本文目录导读：
我为您的需求整理了几种适合在 JEditorPane/HTMLEditorKit 环境中使用的 HTML 解析和排序算法实现方案。
HTML 内容提取与排序
import javax.swing.*;
import javax.swing.text.*;
import javax.swing.text.html.*;
import java.io.*;
import java.util.*;
public class HTMLSortExample {
public static void main(String[] args) {
JFrame frame = new JFrame("HTML Sorting Demo");
JEditorPane editorPane = new JEditorPane();
editorPane.setContentType("text/html");
editorPane.setEditable(false);
// 示例 HTML
String html = "<html><body>" +
"<h1>Items</h1>" +
"<ul>" +
"<li>Banana</li>" +
"<li>Apple</li>" +
"<li>Cherry</li>" +
"<li>Date</li>" +
"</ul>" +
"</body></html>";
editorPane.setText(html);
// 排序按钮
JButton sortBtn = new JButton("Sort Items");
sortBtn.addActionListener(e -> {
String sortedHtml = sortHTMLList(html, false);
editorPane.setText(sortedHtml);
});
JPanel panel = new JPanel(new BorderLayout());
panel.add(new JScrollPane(editorPane), BorderLayout.CENTER);
panel.add(sortBtn, BorderLayout.SOUTH);
frame.add(panel);
frame.setSize(400, 300);
frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
frame.setVisible(true);
}
// 提取并排序 HTML 列表内容
public static String sortHTMLList(String html, boolean descending) {
try {
HTMLEditorKit kit = new HTMLEditorKit();
HTMLDocument doc = (HTMLDocument) kit.createDefaultDocument();
kit.read(new StringReader(html), doc, 0);
// 提取所有列表项
Element root = doc.getDefaultRootElement();
List<String> items = new ArrayList<>();
List<Element> liElements = new ArrayList<>();
extractListItems(root, items, liElements);
// 排序
if (descending) {
items.sort(Collections.reverseOrder());
} else {
Collections.sort(items);
}
// 重建 HTML
return rebuildHTML(html, items, liElements);
} catch (Exception e) {
e.printStackTrace();
return html;
}
}
private static void extractListItems(Element element, List<String> items, List<Element> liElements) {
for (int i = 0; i < element.getElementCount(); i++) {
Element child = element.getElement(i);
if ("li".equals(child.getName())) {
try {
int start = child.getStartOffset();
int end = child.getEndOffset();
String text = child.getDocument().getText(start, end - start).trim();
items.add(text);
liElements.add(child);
} catch (BadLocationException e) {
e.printStackTrace();
}
}
extractListItems(child, items, liElements);
}
}
private static String rebuildHTML(String originalHtml, List<String> sortedItems, List<Element> liElements) {
// 直接替换文本内容的简化实现
StringBuilder sb = new StringBuilder(originalHtml);
// 从后往前替换，避免位置偏移
for (int i = liElements.size() - 1; i >= 0; i--) {
Element li = liElements.get(i);
try {
int start = li.getStartOffset();
int end = li.getEndOffset();
String originalText = li.getDocument().getText(start, end - start);
// 在原始 HTML 中找到这个文本并替换
int htmlIndex = sb.indexOf(originalText);
if (htmlIndex >= 0) {
sb.replace(htmlIndex, htmlIndex + originalText.length(), sortedItems.get(i));
}
} catch (BadLocationException e) {
e.printStackTrace();
}
}
return sb.toString();
}
}
使用 DOM 解析器进行排序
import javax.swing.text.html.parser.*;
import javax.swing.text.html.*;
import javax.swing.text.*;
import java.util.*;
public class DOMSortExample {
public static String sortHTMLByTags(String html, String tagName) {
try {
HTMLEditorKit kit = new HTMLEditorKit();
HTMLDocument doc = (HTMLDocument) kit.createDefaultDocument();
kit.read(new StringReader(html), doc, 0);
// 查找指定标签的所有元素
ElementIterator iterator = new ElementIterator(doc);
Element element;
List<SortableElement> elements = new ArrayList<>();
while ((element = iterator.next()) != null) {
if (tagName.equals(element.getName())) {
String text = getElementText(doc, element);
elements.add(new SortableElement(element, text));
}
}
// 按文本排序
elements.sort(Comparator.comparing(e -> e.text));
// 返回排序后的 HTML
return buildSortedHTML(doc, elements, tagName);
} catch (Exception e) {
e.printStackTrace();
return html;
}
}
private static String getElementText(HTMLDocument doc, Element element) {
try {
int start = element.getStartOffset();
int end = element.getEndOffset();
return doc.getText(start, end - start).trim();
} catch (BadLocationException e) {
return "";
}
}
private static String buildSortedHTML(HTMLDocument doc, List<SortableElement> sortedElements, String tagName) {
// 这里实现重建 HTML 的逻辑
// 简化版本直接返回原始文档的字符串
StringBuilder result = new StringBuilder();
try {
StringWriter writer = new StringWriter();
new HTMLEditorKit().write(writer, doc, 0, doc.getLength());
result.append(writer.toString());
} catch (Exception e) {
e.printStackTrace();
}
return result.toString();
}
