✨ Improve code block function

frontend/src/views/editor/extensions/codeblock/lang-parser/build-parser.js

@@ -0,0 +1,52 @@
+#!/usr/bin/env node
+
+/**
+ * 解析器构建脚本
+ * 使用 lezer-generator 从语法文件生成解析器
+ * 使用：node build-parser.js
+ */
+
+import { execSync } from 'child_process';
+import path from 'path';
+import fs from 'fs';
+import { fileURLToPath } from 'url';
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+
+console.log('🚀 start building parser...');
+
+try {
+  // 检查语法文件是否存在
+  const grammarFile = path.join(__dirname, 'codeblock.grammar');
+  if (!fs.existsSync(grammarFile)) {
+    throw new Error('grammarFile codeblock.grammar not found');
+  }
+
+  console.log('📄 grammar file:', grammarFile);
+
+  // 运行 lezer-generator
+  console.log('⚙️  building parser...');
+  execSync('npx lezer-generator codeblock.grammar -o parser.js', {
+    cwd: __dirname,
+    stdio: 'inherit'
+  });
+
+  // 检查生成的文件
+  const parserFile = path.join(__dirname, 'parser.js');
+  const termsFile = path.join(__dirname, 'parser.terms.js');
+
+  if (fs.existsSync(parserFile) && fs.existsSync(termsFile)) {
+    console.log('✅ parser file successfully generated！');
+    console.log('📦 parser files:');
+    console.log('  - parser.js');
+    console.log('  - parser.terms.js');
+  } else {
+    throw new Error('failed to generate parser');
+  }
+
+  console.log('🎉 build success！');
+
+} catch (error) {
+  console.error('❌ build failed:', error.message);
+  process.exit(1);
+} 

frontend/src/views/editor/extensions/codeblock/lang-parser/codeblock-lang.ts

@@ -0,0 +1,65 @@
+/**
+ * 代码块语言支持
+ * 提供多语言代码块支持
+ */
+
+import { parser } from "./parser.js";
+import { configureNesting } from "./nested-parser";
+
+import {
+  LRLanguage,
+  LanguageSupport,
+  foldNodeProp,
+} from "@codemirror/language";
+import { styleTags, tags as t } from "@lezer/highlight";
+
+import { json } from "@codemirror/lang-json";
+
+/**
+ * 折叠节点函数
+ */
+function foldNode(node: any) {
+  return { from: node.from, to: node.to - 1 };
+}
+
+/**
+ * 代码块语言定义
+ */
+export const CodeBlockLanguage = LRLanguage.define({
+  parser: parser.configure({
+    props: [
+      styleTags({
+        BlockDelimiter: t.tagName,
+      }),
+
+      foldNodeProp.add({
+        BlockContent(node: any) {
+          return { from: node.from, to: node.to - 1 };
+        },
+      }),
+    ],
+    wrap: configureNesting(),
+  }),
+  languageData: {
+    commentTokens: { line: ";" }
+  }
+});
+
+/**
+ * 创建代码块语言支持
+ */
+export function codeBlockLang() {
+  let wrap = configureNesting();
+  let lang = CodeBlockLanguage.configure({ dialect: "", wrap: wrap });
+  
+  return [
+    new LanguageSupport(lang, [json().support]),
+  ];
+}
+
+/**
+ * 获取代码块语言扩展
+ */
+export function getCodeBlockLanguageExtension() {
+  return codeBlockLang();
+} 

frontend/src/views/editor/extensions/codeblock/lang-parser/codeblock.grammar

@@ -0,0 +1,23 @@
+@external tokens blockContent from "./external-tokens.js" {
+  BlockContent
+}
+
+@top Document { Block* }
+
+Block {
+  BlockDelimiter BlockContent
+}
+
+BlockDelimiter {
+  "\n∞∞∞" BlockLanguage Auto? "\n"
+}
+
+BlockLanguage {
+  "text" | "math" | "json" | "python" | "html" | "sql" | "markdown" | 
+  "java" | "php" | "css" | "xml" | "cpp" | "rust" | "ruby" | "shell" | 
+  "yaml" | "go" | "javascript" | "typescript"
+}
+
+@tokens {
+  Auto { "-a" }
+} 

