kreuzberg 4.2.9 → 4.2.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1bdd32141526f545868c567acbc8e3a7caf94b4ff7e42bebf859fe33416669e4
-  data.tar.gz: 10da5a6da3a781b9676ba1213a535a69edde90b89ccad45489fab9fb593f5f73
+  metadata.gz: abf625c4f7eedb0ba24619d640ac572192a112bf29876c25c662c8faf8a7219c
+  data.tar.gz: 460cdf492f802db89332e989340070448c5b60bb44ce0860a1104889814bb9ac
 SHA512:
-  metadata.gz: e45428f1c646ed0683f51fa932c2432b0563d3258912fbe7b49f75acf0cdbc43c844c92b17cf7d4a5ddccb0b010d23cce4b20de950877fbe64ecafb858312bc5
-  data.tar.gz: f0abcd49fe46a4f0e3e2bf80e217ff36970b4a6037ecec6ea889230605a83178d76bff31d0960d50fb2ad4e1ea6f703c595bd43c244ff0e082ab365eb86bf02a
+  metadata.gz: 6e9b8b00347a73747e7ab8aad698f2d7a5798609dd1b086fe6df3a723c49bd05c5dff3c8ad0e7c83720cc3944b1a9d66fdec710405c9f1e22e43fe55387cdc92
+  data.tar.gz: dab907905f37a8fbc13d4c3e7e893cf6162fe57c6d735bfe08dfec32ea721706ab683d1baa4cfa6b0db4db8c393e7909ee3cf98195881ea31c8dc5ce0cda0b6a

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    kreuzberg (4.2.9)
+    kreuzberg (4.2.10)
       rb_sys (~> 0.9.119)
 
