kreuzberg 4.0.0.pre.rc.6

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9fc516b53481da9460a558cdfd860a53274d43091d8f750d76250e32059758be
+  data.tar.gz: 886d27a343998685e302d771e3e517d0ed23620fba52fd9412c0d780f8034580
+SHA512:
+  metadata.gz: 22ffa8ab5ec78709a6b09927a21ae5ef08fc8c24cccfe94a14a54f47fa087935fb84c80719bc6a00266210178d453baaa798961fd00b91bbd484d20f4f73ddd8
+  data.tar.gz: 859ae29e4fc31def124754482f018d022580e7f4ef7a1a7662dab5a57d8a7620c0de77a218c39ff033f30af2272961fd1cc9f6460690553d7a266b9916816828

data/.gitignore

@@ -0,0 +1,14 @@
+tmp/
+lib/*.bundle
+lib/*.dylib
+lib/*.so
+lib/*.dll
+lib/*.dylib
+lib/*.so
+lib/*.dll
+
+# Vendor directory for local development (symlink to ../../crates/kreuzberg)
+# In CI, this is replaced by the actual vendored crate files
+# Exception: vendor/rb-sys is patched and committed
+!vendor/rb-sys/
+vendor/

data/.rspec

@@ -0,0 +1,3 @@
+--require spec_helper
+--format documentation
+--color

data/.rubocop.yaml

@@ -0,0 +1 @@
+inherit_from: .rubocop.yml

data/.rubocop.yml

@@ -0,0 +1,538 @@
+
+plugins:
+  - rubocop-performance
+  - rubocop-rspec
+
+AllCops:
+  TargetRubyVersion: 3.2
+  NewCops: enable
+  SuggestExtensions: false
+  Exclude:
+    - 'vendor/**/*'
+    - 'tmp/**/*'
+    - 'lib/**/*.bundle'
+    - 'ext/**/*'
+
+Style/StringLiterals:
+  Enabled: true
+  EnforcedStyle: single_quotes
+
+Style/StringLiteralsInInterpolation:
+  Enabled: true
+  EnforcedStyle: single_quotes
+
+Style/FrozenStringLiteralComment:
+  Enabled: true
+  EnforcedStyle: always
+
+Style/Documentation:
+  Enabled: false
+
+Layout/LineLength:
+  Max: 120
+  AllowedPatterns:
+    - '\A\s*#'
+  Exclude:
+    - 'spec/**/*'
+
+Metrics/BlockLength:
+  Enabled: true
+  Max: 350
+  CountComments: false
+  CountAsOne: []
+
+Metrics/MethodLength:
+  Max: 18
+  Exclude:
+    - 'spec/**/*'
+    - 'examples/**/*'
+
+Metrics/AbcSize:
+  Max: 20
+  Exclude:
+    - 'spec/**/*'
+    - 'examples/**/*'
+
+Naming/FileName:
+  Enabled: true
+  Exclude:
+    - 'Gemfile'
+    - 'Rakefile'
+
+RSpec/SpecFilePathFormat:
+  Enabled: false
+RSpec/SpecFilePathSuffix:
+  Enabled: false
+
+RSpec/PendingWithoutReason:
+  Enabled: false
+
+RSpec/LeakyConstantDeclaration:
+  Enabled: false
+
+RSpec/UnspecifiedException:
+  Enabled: false
+
+Lint/ConstantDefinitionInBlock:
+  Enabled: false
+  Exclude:
+    - 'spec/**/*'
+
+RSpec/InstanceVariable:
+  Enabled: false
+
+Gemspec/DevelopmentDependencies:
+  Enabled: false
+
+Metrics/ParameterLists:
+  Max: 14
+  Exclude:
+    - 'lib/kreuzberg/config.rb'
+
+Metrics/CyclomaticComplexity:
+  Max: 7
+  Exclude:
+    - 'lib/kreuzberg/config.rb'
+
+Metrics/PerceivedComplexity:
+  Max: 12
+  Exclude:
+    - 'lib/kreuzberg/config.rb'
+
+RSpec/RepeatedExampleGroupBody:
+  Enabled: false
+
+RSpec/DescribeClass:
+  Enabled: false
+
+RSpec/PredicateMatcher:
+  Enabled: false
+
+Gemspec/AddRuntimeDependency:
+  Enabled: true
+
+Gemspec/AttributeAssignment:
+  Enabled: true
+
+Gemspec/DeprecatedAttributeAssignment:
+  Enabled: true
+
+Gemspec/RequireMFA:
+  Enabled: false
+
+Layout/EmptyLinesAfterModuleInclusion:
+  Enabled: true
+
+Layout/LineContinuationLeadingSpace:
+  Enabled: true
+
+Layout/LineContinuationSpacing:
