MultiforaDB/tests/spec/positional/record.js

// Record a positional-update corpus by asking a real mongod what the answer is.
//
// The pinned crud suite tests `$[<identifier>]` in four files and does not
// contain a single `$[]` or bare `$` case -- see PLAN amendment on M3 and
// `docs/M3_ARRAYFILTERS_DESIGN_REVIEW.md` §3. That gap is not academic: all
// three spellings shared one code path, and while it destroyed the array it
// walked, only the `$[<identifier>]` third of it was externally visible.
//
// Same discipline as `tests/spec/aggregate/`: *inputs* are authored in
// `sources/`, *expectations* are measured here. A corpus we write end to end
// is a corpus that can encode our own bugs as expectations and then agree with
// us forever -- and the review's own guesses about `$[]`, missing paths and
// upserts were all wrong before mongod was asked.
//
//   1. author `sources/<name>.json`: documents, and a list of operations
//   2. run this against a real mongod
//   3. it writes `<name>.json` in the unified format, expectations filled in
//   4. `node tests/spec/run.js --suite-dir tests/spec/positional` runs it
//
//   node tests/spec/positional/record.js --mongod-port 27099
//
// Options:
//   --mongod-port <n>  a running mongod to measure against (default 27099)
//   --only <name>      record just one source file
const fs = require('fs');
const path = require('path');
// The same pinned driver `run.js` uses, resolved the same way: there is one
// lockfile in this repo and it lives with the e2e suites.
const { MongoClient } = require(path.join(__dirname, '..', '..', 'e2e', 'node_modules', 'mongodb'));

const argv = process.argv.slice(2);
function opt(name, dflt) {
    const i = argv.indexOf('--' + name);
    if (i < 0) return dflt;
    const v = argv[i + 1];
    return v === undefined || v.startsWith('--') ? true : v;
}

const PORT = parseInt(opt('mongod-port', '27099'), 10);
const ONLY = opt('only', null);
const SRC_DIR = path.join(__dirname, 'sources');
const DB_NAME = 'positional-corpus';
const COLL = 'coll';

// Every construct here is 3.6 or older (`$` is ancient, `$[]` and
// `$[<id>]` are 3.6), so nothing in this corpus depends on a server newer
// than the 4.4 this one reports. A case that did should be left out rather
// than annotated -- recording it from mongod 8.x and judging it against a 4.4
// answer measures the version gap, not the engine.
const SCHEMA_VERSION = '1.4';

/// Which fields of a driver result are recorded, per operation.
///
/// The whole result object is not recorded: it carries `upsertedId: null` and
/// driver-side types that do not survive a JSON round trip, and the pinned
/// corpus asserts exactly these three for an update. `findOneAndUpdate`
/// returns the document itself.
const UPDATE_KEYS = ['matchedCount', 'modifiedCount', 'upsertedCount'];

async function main() {
    if (!fs.existsSync(SRC_DIR)) {
        console.error(`missing ${SRC_DIR}`);
        process.exit(2);
    }
    const client = new MongoClient(`mongodb://127.0.0.1:${PORT}`, { serverSelectionTimeoutMS: 3000 });
    try {
        await client.connect();
    } catch (e) {
        console.error(`no mongod on :${PORT} -- start one first:\n` +
            `  mongod --port ${PORT} --dbpath <dir>\n${e.message}`);
        process.exit(2);
    }
    const build = await client.db('admin').command({ buildInfo: 1 });
    console.log(`recording against mongod ${build.version} on :${PORT}`);

    const sources = fs.readdirSync(SRC_DIR).filter((f) => f.endsWith('.json'))
        .filter((f) => !ONLY || f === ONLY || f === ONLY + '.json')
        .sort();
    if (!sources.length) {
        console.error('no source files');
        process.exit(2);
    }

    for (const file of sources) {
        const src = JSON.parse(fs.readFileSync(path.join(SRC_DIR, file), 'utf8'));
        const name = path.basename(file, '.json');
        const out = await record(client, name, src);
        fs.writeFileSync(path.join(__dirname, `${name}.json`), JSON.stringify(out, null, 2) + '\n');
        const errs = out.tests.filter((t) => t.operations[t.operations.length - 1].expectError).length;
        console.log(`  ${name}: ${out.tests.length} cases, ${errs} of them errors`);
    }
    await client.close();
    console.log('RECORDED');
}

