RTF转HTML(＜div＞标签)格式的方法(java)

最新推荐文章于 2024-08-18 10:27:18 发布

Rookie_cc

最新推荐文章于 2024-08-18 10:27:18 发布

阅读量1.3k

点赞数 1

分类专栏：其他文章标签： html rtf

本文链接：https://blog.csdn.net/Rookie_cc/article/details/107555259

版权

本文介绍了如何使用Java通过RTF2HTML类将RTF文件转换为HTML格式，主要以div标签展示内容，并解决了中文乱码问题。尽管目前无法转换RTF中的表格和图片，但提供了WebCAT项目的RTF2HTML类作为工具。

摘要由CSDN通过智能技术生成

最近有一个将RTF格式的文件转换成HTML格式的需求，网上搜索发现相关资料比较少，能找到的一些资料也年代比较久远。经过一番摸索和测试，终于成功的将RTF转成了HTML(主要以div标签为主)，并且解决了烦人的中文乱码问题。但是很遗憾，目前RTF文件里面的表格和图片还无法转换（没有找到方案）。

1、首先，我们需要先借助WebCAT里面的RTF2HTML这个类，WebCAT的下载地址为：http://webcat.sourceforge.net/或者https://download.csdn.net/download/Rookie_cc/12657315。(你也可以直接参考下面的代码，不用下载WebCAT)

2、具体代码如下：

RTF2HTML工具类：

package com.fish.fileparser.utils;

import java.awt.Color;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.StringTokenizer;

import javax.swing.text.AttributeSet;
import javax.swing.text.BadLocationException;
import javax.swing.text.DefaultStyledDocument;
import javax.swing.text.Document;
import javax.swing.text.Element;
import javax.swing.text.StyleConstants;
import javax.swing.text.rtf.RTFEditorKit;


/**
 *  Description of the Class
 *
 *@author     bmartins
 *@created    22 de Agosto de 2002
 */
public class RTF2HTML {

    /**
     * rtf文件表格标识
     */
    public static final String TABLE = "\\trowd";

    /**
     * rtf文件图片标识
     */
    public static final String PICTURE = "\\*\\shppic";

    /**
     *  Description of the Class
     *
     *@author     bmartins
     *@created    22 de Agosto de 2002
     */
    private class HTMLStateMachine {

        private String alignNames[] = { "left", "center", "right" };
        /**
         *  Description of the Field
         */
        public boolean acceptFonts;
        private String fontName;
        private Color color;
        private int size;
        private int alignment;
        private boolean bold;
        private boolean italic;
        private boolean underline;
        private double firstLineIndent;
        private double oldLeftIndent;
        private double oldRightIndent;
        private double leftIndent;
        private double rightIndent;
        private boolean firstLine;

        /**
         *  Constructor for the HTMLStateMachine object
         */
        HTMLStateMachine() {
            acceptFonts = true;
            fontName = "";
            alignment = -1;
            bold = false;
            italic = false;
            underline = false;
            color = null;
            size = -1;
            firstLineIndent = 0.0D;
            oldLeftIndent = 0.0D;
            oldRightIndent = 0.0D;
            leftIndent = 0.0D;
            rightIndent = 0.0D;
            firstLine = false;
        }

        /**
         *  Description of the Method
         *
         *@param  attributeset  Description of the Parameter
         *@param  stringbuffer  Description of the Parameter
         *@param  element       Description of the Parameter
         */
        public void updateState(
                AttributeSet attributeset,
                StringBuffer stringbuffer,
                Element element) {
            String s = element.getName();
            if (s.equalsIgnoreCase("paragraph")) {
                firstLine = true;
            }
            leftIndent =
                    updateDouble(
                            attributeset,
                            leftIndent,
                            StyleConstants.LeftIndent);
            rightIndent =
                    updateDouble(
                            attributeset,
                            rightIndent,
                            StyleConstants.RightIndent);
            if (leftIndent != oldLeftIndent || rightIndent != oldRightIndent) {
                closeIndentTable(stringbuffer, oldLeftIndent, oldRightIndent);
            }
            bold =
                    updateBoolean(
                            attributeset,
                            StyleConstants.Bold,
                            "b",
                            bold,
                            stringbuffer);
            italic =
                    updateBoolean(
                            attributeset,
                            StyleConstants.Italic,
                            "i",
                            italic,
                            stringbuffer);
            underline =
                    updateBoolean(
                            attributeset,
                            StyleConstants.Underline,
                            "u",
                            underline,
                            stringbuffer);
            size = updateFontSize(attributeset, size, stringbuffer);
            color = updateFontColor(attributeset, color, stringbuffer);
            if (acceptFonts) {
                fontName = updateFontName(attributeset, fontName, stringbuffer);
            }
            alignment = updateAlignment(attributeset, alignment, stringbuffer);
            firstLineIndent =
                    updateDouble(
                            attributeset,
                            firstLineIndent,
                            StyleConstants.FirstLineIndent);
            if (leftIndent != oldLeftIndent || rightIndent != oldRightIndent) {
                openIndentTable(stringbuffer, leftIndent, rightIndent);
                oldLeftIndent = leftIndent;
                oldRightIndent = rightIndent;
            }
        }

        /**
         *  Description of the Method
         *
         *@param  stringbuffer  Description of the Parameter
         *@param  d             Description of the Parameter
         *@param  d1            Description of the Parameter
         */
        private void openIndentTable(
                StringBuffer stringbuffer,
                double d,
                double d1) {
            if (d != 0.0D || d1 != 0.0D) {
                closeSubsetTags(stringbuffer);
                stringbuffer.append("<table><tr>");
                String s = getSpaceTab((int) (d / 4D));
                if (s.length() > 0) {
                    stringbuffer.append("<td>" + s + "</td>");