新增能力:将 DOCX 发布验收拆分为四套独立 140,支持真实语料冻结、指纹复用、失败与基础设施错误独立统计,并为表格换行、全 JSON 围栏、代码连续性和长文档分页建立通用门禁。 问题修复:冻结 Paged.js 分片前的逻辑表格列轨并传递打印几何,统一 Markdown 表格换行、代码、段落与 OOXML 翻译;改进 PDF 文本流排序、语义块映射、颜色与栅格比较,消除窄字符重叠和跨行范围符号误报。 兼容与部署:版本统一为 0.6.2;正式 Docker 镜像内置固定 Chromium、Pandoc 3.9.0.2 和 Serif/Sans/Mono 字体;Desktop NSIS 与 ZIP 继续直接内置字体,无需系统字体安装。 验证结果:合成基线与长庆严格 280/280,M4N 140/140;健康数据残余误报 6/115(5.22%),均核查为重复表头自动对齐/取样误报且基础设施错误为 0。全项目测试、类型检查、生产构建和 git diff --check 通过;正式 Docker、NSIS、ZIP、离线镜像、部署包、清单及 SHA-256 均已生成并校验。
238 lines
7.9 KiB
TypeScript
238 lines
7.9 KiB
TypeScript
import { createHash } from "node:crypto";
|
|
|
|
import { createCanvas } from "@napi-rs/canvas";
|
|
import { describe, expect, it } from "vitest";
|
|
|
|
import {
|
|
comparePageRasters,
|
|
type PdfPageRaster,
|
|
} from "../src/index.js";
|
|
|
|
function raster(rectangleX: number): PdfPageRaster {
|
|
const canvas = createCanvas(80, 100);
|
|
const context = canvas.getContext("2d");
|
|
context.fillStyle = "#ffffff";
|
|
context.fillRect(0, 0, 80, 100);
|
|
context.fillStyle = "#111111";
|
|
context.fillRect(rectangleX, 20, 20, 40);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: 80,
|
|
heightPx: 100,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
};
|
|
}
|
|
|
|
function differentlySizedRaster(width: number, height: number): PdfPageRaster {
|
|
const canvas = createCanvas(width, height);
|
|
const context = canvas.getContext("2d");
|
|
context.fillStyle = "#ffffff";
|
|
context.fillRect(0, 0, width, height);
|
|
context.fillStyle = "#111111";
|
|
context.fillRect(width * 0.25, height * 0.2, width * 0.25, height * 0.4);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: width,
|
|
heightPx: height,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
};
|
|
}
|
|
|
|
describe("PDF 栅格差异", () => {
|
|
it("相同页面的全部指标为无差异", async () => {
|
|
const page = raster(10);
|
|
const result = await comparePageRasters(page, page);
|
|
expect(result.metrics).toMatchObject({
|
|
dimensionsMatch: true,
|
|
spatialTolerancePx: 4,
|
|
meanAbsoluteError: 0,
|
|
changedPixelRatio: 0,
|
|
inkIou: 1,
|
|
foregroundInkIou: 1,
|
|
edgeIou: 1,
|
|
backgroundColorDelta: 0,
|
|
foregroundColorDelta: 0,
|
|
});
|
|
expect(result.artifacts.overlayPng.subarray(0, 8)).toEqual(
|
|
new Uint8Array([137, 80, 78, 71, 13, 10, 26, 10]),
|
|
);
|
|
});
|
|
|
|
it("分别量化块背景色与背景相对的前景形状", async () => {
|
|
const coloredRaster = (background: string, foreground: string) => {
|
|
const canvas = createCanvas(80, 40);
|
|
const context = canvas.getContext("2d");
|
|
context.fillStyle = background;
|
|
context.fillRect(0, 0, 80, 40);
|
|
context.fillStyle = foreground;
|
|
context.fillRect(20, 10, 40, 20);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: 80,
|
|
heightPx: 40,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
} satisfies PdfPageRaster;
|
|
};
|
|
const sameShape = await comparePageRasters(
|
|
coloredRaster("#f2f2f2", "#202020"),
|
|
coloredRaster("#ffffff", "#202020"),
|
|
);
|
|
|
|
expect(sameShape.metrics.inkIou).toBe(1);
|
|
expect(sameShape.metrics.backgroundColorDelta).toBeGreaterThan(10);
|
|
expect(sameShape.metrics.foregroundColorDelta).toBeLessThan(1);
|
|
});
|
|
|
|
it("双背景占比翻转时仍独立量化核心字形拓扑", async () => {
|
|
const inlineCodeRaster = (fullHeightShading: boolean) => {
|
|
const canvas = createCanvas(216, 25);
|
|
const context = canvas.getContext("2d");
|
|
context.fillStyle = "#ffffff";
|
|
context.fillRect(0, 0, 216, 25);
|
|
context.fillStyle = "#f3f3f3";
|
|
context.fillRect(28, fullHeightShading ? 0 : 5, 120, fullHeightShading ? 25 : 16);
|
|
context.fillStyle = "#333333";
|
|
context.fillRect(34, 10, 80, 4);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: 216,
|
|
heightPx: 25,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
} satisfies PdfPageRaster;
|
|
};
|
|
const result = await comparePageRasters(
|
|
inlineCodeRaster(false),
|
|
inlineCodeRaster(true),
|
|
);
|
|
|
|
