kreuzcrawl 0.3.0.pre.rc.43 → 0.3.0.pre.rc.50

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 26b349c9879f4dbbf63ac4a65c34d5546c846203cfb97825d4040eeb9202d62d
-  data.tar.gz: 8aa9682613741bfa3a787435901a5a32b5a5a89b9b760d2f720af65dd4ff6b20
+  metadata.gz: 2213fa1c83d734c7ad5e7fb41a87d910654b54de2623485ded5ef78e0af04b61
+  data.tar.gz: 1254c10de4a176e4548db7a246463fcdadf836a4521db41e64ff44f59b75cd0c
 SHA512:
-  metadata.gz: 8d623f74a48c685b0414f6ce43cf82f937f8ffd37a2f606cd8ffbbdba410e401078e6191ad4813bd59e7265321a0df7f2991146eae847b80d9164703444dcf8b
-  data.tar.gz: 7543119c313782eff3ab9f8942f95f818e9bc27cea1eb0ad8e7ce9b0a6ed6a8e290a1043d804acdd9e85d45e4c314c8d395f46614181e59a1adf471c091e028c
+  metadata.gz: 7929332edca6661be7a3b575db2e524f2d3ebafe2ad0a70f1f5113dc5f1696b41fd574f49acca26ae12fb80b19b9a039e4ddaa6a34fc9529ee633b8d0d9e59ca
+  data.tar.gz: ad173c414b49aad8fd64a8e5de62e1e8ea09178e4eaa91c288fc48f83055e00c7f4300f2518a44a8f382a33a93c644b3fb3d53b6eccde72b45c64d8087b99eee

data/ext/kreuzcrawl_rb/native/Cargo.lock

@@ -1469,7 +1469,7 @@ dependencies = [
 
 [[package]]
 name = "kreuzcrawl"
-version = "0.3.0-rc.43"
+version = "0.3.0-rc.50"
 dependencies = [
  "ahash",
  "aho-corasick",
@@ -1506,7 +1506,7 @@ dependencies = [
 
 [[package]]
 name = "kreuzcrawl-rb"
-version = "0.3.0-rc.43"
+version = "0.3.0-rc.50"
 dependencies = [
  "futures",
  "kreuzcrawl",

data/ext/kreuzcrawl_rb/native/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kreuzcrawl-rb"
-version = "0.3.0-rc.43"
+version = "0.3.0-rc.50"
 edition = "2024"
 license = "Elastic-2.0"
 description = "High-performance web crawling engine"
@@ -18,7 +18,7 @@ crate-type = ["cdylib"]
 
 [dependencies]
 futures = "0.3"
-kreuzcrawl = { version = "0.3.0-rc.43", path = "../../../../../crates/kreuzcrawl", features = ["interact", "browser-chromiumoxide"] }
+kreuzcrawl = { version = "0.3.0-rc.50", path = "../../../../../crates/kreuzcrawl", features = ["interact", "browser-chromiumoxide"] }
 magnus = "0.8"
 rb-sys = ">=0.9, <0.9.128"
 serde = { version = "1", features = ["derive"] }

data/ext/kreuzcrawl_rb/native/extconf.rb

@@ -7,5 +7,8 @@ default_profile = ENV.fetch("CARGO_PROFILE", "release")
 
 create_rust_makefile("kreuzcrawl_rb") do |config|
   config.profile = default_profile.to_sym
-  config.ext_dir = "native"
+  # extconf.rb and Cargo.toml are siblings under ext/kreuzcrawl_rb/native/; rb_sys interprets
+  # ext_dir relative to extconf.rb, so "." finds the sibling Cargo.toml. "native" would
+  # resolve to native/native/Cargo.toml and break `gem install` on end-user machines.
+  config.ext_dir = "."
 end

