kreuzberg 4.0.0.rc2 → 4.0.0
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 +14 -14
- data/.rspec +3 -3
- data/.rubocop.yaml +1 -1
- data/.rubocop.yml +543 -538
- data/Gemfile +8 -8
- data/Gemfile.lock +194 -6
- data/README.md +396 -426
- data/Rakefile +34 -25
- data/Steepfile +51 -47
- data/examples/async_patterns.rb +283 -341
- data/ext/kreuzberg_rb/extconf.rb +65 -45
- data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
- data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
- data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +15 -15
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
- data/ext/kreuzberg_rb/native/include/strings.h +20 -20
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
- data/ext/kreuzberg_rb/native/src/lib.rs +3802 -2998
- data/extconf.rb +60 -28
- data/kreuzberg.gemspec +199 -148
- data/lib/kreuzberg/api_proxy.rb +126 -142
- data/lib/kreuzberg/cache_api.rb +67 -46
- data/lib/kreuzberg/cli.rb +47 -55
- data/lib/kreuzberg/cli_proxy.rb +117 -127
- data/lib/kreuzberg/config.rb +936 -691
- data/lib/kreuzberg/error_context.rb +136 -32
- data/lib/kreuzberg/errors.rb +116 -118
- data/lib/kreuzberg/extraction_api.rb +313 -85
- data/lib/kreuzberg/mcp_proxy.rb +177 -186
- data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
- data/lib/kreuzberg/post_processor_protocol.rb +15 -86
- data/lib/kreuzberg/result.rb +334 -216
- data/lib/kreuzberg/setup_lib_path.rb +99 -80
- data/lib/kreuzberg/types.rb +170 -0
- data/lib/kreuzberg/validator_protocol.rb +16 -89
- data/lib/kreuzberg/version.rb +5 -5
- data/lib/kreuzberg.rb +96 -103
- data/lib/libpdfium.so +0 -0
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +561 -520
- data/spec/binding/async_operations_spec.rb +473 -0
- data/spec/binding/batch_operations_spec.rb +595 -0
- data/spec/binding/batch_spec.rb +359 -0
- data/spec/binding/cache_spec.rb +227 -227
- data/spec/binding/cli_proxy_spec.rb +85 -85
- data/spec/binding/cli_spec.rb +55 -55
- data/spec/binding/config_result_spec.rb +377 -0
- data/spec/binding/config_spec.rb +419 -345
- data/spec/binding/config_validation_spec.rb +377 -283
- data/spec/binding/embeddings_spec.rb +816 -0
- data/spec/binding/error_handling_spec.rb +399 -213
- data/spec/binding/error_recovery_spec.rb +488 -0
- data/spec/binding/errors_spec.rb +66 -66
- data/spec/binding/font_config_spec.rb +220 -0
- data/spec/binding/images_spec.rb +738 -0
- data/spec/binding/keywords_extraction_spec.rb +600 -0
- data/spec/binding/metadata_types_spec.rb +1228 -0
- data/spec/binding/pages_extraction_spec.rb +471 -0
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
- data/spec/binding/plugins/postprocessor_spec.rb +269 -269
- data/spec/binding/plugins/validator_spec.rb +273 -274
- data/spec/binding/tables_spec.rb +641 -0
- data/spec/fixtures/config.toml +38 -39
- data/spec/fixtures/config.yaml +41 -41
- data/spec/fixtures/invalid_config.toml +3 -4
- data/spec/smoke/package_spec.rb +177 -178
- data/spec/spec_helper.rb +40 -42
- data/spec/unit/config/chunking_config_spec.rb +213 -0
- data/spec/unit/config/embedding_config_spec.rb +343 -0
- data/spec/unit/config/extraction_config_spec.rb +438 -0
- data/spec/unit/config/font_config_spec.rb +285 -0
- data/spec/unit/config/hierarchy_config_spec.rb +314 -0
- data/spec/unit/config/image_extraction_config_spec.rb +209 -0
- data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
- data/spec/unit/config/keyword_config_spec.rb +229 -0
- data/spec/unit/config/language_detection_config_spec.rb +258 -0
- data/spec/unit/config/ocr_config_spec.rb +171 -0
- data/spec/unit/config/page_config_spec.rb +221 -0
- data/spec/unit/config/pdf_config_spec.rb +267 -0
- data/spec/unit/config/postprocessor_config_spec.rb +290 -0
- data/spec/unit/config/tesseract_config_spec.rb +181 -0
- data/spec/unit/config/token_reduction_config_spec.rb +251 -0
- data/test/metadata_types_test.rb +959 -0
- data/vendor/Cargo.toml +61 -0
- data/vendor/kreuzberg/Cargo.toml +259 -204
- data/vendor/kreuzberg/README.md +263 -175
- data/vendor/kreuzberg/build.rs +782 -474
- data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
- data/vendor/kreuzberg/src/api/error.rs +81 -81
- data/vendor/kreuzberg/src/api/handlers.rs +320 -199
- data/vendor/kreuzberg/src/api/mod.rs +94 -79
- data/vendor/kreuzberg/src/api/server.rs +518 -353
- data/vendor/kreuzberg/src/api/types.rs +206 -170
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
- data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
- data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
- data/vendor/kreuzberg/src/core/config.rs +1914 -1032
- data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
- data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
- data/vendor/kreuzberg/src/core/formats.rs +235 -0
- data/vendor/kreuzberg/src/core/io.rs +329 -329
- data/vendor/kreuzberg/src/core/mime.rs +605 -605
- data/vendor/kreuzberg/src/core/mod.rs +61 -45
- data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
- data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
- data/vendor/kreuzberg/src/embeddings.rs +471 -432
