@incremark/core 0.1.2 → 0.2.0

package/dist/utils/index.d.ts

@@ -1,6 +1,9 @@
+import { RootContent, Definition, FootnoteDefinition } from 'mdast';
+
 /**
  * 工具函数
  */
+
 declare function generateId(prefix?: string): string;
 /**
  * 重置 ID 计数器（用于测试）
@@ -18,5 +21,7 @@ declare function splitLines(text: string): string[];
  * 合并行为文本
  */
 declare function joinLines(lines: string[], start: number, end: number): string;
+declare function isDefinitionNode(node: RootContent): node is Definition;
+declare function isFootnoteDefinitionNode(node: RootContent): node is FootnoteDefinition;
 
-export { calculateLineOffset, generateId, joinLines, resetIdCounter, splitLines };
+export { calculateLineOffset, generateId, isDefinitionNode, isFootnoteDefinitionNode, joinLines, resetIdCounter, splitLines };

package/dist/utils/index.js

@@ -19,7 +19,13 @@ function splitLines(text) {
 function joinLines(lines, start, end) {
   return lines.slice(start, end + 1).join("\n");
 }
+function isDefinitionNode(node) {
+  return node.type === "definition";
+}
+function isFootnoteDefinitionNode(node) {
+  return node.type === "footnoteDefinition";
+}
 
-export { calculateLineOffset, generateId, joinLines, resetIdCounter, splitLines };
+export { calculateLineOffset, generateId, isDefinitionNode, isFootnoteDefinitionNode, joinLines, resetIdCounter, splitLines };
 //# sourceMappingURL=index.js.map
 //# sourceMappingURL=index.js.map

