lark-docx2md 0.5.3-beta.1 → 0.5.3-beta.2

package/README.md

@@ -57,6 +57,7 @@ npx -y lark-docx2md@latest download <url>
 > - 非 agent 模式下 `--wb-format yaml` 时：`--wb-image-mode` 强制为 `online`。
 > - `--filter-title`：按标题文本精确匹配（忽略前后空格），收集该标题及其所有子级块，遇到同级或更高级标题时停止。同名标题取首个；未匹配时错误信息附全文标题 yaml 清单。
 > - `--filter-title-block-id`：按 heading 块 id 严格相等匹配，适用于同名标题或脚本化场景；通常先用 `get-titles` 查出目标 `blockId` 再传入。与 `--filter-title` 互斥。
+> - **命中深层标题时自动注入父级标题（仅 heading 块本身）**：两个过滤参数均会按文档顺序补齐包含路径上的顶层→该标题的所有祖先标题，以保留章节层级上下文；不会引入旁支兄弟或伪造跳级。
 
 ## 子命令：`get-titles`
 
@@ -100,7 +101,7 @@ npx -y lark-docx2md@latest get-titles --agent <url>
 | Callout             | 高亮块     | `>[!TIP]` + 子块             |
 | Divider             | 分割线     | `---`                      |
 | Image               | 图片      | `![图片](url)`               |
-| Table / TableCell   | 表格      | `<table>` HTML（支持合并单元格）    |
+| Table / TableCell   | 表格      | GFM 管道表格（合并单元格按值展开）  |
 | QuoteContainer      | 引用容器    | `> 子块内容`                   |
 | Grid / GridColumn   | 分栏布局    | 展平为子块内容                    |
 | Sheet               | 电子表格    | GFM 表格（合并单元格自动展开）          |

package/dist/cli.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { a as setLogLevel, n as buildTitleTree, o as serializeYaml, r as getTitles, t as convert } from "./converter-DLMAssSI.js";
+import { a as setLogLevel, n as buildTitleTree, o as serializeYaml, r as getTitles, t as convert } from "./converter-C2dAcaTO.js";
 import * as fs from "node:fs";
 import * as path from "node:path";
 import { Command } from "commander";

