MultiforaDB/tests/spec/operators/record.js

// Record an update-operator corpus by asking a real mongod what the answer is.
//
// Eight operators PLAN §3 lists for M3 -- `$setOnInsert`, `$addToSet`, `$mul`,
// `$min`, `$max`, `$pop`, `$pullAll`, `$currentDate` -- plus `$push`'s
// `$slice`/`$position`/`$sort` modifiers. The pinned crud corpus contains
// almost nothing about any of them, and a probe against both servers found
// every one of the eight answering `bad update` here, and the three `$push`
// modifiers *silently ignored*: `{$each: [3, 4], $slice: -3}` appended without
// slicing and answered ok: 1. Same discipline as `tests/spec/positional/` and
// `tests/spec/aggregate/`: inputs are authored in `sources/`, expectations are
// measured here.
//
//   node tests/spec/operators/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.
const DRIVER = path.join(__dirname, '..', '..', 'e2e', 'node_modules', 'mongodb');
const { MongoClient } = require(DRIVER);
const { EJSON, ObjectId, Timestamp } = require(path.join(DRIVER, 'lib', 'bson.js'));

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 = 'operator-corpus';
const COLL = 'coll';

// Every construct here predates 4.0, so nothing depends on a server newer than
// the 4.4 this one reports.
const SCHEMA_VERSION = '1.4';

const UPDATE_KEYS = ['matchedCount', 'modifiedCount', 'upsertedCount'];

/// Values nobody can predict, replaced by an assertion about their type.
///
/// Two kinds, and both are the corpus staying honest rather than the corpus
/// looking away: a `$currentDate` field is whatever the clock said, and an
/// upsert that inserts gets a generated ObjectId. Everything else about the
/// document -- which fields exist, in what order, holding what -- is still
/// compared exactly, so a case that lost a field still fails.
///
/// The ObjectId rule is automatic because it is unambiguous: no source file
/// authors one. A date is not: `volatile` names those per case, so a corpus
/// that one day wants to pin a real stored date still can.
function maskGenerated(value) {
    if (value instanceof ObjectId) return { $$type: 'objectId' };
    if (Array.isArray(value)) return value.map(maskGenerated);
    if (value && typeof value === 'object' && value.constructor === Object) {
        const out = {};
        for (const [k, v] of Object.entries(value)) out[k] = maskGenerated(v);
        return out;
    }
    return value;
}

function maskVolatile(docs, paths) {
    for (const p of paths) {
        for (const doc of docs) {
            const segs = p.split('.');
            let cur = doc;
            for (const s of segs.slice(0, -1)) cur = cur === undefined ? undefined : cur[s];
            const last = segs[segs.length - 1];
            if (cur === undefined || !(last in cur)) {
                throw new Error(`volatile path '${p}' is not in the recorded document ` +
                    `${JSON.stringify(doc)} -- the case did not write what it said it would`);
            }
            const v = cur[last];
            if (v instanceof Date) cur[last] = { $$type: 'date' };
            else if (v instanceof Timestamp) cur[last] = { $$type: 'timestamp' };
            else throw new Error(`volatile path '${p}' holds ${v}, which is neither a date nor a timestamp`);
        }
    }
}

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);
        const text = EJSON.stringify(out, { relaxed: false, indent: 2 });
        fs.writeFileSync(path.join(__dirname, `${name}.json`), text + '\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) {
        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*:
        // the unified format's `initialData` is per file, and the runner seeds
        // it once per test.
        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 = maskGenerated(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 several of these embed a rendering of the
            // offending BSON that no formatter here produces.
            delete op.expectResult;
            op.expectError = { isError: true, errorCode: e.code };
        }

        // Recorded for every case including the refusals: a refusal that left
        // the document half-written would look identical to a clean one in
        // `expectError` alone.
        const after = await coll.find({}, { sort: { _id: 1 } }).toArray();
        if (c.volatile) maskVolatile(after, c.volatile);

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

    return {
        description: name,
        schemaVersion: SCHEMA_VERSION,
        // Recorded, not authored. Regenerate with tests/spec/operators/record.js.
        createEntities: [
            { client: { id: 'client0' } },
            { database: { id: 'database0', client: 'client0', databaseName: DB_NAME } },
            { collection: { id: 'collection0', database: 'database0', collectionName: COLL } },
        ],
        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);
});