kreuzberg 4.5.2-aarch64-linux → 4.6.0-aarch64-linux

data/Gemfile.lock

@@ -1,274 +0,0 @@
-PATH
-  remote: .
-  specs:
-    kreuzberg (4.5.2)
-      rb_sys (~> 0.9.119)
-      sorbet-runtime (~> 0.5)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    activesupport (8.1.2)
-      base64
-      bigdecimal
-      concurrent-ruby (~> 1.0, >= 1.3.1)
-      connection_pool (>= 2.2.5)
-      drb
-      i18n (>= 1.6, < 2)
-      json
-      logger (>= 1.4.2)
-      minitest (>= 5.1)
-      securerandom (>= 0.3)
-      tzinfo (~> 2.0, >= 2.0.5)
-      uri (>= 0.13.1)
-    addressable (2.8.9)
-      public_suffix (>= 2.0.2, < 8.0)
-    ast (2.4.3)
-    base64 (0.3.0)
-    bigdecimal (4.0.1)
-    byebug (13.0.0)
-      reline (>= 0.6.0)
-    coderay (1.1.3)
-    concurrent-ruby (1.3.6)
-    connection_pool (3.0.2)
-    csv (3.3.5)
-    diff-lcs (1.6.2)
-    drb (2.2.3)
-    ffi (1.17.3)
-    ffi (1.17.3-aarch64-linux-gnu)
-    ffi (1.17.3-aarch64-linux-musl)
-    ffi (1.17.3-arm-linux-gnu)
-    ffi (1.17.3-arm-linux-musl)
-    ffi (1.17.3-arm64-darwin)
-    ffi (1.17.3-x86-linux-gnu)
-    ffi (1.17.3-x86-linux-musl)
-    ffi (1.17.3-x86_64-darwin)
-    ffi (1.17.3-x86_64-linux-gnu)
-    ffi (1.17.3-x86_64-linux-musl)
-    fileutils (1.8.0)
-    i18n (1.14.8)
-      concurrent-ruby (~> 1.0)
-    io-console (0.8.2)
-    json (2.19.2)
-    json-schema (6.2.0)
-      addressable (~> 2.8)
-      bigdecimal (>= 3.1, < 5)
-    language_server-protocol (3.17.0.5)
-    lint_roller (1.1.0)
-    listen (3.10.0)
-      logger
-      rb-fsevent (~> 0.10, >= 0.10.3)
-      rb-inotify (~> 0.9, >= 0.9.10)
-    logger (1.7.0)
-    mcp (0.9.0)
-      json-schema (>= 4.1)
-    method_source (1.1.0)
-    minitest (6.0.2)
-      drb (~> 2.0)
-      prism (~> 1.5)
-    mutex_m (0.3.0)
-    parallel (1.27.0)
-    parser (3.3.10.2)
-      ast (~> 2.4.1)
-      racc
-    prism (1.9.0)
-    pry (0.16.0)
-      coderay (~> 1.1)
-      method_source (~> 1.0)
-      reline (>= 0.6.0)
-    pry-byebug (3.12.0)
-      byebug (~> 13.0)
-      pry (>= 0.13, < 0.17)
-    public_suffix (7.0.5)
-    racc (1.8.1)
-    rainbow (3.1.1)
-    rake (13.3.1)
-    rake-compiler (1.3.1)
-      rake
-    rake-compiler-dock (1.11.0)
-    rb-fsevent (0.11.2)
-    rb-inotify (0.11.1)
-      ffi (~> 1.0)
-    rb_sys (0.9.124)
-      rake-compiler-dock (= 1.11.0)
-    rbs (3.10.3)
-      logger
-      tsort
-    regexp_parser (2.11.3)
-    reline (0.6.3)
-      io-console (~> 0.5)
-    rspec (3.13.2)
-      rspec-core (~> 3.13.0)
-      rspec-expectations (~> 3.13.0)
-      rspec-mocks (~> 3.13.0)
-    rspec-core (3.13.6)
-      rspec-support (~> 3.13.0)
-    rspec-expectations (3.13.5)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.8)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.13.0)
-    rspec-support (3.13.7)
-    rubocop (1.85.1)
-      json (~> 2.3)
-      language_server-protocol (~> 3.17.0.2)
-      lint_roller (~> 1.1.0)
-      mcp (~> 0.6)
-      parallel (~> 1.10)
-      parser (>= 3.3.0.2)
-      rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.49.0, < 2.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.49.1)
-      parser (>= 3.3.7.2)
-      prism (~> 1.7)
