using System;
using System.IO;
using System.Linq;
using System.Text;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;/// <summary>
/// 使用OpenXML獲取文檔內容，替代Aspose方式
/// </summary>
/// <param name="path">文檔路徑</param>
/// <param name="password">密碼</param>
/// <returns>文檔內容字符串</returns>
public static string GetWordContentByOpenXml(string path, string password)
{try{using (var document = WordprocessingDocument.Open(path, false, new OpenSettings(){Password = password})){if (document.MainDocumentPart?.Document?.Body == null)return null;// 創建StringBuilder來存儲文檔主體內容var contentBuilder = new StringBuilder();// 獲取文檔主體，排除頁眉頁腳var body = document.MainDocumentPart.Document.Body;// 提取主文檔內容（不包括頁眉頁腳）ExtractBodyContent(body, contentBuilder);// 獲取原始內容string contentWithoutHeaderFooter = contentBuilder.ToString();// 應用內容清理和格式化string content = CleanContent(contentWithoutHeaderFooter);// 處理特定的截取邏輯int index = content.LastIndexOf("限公司第");if (index > 0){return content.Substring(0, index).Trim();}else{return content;}}}catch (Exception ex){LogManager.WriteError("GetWordContentByOpenXml()", ex.StackTrace?.ToString());return null;}
}/// <summary>
/// 提取文檔主體內容，排除頁眉頁腳
/// </summary>
/// <param name="body">文檔主體</param>
/// <param name="contentBuilder">內容構建器</param>
private static void ExtractBodyContent(Body body, StringBuilder contentBuilder)
{// 遍歷文檔主體中的所有元素foreach (var element in body.Elements()){ExtractElementContent(element, contentBuilder);}
}/// <summary>
/// 遞歸提取元素內容
/// </summary>
/// <param name="element">OpenXML元素</param>
/// <param name="contentBuilder">內容構建器</param>
private static void ExtractElementContent(OpenXmlElement element, StringBuilder contentBuilder)
{switch (element){case Paragraph paragraph:ExtractParagraphContent(paragraph, contentBuilder);contentBuilder.AppendLine(); // 段落后換行break;case Table table:ExtractTableContent(table, contentBuilder);break;case SectionProperties _:// 跳過節屬性，這些通常包含頁眉頁腳引用break;default:// 遞歸處理其他容器元素foreach (var childElement in element.Elements()){ExtractElementContent(childElement, contentBuilder);}break;}
}/// <summary>
/// 提取段落內容
/// </summary>
/// <param name="paragraph">段落元素</param>
/// <param name="contentBuilder">內容構建器</param>
private static void ExtractParagraphContent(Paragraph paragraph, StringBuilder contentBuilder)
{foreach (var run in paragraph.Elements<Run>()){foreach (var text in run.Elements<Text>()){contentBuilder.Append(text.Text);}// 處理制表符foreach (var tab in run.Elements<TabChar>()){contentBuilder.Append("\t");}// 處理換行符foreach (var br in run.Elements<Break>()){contentBuilder.AppendLine();}}
}/// <summary>
/// 提取表格內容
/// </summary>
/// <param name="table">表格元素</param>
/// <param name="contentBuilder">內容構建器</param>
private static void ExtractTableContent(Table table, StringBuilder contentBuilder)
{foreach (var row in table.Elements<TableRow>()){foreach (var cell in row.Elements<TableCell>()){foreach (var paragraph in cell.Elements<Paragraph>()){ExtractParagraphContent(paragraph, contentBuilder);}contentBuilder.Append("\t"); // 單元格間用制表符分隔}contentBuilder.AppendLine(); // 表格行后換行}
}/// <summary>
/// 清理和格式化內容，模擬Aspose的清理功能
/// </summary>
/// <param name="content">原始內容</param>
/// <returns>清理后的內容</returns>
private static string CleanContent(string content)
{if (string.IsNullOrEmpty(content))return string.Empty;// 移除多余的空白字符（模擬Tool.TrimAll功能）content = System.Text.RegularExpressions.Regex.Replace(content, @"\s+", " ");content = content.Trim();// 移除多余的換行符content = System.Text.RegularExpressions.Regex.Replace(content, @"\n\s*\n", "\n");// 移除Aspose評估版本的水印文本（雖然OpenXML不會有，但保持兼容性）content = content.Replace("EvaluationOnly.CreatedwithAspose.Words.Copyright2003-2024AsposePtyLtd.", "");// 移除其他可能的控制字符content = System.Text.RegularExpressions.Regex.Replace(content, @"[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]", "");return content.Trim();