+  Enabled: true
+
+Layout/LineEndStringConcatenationIndentation:
+  Enabled: true
+
+Layout/SpaceBeforeBrackets:
+  Enabled: true
+
+Lint/AmbiguousAssignment:
+  Enabled: true
+
+Lint/AmbiguousOperatorPrecedence:
+  Enabled: true
+
+Lint/AmbiguousRange:
+  Enabled: true
+
+Lint/ArrayLiteralInRegexp:
+  Enabled: true
+
+Lint/ConstantOverwrittenInRescue:
+  Enabled: true
+
+Lint/ConstantReassignment:
+  Enabled: true
+
+Lint/CopDirectiveSyntax:
+  Enabled: true
+
+Lint/DeprecatedConstants:
+  Enabled: true
+
+Lint/DuplicateBranch:
+  Enabled: true
+
+Lint/DuplicateMagicComment:
+  Enabled: true
+
+Lint/DuplicateMatchPattern:
+  Enabled: true
+
+Lint/DuplicateRegexpCharacterClassElement:
+  Enabled: true
+
+Lint/DuplicateSetElement:
+  Enabled: true
+
+Lint/EmptyBlock:
+  Enabled: true
+
+Lint/EmptyClass:
+  Enabled: true
+
+Lint/EmptyInPattern:
+  Enabled: true
+
+Lint/HashNewWithKeywordArgumentsAsDefault:
+  Enabled: true
+
+Lint/IncompatibleIoSelectWithFiberScheduler:
+  Enabled: true
+
+Lint/ItWithoutArgumentsInBlock:
+  Enabled: true
+
+Lint/LambdaWithoutLiteralBlock:
+  Enabled: true
+
+Lint/LiteralAssignmentInCondition:
+  Enabled: true
+
+Lint/MixedCaseRange:
+  Enabled: true
+
+Lint/NoReturnInBeginEndBlocks:
+  Enabled: true
+
+Lint/NonAtomicFileOperation:
+  Enabled: true
+
+Lint/NumberedParameterAssignment:
+  Enabled: true
+
+Lint/NumericOperationWithConstantResult:
+  Enabled: true
+
+Lint/OrAssignmentToConstant:
+  Enabled: true
+
+Lint/RedundantDirGlobSort:
+  Enabled: true
+
+Lint/RedundantRegexpQuantifiers:
+  Enabled: true
+
+Lint/RedundantTypeConversion:
+  Enabled: true
+
+Lint/RefinementImportMethods:
+  Enabled: true
+
+Lint/RequireRangeParentheses:
+  Enabled: true
+
+Lint/RequireRelativeSelfPath:
+  Enabled: true
+
+Lint/SharedMutableDefault:
+  Enabled: true
+
+Lint/SuppressedExceptionInNumberConversion:
+  Enabled: true
+
+Lint/SymbolConversion:
+  Enabled: true
+
+Lint/ToEnumArguments:
+  Enabled: true
+
+Lint/TripleQuotes:
+  Enabled: true
+
+Lint/UnescapedBracketInRegexp:
+  Enabled: true
+
+Lint/UnexpectedBlockArity:
+  Enabled: true
+
+Lint/UnmodifiedReduceAccumulator:
+  Enabled: true
+
+Lint/UselessConstantScoping:
+  Enabled: true
+
+Lint/UselessDefaultValueArgument:
+  Enabled: true
+
+Lint/UselessDefined:
+  Enabled: true
+
+Lint/UselessNumericOperation:
+  Enabled: true
+
+Lint/UselessOr:
+  Enabled: true
+
+Lint/UselessRescue:
+  Enabled: true
+
+Lint/UselessRuby2Keywords:
+  Enabled: true
+
+Metrics/CollectionLiteralLength:
+  Enabled: true
+
+Naming/BlockForwarding:
+  Enabled: true
+
+Naming/PredicateMethod:
+  Enabled: true
+
+Security/CompoundHash:
+  Enabled: true
+
+Security/IoMethods:
+  Enabled: true
+
+Style/AmbiguousEndlessMethodDefinition:
+  Enabled: true
+
+Style/ArgumentsForwarding:
+  Enabled: true
+
+Style/ArrayIntersect:
+  Enabled: true
+
+Style/ArrayIntersectWithSingleElement:
+  Enabled: true
+
+Style/BitwisePredicate:
+  Enabled: true
+
+Style/CollectionCompact:
+  Enabled: true
+
+Style/CollectionQuerying:
+  Enabled: true
+
+Style/CombinableDefined:
+  Enabled: true
+
+Style/ComparableBetween:
+  Enabled: true
+
+Style/ComparableClamp:
+  Enabled: true
+
+Style/ConcatArrayLiterals:
