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
|
@@ -19,7 +19,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
19
19
|
end
|
|
20
20
|
|
|
21
21
|
Kreuzberg.register_post_processor('upcase', processor)
|
|
22
|
-
result = Kreuzberg.extract_file_sync(
|
|
22
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
23
23
|
|
|
24
24
|
expect(processor_called).to be true
|
|
25
25
|
expect(result.content).to eq(result.content.upcase)
|
|
@@ -32,7 +32,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
32
32
|
end
|
|
33
33
|
|
|
34
34
|
Kreuzberg.register_post_processor('prefix', processor)
|
|
35
|
-
result = Kreuzberg.extract_file_sync(
|
|
35
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
36
36
|
|
|
37
37
|
expect(result.content).to start_with('[PROCESSED]')
|
|
38
38
|
end
|
|
@@ -45,7 +45,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
45
45
|
end
|
|
46
46
|
|
|
47
47
|
Kreuzberg.register_post_processor('metadata_adder', processor)
|
|
48
|
-
result = Kreuzberg.extract_file_sync(
|
|
48
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
49
49
|
|
|
50
50
|
expect(result.metadata['custom_field']).to eq('custom_value')
|
|
51
51
|
expect(result.metadata['word_count']).to be_positive
|
|
@@ -67,7 +67,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
67
67
|
|
|
68
68
|
processor = WordCountProcessor.new
|
|
69
69
|
Kreuzberg.register_post_processor('word_count', processor)
|
|
70
|
-
result = Kreuzberg.extract_file_sync(
|
|
70
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
71
71
|
|
|
72
72
|
expect(result.metadata['word_count']).to be_positive
|
|
73
73
|
expect(result.metadata['processor_name']).to eq('WordCountProcessor')
|
|
@@ -89,7 +89,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
89
89
|
|
|
90
90
|
processor = TruncateProcessor.new(50)
|
|
91
91
|
Kreuzberg.register_post_processor('truncate', processor)
|
|
92
|
-
result = Kreuzberg.extract_file_sync(
|
|
92
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
93
93
|
|
|
94
94
|
expect(result.content.length).to be <= 53
|
|
95
95
|
end
|
|
@@ -109,7 +109,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
109
109
|
|
|
110
110
|
Kreuzberg.register_post_processor('proc1', processor1)
|
|
111
111
|
Kreuzberg.register_post_processor('proc2', processor2)
|
|
112
|
-
result = Kreuzberg.extract_file_sync(
|
|
112
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
113
113
|
|
|
114
114
|
expect(result.metadata['processor1']).to eq('executed')
|
|
115
115
|
expect(result.metadata['processor2']).to eq('executed')
|
|
@@ -125,7 +125,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
125
125
|
|
|
126
126
|
Kreuzberg.register_post_processor('removable', processor)
|
|
127
127
|
Kreuzberg.unregister_post_processor('removable')
|
|
128
|
-
result = Kreuzberg.extract_file_sync(
|
|
128
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
129
129
|
|
|
130
130
|
expect(result.metadata['should_not_appear']).to be_nil
|
|
131
131
|
end
|
|
@@ -151,7 +151,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
151
151
|
Kreuzberg.register_post_processor('keep3', processor3)
|
|
152
152
|
|
|
153
153
|
Kreuzberg.unregister_post_processor('remove')
|
|
154
|
-
result = Kreuzberg.extract_file_sync(
|
|
154
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
155
155
|
|
|
156
156
|
expect(result.metadata['keep1']).to eq('value1')
|
|
157
157
|
expect(result.metadata['remove']).to be_nil
|
|
@@ -175,7 +175,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
175
175
|
Kreuzberg.register_post_processor('proc2', processor2)
|
|
176
176
|
|
|
177
177
|
Kreuzberg.clear_post_processors
|
|
178
|
-
result = Kreuzberg.extract_file_sync(
|
|
178
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
179
179
|
|
|
180
180
|
expect(result.metadata['proc1']).to be_nil
|
|
181
181
|
expect(result.metadata['proc2']).to be_nil
|
|
@@ -191,7 +191,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
191
191
|
Kreuzberg.register_post_processor('failing', processor)
|
|
192
192
|
|
|
193
193
|
expect do
|
|
194
|
-
Kreuzberg.extract_file_sync(
|
|
194
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
195
195
|
end.to raise_error(StandardError, /Post-processor error/)
