kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitignore +0 -6
- data/.rubocop.yaml +534 -1
- data/Gemfile +2 -1
- data/Gemfile.lock +28 -116
- data/README.md +269 -629
- data/Rakefile +0 -9
- data/Steepfile +4 -8
- data/examples/async_patterns.rb +58 -1
- data/ext/kreuzberg_rb/extconf.rb +5 -35
- data/ext/kreuzberg_rb/native/Cargo.toml +16 -55
- data/ext/kreuzberg_rb/native/build.rs +14 -12
- data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
- data/ext/kreuzberg_rb/native/include/strings.h +2 -2
- data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
- data/ext/kreuzberg_rb/native/src/lib.rs +34 -897
- data/extconf.rb +6 -38
- data/kreuzberg.gemspec +20 -114
- data/lib/kreuzberg/api_proxy.rb +18 -2
- data/lib/kreuzberg/cache_api.rb +0 -22
- data/lib/kreuzberg/cli.rb +10 -2
- data/lib/kreuzberg/cli_proxy.rb +10 -0
- data/lib/kreuzberg/config.rb +22 -274
- data/lib/kreuzberg/errors.rb +7 -73
- data/lib/kreuzberg/extraction_api.rb +8 -237
- data/lib/kreuzberg/mcp_proxy.rb +11 -2
- data/lib/kreuzberg/ocr_backend_protocol.rb +73 -0
- data/lib/kreuzberg/post_processor_protocol.rb +71 -0
- data/lib/kreuzberg/result.rb +33 -151
- data/lib/kreuzberg/setup_lib_path.rb +2 -22
- data/lib/kreuzberg/validator_protocol.rb +73 -0
- data/lib/kreuzberg/version.rb +1 -1
- data/lib/kreuzberg.rb +13 -27
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg.rbs +12 -105
- data/spec/binding/cache_spec.rb +22 -22
- data/spec/binding/cli_proxy_spec.rb +4 -2
- data/spec/binding/cli_spec.rb +11 -12
- data/spec/binding/config_spec.rb +0 -74
- data/spec/binding/config_validation_spec.rb +6 -100
- data/spec/binding/error_handling_spec.rb +97 -283
- data/spec/binding/plugins/ocr_backend_spec.rb +8 -8
- data/spec/binding/plugins/postprocessor_spec.rb +11 -11
- data/spec/binding/plugins/validator_spec.rb +13 -12
- data/spec/examples.txt +104 -0
- data/spec/fixtures/config.toml +1 -0
- data/spec/fixtures/config.yaml +1 -0
- data/spec/fixtures/invalid_config.toml +1 -0
- data/spec/smoke/package_spec.rb +3 -2
- data/spec/spec_helper.rb +3 -1
- data/vendor/kreuzberg/Cargo.toml +67 -192
- data/vendor/kreuzberg/README.md +9 -97
- data/vendor/kreuzberg/build.rs +194 -516
- data/vendor/kreuzberg/src/api/handlers.rs +9 -130
- data/vendor/kreuzberg/src/api/mod.rs +3 -18
- data/vendor/kreuzberg/src/api/server.rs +71 -236
- data/vendor/kreuzberg/src/api/types.rs +7 -43
- data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +3 -27
- data/vendor/kreuzberg/src/chunking/mod.rs +79 -1705
- data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
- data/vendor/kreuzberg/src/core/config.rs +23 -905
- data/vendor/kreuzberg/src/core/extractor.rs +106 -403
- data/vendor/kreuzberg/src/core/io.rs +2 -4
- data/vendor/kreuzberg/src/core/mime.rs +12 -2
- data/vendor/kreuzberg/src/core/mod.rs +3 -22
- data/vendor/kreuzberg/src/core/pipeline.rs +78 -395
- data/vendor/kreuzberg/src/embeddings.rs +21 -169
- data/vendor/kreuzberg/src/error.rs +2 -2
- data/vendor/kreuzberg/src/extraction/archive.rs +31 -36
- data/vendor/kreuzberg/src/extraction/docx.rs +1 -365
- data/vendor/kreuzberg/src/extraction/email.rs +11 -12
- data/vendor/kreuzberg/src/extraction/excel.rs +129 -138
- data/vendor/kreuzberg/src/extraction/html.rs +170 -1447
- data/vendor/kreuzberg/src/extraction/image.rs +14 -138
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +3 -13
- data/vendor/kreuzberg/src/extraction/mod.rs +5 -21
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +94 -196
- data/vendor/kreuzberg/src/extraction/structured.rs +4 -5
- data/vendor/kreuzberg/src/extraction/table.rs +1 -2
- data/vendor/kreuzberg/src/extraction/text.rs +10 -18
- data/vendor/kreuzberg/src/extractors/archive.rs +0 -22
- data/vendor/kreuzberg/src/extractors/docx.rs +148 -69
- data/vendor/kreuzberg/src/extractors/email.rs +9 -37
- data/vendor/kreuzberg/src/extractors/excel.rs +40 -81
- data/vendor/kreuzberg/src/extractors/html.rs +173 -182
- data/vendor/kreuzberg/src/extractors/image.rs +8 -32
- data/vendor/kreuzberg/src/extractors/mod.rs +10 -171