-    rubocop-performance (1.26.1)
-      lint_roller (~> 1.1)
-      rubocop (>= 1.75.0, < 2.0)
-      rubocop-ast (>= 1.47.1, < 2.0)
-    rubocop-rspec (3.9.0)
-      lint_roller (~> 1.1)
-      rubocop (~> 1.81)
-    ruby-progressbar (1.13.0)
-    securerandom (0.4.1)
-    sorbet-runtime (0.6.13055)
-    steep (1.10.0)
-      activesupport (>= 5.1)
-      concurrent-ruby (>= 1.1.10)
-      csv (>= 3.0.9)
-      fileutils (>= 1.1.0)
-      json (>= 2.1.0)
-      language_server-protocol (>= 3.17.0.4, < 4.0)
-      listen (~> 3.0)
-      logger (>= 1.3.0)
-      mutex_m (>= 0.3.0)
-      parser (>= 3.1)
-      rainbow (>= 2.2.2, < 4.0)
-      rbs (~> 3.9)
-      securerandom (>= 0.1)
-      strscan (>= 1.0.0)
-      terminal-table (>= 2, < 5)
-      uri (>= 0.12.0)
-    strscan (3.1.7)
-    terminal-table (4.0.0)
-      unicode-display_width (>= 1.1.1, < 4)
-    tsort (0.2.0)
-    tzinfo (2.0.6)
-      concurrent-ruby (~> 1.0)
-    unicode-display_width (3.2.0)
-      unicode-emoji (~> 4.1)
-    unicode-emoji (4.2.0)
-    uri (1.1.1)
-    yard (0.9.38)
-
-PLATFORMS
-  aarch64-linux-gnu
-  aarch64-linux-musl
-  arm-linux-gnu
-  arm-linux-musl
-  arm64-darwin
-  ruby
-  x86-linux-gnu
-  x86-linux-musl
-  x86_64-darwin
-  x86_64-linux
-  x86_64-linux-gnu
-  x86_64-linux-musl
-
-DEPENDENCIES
-  bundler (~> 4.0)
-  kreuzberg!
-  pry (~> 0.14)
-  pry-byebug (~> 3.10)
-  rake (~> 13.0)
-  rake-compiler (~> 1.2)
-  rbs (~> 3.0)
-  rspec (~> 3.12)
-  rubocop (~> 1.66)
-  rubocop-performance (~> 1.21)
-  rubocop-rspec (~> 3.0)
-  steep (~> 1.8)
-  yard (~> 0.9)
-
-CHECKSUMS
-  activesupport (8.1.2) sha256=88842578ccd0d40f658289b0e8c842acfe9af751afee2e0744a7873f50b6fdae
-  addressable (2.8.9) sha256=cc154fcbe689711808a43601dee7b980238ce54368d23e127421753e46895485
-  ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
-  base64 (0.3.0) sha256=27337aeabad6ffae05c265c450490628ef3ebd4b67be58257393227588f5a97b
-  bigdecimal (4.0.1) sha256=8b07d3d065a9f921c80ceaea7c9d4ae596697295b584c296fe599dd0ad01c4a7
-  byebug (13.0.0) sha256=d2263efe751941ca520fa29744b71972d39cbc41839496706f5d9b22e92ae05d
-  coderay (1.1.3) sha256=dc530018a4684512f8f38143cd2a096c9f02a1fc2459edcfe534787a7fc77d4b
-  concurrent-ruby (1.3.6) sha256=6b56837e1e7e5292f9864f34b69c5a2cbc75c0cf5338f1ce9903d10fa762d5ab
-  connection_pool (3.0.2) sha256=33fff5ba71a12d2aa26cb72b1db8bba2a1a01823559fb01d29eb74c286e62e0a
-  csv (3.3.5) sha256=6e5134ac3383ef728b7f02725d9872934f523cb40b961479f69cf3afa6c8e73f
-  diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
-  drb (2.2.3) sha256=0b00d6fdb50995fe4a45dea13663493c841112e4068656854646f418fda13373
-  ffi (1.17.3) sha256=0e9f39f7bb3934f77ad6feab49662be77e87eedcdeb2a3f5c0234c2938563d4c
-  ffi (1.17.3-aarch64-linux-gnu) sha256=28ad573df26560f0aedd8a90c3371279a0b2bd0b4e834b16a2baa10bd7a97068
-  ffi (1.17.3-aarch64-linux-musl) sha256=020b33b76775b1abacc3b7d86b287cef3251f66d747092deec592c7f5df764b2
-  ffi (1.17.3-arm-linux-gnu) sha256=5bd4cea83b68b5ec0037f99c57d5ce2dd5aa438f35decc5ef68a7d085c785668
-  ffi (1.17.3-arm-linux-musl) sha256=0d7626bb96265f9af78afa33e267d71cfef9d9a8eb8f5525344f8da6c7d76053
-  ffi (1.17.3-arm64-darwin) sha256=0c690555d4cee17a7f07c04d59df39b2fba74ec440b19da1f685c6579bb0717f
