crawlberg 0.0.1 → 1.0.0.pre.rc.2

data/lib/crawlberg/native.rb

@@ -0,0 +1,494 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:cc01a1c094d3c52a5b52b4a912620f9a716410d5ef08dea3520ea2a80cd328ad
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# frozen_string_literal: true
+
+require "json"
+require "sorbet-runtime"
+require "crawlberg_rb"
+module Crawlberg
+  # Authentication configuration.
+  module AuthConfig
+    extend T::Helpers
+    extend T::Sig
+
+    interface!
+
+    # Dispatch from a Hash to the appropriate variant constructor.
+    # @param hash [Hash] with discriminator field and variant-specific fields
+    # @return [variant_class] an instance of the appropriate variant
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.untyped) }
+    def self.from_hash(hash)
+      discriminator = hash[:type] || hash["type"]
+      case discriminator
+      when "basic" then AuthConfigBasic.from_hash(hash)
+      when "bearer" then AuthConfigBearer.from_hash(hash)
+      when "header" then AuthConfigHeader.from_hash(hash)
+      else raise "Unknown discriminator: #{discriminator}"
+      end
+    end
+  end
+  ## HTTP Basic authentication.
+  AuthConfigBasic = Data.define(:username, :password) do
+    include AuthConfig
+    extend T::Sig
+
+    # Username sent in the `Authorization: Basic` header.
+    sig { returns(String) }
+    def username = super # rubocop:disable Lint/UselessMethodDefinition
+    # Password sent in the `Authorization: Basic` header.
+    sig { returns(String) }
+    def password = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def basic? = true
+    sig { returns(T::Boolean) }
+    def bearer? = false
+    sig { returns(T::Boolean) }
+    def header? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(username: hash[:username] || hash["username"], password: hash[:password] || hash["password"])
+    end
+  end
+  ## Bearer token authentication.
+  AuthConfigBearer = Data.define(:token) do
+    include AuthConfig
+    extend T::Sig
+
+    # Token sent in the `Authorization: Bearer` header.
+    sig { returns(String) }
+    def token = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def basic? = false
+    sig { returns(T::Boolean) }
+    def bearer? = true
+    sig { returns(T::Boolean) }
+    def header? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(token: hash[:token] || hash["token"])
+    end
+  end
+  ## Custom authentication header.
+  AuthConfigHeader = Data.define(:name, :value) do
+    include AuthConfig
+    extend T::Sig
+
+    # HTTP header name to set on each request.
+    sig { returns(String) }
+    def name = super # rubocop:disable Lint/UselessMethodDefinition
+    # HTTP header value to send.
+    sig { returns(String) }
+    def value = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def basic? = false
+    sig { returns(T::Boolean) }
+    def bearer? = false
+    sig { returns(T::Boolean) }
+    def header? = true
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(name: hash[:name] || hash["name"], value: hash[:value] || hash["value"])
+    end
+  end
+end
+
+module Crawlberg
+  # An event emitted during a streaming crawl operation.
+  #
+  # Not available on `wasm32` targets — streaming requires native concurrency
+  # primitives (tokio channels, `JoinSet`) that are not supported on wasm32.
+  #
+  # Delivered to bindings through each target's native streaming idiom.
+  module CrawlEvent
+    extend T::Helpers
+    extend T::Sig
+
+    interface!
+
+    # Dispatch from a Hash to the appropriate variant constructor.
+    # @param hash [Hash] with discriminator field and variant-specific fields
+    # @return [variant_class] an instance of the appropriate variant
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.untyped) }
+    def self.from_hash(hash)
+      discriminator = hash[:type] || hash["type"]
+      case discriminator
+      when "page" then CrawlEventPage.from_hash(hash)
+      when "error" then CrawlEventError.from_hash(hash)
+      when "complete" then CrawlEventComplete.from_hash(hash)
+      else raise "Unknown discriminator: #{discriminator}"
+      end
+    end
+  end
+  ## A single page has been crawled.
+  CrawlEventPage = Data.define(:result) do
+    include CrawlEvent
+    extend T::Sig
+
+    # The crawled page result.
+    sig { returns(CrawlPageResult) }
+    def result = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def page? = true
+    sig { returns(T::Boolean) }