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +64 -329
- data/vendor/kreuzberg/src/extractors/pptx.rs +34 -79
- data/vendor/kreuzberg/src/extractors/structured.rs +0 -16
- data/vendor/kreuzberg/src/extractors/text.rs +7 -30
- data/vendor/kreuzberg/src/extractors/xml.rs +8 -27
- data/vendor/kreuzberg/src/keywords/processor.rs +1 -9
- data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
- data/vendor/kreuzberg/src/language_detection/mod.rs +51 -94
- data/vendor/kreuzberg/src/lib.rs +5 -17
- data/vendor/kreuzberg/src/mcp/mod.rs +1 -4
- data/vendor/kreuzberg/src/mcp/server.rs +21 -145
- data/vendor/kreuzberg/src/ocr/mod.rs +0 -2
- data/vendor/kreuzberg/src/ocr/processor.rs +8 -19
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -2
- data/vendor/kreuzberg/src/pdf/error.rs +1 -93
- data/vendor/kreuzberg/src/pdf/metadata.rs +100 -263
- data/vendor/kreuzberg/src/pdf/mod.rs +2 -33
- data/vendor/kreuzberg/src/pdf/rendering.rs +12 -12
- data/vendor/kreuzberg/src/pdf/table.rs +64 -61
- data/vendor/kreuzberg/src/pdf/text.rs +24 -416
- data/vendor/kreuzberg/src/plugins/extractor.rs +8 -40
- data/vendor/kreuzberg/src/plugins/mod.rs +0 -3
- data/vendor/kreuzberg/src/plugins/ocr.rs +14 -22
- data/vendor/kreuzberg/src/plugins/processor.rs +1 -10
- data/vendor/kreuzberg/src/plugins/registry.rs +0 -15
- data/vendor/kreuzberg/src/plugins/validator.rs +8 -20
- data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
- data/vendor/kreuzberg/src/text/mod.rs +0 -8
- data/vendor/kreuzberg/src/text/quality.rs +15 -28
- data/vendor/kreuzberg/src/text/string_utils.rs +10 -22
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +50 -86
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +16 -37
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +1 -2
- data/vendor/kreuzberg/src/types.rs +67 -907
- data/vendor/kreuzberg/src/utils/mod.rs +0 -14
- data/vendor/kreuzberg/src/utils/quality.rs +3 -12
- data/vendor/kreuzberg/tests/api_tests.rs +0 -506
- data/vendor/kreuzberg/tests/archive_integration.rs +0 -2
- data/vendor/kreuzberg/tests/batch_orchestration.rs +12 -57
- data/vendor/kreuzberg/tests/batch_processing.rs +8 -32
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +8 -40
- data/vendor/kreuzberg/tests/config_features.rs +1 -33
- data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -16
- data/vendor/kreuzberg/tests/core_integration.rs +9 -35
- data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
- data/vendor/kreuzberg/tests/email_integration.rs +1 -3
- data/vendor/kreuzberg/tests/error_handling.rs +34 -43
- data/vendor/kreuzberg/tests/format_integration.rs +1 -7
- data/vendor/kreuzberg/tests/helpers/mod.rs +0 -60
- data/vendor/kreuzberg/tests/image_integration.rs +0 -2
- data/vendor/kreuzberg/tests/mime_detection.rs +16 -17
- data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -4
- data/vendor/kreuzberg/tests/ocr_errors.rs +0 -22
- data/vendor/kreuzberg/tests/ocr_quality.rs +0 -2
- data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +0 -2
- data/vendor/kreuzberg/tests/pipeline_integration.rs +2 -36
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -5
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -17
- data/vendor/kreuzberg/tests/plugin_system.rs +0 -6
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -2
- data/vendor/kreuzberg/tests/security_validation.rs +1 -13
- data/vendor/kreuzberg/tests/test_fastembed.rs +23 -45
- metadata +25 -171
- data/.rubocop.yml +0 -543
- data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -23
- data/ext/kreuzberg_rb/native/Cargo.lock +0 -7619
- data/lib/kreuzberg/error_context.rb +0 -136
- data/lib/kreuzberg/types.rb +0 -170
- data/lib/libpdfium.so +0 -0
- data/spec/binding/async_operations_spec.rb +0 -473
- data/spec/binding/batch_operations_spec.rb +0 -595
- data/spec/binding/batch_spec.rb +0 -359
- data/spec/binding/config_result_spec.rb +0 -377
- data/spec/binding/embeddings_spec.rb +0 -816
- data/spec/binding/error_recovery_spec.rb +0 -488
- data/spec/binding/font_config_spec.rb +0 -220
- data/spec/binding/images_spec.rb +0 -738
