mainPart.AddAlternativeFormatImportPart(AlternativeFormatImportPartType.WordprocessingML, altChunkId);

                        using (FileStream fileStream = File.Open(paths[i], FileMode.Open))
                        {
                            chunk.FeedData(fileStream);
                        }
                        var altChunk = new AltChunk();
                        altChunk.Id = altChunkId;

                        mainPart.Document.Append(altChunk);

                        //如果需要换新页面
                        if (breakNewPage && i < paths.Length - 1)
                        {
                            mainPart.Document.Append(new Paragraph(new Run(new Break() { Type = BreakValues.Page })));
                        }
                    }

                    mainPart.Document.Save();
                }

                return stream.ToArray();
            }
        }

生成文档如下

我们看到基本保持了原先的样式及图片。

开源地址：https://gitee.com/hcgit/hcf.-office.-word