static class SortableElement {
Element element;
String text;
SortableElement(Element element, String text) {
this.element = element;
this.text = text;
}
}
}
简单字符串解析排序
import java.util.*;
import java.util.regex.*;
public class StringBasedHTMLSort {
// 按 HTML 标签内容排序
public static String sortByTagContent(String html, String tag) {
String regex = "<" + tag + "[^>]*>(.*?)</" + tag + ">";
Pattern pattern = Pattern.compile(regex, Pattern.DOTALL);
Matcher matcher = pattern.matcher(html);
List<MatchPair> matches = new ArrayList<>();
while (matcher.find()) {
matches.add(new MatchPair(matcher.start(), matcher.end(), matcher.group()));
}
// 按内容排序
matches.sort((a, b) -> {
String aContent = extractContent(a.text, tag);
String bContent = extractContent(b.text, tag);
return aContent.compareTo(bContent);
});
// 重建 HTML
StringBuilder result = new StringBuilder();
int lastEnd = 0;
for (MatchPair match : matches) {
result.append(html, lastEnd, match.start);
result.append(match.text);
lastEnd = match.end;
}
result.append(html.substring(lastEnd));
return result.toString();
}
private static String extractContent(String tagHtml, String tag) {
Pattern pattern = Pattern.compile("<" + tag + "[^>]*>(.*?)</" + tag + ">", Pattern.DOTALL);
Matcher matcher = pattern.matcher(tagHtml);
if (matcher.find()) {
return matcher.group(1).trim();
}
return "";
}
static class MatchPair {
int start, end;
String text;
MatchPair(int start, int end, String text) {
this.start = start;
this.end = end;
this.text = text;
}
}
// 使用示例
public static void main(String[] args) {
String html = "<div>" +
"<p>Banana</p>" +
"<p>Apple</p>" +
"<p>Cherry</p>" +
"</div>";
String sorted = sortByTagContent(html, "p");
System.out.println("Original: " + html);
System.out.println("Sorted: " + sorted);
}
}
完整表格行列排序示例
import javax.swing.*;
import javax.swing.table.*;
import java.awt.*;
public class JEditorPaneTableSorter extends JFrame {
public JEditorPaneTableSorter() {
setTitle("HTML Table Sorter");
setLayout(new BorderLayout());
JEditorPane editorPane = new JEditorPane();
editorPane.setContentType("text/html");
editorPane.setEditable(false);
String tableHtml = "<html><body>" +
"<table border='1'>" +
"<tr><th>Name</th><th>Age</th><th>City</th></tr>" +
"<tr><td>Alice</td><td>30</td><td>NYC</td></tr>" +
"<tr><td>Bob</td><td>25</td><td>LA</td></tr>" +
"<tr><td>Charlie</td><td>35</td><td>Chicago</td></tr>" +
"</table></body></html>";
editorPane.setText(tableHtml);
JButton sortByNameBtn = new JButton("Sort by Name");
JButton sortByAgeBtn = new JButton("Sort by Age");
JButton sortByCityBtn = new JButton("Sort by City");
sortByNameBtn.addActionListener(e -> {
String sorted = sortTableByColumn(tableHtml, 0);
editorPane.setText(sorted);
});
sortByAgeBtn.addActionListener(e -> {
String sorted = sortTableByColumn(tableHtml, 1);
editorPane.setText(sorted);
});
sortByCityBtn.addActionListener(e -> {
String sorted = sortTableByColumn(tableHtml, 2);
editorPane.setText(sorted);
});
JPanel buttonPanel = new JPanel();
buttonPanel.add(sortByNameBtn);
buttonPanel.add(sortByAgeBtn);
buttonPanel.add(sortByCityBtn);
add(new JScrollPane(editorPane), BorderLayout.CENTER);
add(buttonPanel, BorderLayout.SOUTH);
setSize(500, 400);
setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);
setVisible(true);
}
private String sortTableByColumn(String html, int columnIndex) {
// 解析表格并排序
String[] rows = html.split("</tr>");
if (rows.length < 2) return html;
// 分离表头和表体
String header = rows[0] + "</tr>";
List<String> bodyRows = new ArrayList<>();
for (int i = 1; i < rows.length; i++) {
bodyRows.add(rows[i] + "</tr>");
}
// 按指定列排序
bodyRows.sort((r1, r2) -> {
String[] cols1 = r1.split("</td>");
String[] cols2 = r2.split("</td>");
if (columnIndex < cols1.length && columnIndex < cols2.length) {
String val1 = cols1[columnIndex].replaceAll("<[^>]+>", "").trim();
String val2 = cols2[columnIndex].replaceAll("<[^>]+>", "").trim();
return val1.compareTo(val2);
}
return 0;
});
// 重建 HTML
StringBuilder sorted = new StringBuilder(header);
for (String row : bodyRows) {
sorted.append(row);
}
// 确保 HTML 结构完整
String result = sorted.toString();
if (!result.startsWith("<html>")) {
result = "<html><body><table border='1'>" + result + "</table></body></html>";
}
return result;
}
public static void main(String[] args) {
SwingUtilities.invokeLater(JEditorPaneTableSorter::new);
}
}
选择建议
- 简单列表排序：使用方法 1 的
sortHTMLList() - 按标签排序：使用方法 2 或 3
- 表格排序：使用方法 4
- 性能要求高：使用方法 3 的字符串解析
这些算法都兼容 JEditorPane/HTMLEditorKit 环境，您可以根据具体需求选择最适合的实现。