- data/spec/binding/keywords_extraction_spec.rb +0 -600
- data/spec/binding/metadata_types_spec.rb +0 -1228
- data/spec/binding/pages_extraction_spec.rb +0 -471
- data/spec/binding/tables_spec.rb +0 -641
- data/spec/unit/config/chunking_config_spec.rb +0 -213
- data/spec/unit/config/embedding_config_spec.rb +0 -343
- data/spec/unit/config/extraction_config_spec.rb +0 -438
- data/spec/unit/config/font_config_spec.rb +0 -285
- data/spec/unit/config/hierarchy_config_spec.rb +0 -314
- data/spec/unit/config/image_extraction_config_spec.rb +0 -209
- data/spec/unit/config/image_preprocessing_config_spec.rb +0 -249
- data/spec/unit/config/keyword_config_spec.rb +0 -229
- data/spec/unit/config/language_detection_config_spec.rb +0 -258
- data/spec/unit/config/ocr_config_spec.rb +0 -171
- data/spec/unit/config/page_config_spec.rb +0 -221
- data/spec/unit/config/pdf_config_spec.rb +0 -267
- data/spec/unit/config/postprocessor_config_spec.rb +0 -290
- data/spec/unit/config/tesseract_config_spec.rb +0 -181
- data/spec/unit/config/token_reduction_config_spec.rb +0 -251
- data/test/metadata_types_test.rb +0 -959
- data/vendor/Cargo.toml +0 -61
- data/vendor/kreuzberg/examples/bench_fixes.rs +0 -71
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +0 -62
- data/vendor/kreuzberg/src/chunking/processor.rs +0 -219
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -385
- data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
- data/vendor/kreuzberg/src/core/formats.rs +0 -235
- data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
- data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
- data/vendor/kreuzberg/src/extraction/markdown.rs +0 -216
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -284
- data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -470
- data/vendor/kreuzberg/src/extractors/docbook.rs +0 -504
- data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -492
- data/vendor/kreuzberg/src/extractors/jats.rs +0 -1054
- data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -368
- data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
- data/vendor/kreuzberg/src/extractors/markdown.rs +0 -701
- data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
- data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -529
- data/vendor/kreuzberg/src/extractors/rst.rs +0 -577
- data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
- data/vendor/kreuzberg/src/extractors/security.rs +0 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
- data/vendor/kreuzberg/src/extractors/typst.rs +0 -651
- data/vendor/kreuzberg/src/language_detection/processor.rs +0 -218
- data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -520
- data/vendor/kreuzberg/src/panic_context.rs +0 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +0 -306
- data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
- data/vendor/kreuzberg/src/pdf/fonts.rs +0 -358
- data/vendor/kreuzberg/src/pdf/hierarchy.rs +0 -903
- data/vendor/kreuzberg/src/text/quality_processor.rs +0 -231
- data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
- data/vendor/kreuzberg/src/utils/pool.rs +0 -503
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
- data/vendor/kreuzberg/src/utils/string_pool.rs +0 -761
- data/vendor/kreuzberg/tests/api_embed.rs +0 -360
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +0 -471
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +0 -289
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
- data/vendor/kreuzberg/tests/config_integration_test.rs +0 -753
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -500
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
- data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
- data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -674
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
- data/vendor/kreuzberg/tests/page_markers.rs +0 -297
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -589
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -475
- data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -775