package/dist/utils/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../../src/utils/index.ts"],"names":[],"mappings":";AAOA,IAAI,SAAA,GAAY,CAAA;AACT,SAAS,UAAA,CAAW,SAAS,OAAA,EAAiB;AACnD,EAAA,OAAO,CAAA,EAAG,MAAM,CAAA,CAAA,EAAI,EAAE,SAAS,CAAA,CAAA;AACjC;AAKO,SAAS,cAAA,GAAuB;AACrC,EAAA,SAAA,GAAY,CAAA;AACd;AAKO,SAAS,mBAAA,CAAoB,OAAiB,SAAA,EAA2B;AAC9E,EAAA,IAAI,MAAA,GAAS,CAAA;AACb,EAAA,KAAA,IAAS,IAAI,CAAA,EAAG,CAAA,GAAI,aAAa,CAAA,GAAI,KAAA,CAAM,QAAQ,CAAA,EAAA,EAAK;AACtD,IAAA,MAAA,IAAU,KAAA,CAAM,CAAC,CAAA,CAAE,MAAA,GAAS,CAAA;AAAA,EAC9B;AACA,EAAA,OAAO,MAAA;AACT;AAKO,SAAS,WAAW,IAAA,EAAwB;AACjD,EAAA,OAAO,IAAA,CAAK,MAAM,IAAI,CAAA;AACxB;AAKO,SAAS,SAAA,CAAU,KAAA,EAAiB,KAAA,EAAe,GAAA,EAAqB;AAC7E,EAAA,OAAO,MAAM,KAAA,CAAM,KAAA,EAAO,MAAM,CAAC,CAAA,CAAE,KAAK,IAAI,CAAA;AAC9C","file":"index.js","sourcesContent":["/**\n * 工具函数\n */\n\n/**\n * 生成唯一 ID\n */\nlet idCounter = 0\nexport function generateId(prefix = 'block'): string {\n  return `${prefix}-${++idCounter}`\n}\n\n/**\n * 重置 ID 计数器（用于测试）\n */\nexport function resetIdCounter(): void {\n  idCounter = 0\n}\n\n/**\n * 计算行的偏移量\n */\nexport function calculateLineOffset(lines: string[], lineIndex: number): number {\n  let offset = 0\n  for (let i = 0; i < lineIndex && i < lines.length; i++) {\n    offset += lines[i].length + 1 // +1 for newline\n  }\n  return offset\n}\n\n/**\n * 将文本按行分割\n */\nexport function splitLines(text: string): string[] {\n  return text.split('\\n')\n}\n\n/**\n * 合并行为文本\n */\nexport function joinLines(lines: string[], start: number, end: number): string {\n  return lines.slice(start, end + 1).join('\\n')\n}\n\n"]}
+{"version":3,"sources":["../../src/utils/index.ts"],"names":[],"mappings":";AASA,IAAI,SAAA,GAAY,CAAA;AACT,SAAS,UAAA,CAAW,SAAS,OAAA,EAAiB;AACnD,EAAA,OAAO,CAAA,EAAG,MAAM,CAAA,CAAA,EAAI,EAAE,SAAS,CAAA,CAAA;AACjC;AAKO,SAAS,cAAA,GAAuB;AACrC,EAAA,SAAA,GAAY,CAAA;AACd;AAKO,SAAS,mBAAA,CAAoB,OAAiB,SAAA,EAA2B;AAC9E,EAAA,IAAI,MAAA,GAAS,CAAA;AACb,EAAA,KAAA,IAAS,IAAI,CAAA,EAAG,CAAA,GAAI,aAAa,CAAA,GAAI,KAAA,CAAM,QAAQ,CAAA,EAAA,EAAK;AACtD,IAAA,MAAA,IAAU,KAAA,CAAM,CAAC,CAAA,CAAE,MAAA,GAAS,CAAA;AAAA,EAC9B;AACA,EAAA,OAAO,MAAA;AACT;AAKO,SAAS,WAAW,IAAA,EAAwB;AACjD,EAAA,OAAO,IAAA,CAAK,MAAM,IAAI,CAAA;AACxB;AAKO,SAAS,SAAA,CAAU,KAAA,EAAiB,KAAA,EAAe,GAAA,EAAqB;AAC7E,EAAA,OAAO,MAAM,KAAA,CAAM,KAAA,EAAO,MAAM,CAAC,CAAA,CAAE,KAAK,IAAI,CAAA;AAC9C;AAEO,SAAS,iBAAiB,IAAA,EAAuC;AACtE,EAAA,OAAO,KAAK,IAAA,KAAS,YAAA;AACvB;AAEO,SAAS,yBAAyB,IAAA,EAA+C;AACtF,EAAA,OAAO,KAAK,IAAA,KAAS,oBAAA;AACvB","file":"index.js","sourcesContent":["/**\n * 工具函数\n */\n\nimport type { Definition, FootnoteDefinition, RootContent } from \"mdast\"\n\n/**\n * 生成唯一 ID\n */\nlet idCounter = 0\nexport function generateId(prefix = 'block'): string {\n  return `${prefix}-${++idCounter}`\n}\n\n/**\n * 重置 ID 计数器（用于测试）\n */\nexport function resetIdCounter(): void {\n  idCounter = 0\n}\n\n/**\n * 计算行的偏移量\n */\nexport function calculateLineOffset(lines: string[], lineIndex: number): number {\n  let offset = 0\n  for (let i = 0; i < lineIndex && i < lines.length; i++) {\n    offset += lines[i].length + 1 // +1 for newline\n  }\n  return offset\n}\n\n/**\n * 将文本按行分割\n */\nexport function splitLines(text: string): string[] {\n  return text.split('\\n')\n}\n\n/**\n * 合并行为文本\n */\nexport function joinLines(lines: string[], start: number, end: number): string {\n  return lines.slice(start, end + 1).join('\\n')\n}\n\nexport function isDefinitionNode(node: RootContent): node is Definition {\n  return node.type === 'definition'\n}\n\nexport function isFootnoteDefinitionNode(node: RootContent): node is FootnoteDefinition {\n  return node.type === 'footnoteDefinition'\n}"]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@incremark/core",
-  "version": "0.1.2",
+  "version": "0.2.0",
   "description": "增量式 Markdown 解析器核心库",
   "type": "module",
   "main": "./dist/index.js",
@@ -30,6 +30,12 @@
     "mdast-util-from-markdown": "^2.0.0",
     "mdast-util-gfm": "^3.0.0",
     "micromark-extension-gfm": "^3.0.0",
+    "micromark-factory-destination": "^2.0.0",
+    "micromark-factory-label": "^2.0.0",
+    "micromark-factory-title": "^2.0.0",
+    "micromark-factory-whitespace": "^2.0.0",
+    "micromark-util-character": "^2.0.0",
+    "micromark-util-symbol": "^2.0.0",
     "micromark-util-types": "^2.0.0"
   },
   "devDependencies": {

