apify-schema-tools 2.0.1

package/samples/deep-merged-schemas/src-schemas/input.json

@@ -0,0 +1,73 @@
+{
+	"title": "Input schema for Web Scraper",
+	"description": "startUrls and searchTerm are required.",
+	"type": "object",
+	"schemaVersion": 1,
+	"properties": {
+		"startUrls": {
+			"position": 10,
+			"type": "array",
+			"title": "Start URLs",
+			"description": "List of URLs to scrape",
+			"default": [],
+			"editor": "requestListSources",
+			"items": {
+				"type": "object",
+				"properties": {
+					"url": { "type": "string" }
+				}
+			}
+		},
+		"searchTerm": {
+			"position": 20,
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"minLength": 1,
+			"maxLength": 100
+		},
+		"categories": {
+			"position": 30,
+			"type": "array",
+			"title": "Categories",
+			"description": "List of categories to filter results",
+			"default": [],
+			"items": {
+				"type": "object",
+				"properties": {
+					"name": { "type": "string", "title": "Category name" },
+					"id": { "type": "string", "title": "Category ID" }
+				}
+			}
+		},
+		"maxPages": {
+			"position": 30,
+			"sectionCaption": "Scraping options",
+			"sectionDescription": "Configure how many pages to scrape and other options.",
+			"type": "integer",
+			"title": "Maximum pages",
+			"description": "Maximum number of pages to scrape",
+			"default": 10,
+			"minimum": 1,
+			"maximum": 1000
+		},
+		"proxy": {
+			"position": 40,
+			"type": "object",
+			"title": "Proxy configuration",
+			"description": "Proxy settings",
+			"default": { "useApifyProxy": true },
+			"properties": {
+				"useApifyProxy": { "type": "boolean", "default": true }
+			}
+		},
+		"debugMode": {
+			"position": 60,
+			"type": "boolean",
+			"title": "Debug mode",
+			"description": "Enable debug logging",
+			"default": false
+		}
+	},
+	"required": ["startUrls", "searchTerm"]
+}

package/samples/merged-schemas/.actor/actor.json

@@ -0,0 +1,15 @@
+{
+	"actorSpecification": 1,
+	"name": "web-scraper-merged",
+	"title": "Web Scraper with merged schemas",
+	"description": "A web scraper with merged schemas.",
+	"version": "0.0",
+	"meta": {
+		"templateId": "ts-crawlee-playwright-chrome"
+	},
+	"input": "./input_schema.json",
+	"storages": {
+		"dataset": "./dataset_schema.json"
+	},
+	"dockerfile": "./Dockerfile"
+}

package/samples/merged-schemas/.actor/dataset_schema.json

@@ -0,0 +1,37 @@
+{
+	"actorSpecification": 1,
+	"fields": {
+		"$schema": "http://json-schema.org/draft-07/schema#",
+		"title": "Dataset schema for Web Scraper",
+		"type": "object",
+		"properties": {
+			"title": {
+				"type": "string",
+				"title": "Title",
+				"description": "Page title"
+			},
+			"url": {
+				"type": "string",
+				"title": "URL",
+				"description": "Page URL"
+			},
+			"text": {
+				"type": "string",
+				"title": "Text content",
+				"description": "Extracted text"
+			},
+			"timestamp": {
+				"type": "string",
+				"title": "Timestamp",
+				"description": "When the data was scraped"
+			},
+			"type": {
+				"type": "string",
+				"title": "Type",
+				"description": "Item type"
+			}
+		},
+		"required": ["title", "url", "type"]
+	},
+	"views": {}
+}

package/samples/merged-schemas/.actor/input_schema.json

@@ -0,0 +1,58 @@
+{
+	"title": "Input schema for Web Scraper merged",
+	"description": "startUrls and searchTerm are required. searchTerm must be one of the predefined values.",
+	"type": "object",
+	"schemaVersion": 1,
+	"properties": {
+		"startUrls": {
+			"type": "array",
+			"title": "Start URLs",
+			"description": "List of URLs to scrape",
+			"default": [],
+			"editor": "requestListSources"
+		},
+		"searchTerm": {
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"enum": ["example", "test", "sample"],
+			"enumTitles": ["Example", "Test", "Sample"]
+		},
+		"categories": {
+			"type": "array"
+		},
+		"maxPages": {
+			"type": "integer",
+			"title": "Maximum pages",
+			"description": "Maximum number of pages to scrape",
+			"default": 10,
+			"sectionCaption": "Scraping options",
+			"sectionDescription": "Configure how many pages to scrape and other options.",
+			"maximum": 1000,
+			"minimum": 1
+		},
+		"proxy": {
+			"type": "object",
+			"title": "Proxy configuration",
+			"description": "Proxy settings",
+			"default": {
+				"useApifyProxy": true
+			}
+		},
+		"maxRetries": {
+			"type": "integer",
+			"title": "Maximum retries",
+			"description": "Maximum number of retries",
+			"default": 3,
+			"maximum": 20,
+			"minimum": 1
+		},
+		"debugMode": {
+			"type": "boolean",
+			"title": "Debug mode",
+			"description": "Enable debug logging",
+			"default": false
+		}
+	},
+	"required": ["startUrls", "searchTerm"]
+}