frontend/src/views/editor/extensions/codeblock/lang-parser/external-tokens.ts

@@ -0,0 +1,51 @@
+/**
+ * 外部标记器
+ * 用于识别代码块内容的边界
+ */
+
+import { ExternalTokenizer } from "@lezer/lr";
+import { BlockContent } from "./parser.terms.js";
+import { LANGUAGES } from "./languages";
+
+const EOF = -1;
+
+const FIRST_TOKEN_CHAR = "\n".charCodeAt(0);
+const SECOND_TOKEN_CHAR = "∞".charCodeAt(0);
+
+// 创建语言标记匹配器
+const languageTokensMatcher = LANGUAGES.map(l => l.token).join("|");
+const tokenRegEx = new RegExp(`^\\n∞∞∞(${languageTokensMatcher})(-a)?\\n`, "g");
+
+/**
+ * 代码块内容标记器
+ * 识别 ∞∞∞ 分隔符之间的内容
+ */
+export const blockContent = new ExternalTokenizer((input) => {
+  let current = input.peek(0);
+  let next = input.peek(1);
+
+  if (current === EOF) {
+    return;
+  }
+
+  while (true) {
+    // 除非前两个字符是换行符和"∞"字符，否则我们没有代码块内容标记
+    // 所以我们不需要检查标记的其余部分
+    if (current === FIRST_TOKEN_CHAR && next === SECOND_TOKEN_CHAR) {
+      let potentialLang = "";
+      for (let i = 0; i < 18; i++) {
+        potentialLang += String.fromCharCode(input.peek(i));
+      }
+      if (potentialLang.match(tokenRegEx)) {
+        input.acceptToken(BlockContent);
+        return;
+      }
+    }
+    if (next === EOF) {
+      input.acceptToken(BlockContent, 1);
+      return;
+    }
+    current = input.advance(1);
+    next = input.peek(1);
+  }
+}); 

frontend/src/views/editor/extensions/codeblock/lang-parser/index.ts

@@ -0,0 +1,38 @@
+/**
+ * 代码块语言解析器入口
+ * 导出所有语言解析相关的功能
+ */
+
+// 主要语言支持
+export {
+  CodeBlockLanguage,
+  codeBlockLang,
+  getCodeBlockLanguageExtension
+} from './codeblock-lang';
+
+// 语言映射和信息
+export {
+  LanguageInfo,
+  LANGUAGES,
+  languageMapping,
+  getLanguage,
+  getLanguageTokens
+} from './languages';
+
+// 嵌套解析器
+export {
+  configureNesting
+} from './nested-parser';
+
+// 解析器术语
+export * from './parser.terms.js';
+
+// 外部标记器
+export {
+  blockContent
+} from './external-tokens';
+
+// 解析器
+export {
+  parser
+} from './parser.js'; 