-  ffi (1.17.3-x86-linux-gnu) sha256=868a88fcaf5186c3a46b7c7c2b2c34550e1e61a405670ab23f5b6c9971529089
-  ffi (1.17.3-x86-linux-musl) sha256=f0286aa6ef40605cf586e61406c446de34397b85dbb08cc99fdaddaef8343945
-  ffi (1.17.3-x86_64-darwin) sha256=1f211811eb5cfaa25998322cdd92ab104bfbd26d1c4c08471599c511f2c00bb5
-  ffi (1.17.3-x86_64-linux-gnu) sha256=3746b01f677aae7b16dc1acb7cb3cc17b3e35bdae7676a3f568153fb0e2c887f
-  ffi (1.17.3-x86_64-linux-musl) sha256=086b221c3a68320b7564066f46fed23449a44f7a1935f1fe5a245bd89d9aea56
-  fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
-  i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
-  io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
-  json (2.19.2) sha256=e7e1bd318b2c37c4ceee2444841c86539bc462e81f40d134cf97826cb14e83cf
-  json-schema (6.2.0) sha256=e8bff46ed845a22c1ab2bd0d7eccf831c01fe23bb3920caa4c74db4306813666
-  kreuzberg (4.5.2)
-  language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
-  lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
-  listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
-  logger (1.7.0) sha256=196edec7cc44b66cfb40f9755ce11b392f21f7967696af15d274dde7edff0203
-  mcp (0.9.0) sha256=a0a3737b0ac9df0772f4ef7e2b013c260ddbcf217a5d50a66bff0baeddf03e47
-  method_source (1.1.0) sha256=181301c9c45b731b4769bc81e8860e72f9161ad7d66dd99103c9ab84f560f5c5
-  minitest (6.0.2) sha256=db6e57956f6ecc6134683b4c87467d6dd792323c7f0eea7b93f66bd284adbc3d
-  mutex_m (0.3.0) sha256=cfcb04ac16b69c4813777022fdceda24e9f798e48092a2b817eb4c0a782b0751
-  parallel (1.27.0) sha256=4ac151e1806b755fb4e2dc2332cbf0e54f2e24ba821ff2d3dcf86bf6dc4ae130
-  parser (3.3.10.2) sha256=6f60c84aa4bdcedb6d1a2434b738fe8a8136807b6adc8f7f53b97da9bc4e9357
-  prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
-  pry (0.16.0) sha256=d76c69065698ed1f85e717bd33d7942c38a50868f6b0673c636192b3d1b6054e
-  pry-byebug (3.12.0) sha256=594e094ae8a8390a7ad4c7b36ae36e13304ed02664c67417d108dc5f7213d1b7
-  public_suffix (7.0.5) sha256=1a8bb08f1bbea19228d3bed6e5ed908d1cb4f7c2726d18bd9cadf60bc676f623
-  racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
-  rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
-  rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
-  rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
-  rake-compiler-dock (1.11.0) sha256=eab51f2cd533eb35cea6b624a75281f047123e70a64c58b607471bb49428f8c2
-  rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
-  rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
-  rb_sys (0.9.124) sha256=513476557b12eaf73764b3da9f8746024558fe8699bda785fb548c9aa3877ae7
-  rbs (3.10.3) sha256=70627f3919016134d554e6c99195552ae3ef6020fe034c8e983facc9c192daa6
-  regexp_parser (2.11.3) sha256=ca13f381a173b7a93450e53459075c9b76a10433caadcb2f1180f2c741fc55a4
-  reline (0.6.3) sha256=1198b04973565b36ec0f11542ab3f5cfeeec34823f4e54cebde90968092b1835
-  rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
-  rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
-  rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
-  rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
-  rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
