Files
MorphDoc/packages/core/src/docx.ts
T
SkyJourney 2c5c1bd317 release: 发布 v0.6.1 DOCX 视觉一致性修复
新增通用 CSS 到 OOXML 翻译修复,统一字体、字距、精确行距、段落、列表、表格、引用、代码块与行内代码连续性,不引入按主题 ID 分支。

新增 MdTP Mono 并统一 Serif、Sans、Mono 三字体包的 Chromium 与 DOCX 使用链;字体声明、嵌入部件和 Word/WPS 实际采用均进入硬门禁。

重建封面整页及正文语义块视觉差分,14 套主题、纵横两个方向、五组页边距共 140 个真实场景全部通过,阻断失败和诊断失败均为零。

源码服务、Docker Web API 与实际安装 Desktop 的 red-briefing 导出均包含 5 个字体部件;Word/WPS 原生渲染和逐页复核通过。修复 Docker 构建上下文与运行层复用软链接,并完善 v0.6.1 版本、发行说明和发布归集。

验证:npm test(116 个文件、616 项测试)、npm run typecheck、npm run build、git diff --check 全部通过。Desktop 安装器与 ZIP、Docker v0.6.1 镜像已生成;Windows 产物仍为未签名内部发行。
2026-08-04 10:30:44 +08:00