+  Enabled: true
+
+Style/DataInheritance:
+  Enabled: true
+
+Style/DigChain:
+  Enabled: true
+
+Style/DirEmpty:
+  Enabled: true
+
+Style/DocumentDynamicEvalDefinition:
+  Enabled: true
+
+Style/EmptyHeredoc:
+  Enabled: true
+
+Style/EmptyStringInsideInterpolation:
+  Enabled: true
+
+Style/EndlessMethod:
+  Enabled: true
+
+Style/EnvHome:
+  Enabled: true
+
+Style/ExactRegexpMatch:
+  Enabled: true
+
+Style/FetchEnvVar:
+  Enabled: true
+
+Style/FileEmpty:
+  Enabled: true
+
+Style/FileNull:
+  Enabled: true
+
+Style/FileRead:
+  Enabled: true
+
+Style/FileTouch:
+  Enabled: true
+
+Style/FileWrite:
+  Enabled: true
+
+Style/HashConversion:
+  Enabled: true
+
+Style/HashExcept:
+  Enabled: true
+
+Style/HashFetchChain:
+  Enabled: true
+
+Style/HashSlice:
+  Enabled: true
+
+Style/IfWithBooleanLiteralBranches:
+  Enabled: true
+
+Style/InPatternThen:
+  Enabled: true
+
+Style/ItAssignment:
+  Enabled: true
+
+Style/ItBlockParameter:
+  Enabled: true
+
+Style/KeywordArgumentsMerging:
+  Enabled: true
+
+Style/MagicCommentFormat:
+  Enabled: true
+
+Style/MapCompactWithConditionalBlock:
+  Enabled: true
+
+Style/MapIntoArray:
+  Enabled: true
+
+Style/MapToHash:
+  Enabled: true
+
+Style/MapToSet:
+  Enabled: true
+
+Style/MinMaxComparison:
+  Enabled: true
+
+Style/MultilineInPatternThen:
+  Enabled: true
+
+Style/NegatedIfElseCondition:
+  Enabled: true
+
+Style/NestedFileDirname:
+  Enabled: true
+
+Style/NilLambda:
+  Enabled: true
+
+Style/NumberedParameters:
+  Enabled: true
+
+Style/NumberedParametersLimit:
+  Enabled: true
+
+Style/ObjectThen:
+  Enabled: true
+
+Style/OpenStructUse:
+  Enabled: true
+
+Style/OperatorMethodCall:
+  Enabled: true
+
+Style/QuotedSymbols:
+  Enabled: true
+
+Style/RedundantArgument:
+  Enabled: true
+
+Style/RedundantArrayConstructor:
+  Enabled: true
+
+Style/RedundantArrayFlatten:
+  Enabled: true
+
+Style/RedundantConstantBase:
+  Enabled: true
+
+Style/RedundantCurrentDirectoryInPath:
+  Enabled: true
+
+Style/RedundantDoubleSplatHashBraces:
+  Enabled: true
+
+Style/RedundantEach:
+  Enabled: true
+
+Style/RedundantFilterChain:
+  Enabled: true
+
+Style/RedundantFormat:
+  Enabled: true
+
+Style/RedundantHeredocDelimiterQuotes:
+  Enabled: true
+
+Style/RedundantInitialize:
+  Enabled: true
+
+Style/RedundantInterpolationUnfreeze:
+  Enabled: true
+
+Style/RedundantLineContinuation:
+  Enabled: true
+
+Style/RedundantRegexpArgument:
+  Enabled: true
+
+Style/RedundantRegexpConstructor:
+  Enabled: true
+
+Style/RedundantSelfAssignmentBranch:
+  Enabled: true
+
+Style/RedundantStringEscape:
+  Enabled: true
+
+Style/ReturnNilInPredicateMethodDefinition:
+  Enabled: true
+
+Style/SafeNavigationChainLength:
+  Enabled: true
+
+Style/SelectByRegexp:
+  Enabled: true
+
+Style/SendWithLiteralMethodName:
+  Enabled: true
+
+Style/SingleLineDoEndBlock:
+  Enabled: true
+
+Style/StringChars:
+  Enabled: true
+
+Style/SuperArguments:
+  Enabled: true
+
+Style/SuperWithArgsParentheses:
+  Enabled: true
+
+Style/SwapValues:
+  Enabled: true
+
+Style/YAMLFileRead:
+  Enabled: true
+
+RSpec/ExampleLength:
+  Max: 35
+
+RSpec/MultipleExpectations:
+  Max: 15
+
+RSpec/NestedGroups:
+  Max: 6