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1260
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -648
- data/vendor/kreuzberg-ffi/Cargo.toml +0 -67
- data/vendor/kreuzberg-ffi/README.md +0 -851
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -227
- data/vendor/kreuzberg-ffi/build.rs +0 -168
- data/vendor/kreuzberg-ffi/cbindgen.toml +0 -37
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3012
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -588
- data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
- data/vendor/kreuzberg-ffi/src/error.rs +0 -901
- data/vendor/kreuzberg-ffi/src/extraction.rs +0 -555
- data/vendor/kreuzberg-ffi/src/helpers.rs +0 -879
- data/vendor/kreuzberg-ffi/src/lib.rs +0 -977
- data/vendor/kreuzberg-ffi/src/memory.rs +0 -493
- data/vendor/kreuzberg-ffi/src/mime.rs +0 -329
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -265
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -442
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -14
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -628
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -438
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -329
- data/vendor/kreuzberg-ffi/src/result.rs +0 -510
- data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -639
- data/vendor/kreuzberg-ffi/src/result_view.rs +0 -773
- data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -568
- data/vendor/kreuzberg-ffi/src/types.rs +0 -363
- data/vendor/kreuzberg-ffi/src/util.rs +0 -210
- data/vendor/kreuzberg-ffi/src/validation.rs +0 -848
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +0 -13
- data/vendor/kreuzberg-tesseract/.crate-ignore +0 -2
- data/vendor/kreuzberg-tesseract/Cargo.lock +0 -2933
- data/vendor/kreuzberg-tesseract/Cargo.toml +0 -57
- data/vendor/kreuzberg-tesseract/LICENSE +0 -22
- data/vendor/kreuzberg-tesseract/README.md +0 -399
- data/vendor/kreuzberg-tesseract/build.rs +0 -1127
- data/vendor/kreuzberg-tesseract/patches/README.md +0 -71
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
- data/vendor/kreuzberg-tesseract/src/api.rs +0 -1371
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
- data/vendor/kreuzberg-tesseract/src/enums.rs +0 -297
- data/vendor/kreuzberg-tesseract/src/error.rs +0 -81
- data/vendor/kreuzberg-tesseract/src/lib.rs +0 -145
- data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -57
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -253
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -286
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -183
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211
|
@@ -1,471 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
RSpec.describe 'Pages Extraction' do
|
|
4
|
-
describe 'Extract Pages' do
|
|
5
|
-
it 'returns pages array when extractPages is true' do
|
|
6
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
7
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
8
|
-
)
|
|
9
|
-
|
|
10
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
11
|
-
|
|
12
|
-
expect(result).not_to be_nil
|
|
13
|
-
expect(result.pages).not_to be_nil
|
|
14
|
-
expect(result.pages).to be_a(Array)
|
|
15
|
-
expect(result.pages.length).to be > 0
|
|
16
|
-
end
|
|
17
|
-
|
|
18
|
-
it 'returns page numbers for each page' do
|
|
19
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
20
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
21
|
-
)
|
|
22
|
-
|
|
23
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
24
|
-
|
|
25
|
-
expect(result.pages).not_to be_nil
|
|
26
|
-
result.pages.each do |page|
|
|
27
|
-
expect(page.page_number).to be > 0
|
|
28
|
-
end
|
|
29
|
-
end
|
|
30
|
-
|
|
31
|
-
it 'returns page content for each page' do
|
|
32
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
33
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
34
|
-
)
|
|
35
|
-
|
|
36
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
37
|
-
|
|
38
|
-
expect(result.pages).not_to be_nil
|
|
39
|
-
result.pages.each do |page|
|
|
40
|
-