 GEM
@@ -46,7 +46,7 @@ GEM
     i18n (1.14.8)
       concurrent-ruby (~> 1.0)
     io-console (0.8.2)
-    json (2.18.0)
+    json (2.18.1)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
     listen (3.10.0)
@@ -75,12 +75,12 @@ GEM
     rake (13.3.1)
     rake-compiler (1.3.1)
       rake
-    rake-compiler-dock (1.10.0)
+    rake-compiler-dock (1.11.0)
     rb-fsevent (0.11.2)
     rb-inotify (0.11.1)
       ffi (~> 1.0)
-    rb_sys (0.9.119)
-      rake-compiler-dock (= 1.10.0)
+    rb_sys (0.9.124)
+      rake-compiler-dock (= 1.11.0)
     rbs (3.10.3)
       logger
       tsort
@@ -100,7 +100,7 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
     rspec-support (3.13.7)
-    rubocop (1.84.0)
+    rubocop (1.84.1)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
@@ -123,7 +123,7 @@ GEM
       rubocop (~> 1.81)
     ruby-progressbar (1.13.0)
     securerandom (0.4.1)
-    sorbet-runtime (0.6.12908)
+    sorbet-runtime (0.6.12914)
     steep (1.10.0)
       activesupport (>= 5.1)
       concurrent-ruby (>= 1.1.10)
@@ -208,8 +208,8 @@ CHECKSUMS
   fileutils (1.8.0) sha256=8c6b1df54e2540bdb2f39258f08af78853aa70bad52b4d394bbc6424593c6e02
   i18n (1.14.8) sha256=285778639134865c5e0f6269e0b818256017e8cde89993fdfcbfb64d088824a5
   io-console (0.8.2) sha256=d6e3ae7a7cc7574f4b8893b4fca2162e57a825b223a177b7afa236c5ef9814cc
-  json (2.18.0) sha256=b10506aee4183f5cf49e0efc48073d7b75843ce3782c68dbeb763351c08fd505
-  kreuzberg (4.2.9)
+  json (2.18.1) sha256=fe112755501b8d0466b5ada6cf50c8c3f41e897fa128ac5d263ec09eedc9f986
+  kreuzberg (4.2.10)
   language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
   lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
   listen (3.10.0) sha256=c6e182db62143aeccc2e1960033bebe7445309c7272061979bb098d03760c9d2
@@ -226,10 +226,10 @@ CHECKSUMS
   rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
   rake (13.3.1) sha256=8c9e89d09f66a26a01264e7e3480ec0607f0c497a861ef16063604b1b08eb19c
   rake-compiler (1.3.1) sha256=6b351612b6e2d73ddd5563ee799bb58685176e05363db6758504bd11573d670a
-  rake-compiler-dock (1.10.0) sha256=dd62ee19df2a185a3315697e560cfa8cc9129901332152851e023fab0e94bf11
+  rake-compiler-dock (1.11.0) sha256=eab51f2cd533eb35cea6b624a75281f047123e70a64c58b607471bb49428f8c2
   rb-fsevent (0.11.2) sha256=43900b972e7301d6570f64b850a5aa67833ee7d87b458ee92805d56b7318aefe
   rb-inotify (0.11.1) sha256=a0a700441239b0ff18eb65e3866236cd78613d6b9f78fea1f9ac47a85e47be6e
-  rb_sys (0.9.119) sha256=64393fa148e402e1b79b64496d2aabfc7df79da6b822b8bb48dc1141eaf40b4b
+  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
@@ -238,13 +238,13 @@ CHECKSUMS
   rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
   rspec-mocks (3.13.7) sha256=0979034e64b1d7a838aaaddf12bf065ea4dc40ef3d4c39f01f93ae2c66c62b1c
   rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
-  rubocop (1.84.0) sha256=88dec310153bb685a879f5a7cdb601f6287b8f0ee675d9dc63a17c7204c4190a
+  rubocop (1.84.1) sha256=14cc626f355141f5a2ef53c10a68d66b13bb30639b26370a76559096cc6bcc1a
   rubocop-ast (1.49.0) sha256=49c3676d3123a0923d333e20c6c2dbaaae2d2287b475273fddee0c61da9f71fd
   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 (0.6.12908) sha256=229f43e76527b01c5291c00c43cc29ccebe437a87b34925c3ee250ebf23d328e
+  sorbet-runtime (0.6.12914) sha256=6d3c985d671dab9ab8ea244b51888b6e8e8e65e881e5bf816d1ac0950479dce6
   steep (1.10.0) sha256=1b295b55f9aaff1b8d3ee42453ee55bc2a1078fda0268f288edb2dc014f4d7d1
   strscan (3.1.7) sha256=5f76462b94a3ea50b44973225b7d75b2cb96d4e1bee9ef1319b99ca117b72c8c
   terminal-table (4.0.0) sha256=f504793203f8251b2ea7c7068333053f0beeea26093ec9962e62ea79f94301d2

data/README.md

@@ -22,7 +22,7 @@
     <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
   </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.2.9" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.2.10" alt="Go">
   </a>
   <a href="https://www.nuget.org/packages/Kreuzberg/">
     <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">

data/ext/kreuzberg_rb/native/Cargo.toml

@@ -37,7 +37,7 @@ collapsible_if = "allow"
 
 [package]
 name = "kreuzberg-rb"
-version = "4.0.0"
+version = "4.2.10"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]

data/lib/kreuzberg/config.rb

@@ -71,7 +71,6 @@ module Kreuzberg
     class Chunking
       attr_reader :max_chars, :max_overlap, :preset, :embedding, :enabled
 
-      # rubocop:disable Metrics/CyclomaticComplexity
       def initialize(
         max_chars: nil,
         max_overlap: nil,
@@ -81,7 +80,6 @@ module Kreuzberg
         chunk_overlap: nil,
         enabled: true
       )
-        # rubocop:enable Metrics/CyclomaticComplexity
         resolved_size = chunk_size || max_chars || 1000
         resolved_overlap = chunk_overlap || max_overlap || 200
 
@@ -867,7 +865,6 @@ module Kreuzberg
               "Invalid result_format: #{value}. Valid values: #{VALID_RESULT_FORMATS.join(', ')}"
       end
 