expect(result.metrics.backgroundColorDelta).toBeGreaterThan(10);
|
|
expect(result.metrics.foregroundInkIou).toBe(1);
|
|
});
|
|
|
|
it("渐变背景不会把深色文字误判为背景", async () => {
|
|
const gradientRaster = (gradient: boolean) => {
|
|
const canvas = createCanvas(160, 40);
|
|
const context = canvas.getContext("2d");
|
|
if (gradient) {
|
|
const fill = context.createLinearGradient(0, 0, 160, 0);
|
|
fill.addColorStop(0, "#edf5fa");
|
|
fill.addColorStop(1, "#ffffff");
|
|
context.fillStyle = fill;
|
|
} else {
|
|
context.fillStyle = "#f6fafc";
|
|
}
|
|
context.fillRect(0, 0, 160, 40);
|
|
context.fillStyle = "#0b3557";
|
|
context.fillRect(4, 4, 148, 32);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: 160,
|
|
heightPx: 40,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
} satisfies PdfPageRaster;
|
|
};
|
|
|
|
const result = await comparePageRasters(
|
|
gradientRaster(true),
|
|
gradientRaster(false),
|
|
);
|
|
expect(result.metrics.foregroundColorDelta).toBeLessThan(1);
|
|
expect(result.metrics.backgroundColorDelta).toBeLessThan(8);
|
|
expect(result.metrics.inkIou).toBeGreaterThan(0.95);
|
|
});
|
|
|
|
it("裁剪跨过深色盒边界时不会把外部白色误判为盒背景", async () => {
|
|
const boxedRaster = (exposeOutside: boolean) => {
|
|
const canvas = createCanvas(80, 40);
|
|
const context = canvas.getContext("2d");
|
|
context.fillStyle = "#ffffff";
|
|
context.fillRect(0, 0, 80, 40);
|
|
context.fillStyle = "#464646";
|
|
context.fillRect(0, 0, exposeOutside ? 68 : 80, exposeOutside ? 32 : 40);
|
|
context.fillStyle = "#ffffff";
|
|
context.fillRect(18, 10, 32, 16);
|
|
const png = Uint8Array.from(canvas.toBuffer("image/png"));
|
|
return {
|
|
widthPx: 80,
|
|
heightPx: 40,
|
|
dpi: 144,
|
|
sha256: createHash("sha256").update(png).digest("hex"),
|
|
png,
|
|
} satisfies PdfPageRaster;
|
|
};
|
|
|
|
const result = await comparePageRasters(
|
|
boxedRaster(true),
|
|
boxedRaster(false),
|
|
);
|
|
expect(result.metrics.backgroundColorDelta).toBeLessThan(1);
|
|
expect(result.metrics.foregroundColorDelta).toBeLessThan(1);
|
|
});
|
|
|
|
it("量化位移并生成稳定叠加图与热力图", async () => {
|
|
const result = await comparePageRasters(raster(10), raster(20), {
|
|
spatialTolerancePx: 0,
|
|
});
|
|
expect(result.metrics.meanAbsoluteError).toBeGreaterThan(10);
|
|
expect(result.metrics.changedPixelRatio).toBeCloseTo(0.1, 2);
|
|
expect(result.metrics.inkIou).toBeCloseTo(1 / 3, 2);
|
|
expect(result.metrics.edgeIou).toBeLessThan(0.4);
|
|
expect(result.artifacts.overlaySha256).toHaveLength(64);
|
|
expect(result.artifacts.heatmapSha256).toHaveLength(64);
|
|
});
|
|
|
|
it("只容忍三个像素以内的跨引擎栅格偏移", async () => {
|
|
const near = await comparePageRasters(raster(10), raster(13));
|
|
const far = await comparePageRasters(raster(10), raster(17));
|
|
|
|
expect(near.metrics.inkIou).toBe(1);
|
|
expect(near.metrics.edgeIou).toBe(1);
|
|
expect(far.metrics.inkIou).toBeLessThan(0.75);
|
|
expect(far.metrics.edgeIou).toBeLessThan(0.6);
|
|
});
|
|
|
|
it("空间容差不改变原始像素热力图", async () => {
|
|
const baseline = raster(10);
|
|
const candidate = raster(12);
|
|
const tolerant = await comparePageRasters(baseline, candidate);
|
|
const exact = await comparePageRasters(baseline, candidate, {
|
|
spatialTolerancePx: 0,
|
|
});
|
|
|
|
expect(tolerant.metrics.inkIou).toBeGreaterThan(exact.metrics.inkIou);
|
|
expect(tolerant.artifacts.heatmapSha256).toBe(
|
|
exact.artifacts.heatmapSha256,
|
|
);
|
|
});
|
|
|
|
it("可按物理页面基线规范化一像素的栅格舍入差", async () => {
|
|
const result = await comparePageRasters(
|
|
differentlySizedRaster(80, 100),
|
|
differentlySizedRaster(81, 101),
|
|
{
|
|
targetWidthPx: 80,
|
|
targetHeightPx: 100,
|
|
geometryNormalized: true,
|
|
},
|
|
);
|
|
expect(result.metrics).toMatchObject({
|
|
baselineWidthPx: 80,
|
|
candidateWidthPx: 81,
|
|
comparedWidthPx: 80,
|
|
dimensionsMatch: false,
|
|
geometryNormalized: true,
|
|
});
|
|
expect(result.metrics.meanAbsoluteError).toBeLessThan(2);
|
|
});
|
|
});
|