|
|
196
196
|
end
|
|
197
197
|
|
|
@@ -203,7 +203,7 @@ RSpec.describe 'PostProcessor Plugin System' do
|
|
|
203
203
|
Kreuzberg.register_post_processor('invalid', processor)
|
|
204
204
|
|
|
205
205
|
expect do
|
|
206
|
-
Kreuzberg.extract_file_sync(
|
|
206
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
207
207
|
end.to raise_error
|
|
208
208
|
end
|
|
209
209
|
end
|
|
@@ -17,17 +17,18 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
17
17
|
end
|
|
18
18
|
|
|
19
19
|
Kreuzberg.register_validator('check_called', validator)
|
|
20
|
-
Kreuzberg.extract_file_sync(
|
|
20
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
21
21
|
|
|
22
22
|
expect(validator_called).to be true
|
|
23
23
|
end
|
|
24
24
|
|
|
25
25
|
it 'allows extraction to proceed when validator passes' do
|
|
26
26
|
validator = lambda do |result|
|
|
27
|
+
# Validation passes - do nothing
|
|
27
28
|
end
|
|
28
29
|
|
|
29
30
|
Kreuzberg.register_validator('pass_validator', validator)
|
|
30
|
-
result = Kreuzberg.extract_file_sync(
|
|
31
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
31
32
|
|
|
32
33
|
expect(result).to be_a(Kreuzberg::Result)
|
|
33
34
|
expect(result.content).not_to be_empty
|
|
@@ -43,7 +44,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
43
44
|
Kreuzberg.register_validator('min_length', validator)
|
|
44
45
|
|
|
45
46
|
expect do
|
|
46
|
-
Kreuzberg.extract_file_sync(
|
|
47
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
47
48
|
end.to raise_error(Kreuzberg::Errors::ValidationError, /Content too short/)
|
|
48
49
|
end
|
|
49
50
|
end
|
|
@@ -66,7 +67,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
66
67
|
|
|
67
68
|
validator = MinimumLengthValidator.new(10)
|
|
68
69
|
Kreuzberg.register_validator('min_length', validator)
|
|
69
|
-
result = Kreuzberg.extract_file_sync(
|
|
70
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
70
71
|
|
|
71
72
|
expect(result).to be_a(Kreuzberg::Result)
|
|
72
73
|
expect(result.content.length).to be >= 10
|
|
@@ -85,7 +86,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
85
86
|
|
|
86
87
|
validator = NonEmptyValidator.new
|
|
87
88
|
Kreuzberg.register_validator('non_empty', validator)
|
|
88
|
-
result = Kreuzberg.extract_file_sync(
|
|
89
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
89
90
|
|
|
90
91
|
expect(result.content.strip).not_to be_empty
|
|
91
92
|
end
|
|
@@ -99,7 +100,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
99
100
|
end
|
|
100
101
|
|
|
101
102
|
Kreuzberg.register_validator('capture', validator)
|
|
102
|
-
Kreuzberg.extract_file_sync(
|
|
103
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
103
104
|
|
|
104
105
|
expect(received_result).to be_a(Hash)
|
|
105
106
|
expect(received_result).to have_key('content')
|
|
@@ -115,7 +116,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
115
116
|
end
|
|
116
117
|
|
|
117
118
|
Kreuzberg.register_validator('capture_content', validator)
|
|
118
|
-
result = Kreuzberg.extract_file_sync(
|
|
119
|
+
result = Kreuzberg.extract_file_sync(test_pdf)
|
|
119
120
|
|
|
120
121
|
expect(received_content).to eq(result.content)
|
|
121
122
|
end
|
|
@@ -136,7 +137,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
136
137
|
|
|
137
138
|
Kreuzberg.register_validator('val1', validator1)
|
|
138
139
|
Kreuzberg.register_validator('val2', validator2)
|
|
139
|
-
Kreuzberg.extract_file_sync(
|
|
140
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
140
141
|
|
|
141
142
|
expect(validator1_called).to be true
|
|
142
143
|
expect(validator2_called).to be true
|
|
@@ -155,7 +156,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
155
156
|
Kreuzberg.register_validator('never_reached', validator2)
|
|
156
157
|
|
|
157
158
|
expect do
|
|
158
|
-
Kreuzberg.extract_file_sync(
|
|
159
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
159
160
|
end.to raise_error(Kreuzberg::Errors::ValidationError, /First validator failed/)
|
|
160
161
|
end
|
|
161
162
|
end
|
|
@@ -170,7 +171,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
170
171
|
Kreuzberg.unregister_validator('removable')
|
|
171
172
|
|
|
172
173
|
expect do
|
|
173
|
-