- data/vendor/kreuzberg/src/error.rs +431 -431
- data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
- data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
- data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
- data/vendor/kreuzberg/src/extraction/email.rs +855 -854
- data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
- data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
- data/vendor/kreuzberg/src/extraction/image.rs +492 -368
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
- data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
- data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
- data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
- data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
- data/vendor/kreuzberg/src/extraction/table.rs +329 -328
- data/vendor/kreuzberg/src/extraction/text.rs +277 -269
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
- data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
- data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
- data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
- data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
- data/vendor/kreuzberg/src/extractors/email.rs +157 -143
- data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
- data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
- data/vendor/kreuzberg/src/extractors/html.rs +419 -393
- data/vendor/kreuzberg/src/extractors/image.rs +219 -198
- data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
- data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
- data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
- data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
- data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
- data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
- data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
- data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
- data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
- data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
- data/vendor/kreuzberg/src/extractors/security.rs +484 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
- data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
- data/vendor/kreuzberg/src/extractors/text.rs +265 -260
- data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
- data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
- data/vendor/kreuzberg/src/image/dpi.rs +164 -164
- data/vendor/kreuzberg/src/image/mod.rs +6 -6
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
- data/vendor/kreuzberg/src/image/resize.rs +89 -89
- data/vendor/kreuzberg/src/keywords/config.rs +154 -154
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
- data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
- data/vendor/kreuzberg/src/keywords/types.rs +68 -68
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
- data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
- data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
- data/vendor/kreuzberg/src/lib.rs +114 -105
- data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
- data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
- data/vendor/kreuzberg/src/ocr/error.rs +37 -37
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
- data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
- data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
- data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
- data/vendor/kreuzberg/src/ocr/types.rs +393 -393
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
- data/vendor/kreuzberg/src/panic_context.rs +154 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
- data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
- data/vendor/kreuzberg/src/pdf/error.rs +214 -122
- data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
- data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
- data/vendor/kreuzberg/src/pdf/images.rs +139 -139
- data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
- data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
- data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
- data/vendor/kreuzberg/src/pdf/table.rs +417 -393
- data/vendor/kreuzberg/src/pdf/text.rs +553 -158
- data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
- data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
- data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
- data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
- data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
- data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
- data/vendor/kreuzberg/src/text/mod.rs +27 -19
- data/vendor/kreuzberg/src/text/quality.rs +710 -697
- data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
- data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
- data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
- data/vendor/kreuzberg/src/types.rs +1713 -903
- data/vendor/kreuzberg/src/utils/mod.rs +31 -17
- data/vendor/kreuzberg/src/utils/pool.rs +503 -0
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
