在Java中使用格式将rtf转换为html答案

【问题标题】：Converting rtf to html with format in Java在Java中使用格式将rtf转换为html
【发布时间】：2014-04-18 16:30:13
【问题描述】：

我可以使用 JEditorPane 来解析 rtf 文本并将其转换为 html。但是 html 输出缺少某种格式，即本例中的删除线标记。正如您在输出中看到的那样，下划线文本正确地包裹在中，但没有删除线包裹。有什么想法吗？

public void testRtfToHtml()
{
    JEditorPane pane = new JEditorPane();
    pane.setContentType("text/rtf");

    StyledEditorKit kitRtf = (StyledEditorKit) pane.getEditorKitForContentType("text/rtf");

    try
    {
        kitRtf.read(
            new StringReader(
                "{\\rtf1\\ansi \\deflang1033\\deff0{\\fonttbl {\\f0\\froman \\fcharset0 \\fprq2 Times New Roman;}}{\\colortbl;\\red0\\green0\\blue0;} {\\stylesheet{\\fs20 \\snext0 Normal;}} {\\plain \\fs26 \\strike\\fs26 This is supposed to be strike-through.}{\\plain \\fs26 \\fs26  } {\\plain \\fs26 \\ul\\fs26 Underline text here} {\\plain \\fs26 \\fs26 .{\\u698\\'20}}"),
            pane.getDocument(), 0);
        kitRtf = null;

        StyledEditorKit kitHtml =
            (StyledEditorKit) pane.getEditorKitForContentType("text/html");

        Writer writer = new StringWriter();
        kitHtml.write(writer, pane.getDocument(), 0, pane.getDocument().getLength());
        System.out.println(writer.toString());
    }
    catch (Exception e)
    {
        e.printStackTrace();
    }
}

输出：

<html>
  <head>
    <style>
      <!--
        p.Normal {
          RightIndent:0.0;
          FirstLineIndent:0.0;
          LeftIndent:0.0;
        }
      -->
    </style>
  </head>
  <body>
    <p class=default>
              <span style="color: #000000; font-size: 13pt; font-family: Times New Roman">
This is supposed to be strike-through.
      </span>
      <span style="color: #000000; font-size: 13pt; font-family: Times New Roman">

      </span>
       <span style="color: #000000; font-size: 13pt; font-family: Times New Roman">
<u>Underline text here</u>
      </span>
       <span style="color: #000000; font-size: 13pt; font-family: Times New Roman">
.?
      </span>

    </p>
  </body>
</html>

【问题讨论】：

标签： java html rtf jeditorpane strikethrough

【解决方案1】：

您可以尝试使用 this converter library 使用 OpenOffice 或 LibreOffice 进行转换，如 in this blog post 所述

【讨论】：

【解决方案2】：

这是我用来将 RTF 从 .msg 正文转换为 HTML 的函数。在 GitHub 上查看我的 Outlook 消息解析器 yamp 存储库。

public static String rtfToHtml(String rtfText) {
    if (rtfText != null) {
        rtfText = rtfText.replaceAll("\\{\\\\\\*\\\\[m]?htmltag[\\d]*(.*)}", "$1")
            .replaceAll("\\\\htmlrtf[1]?(.*)\\\\htmlrtf0", "")
            .replaceAll("\\\\htmlrtf[01]?", "")
            .replaceAll("\\\\htmlbase", "")
            .replaceAll("\\\\par", "\n")
            .replaceAll("\\\\tab", "\t")
            .replaceAll("\\\\line", "\n")
            .replaceAll("\\\\page", "\n\n")
            .replaceAll("\\\\sect", "\n\n")
            .replaceAll("\\\\emdash", "&#2014;")
            .replaceAll("\\\\endash", "&#2013;")
            .replaceAll("\\\\emspace", "&#2003;")
            .replaceAll("\\\\enspace", "&#2002;")
            .replaceAll("\\\\qmspace", "&#2005;")
            .replaceAll("\\\\bullet", "&#2022;")
            .replaceAll("\\\\lquote", "&#2018;")
            .replaceAll("\\\\rquote", "&#2019;")
            .replaceAll("\\\\ldblquote", "&#201C;")
            .replaceAll("\\\\rdblquote", "&#201D;")
            .replaceAll("\\\\row", "\n")
            .replaceAll("\\\\cell", "|")
            .replaceAll("\\\\nestcell", "|")
            .replaceAll("([^\\\\])\\{", "$1")
            .replaceAll("([^\\\\])}", "$1")
            .replaceAll("[\\\\](\\{)", "$1")
            .replaceAll("[\\\\](})", "$1")
            .replaceAll("\\\\u([0-9]{2,5})", "&#$1;")
            .replaceAll("\\\\'([0-9A-Fa-f]{2})", "&#x$1;")
            .replaceAll("\"cid:(.*)@.*\"", "\"$1\"");

