新增样例文章加载器

This commit is contained in:
czj
2026-07-01 14:58:13 +08:00
parent 34e6da23b0
commit 1781088640
3 changed files with 319 additions and 0 deletions
+117
View File
@@ -0,0 +1,117 @@
import { existsSync, readdirSync, readFileSync } from "node:fs";
import { basename, join } from "node:path";
import {
type ArticleSample,
type LoadedArticleSamples,
supportedPlatforms,
type SamplePlatform,
} from "./types";
interface RawSample {
name?: unknown;
input?: {
title?: unknown;
body?: unknown;
image_lines?: unknown;
platform?: unknown;
user_instructions?: unknown;
};
expectedHardFailures?: unknown;
expectedWarnings?: unknown;
}
export function loadArticleSamples(samplesDir: string): LoadedArticleSamples {
if (!existsSync(samplesDir)) {
return { valid: [], invalid: [] };
}
const files = readdirSync(samplesDir)
.filter((fileName) => fileName.endsWith(".json"))
.sort((left, right) => left.localeCompare(right));
const valid: ArticleSample[] = [];
const invalid: LoadedArticleSamples["invalid"] = [];
for (const fileName of files) {
const filePath = join(samplesDir, fileName);
try {
const raw = JSON.parse(readFileSync(filePath, "utf8")) as RawSample;
const sample = normalizeSample(raw, filePath, fileName);
valid.push(sample);
} catch (error) {
invalid.push({
filePath,
fileName,
reason:
error instanceof Error ? error.message : "sample could not be parsed",
});
}
}
return { valid, invalid };
}
function normalizeSample(
raw: RawSample,
filePath: string,
fileName: string,
): ArticleSample {
if (!raw || typeof raw !== "object") {
throw new Error("sample must be a JSON object");
}
if (!raw.input || typeof raw.input !== "object") {
throw new Error("input must be an object");
}
if (typeof raw.input.body !== "string" || raw.input.body.trim().length === 0) {
throw new Error("input.body must be a non-empty string");
}
if (!isSupportedPlatform(raw.input.platform)) {
throw new Error(
`input.platform must be one of ${supportedPlatforms.join(", ")}`,
);
}
return {
filePath,
fileName,
slug: slugFromFileName(fileName),
name:
typeof raw.name === "string" && raw.name.trim().length > 0
? raw.name.trim()
: basename(fileName, ".json"),
input: {
title: stringOrEmpty(raw.input.title),
body: raw.input.body,
image_lines: stringOrEmpty(raw.input.image_lines),
platform: raw.input.platform,
user_instructions: stringOrEmpty(raw.input.user_instructions),
},
expectedHardFailures: stringArrayOrEmpty(raw.expectedHardFailures),
expectedWarnings: stringArrayOrEmpty(raw.expectedWarnings),
};
}
function isSupportedPlatform(value: unknown): value is SamplePlatform {
return (
typeof value === "string" &&
supportedPlatforms.includes(value as SamplePlatform)
);
}
function stringOrEmpty(value: unknown) {
return typeof value === "string" ? value : "";
}
function stringArrayOrEmpty(value: unknown) {
return Array.isArray(value)
? value.filter((item): item is string => typeof item === "string")
: [];
}
function slugFromFileName(fileName: string) {
return basename(fileName, ".json")
.toLowerCase()
.replace(/[^a-z0-9-]+/g, "-")
.replace(/^-+|-+$/g, "");
}
+97
View File
@@ -0,0 +1,97 @@
export const supportedPlatforms = [
"official_site",
"media_article",
"comparison_review",
"recommendation_list",
] as const;
export type SamplePlatform = (typeof supportedPlatforms)[number];
export interface ArticleSampleInput {
title: string;
body: string;
image_lines: string;
platform: SamplePlatform;
user_instructions: string;
}
export interface ArticleSample {
filePath: string;
fileName: string;
slug: string;
name: string;
input: ArticleSampleInput;
expectedHardFailures: string[];