+    def error? = false
+    sig { returns(T::Boolean) }
+    def complete? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(result: hash[:result] || hash["result"])
+    end
+  end
+  ## An error occurred while crawling a URL.
+  CrawlEventError = Data.define(:url, :error) do
+    include CrawlEvent
+    extend T::Sig
+
+    # The URL that failed.
+    sig { returns(String) }
+    def url = super # rubocop:disable Lint/UselessMethodDefinition
+    # The error message.
+    sig { returns(String) }
+    def error = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def page? = false
+    sig { returns(T::Boolean) }
+    def error? = true
+    sig { returns(T::Boolean) }
+    def complete? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(url: hash[:url] || hash["url"], error: hash[:error] || hash["error"])
+    end
+  end
+  ## The crawl has completed.
+  CrawlEventComplete = Data.define(:pages_crawled) do
+    include CrawlEvent
+    extend T::Sig
+
+    # Total number of pages crawled.
+    sig { returns(Integer) }
+    def pages_crawled = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def page? = false
+    sig { returns(T::Boolean) }
+    def error? = false
+    sig { returns(T::Boolean) }
+    def complete? = true
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(pages_crawled: hash[:pages_crawled] || hash["pages_crawled"])
+    end
+  end
+end
+
+module Crawlberg
+  # A single page interaction action.
+  #
+  # Actions are serialized with a `type` tag using camelCase naming,
+  # except `ExecuteJs` which is explicitly renamed to `"executeJs"`.
+  module PageAction
+    extend T::Helpers
+    extend T::Sig
+
+    interface!
+
+    # Dispatch from a Hash to the appropriate variant constructor.
+    # @param hash [Hash] with discriminator field and variant-specific fields
+    # @return [variant_class] an instance of the appropriate variant
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.untyped) }
+    def self.from_hash(hash)
+      discriminator = hash[:type] || hash["type"]
+      case discriminator
+      when "click" then PageActionClick.from_hash(hash)
+      when "type" then PageActionTypeText.from_hash(hash)
+      when "press" then PageActionPress.from_hash(hash)
+      when "scroll" then PageActionScroll.from_hash(hash)
+      when "wait" then PageActionWait.from_hash(hash)
+      when "screenshot" then PageActionScreenshot.from_hash(hash)
+      when "executeJs" then PageActionExecuteJs.from_hash(hash)
+      when "scrape" then PageActionScrape.from_hash(hash)
+      else raise "Unknown discriminator: #{discriminator}"
+      end
+    end
+  end
+  ## Click on an element matching the given CSS selector.
+  PageActionClick = Data.define(:selector) do
+    include PageAction
+    extend T::Sig
+
+    # CSS selector for the element to click.
+    sig { returns(String) }
+    def selector = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = true
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(selector: hash[:selector] || hash["selector"])
+    end
+  end
+  ## Type text into an element matching the given CSS selector.
+  PageActionTypeText = Data.define(:selector, :text) do
+    include PageAction
+    extend T::Sig
+
+    # CSS selector for the input element.
+    sig { returns(String) }
+    def selector = super # rubocop:disable Lint/UselessMethodDefinition
+    # Text to type into the element.
+    sig { returns(String) }
+    def text = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = true
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(selector: hash[:selector] || hash["selector"], text: hash[:text] || hash["text"])
+    end
+  end
+  ## Press a keyboard key (e.g. "Enter", "Tab", "Escape").
+  PageActionPress = Data.define(:key) do
+    include PageAction
+    extend T::Sig
+
+    # Key name to press.
+    sig { returns(String) }
+    def key = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = true
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(key: hash[:key] || hash["key"])
+    end
+  end
+  ## Scroll the page or a specific element.
+  PageActionScroll = Data.define(:direction, :selector, :amount) do
+    include PageAction
+    extend T::Sig
+
+    # Direction to scroll.
+    sig { returns(ScrollDirection) }
+    def direction = super # rubocop:disable Lint/UselessMethodDefinition
+    # Optional CSS selector for a scrollable element. Scrolls the page if absent.
+    sig { returns(T.nilable(String)) }
