Rename Dataset Fields

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "root": true,
    "env": {
        "browser": true,
        "es2020": true,
        "node": true
    },
    "extends": [
        "@apify/eslint-config-ts"
    ],
    "parserOptions": {
        "project": "./tsconfig.json",
        "ecmaVersion": 2020
    },
    "ignorePatterns": [
        "node_modules",
        "dist",
        "**/*.d.ts"
    ]
}

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage

# Added by Apify CLI
.venv

{
	"name": "rename-dataset-fields",
	"version": "0.0.1",
	"type": "module",
	"description": "This is a boilerplate of an Apify actor.",
	"engines": {
		"node": ">=18.0.0"
	},
	"dependencies": {
		"apify": "^3.1.10",
		"crawlee": "^3.5.4"
	},
	"devDependencies": {
		"@apify/eslint-config-ts": "^0.3.0",
		"@apify/tsconfig": "^0.1.0",
		"@typescript-eslint/eslint-plugin": "^6.7.2",
		"@typescript-eslint/parser": "^6.7.2",
		"eslint": "^8.50.0",
		"tsx": "^4.6.2",
		"typescript": "^5.3.3"
	},
	"scripts": {
		"start": "npm run start:dev",
		"start:prod": "node dist/main.js",
		"start:dev": "tsx src/main.ts",
		"build": "tsc",
		"lint": "eslint ./src --ext .ts",
		"lint:fix": "eslint ./src --ext .ts --fix",
		"test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
	},
	"author": "It's not you it's me",
	"license": "ISC"
}

{
    "extends": "@apify/tsconfig",
    "compilerOptions": {
        "module": "NodeNext",
        "moduleResolution": "NodeNext",
        "target": "ES2022",
        "outDir": "dist",
        "noUnusedLocals": false,
        "skipLibCheck": true,
        "lib": ["DOM"]
    },
    "include": [
        "./src/**/*"
    ]
}

# Specify the base Docker image. You can read more about
# the available images at https://crawlee.dev/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:20 AS builder

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
FROM apify/actor-node:20

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY package*.json ./

# Install NPM packages, skip optional and development dependencies to
# keep the image small. Avoid logging too much and print the dependency
# tree for debugging
RUN npm --quiet set progress=false \
    && npm install --omit=dev --omit=optional \
    && echo "Installed NPM packages:" \
    && (npm list --omit=dev --all || true) \
    && echo "Node.js version:" \
    && node --version \
    && echo "NPM version:" \
    && npm --version \
    && rm -r ~/.npm

# Copy built JS files from builder image
COPY --from=builder /usr/src/app/dist ./dist

# Next, copy the remaining files and directories with the source code.
# Since we do this after NPM install, quick build will be really fast
# for most source file changes.
COPY . ./


# Run the image.
CMD npm run start:prod --silent

{
	"actorSpecification": 1,
	"name": "rename-dataset-fields",
	"title": "Project Cheerio Crawler Typescript",
	"description": "Crawlee and Cheerio project in typescript.",
	"version": "0.0",
	"meta": {
		"templateId": "ts-crawlee-cheerio"
	},
	"input": "./input_schema.json",
	"dockerfile": "./Dockerfile"
}

{
    "title": "CheerioCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "datasetId": {
            "title": "Dataset ID",
            "type": "string",
            "description": "ID of the dataset you want to rename the columns in. Can also use run ID.",
            "editor": "textfield"
        },
        "renameMapping": {
            "title": "Rename fields mapping",
            "type": "array",
            "editor": "keyValue",
            "placeholderKey": "old_field_name",
            "placeholderValue": "new_field_name",
            "description": "Mapping of old field names to new field names."
        }
    }
}

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor, ActorRun } from 'apify';
3
4interface Input {
5    renameMapping: { key: string, value: string }[],
6    datasetId?: string,
7
8    // Maybe take datasetId from webhook
9    payload?: { resource: ActorRun },
10    resource?: ActorRun,
11}
12
13// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
14await Actor.init();
15
16// Structure of input is defined in input_schema.json
17const {
18    datasetId,
19    renameMapping = [],
20    payload,
21    resource,
22} = (await Actor.getInput<Input>())!;
23
24const realDatasetId = datasetId || payload?.resource?.defaultDatasetId || resource?.defaultDatasetId;
25
26const preDedupTransformFunction = (items: Record<string, unknown>[], { customInputData }: { customInputData: { renameMapping: Input['renameMapping'] } }) => {
27    return items.map((item) => {
28        const newFields: Record<string, unknown> = {};
29        customInputData.renameMapping.forEach(({ key: from, value: to }) => {
30            if (item[from] !== undefined) {
31                newFields[to] = item[from];
32                delete item[from];
33            }
34        });
35
36        // We want the renamed fields to be the first in that order
37        return {
38            ...newFields,
39            ...item,
40        };
41    });
42};
43
44const dedupActorInput = {
45    datasetIds: [realDatasetId],
46    preDedupTransformFunction,
47    customInputData: {
48        renameMapping,
49    },
50};
51
52if (Actor.isAtHome()) {
53    await Actor.metamorph('lukaskrivka/dedup-datasets', dedupActorInput);
54} else {
55    await Actor.call('lukaskrivka/dedup-datasets', dedupActorInput, { waitSecs: 0 });
56}
57
58// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
59await Actor.exit();