expect(page.content).not_to be_nil
|
|
41
|
-
end
|
|
42
|
-
end
|
|
43
|
-
|
|
44
|
-
it 'returns nil for pages when extractPages is false' do
|
|
45
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
46
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: false)
|
|
47
|
-
)
|
|
48
|
-
|
|
49
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
50
|
-
|
|
51
|
-
expect(result).not_to be_nil
|
|
52
|
-
expect(result.pages).to be_nil
|
|
53
|
-
end
|
|
54
|
-
|
|
55
|
-
it 'preserves page order' do
|
|
56
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
57
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
58
|
-
)
|
|
59
|
-
|
|
60
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
61
|
-
|
|
62
|
-
if result.pages.length > 1
|
|
63
|
-
(0...(result.pages.length - 1)).each do |i|
|
|
64
|
-
expect(result.pages[i].page_number).to be < result.pages[i + 1].page_number
|
|
65
|
-
end
|
|
66
|
-
end
|
|
67
|
-
end
|
|
68
|
-
end
|
|
69
|
-
|
|
70
|
-
describe 'Insert Page Markers' do
|
|
71
|
-
it 'inserts page markers when insertPageMarkers is true' do
|
|
72
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
73
|
-
pages: Kreuzberg::Config::PageConfig.new(insert_page_markers: true)
|
|
74
|
-
)
|
|
75
|
-
|
|
76
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
77
|
-
|
|
78
|
-
expect(result).not_to be_nil
|
|
79
|
-
expect(result.content).not_to be_nil
|
|
80
|
-
expect(result.content).to include('<!-- PAGE')
|
|
81
|
-
end
|
|
82
|
-
|
|
83
|
-
it 'does not insert markers when insertPageMarkers is false' do
|
|
84
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
85
|
-
pages: Kreuzberg::Config::PageConfig.new(insert_page_markers: false)
|
|
86
|
-
)
|
|
87
|
-
|
|
88
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
89
|
-
|
|
90
|
-
expect(result).not_to be_nil
|
|
91
|
-
# Default marker format should not appear when not enabled
|
|
92
|
-
expect(result.content).not_to include('<!-- PAGE')
|
|
93
|
-
end
|
|
94
|
-
|
|
95
|
-
it 'contains page numbers in markers' do
|
|
96
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
97
|
-
pages: Kreuzberg::Config::PageConfig.new(insert_page_markers: true)
|
|
98
|
-
)
|
|
99
|
-
|
|
100
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
101
|
-
|
|
102
|
-
expect(result.content).not_to be_nil
|
|
103
|
-
# Should contain at least page 1
|
|
104
|
-
expect(result.content).to include('1')
|
|
105
|
-
end
|
|
106
|
-
|
|
107
|
-
it 'inserts multiple markers for multi-page documents' do
|
|
108
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
109
|
-
pages: Kreuzberg::Config::PageConfig.new(insert_page_markers: true)
|
|
110
|
-
)
|
|
111
|
-
|
|
112
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
113
|
-
|
|
114
|
-
expect(result.content).not_to be_nil
|
|
115
|
-
marker_count = result.content.scan('<!-- PAGE').length
|
|
116
|
-
expect(marker_count).to be > 0
|
|
117
|
-
end
|
|
118
|
-
end
|
|
119
|
-
|
|
120
|
-
describe 'Custom Marker Format' do
|
|
121
|
-
it 'uses custom marker format when specified' do
|
|
122
|
-
custom_format = '=== PAGE {page_num} ==='
|
|
123
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
124
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
125
|
-
insert_page_markers: true,
|
|
126
|
-
marker_format: custom_format
|
|
127
|
-
)
|
|
128
|
-
)
|
|
129
|
-
|
|
130
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
131
|
-
|
|
132
|
-
expect(result).not_to be_nil
|
|
133
|
-
expect(result.content).not_to be_nil
|
|
134
|
-
expect(result.content).to include('=== PAGE')
|
|
135
|
-
end
|
|
136
|
-
|
|
137
|
-
it 'replaces page_num placeholder in custom format' do
|
|
138
|
-
custom_format = '[Page Number: {page_num}]'
|
|
139
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
140
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
141
|
-
insert_page_markers: true,
|
|
142
|
-
marker_format: custom_format
|
|
143
|
-
)
|
|
144
|
-
)
|
|
145
|
-
|
|
146
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
147
|
-
|
|
148
|
-
expect(result.content).not_to be_nil