-  rubocop (1.85.1) sha256=3dbcf9e961baa4c376eeeb2a03913dca5e3987033b04d38fa538aa1e7406cc77
-  rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
-  rubocop-performance (1.26.1) sha256=cd19b936ff196df85829d264b522fd4f98b6c89ad271fa52744a8c11b8f71834
-  rubocop-rspec (3.9.0) sha256=8fa70a3619408237d789aeecfb9beef40576acc855173e60939d63332fdb55e2
-  ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
-  securerandom (0.4.1) sha256=cc5193d414a4341b6e225f0cb4446aceca8e50d5e1888743fac16987638ea0b1
-  sorbet-runtime (0.6.13055) sha256=c8ae8c81310e0a28d290b11f44ddca59659b7d7f13752c0ef5d16964bbb84d18
-  steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
-  strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
-  terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2
-  tsort (0.2.0) sha256=9650a793f6859a43b6641671278f79cfead60ac714148aabe4e3f0060480089f
-  tzinfo (2.0.6) sha256=8daf828cc77bcf7d63b0e3bdb6caa47e2272dcfaf4fbfe46f8c3a9df087a829b
-  unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
-  unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
-  uri (1.1.1) sha256=379fa58d27ffb1387eaada68c749d1426738bd0f654d812fcc07e7568f5c57c6
-  yard (0.9.38) sha256=721fb82afb10532aa49860655f6cc2eaa7130889df291b052e1e6b268283010f
-
-BUNDLED WITH
-  4.0.5

data/Rakefile

@@ -1,34 +0,0 @@
-# frozen_string_literal: true
-
-require 'bundler/gem_tasks'
-require 'rake/extensiontask'
-require 'rspec/core/rake_task'
-
-GEMSPEC = Gem::Specification.load(File.expand_path('kreuzberg.gemspec', __dir__))
-
-# Vendor kreuzberg core crates before compilation
-task :vendor do
-  vendor_script = File.expand_path('../../scripts/ci/ruby/vendor-kreuzberg-core.py', __dir__)
-  puts 'Vendoring kreuzberg core crates...'
-  sh "python3 #{vendor_script}"
-end
-
-Rake::ExtensionTask.new('kreuzberg_rb', GEMSPEC) do |ext|
-  ext.lib_dir = 'lib'
-  ext.ext_dir = 'ext/kreuzberg_rb'
-  ext.cross_compile = true
-  ext.cross_platform = %w[
-    x86_64-linux
-    aarch64-linux
-    x86_64-darwin
-    arm64-darwin
-    x64-mingw32
-    x64-mingw-ucrt
-  ]
-end
-
-RSpec::Core::RakeTask.new(:spec)
-
-task compile: :vendor
-task spec: :compile
-task default: :spec

data/Steepfile

@@ -1,51 +0,0 @@
-# frozen_string_literal: true
-
-# Steep configuration for Kreuzberg Ruby package
-
-target :lib do
-  signature 'sig'
-
-  check 'lib'
-
-  # Core library
-  library 'pathname'
-  library 'json'
-  library 'fileutils'
-  library 'open3'
-
-  # Strategic ignores for steep limitations (not fixable, safe to ignore):
-
-  # 1. Sorbet type annotations - Steep doesn't recognize Sorbet's T::Struct and T::Sig
-  #    This file uses Sorbet exclusively for type definitions
-  ignore 'lib/kreuzberg/types.rb'
-
-  # 2. Struct.new with keyword_init - steep cannot understand implicit attr_readers
-  #    defined by Struct.new in blocks (Table and Chunk classes)
-  ignore 'lib/kreuzberg/result.rb'
-
-  # 3. Generic type parameters in normalize_config - steep has difficulty with
-  #    methods that take Class as parameter and return instances
-  ignore 'lib/kreuzberg/config.rb'
-
-  # 4. Interface types - steep doesn't recognize that all Ruby objects have nil? and is_a?