-      # rubocop:disable Metrics/CyclomaticComplexity
       def to_h
         {
           use_cache: @use_cache,
@@ -888,7 +885,6 @@ module Kreuzberg
           result_format: @result_format
         }.compact
       end
-      # rubocop:enable Metrics/CyclomaticComplexity
 
       # Serialize configuration to JSON string
       #
@@ -992,7 +988,7 @@ module Kreuzberg
       #   config[:use_cache] = false
       #   config[:force_ocr] = true
       #
-      # rubocop:disable Metrics/CyclomaticComplexity, Metrics/MethodLength
+      # rubocop:disable Metrics/MethodLength
       def []=(key, value)
         key_sym = key.to_sym
         case key_sym
@@ -1032,7 +1028,7 @@ module Kreuzberg
           raise ArgumentError, "Unknown configuration key: #{key}"
         end
       end
-      # rubocop:enable Metrics/CyclomaticComplexity, Metrics/MethodLength
+      # rubocop:enable Metrics/MethodLength
 
       # Get a configuration field using hash-like syntax
       #

data/lib/kreuzberg/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Kreuzberg
-  VERSION = '4.2.9'
+  VERSION = '4.2.10'
 end

data/spec/binding/cache_spec.rb

@@ -4,10 +4,10 @@ require 'spec_helper'
 
 RSpec.describe 'Cache Management' do
   let(:test_pdf) do
-    test_document_path('pdfs/5_level_paging_and_5_level_ept_intel_revision_1_1_may_2017.pdf')
+    test_document_path('pdf/5_level_paging_and_5_level_ept_intel_revision_1_1_may_2017.pdf')
   end
   let(:test_text) { test_document_path('text/contract_test.txt') }
-  let(:test_docx) { test_document_path('documents/contract.docx') }
+  let(:test_docx) { test_document_path('docx/extraction_test.docx') }
 
   before do
     Kreuzberg.clear_cache

data/spec/binding/cli_spec.rb

@@ -3,7 +3,7 @@
 RSpec.describe Kreuzberg::CLI do
   describe '.extract' do
     it 'extracts content from a file' do
-      path = test_document_path('documents/simple.odt')
+      path = test_document_path('odt/simple.odt')
       output = described_class.extract(path)
 
       expect(output).to be_a(String)
@@ -11,7 +11,7 @@ RSpec.describe Kreuzberg::CLI do
     end
 
     it 'accepts output format option' do
-      path = test_document_path('documents/simple.odt')
+      path = test_document_path('odt/simple.odt')
       output = described_class.extract(path, output: 'json')
 
       expect(output).to be_a(String)
@@ -19,7 +19,7 @@ RSpec.describe Kreuzberg::CLI do
     end
 
     it 'accepts OCR option' do
-      path = test_document_path('pdfs/100_g_networking_technology_overview_slides_toronto_august_2016.pdf')
+      path = test_document_path('pdf/100_g_networking_technology_overview_slides_toronto_august_2016.pdf')
       output = described_class.extract(path, ocr: false)
 
       expect(output).to be_a(String)
@@ -29,7 +29,7 @@ RSpec.describe Kreuzberg::CLI do
 
   describe '.detect' do
     it 'detects MIME type' do
-      path = test_document_path('documents/simple.odt')
+      path = test_document_path('odt/simple.odt')
       mime_type = described_class.detect(path)
 
       expect(mime_type).to be_a(String)

data/spec/binding/images_spec.rb

@@ -108,7 +108,7 @@ RSpec.describe 'Image Extraction' do
       )
 
       begin
-        docx_path = test_document_path('office/document.docx')
+        docx_path = test_document_path('docx/extraction_test.docx')
         result = Kreuzberg.extract_file_sync(path: docx_path, config: config)
 
         expect(result).not_to be_nil
@@ -126,7 +126,7 @@ RSpec.describe 'Image Extraction' do
       )
 
       begin
-        pptx_path = test_document_path('presentations/simple.pptx')
+        pptx_path = test_document_path('pptx/simple.pptx')
         result = Kreuzberg.extract_file_sync(path: pptx_path, config: config)
 