|
|
149
|
-
expect(result.content).to include('[Page Number:')
|
|
150
|
-
expect(result.content).not_to include('{page_num}')
|
|
151
|
-
end
|
|
152
|
-
|
|
153
|
-
it 'handles simple custom format' do
|
|
154
|
-
custom_format = 'PAGE_{page_num}'
|
|
155
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
156
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
157
|
-
insert_page_markers: true,
|
|
158
|
-
marker_format: custom_format
|
|
159
|
-
)
|
|
160
|
-
)
|
|
161
|
-
|
|
162
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
163
|
-
|
|
164
|
-
expect(result.content).not_to be_nil
|
|
165
|
-
expect(result.content).to include('PAGE_')
|
|
166
|
-
end
|
|
167
|
-
|
|
168
|
-
it 'handles custom format with line separators' do
|
|
169
|
-
custom_format = "\n---PAGE {page_num}---\n"
|
|
170
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
171
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
172
|
-
insert_page_markers: true,
|
|
173
|
-
marker_format: custom_format
|
|
174
|
-
)
|
|
175
|
-
)
|
|
176
|
-
|
|
177
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
178
|
-
|
|
179
|
-
expect(result.content).not_to be_nil
|
|
180
|
-
expect(result.content).to include('---PAGE')
|
|
181
|
-
end
|
|
182
|
-
|
|
183
|
-
it 'overrides default marker format' do
|
|
184
|
-
custom_format = 'CUSTOM_PAGE_{page_num}'
|
|
185
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
186
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
187
|
-
insert_page_markers: true,
|
|
188
|
-
marker_format: custom_format
|
|
189
|
-
)
|
|
190
|
-
)
|
|
191
|
-
|
|
192
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
193
|
-
|
|
194
|
-
expect(result.content).not_to be_nil
|
|
195
|
-
expect(result.content).to include('CUSTOM_PAGE_')
|
|
196
|
-
end
|
|
197
|
-
end
|
|
198
|
-
|
|
199
|
-
describe 'Multi-Page PDF' do
|
|
200
|
-
it 'produces multiple pages from multi-page PDF' do
|
|
201
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
202
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
203
|
-
)
|
|
204
|
-
|
|
205
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
206
|
-
|
|
207
|
-
expect(result.pages).not_to be_nil
|
|
208
|
-
expect(result.pages.length).to be > 0
|
|
209
|
-
end
|
|
210
|
-
|
|
211
|
-
it 'page numbers are sequential' do
|
|
212
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
213
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
214
|
-
)
|
|
215
|
-
|
|
216
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
217
|
-
|
|
218
|
-
expect(result.pages).not_to be_nil
|
|
219
|
-
result.pages.each_with_index do |page, index|
|
|
220
|
-
expect(page.page_number).to eq(index + 1)
|
|
221
|
-
end
|
|
222
|
-
end
|
|
223
|
-
|
|
224
|
-
it 'each page has content' do
|
|
225
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
226
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
227
|
-
)
|
|
228
|
-
|
|
229
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
230
|
-
|
|
231
|
-
expect(result.pages).not_to be_nil
|
|
232
|
-
result.pages.each do |page|
|
|
233
|
-
expect(page.content).not_to be_nil
|
|
234
|
-
expect(page.content.strip).not_to be_empty
|
|
235
|
-
end
|
|
236
|
-
end
|
|
237
|
-
|
|
238
|
-
it 'with markers contains all pages' do
|
|
239
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
240
|
-
pages: Kreuzberg::Config::PageConfig.new(insert_page_markers: true)
|
|
241
|
-
)
|
|
242
|
-
|
|
243
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
244
|
-
|
|
245
|
-
expect(result.content).not_to be_nil
|
|
246
|
-
marker_count = result.content.scan('<!-- PAGE').length
|
|
247
|
-
expect(marker_count).to be >= 1
|
|
248
|
-
end
|
|
249
|
-
end
|
|
250
|
-
|
|
251
|
-
describe 'Page Content Structure Validation' do
|
|
252
|
-
it 'validates page structure' do
|
|
253
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
254
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
255
|
-
)
|
|
256
|
-
|
|
257
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
258
|
-
|
|
259
|
-