-  #    even for interface types like _ToH
-  ignore 'lib/kreuzberg/extraction_api.rb'
-
-  # 5. Open3 methods - steep's built-in Open3 RBS signatures incomplete
-  #    (capture2, capture3, popen3 are standard library methods)
-  ignore 'lib/kreuzberg/setup_lib_path.rb'
-  ignore 'lib/kreuzberg/cli_proxy.rb'
-  ignore 'lib/kreuzberg/mcp_proxy.rb'
-
-  # Ignore Rust extension methods (defined in native code)
-  ignore 'ext'
-
-  # Ignore vendored code
-  ignore 'vendor'
-
-  # Ignore test files
-  ignore 'spec'
-
-  # Ignore examples
-  ignore 'examples'
-end

data/examples/async_patterns.rb

@@ -1,282 +0,0 @@
-# frozen_string_literal: true
-
-require 'kreuzberg'
-
-# NOTE: Ruby bindings use Tokio runtime with block_on() internally.
-# The "async" functions block the Ruby GVL during execution, so there's
-# no performance benefit over the _sync variants from Ruby's perspective.
-
-# ============================================================================
-# Pattern 1: Synchronous Extraction (Recommended)
-# ============================================================================
-
-def basic_sync_extraction
-  result = Kreuzberg.extract_file_sync('document.pdf')
-  puts "Content: #{result[:content]}"
-  puts "MIME type: #{result[:mime_type]}"
-end
-
-# ============================================================================
-# Pattern 2: "Async" Extraction (Same Performance as Sync)
-# ============================================================================
-
-def basic_async_extraction
-  result = Kreuzberg.extract_file('document.pdf')
-  puts "Content: #{result[:content]}"
-end
-
-# ============================================================================
-# Pattern 3: Concurrent Processing with Ruby Threads
-# ============================================================================
-
-def concurrent_with_threads
-  files = ['doc1.pdf', 'doc2.pdf', 'doc3.pdf']
-
-  threads = files.map do |file|
-    Thread.new do
-      Kreuzberg.extract_file_sync(file)
-    end
-  end
-
-  results = threads.map(&:value)
-  results.each_with_index do |result, index|
-    puts "File #{index + 1}: #{result[:content][0..100]}"
-  end
-end
-
-# ============================================================================
-# Pattern 4: Batch Processing (Preferred for Multiple Files)
-# ============================================================================
-
-def batch_processing
-  files = ['doc1.pdf', 'doc2.pdf', 'doc3.pdf']
-
-  results = Kreuzberg.batch_extract_files_sync(files)
-
-  puts "Processed #{results.length} files"
-  results.each do |result|
-    puts "Content preview: #{result[:content][0..50]}"
-  end
-end
-
-# ============================================================================
-# Pattern 5: Extraction with Configuration
-# ============================================================================
-
-def extraction_with_config
-  config = {
-    ocr: {
-      backend: 'tesseract',
-      language: 'eng'
-    },
-    force_ocr: false
-  }
-
-  result = Kreuzberg.extract_file_sync('scanned.pdf', **config)
-  puts "Extracted with OCR: #{result[:content]}"
-end
-
-# ============================================================================
-# Pattern 6: Extract from Bytes
-# ============================================================================
-
-def extract_from_bytes
-  data = File.binread('document.pdf')
-  result = Kreuzberg.extract_bytes_sync(data, 'application/pdf')
-  puts "Extracted from memory: #{result[:content]}"
-end
-
-# ============================================================================
-# Pattern 7: Batch Extract from Bytes
-# ============================================================================
-
-def batch_extract_from_bytes
-  files = ['doc1.pdf', 'doc2.pdf']
-  bytes_array = files.map { |f| File.binread(f) }
-  mime_types = ['application/pdf', 'application/pdf']
-
-  results = Kreuzberg.batch_extract_bytes_sync(bytes_array, mime_types)