- data/vendor/kreuzberg/src/utils/quality.rs +968 -959
- data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
- data/vendor/kreuzberg/tests/api_embed.rs +360 -0
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
- data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
- data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
- data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
- data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
- data/vendor/kreuzberg/tests/config_features.rs +612 -598
- data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
- data/vendor/kreuzberg/tests/core_integration.rs +519 -510
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
- data/vendor/kreuzberg/tests/email_integration.rs +327 -325
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
- data/vendor/kreuzberg/tests/error_handling.rs +402 -393
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
- data/vendor/kreuzberg/tests/format_integration.rs +165 -159
- data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
- data/vendor/kreuzberg/tests/image_integration.rs +255 -253
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
- data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
- data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
- data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
- data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
- data/vendor/kreuzberg/tests/page_markers.rs +297 -0
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
- data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
- data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
- data/vendor/kreuzberg/tests/security_validation.rs +416 -415
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
- data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
- data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
- data/vendor/kreuzberg-ffi/README.md +851 -0
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
- data/vendor/kreuzberg-ffi/build.rs +168 -0
- data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
- data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
- data/vendor/kreuzberg-ffi/src/error.rs +901 -0
- data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
- data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
- data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
- data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
- data/vendor/kreuzberg-ffi/src/result.rs +510 -0
- data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
- data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
- data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
- data/vendor/kreuzberg-ffi/src/types.rs +363 -0
- data/vendor/kreuzberg-ffi/src/util.rs +210 -0
- data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
- data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
- data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
- data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
- data/vendor/kreuzberg-tesseract/README.md +399 -0
- data/vendor/kreuzberg-tesseract/build.rs +1127 -0
- data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
- data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
- data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
- data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
- data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
- data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
- metadata +196 -45
- data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
- data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
- data/vendor/rb-sys/.cargo-ok +0 -1
- data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
- data/vendor/rb-sys/Cargo.lock +0 -393
- data/vendor/rb-sys/Cargo.toml +0 -70
- data/vendor/rb-sys/Cargo.toml.orig +0 -57
- data/vendor/rb-sys/LICENSE-APACHE +0 -190
- data/vendor/rb-sys/bin/release.sh +0 -21
- data/vendor/rb-sys/build/features.rs +0 -108
- data/vendor/rb-sys/build/main.rs +0 -246
- data/vendor/rb-sys/build/stable_api_config.rs +0 -153
- data/vendor/rb-sys/build/version.rs +0 -48
- data/vendor/rb-sys/readme.md +0 -36
- data/vendor/rb-sys/src/bindings.rs +0 -21
- data/vendor/rb-sys/src/hidden.rs +0 -11
- data/vendor/rb-sys/src/lib.rs +0 -34
- data/vendor/rb-sys/src/macros.rs +0 -371
- data/vendor/rb-sys/src/memory.rs +0 -53
- data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
- data/vendor/rb-sys/src/special_consts.rs +0 -31
- data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
- data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
- data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
- data/vendor/rb-sys/src/stable_api.rs +0 -261
- data/vendor/rb-sys/src/symbol.rs +0 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
- data/vendor/rb-sys/src/utils.rs +0 -89
- data/vendor/rb-sys/src/value_type.rs +0 -7
|
@@ -0,0 +1,209 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
RSpec.describe Kreuzberg::Config::ImageExtraction do
|
|
4
|
+
describe '#initialize' do
|
|
5
|
+
it 'creates config with default values' do
|