data/ext/kreuzcrawl_rb/src/lib.rs

@@ -1,5 +1,5 @@
 // This file is auto-generated by alef. DO NOT EDIT.
-// alef:hash:7b9c93728a9ad6929902470aae4101dc3ceb9f7790425e064878ef114f164df6
+// alef:hash:e0b048907e4acd1bff8132ca9fab8a2ec941d36e30e70ac1f6ce3cd337219c92
 // Re-generate with: alef generate
 #![allow(dead_code, unused_imports, unused_variables)]
 #![allow(

data/lib/kreuzcrawl/native.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:7b9c93728a9ad6929902470aae4101dc3ceb9f7790425e064878ef114f164df6
+# alef:hash:e0b048907e4acd1bff8132ca9fab8a2ec941d36e30e70ac1f6ce3cd337219c92
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
@@ -29,8 +29,7 @@ module Kreuzcrawl
       end
     end
   end
-
-  # HTTP Basic authentication.
+  ## HTTP Basic authentication.
   AuthConfigBasic = Data.define(:username, :password) do
     include AuthConfig
     extend T::Sig
@@ -38,20 +37,15 @@ module Kreuzcrawl
     # 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) }
@@ -59,8 +53,7 @@ module Kreuzcrawl
       new(username: hash[:username] || hash["username"], password: hash[:password] || hash["password"])
     end
   end
-
-  # Bearer token authentication.
+  ## Bearer token authentication.
   AuthConfigBearer = Data.define(:token) do
     include AuthConfig
     extend T::Sig
@@ -68,16 +61,12 @@ module Kreuzcrawl
     # 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) }
@@ -85,8 +74,7 @@ module Kreuzcrawl
       new(token: hash[:token] || hash["token"])
     end
   end
-
-  # Custom authentication header.
+  ## Custom authentication header.
   AuthConfigHeader = Data.define(:name, :value) do
     include AuthConfig
     extend T::Sig
@@ -94,20 +82,15 @@ module Kreuzcrawl
     # 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) }
@@ -147,8 +130,7 @@ module Kreuzcrawl
       end
     end
   end
-
-  # A single page has been crawled.
+  ## A single page has been crawled.
   CrawlEventPage = Data.define(:result) do
     include CrawlEvent
     extend T::Sig
@@ -156,16 +138,12 @@ module Kreuzcrawl
     # 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) }
@@ -173,8 +151,7 @@ module Kreuzcrawl
       new(result: hash[:result] || hash["result"])
     end
   end
-
-  # An error occurred while crawling a URL.
+  ## An error occurred while crawling a URL.
   CrawlEventError = Data.define(:url, :error) do
     include CrawlEvent
     extend T::Sig
@@ -182,20 +159,15 @@ module Kreuzcrawl
     # 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) }
@@ -203,8 +175,7 @@ module Kreuzcrawl
       new(url: hash[:url] || hash["url"], error: hash[:error] || hash["error"])
     end
   end
-
-  # The crawl has completed.
+  ## The crawl has completed.
   CrawlEventComplete = Data.define(:pages_crawled) do
     include CrawlEvent
     extend T::Sig
@@ -212,16 +183,12 @@ module Kreuzcrawl
     # 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) }
@@ -261,8 +228,7 @@ module Kreuzcrawl
       end
     end
   end
-
-  # Click on an element matching the given CSS selector.
+  ## Click on an element matching the given CSS selector.
   PageActionClick = Data.define(:selector) do
     include PageAction
     extend T::Sig
@@ -270,31 +236,22 @@ module Kreuzcrawl
     # 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) }
@@ -302,8 +259,7 @@ module Kreuzcrawl
       new(selector: hash[:selector] || hash["selector"])
     end
   end
-
-  # Type text into an element matching the given CSS selector.
+  ## Type text into an element matching the given CSS selector.
   PageActionTypeText = Data.define(:selector, :text) do
     include PageAction
     extend T::Sig
@@ -311,35 +267,25 @@ module Kreuzcrawl
     # 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) }
@@ -347,8 +293,7 @@ module Kreuzcrawl
       new(selector: hash[:selector] || hash["selector"], text: hash[:text] || hash["text"])
     end
   end
-
-  # Press a keyboard key (e.g. "Enter", "Tab", "Escape").
+  ## Press a keyboard key (e.g. "Enter", "Tab", "Escape").
   PageActionPress = Data.define(:key) do
     include PageAction
     extend T::Sig
@@ -356,31 +301,22 @@ module Kreuzcrawl
     # 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) }
@@ -388,8 +324,7 @@ module Kreuzcrawl
       new(key: hash[:key] || hash["key"])
     end
   end
-
-  # Scroll the page or a specific element.
+  ## Scroll the page or a specific element.
   PageActionScroll = Data.define(:direction, :selector, :amount) do
     include PageAction
     extend T::Sig
@@ -397,39 +332,28 @@ module Kreuzcrawl
     # 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) }
@@ -437,8 +361,7 @@ module Kreuzcrawl
       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.
+  ## Wait for a duration or for an element to appear.
   PageActionWait = Data.define(:milliseconds, :selector) do
     include PageAction
     extend T::Sig
@@ -446,35 +369,25 @@ module Kreuzcrawl
     # 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) }
@@ -482,8 +395,7 @@ module Kreuzcrawl
       new(milliseconds: hash[:milliseconds] || hash["milliseconds"], selector: hash[:selector] || hash["selector"])
     end
   end
-
-  # Take a screenshot of the current page.
+  ## Take a screenshot of the current page.
   PageActionScreenshot = Data.define(:full_page) do
     include PageAction
     extend T::Sig
@@ -495,31 +407,22 @@ module Kreuzcrawl
     # 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) }
@@ -527,13 +430,12 @@ module Kreuzcrawl
       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.
+  ## 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
@@ -541,31 +443,22 @@ module Kreuzcrawl
     # 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) }
@@ -573,36 +466,27 @@ module Kreuzcrawl
       new(script: hash[:script] || hash["script"])
     end
   end
-
-  # Scrape the current page HTML.
+  ## 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) }

