update code

This commit is contained in:
lychang
2025-11-19 12:10:42 +08:00
parent 37c6ae9457
commit 8ff1b80be6
6 changed files with 1162 additions and 0 deletions

View File

@@ -0,0 +1,301 @@
/**
* 基础Markdown解析器
* 支持标题、粗体、斜体、列表、链接、图片、代码、引用等基础语法
*/
class MarkdownParser {
constructor() {
this.patterns = {
heading: /^(#{1,6})\s+(.+)$/gm,
bold: /\*\*(.*?)\*\*/g,
italic: /\*(.*?)\*/g,
inlineCode: /`(.*?)`/g,
image: /!\[(.*?)]\((.*?)\)/g,
base64Image: /!\[(.*?)]\((data:image\/[^;]+;base64,[^\)]+)\)/gi,
imageLink: /\[(.*?)]\((.*?\.(?:jpg|jpeg|png|gif|bmp|webp|svg))\s*(?:"(.*?)")?\)/gi,
link: /\[(.*?)]\((?!.*\.(?:jpg|jpeg|png|gif|bmp|webp|svg))(.*?)\)/g,
blockquote: /^>\s+(.+)$/gm,
unorderedList: /^\s*[-*+]\s+(.+)$/gm,
orderedList: /^\d+\.\s+(.+)$/gm,
codeBlock: /```.*?\n([\s\S]*?)```/g,
horizontalRule: /^---$/gm,
comment: /<!--([\s\S]*?)-->/g
};
}
/**
* 解析Markdown文本为HTML
* @param {string} markdown - Markdown文本
* @returns {string} - HTML文本
*/
parse(markdown) {
let html = markdown;
// 处理代码块(先处理,避免其他语法干扰)
html = html.replace(this.patterns.codeBlock, (match, code) => {
// 保留代码内部的换行符,只去除首尾空白
let codeLines = code.split('\n');
let result = '<pre>';
for (let i in codeLines) {
if (codeLines[i].trim() === '') {
continue;
} else {
result += `<code>${codeLines[i]}</code><br>`;
}
}
result += '</pre>';
return result;
});
// 处理块引用
html = html.replace(this.patterns.blockquote, (match, text) => {
return `<blockquote>${this.parseInline(text)}</blockquote>`;
});
// 处理水平分割线
html = html.replace(this.patterns.horizontalRule, '<hr>');
// 处理注释(保留HTML注释)
html = html.replace(this.patterns.comment, '<!--$1-->');
// 处理列表(先处理有序列表,再处理无序列表,避免冲突)
html = this.processLists(html);
// 处理段落(将连续文本包装为段落)
html = this.wrapParagraphs(html);
return html;
}
/**
* 解析行内元素
* @param {string} text - 文本内容
* @returns {string} - 解析后的HTML
*/
parseInline(text) {
let html = text;
// 处理粗体
html = html.replace(this.patterns.bold, '<strong>$1</strong>');
// 处理斜体
html = html.replace(this.patterns.italic, '<em>$1</em>');
// 处理行内代码
html = html.replace(this.patterns.inlineCode, '<code>$1</code>');
// 处理普通图片格式 ![alt](url)
html = html.replace(this.patterns.image, '<img width="100%" src="$2" alt="$1">');
// 处理base64图片格式 ![alt](data:image/...)