Kreuzberg.extract_file_sync(
|
|
174
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
174
175
|
end.not_to raise_error
|
|
175
176
|
end
|
|
176
177
|
|
|
@@ -195,7 +196,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
195
196
|
Kreuzberg.register_validator('keep3', validator3)
|
|
196
197
|
|
|
197
198
|
Kreuzberg.unregister_validator('remove')
|
|
198
|
-
Kreuzberg.extract_file_sync(
|
|
199
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
199
200
|
|
|
200
201
|
expect(validator1_called).to be true
|
|
201
202
|
expect(validator3_called).to be true
|
|
@@ -218,7 +219,7 @@ RSpec.describe 'Validator Plugin System' do
|
|
|
218
219
|
Kreuzberg.clear_validators
|
|
219
220
|
|
|
220
221
|
expect do
|
|
221
|
-
Kreuzberg.extract_file_sync(
|
|
222
|
+
Kreuzberg.extract_file_sync(test_pdf)
|
|
222
223
|
end.not_to raise_error
|
|
223
224
|
end
|
|
224
225
|
end
|
data/spec/examples.txt
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
1
|
+
example_id | status | run_time |
|
|
2
|
+
---------------------------------------------------------------------------------- | ------ | --------------- |
|
|
3
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:1:1] | failed | 0.00173 seconds |
|
|
4
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:1:2] | failed | 0.0018 seconds |
|
|
5
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:2:1] | failed | 0.00192 seconds |
|
|
6
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:2:2] | failed | 0.00581 seconds |
|
|
7
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:3:1] | failed | 0.00184 seconds |
|
|
8
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:4:1] | passed | 0.00088 seconds |
|
|
9
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:4:2] | passed | 0.00045 seconds |
|
|
10
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:5:1] | passed | 0.00007 seconds |
|
|
11
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:5:2] | passed | 0.00052 seconds |
|
|
12
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:6:1:1] | passed | 0.00012 seconds |
|
|
13
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:6:1:2] | passed | 0.00079 seconds |
|
|
14
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:6:2:1] | passed | 0.00004 seconds |
|
|
15
|
+
./spec/binding/plugins/ocr_backend_spec.rb[1:6:2:2] | passed | 0.00029 seconds |
|
|
16
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:1:1] | failed | 0.00139 seconds |
|
|
17
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:1:2] | failed | 0.00153 seconds |
|
|
18
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:1:3] | failed | 0.0014 seconds |
|
|
19
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:2:1] | failed | 0.00182 seconds |
|
|
20
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:2:2] | failed | 0.00209 seconds |
|
|
21
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:3:1] | failed | 0.00165 seconds |
|
|
22
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:4:1] | failed | 0.00142 seconds |
|
|
23
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:4:2] | failed | 0.00148 seconds |
|
|
24
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:5:1] | failed | 0.00148 seconds |
|
|
25
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:6:1] | passed | 0.0001 seconds |
|
|
26
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:6:2] | passed | 0.00011 seconds |
|
|
27
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:7:1] | passed | 0.00003 seconds |
|
|
28
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:7:2] | passed | 0.00002 seconds |
|
|
29
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:7:3] | passed | 0.00003 seconds |
|
|
30
|
+
./spec/binding/plugins/postprocessor_spec.rb[1:7:4] | passed | 0.00006 seconds |
|
|
31
|
+
./spec/binding/plugins/validator_spec.rb[1:1:1] | failed | 0.00154 seconds |
|
|
32
|
+
./spec/binding/plugins/validator_spec.rb[1:1:2] | failed | 0.00171 seconds |
|
|
33
|
+
./spec/binding/plugins/validator_spec.rb[1:1:3] | passed | 0.00099 seconds |
|
|
34
|
+
./spec/binding/plugins/validator_spec.rb[1:2:1] | failed | 0.00186 seconds |
|
|
35
|
+
./spec/binding/plugins/validator_spec.rb[1:2:2] | failed | 0.0016 seconds |
