forked from bai/curriculum-project-hub
hongjr03
33de8901e7
Two fixes discovered by real end-to-end smoke test against Aliyun docmind:
1. fileUrlObject must be a ReadStream, not a Buffer. The SDK serializes
Buffers as JSON {type:'Buffer',data:[...]} which the API can't read;
a Stream is uploaded as multipart form data. Switched readFile → createReadStream.
2. QueryDocParserStatus returns data.status (not top-level completed/status).
The markdown output URL is in data.outputFormatResult[].outputFileUrl,
not in a separate GetDocParserResult call. Rewrote polling to check
data.status === 'success', then download markdown from the OSS URL.
Also added image download: markdown contains  references;
the client now downloads those images and rewrites paths to local filenames.
Smoke test verified: prime_sieve.pdf → 15s → markdown with image refs downloaded.
AliyunDocmindClient is now production-ready given an AccessKey.
90 lines
2.9 KiB
TypeScript
90 lines
2.9 KiB
TypeScript
/**
|
|
* Smoke test: real Aliyun docmind API call using createReadStream.
|
|
* Run: node --experimental-strip-types scripts/smoke-docmind.ts <pdf-path>
|
|
*/
|
|
import DocmindClient from "@alicloud/docmind-api20220711";
|
|
import { RuntimeOptions } from "@alicloud/tea-util";
|
|
import { createReadStream } from "node:fs";
|
|
import { basename } from "node:path";
|
|
|
|
const accessKeyId = process.env["ALIBABA_CLOUD_ACCESS_KEY_ID"];
|
|
const accessKeySecret = process.env["ALIBABA_CLOUD_ACCESS_KEY_SECRET"];
|
|
if (accessKeyId === undefined || accessKeySecret === undefined) {
|
|
console.error("Set ALIBABA_CLOUD_ACCESS_KEY_ID and ALIBABA_CLOUD_ACCESS_KEY_SECRET env vars.");
|
|
process.exit(1);
|
|
}
|
|
|
|
const pdfPath = process.argv[2] ?? "../examples/trial/prime_sieve.pdf";
|
|
console.log(`Parsing: ${pdfPath}`);
|
|
|
|
const client = new DocmindClient.default({
|
|
endpoint: "docmind-api.cn-hangzhou.aliyuncs.com",
|
|
accessKeyId,
|
|
accessKeySecret,
|
|
type: "access_key",
|
|
regionId: "cn-hangzhou",
|
|
} as never);
|
|
|
|
const fileStream = createReadStream(pdfPath);
|
|
const runtime = new RuntimeOptions({});
|
|
|
|
console.log("Submitting job...");
|
|
const submitResp = await client.submitDocParserJobAdvance(
|
|
new DocmindClient.SubmitDocParserJobAdvanceRequest({
|
|
fileUrlObject: fileStream,
|
|
fileName: basename(pdfPath),
|
|
outputFormat: ["markdown"],
|
|
formulaEnhancement: true,
|
|
}),
|
|
runtime,
|
|
);
|
|
const jobId = submitResp.body?.data?.id;
|
|
console.log("Job ID:", jobId);
|
|
|
|
if (jobId === undefined) {
|
|
console.error("No job id:", JSON.stringify(submitResp.body));
|
|
process.exit(1);
|
|
}
|
|
|
|
console.log("Polling...");
|
|
const deadline = Date.now() + 5 * 60_000;
|
|
let status = "";
|
|
let markdownUrl = "";
|
|
let pageCount = 0;
|
|
while (Date.now() < deadline) {
|
|
await new Promise((r) => setTimeout(r, 10_000));
|
|
const resp = await client.queryDocParserStatus(
|
|
new DocmindClient.QueryDocParserStatusRequest({ id: jobId }),
|
|
);
|
|
const data = (resp.body as { data?: { status?: string; pageCountEstimate?: number; outputFormatResult?: Array<{ outputFileUrl?: string; outputType?: string }> } }).data;
|
|
status = data?.status ?? "";
|
|
console.log(` status: ${status}`);
|
|
if (status === "success") {
|
|
const md = data?.outputFormatResult?.find((r) => r.outputType === "markdown");
|
|
markdownUrl = md?.outputFileUrl ?? "";
|
|
pageCount = data?.pageCountEstimate ?? 0;
|
|
break;
|
|
}
|
|
if (status === "fail") {
|
|
console.error("Job failed!");
|
|
process.exit(1);
|
|
}
|
|
}
|
|
|
|
if (status !== "success" || markdownUrl === "") {
|
|
console.error("Failed or timed out:", status);
|
|
process.exit(1);
|
|
}
|
|
|
|
console.log("Downloading markdown from OSS...");
|
|
const mdResp = await fetch(markdownUrl);
|
|
const markdown = await mdResp.text();
|
|
|
|
console.log("--- Result ---");
|
|
console.log("Pages:", pageCount);
|
|
console.log("Cost (USD, est):", ((pageCount > 0 ? pageCount : 1) * 0.0056).toFixed(4));
|
|
console.log("Job ID:", jobId);
|
|
console.log("Markdown length:", markdown.length, "chars");
|
|
console.log("--- Markdown (first 1000 chars) ---");
|
|
console.log(markdown.slice(0, 1000));
|