|
6
|
+
config = described_class.new
|
|
7
|
+
|
|
8
|
+
expect(config.extract_images).to be true
|
|
9
|
+
expect(config.target_dpi).to eq 300
|
|
10
|
+
expect(config.max_image_dimension).to eq 2000
|
|
11
|
+
expect(config.auto_adjust_dpi).to be true
|
|
12
|
+
expect(config.min_dpi).to eq 150
|
|
13
|
+
expect(config.max_dpi).to eq 600
|
|
14
|
+
end
|
|
15
|
+
|
|
16
|
+
it 'creates config with custom values' do
|
|
17
|
+
config = described_class.new(
|
|
18
|
+
extract_images: false,
|
|
19
|
+
target_dpi: 600,
|
|
20
|
+
max_image_dimension: 4000,
|
|
21
|
+
auto_adjust_dpi: false,
|
|
22
|
+
min_dpi: 100,
|
|
23
|
+
max_dpi: 1200
|
|
24
|
+
)
|
|
25
|
+
|
|
26
|
+
expect(config.extract_images).to be false
|
|
27
|
+
expect(config.target_dpi).to eq 600
|
|
28
|
+
expect(config.max_image_dimension).to eq 4000
|
|
29
|
+
expect(config.auto_adjust_dpi).to be false
|
|
30
|
+
expect(config.min_dpi).to eq 100
|
|
31
|
+
expect(config.max_dpi).to eq 1200
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
it 'converts values to integers' do
|
|
35
|
+
config = described_class.new(
|
|
36
|
+
target_dpi: '300',
|
|
37
|
+
max_image_dimension: '2000',
|
|
38
|
+
min_dpi: '150',
|
|
39
|
+
max_dpi: '600'
|
|
40
|
+
)
|
|
41
|
+
|
|
42
|
+
expect(config.target_dpi).to eq 300
|
|
43
|
+
expect(config.max_image_dimension).to eq 2000
|
|
44
|
+
expect(config.min_dpi).to eq 150
|
|
45
|
+
expect(config.max_dpi).to eq 600
|
|
46
|
+
expect(config.target_dpi).to be_a Integer
|
|
47
|
+
end
|
|
48
|
+
|
|
49
|
+
it 'converts boolean values correctly' do
|
|
50
|
+
config = described_class.new(
|
|
51
|
+
extract_images: true,
|
|
52
|
+
auto_adjust_dpi: false
|
|
53
|
+
)
|
|
54
|
+
|
|
55
|
+
expect(config.extract_images).to be true
|
|
56
|
+
expect(config.auto_adjust_dpi).to be false
|
|
57
|
+
end
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
describe '#to_h' do
|
|
61
|
+
it 'serializes to hash with all values' do
|
|
62
|
+
config = described_class.new(
|
|
63
|
+
target_dpi: 300,
|
|
64
|
+
max_image_dimension: 2000
|
|
65
|
+
)
|
|
66
|
+
hash = config.to_h
|
|
67
|
+
|
|
68
|
+
expect(hash).to be_a Hash
|
|
69
|
+
expect(hash[:extract_images]).to be true
|
|
70
|
+
expect(hash[:target_dpi]).to eq 300
|
|
71
|
+
expect(hash[:max_image_dimension]).to eq 2000
|
|
72
|
+
expect(hash[:auto_adjust_dpi]).to be true
|
|
73
|
+
expect(hash[:min_dpi]).to eq 150
|
|
74
|
+
expect(hash[:max_dpi]).to eq 600
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
it 'always includes all keys in hash' do
|
|
78
|
+
config = described_class.new
|
|
79
|
+
hash = config.to_h
|
|
80
|
+
|
|
81
|
+
expect(hash.keys).to contain_exactly(
|
|
82
|
+
:extract_images,
|
|
83
|
+
:target_dpi,
|
|
84
|
+
:max_image_dimension,
|
|
85
|
+
:auto_adjust_dpi,
|
|
86
|
+
:min_dpi,
|
|
87
|
+
:max_dpi
|
|
88
|
+
)
|
|
89
|
+
end
|
|
90
|
+
end
|
|
91
|
+
|
|
92
|
+
describe 'validation' do
|
|
93
|
+
it 'accepts valid DPI values' do
|
|
94
|
+
expect do
|
|
95
|
+
described_class.new(target_dpi: 300, min_dpi: 150, max_dpi: 600)
|
|
96
|
+
end.not_to raise_error
|
|
97
|
+
end
|
|
98
|
+
|
|
99
|
+
it 'accepts valid image dimensions' do
|
|
100
|
+
expect do
|
|
101
|
+
described_class.new(max_image_dimension: 4000)
|
|
102
|
+
end.not_to raise_error
|
|
103
|
+
end
|
|
104
|
+
|
|
105
|
+
it 'converts float DPI to integer' do
|
|
106
|
+
config = described_class.new(target_dpi: 300.5)
|
|
107
|
+
|
|
108
|
+
expect(config.target_dpi).to eq 300
|
|
109
|
+
expect(config.target_dpi).to be_a Integer
|
|
110
|
+
end
|
|
111
|
+
end
|
|
112
|
+
|
|
113
|
+
describe 'keyword arguments' do
|
|
114
|
+
it 'accepts all keyword arguments' do
|
|
115
|
+
config = described_class.new(
|
|
116
|
+
extract_images: true,
|
|
117
|
+
target_dpi: 600,
|
|
118
|
+
max_image_dimension: 3000,
|
|
119
|
+
auto_adjust_dpi: true,
|
|
120
|
+
min_dpi: 200,
|
|
121
|
+
max_dpi: 800
|
|
122
|
+
)
|
|
123
|
+
|
|
124
|
+
expect(config.extract_images).to be true
|
|
125
|
+
expect(config.target_dpi).to eq 600
|
|
126
|
+
expect(config.max_image_dimension).to eq 3000
|
|
127
|
+
expect(config.auto_adjust_dpi).to be true
|
|
128
|
+
expect(config.min_dpi).to eq 200
|
|
129
|
+
expect(config.max_dpi).to eq 800
|
|
130
|
+
end
|
|
131
|
+
end
|
|
132
|
+
|
|
133
|
+
describe 'equality' do
|
|
134
|
+
it 'compares configs by value' do
|
|
135
|
+
config1 = described_class.new(target_dpi: 300, max_image_dimension: 2000)
|
|
136
|
+
config2 = described_class.new(target_dpi: 300, max_image_dimension: 2000)
|
|
137
|
+
|
|
138
|
+
expect(config1.target_dpi).to eq config2.target_dpi
|
|
139
|
+
expect(config1.max_image_dimension).to eq config2.max_image_dimension
|
|
140
|
+
end
|
|
141
|
+
|
|
142
|
+
it 'detects differences in DPI' do
|
|
143
|
+
config1 = described_class.new(target_dpi: 300)
|
|
144
|
+
config2 = described_class.new(target_dpi: 600)
|
|
145
|
+
|
|
146
|
+
expect(config1.target_dpi).not_to eq config2.target_dpi
|
|
147
|
+
end
|
|
148
|
+
|
|
149
|
+
it 'detects differences in extract_images' do
|
|
150
|
+