|
|
36
|
+
./spec/binding/plugins/validator_spec.rb[1:3:1] | failed | 0.00182 seconds |
|
|
37
|
+
./spec/binding/plugins/validator_spec.rb[1:3:2] | failed | 0.0128 seconds |
|
|
38
|
+
./spec/binding/plugins/validator_spec.rb[1:4:1] | failed | 0.00156 seconds |
|
|
39
|
+
./spec/binding/plugins/validator_spec.rb[1:4:2] | passed | 0.0001 seconds |
|
|
40
|
+
./spec/binding/plugins/validator_spec.rb[1:5:1] | failed | 0.00445 seconds |
|
|
41
|
+
./spec/binding/plugins/validator_spec.rb[1:5:2] | failed | 0.00198 seconds |
|
|
42
|
+
./spec/binding/plugins/validator_spec.rb[1:6:1] | failed | 0.00179 seconds |
|
|
43
|
+
./spec/binding/plugins/validator_spec.rb[1:7:1] | passed | 0.00068 seconds |
|
|
44
|
+
./spec/binding/plugins/validator_spec.rb[1:7:2] | passed | 0.00088 seconds |
|
|
45
|
+
./spec/binding/plugins/validator_spec.rb[1:7:3] | passed | 0.00045 seconds |
|
|
46
|
+
./spec/binding/plugins/validator_spec.rb[1:7:4] | passed | 0.00004 seconds |
|
|
47
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/email_spec.rb[1:1] | passed | 0.01048 seconds |
|
|
48
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/html_spec.rb[1:1] | passed | 1.95 seconds |
|
|
49
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/html_spec.rb[1:2] | passed | 0.00031 seconds |
|
|
50
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/image_spec.rb[1:1] | passed | 0.0027 seconds |
|
|
51
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:1] | passed | 0.04721 seconds |
|
|
52
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:2] | passed | 0.04402 seconds |
|
|
53
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:3] | passed | 3.41 seconds |
|
|
54
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:4] | passed | 0.34493 seconds |
|
|
55
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:5] | passed | 0.33223 seconds |
|
|
56
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:1] | passed | 2.74 seconds |
|
|
57
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:2] | passed | 0.00021 seconds |
|
|
58
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:3] | passed | 0.00035 seconds |
|
|
59
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:4] | passed | 0.00021 seconds |
|
|
60
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:5] | passed | 0.0003 seconds |
|
|
61
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:6] | passed | 0.00027 seconds |
|
|
62
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:7] | passed | 0.00023 seconds |
|
|
63
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:8] | passed | 0.00016 seconds |
|
|
64
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:9] | passed | 2.65 seconds |
|
|
65
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:10] | passed | 0.0003 seconds |
|
|
66
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:11] | passed | 0.0002 seconds |
|
|
67
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:12] | passed | 0.00984 seconds |
|
|
68
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:13] | passed | 0.00096 seconds |
|
|
69
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:14] | passed | 0.00115 seconds |
|
|
70
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:15] | passed | 0.00038 seconds |
|
|
71
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:16] | passed | 0.00448 seconds |
|
|
72
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:1] | passed | 0.99668 seconds |
|
|
73
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:2] | passed | 4.11 seconds |
|
|
74
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:3] | passed | 0.00451 seconds |
|
|
75
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:4] | passed | 0.07588 seconds |
|
|
76
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:5] | passed | 0.00339 seconds |
|
|
77
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:6] | passed | 0.00238 seconds |
|
|
78
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:7] | passed | 0.24683 seconds |
|
|
79
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:8] | passed | 0.07999 seconds |
|
|
80
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:9] | passed | 0.01214 seconds |
|
|
81