expect(result.pages).not_to be_nil
|
|
260
|
-
result.pages.each do |page|
|
|
261
|
-
expect(page.content).not_to be_nil
|
|
262
|
-
expect(page.page_number).to be > 0
|
|
263
|
-
end
|
|
264
|
-
end
|
|
265
|
-
|
|
266
|
-
it 'page content has required fields' do
|
|
267
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
268
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
269
|
-
)
|
|
270
|
-
|
|
271
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
272
|
-
|
|
273
|
-
expect(result.pages).not_to be_nil
|
|
274
|
-
result.pages.each do |page|
|
|
275
|
-
expect(page.page_number).to be > 0
|
|
276
|
-
expect(page.content).not_to be_nil
|
|
277
|
-
end
|
|
278
|
-
end
|
|
279
|
-
|
|
280
|
-
it 'page content with tables preserves table data' do
|
|
281
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
282
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
283
|
-
)
|
|
284
|
-
|
|
285
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
286
|
-
|
|
287
|
-
expect(result.pages).not_to be_nil
|
|
288
|
-
result.pages.each do |page|
|
|
289
|
-
# Tables in page content are optional
|
|
290
|
-
expect(page.tables).to be_an(Array) if page.respond_to?(:tables) && page.tables
|
|
291
|
-
end
|
|
292
|
-
end
|
|
293
|
-
|
|
294
|
-
it 'page content with images preserves image data' do
|
|
295
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
296
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
297
|
-
)
|
|
298
|
-
|
|
299
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
300
|
-
|
|
301
|
-
expect(result.pages).not_to be_nil
|
|
302
|
-
result.pages.each do |page|
|
|
303
|
-
# Images in page content are optional
|
|
304
|
-
expect(page.images).to be_an(Array) if page.respond_to?(:images) && page.images
|
|
305
|
-
end
|
|
306
|
-
end
|
|
307
|
-
|
|
308
|
-
it 'page content is not empty' do
|
|
309
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
310
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
311
|
-
)
|
|
312
|
-
|
|
313
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
314
|
-
|
|
315
|
-
expect(result.pages).not_to be_nil
|
|
316
|
-
page_with_content = result.pages.find { |p| p.content && !p.content.strip.empty? }
|
|
317
|
-
expect(page_with_content).not_to be_nil
|
|
318
|
-
end
|
|
319
|
-
end
|
|
320
|
-
|
|
321
|
-
describe 'Combined Features' do
|
|
322
|
-
it 'extract pages and insert markers together' do
|
|
323
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
324
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
325
|
-
extract_pages: true,
|
|
326
|
-
insert_page_markers: true
|
|
327
|
-
)
|
|
328
|
-
)
|
|
329
|
-
|
|
330
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
331
|
-
|
|
332
|
-
expect(result).not_to be_nil
|
|
333
|
-
expect(result.pages).not_to be_nil
|
|
334
|
-
expect(result.pages.length).to be > 0
|
|
335
|
-
expect(result.content).to include('<!-- PAGE')
|
|
336
|
-
end
|
|
337
|
-
|
|
338
|
-
it 'extract pages with custom marker format' do
|
|
339
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
340
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
341
|
-
extract_pages: true,
|
|
342
|
-
insert_page_markers: true,
|
|
343
|
-
marker_format: '[PAGE {page_num}]'
|
|
344
|
-
)
|
|
345
|
-
)
|
|
346
|
-
|
|
347
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
348
|
-
|
|
349
|
-
expect(result.pages).not_to be_nil
|
|
350
|
-
expect(result.pages.length).to be > 0
|
|
351
|
-
expect(result.content).to include('[PAGE')
|
|
352
|
-
end
|
|
353
|
-
|
|
354
|
-
it 'page extraction consistency between array and markers' do
|
|
355
|
-
config = Kreuzberg::Config::Extraction.new(
|
|
356
|
-
pages: Kreuzberg::Config::PageConfig.new(
|
|
357
|
-
extract_pages: true,
|
|
358
|
-
insert_page_markers: true
|
|
359
|
-
)
|
|
360
|
-
)
|
|
361
|
-
|
|
362
|
-
result = Kreuzberg.extract_file(path: 'test.pdf', config: config)
|
|
363
|
-
|
|
364
|
-
expect(result.pages).not_to be_nil
|
|
365
|
-
expect(result.content).not_to be_nil
|
|
366
|
-
|
|
367
|
-
page_array_count = result.pages.length
|
|