package/dist/{converter-DLMAssSI.js → converter-C2dAcaTO.js}

@@ -657,6 +657,75 @@ function registerBuiltinParsers(parser) {
 	parser.register(sheetBlockParser);
 }
 //#endregion
+//#region src/sheet/index.ts
+const escapeCell = (s) => s.replace(/\|/g, "\\|").replace(/\n/g, "<br>");
+function cellToMd(cell) {
+	if (cell == null) return "";
+	if (typeof cell !== "object") return escapeCell(String(cell));
+	if (Array.isArray(cell)) return cell.map(cellToMd).join("");
+	const o = cell;
+	switch (o.type) {
+		case "text": return escapeCell(String(o.text ?? ""));
+		case "url": return `[${escapeCell(o.text ?? o.link ?? "")}](${o.link ?? ""})`;
+		case "mentionUser": return `@${escapeCell(o.name ?? o.textArr?.join("") ?? "")}`;
+		case "formula": return `\`${escapeCell(o.text ?? "")}\``;
+		default:
+			if (o.text != null) return escapeCell(String(o.text));
+			return "";
+	}
+}
+function expandMerges(rows, merges) {
+	const grid = rows.map((r) => r.slice());
+	for (const m of merges) {
+		const r0 = m.start_row_index ?? 0;
+		const r1 = m.end_row_index ?? r0;
+		const c0 = m.start_column_index ?? 0;
+		const c1 = m.end_column_index ?? c0;
+		const v = grid[r0]?.[c0] ?? "";
+		for (let r = r0; r <= r1; r++) {
+			if (!grid[r]) grid[r] = [];
+			for (let c = c0; c <= c1; c++) {
+				if (r === r0 && c === c0) continue;
+				grid[r][c] = v;
+			}
+		}
+	}
+	return grid;
+}
+const isEmptyCell = (v) => v == null || v === "";
+function trimTrailingEmpty(rows) {
+	let lastRow = -1;
+	for (let r = 0; r < rows.length; r++) if ((rows[r] ?? []).some((c) => !isEmptyCell(c))) lastRow = r;
+	if (lastRow < 0) return [];
+	const trimmedRows = rows.slice(0, lastRow + 1);
+	let lastCol = -1;
+	for (const row of trimmedRows) for (let c = (row?.length ?? 0) - 1; c >= 0; c--) if (!isEmptyCell(row[c])) {
+		if (c > lastCol) lastCol = c;
+		break;
+	}
+	if (lastCol < 0) return trimmedRows.map(() => []);
+	return trimmedRows.map((r) => (r ?? []).slice(0, lastCol + 1));
+}
+function columnIndexToLetter(n) {
+	let result = "";
+	while (n > 0) {
+		n--;
+		result = String.fromCharCode(65 + n % 26) + result;
+		n = Math.floor(n / 26);
+	}
+	return result;
+}
+function renderMarkdownTable(rows) {
+	if (!rows.length) return "_（空表）_\n\n";
+	const [head, ...body] = rows;
+	if (!head || head.length === 0) return "_（空表）_\n\n";
+	let out = `| ${head.join(" | ")} |\n`;
+	out += `| ${head.map(() => "---").join(" | ")} |\n`;
+	for (const r of body) out += `| ${r.join(" | ")} |\n`;
+	out += "\n";
+	return out;
+}
+//#endregion
 //#region src/md-ast/serializer.ts
 var MdSerializer = class {
 	constructor() {
@@ -821,22 +890,38 @@ const tableSerializer = {
 	type: "table",
 	serialize(node, ctx) {
 		if (node.type !== "table") return "";
-		let buf = "<table>\n";
-		for (const row of node.rows) {
-			buf += "<tr>\n";
-			for (const cell of row.cells) {
-				let attrs = "";
-				if (cell.rowSpan && cell.rowSpan > 1) attrs += ` rowspan="${cell.rowSpan}"`;
-				if (cell.colSpan && cell.colSpan > 1) attrs += ` colspan="${cell.colSpan}"`;
-				const content = ctx.serializeInline(cell.content);
-				buf += `<td${attrs}>${content}</td>`;
+		return renderMarkdownTable(rebuildGrid(node.rows, ctx));
+	}
+};
+/**
+* 基于 parser 产出的稀疏 rows（被合并覆盖的格已被过滤，顶格包含 rowSpan/colSpan）
+* 还原为稠密二维字符串网格：Markdown 不支持合并，按"复制左上角值"展开。
+*/
+function rebuildGrid(rows, ctx) {
+	const occupied = /* @__PURE__ */ new Set();
+	const grid = [];
+	for (let r = 0; r < rows.length; r++) {
+		if (!grid[r]) grid[r] = [];
+		let c = 0;
+		for (const cell of rows[r].cells) {
+			while (occupied.has(`${r}-${c}`)) c++;
+			const value = escapeCell(ctx.serializeInline(cell.content));
+			const rs = cell.rowSpan ?? 1;
+			const cs = cell.colSpan ?? 1;
+			for (let rr = r; rr < r + rs; rr++) {
+				if (!grid[rr]) grid[rr] = [];
+				for (let cc = c; cc < c + cs; cc++) {
+					grid[rr][cc] = value;
+					if (rr !== r || cc !== c) occupied.add(`${rr}-${cc}`);
+				}
 			}
-			buf += "</tr>\n";
+			c += cs;
 		}
-		buf += "</table>\n";
-		return buf;
 	}
-};
+	const maxCols = grid.reduce((m, row) => Math.max(m, row.length), 0);
+	for (const row of grid) for (let i = 0; i < maxCols; i++) if (row[i] === void 0) row[i] = "";
+	return grid;
+}
 const gridSerializer = {
 	type: "grid",
 	serialize(node, ctx) {