package/samples/merged-schemas/add-schemas/dataset-item.json

@@ -0,0 +1,10 @@
+{
+	"properties": {
+		"type": {
+			"type": "string",
+			"title": "Type",
+			"description": "Item type"
+		}
+	},
+	"required": ["type"]
+}

package/samples/merged-schemas/add-schemas/input.json

@@ -0,0 +1,33 @@
+{
+	"title": "Input schema for Web Scraper merged",
+	"description": "startUrls and searchTerm are required. searchTerm must be one of the predefined values.",
+	"properties": {
+		"searchTerm": {
+			"position": 20,
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"enum": ["example", "test", "sample"],
+			"enumTitles": ["Example", "Test", "Sample"]
+		},
+		"categories": {
+			"position": 30,
+			"type": "array",
+			"items": {
+				"type": "object",
+				"properties": {
+					"url": { "type": "string", "title": "Category URL" }
+				}
+			}
+		},
+		"maxRetries": {
+			"position": 45,
+			"type": "integer",
+			"title": "Maximum retries",
+			"description": "Maximum number of retries",
+			"default": 3,
+			"minimum": 1,
+			"maximum": 20
+		}
+	}
+}

package/samples/merged-schemas/src/generated/dataset.ts

@@ -0,0 +1,28 @@
+/**
+ * This file was automatically generated by apify-schema-tools.
+ * DO NOT MODIFY IT BY HAND. Instead, modify the source JSONSchema file,
+ * and run apify-schema-tools' "sync" command to regenerate this file.
+ */
+
+export interface DatasetItem {
+	/**
+	 * Page title
+	 */
+	title: string;
+	/**
+	 * Page URL
+	 */
+	url: string;
+	/**
+	 * Extracted text
+	 */
+	text?: string;
+	/**
+	 * When the data was scraped
+	 */
+	timestamp?: string;
+	/**
+	 * Item type
+	 */
+	type: string;
+}

package/samples/merged-schemas/src/generated/input-utils.ts

@@ -0,0 +1,57 @@
+/**
+ * This file was automatically generated by apify-schema-tools.
+ * DO NOT MODIFY IT BY HAND. Instead, modify the source JSONSchema file,
+ * and run apify-schema-tools' "sync" command to regenerate this file.
+ */
+
+import { Actor } from "apify";
+import type { Input } from "./input.js";
+
+export const DEFAULT_INPUT_VALUES = {
+	startUrls: [],
+	maxPages: 10,
+	proxy: {
+		useApifyProxy: true,
+	},
+	maxRetries: 3,
+	debugMode: false,
+};
+
+export const REQUIRED_INPUT_FIELDS_WITHOUT_DEFAULT = ["searchTerm"];
+
+export type InputWithDefaults = Input & {
+	/**
+	 * Maximum number of pages to scrape
+	 */
+	maxPages: number;
+	/**
+	 * Proxy settings
+	 */
+	proxy: {
+		useApifyProxy?: boolean;
+	};
+	/**
+	 * Maximum number of retries
+	 */
+	maxRetries: number;
+	/**
+	 * Enable debug logging
+	 */
+	debugMode: boolean;
+};
+
+export function getInputWithDefaultValues(input?: Input | null): InputWithDefaults {
+	if (Actor.isAtHome()) {
+		// The platform is supposed to fill in the default values
+		return input as InputWithDefaults;
+	}
+	if (!input) {
+		throw new Error(
+			`Input is required, because the following fields are required: ${REQUIRED_INPUT_FIELDS_WITHOUT_DEFAULT.join(", ")}`,
+		);
+	}
+	return {
+		...DEFAULT_INPUT_VALUES,
+		...(input ?? ({} as Input)),
+	};
+}