335 lines
9.3 KiB
TypeScript

import { z } from "zod";
import { exportConfigSchema } from "./export-config.js";
export const DOCX_PANDOC_VERSION = "3.9.0.2";
export const DOCX_MIME_TYPE =
"application/vnd.openxmlformats-officedocument.wordprocessingml.document";
export const DOCX_FILE_EXTENSION = ".docx";
export const MAXIMUM_DOCX_MARKDOWN_LENGTH = 1_500_000;
export const MAXIMUM_DOCX_FILE_NAME_LENGTH = 500;
export const MAXIMUM_DOCX_RESOURCE_COUNT = 50;
export const DOCX_MEDIA_RASTER_DPI = 300;
export const DOCX_MEDIA_CSS_DPI = 96;
export const DOCX_MEDIA_RASTER_SCALE =
DOCX_MEDIA_RASTER_DPI / DOCX_MEDIA_CSS_DPI;
export const MAXIMUM_DOCX_MEDIA_EDGE_PIXELS = 4_096;
export const MAXIMUM_DOCX_MEDIA_PIXELS = 16_000_000;
export const MAXIMUM_DOCX_MEDIA_BYTES = 8 * 1024 * 1024;
export const MAXIMUM_DOCX_TOTAL_MEDIA_BYTES = 30 * 1024 * 1024;
export const MAXIMUM_DOCX_OUTPUT_BYTES = 64 * 1024 * 1024;
export const documentExportFormatSchema = z.enum(["pdf", "docx"]);
export type DocumentExportFormat = z.infer<
typeof documentExportFormatSchema
>;
export const docxSourceResourceSchema = z.object({
path: z.string().min(1).max(1_000),
contentType: z.string().min(1).max(100).optional(),
data: z.string().min(1)
});
export type DocxSourceResource = z.infer<
typeof docxSourceResourceSchema
>;
export const docxExportRequestSchema = z.object({
markdown: z.string().max(MAXIMUM_DOCX_MARKDOWN_LENGTH),
fileName: z
.string()
.max(MAXIMUM_DOCX_FILE_NAME_LENGTH)
.default("文档.md"),
language: z.string().max(50).default("zh-CN"),
resources: z
.array(docxSourceResourceSchema)
.max(MAXIMUM_DOCX_RESOURCE_COUNT)
.default([]),
exportConfig: exportConfigSchema
});
export type DocxExportRequest = z.infer<
typeof docxExportRequestSchema
>;
export type DocxExportRequestInput = z.input<
typeof docxExportRequestSchema
>;
export const docxRuntimeStatusSchema = z.enum([
"available",
"not-found",
"version-mismatch",
"not-executable",
"probe-timeout"
]);
export type DocxRuntimeStatus = z.infer<
typeof docxRuntimeStatusSchema
>;
const availableDocxCapabilitySchema = z.object({
format: z.literal("docx"),
status: z.literal("available"),
expectedVersion: z.literal(DOCX_PANDOC_VERSION),
detectedVersion: z.literal(DOCX_PANDOC_VERSION)
});
const unavailableDocxCapabilitySchema = z.object({
format: z.literal("docx"),
status: docxRuntimeStatusSchema.exclude(["available"]),
expectedVersion: z.literal(DOCX_PANDOC_VERSION),
detectedVersion: z.string().max(100).optional(),
message: z.string().max(500)
});
export const docxCapabilitySchema = z.discriminatedUnion("status", [
availableDocxCapabilitySchema,
unavailableDocxCapabilitySchema
]);
export type DocxCapability = z.infer<typeof docxCapabilitySchema>;
export const docxMediaKindSchema = z.enum([
"image",
"mermaid",
"echarts"
]);
export type DocxMediaKind = z.infer<typeof docxMediaKindSchema>;
export const docxMediaAlignmentSchema = z.enum([
"left",
"center",
"right"
]);
export type DocxMediaAlignment = z.infer<
typeof docxMediaAlignmentSchema
>;
export const docxTableLayoutSchema = z.object({
ordinal: z.number().int().min(1).max(256),
widthPercent: z.number().positive().max(100),
leftOffsetPercent: z.number().min(0).max(100),
columnWidthPercents: z
.array(z.number().positive().max(100))
.min(1)
.max(64),
rows: z
.array(
z.object({
cells: z
.array(
z.object({
columnSpan: z.number().int().min(1).max(64),
backgroundColor: z
.string()
.regex(/^#[0-9a-f]{6}$/iu),
color: z.string().regex(/^#[0-9a-f]{6}$/iu),
bold: z.boolean(),
italic: z.boolean(),
alignment: z.enum(["left", "center", "right", "justify"])
})
)
.min(1)
.max(64)
})
)
.max(2048)
});
export type DocxTableLayout = z.infer<
typeof docxTableLayoutSchema
>;
export const docxTextBlockLayoutSchema = z.object({
ordinal: z.number().int().min(1).max(100_000),
text: z.string().min(1).max(100_000),
letterSpacingPt: z.number().min(-20).max(100),
alignment: z
.enum(["left", "center", "right", "justify", "distribute"])
.optional(),
linePitchPt: z.number().min(1).max(500).optional(),
lineBreakOffsets: z
.array(z.number().int().min(1).max(100_000))
.max(10_000)
});
export type DocxTextBlockLayout = z.infer<
typeof docxTextBlockLayoutSchema
>;
export const docxListItemLayoutSchema = z.object({
ordinal: z.number().int().min(1).max(100_000),
text: z.string().min(1).max(100_000),
depth: z.number().int().min(0).max(64),
textStartPt: z.number().min(0).max(2_000)
});
export type DocxListItemLayout = z.infer<