config1 = described_class.new(extract_images: true)
|
|
151
|
+
config2 = described_class.new(extract_images: false)
|
|
152
|
+
|
|
153
|
+
expect(config1.extract_images).not_to eq config2.extract_images
|
|
154
|
+
end
|
|
155
|
+
end
|
|
156
|
+
|
|
157
|
+
describe 'nested config integration' do
|
|
158
|
+
it 'can be nested in Extraction config' do
|
|
159
|
+
image_config = described_class.new(target_dpi: 600)
|
|
160
|
+
extraction = Kreuzberg::Config::Extraction.new(image_extraction: image_config)
|
|
161
|
+
|
|
162
|
+
expect(extraction.image_extraction).to be_a described_class
|
|
163
|
+
expect(extraction.image_extraction.target_dpi).to eq 600
|
|
164
|
+
end
|
|
165
|
+
|
|
166
|
+
it 'accepts hash in Extraction config' do
|
|
167
|
+
extraction = Kreuzberg::Config::Extraction.new(
|
|
168
|
+
image_extraction: { target_dpi: 600, extract_images: true }
|
|
169
|
+
)
|
|
170
|
+
|
|
171
|
+
expect(extraction.image_extraction).to be_a described_class
|
|
172
|
+
expect(extraction.image_extraction.target_dpi).to eq 600
|
|
173
|
+
end
|
|
174
|
+
end
|
|
175
|
+
|
|
176
|
+
describe 'DPI range' do
|
|
177
|
+
it 'allows realistic DPI values' do
|
|
178
|
+
config = described_class.new(min_dpi: 150, max_dpi: 1200)
|
|
179
|
+
|
|
180
|
+
expect(config.min_dpi).to eq 150
|
|
181
|
+
expect(config.max_dpi).to eq 1200
|
|
182
|
+
end
|
|
183
|
+
|
|
184
|
+
it 'maintains DPI relationships' do
|
|
185
|
+
config = described_class.new(
|
|
186
|
+
target_dpi: 300,
|
|
187
|
+
min_dpi: 100,
|
|
188
|
+
max_dpi: 600
|
|
189
|
+
)
|
|
190
|
+
|
|
191
|
+
expect(config.min_dpi).to be <= config.target_dpi
|
|
192
|
+
expect(config.target_dpi).to be <= config.max_dpi
|
|
193
|
+
end
|
|
194
|
+
end
|
|
195
|
+
|
|
196
|
+
describe 'image dimension constraints' do
|
|
197
|
+
it 'accepts large image dimensions' do
|
|
198
|
+
config = described_class.new(max_image_dimension: 10_000)
|
|
199
|
+
|
|
200
|
+
expect(config.max_image_dimension).to eq 10_000
|
|
201
|
+
end
|
|
202
|
+
|
|
203
|
+
it 'accepts small image dimensions' do
|
|
204
|
+
config = described_class.new(max_image_dimension: 100)
|
|
205
|
+
|
|
206
|
+
expect(config.max_image_dimension).to eq 100
|
|
207
|
+
end
|
|
208
|
+
end
|
|
209
|
+
end
|
|
@@ -0,0 +1,249 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
RSpec.describe Kreuzberg::Config::ImagePreprocessing do
|
|
4
|
+
describe '#initialize' do
|
|
5
|
+
it 'creates config with default values' do
|
|
6
|
+
config = described_class.new
|
|
7
|
+
|
|
8
|
+
expect(config.target_dpi).to eq 300
|
|
9
|
+
expect(config.auto_rotate).to be true
|
|
10
|
+
expect(config.deskew).to be true
|
|
11
|
+
expect(config.denoise).to be false
|
|
12
|
+
expect(config.contrast_enhance).to be true
|
|
13
|
+
expect(config.binarization_method).to eq 'otsu'
|
|
14
|
+
expect(config.invert_colors).to be false
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
it 'creates config with custom values' do
|
|
18
|
+
config = described_class.new(
|
|
19
|
+
target_dpi: 600,
|
|
20
|
+
auto_rotate: false,
|
|
21
|
+
deskew: false,
|
|
22
|
+
denoise: true,
|
|
23
|
+
contrast_enhance: false,
|
|
24
|
+
binarization_method: 'sauvola',
|
|
25
|
+
invert_colors: true
|
|
26
|
+
)
|
|
27
|
+
|
|
28
|
+
expect(config.target_dpi).to eq 600
|
|
29
|
+
expect(config.auto_rotate).to be false
|
|
30
|
+
expect(config.deskew).to be false
|
|
31
|
+
expect(config.denoise).to be true
|
|
32
|
+
expect(config.contrast_enhance).to be false
|
|
33
|
+
expect(config.binarization_method).to eq 'sauvola'
|
|
34
|
+
expect(config.invert_colors).to be true
|
|
35
|
+
end
|
|
36
|
+
|
|
37
|
+
it 'converts target_dpi to integer' do
|
|
38
|
+
config = described_class.new(target_dpi: '300')
|
|
39
|
+
|
|
40
|
+
expect(config.target_dpi).to eq 300
|
|
41
|
+
expect(config.target_dpi).to be_a Integer
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
it 'converts binarization_method to string' do
|
|
45
|
+
config = described_class.new(binarization_method: :niblack)
|
|
46
|
+
|
|
47
|
+
expect(config.binarization_method).to eq 'niblack'
|
|
48
|
+
expect(config.binarization_method).to be_a String
|
|
49
|
+
end
|
|
50
|
+
end
|
|
51
|
+
|
|
52
|
+
describe '#to_h' do
|
|
53
|
+
it 'serializes to hash with all values' do
|
|
54
|
+
config = described_class.new(target_dpi: 300, denoise: true)
|
|
55
|
+
hash = config.to_h
|
|
56
|
+
|
|
57
|
+
expect(hash).to be_a Hash
|
|
58
|
+
expect(hash[:target_dpi]).to eq 300
|
|
59
|
+
expect(hash[:denoise]).to be true
|
|
60
|
+
expect(hash[:auto_rotate]).to be true
|
|
61
|
+
expect(hash[:binarization_method]).to eq 'otsu'
|
|
62
|
+
end
|
|
63
|
+
|
|
64
|
+
it 'always includes all keys in hash' do
|
|
65
|
+
config = described_class.new
|
|
66
|
+
hash = config.to_h
|
|
67
|
+
|
|
68
|
+
expect(hash.keys).to contain_exactly(
|
|
69
|
+
:target_dpi,
|
|
70
|
+
:auto_rotate,
|
|
71
|
+
:deskew,
|
|
72
|
+
:denoise,
|
|
73
|
+
:contrast_enhance,
|
|
74
|
+
:binarization_method,
|
|
75
|
+
:invert_colors
|
|
76
|
+
)
|
|
77
|
+
end
|
|
78
|
+
end
|
|
79
|
+
|
|
80
|
+