frontend/src/views/editor/extensions/codeblock/lang-parser/languages.ts

@@ -0,0 +1,82 @@
+/**
+ * 语言映射和解析器配置
+ */
+
+import { jsonLanguage } from "@codemirror/lang-json";
+import { pythonLanguage } from "@codemirror/lang-python";
+import { javascriptLanguage, typescriptLanguage } from "@codemirror/lang-javascript";
+import { htmlLanguage } from "@codemirror/lang-html";
+import { StandardSQL } from "@codemirror/lang-sql";
+import { markdownLanguage } from "@codemirror/lang-markdown";
+import { javaLanguage } from "@codemirror/lang-java";
+import { phpLanguage } from "@codemirror/lang-php";
+import { cssLanguage } from "@codemirror/lang-css";
+import { cppLanguage } from "@codemirror/lang-cpp";
+import { xmlLanguage } from "@codemirror/lang-xml";
+import { rustLanguage } from "@codemirror/lang-rust";
+
+import { StreamLanguage } from "@codemirror/language";
+import { ruby } from "@codemirror/legacy-modes/mode/ruby";
+import { shell } from "@codemirror/legacy-modes/mode/shell";
+import { go } from "@codemirror/legacy-modes/mode/go";
+import { yamlLanguage } from "@codemirror/lang-yaml";
+
+import { SupportedLanguage } from '../types';
+
+/**
+ * 语言信息类
+ */
+export class LanguageInfo {
+  constructor(
+    public token: SupportedLanguage,
+    public name: string,
+    public parser: any,
+    public guesslang?: string | null
+  ) {}
+}
+
+/**
+ * 支持的语言列表
+ */
+export const LANGUAGES: LanguageInfo[] = [
+  new LanguageInfo("text", "Plain Text", null),
+  new LanguageInfo("json", "JSON", jsonLanguage.parser, "json"),
+  new LanguageInfo("python", "Python", pythonLanguage.parser, "py"),
+  new LanguageInfo("javascript", "JavaScript", javascriptLanguage.parser, "js"),
+  new LanguageInfo("typescript", "TypeScript", typescriptLanguage.parser, "ts"),
+  new LanguageInfo("html", "HTML", htmlLanguage.parser, "html"),
+  new LanguageInfo("css", "CSS", cssLanguage.parser, "css"),
+  new LanguageInfo("sql", "SQL", StandardSQL.language.parser, "sql"),
+  new LanguageInfo("markdown", "Markdown", markdownLanguage.parser, "md"),
+  new LanguageInfo("java", "Java", javaLanguage.parser, "java"),
+  new LanguageInfo("php", "PHP", phpLanguage.configure({top:"Program"}).parser, "php"),
+  new LanguageInfo("xml", "XML", xmlLanguage.parser, "xml"),
+  new LanguageInfo("cpp", "C++", cppLanguage.parser, "cpp"),
+  new LanguageInfo("c", "C", cppLanguage.parser, "c"),
+  new LanguageInfo("rust", "Rust", rustLanguage.parser, "rs"),
+  new LanguageInfo("ruby", "Ruby", StreamLanguage.define(ruby).parser, "rb"),
+  new LanguageInfo("shell", "Shell", StreamLanguage.define(shell).parser, "sh"),
+  new LanguageInfo("yaml", "YAML", yamlLanguage.parser, "yaml"),
+  new LanguageInfo("go", "Go", StreamLanguage.define(go).parser, "go"),
+];
+
+/**
+ * 语言映射表
+ */
+export const languageMapping = Object.fromEntries(
+  LANGUAGES.map(l => [l.token, l.parser])
+);
+
+/**
+ * 根据 token 获取语言信息
+ */
+export function getLanguage(token: SupportedLanguage): LanguageInfo | undefined {
+  return LANGUAGES.find(lang => lang.token === token);
+}
+
+/**
+ * 获取所有语言的 token 列表
+ */
+export function getLanguageTokens(): SupportedLanguage[] {
+  return LANGUAGES.map(lang => lang.token);
+} 

frontend/src/views/editor/extensions/codeblock/lang-parser/nested-parser.ts

@@ -0,0 +1,44 @@
+/**
+ * 嵌套解析器配置
+ * 为不同语言的代码块提供语法高亮支持
+ */
+
+import { parseMixed } from "@lezer/common";
+import { BlockContent, BlockLanguage } from "./parser.terms.js";
+import { languageMapping } from "./languages";
+
+/**
+ * 配置嵌套解析器
+ * 根据代码块的语言标记选择相应的解析器
+ */
+export function configureNesting() {
+  return parseMixed((node, input) => {
+    let id = node.type.id;
+    
+    if (id === BlockContent) {
+      // 获取父节点中的语言标记
+      let blockLang = node.node.parent?.firstChild?.getChildren(BlockLanguage)[0];
+      let langName = blockLang ? input.read(blockLang.from, blockLang.to) : null;
+      
+      // 如果 BlockContent 为空，不返回解析器
+      // 这可以避免 StreamLanguage 解析器在大缓冲区时出错
+      if (node.node.from === node.node.to) {
+        return null;
+      }
+      
+      // 处理自动检测标记
+      if (langName && langName.endsWith('-a')) {
+        langName = langName.slice(0, -2); // 移除 '-a' 后缀
+      }
+      
+      // 查找对应的语言解析器
+      if (langName && langName in languageMapping && languageMapping[langName] !== null) {
+        return {
+          parser: languageMapping[langName],
+        };
+      }
+    }
+    
+    return null;
+  });
+} 