typeof docxListItemLayoutSchema
>;
export const docxInlineCodeLayoutSchema = z.object({
ordinal: z.number().int().min(1).max(100_000),
text: z.string().min(1).max(100_000),
fontSizePt: z.number().min(1).max(200),
letterSpacingPt: z.number().min(-20).max(100),
color: z.string().regex(/^#[0-9a-f]{6}$/iu),
backgroundColor: z.string().regex(/^#[0-9a-f]{6}$/iu).optional(),
paddingPt: z.object({
top: z.number().min(0).max(1_000),
right: z.number().min(0).max(1_000),
bottom: z.number().min(0).max(1_000),
left: z.number().min(0).max(1_000)
}),
borderPt: z.object({
top: z.number().min(0).max(20),
right: z.number().min(0).max(20),
bottom: z.number().min(0).max(20),
left: z.number().min(0).max(20)
})
});
export type DocxInlineCodeLayout = z.infer<
typeof docxInlineCodeLayoutSchema
>;
export const docxDocumentLayoutPlanSchema = z.object({
tables: z.array(docxTableLayoutSchema).max(256),
textBlocks: z.array(docxTextBlockLayoutSchema).max(100_000).optional(),
listItems: z.array(docxListItemLayoutSchema).max(100_000).optional(),
inlineCodes: z.array(docxInlineCodeLayoutSchema).max(100_000).optional()
});
export type DocxDocumentLayoutPlan = z.infer<
typeof docxDocumentLayoutPlanSchema
>;
export const docxMediaCaptureTargetSchema = z.object({
id: z.string().regex(/^docx-media-\d+$/u),
kind: docxMediaKindSchema,
ordinal: z.number().int().min(1).max(MAXIMUM_DOCX_RESOURCE_COUNT),
kindOrdinal: z
.number()
.int()
.min(1)
.max(MAXIMUM_DOCX_RESOURCE_COUNT),
altText: z.string().max(1_000),
caption: z.string().max(1_000).optional(),
alignment: docxMediaAlignmentSchema,
displayWidthPx: z.number().positive().max(10_000),
displayHeightPx: z.number().positive().max(10_000),
captureX: z.number().int().nonnegative().max(100_000),
captureY: z.number().int().nonnegative().max(100_000),
captureWidthPx: z.number().int().positive().max(10_000),
captureHeightPx: z.number().int().positive().max(10_000),
rasterScale: z.number().positive().max(DOCX_MEDIA_RASTER_SCALE)
});
export type DocxMediaCaptureTarget = z.infer<
typeof docxMediaCaptureTargetSchema
>;
export const docxMediaCapturePlanSchema = z.object({
targets: z
.array(docxMediaCaptureTargetSchema)
.max(MAXIMUM_DOCX_RESOURCE_COUNT),
echartsErrors: z.array(z.string().max(1_000)),
mermaidErrors: z.array(z.string().max(1_000)),
documentLayout: docxDocumentLayoutPlanSchema.optional()
});
export type DocxMediaCapturePlan = z.infer<
typeof docxMediaCapturePlanSchema
>;
export interface DocxPngMediaResource
extends DocxMediaCaptureTarget {
fileName: string;
contentType: "image/png";
content: Uint8Array;
pixelWidth: number;
pixelHeight: number;
}
export interface PreparedDocxMedia {
resources: DocxPngMediaResource[];
echartsErrors: string[];
mermaidErrors: string[];
warnings: string[];
totalBytes: number;
documentLayout?: DocxDocumentLayoutPlan;
}
export const docxExportErrorCodeSchema = z.enum([
"INVALID_DOCX_REQUEST",
"INVALID_EXPORT_CONFIG",
"INVALID_FILE_NAME",
"INVALID_MARKDOWN",
"INVALID_FRONT_MATTER",
"MARKDOWN_TOO_LARGE",
"INVALID_IMAGE_RESOURCES",
"IMAGE_RESOURCES_TOO_LARGE",
"THEME_NOT_FOUND",
"DOCX_RUNTIME_NOT_FOUND",
"DOCX_RUNTIME_VERSION_MISMATCH",
"DOCX_RUNTIME_NOT_EXECUTABLE",
"DOCX_RUNTIME_PROBE_TIMEOUT",
"DOCX_QUEUE_FULL",
"DOCX_RENDER_TIMEOUT",
"DOCX_GENERATION_FAILED",
"DOCX_OUTPUT_INVALID"
]);
export type DocxExportErrorCode = z.infer<
typeof docxExportErrorCodeSchema
>;
export const docxExportErrorResponseSchema = z.object({
error: docxExportErrorCodeSchema,
message: z.string().min(1).max(1_000),
retryable: z.boolean().default(false)
});
export type DocxExportErrorResponse = z.infer<
typeof docxExportErrorResponseSchema
>;
export interface DocxGenerationTimings {
queueMs: number;
probeMs: number;
prepareMs: number;
themeStyleMs: number;
mediaMs: number;
referenceMs: number;
pandocMs: number;
validationMs: number;
totalMs: number;
}
export interface DocxExportDiagnostics {
warnings: string[];
echartsErrors: string[];
mermaidErrors: string[];
}
export interface DocxExportResult {
docx: Uint8Array;
fileName: string;
diagnostics: DocxExportDiagnostics;
timings: DocxGenerationTimings;
}
export function createDocxFileName(fileName: unknown) {
const source =
typeof fileName === "string"
? fileName.split(/[\\/]/).at(-1) ?? ""
: "";
const stem = source
.replace(/\.(?:md|markdown|docx)$/i, "")
.replace(/[<>:"/\\|?*\u0000-\u001f]/g, "_")
.replace(/[.\s]+$/g, "")
.trim();
return `${stem || "文档"}${DOCX_FILE_EXTENSION}`;
}