        int index = rtfText.indexOf("<html");
        if (index != -1) {
            return rtfText.substring(index);
        }
    }

    return null;
}

【讨论】：

【解决方案3】：

由于一些错误，我像这样修改你的功能：

public static String rtfToHtml(String rtfText) {
    StringBuilder sb = new StringBuilder();
    
    if (rtfText != null) {
        String[] lignes = rtfText.split("[\\r\\n]+");
        for (String ligne : lignes) {
            String tempLine = ligne
                .replaceAll("\\{\\\\\\*\\\\[m]?htmltag[\\d]*([^}]*)\\}", "$1")
                .replaceAll("\\\\htmlrtf0([^\\\\]*)\\\\htmlrtf", "$1")
                .replaceAll("\\\\htmlrtf \\{(.*)\\}\\\\htmlrtf0", "$1")
                .replaceAll("\\\\htmlrtf (.*)\\\\htmlrtf0", "")
                .replaceAll("\\\\htmlrtf[0]?", "")
                .replaceAll("\\\\field\\{\\\\\\*\\\\fldinst\\{[^}]*\\}\\}", "")
                .replaceAll("\\{\\\\fldrslt\\\\cf1\\\\ul([^}]*)\\}", "$1")
                .replaceAll("\\\\htmlbase", "")
                .replaceAll("\\\\par", "\n")
                .replaceAll("\\\\tab", "\t")
                .replaceAll("\\\\line", "\n")
                .replaceAll("\\\\page", "\n\n")
                .replaceAll("\\\\sect", "\n\n")
                .replaceAll("\\\\emdash", "&#2014;")
                .replaceAll("\\\\endash", "&#2013;")
                .replaceAll("\\\\emspace", "&#2003;")
                .replaceAll("\\\\enspace", "&#2002;")
                .replaceAll("\\\\qmspace", "&#2005;")
                .replaceAll("\\\\bullet", "&#2022;")
                .replaceAll("\\\\lquote", "&#2018;")
                .replaceAll("\\\\rquote", "&#2019;")
                .replaceAll("\\\\ldblquote", "&#201C;")
                .replaceAll("\\\\rdblquote", "&#201D;")
                .replaceAll("\\\\row", "\n")
                .replaceAll("\\\\cell", "|")
                .replaceAll("\\\\nestcell", "|")
                .replaceAll("([^\\\\])\\{", "$1")
                .replaceAll("([^\\\\])}", "$1")
                .replaceAll("[\\\\](\\{)", "$1")
                .replaceAll("[\\\\](})", "$1")
                .replaceAll("\\\\u([0-9]{2,5})", "&#$1;")
                .replaceAll("\\\\'([0-9A-Fa-f]{2})", "&#x$1;")
                .replaceAll("\"cid:(.*)@.*\"", "\"$1\"")
                .replaceAll(" {2,}", " ")
            ;
            
            if (!tempLine.replaceAll("\\s+", "").isEmpty()) {
                sb.append(tempLine).append("\r\n");
            }
        }
        
        rtfText = sb.toString();

        int index = rtfText.indexOf("<html");
        if (index != -1) {
            return rtfText.substring(index);
        }
    }

    return null;
}

【讨论】：