expectedWarnings: string[];
}
export interface InvalidArticleSample {
filePath: string;
fileName: string;
reason: string;
}
export interface LoadedArticleSamples {
valid: ArticleSample[];
invalid: InvalidArticleSample[];
}
export type SampleStatus = "passed" | "failed" | "skipped";
export type FailureCategory =
| "preflight_failed"
| "sample_invalid"
| "page_flow_failed"
| "stream_timeout"
| "stream_failed"
| "llm_failed"
| "export_failed"
| "console_error"
| "unknown_failed";
export interface ExportValidationResult {
fileName: "optimized.md" | "optimized.docx" | "qa_report.json";
status: "passed" | "failed";
statusCode?: number;
error?: string;
}
export interface SampleResult {
file: string;
name: string;
slug: string;
status: SampleStatus;
duration_ms: number;
job_id?: string;
qa_status?: "pass" | "warn" | "fail";
qa_fail_rules: string[];
qa_warn_rules: string[];
expected_hard_failures: string[];
expected_warnings: string[];
exports: Record<string, "passed" | "failed">;
llm_tasks: string[];
failure_category?: FailureCategory;
failure_message?: string;
artifacts: {
final_screenshot?: string;
failure_screenshot?: string;
trace?: string;
};
}
export interface RunSummary {
started_at: string;
finished_at: string;
mode: "live";
provider: string;
model: string;
base_url: string;
report_dir: string;
totals: {
passed: number;
failed: number;
skipped: number;
};
samples: SampleResult[];
invalid_samples: InvalidArticleSample[];
}
+105
View File
@@ -0,0 +1,105 @@
import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { afterEach, beforeEach, describe, expect, it } from "vitest";
import { loadArticleSamples } from "../e2e/sample-flow/sample-loader";
describe("loadArticleSamples", () => {
let tempDir: string;
beforeEach(() => {
tempDir = mkdtempSync(join(tmpdir(), "geo-samples-"));
});
afterEach(() => {
rmSync(tempDir, { recursive: true, force: true });
});
it("loads valid samples in filename order and normalizes optional fields", () => {
writeFileSync(
join(tempDir, "b-sample.json"),
JSON.stringify({
name: "B sample",
input: {
body: "第二篇文章正文",
platform: "media_article",
},
}),
);
writeFileSync(
join(tempDir, "a-sample.json"),
JSON.stringify({
name: "A sample",
input: {
title: "标题",
body: "第一篇文章正文",
image_lines: "图一",
platform: "official_site",
user_instructions: "保持事实准确",
},
expectedHardFailures: ["body_quality"],
expectedWarnings: ["context_sensitive_terms"],
}),
);
const result = loadArticleSamples(tempDir);
expect(result.valid.map((sample) => sample.fileName)).toEqual([
"a-sample.json",
"b-sample.json",
]);
expect(result.invalid).toEqual([]);
expect(result.valid[1]).toEqual(
expect.objectContaining({
name: "B sample",
input: expect.objectContaining({
title: "",
image_lines: "",
user_instructions: "",
}),
expectedHardFailures: [],
expectedWarnings: [],
}),
);
});
it("returns invalid entries for malformed samples without throwing", () => {
writeFileSync(
join(tempDir, "empty-body.json"),
JSON.stringify({
name: "Empty body",
input: {
body: " ",
platform: "official_site",
},
}),
);
writeFileSync(
join(tempDir, "bad-platform.json"),
JSON.stringify({
name: "Bad platform",
input: {
body: "正文",
platform: "unknown",
},
}),
);
const result = loadArticleSamples(tempDir);
expect(result.valid).toEqual([]);
expect(result.invalid).toEqual([
expect.objectContaining({
fileName: "bad-platform.json",
reason:
"input.platform must be one of official_site, media_article, comparison_review, recommendation_list",
}),
expect.objectContaining({
fileName: "empty-body.json",
reason: "input.body must be a non-empty string",
}),
]);
});
});