package/src/__tests__/footnote.test.ts

@@ -0,0 +1,214 @@
+/**
+ * 脚注解析测试
+ * 
+ * 测试增量解析场景下的脚注引用和定义
+ */
+
+import { describe, it, expect } from 'vitest'
+import { createIncremarkParser } from '../parser/IncremarkParser'
+
+describe('Footnote Parsing', () => {
+  describe('Basic Footnote', () => {
+    it('should parse footnote reference before definition', () => {
+      const markdown = `这是一个简单的脚注[^1]。
+
+[^1]: 这是第一个脚注的内容。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      // 检查是否有脚注引用
+      const paragraph = ast.children[0]
+      expect(paragraph.type).toBe('paragraph')
+      
+      const hasFootnoteRef = paragraph.children?.some(
+        (node: any) => node.type === 'footnoteReference' && node.identifier === '1'
+      )
+      expect(hasFootnoteRef).toBe(true)
+
+      // 检查是否有脚注定义
+      const hasFootnoteDef = ast.children.some(
+        (node: any) => node.type === 'footnoteDefinition' && node.identifier === '1'
+      )
+      expect(hasFootnoteDef).toBe(true)
+    })
+
+    it('should parse multiple footnotes', () => {
+      const markdown = `第一个脚注[^1]，第二个脚注[^2]。
+
+[^1]: 第一个内容。
+[^2]: 第二个内容。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      // 检查两个脚注引用
+      const paragraph = ast.children[0]
+      const footnoteRefs = paragraph.children?.filter(
+        (node: any) => node.type === 'footnoteReference'
+      )
+      expect(footnoteRefs).toHaveLength(2)
+      expect(footnoteRefs?.[0].identifier).toBe('1')
+      expect(footnoteRefs?.[1].identifier).toBe('2')
+
+      // 检查两个脚注定义
+      const footnoteDefs = ast.children.filter(
+        (node: any) => node.type === 'footnoteDefinition'
+      )
+      expect(footnoteDefs).toHaveLength(2)
+      expect(footnoteDefs[0].identifier).toBe('1')
+      expect(footnoteDefs[1].identifier).toBe('2')
+    })
+  })
+
+  describe('Multiline Footnote', () => {
+    it('should parse multiline footnote content', () => {
+      const markdown = `多行脚注[^long]。
+
+[^long]: 第一段内容。
+
+    第二段内容（缩进）。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      // 检查脚注引用
+      const paragraph = ast.children[0]
+      const hasFootnoteRef = paragraph.children?.some(
+        (node: any) => node.type === 'footnoteReference' && node.identifier === 'long'
+      )
+      expect(hasFootnoteRef).toBe(true)
+
+      // 检查脚注定义
+      const footnoteDef = ast.children.find(
+        (node: any) => node.type === 'footnoteDefinition' && node.identifier === 'long'
+      ) as any
+      expect(footnoteDef).toBeDefined()
+      
+      // 检查脚注内容是否包含多个段落
+      expect(footnoteDef.children.length).toBeGreaterThan(1)
+    })
+  })
+
+  describe('Incremental Parsing', () => {
+    it('should handle footnote reference in pending block', () => {
+      const parser = createIncremarkParser({ gfm: true })
+      
+      // 第一次追加：只有引用
+      const update1 = parser.append('这是一个脚注[^1]。\n\n')
+      
+      // 检查 pending blocks 中是否有脚注引用
+      const pendingParagraph = update1.pending[0]?.node
+      const hasPendingRef = pendingParagraph?.children?.some(
+        (node: any) => node.type === 'footnoteReference'
+      )
+      expect(hasPendingRef).toBe(true)
+
+      // 第二次追加：添加定义
+      const update2 = parser.append('[^1]: 脚注内容。')
+      parser.finalize()
+
+      // 检查最终 AST
+      const ast = parser.getAst()
+      const hasFootnoteDef = ast.children.some(
+        (node: any) => node.type === 'footnoteDefinition' && node.identifier === '1'
+      )
+      expect(hasFootnoteDef).toBe(true)
+    })
+
+    it('should handle definition before reference', () => {
+      const markdown = `[^1]: 脚注内容。
+
+这是一个脚注[^1]。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      // 即使定义在前，引用也应该被正确解析
+      const paragraph = ast.children.find((node: any) => node.type === 'paragraph')
+      const hasFootnoteRef = paragraph?.children?.some(
+        (node: any) => node.type === 'footnoteReference' && node.identifier === '1'
+      )
+      expect(hasFootnoteRef).toBe(true)
+
+      const hasFootnoteDef = ast.children.some(
+        (node: any) => node.type === 'footnoteDefinition' && node.identifier === '1'
+      )
+      expect(hasFootnoteDef).toBe(true)
+    })
+  })
+
+  describe('Edge Cases', () => {
+    it('should handle footnote with special characters in identifier', () => {
+      const markdown = `脚注[^note-1]。
+
+[^note-1]: 内容。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      const paragraph = ast.children[0]
+      const hasFootnoteRef = paragraph.children?.some(
+        (node: any) => node.type === 'footnoteReference' && node.identifier === 'note-1'
+      )
+      expect(hasFootnoteRef).toBe(true)
+    })
+
+    it('should handle footnote with markdown in content', () => {
+      const markdown = `脚注[^complex]。
+
+[^complex]: 包含 **粗体** 和 *斜体*。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      const footnoteDef = ast.children.find(
+        (node: any) => node.type === 'footnoteDefinition' && node.identifier === 'complex'
+      ) as any
+      expect(footnoteDef).toBeDefined()
+
+      // 检查脚注内容是否包含格式化文本
+      const paragraph = footnoteDef.children[0]
+      const hasStrong = paragraph.children?.some((node: any) => node.type === 'strong')
+      const hasEmphasis = paragraph.children?.some((node: any) => node.type === 'emphasis')
+      expect(hasStrong || hasEmphasis).toBe(true)
+    })
+
+    it('should not parse invalid footnote syntax', () => {
+      const markdown = `这不是脚注[^ 1]。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+      const ast = result.ast
+
+      // 空格会导致解析失败，应该被当作普通文本
+      const paragraph = ast.children[0]
+      const hasFootnoteRef = paragraph.children?.some(
+        (node: any) => node.type === 'footnoteReference'
+      )
+      expect(hasFootnoteRef).toBe(false)
+    })
+  })
+
+  describe('Footnote Reference Order', () => {
+    it('should track footnote reference order', () => {
+      const markdown = `第二个[^2]出现在第一个[^1]之前。
+
+[^1]: 第一个定义。
+[^2]: 第二个定义。`
+
+      const parser = createIncremarkParser({ gfm: true })
+      const result = parser.render(markdown)
+
+      // 检查引用顺序
+      expect(result.footnoteReferenceOrder).toEqual(['2', '1'])
+    })
+  })
+})
+