@@ -862,19 +947,7 @@ const sheetResolvedSerializer = {
 				out += `> ${s.error}\n\n`;
 				continue;
 			}
-			if (!s.rows.length) {
-				out += "_（空表）_\n\n";
-				continue;
-			}
-			const [head, ...body] = s.rows;
-			if (!head) {
-				out += "_（空表）_\n\n";
-				continue;
-			}
-			out += `| ${head.join(" | ")} |\n`;
-			out += `| ${head.map(() => "---").join(" | ")} |\n`;
-			for (const r of body) out += `| ${r.join(" | ")} |\n`;
-			out += "\n";
+			out += renderMarkdownTable(s.rows);
 		}
 		return out;
 	}
@@ -2587,65 +2660,6 @@ function collectImageTokens(nodes, out) {
 	}
 }
 //#endregion
-//#region src/sheet/index.ts
-const escapeCell = (s) => s.replace(/\|/g, "\\|").replace(/\n/g, "<br>");
-function cellToMd(cell) {
-	if (cell == null) return "";
-	if (typeof cell !== "object") return escapeCell(String(cell));
-	if (Array.isArray(cell)) return cell.map(cellToMd).join("");
-	const o = cell;
-	switch (o.type) {
-		case "text": return escapeCell(String(o.text ?? ""));
-		case "url": return `[${escapeCell(o.text ?? o.link ?? "")}](${o.link ?? ""})`;
-		case "mentionUser": return `@${escapeCell(o.name ?? o.textArr?.join("") ?? "")}`;
-		case "formula": return `\`${escapeCell(o.text ?? "")}\``;
-		default:
-			if (o.text != null) return escapeCell(String(o.text));
-			return "";
-	}
-}
-function expandMerges(rows, merges) {
-	const grid = rows.map((r) => r.slice());
-	for (const m of merges) {
-		const r0 = m.start_row_index ?? 0;
-		const r1 = m.end_row_index ?? r0;
-		const c0 = m.start_column_index ?? 0;
-		const c1 = m.end_column_index ?? c0;
-		const v = grid[r0]?.[c0] ?? "";
-		for (let r = r0; r <= r1; r++) {
-			if (!grid[r]) grid[r] = [];
-			for (let c = c0; c <= c1; c++) {
-				if (r === r0 && c === c0) continue;
-				grid[r][c] = v;
-			}
-		}
-	}
-	return grid;
-}
-const isEmptyCell = (v) => v == null || v === "";
-function trimTrailingEmpty(rows) {
-	let lastRow = -1;
-	for (let r = 0; r < rows.length; r++) if ((rows[r] ?? []).some((c) => !isEmptyCell(c))) lastRow = r;
-	if (lastRow < 0) return [];
-	const trimmedRows = rows.slice(0, lastRow + 1);
-	let lastCol = -1;
-	for (const row of trimmedRows) for (let c = (row?.length ?? 0) - 1; c >= 0; c--) if (!isEmptyCell(row[c])) {
-		if (c > lastCol) lastCol = c;
-		break;
-	}
-	if (lastCol < 0) return trimmedRows.map(() => []);
-	return trimmedRows.map((r) => (r ?? []).slice(0, lastCol + 1));
-}
-function columnIndexToLetter(n) {
-	let result = "";
-	while (n > 0) {
-		n--;
-		result = String.fromCharCode(65 + n % 26) + result;
-		n = Math.floor(n / 26);
-	}
-	return result;
-}
-//#endregion
 //#region src/logger.ts
 const COLORS = {
 	[LoggerLevel.fatal]: "\x1B[35m",
@@ -3013,7 +3027,9 @@ function toHeadingInfo(block) {
 *
 * 复用要点：
 * - page 节点（block_type=1）始终保留
-* - scanning 阶段把所有 heading 推入 availableHeadings
+* - scanning 阶段把所有 heading 推入 availableHeadings，并以栈式回溯维护祖先链
+* - 命中时把祖先 heading（level < 命中 level）按文档顺序注入 collected，
+*   作为「仅标题」上下文（heading 的非命中兄弟内容不在 blockMap 中，Parser 会自动跳过）
 * - collecting 阶段遇到同级或更高级标题终止
 */
 function createHeadingMatchFilter(match) {
@@ -3021,6 +3037,7 @@ function createHeadingMatchFilter(match) {
 	let matchedLevel = 0;
 	const collected = [];
 	const seen = [];
+	const ancestorStack = [];
 	function pageHandler(blocks) {
 		for (const block of blocks) {
 			if (block.block_type === 1) {
@@ -3031,12 +3048,17 @@ function createHeadingMatchFilter(match) {
 				case "scanning": {
 					const info = toHeadingInfo(block);
 					if (info) {
+						while (ancestorStack.length > 0 && ancestorStack[ancestorStack.length - 1].info.level >= info.level) ancestorStack.pop();
 						seen.push(info);
 						if (match(block, info)) {
+							for (const entry of ancestorStack) collected.push(entry.block);
 							state = "collecting";
 							matchedLevel = info.level;
 							collected.push(block);
-						}
+						} else ancestorStack.push({
+							info,
+							block
+						});
 					}
 					break;
 				}
@@ -3240,4 +3262,4 @@ function buildFilterErrorMessage(opts, result, url, docToken) {
 //#endregion
 export { setLogLevel as a, parseWikiUrl as i, buildTitleTree as n, serializeYaml as o, getTitles as r, convert as t };
 
-//# sourceMappingURL=converter-DLMAssSI.js.map
+//# sourceMappingURL=converter-C2dAcaTO.js.map