package/samples/merged-schemas/src/generated/input.ts

@@ -0,0 +1,42 @@
+/**
+ * This file was automatically generated by apify-schema-tools.
+ * DO NOT MODIFY IT BY HAND. Instead, modify the source JSONSchema file,
+ * and run apify-schema-tools' "sync" command to regenerate this file.
+ */
+
+/**
+ * startUrls and searchTerm are required. searchTerm must be one of the predefined values.
+ */
+export interface Input {
+	/**
+	 * List of URLs to scrape
+	 */
+	startUrls: {
+		url?: string;
+	}[];
+	/**
+	 * Term to search for
+	 */
+	searchTerm: "example" | "test" | "sample";
+	categories?: {
+		url?: string;
+	}[];
+	/**
+	 * Maximum number of pages to scrape
+	 */
+	maxPages?: number;
+	/**
+	 * Proxy settings
+	 */
+	proxy?: {
+		useApifyProxy?: boolean;
+	};
+	/**
+	 * Maximum number of retries
+	 */
+	maxRetries?: number;
+	/**
+	 * Enable debug logging
+	 */
+	debugMode?: boolean;
+}

package/samples/merged-schemas/src-schemas/dataset-item.json

@@ -0,0 +1,28 @@
+{
+	"$schema": "http://json-schema.org/draft-07/schema#",
+	"title": "Dataset schema for Web Scraper",
+	"type": "object",
+	"properties": {
+		"title": {
+			"type": "string",
+			"title": "Title",
+			"description": "Page title"
+		},
+		"url": {
+			"type": "string",
+			"title": "URL",
+			"description": "Page URL"
+		},
+		"text": {
+			"type": "string",
+			"title": "Text content",
+			"description": "Extracted text"
+		},
+		"timestamp": {
+			"type": "string",
+			"title": "Timestamp",
+			"description": "When the data was scraped"
+		}
+	},
+	"required": ["title", "url"]
+}

package/samples/merged-schemas/src-schemas/input.json

@@ -0,0 +1,73 @@
+{
+	"title": "Input schema for Web Scraper",
+	"description": "startUrls and searchTerm are required.",
+	"type": "object",
+	"schemaVersion": 1,
+	"properties": {
+		"startUrls": {
+			"position": 10,
+			"type": "array",
+			"title": "Start URLs",
+			"description": "List of URLs to scrape",
+			"default": [],
+			"editor": "requestListSources",
+			"items": {
+				"type": "object",
+				"properties": {
+					"url": { "type": "string" }
+				}
+			}
+		},
+		"searchTerm": {
+			"position": 20,
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"minLength": 1,
+			"maxLength": 100
+		},
+		"categories": {
+			"position": 30,
+			"type": "array",
+			"title": "Categories",
+			"description": "List of categories to filter results",
+			"default": [],
+			"items": {
+				"type": "object",
+				"properties": {
+					"name": { "type": "string", "title": "Category name" },
+					"id": { "type": "string", "title": "Category ID" }
+				}
+			}
+		},
+		"maxPages": {
+			"position": 30,
+			"sectionCaption": "Scraping options",
+			"sectionDescription": "Configure how many pages to scrape and other options.",
+			"type": "integer",
+			"title": "Maximum pages",
+			"description": "Maximum number of pages to scrape",
+			"default": 10,
+			"minimum": 1,
+			"maximum": 1000
+		},
+		"proxy": {
+			"position": 40,
+			"type": "object",
+			"title": "Proxy configuration",
+			"description": "Proxy settings",
+			"default": { "useApifyProxy": true },
+			"properties": {
+				"useApifyProxy": { "type": "boolean", "default": true }
+			}
+		},
+		"debugMode": {
+			"position": 60,
+			"type": "boolean",
+			"title": "Debug mode",
+			"description": "Enable debug logging",
+			"default": false
+		}
+	},
+	"required": ["startUrls", "searchTerm"]
+}

package/samples/package-json-config/.actor/actor.json

@@ -0,0 +1,15 @@
+{
+	"actorSpecification": 1,
+	"name": "web-scraper",
+	"title": "Web Scraper",
+	"description": "A web scraper.",
+	"version": "0.0",
+	"meta": {
+		"templateId": "ts-crawlee-playwright-chrome"
+	},
+	"input": "./input_schema.json",
+	"storages": {
+		"dataset": "./dataset_schema.json"
+	},
+	"dockerfile": "./Dockerfile"
+}

package/samples/package-json-config/.actor/dataset_schema.json

@@ -0,0 +1,32 @@
+{
+	"actorSpecification": 1,
+	"fields": {
+		"$schema": "http://json-schema.org/draft-07/schema#",
+		"title": "Dataset schema for Web Scraper",
+		"type": "object",
+		"properties": {
+			"title": {
+				"type": "string",
+				"title": "Title",
+				"description": "Page title"
+			},
+			"url": {
+				"type": "string",
+				"title": "URL",
+				"description": "Page URL"
+			},
+			"text": {
+				"type": "string",
+				"title": "Text content",
+				"description": "Extracted text"
+			},
+			"timestamp": {
+				"type": "string",
+				"title": "Timestamp",
+				"description": "When the data was scraped"
+			}
+		},
+		"required": ["title", "url"]
+	},
+	"views": {}
+}