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:10] | passed | 0.00095 seconds |
|
|
82
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:11] | passed | 0.03728 seconds |
|
|
83
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:12] | passed | 0.01741 seconds |
|
|
84
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:13] | passed | 0.0036 seconds |
|
|
85
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:14] | passed | 0.89424 seconds |
|
|
86
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[1:1] | passed | 0.00228 seconds |
|
|
87
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[1:2] | passed | 0.0012 seconds |
|
|
88
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:1] | passed | 0.0008 seconds |
|
|
89
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:2] | passed | 0.00119 seconds |
|
|
90
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:3] | passed | 0.0013 seconds |
|
|
91
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:1] | passed | 0.00184 seconds |
|
|
92
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:2] | passed | 0.00053 seconds |
|
|
93
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:3] | passed | 0.00004 seconds |
|
|
94
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:1] | passed | 0.00049 seconds |
|
|
95
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:2] | passed | 0.00006 seconds |
|
|
96
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:3] | passed | 0.00005 seconds |
|
|
97
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[5:1] | passed | 0.00007 seconds |
|
|
98
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[5:2] | passed | 0.00011 seconds |
|
|
99
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[6:1] | passed | 0.00003 seconds |
|
|
100
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[6:2] | passed | 0.00002 seconds |
|
|
101
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:1] | passed | 0.00101 seconds |
|
|
102
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:2] | passed | 0.00041 seconds |
|
|
103
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:3] | passed | 0.00035 seconds |
|
|
104
|
+
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/xml_spec.rb[1:1] | passed | 0.00078 seconds |
|
data/spec/fixtures/config.toml
CHANGED
data/spec/fixtures/config.yaml
CHANGED
data/spec/smoke/package_spec.rb
CHANGED
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
+
# Basic smoke tests to verify package structure and imports work
|
|
3
4
|
require 'stringio'
|
|
4
5
|
|
|
5
6
|
RSpec.describe 'Kreuzberg package' do
|
|
@@ -158,7 +159,7 @@ RSpec.describe 'Kreuzberg package' do
|
|
|
158
159
|
describe 'basic extraction smoke tests' do
|
|
159
160
|
it 'extracts inline text via bytes API' do
|
|
160
161
|
bytes = StringIO.new('Hello from Kreuzberg')
|
|
161
|
-
result = Kreuzberg.extract_bytes_sync(
|
|
162
|
+
result = Kreuzberg.extract_bytes_sync(bytes.string, 'text/plain')
|
|
162
163
|
|
|
163
164
|
expect(result.content).to include('Hello')
|
|
164
165
|
expect(result.mime_type).to eq('text/plain')
|
|
@@ -166,7 +167,7 @@ RSpec.describe 'Kreuzberg package' do
|
|
|
166
167
|
|
|
167
168
|
it 'extracts from small temp file via sync API' do
|
|
168
169
|
file = create_test_file('Simple document for smoke testing')
|
|
169
|
-
result = Kreuzberg.extract_file_sync(
|
|
170
|
+
result = Kreuzberg.extract_file_sync(file)
|
|
170
171
|
|
|
171
172
|
expect(result.content).to include('Simple document')
|
|
172
173
|
expect(result.mime_type).to eq('text/plain')
|
data/spec/spec_helper.rb
CHANGED
|
@@ -22,13 +22,15 @@ RSpec.configure do |config|
|
|
|
22
22
|
config.order = :random
|
|
23
23
|
Kernel.srand config.seed
|
|
24
24
|
|
|
25
|
+
# Helpers
|
|
25
26
|
config.include(Module.new do
|
|
26
27
|
def fixture_path(filename)
|
|
27
28
|
File.join(__dir__, 'fixtures', filename)
|
|
28
29
|
end
|
|
29
30
|
|
|
30
31
|
def test_document_path(relative_path)
|
|
31
|
-
|
|
32
|
+
# Go up from packages/ruby/spec to project root, then into test_documents
|
|
33
|
+
File.join(__dir__, '..', '..', '..', 'test_documents', relative_path)
|
|
32
34
|
end
|
|
33
35
|
|
|
34
36
|
def create_test_file(content, filename: 'test.txt')
|