-  puts "Processed #{results.length} files from memory"
-end
-
-# ============================================================================
-# Pattern 8: Error Handling
-# ============================================================================
-
-def error_handling
-  Kreuzberg.extract_file_sync('nonexistent.pdf')
-rescue StandardError => e
-  puts "Extraction failed: #{e.message}"
-end
-
-# ============================================================================
-# Pattern 9: Sequential Processing
-# ============================================================================
-
-def sequential_processing
-  files = ['doc1.pdf', 'doc2.pdf', 'doc3.pdf']
-
-  files.each do |file|
-    result = Kreuzberg.extract_file_sync(file)
-    puts "Processed #{file}: #{result[:content][0..50]}"
-  end
-end
-
-# ============================================================================
-# Pattern 10: Background Processing with ActiveJob (Rails)
-# ============================================================================
-
-# Example ActiveJob for async processing in Rails
-# < ApplicationJob
-class DocumentExtractionJob
-  def perform(file_path)
-    result = Kreuzberg.extract_file_sync(file_path)
-    puts "Background extraction complete: #{result[:content][0..100]}"
-  end
-end
-
-# Usage in Rails controller:
-# DocumentExtractionJob.perform_later('document.pdf')
-
-# ============================================================================
-# Pattern 11: Concurrent Processing with Parallel Gem
-# ============================================================================
-
-def concurrent_with_parallel_gem
-  require 'parallel'
-
-  files = ['doc1.pdf', 'doc2.pdf', 'doc3.pdf', 'doc4.pdf']
-
-  results = Parallel.map(files, in_processes: 4) do |file|
-    Kreuzberg.extract_file_sync(file)
-  end
-
-  results.each do |result|
-    puts "Content: #{result[:content][0..50]}"
-  end
-end
-
-# ============================================================================
-# Pattern 12: Timeout Wrapper
-# ============================================================================
-
-def extraction_with_timeout(file_path, timeout_seconds = 30)
-  require 'timeout'
-
-  Timeout.timeout(timeout_seconds) do
-    Kreuzberg.extract_file_sync(file_path)
-  end
-rescue Timeout::Error
-  puts "Extraction timed out after #{timeout_seconds} seconds"
-  nil
-end
-
-# ============================================================================
-# Pattern 13: Custom Ruby PostProcessor Plugin
-# ============================================================================
-
-def register_postprocessor
-  uppercase_processor = lambda do |result|
-    result[:content] = result[:content].upcase
-    result
-  end
-
-  Kreuzberg.register_post_processor('uppercase', uppercase_processor, 100)
-
-  result = Kreuzberg.extract_file_sync('document.pdf')
-  puts "Uppercase content: #{result[:content]}"
-
-  Kreuzberg.unregister_post_processor('uppercase')
-end
-
-# ============================================================================
-# Pattern 14: Custom Ruby Validator Plugin
-# ============================================================================
-
-def register_validator
-  min_length_validator = lambda do |result|
-    raise 'Content too short' if result[:content].length < 100
-  end
-
-  Kreuzberg.register_validator('min_length', min_length_validator, 100)
-
-  begin
-    result = Kreuzberg.extract_file_sync('short_document.pdf')
-    puts "Validation passed: #{result[:content]}"
-  rescue StandardError => e
-    puts "Validation failed: #{e.message}"
-  end
-
-  Kreuzberg.unregister_validator('min_length')
-end
-
-# ============================================================================
-# Pattern 15: Custom Ruby OCR Backend Plugin
-# ============================================================================
-
-# Example OCR backend implementation for custom processing.