         expect(result).not_to be_nil

data/spec/binding/metadata_types_spec.rb

@@ -959,7 +959,7 @@ RSpec.describe 'Kreuzberg Metadata Types' do
 
   describe 'Integration Test: Extract actual HTML file' do
     it 'extracts metadata from actual HTML file' do
-      html_file = test_document_path('web/html.html')
+      html_file = test_document_path('html/html.html')
 
       expect(File.exist?(html_file)).to be(true)
 

data/spec/binding/pages_extraction_spec.rb

@@ -3,7 +3,7 @@
 RSpec.describe 'Pages Extraction' do
   describe 'Extract Pages' do
     it 'returns pages array when extractPages is true' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -18,7 +18,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'returns page numbers for each page' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -34,7 +34,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'returns page content for each page' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -50,7 +50,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'returns nil for pages when extractPages is false' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -64,7 +64,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'preserves page order' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -83,7 +83,7 @@ RSpec.describe 'Pages Extraction' do
 
   describe 'Insert Page Markers' do
     it 'inserts page markers when insertPageMarkers is true' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -98,7 +98,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'does not insert markers when insertPageMarkers is false' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -113,7 +113,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'contains page numbers in markers' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -128,7 +128,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'inserts multiple markers for multi-page documents' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -145,7 +145,7 @@ RSpec.describe 'Pages Extraction' do
 
   describe 'Custom Marker Format' do
     it 'uses custom marker format when specified' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       custom_format = '=== PAGE {page_num} ==='
@@ -164,7 +164,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'replaces page_num placeholder in custom format' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       custom_format = '[Page Number: {page_num}]'
@@ -183,7 +183,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'handles simple custom format' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       custom_format = 'PAGE_{page_num}'
@@ -201,7 +201,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'handles custom format with line separators' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       custom_format = "\n---PAGE {page_num}---\n"
@@ -219,7 +219,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'overrides default marker format' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       custom_format = 'CUSTOM_PAGE_{page_num}'
@@ -239,7 +239,7 @@ RSpec.describe 'Pages Extraction' do
 
   describe 'Multi-Page PDF' do
     it 'produces multiple pages from multi-page PDF' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -253,7 +253,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page numbers are sequential' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -269,7 +269,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'each page has content' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -286,7 +286,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'with markers contains all pages' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -303,7 +303,7 @@ RSpec.describe 'Pages Extraction' do
 
   describe 'Page Content Structure Validation' do
     it 'validates page structure' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -320,7 +320,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page content has required fields' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -337,7 +337,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page content with tables preserves table data' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -354,7 +354,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page content with images preserves image data' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -371,7 +371,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page content is not empty' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -388,7 +388,7 @@ RSpec.describe 'Pages Extraction' do
 
   describe 'Combined Features' do
     it 'extract pages and insert markers together' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -407,7 +407,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'extract pages with custom marker format' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(
@@ -426,7 +426,7 @@ RSpec.describe 'Pages Extraction' do
     end
 
     it 'page extraction consistency between array and markers' do
-      pdf_file = test_document_path('pdf/sample.pdf')
+      pdf_file = test_document_path('pdf/sample_contract.pdf')
       skip "Test PDF not available at #{pdf_file}" unless File.exist?(pdf_file)
 
       config = Kreuzberg::Config::Extraction.new(

data/spec/binding/tables_spec.rb

@@ -246,7 +246,7 @@ RSpec.describe 'Table Extraction Quality' do
       config = Kreuzberg::Config::Extraction.new
 
       begin
-        result = Kreuzberg.extract_file(path: test_document_path('office/document.docx'), config: config)
+        result = Kreuzberg.extract_file(path: test_document_path('docx/extraction_test.docx'), config: config)
         expect(result).not_to be_nil
       rescue Kreuzberg::Errors::ValidationError
         skip 'DOCX test file not available'

data/vendor/Cargo.toml

@@ -3,7 +3,7 @@ members = ["kreuzberg", "kreuzberg-tesseract", "kreuzberg-ffi"]
 resolver = "2"
 