+    def selector = super # rubocop:disable Lint/UselessMethodDefinition
+    # Optional pixel amount to scroll. Uses a default if absent.
+    sig { returns(T.nilable(Integer)) }
+    def amount = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = true
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(direction: hash[:direction] || hash["direction"], selector: hash[:selector] || hash["selector"], amount: hash[:amount] || hash["amount"])
+    end
+  end
+  ## Wait for a duration or for an element to appear.
+  PageActionWait = Data.define(:milliseconds, :selector) do
+    include PageAction
+    extend T::Sig
+
+    # Milliseconds to wait. Ignored if `selector` is provided.
+    sig { returns(T.nilable(Integer)) }
+    def milliseconds = super # rubocop:disable Lint/UselessMethodDefinition
+    # CSS selector to wait for.
+    sig { returns(T.nilable(String)) }
+    def selector = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = true
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(milliseconds: hash[:milliseconds] || hash["milliseconds"], selector: hash[:selector] || hash["selector"])
+    end
+  end
+  ## Take a screenshot of the current page.
+  PageActionScreenshot = Data.define(:full_page) do
+    include PageAction
+    extend T::Sig
+
+    # Whether to capture the full scrollable page. Defaults to viewport only.
+    #
+    # Accepts both the canonical `fullPage` (camelCase) form and the
+    # `full_page` (snake_case) alias so language bindings and fixtures can
+    # use either convention without error.
+    sig { returns(T.nilable(T::Boolean)) }
+    def full_page = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = true
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(full_page: hash[:full_page] || hash["full_page"])
+    end
+  end
+  ## Execute arbitrary JavaScript in the page context.
+  ##
+  ## # Safety
+  ##
+  ## The script runs with full page privileges in the browser context.
+  ## Only execute scripts from trusted sources.
+  PageActionExecuteJs = Data.define(:script) do
+    include PageAction
+    extend T::Sig
+
+    # JavaScript source code to execute. Max 1 MB.
+    sig { returns(String) }
+    def script = super # rubocop:disable Lint/UselessMethodDefinition
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = true
+    sig { returns(T::Boolean) }
+    def scrape? = false
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new(script: hash[:script] || hash["script"])
+    end
+  end
+  ## Scrape the current page HTML.
+  PageActionScrape = Data.define do
+    include PageAction
+    extend T::Sig
+
+    sig { returns(T::Boolean) }
+    def click? = false
+    sig { returns(T::Boolean) }
+    def type_text? = false
+    sig { returns(T::Boolean) }
+    def press? = false
+    sig { returns(T::Boolean) }
+    def scroll? = false
+    sig { returns(T::Boolean) }
+    def wait? = false
+    sig { returns(T::Boolean) }
+    def screenshot? = false
+    sig { returns(T::Boolean) }
+    def execute_js? = false
+    sig { returns(T::Boolean) }
+    def scrape? = true
+    # @param hash [Hash] deserialized from the native extension
+    # @return [self]
+    sig { params(hash: T::Hash[T.untyped, T.untyped]).returns(T.attached_class) }
+    def self.from_hash(hash)
+      new
+    end
+  end
+end

data/lib/crawlberg/version.rb

@@ -0,0 +1,10 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:cc01a1c094d3c52a5b52b4a912620f9a716410d5ef08dea3520ea2a80cd328ad
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
+# frozen_string_literal: true
+
+module Crawlberg
+  ## The version string for this package.
+  VERSION = "1.0.0.pre.rc.2"
+end

data/lib/crawlberg.rb

@@ -1,6 +1,18 @@
+# This file is auto-generated by alef — DO NOT EDIT.
+# alef:hash:cc01a1c094d3c52a5b52b4a912620f9a716410d5ef08dea3520ea2a80cd328ad
+# To regenerate: alef generate
+# To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
-# Reserved name for crawlberg. See https://github.com/xberg-io/crawlberg
+require_relative "crawlberg/version"
+require_relative "crawlberg/native"
+
+# Top-level namespace for the Crawlberg Ruby binding.
+#
+# All type and function symbols are re-exported from the native extension
+# loaded via `require_relative "crawlberg/native"`. See
+# {file:README.md} for usage examples and the upstream documentation
+# for the full API reference.
 module Crawlberg
-  VERSION = "0.0.1"
+  # Re-export all types and functions from native extension
 end