html = html.replace(this.patterns.base64Image, '<img width="100%" src="$2" alt="$1">');
// 处理图片链接格式 [alt](image.jpg "title")
html = html.replace(this.patterns.imageLink, (match, alt, src, title) => {
const titleAttr = title ? ` title="${title}"` : '';
return `<img width="100%" src="${src}" alt="${alt}"${titleAttr}>`;
});
// 处理链接
html = html.replace(this.patterns.link, '<a href="$2">$1</a>');
return html;
}
/**
* 处理所有列表,先识别列表类型再处理列表项
* @param {string} html - HTML文本
* @returns {string} - 处理后的HTML
*/
processLists(html) {
// 先识别并标记列表类型
const lines = html.split('\n');
let result = '';
let currentListType = '';
let listItems = [];
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
if (line.match(/^\d+\.\s/)) {
// 有序列表项
if (currentListType !== 'ol') {
// 结束前一个列表
if (listItems.length > 0) {
result += this.wrapListItems(listItems, currentListType);
listItems = [];
}
currentListType = 'ol';
}
const content = line.replace(/^\d+\.\s+/, '');
listItems.push(`<li>${this.parseInline(content)}</li>`);
} else if (line.match(/^[-*+]\s/)) {
// 无序列表项
if (currentListType !== 'ul') {
// 结束前一个列表
if (listItems.length > 0) {
result += this.wrapListItems(listItems, currentListType);
listItems = [];
}
currentListType = 'ul';
}
const content = line.replace(/^[-*+]\s+/, '');
listItems.push(`<li>${this.parseInline(content)}</li>`);
} else {
// 非列表项
if (listItems.length > 0) {
result += this.wrapListItems(listItems, currentListType);
listItems = [];
currentListType = '';
}
result += lines[i] + '\n';
}
}
// 处理最后一个列表
if (listItems.length > 0) {
result += this.wrapListItems(listItems, currentListType);
}
return result;
}
/**
* 包装列表项
* @param {Array} listItems - 列表项数组
* @param {string} listType - 列表类型(ul或ol)
* @returns {string} - 包装后的HTML列表
*/
wrapListItems(listItems, listType) {
if (listItems.length === 0) return '';
const listTag = listType === 'ol' ? 'ol' : 'ul';
return `<${listTag}>\n${listItems.join('\n')}\n</${listTag}>\n`;
}
/**
* 包装段落,保留Markdown原有换行
* @param {string} html - HTML文本
* @returns {string} - 包装后的HTML
*/
wrapParagraphs(html) {
const lines = html.split('\n');
let result = '';
let currentParagraph = '';
for (let i = 0; i < lines.length; i++) {
const line = lines[i];
const trimmedLine = line.trim();
if (!trimmedLine) {
// 空行,结束当前段落
if (currentParagraph) {
// 检查当前段落是否已经是块级元素
if (!currentParagraph.match(/^<(h[1-6]|blockquote|ul|ol|li|pre|hr)/)) {
result += `<p>${this.parseInline(currentParagraph)}</p>`;
} else {
result += currentParagraph;
}
currentParagraph = '';
}
result += '\n';
} else if (trimmedLine.match(/^<(h[1-6]|blockquote|ul|ol|li|pre|hr)/)) {
// 已经是块级元素,直接添加
if (currentParagraph) {
if (!currentParagraph.match(/^<(h[1-6]|blockquote|ul|ol|li|pre|hr)/)) {
result += `<p>${this.parseInline(currentParagraph)}</p>`;
} else {
result += currentParagraph;
}
currentParagraph = '';
}
result += line + '\n';
} else {
// 保留原有换行,不合并为一行
if (currentParagraph) {
currentParagraph += '\n' + line;
} else {
currentParagraph = line;
}
}
}
// 处理最后一个段落
if (currentParagraph) {
if (!currentParagraph.match(/^<(h[1-6]|blockquote|ul|ol|li|pre|hr)/)) {
result += `<p>${this.parseInline(currentParagraph)}</p>`;
} else {
result += currentParagraph;
}
}
return result;
}
/**
* HTML转义
* @param {string} text - 原始文本
* @returns {string} - 转义后的文本
*/
escapeHTML(text) {
const div = document.createElement('div');
div.textContent = text;
return div.innerHTML;
}
/**
* 专门解析表格(与MergeTableParser配合使用)