368
|
-
marker_count = result.content.scan('<!-- PAGE').length
|
|
369
|
-
|
|
370
|
-
expect(page_array_count).to eq(marker_count)
|
|
371
|
-
end
|
|
372
|
-
end
|
|
373
|
-
|
|
374
|
-
describe 'PageConfig' do
|
|
375
|
-
it 'creates with default values' do
|
|
376
|
-
config = Kreuzberg::Config::PageConfig.new
|
|
377
|
-
|
|
378
|
-
expect(config.extract_pages).to be false
|
|
379
|
-
expect(config.insert_page_markers).to be false
|
|
380
|
-
expect(config.marker_format).to match(/<!-- PAGE/)
|
|
381
|
-
end
|
|
382
|
-
|
|
383
|
-
it 'creates with custom values' do
|
|
384
|
-
config = Kreuzberg::Config::PageConfig.new(
|
|
385
|
-
extract_pages: true,
|
|
386
|
-
insert_page_markers: true,
|
|
387
|
-
marker_format: 'CUSTOM_{page_num}'
|
|
388
|
-
)
|
|
389
|
-
|
|
390
|
-
expect(config.extract_pages).to be true
|
|
391
|
-
expect(config.insert_page_markers).to be true
|
|
392
|
-
expect(config.marker_format).to eq('CUSTOM_{page_num}')
|
|
393
|
-
end
|
|
394
|
-
|
|
395
|
-
it 'converts to hash' do
|
|
396
|
-
config = Kreuzberg::Config::PageConfig.new(
|
|
397
|
-
extract_pages: true,
|
|
398
|
-
insert_page_markers: false,
|
|
399
|
-
marker_format: 'TEST_{page_num}'
|
|
400
|
-
)
|
|
401
|
-
|
|
402
|
-
hash = config.to_h
|
|
403
|
-
|
|
404
|
-
expect(hash).to be_a(Hash)
|
|
405
|
-
expect(hash[:extract_pages]).to be true
|
|
406
|
-
expect(hash[:insert_page_markers]).to be false
|
|
407
|
-
expect(hash[:marker_format]).to eq('TEST_{page_num}')
|
|
408
|
-
end
|
|
409
|
-
|
|
410
|
-
it 'handles boolean conversion' do
|
|
411
|
-
config = Kreuzberg::Config::PageConfig.new(
|
|
412
|
-
extract_pages: 1,
|
|
413
|
-
insert_page_markers: 0
|
|
414
|
-
)
|
|
415
|
-
|
|
416
|
-
expect(config.extract_pages).to be true
|
|
417
|
-
expect(config.insert_page_markers).to be false
|
|
418
|
-
end
|
|
419
|
-
|
|
420
|
-
it 'preserves marker format default' do
|
|
421
|
-
config = Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
422
|
-
|
|
423
|
-
expect(config.marker_format).not_to be_nil
|
|
424
|
-
expect(config.marker_format).to match(/<!-- PAGE/)
|
|
425
|
-
end
|
|
426
|
-
end
|
|
427
|
-
|
|
428
|
-
describe 'Integration Tests' do
|
|
429
|
-
it 'extraction config includes pages config' do
|
|
430
|
-
extraction_config = Kreuzberg::Config::Extraction.new(
|
|
431
|
-
pages: Kreuzberg::Config::PageConfig.new(extract_pages: true)
|
|
432
|
-
)
|
|
433
|
-
|
|
434
|
-
expect(extraction_config.pages).not_to be_nil
|
|
435
|
-
expect(extraction_config.pages).to be_a(Kreuzberg::Config::PageConfig)
|
|
436
|
-
expect(extraction_config.pages.extract_pages).to be true
|
|
437
|
-
end
|
|
438
|
-
|
|
439
|
-
it 'extraction config to_h includes pages' do
|
|
440
|
-
pages_config = Kreuzberg::Config::PageConfig.new(
|
|
441
|
-
extract_pages: true,
|
|
442
|
-
insert_page_markers: true,
|
|
443
|
-
marker_format: 'CUSTOM_{page_num}'
|
|
444
|
-
)
|
|
445
|
-
extraction_config = Kreuzberg::Config::Extraction.new(pages: pages_config)
|
|
446
|
-
|
|
447
|
-
hash = extraction_config.to_h
|
|
448
|
-
|
|
449
|
-
expect(hash).to include(:pages)
|
|
450
|
-
expect(hash[:pages]).to be_a(Hash)
|
|
451
|
-
expect(hash[:pages][:extract_pages]).to be true
|
|
452
|
-
expect(hash[:pages][:insert_page_markers]).to be true
|
|
453
|
-
expect(hash[:pages][:marker_format]).to eq('CUSTOM_{page_num}')
|
|
454
|
-
end
|
|
455
|
-
|
|
456
|
-
it 'accepts pages config as hash in extraction config' do
|
|
457
|
-
extraction_config = Kreuzberg::Config::Extraction.new(
|
|
458
|
-
pages: {
|
|
459
|
-
extract_pages: true,
|
|
460
|
-
insert_page_markers: true,
|
|
461
|
-
marker_format: 'HASH_{page_num}'
|
|
462
|
-
}
|
|
463
|
-
)
|
|
464
|
-
|
|
465
|
-
expect(extraction_config.pages).to be_a(Kreuzberg::Config::PageConfig)
|
|
466
|
-
expect(extraction_config.pages.extract_pages).to be true
|
|
467
|
-
expect(extraction_config.pages.insert_page_markers).to be true
|
|
468
|
-
expect(extraction_config.pages.marker_format).to eq('HASH_{page_num}')
|
|
469
|
-
end
|
|
470
|
-
end
|
|
471
|
-
end
|