describe 'validation' do
|
|
81
|
+
it 'rejects invalid binarization method' do
|
|
82
|
+
expect do
|
|
83
|
+
described_class.new(binarization_method: 'invalid_method')
|
|
84
|
+
end.to raise_error ArgumentError, /Invalid binarization_method/
|
|
85
|
+
end
|
|
86
|
+
|
|
87
|
+
it 'accepts all valid binarization methods' do
|
|
88
|
+
valid_methods = %w[otsu sauvola niblack wolf bradley adaptive]
|
|
89
|
+
|
|
90
|
+
valid_methods.each do |method|
|
|
91
|
+
expect do
|
|
92
|
+
described_class.new(binarization_method: method)
|
|
93
|
+
end.not_to raise_error
|
|
94
|
+
end
|
|
95
|
+
end
|
|
96
|
+
|
|
97
|
+
it 'accepts binarization method as symbol' do
|
|
98
|
+
expect do
|
|
99
|
+
described_class.new(binarization_method: :sauvola)
|
|
100
|
+
end.not_to raise_error
|
|
101
|
+
end
|
|
102
|
+
end
|
|
103
|
+
|
|
104
|
+
describe 'keyword arguments' do
|
|
105
|
+
it 'accepts all keyword arguments' do
|
|
106
|
+
config = described_class.new(
|
|
107
|
+
target_dpi: 600,
|
|
108
|
+
auto_rotate: true,
|
|
109
|
+
deskew: false,
|
|
110
|
+
denoise: true,
|
|
111
|
+
contrast_enhance: false,
|
|
112
|
+
binarization_method: 'bradley',
|
|
113
|
+
invert_colors: true
|
|
114
|
+
)
|
|
115
|
+
|
|
116
|
+
expect(config.target_dpi).to eq 600
|
|
117
|
+
expect(config.auto_rotate).to be true
|
|
118
|
+
expect(config.deskew).to be false
|
|
119
|
+
expect(config.denoise).to be true
|
|
120
|
+
expect(config.contrast_enhance).to be false
|
|
121
|
+
expect(config.binarization_method).to eq 'bradley'
|
|
122
|
+
expect(config.invert_colors).to be true
|
|
123
|
+
end
|
|
124
|
+
end
|
|
125
|
+
|
|
126
|
+
describe 'equality' do
|
|
127
|
+
it 'compares configs by value' do
|
|
128
|
+
config1 = described_class.new(
|
|
129
|
+
target_dpi: 300,
|
|
130
|
+
binarization_method: 'otsu',
|
|
131
|
+
denoise: true
|
|
132
|
+
)
|
|
133
|
+
config2 = described_class.new(
|
|
134
|
+
target_dpi: 300,
|
|
135
|
+
binarization_method: 'otsu',
|
|
136
|
+
denoise: true
|
|
137
|
+
)
|
|
138
|
+
|
|
139
|
+
expect(config1.target_dpi).to eq config2.target_dpi
|
|
140
|
+
expect(config1.binarization_method).to eq config2.binarization_method
|
|
141
|
+
expect(config1.denoise).to eq config2.denoise
|
|
142
|
+
end
|
|
143
|
+
|
|
144
|
+
it 'detects differences in target_dpi' do
|
|
145
|
+
config1 = described_class.new(target_dpi: 300)
|
|
146
|
+
config2 = described_class.new(target_dpi: 600)
|
|
147
|
+
|
|
148
|
+
expect(config1.target_dpi).not_to eq config2.target_dpi
|
|
149
|
+
end
|
|
150
|
+
|
|
151
|
+
it 'detects differences in binarization_method' do
|
|
152
|
+
config1 = described_class.new(binarization_method: 'otsu')
|
|
153
|
+
config2 = described_class.new(binarization_method: 'sauvola')
|
|
154
|
+
|
|
155
|
+
expect(config1.binarization_method).not_to eq config2.binarization_method
|
|
156
|
+
end
|
|
157
|
+
end
|
|
158
|
+
|
|
159
|
+
describe 'nested config integration' do
|
|
160
|
+
it 'can be nested in Extraction config' do
|
|
161
|
+
preprocessing = described_class.new(target_dpi: 600, denoise: true)
|
|
162
|
+
extraction = Kreuzberg::Config::Extraction.new(image_preprocessing: preprocessing)
|
|
163
|
+
|
|
164
|
+
expect(extraction.image_preprocessing).to be_a described_class
|
|
165
|
+
expect(extraction.image_preprocessing.target_dpi).to eq 600
|
|
166
|
+
expect(extraction.image_preprocessing.denoise).to be true
|
|
167
|
+
end
|
|
168
|
+
|
|
169
|
+
it 'accepts hash in Extraction config' do
|
|
170
|
+
extraction = Kreuzberg::Config::Extraction.new(
|
|
171
|
+
image_preprocessing: { target_dpi: 600, binarization_method: 'sauvola' }
|
|
172
|
+
)
|
|
173
|
+
|
|
174
|
+
expect(extraction.image_preprocessing).to be_a described_class
|
|
175
|
+
expect(extraction.image_preprocessing.target_dpi).to eq 600
|
|
176
|
+
expect(extraction.image_preprocessing.binarization_method).to eq 'sauvola'
|
|
177
|
+
end
|
|
178
|
+
|
|
179
|
+
it 'can be nested in Tesseract config' do
|
|
180
|
+
preprocessing = described_class.new(denoise: true)
|
|
181
|
+
tesseract = Kreuzberg::Config::Tesseract.new(preprocessing: preprocessing)
|
|
182
|
+
|
|
183
|
+
expect(tesseract.options[:preprocessing]).to be_a described_class
|
|
184
|
+
expect(tesseract.options[:preprocessing].denoise).to be true
|
|
185
|
+
end
|
|
186
|
+
end
|
|
187
|
+
|
|
188
|
+
describe 'symbol vs string key handling' do
|
|
189
|
+
it 'converts symbol binarization method to string' do
|
|
190
|
+
config = described_class.new(binarization_method: :bradley)
|
|
191
|
+
|
|
192
|
+
expect(config.binarization_method).to eq 'bradley'
|
|
193
|
+
expect(config.binarization_method).to be_a String
|
|
194
|
+
end
|
|
195
|
+
|
|
196
|
+
it 'converts string target_dpi to integer' do
|
|
197
|
+
config = described_class.new(target_dpi: '600')
|
|
198
|
+
|
|
199
|
+
expect(config.target_dpi).to eq 600
|
|
200
|
+
expect(config.target_dpi).to be_a Integer
|
|
201
|
+
end
|
|
202
|
+
end
|
|
203
|
+
|
|
204
|
+
describe 'boolean conversion' do
|
|
205
|
+
it 'converts truthy values to boolean' do
|
|
206
|
+