frontend/src/views/editor/extensions/codeblock/lang-parser/parser.js

@@ -0,0 +1,17 @@
+// This file was generated by lezer-generator. You probably shouldn't edit it.
+import {LRParser} from "@lezer/lr"
+import {blockContent} from "./external-tokens.js"
+export const parser = LRParser.deserialize({
+  version: 14,
+  states: "!jQQOQOOOVOQO'#C`O!dOPO'#C_OOOO'#Cc'#CcQQOQOOOOOO'#Ca'#CaO!iOSO,58zOOOO,58y,58yOOOO-E6a-E6aOOOP1G.f1G.fO!qOSO1G.fOOOP7+$Q7+$Q",
+  stateData: "!v~OXPO~OYTOZTO[TO]TO^TO_TO`TOaTObTOcTOdTOeTOfTOgTOhTOiTOjTOkTOlTO~OPVO~OUYOmXO~OmZO~O",
+  goto: "jWPPPX]aPdTROSTQOSRUPQSORWS",
+  nodeNames: "⚠ BlockContent Document Block BlockDelimiter BlockLanguage Auto",
+  maxTerm: 29,
+  skippedNodes: [0],
+  repeatNodeCount: 1,
+  tokenData: ",k~R]YZz}!O!e#V#W!p#Z#[#a#[#]#l#^#_$T#a#b%x#d#e'X#f#g([#g#h)R#h#i*O#l#m+q#m#n,SR!PPmQ%&x%&y!SP!VP%&x%&y!YP!]P%&x%&y!`P!eOXP~!hP#T#U!k~!pOU~~!sQ#d#e!y#g#h#U~!|P#d#e#P~#UOe~~#XP#g#h#[~#aOc~~#dP#c#d#g~#lOj~~#oP#h#i#r~#uP#a#b#x~#{P#`#a$O~$TO^~~$WQ#T#U$^#g#h%g~$aP#j#k$d~$gP#T#U$j~$oPa~#g#h$r~$uP#V#W$x~${P#f#g%O~%RP#]#^%U~%XP#d#e%[~%_P#h#i%b~%gOk~~%jP#c#d%m~%pP#b#c%s~%xO[~~%{P#T#U&O~&RQ#f#g&X#h#i&|~&[P#_#`&_~&bP#W#X&e~&hP#c#d&k~&nP#k#l&q~&tP#b#c&w~&|O`~~'PP#[#]'S~'XOZ~~'[Q#[#]'b#m#n'm~'eP#d#e'h~'mOb~~'pP#h#i's~'vP#[#]'y~'|P#c#d(P~(SP#b#c(V~([O]~~(_P#i#j(b~(eQ#U#V(k#g#h(v~(nP#m#n(q~(vOg~~(yP#h#i(|~)ROf~~)UQ#[#])[#e#f)s~)_P#X#Y)b~)eP#`#a)h~)kP#`#a)n~)sOh~~)vP#`#a)y~*OO_~~*RQ#X#Y*X#m#n*j~*[P#l#m*_~*bP#h#i*e~*jOY~~*mP#d#e*p~*sP#X#Y*v~*yP#g#h*|~+PP#V#W+S~+VP#f#g+Y~+]P#]#^+`~+cP#d#e+f~+iP#h#i+l~+qOl~~+tP#a#b+w~+zP#`#a+}~,SOd~~,VP#T#U,Y~,]P#a#b,`~,cP#`#a,f~,kOi~",
+  tokenizers: [blockContent, 0, 1],
+  topRules: {"Document":[0,2]},
+  tokenPrec: 0
+})

frontend/src/views/editor/extensions/codeblock/lang-parser/parser.terms.js

@@ -0,0 +1,8 @@
+// This file was generated by lezer-generator. You probably shouldn't edit it.
+export const
+  BlockContent = 1,
+  Document = 2,
+  Block = 3,
+  BlockDelimiter = 4,
+  BlockLanguage = 5,
+  Auto = 6