NPM Packages (~1.9M packages)

- input.json.gz contains the raw NPM data dump from the replicate.npmjs.org database (downloaded on June 4th, 2022) in the following format:

{
    "total_rows": 1997865,
    "offset": 0,
    "rows": [
        {
            "id": "-",
            "key": "-",
            "value": {
                "rev": "5-92e28c1ea7f24d165faa202aabd92669"
            },
            "doc": {
                "_id": "-",
                "_rev": "5-92e28c1ea7f24d165faa202aabd92669",
                "name": "-",
                "dist-tags": {
                    "latest": "0.0.1"
                },
                "versions": {
                    "0.0.1": {
                        "name": "-",
                        "version": "0.0.1",
                        "license": "UNLICENSED",
                        "keywords": [],
                        "main": "dist/index.js",
                        "types": "dist/index.d.ts",
                        "scripts": {
                            "test": "echo \"Error: no test specified\" && exit 1",
                            "start": "node --require ts-node/register src",
                            "build": "tsc"
                        },
                        "devDependencies": {
                            "@types/node": "13.9.0",
                            "ts-node": "8.6.2",
                            "typescript": "3.8.3"
                        },
                        "description": "...",
                        "_id": "-@0.0.1",
                        "_nodeVersion": "13.3.0",
                        "_npmVersion": "6.14.4",
                        "dist": {...},
                        "maintainers": [
                            {
                                "name": "parzhitsky",
                                "email": "parzhitsky@gmail.com"
                            }
                        ],
                        "_npmUser": {
                            "name": "parzhitsky",
                            "email": "parzhitsky@gmail.com"
                        },
                        "directories": {},
                        "_npmOperationalInternal": {
                            "host": "s3://npm-registry-packages",
                            "tmp": "tmp/-_0.0.1_1585828132159_0.6185838126718755"
                        },
                        "_hasShrinkwrap": false
                    }
                },
                "time": {
                    "created": "2020-04-02T11:48:52.159Z",
                    "0.0.1": "2020-04-02T11:48:52.339Z",
                    "modified": "2022-04-04T10:06:01.120Z"
                },
                "maintainers": [
                    {
                        "email": "support@npmjs.com",
                        "name": "npm-support"
                    }
                ],
                "description": "...",
                "keywords": [],
                "license": "UNLICENSED",
                "readme": "...",
                "readmeFilename": "README.md"
            }
        },
      ...
    ]
}

- streamedout.json.gz contains a processed file that has the following format

{"pkgs": [
    {
        "name": "react",
        "versions": {
                "1.00": {
                "timestamp": "06-05-2022T10:00:01",
                "dependencies": {
                    "name": "^1.0.2"
                }
            }
        }
    },
...
]}