@clickup/pg-microsharding/dist/internal/getDump.js

Microshards support for PostgreSQL

"use strict";
var __importDefault = (this && this.__importDefault) || function (mod) {
    return (mod && mod.__esModule) ? mod : { "default": mod };
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.getDump = getDump;
const compact_1 = __importDefault(require("lodash/compact"));
const partition_1 = __importDefault(require("lodash/partition"));
const names_1 = require("./names");
const quote_1 = require("./quote");
const runShell_1 = require("./runShell");
/**
 * Runs pg_dump, does some basic parsing and returns the result.
 *
 * By default, the tool does not validate FKs on the destination, since it's
 * implied they were already valid on the source. So the FKs on the destination
 * are created with "NOT VALID" clause. This speeds up microshards moving
 * severely. The downside is that, if we later run pg_dump over the migrated
 * destination shard, it will emit "ALTER TABLE ... ADD CONSTRAINT ... NOT
 * VALID" as well (i.e. PG remembers that the FKs were not validated). This is
 * not the end of the world, just inaccurate.
 */
async function getDump({ fromDsn, schema, validateFKs, }) {
    const preData = parseDump(await (0, runShell_1.runShell)(`${(0, names_1.pgDump)(fromDsn)} -n ${(0, quote_1.shellQuote)(schema)} --section=pre-data`, null, `Reading pre-data DDL (except indexes) for ${schema} from ${fromDsn}`));
    const postDataAll = parseDump(await (0, runShell_1.runShell)(`${(0, names_1.pgDump)(fromDsn)} -n ${(0, quote_1.shellQuote)(schema)} --section=post-data`, null, `Reading post-data DDL (indexes, foreign keys) for ${schema} from ${fromDsn}`));
    // For logical replication to work, each table on the subscription part must
    // have an index that allows the logical worker to find the row it receives
    // from the publication end. PostgreSQL 16+ can use regular indexes for that,
    // but the earlier versions require the subscription end to have either a
    // REPLICA IDENTITY or a PRIMARY KEY. Thus, we extract such indexes from the
    // post-data section of the dump and create them before creating the
    // subscription.
    const [primaryKeys, postData] = (0, partition_1.default)(postDataAll.map((entry) => entry.replace(/^(ALTER TABLE ONLY [^\n]+\n +ADD CONSTRAINT [^\n]+ FOREIGN KEY [^\n]+ REFERENCES [^\n]+?)(?: NOT VALID)?(;)$/s, (_, sql, end) => sql + (validateFKs ? "" : " NOT VALID") + end)), (entry) => entry.match(/^ALTER TABLE .* ADD CONSTRAINT .* PRIMARY KEY \([^)]+\);$/s) ||
        entry.match(/^CREATE UNIQUE INDEX (.*?) ON .*\nALTER TABLE .*? REPLICA IDENTITY USING INDEX \1;$/s));
    return {
        preData: (0, quote_1.join)(preData, "\n"),
        primaryKeys,
        postData: (0, quote_1.join)(postData, "\n"),
    };
}
/**
 * The text generated by pg_dump consists of entries divided by 3 lines of
 * "--"-comments. We split the dump into that entries, and only then analyze it
 * in the further logic.
 */
function parseDump(dump) {
    const entries = (0, compact_1.default)(dump
        .split(/^--\n-- \w+[^\n]*\n--\n/m)
        .map((entry) => entry.trim())
        // Added in PG17+ and is not supported in earlier versions.
        .map((entry) => entry.replace(/^SET transaction_timeout = [^\n]+/m, "-- $&")));
    entries[0] = entries[0].replace(/\n\n+/gs, "\n");
    return entries;
}
//# sourceMappingURL=getDump.js.map