data/Gemfile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+gemspec
+
+gem 'pry', '~> 0.14', group: :development
+gem 'pry-byebug', '~> 3.10', group: :development, platforms: %i[ruby mri]

data/Gemfile.lock

@@ -0,0 +1,157 @@
+PATH
+  remote: .
+  specs:
+    kreuzberg (4.0.0.pre.rc.6)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (8.1.1)
+      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)
+    ast (2.4.3)
+    base64 (0.3.0)
+    bigdecimal (3.3.1)
+    byebug (12.0.0)
+    coderay (1.1.3)
+    concurrent-ruby (1.3.5)
+    connection_pool (3.0.2)
+    csv (3.3.5)
+    diff-lcs (1.6.2)
+    drb (2.2.3)
+    ffi (1.17.2)
+    ffi (1.17.2-arm64-darwin)
+    fileutils (1.8.0)
+    i18n (1.14.7)
+      concurrent-ruby (~> 1.0)
+    json (2.17.1)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    listen (3.9.0)
+      rb-fsevent (~> 0.10, >= 0.10.3)
+      rb-inotify (~> 0.9, >= 0.9.10)
+    logger (1.7.0)
+    method_source (1.1.0)
+    minitest (5.26.2)
+    mutex_m (0.3.0)
+    parallel (1.27.0)
+    parser (3.3.10.0)
+      ast (~> 2.4.1)
+      racc
+    prism (1.6.0)
+    pry (0.15.2)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    pry-byebug (3.11.0)
+      byebug (~> 12.0)
+      pry (>= 0.13, < 0.16)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    rake (13.3.1)
+    rake-compiler (1.3.0)
+      rake
+    rake-compiler-dock (1.10.0)
+    rb-fsevent (0.11.2)
+    rb-inotify (0.11.1)
+      ffi (~> 1.0)
+    rb_sys (0.9.119)
+      rake-compiler-dock (= 1.10.0)
+    rbs (3.9.5)
+      logger
+    regexp_parser (2.11.3)
+    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 (3.13.7)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.6)
+    rubocop (1.81.7)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.47.1, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.48.0)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    rubocop-performance (1.26.1)
+      lint_roller (~> 1.1)
+      rubocop (>= 1.75.0, < 2.0)
+      rubocop-ast (>= 1.47.1, < 2.0)
+    rubocop-rspec (3.8.0)
+      lint_roller (~> 1.1)
+      rubocop (~> 1.81)
+    ruby-progressbar (1.13.0)
+    securerandom (0.4.1)
+    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 (3.1.5)
+    terminal-table (4.0.0)
+      unicode-display_width (>= 1.1.1, < 4)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (3.2.0)
+      unicode-emoji (~> 4.1)
+    unicode-emoji (4.1.0)
+    uri (1.1.1)
+    yard (0.9.38)
+
+PLATFORMS
+  arm64-darwin-23
+  arm64-darwin-24
+
+DEPENDENCIES
+  bundler (~> 4.0)
+  kreuzberg!
+  pry (~> 0.14)
+  pry-byebug (~> 3.10)
+  rake (~> 13.0)
+  rake-compiler (~> 1.2)
+  rb_sys (~> 0.9.119)
+  rbs (~> 3.0)
+  rspec (~> 3.12)
+  rubocop (~> 1.66)
+  rubocop-performance (~> 1.21)
+  rubocop-rspec (~> 3.0)
+  steep (~> 1.8)
+  yard (~> 0.9)
+
+BUNDLED WITH
+  4.0.0