 [workspace.package]
-version = "4.2.9"
+version = "4.2.10"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]

data/vendor/kreuzberg/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "kreuzberg"
-version = "4.2.9"
+version = "4.2.10"
 edition = "2024"
 rust-version = "1.91"
 authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
@@ -133,7 +133,7 @@ once_cell = { workspace = true }
 parking_lot = { workspace = true }
 pastey = "0.2"
 rayon = "1.11.0"
-regex = "1.12.2"
+regex = "1.12.3"
 serde = { workspace = true }
 serde_json = { workspace = true }
 serde_yaml_ng = "0.10.0"

data/vendor/kreuzberg/README.md

@@ -17,7 +17,7 @@ High-performance document intelligence library for Rust. Extract text, metadata,
 
 This is the core Rust library that powers the Python, TypeScript, and Ruby bindings.
 
-> **🚀 Version 4.2.9 Release**
+> **🚀 Version 4.2.10 Release**
 > This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/kreuzberg-dev/kreuzberg/issues) you encounter.
 >
 > **Note**: The Rust crate is not currently published to crates.io for this RC. Use git dependencies or language bindings (Python, TypeScript, Ruby) instead.

data/vendor/kreuzberg/examples/bench_fixes.rs

@@ -5,14 +5,11 @@ use std::time::Instant;
 fn main() -> Result<(), Box<dyn std::error::Error>> {
     let test_pdfs = [
         (
-            "a_comprehensive_study_of_convergent_and_commutative_replicated_data_types.pdf",
+            "a_comprehensive_stud_large_acomprehensives.pdf",
             "Academic Paper (18 fonts)",
         ),
-        (
-            "5_level_paging_and_5_level_ept_intel_revision_1_1_may_2017.pdf",
-            "Intel PDF (5 fonts)",
-        ),
-        ("fake_memo.pdf", "Tiny Memo (3-5 fonts)"),
+        ("5_level_paging_and_5_medium_5levelpagingand.pdf", "Intel PDF (5 fonts)"),
+        ("simple_small_fakememo.pdf", "Tiny Memo (3-5 fonts)"),
     ];
 
     let config = ExtractionConfig {
@@ -24,7 +21,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
     println!("Testing warm execution fix and font overhead fix\n");
 
     for (file, description) in &test_pdfs {
-        let path = PathBuf::from(format!("test_documents/pdfs/{}", file));
+        let path = PathBuf::from(format!("test_documents/pdf/{}", file));
         println!("=== {} ===", description);
         println!("File: {}\n", file);
 

data/vendor/kreuzberg/examples/test_pdfium_fork.rs

@@ -12,7 +12,7 @@ async fn main() {
 
     println!("Test 1: fake_memo.pdf");
     let start = Instant::now();
-    match extract_file("test_documents/pdfs/fake_memo.pdf", None, &config).await {
+    match extract_file("test_documents/pdf/fake_memo.pdf", None, &config).await {
         Ok(result) => {
             let duration = start.elapsed();
             println!("  ✓ Success! Duration: {:?}", duration);
@@ -26,7 +26,7 @@ async fn main() {
 
     println!("\nTest 2: Warm iteration");
     let start = Instant::now();
-    match extract_file("test_documents/pdfs/fake_memo.pdf", None, &config).await {
+    match extract_file("test_documents/pdf/fake_memo.pdf", None, &config).await {
         Ok(result) => {
             let duration = start.elapsed();
             println!("  ✓ Success! Duration: {:?}", duration);
@@ -41,7 +41,7 @@ async fn main() {
     println!("\nTest 3: Academic Paper (18 fonts)");
     let start = Instant::now();
     match extract_file(
-        "test_documents/pdfs/a_comprehensive_study_of_convergent_and_commutative_replicated_data_types.pdf",
+        "test_documents/pdf/a_comprehensive_study_of_convergent_and_commutative_replicated_data_types.pdf",
         None,
         &config,
     )