package/samples/package-json-config/.actor/input_schema.json

@@ -0,0 +1,53 @@
+{
+	"title": "Input schema for Web Scraper",
+	"description": "startUrls and searchTerm are required.",
+	"type": "object",
+	"schemaVersion": 1,
+	"properties": {
+		"startUrls": {
+			"type": "array",
+			"title": "Start URLs",
+			"description": "List of URLs to scrape",
+			"default": [],
+			"editor": "requestListSources"
+		},
+		"searchTerm": {
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"minLength": 1,
+			"maxLength": 100
+		},
+		"categories": {
+			"type": "array",
+			"title": "Categories",
+			"description": "List of categories to filter results",
+			"default": []
+		},
+		"maxPages": {
+			"type": "integer",
+			"title": "Maximum pages",
+			"description": "Maximum number of pages to scrape",
+			"default": 10,
+			"sectionCaption": "Scraping options",
+			"sectionDescription": "Configure how many pages to scrape and other options.",
+			"maximum": 1000,
+			"minimum": 1
+		},
+		"proxy": {
+			"type": "object",
+			"title": "Proxy configuration",
+			"description": "Proxy settings",
+			"default": {
+				"useApifyProxy": true
+			}
+		},
+		"debugMode": {
+			"type": "boolean",
+			"title": "Debug mode",
+			"description": "Enable debug logging",
+			"default": false
+		}
+	},
+	"required": ["startUrls", "searchTerm"]
+}

package/samples/package-json-config/custom-src-schemas/dataset-item.json

@@ -0,0 +1,28 @@
+{
+	"$schema": "http://json-schema.org/draft-07/schema#",
+	"title": "Dataset schema for Web Scraper",
+	"type": "object",
+	"properties": {
+		"title": {
+			"type": "string",
+			"title": "Title",
+			"description": "Page title"
+		},
+		"url": {
+			"type": "string",
+			"title": "URL",
+			"description": "Page URL"
+		},
+		"text": {
+			"type": "string",
+			"title": "Text content",
+			"description": "Extracted text"
+		},
+		"timestamp": {
+			"type": "string",
+			"title": "Timestamp",
+			"description": "When the data was scraped"
+		}
+	},
+	"required": ["title", "url"]
+}

package/samples/package-json-config/custom-src-schemas/input.json

@@ -0,0 +1,73 @@
+{
+	"title": "Input schema for Web Scraper",
+	"description": "startUrls and searchTerm are required.",
+	"type": "object",
+	"schemaVersion": 1,
+	"properties": {
+		"startUrls": {
+			"position": 10,
+			"type": "array",
+			"title": "Start URLs",
+			"description": "List of URLs to scrape",
+			"default": [],
+			"editor": "requestListSources",
+			"items": {
+				"type": "object",
+				"properties": {
+					"url": { "type": "string" }
+				}
+			}
+		},
+		"searchTerm": {
+			"position": 20,
+			"type": "string",
+			"title": "Search term",
+			"description": "Term to search for",
+			"minLength": 1,
+			"maxLength": 100
+		},
+		"categories": {
+			"position": 30,
+			"type": "array",
+			"title": "Categories",
+			"description": "List of categories to filter results",
+			"default": [],
+			"items": {
+				"type": "object",
+				"properties": {
+					"name": { "type": "string", "title": "Category name" },
+					"id": { "type": "string", "title": "Category ID" }
+				}
+			}
+		},
+		"maxPages": {
+			"position": 30,
+			"sectionCaption": "Scraping options",
+			"sectionDescription": "Configure how many pages to scrape and other options.",
+			"type": "integer",
+			"title": "Maximum pages",
+			"description": "Maximum number of pages to scrape",
+			"default": 10,
+			"minimum": 1,
+			"maximum": 1000
+		},
+		"proxy": {
+			"position": 40,
+			"type": "object",
+			"title": "Proxy configuration",
+			"description": "Proxy settings",
+			"default": { "useApifyProxy": true },
+			"properties": {
+				"useApifyProxy": { "type": "boolean", "default": true }
+			}
+		},
+		"debugMode": {
+			"position": 60,
+			"type": "boolean",
+			"title": "Debug mode",
+			"description": "Enable debug logging",
+			"default": false
+		}
+	},
+	"required": ["startUrls", "searchTerm"]
+}

package/samples/package-json-config/package.json

@@ -0,0 +1,11 @@
+{
+	"name": "test-package",
+	"version": "1.0.0",
+	"apify-schema-tools": {
+		"input": ["input", "dataset"],
+		"output": ["json-schemas", "ts-types"],
+		"srcInput": "custom-src-schemas/input.json",
+		"srcDataset": "custom-src-schemas/dataset-item.json",
+		"outputTSDir": "src/custom-generated"
+	}
+}