config = described_class.new(
|
|
207
|
+
auto_rotate: 1,
|
|
208
|
+
deskew: 'yes',
|
|
209
|
+
denoise: true
|
|
210
|
+
)
|
|
211
|
+
|
|
212
|
+
expect(config.auto_rotate).to be true
|
|
213
|
+
expect(config.deskew).to be true
|
|
214
|
+
expect(config.denoise).to be true
|
|
215
|
+
end
|
|
216
|
+
|
|
217
|
+
it 'converts false values to boolean' do
|
|
218
|
+
config = described_class.new(
|
|
219
|
+
auto_rotate: false,
|
|
220
|
+
deskew: false,
|
|
221
|
+
denoise: false
|
|
222
|
+
)
|
|
223
|
+
|
|
224
|
+
expect(config.auto_rotate).to be false
|
|
225
|
+
expect(config.deskew).to be false
|
|
226
|
+
expect(config.denoise).to be false
|
|
227
|
+
end
|
|
228
|
+
end
|
|
229
|
+
|
|
230
|
+
describe 'DPI configuration' do
|
|
231
|
+
it 'accepts realistic DPI values' do
|
|
232
|
+
config = described_class.new(target_dpi: 300)
|
|
233
|
+
|
|
234
|
+
expect(config.target_dpi).to eq 300
|
|
235
|
+
end
|
|
236
|
+
|
|
237
|
+
it 'accepts high DPI values' do
|
|
238
|
+
config = described_class.new(target_dpi: 1200)
|
|
239
|
+
|
|
240
|
+
expect(config.target_dpi).to eq 1200
|
|
241
|
+
end
|
|
242
|
+
|
|
243
|
+
it 'accepts low DPI values' do
|
|
244
|
+
config = described_class.new(target_dpi: 72)
|
|
245
|
+
|
|
246
|
+
expect(config.target_dpi).to eq 72
|
|
247
|
+
end
|
|
248
|
+
end
|
|
249
|
+
end
|
|
@@ -0,0 +1,229 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
RSpec.describe Kreuzberg::Config::Keywords do
|
|
4
|
+
describe '#initialize' do
|
|
5
|
+
it 'creates config with default values' do
|
|
6
|
+
config = described_class.new
|
|
7
|
+
|
|
8
|
+
expect(config.algorithm).to be_nil
|
|
9
|
+
expect(config.max_keywords).to be_nil
|
|
10
|
+
expect(config.min_score).to be_nil
|
|
11
|
+
expect(config.ngram_range).to be_nil
|
|
12
|
+
expect(config.language).to be_nil
|
|
13
|
+
expect(config.yake_params).to be_nil
|
|
14
|
+
expect(config.rake_params).to be_nil
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
it 'creates config with custom values' do
|
|
18
|
+
config = described_class.new(
|
|
19
|
+
algorithm: 'yake',
|
|
20
|
+
max_keywords: 10,
|
|
21
|
+
min_score: 0.5,
|
|
22
|
+
ngram_range: [1, 3],
|
|
23
|
+
language: 'en'
|
|
24
|
+
)
|
|
25
|
+
|
|
26
|
+
expect(config.algorithm).to eq 'yake'
|
|
27
|
+
expect(config.max_keywords).to eq 10
|
|
28
|
+
expect(config.min_score).to eq 0.5
|
|
29
|
+
expect(config.ngram_range).to eq [1, 3]
|
|
30
|
+
expect(config.language).to eq 'en'
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
it 'accepts yake_params as instance' do
|
|
34
|
+
yake_params = Kreuzberg::Config::KeywordYakeParams.new(window_size: 3)
|
|
35
|
+
config = described_class.new(yake_params: yake_params)
|
|
36
|
+
|
|
37
|
+
expect(config.yake_params).to be_a Kreuzberg::Config::KeywordYakeParams
|
|
38
|
+
expect(config.yake_params.window_size).to eq 3
|
|
39
|
+
end
|
|
40
|
+
|
|
41
|
+
it 'converts yake_params hash to instance' do
|
|
42
|
+
config = described_class.new(yake_params: { window_size: 2 })
|
|
43
|
+
|
|
44
|
+
expect(config.yake_params).to be_a Kreuzberg::Config::KeywordYakeParams
|
|
45
|
+
expect(config.yake_params.window_size).to eq 2
|
|
46
|
+
end
|
|
47
|
+
|
|
48
|
+
it 'accepts rake_params as instance' do
|
|
49
|
+
rake_params = Kreuzberg::Config::KeywordRakeParams.new(min_word_length: 3)
|
|
50
|
+
config = described_class.new(rake_params: rake_params)
|
|
51
|
+
|
|
52
|
+
expect(config.rake_params).to be_a Kreuzberg::Config::KeywordRakeParams
|
|
53
|
+
end
|
|
54
|
+
|
|
55
|
+
it 'converts rake_params hash to instance' do
|
|
56
|
+
config = described_class.new(rake_params: { min_word_length: 2 })
|
|
57
|
+
|
|
58
|
+
expect(config.rake_params).to be_a Kreuzberg::Config::KeywordRakeParams
|
|
59
|
+
expect(config.rake_params.min_word_length).to eq 2
|
|
60
|
+
end
|
|
61
|
+
end
|
|
62
|
+
|
|
63
|
+
describe '#to_h' do
|
|
64
|
+
it 'serializes to hash' do
|
|
65
|
+
config = described_class.new(algorithm: 'yake', max_keywords: 10)
|
|
66
|
+
hash = config.to_h
|
|
67
|
+
|
|
68
|
+
expect(hash).to be_a Hash
|
|
69
|
+
expect(hash[:algorithm]).to eq 'yake'
|
|
70
|
+
expect(hash[:max_keywords]).to eq 10
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
it 'includes nested params in hash' do
|
|
74
|
+
config = described_class.new(
|
|
75
|
+
algorithm: 'yake',
|
|
76
|
+
yake_params: { window_size: 3 }
|
|
77
|
+
)
|
|
78
|
+
hash = config.to_h
|
|
79
|
+
|
|
80
|
+
expect(hash[:yake_params]).to be_a Hash
|
|
81
|
+
expect(hash[:yake_params][:window_size]).to eq 3
|
|
82
|
+
end
|
|
83
|
+
|
|
84
|
+
it 'compacts nil values from hash' do
|
|
85
|
+
config = described_class.new(algorithm: 'rake')
|
|
86
|
+
hash = config.to_h
|
|
87
|
+
|
|
88
|
+
expect(hash.key?(:max_keywords)).to be false
|
|
89
|
+
expect(hash.key?(:yake_params)).to be false
|
|
90
|
+
end
|
|
91
|
+
end
|
|
92
|
+
|
|
93
|
+
describe 'validation' do
|
|
94
|
+
it 'accepts valid algorithm names' do
|
|
95
|
+
expect do
|
|
96
|
+
described_class.new(algorithm: 'yake')
|
|
97
|
+
end.not_to raise_error
|
|
98
|
+
end
|
|
99
|
+