* @param {string} markdown - Markdown表格文本
* @returns {string} - HTML表格
*/
parseTable(markdown) {
// 使用MergeTableParser处理表格
if (typeof MergeTableParser !== 'undefined') {
const tableParser = new MergeTableParser();
return tableParser.parseMarkdownTable(markdown);
}
return markdown;
}
/**
* 完整解析Markdown,包含表格处理
* @param {string} markdown - 完整Markdown文本
* @returns {string} - 完整HTML
*/
parseFull(markdown) {
let html = markdown;
// 先处理标题,避免表格干扰
html = html.replace(this.patterns.heading, (match, hashes, text) => {
const level = hashes.length;
return `<h${level}>${this.parseInline(text)}</h${level}>`;
});
// 再提取并处理表格
const tableRegex = /(\|.*?\|\s*\n)+/g;
html = html.replace(tableRegex, (match) => {
// 检查是否是有效的表格格式
const lines = match.trim().split('\n');
if (lines.length >= 2 && lines.every(line => line.trim().startsWith('|') && line.trim().endsWith('|'))) {
return this.parseTable(match);
}
return match;
});
// 然后处理其他Markdown语法
return this.parse(html);
}
}
// 导出为全局变量
if (typeof window !== 'undefined') {
window.MarkdownParser = MarkdownParser;
}
// 使用示例
if (typeof module !== 'undefined' && module.exports) {
module.exports = MarkdownParser;
}

View File

@@ -0,0 +1,263 @@
/**
* 支持合并单元格的Markdown表格解析器
* 语法说明:
* ^n# - 向上合并n个单元格
* >n# - 向左合并n个单元格
* ^n>m# - 同时向上合并n个单元格,向左合并m个单元格
*/
class MergeTableParser {
constructor() {
this.patterns = {
mergeUp: /\^(\d+)#/, // ^2#
mergeLeft: />(\d+)#/, // >3#
mergeBoth: /\^(\d+)>(\d+)#/, // ^2>3#
};
}
/**
* 解析Markdown表格并转换为HTML表格
* @param {string} markdown - Markdown表格文本
* @returns {string} - HTML表格
*/
parseMarkdownTable(markdown) {
const lines = markdown.trim().split('\n');
const tableData = this.parseTableLines(lines);
return this.generateHTMLTable(tableData);
}
/**
* 解析表格行数据
* @param {string[]} lines - 表格行数组
* @returns {Object} - 表格数据对象
*/
parseTableLines(lines) {
const rows = [];
let headers = [];
let separatorIndex = -1;
// 解析表头和分隔符
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
if (line.startsWith('|') && line.endsWith('|')) {
const cells = line.slice(1, -1).split('|').map(cell => cell.trim());
if (line.includes('---') || line.includes('===')) {
separatorIndex = i;
continue;
}
if (separatorIndex === -1) {
headers = cells;
} else {
rows.push(cells);
}
}
}
return { headers, rows, separatorIndex };
}
/**
* 生成HTML表格
* @param {Object} tableData - 表格数据
* @returns {string} - HTML表格字符串
*/
generateHTMLTable(tableData) {
const { headers, rows } = tableData;
const skipMap = new Map(); // 用于标记需要跳过的单元格
let html = '<table border="1" style="border-collapse: collapse; width: 100%;">\n';
// 生成表头(支持合并单元格)
if (headers.length > 0) {
html += ' <thead>\n <tr>\n';
// 处理表头合并单元格
headers.forEach((header, colIndex) => {
// 检查当前单元格是否应该被跳过
const key = `-1,${colIndex}`; // 表头行索引为-1
if (skipMap.has(key)) {
return;
}
const mergeInfo = this.parseMergeSyntax(header);
let cellHtml = '';
if (mergeInfo.rowspan > 1 || mergeInfo.colspan > 1) {
cellHtml = ` <th rowspan="${mergeInfo.rowspan}" colspan="${mergeInfo.colspan}">${this.escapeHTML(mergeInfo.content)}</th>\n`;
// 标记被合并的表头单元格
this.markMergedCells(-1, colIndex, mergeInfo, skipMap);
} else {
cellHtml = ` <th>${this.escapeHTML(header)}</th>\n`;
}
html += cellHtml;
});
html += ' </tr>\n </thead>\n';
}
// 生成表格主体
html += ' <tbody>\n';
// 第一遍:标记所有需要合并的单元格
rows.forEach((row, rowIndex) => {
row.forEach((cell, colIndex) => {
const mergeInfo = this.parseMergeSyntax(cell);