data/lib/kreuzcrawl/version.rb

@@ -1,9 +1,10 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:7b9c93728a9ad6929902470aae4101dc3ceb9f7790425e064878ef114f164df6
+# alef:hash:e0b048907e4acd1bff8132ca9fab8a2ec941d36e30e70ac1f6ce3cd337219c92
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
 
 module Kreuzcrawl
-  VERSION = "0.3.0.pre.rc.43"
+  ## The version string for this package.
+  VERSION = "0.3.0.pre.rc.50"
 end

data/lib/kreuzcrawl.rb

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:7b9c93728a9ad6929902470aae4101dc3ceb9f7790425e064878ef114f164df6
+# alef:hash:e0b048907e4acd1bff8132ca9fab8a2ec941d36e30e70ac1f6ce3cd337219c92
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 # frozen_string_literal: true
@@ -7,6 +7,12 @@
 require_relative "kreuzcrawl/version"
 require_relative "kreuzcrawl/native"
 
+# Top-level namespace for the Kreuzcrawl Ruby binding.
+#
+# All type and function symbols are re-exported from the native extension
+# loaded via `require_relative "kreuzcrawl/native"`. See
+# {file:README.md} for usage examples and the upstream documentation
+# for the full API reference.
 module Kreuzcrawl
   # Re-export all types and functions from native extension
 end

data/sig/types.rbs

@@ -1,5 +1,5 @@
 # This file is auto-generated by alef — DO NOT EDIT.
-# alef:hash:7b9c93728a9ad6929902470aae4101dc3ceb9f7790425e064878ef114f164df6
+# alef:hash:e0b048907e4acd1bff8132ca9fab8a2ec941d36e30e70ac1f6ce3cd337219c92
 # To regenerate: alef generate
 # To verify freshness: alef verify --exit-code
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kreuzcrawl
 version: !ruby/object:Gem::Version
-  version: 0.3.0.pre.rc.43
+  version: 0.3.0.pre.rc.50
 platform: ruby
 authors:
 - Kreuzberg Team
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-06-05 00:00:00.000000000 Z
+date: 2026-06-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rb_sys