|
|
100
|
+
it 'accepts valid max_keywords' do
|
|
101
|
+
expect do
|
|
102
|
+
described_class.new(max_keywords: 20)
|
|
103
|
+
end.not_to raise_error
|
|
104
|
+
end
|
|
105
|
+
|
|
106
|
+
it 'raises error for invalid yake_params type' do
|
|
107
|
+
expect do
|
|
108
|
+
described_class.new(yake_params: 'invalid')
|
|
109
|
+
end.to raise_error ArgumentError, /Expected.*KeywordYakeParams.*Hash.*nil/
|
|
110
|
+
end
|
|
111
|
+
|
|
112
|
+
it 'raises error for invalid rake_params type' do
|
|
113
|
+
expect do
|
|
114
|
+
described_class.new(rake_params: 'invalid')
|
|
115
|
+
end.to raise_error ArgumentError, /Expected.*KeywordRakeParams.*Hash.*nil/
|
|
116
|
+
end
|
|
117
|
+
end
|
|
118
|
+
|
|
119
|
+
describe 'keyword arguments' do
|
|
120
|
+
it 'accepts all keyword arguments' do
|
|
121
|
+
config = described_class.new(
|
|
122
|
+
algorithm: 'yake',
|
|
123
|
+
max_keywords: 15,
|
|
124
|
+
min_score: 0.7,
|
|
125
|
+
ngram_range: [1, 2],
|
|
126
|
+
language: 'fr',
|
|
127
|
+
yake_params: { window_size: 3 }
|
|
128
|
+
)
|
|
129
|
+
|
|
130
|
+
expect(config.algorithm).to eq 'yake'
|
|
131
|
+
expect(config.max_keywords).to eq 15
|
|
132
|
+
expect(config.min_score).to eq 0.7
|
|
133
|
+
expect(config.ngram_range).to eq [1, 2]
|
|
134
|
+
expect(config.language).to eq 'fr'
|
|
135
|
+
expect(config.yake_params).to be_a Kreuzberg::Config::KeywordYakeParams
|
|
136
|
+
end
|
|
137
|
+
end
|
|
138
|
+
|
|
139
|
+
describe 'equality' do
|
|
140
|
+
it 'compares configs by value' do
|
|
141
|
+
config1 = described_class.new(algorithm: 'yake', max_keywords: 10)
|
|
142
|
+
config2 = described_class.new(algorithm: 'yake', max_keywords: 10)
|
|
143
|
+
|
|
144
|
+
expect(config1.algorithm).to eq config2.algorithm
|
|
145
|
+
expect(config1.max_keywords).to eq config2.max_keywords
|
|
146
|
+
end
|
|
147
|
+
|
|
148
|
+
it 'detects differences in algorithm' do
|
|
149
|
+
config1 = described_class.new(algorithm: 'yake')
|
|
150
|
+
config2 = described_class.new(algorithm: 'rake')
|
|
151
|
+
|
|
152
|
+
expect(config1.algorithm).not_to eq config2.algorithm
|
|
153
|
+
end
|
|
154
|
+
|
|
155
|
+
it 'detects differences in max_keywords' do
|
|
156
|
+
config1 = described_class.new(max_keywords: 10)
|
|
157
|
+
config2 = described_class.new(max_keywords: 20)
|
|
158
|
+
|
|
159
|
+
expect(config1.max_keywords).not_to eq config2.max_keywords
|
|
160
|
+
end
|
|
161
|
+
end
|
|
162
|
+
|
|
163
|
+
describe 'nested config integration' do
|
|
164
|
+
it 'can be nested in Extraction config' do
|
|
165
|
+
keywords = described_class.new(algorithm: 'yake', max_keywords: 15)
|
|
166
|
+
extraction = Kreuzberg::Config::Extraction.new(keywords: keywords)
|
|
167
|
+
|
|
168
|
+
expect(extraction.keywords).to be_a described_class
|
|
169
|
+
expect(extraction.keywords.algorithm).to eq 'yake'
|
|
170
|
+
expect(extraction.keywords.max_keywords).to eq 15
|
|
171
|
+
end
|
|
172
|
+
|
|
173
|
+
it 'accepts hash in Extraction config' do
|
|
174
|
+
extraction = Kreuzberg::Config::Extraction.new(
|
|
175
|
+
keywords: { algorithm: 'rake', max_keywords: 10 }
|
|
176
|
+
)
|
|
177
|
+
|
|
178
|
+
expect(extraction.keywords).to be_a described_class
|
|
179
|
+
expect(extraction.keywords.algorithm).to eq 'rake'
|
|
180
|
+
expect(extraction.keywords.max_keywords).to eq 10
|
|
181
|
+
end
|
|
182
|
+
end
|
|
183
|
+
|
|
184
|
+
describe 'symbol vs string key handling' do
|
|
185
|
+
it 'converts symbol algorithm to string' do
|
|
186
|
+
config = described_class.new(algorithm: :yake)
|
|
187
|
+
|
|
188
|
+
expect(config.algorithm).to eq 'yake'
|
|
189
|
+
expect(config.algorithm).to be_a String
|
|
190
|
+
end
|
|
191
|
+
|
|
192
|
+
it 'converts symbol language to string' do
|
|
193
|
+
config = described_class.new(language: :eng)
|
|
194
|
+
|
|
195
|
+
expect(config.language).to eq 'eng'
|
|
196
|
+
expect(config.language).to be_a String
|
|
197
|
+
end
|
|
198
|
+
|
|
199
|
+
it 'converts ngram_range values to integers' do
|
|
200
|
+
config = described_class.new(ngram_range: %w[1 3])
|
|
201
|
+
|
|
202
|
+
expect(config.ngram_range).to eq [1, 3]
|
|
203
|
+
expect(config.ngram_range.all?(Integer)).to be true
|
|
204
|
+
end
|
|
205
|
+
end
|
|
206
|
+
|
|
207
|
+
describe 'parameter conversions' do
|
|
208
|
+
it 'converts max_keywords to integer' do
|
|
209
|
+
config = described_class.new(max_keywords: '20')
|
|
210
|
+
|
|
211
|
+
expect(config.max_keywords).to eq 20
|
|
212
|
+
expect(config.max_keywords).to be_a Integer
|
|
213
|
+
end
|
|
214
|
+
|
|
215
|
+
it 'converts min_score to float' do
|
|
216
|
+
config = described_class.new(min_score: '0.75')
|
|
217
|
+
|
|
218
|
+
expect(config.min_score).to eq 0.75
|
|
219
|
+
expect(config.min_score).to be_a Float
|
|
220
|
+
end
|
|
221
|
+
|
|
222
|
+
it 'converts ngram_range to array of integers' do
|
|
223
|
+
config = described_class.new(ngram_range: [1, 2])
|
|
224
|
+
|
|
225
|
+
expect(config.ngram_range).to eq [1, 2]
|
|
226
|
+
expect(config.ngram_range.all?(Integer)).to be true
|
|
227
|
+
end
|
|
228
|
+
end
|
|
229
|
+
end
|