async function record(client, name, src) {
    const coll = client.db(DB_NAME).collection(COLL);
    const tests = [];

    for (const c of src.cases) {
        // A case may bring its own documents: the shapes that make a missing
        // path or a non-array path meaningful are not the shapes that make a
        // filtered update meaningful.
        const documents = c.documents === undefined ? src.documents : c.documents;
        await coll.drop().catch(() => {});
        if (documents.length) await coll.insertMany(structuredClone(documents));

        // A case that brings its own documents reseeds through *operations*
        // rather than `initialData`, because the unified format's
        // `initialData` is per file and the runner seeds it once per test.
        // Setup-as-operations is what the format offers for this, and it keeps
        // one file per operator instead of one file per document shape.
        const setup = [];
        if (c.documents !== undefined) {
            setup.push({ object: 'collection0', name: 'deleteMany', arguments: { filter: {} } });
            if (documents.length) {
                setup.push({
                    object: 'collection0',
                    name: 'insertMany',
                    arguments: { documents: structuredClone(documents) },
                });
            }
        }
        const op = {
            object: 'collection0',
            name: c.operation,
            arguments: structuredClone(c.arguments),
        };
        try {
            op.expectResult = await invoke(coll, c.operation, structuredClone(c.arguments));
        } catch (e) {
            // The code, not the message: message text is mongod's to change
            // between releases, and a corpus that pinned it would fail for the
            // wrong reason. Several of these messages embed a shell-syntax
            // rendering of the offending element, which no formatter here
            // produces.
            delete op.expectResult;
            op.expectError = { isError: true, errorCode: e.code };
        }

        // Recorded for *every* case, including the refusals, and that is the
        // point of the file. A refusal that left the document mangled would
        // look identical to a clean one in `expectError` alone -- and a
        // mangled document is exactly the bug this corpus exists to catch.
        const after = await coll.find({}, { sort: { _id: 1 } }).toArray();

        tests.push({
            description: c.description,
            operations: [...setup, op],
            outcome: [{ collectionName: COLL, databaseName: DB_NAME, documents: after }],
        });
    }
    await coll.drop().catch(() => {});

    return {
        description: name,
        schemaVersion: SCHEMA_VERSION,
        // Recorded, not authored. Regenerate with tests/spec/positional/record.js.
        createEntities: [
            { client: { id: 'client0' } },
            { database: { id: 'database0', client: 'client0', databaseName: DB_NAME } },
            { collection: { id: 'collection0', database: 'database0', collectionName: COLL } },
        ],
        // Reseeded by the runner before every test. Cases needing a different
        // shape override it with setup operations, above.
        initialData: [{ collectionName: COLL, databaseName: DB_NAME, documents: src.documents }],
        tests,
    };
}

async function invoke(coll, name, args) {
    const { filter, update, replacement, ...rest } = args;
    switch (name) {
        case 'updateOne':
            return pick(await coll.updateOne(filter, update, rest), UPDATE_KEYS);
        case 'updateMany':
            return pick(await coll.updateMany(filter, update, rest), UPDATE_KEYS);
        case 'replaceOne':
            return pick(await coll.replaceOne(filter, replacement, rest), UPDATE_KEYS);
        case 'findOneAndUpdate': {
            const r = await coll.findOneAndUpdate(filter, update, rest);
            // Driver 5+ returns the document itself; 4.x wrapped it in
            // `{value}`. run.js tolerates both the same way.
            return r && typeof r === 'object' && 'value' in r && 'ok' in r ? r.value : r;
        }
        default:
            throw new Error(`record.js does not know the operation '${name}'`);
    }
}

function pick(result, keys) {
    const o = {};
    for (const k of keys) if (result[k] !== undefined) o[k] = result[k];
    return o;
}

main().catch((e) => {
    console.error('RECORD_FAIL', e);
    process.exit(1);
});