package/src/detector/index.ts

@@ -19,6 +19,8 @@ const RE_HTML_BLOCK_1 = /^\s{0,3}<(script|pre|style|textarea|!--|!DOCTYPE|\?|!\[
 const RE_HTML_BLOCK_2 = /^\s{0,3}<\/?[a-zA-Z][a-zA-Z0-9-]*(\s|>|$)/
 const RE_TABLE_DELIMITER = /^\|?\s*:?-{3,}:?\s*(\|\s*:?-{3,}:?\s*)*\|?$/
 const RE_ESCAPE_SPECIAL = /[.*+?^${}()|[\]\\]/g
+const RE_FOOTNOTE_DEFINITION = /^\[\^[^\]]+\]:\s/
+const RE_FOOTNOTE_CONTINUATION = /^(?:    |\t)/
 
 /** fence 结束模式缓存 */
 const fenceEndPatternCache = new Map<string, RegExp>()
@@ -122,6 +124,34 @@ export function isTableDelimiter(line: string): boolean {
   return RE_TABLE_DELIMITER.test(line.trim())
 }
 
+// ============ 脚注检测 ============
+
+/**
+ * 检测是否是脚注定义的起始行
+ * 格式: [^id]: content
+ * 
+ * @example
+ * isFootnoteDefinitionStart('[^1]: 脚注内容') // true
+ * isFootnoteDefinitionStart('[^note]: 内容') // true
+ * isFootnoteDefinitionStart('    缩进内容')   // false
+ */
+export function isFootnoteDefinitionStart(line: string): boolean {
+  return RE_FOOTNOTE_DEFINITION.test(line)
+}
+
+/**
+ * 检测是否是脚注定义的延续行（缩进行）
+ * 至少4个空格或1个tab
+ * 
+ * @example
+ * isFootnoteContinuation('    第二行')  // true
+ * isFootnoteContinuation('\t第二行')    // true
+ * isFootnoteContinuation('  两个空格')   // false
+ */
+export function isFootnoteContinuation(line: string): boolean {
+  return RE_FOOTNOTE_CONTINUATION.test(line)
+}
+
 // ============ 容器检测 ============
 
 /**