-def register_ocr_backend
-  backend = Class.new do
-    def process_image(image_bytes, language)
-      "Extracted text from #{image_bytes.length} bytes using #{language}"
-    end
-
-    def supports_language?(lang)
-      %w[eng deu fra].include?(lang)
-    end
-  end.new
-
-  Kreuzberg.register_ocr_backend('custom', backend)
-
-  config = {
-    ocr: {
-      backend: 'custom',
-      language: 'eng'
-    },
-    force_ocr: true
-  }
-
-  result = Kreuzberg.extract_file_sync('scanned.pdf', **config)
-  puts "Custom OCR result: #{result[:content]}"
-end
-
-# ============================================================================
-# Main Demonstration
-# ============================================================================
-
-def main
-  puts '=== Basic Sync Extraction ==='
-  basic_sync_extraction
-
-  puts '\n=== Basic Async Extraction (Blocks GVL) ==='
-  basic_async_extraction
-
-  puts '\n=== Concurrent with Ruby Threads ==='
-  concurrent_with_threads
-
-  puts '\n=== Batch Processing (Preferred) ==='
-  batch_processing
-
-  puts '\n=== Extraction with Config ==='
-  extraction_with_config
-
-  puts '\n=== Extract from Bytes ==='
-  extract_from_bytes
-
-  puts '\n=== Error Handling ==='
-  error_handling
-
-  puts '\n=== Sequential Processing ==='
-  sequential_processing
-
-  puts '\n=== Extraction with Timeout ==='
-  extraction_with_timeout('large_document.pdf', 30)
-
-  puts '\n=== Custom PostProcessor ==='
-  register_postprocessor
-
-  puts '\n=== Custom Validator ==='
-  register_validator
-end
-
-main if __FILE__ == $PROGRAM_NAME

data/extconf.rb

@@ -1,60 +0,0 @@
-# frozen_string_literal: true
-
-require 'mkmf'
-require 'rb_sys/mkmf'
-require 'rbconfig'
-require 'fileutils'
-
-if Gem.win_platform?
-  # Use CI-provided CARGO_TARGET_DIR if available, otherwise use a short path
-  # GitHub Actions sets CARGO_TARGET_DIR=C:\t for MAX_PATH mitigation
-  if ENV['CARGO_TARGET_DIR']
-    puts "Windows detected: Using existing CARGO_TARGET_DIR=#{ENV['CARGO_TARGET_DIR']}"
-  else
-    short_target_dir = Dir.exist?('C:/t') ? 'C:/t' : 'C:/kz-build'
-    begin
-      FileUtils.mkdir_p(short_target_dir)
-      ENV['CARGO_TARGET_DIR'] = short_target_dir
-      ENV['OUT_DIR'] = short_target_dir
-      puts "Windows detected: Using short build path #{short_target_dir}"
-    rescue StandardError => e
-      puts "Warning: Could not create short path #{short_target_dir}: #{e.message}"
-    end
-  end
-end
-
-if /mswin|mingw/.match?(RbConfig::CONFIG['host_os'])
-  devkit = ENV.fetch('RI_DEVKIT', nil)
-  prefix = ENV['MSYSTEM_PREFIX'] || '/ucrt64'
-
-  # Set up include paths for MSVC compatibility headers
-  native_include = File.expand_path('ext/kreuzberg_rb/native/include', __dir__).tr('\\', '/')
-  compat_include = File.expand_path('ext/kreuzberg_rb/native/include/msvc_compat', __dir__).tr('\\', '/')
-
-  extra_args = []
-  extra_args << "-I#{native_include}"
-  extra_args << "-I#{compat_include}"
-  extra_args << '-fms-extensions'
-  extra_args << '-fno-omit-frame-pointer'
-
-  if devkit
-    sysroot = "#{devkit}#{prefix}".tr('\\', '/')
-    extra_args.push('--target=x86_64-pc-windows-gnu', "--sysroot=#{sysroot}")
-  end
-
-  unless extra_args.empty?
-    existing = ENV['BINDGEN_EXTRA_CLANG_ARGS'].to_s.split(/\s+/).reject(&:empty?)
-    ENV['BINDGEN_EXTRA_CLANG_ARGS'] = (existing + extra_args).uniq.join(' ')
-    puts "BINDGEN_EXTRA_CLANG_ARGS set to: #{ENV.fetch('BINDGEN_EXTRA_CLANG_ARGS', nil)}"
-  end
-
-  # Set target for Windows GNU toolchain if not already set
-  ENV['CARGO_BUILD_TARGET'] ||= 'x86_64-pc-windows-gnu' if devkit || ENV['MSYSTEM']
-end
-
-default_profile = ENV.fetch('CARGO_PROFILE', 'release')
-
-create_rust_makefile('kreuzberg_rb') do |config|
-  config.profile = default_profile.to_sym
-  config.ext_dir = File.expand_path('ext/kreuzberg_rb/native', __dir__)
-end