if (mergeInfo.rowspan > 1 || mergeInfo.colspan > 1) {
this.markMergedCells(rowIndex, colIndex, mergeInfo, skipMap);
}
});
});
// 第二遍:生成HTML,跳过被合并的单元格
rows.forEach((row, rowIndex) => {
html += ' <tr>\n';
let colOffset = 0; // 列偏移量,用于处理被跳过的单元格
row.forEach((cell, colIndex) => {
// 检查当前单元格是否应该被跳过
const key = `${rowIndex},${colIndex}`;
if (skipMap.has(key)) {
colOffset++;
return;
}
const mergeInfo = this.parseMergeSyntax(cell);
let cellHtml = '';
if (mergeInfo.rowspan > 1 || mergeInfo.colspan > 1) {
cellHtml = ` <td rowspan="${mergeInfo.rowspan}" colspan="${mergeInfo.colspan}">${this.escapeHTML(mergeInfo.content)}</td>\n`;
} else {
cellHtml = ` <td>${this.escapeHTML(cell)}</td>\n`;
}
html += cellHtml;
});
html += ' </tr>\n';
});
html += ' </tbody>\n</table>';
return html;
}
/**
* 解析合并语法
* @param {string} cell - 单元格内容
* @returns {Object} - 合并信息
*/
parseMergeSyntax(cell) {
const result = {
content: cell,
rowspan: 1,
colspan: 1,
shouldSkip: false
};
// 检查合并语法
const bothMatch = cell.match(this.patterns.mergeBoth);
const upMatch = cell.match(this.patterns.mergeUp);
const leftMatch = cell.match(this.patterns.mergeLeft);
if (bothMatch) {
result.rowspan = parseInt(bothMatch[1]) + 1;
result.colspan = parseInt(bothMatch[2]) + 1;
result.content = cell.replace(this.patterns.mergeBoth, '').trim();
} else if (upMatch) {
result.rowspan = parseInt(upMatch[1]) + 1;
result.content = cell.replace(this.patterns.mergeUp, '').trim();
} else if (leftMatch) {
result.colspan = parseInt(leftMatch[1]) + 1;
result.content = cell.replace(this.patterns.mergeLeft, '').trim();
}
return result;
}
/**
* 标记被合并的单元格
* @param {number} rowIndex - 行索引
* @param {number} colIndex - 列索引
* @param {Object} mergeInfo - 合并信息
* @param {Map} skipMap - 跳过映射
*/
markMergedCells(rowIndex, colIndex, mergeInfo, skipMap) {
for (let r = 0; r < mergeInfo.rowspan; r++) {
for (let c = 0; c < mergeInfo.colspan; c++) {
if (r === 0 && c === 0) continue; // 跳过主单元格
// 处理表头合并(行索引为-1)
const targetRow = rowIndex === -1 ? -1 : rowIndex + r;
const key = `${targetRow},${colIndex + c}`;
skipMap.set(key, true);
}
}
}
/**
* HTML转义
* @param {string} text - 原始文本
* @returns {string} - 转义后的文本
*/
escapeHTML(text) {
const div = document.createElement('div');
div.textContent = text;
return div.innerHTML;
}
/**
* 将HTML表格转换回Markdown格式
* @param {string} html - HTML表格
* @returns {string} - Markdown表格
*/
htmlToMarkdown(html) {
const parser = new DOMParser();
const doc = parser.parseFromString(html, 'text/html');
const table = doc.querySelector('table');
if (!table) return '';
let markdown = '';
const rows = table.querySelectorAll('tr');
rows.forEach((row, rowIndex) => {
const cells = row.querySelectorAll('th, td');
let rowMarkdown = '|';
cells.forEach(cell => {
const rowspan = parseInt(cell.getAttribute('rowspan') || '1');
const colspan = parseInt(cell.getAttribute('colspan') || '1');
let content = cell.textContent.trim();
// 添加合并语法
if (rowspan > 1) {
content += ` ^${rowspan - 1}`;
}
if (colspan > 1) {
content += ` >${colspan - 1}`;
}
rowMarkdown += ` ${content} |`;
});
markdown += rowMarkdown + '\n';
// 添加分隔符行(仅在第一行后)
if (rowIndex === 0) {
markdown += '|' + cells.map(() => '---').join('|') + '|\n';
}
});
return markdown;
}
}
// 导出为全局变量
if (typeof window !== 'undefined') {
window.MergeTableParser = MergeTableParser;
}
// 使用示例
if (typeof module !== 'undefined' && module.exports) {
module.exports = MergeTableParser;
}