}/// <summary>
/// 檢查文檔是否需要密碼
/// </summary>
/// <param name="path">文檔路徑</param>
/// <returns>是否需要密碼</returns>
public static bool IsPasswordRequired(string path)
{try{using (var document = WordprocessingDocument.Open(path, false)){// 如果能正常打開，說明不需要密碼return false;}}catch (OpenXmlPackageException ex){// 如果拋出密碼相關異常，說明需要密碼return ex.Message.Contains("password") || ex.Message.Contains("encrypted") || ex.Message.Contains("protected");}catch{// 其他異常可能也表示需要密碼return true;}
}/// <summary>
/// 增強版本：支持更多文檔處理選項
/// </summary>
/// <param name="path">文檔路徑</param>
/// <param name="password">密碼</param>
/// <param name="includeHyperlinks">是否包含超鏈接文本</param>
/// <param name="includeFootnotes">是否包含腳注</param>
/// <returns>文檔內容</returns>
public static string GetWordContentByOpenXmlAdvanced(string path, string password, bool includeHyperlinks = false, bool includeFootnotes = false)
{try{using (var document = WordprocessingDocument.Open(path, false, new OpenSettings(){Password = password})){if (document.MainDocumentPart?.Document?.Body == null)return null;var contentBuilder = new StringBuilder();var body = document.MainDocumentPart.Document.Body;// 提取主文檔內容ExtractBodyContentAdvanced(body, contentBuilder, includeHyperlinks);// 如果需要包含腳注if (includeFootnotes && document.MainDocumentPart.FootnotesPart != null){ExtractFootnotesContent(document.MainDocumentPart.FootnotesPart, contentBuilder);}string contentWithoutHeaderFooter = contentBuilder.ToString();string content = CleanContent(contentWithoutHeaderFooter);// 應用特定的截取邏輯int index = content.LastIndexOf("公司第");if (index > 0){return content.Substring(0, index).Trim();}else{return content;}}}catch (Exception ex){LogManager.WriteError("GetWordContentByOpenXmlAdvanced()", ex.StackTrace?.ToString());return null;}
}/// <summary>
/// 高級內容提取，支持超鏈接等
/// </summary>
private static void ExtractBodyContentAdvanced(Body body, StringBuilder contentBuilder, bool includeHyperlinks)
{foreach (var element in body.Elements()){if (element is Paragraph paragraph){ExtractParagraphContentAdvanced(paragraph, contentBuilder, includeHyperlinks);contentBuilder.AppendLine();}else if (element is Table table){ExtractTableContentAdvanced(table, contentBuilder, includeHyperlinks);}else if (!(element is SectionProperties)){// 遞歸處理其他元素foreach (var childElement in element.Elements()){ExtractBodyContentAdvanced(new Body(childElement), contentBuilder, includeHyperlinks);}}}
}/// <summary>
/// 高級段落內容提取
/// </summary>
private static void ExtractParagraphContentAdvanced(Paragraph paragraph, StringBuilder contentBuilder, bool includeHyperlinks)
{foreach (var element in paragraph.Elements()){if (element is Run run){foreach (var text in run.Elements<Text>()){contentBuilder.Append(text.Text);}}else if (element is Hyperlink hyperlink && includeHyperlinks){foreach (var run2 in hyperlink.Elements<Run>()){foreach (var text in run2.Elements<Text>()){contentBuilder.Append(text.Text);}}}}
}/// <summary>
/// 高級表格內容提取
/// </summary>
private static void ExtractTableContentAdvanced(Table table, StringBuilder contentBuilder, bool includeHyperlinks)
{foreach (var row in table.Elements<TableRow>()){foreach (var cell in row.Elements<TableCell>()){foreach (var paragraph in cell.Elements<Paragraph>()){ExtractParagraphContentAdvanced(paragraph, contentBuilder, includeHyperlinks);}contentBuilder.Append("\t");}contentBuilder.AppendLine();}
}/// <summary>
/// 提取腳注內容
/// </summary>
private static void ExtractFootnotesContent(FootnotesPart footnotesPart, StringBuilder contentBuilder)
{if (footnotesPart.Footnotes != null){contentBuilder.AppendLine("\n--- 腳注 ---");foreach (var footnote in footnotesPart.Footnotes.Elements<Footnote>()){foreach (var paragraph in footnote.Elements<Paragraph>()){ExtractParagraphContent(paragraph, contentBuilder);contentBuilder.AppendLine();}}}
}