RubyGems - kreuzberg - Versions diffs - 4.0.0.rc2 → 4.0.0 - Mend

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.

Files changed (446) hide show

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

data/vendor/kreuzberg/tests/core_integration.rs CHANGED Viewed

@@ -1,510 +1,519 @@
-//! Integration tests for core extraction functionality.
-//!
-//! These tests verify the end-to-end behavior of the extraction pipeline,
-//! config loading, MIME detection, and batch processing.
-use kreuzberg::{
-    ExtractionConfig, batch_extract_bytes, batch_extract_bytes_sync, batch_extract_file, batch_extract_file_sync,
-    detect_mime_type, extract_bytes, extract_bytes_sync, extract_file, extract_file_sync, validate_mime_type,
-};
-use std::fs::{self, File};
-use std::io::Write;
-use tempfile::tempdir;
-fn trim_trailing_newlines(value: &str) -> &str {
-    value.trim_end_matches(['\n', '\r'])
-}
-fn assert_text_content(actual: &str, expected: &str) {
-    assert_eq!(
-        trim_trailing_newlines(actual),
-        expected,
-        "Content mismatch after trimming trailing newlines"
-    );
-}
-/// Test basic file extraction with MIME detection.
-#[tokio::test]
-async fn test_extract_file_basic() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("test.txt");
-    let mut file = File::create(&file_path).unwrap();
-    file.write_all(b"Hello, Kreuzberg!").unwrap();
-    let config = ExtractionConfig::default();
-    let result = extract_file(&file_path, None, &config).await;
-    assert!(result.is_ok(), "Basic file extraction should succeed");
-    let result = result.unwrap();
-    assert_text_content(&result.content, "Hello, Kreuzberg!");
-    assert_eq!(result.mime_type, "text/plain");
-    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-    assert!(result.detected_languages.is_none(), "Language detection not enabled");
-    assert!(result.tables.is_empty(), "Text file should not have tables");
-}
-/// Test extraction with explicit MIME type override.
-#[tokio::test]
-async fn test_extract_file_with_mime_override() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("data.bin");
-    let mut file = File::create(&file_path).unwrap();
-    file.write_all(b"Binary content").unwrap();
-    let config = ExtractionConfig::default();
-    let result = extract_file(&file_path, Some("text/plain"), &config).await;
-    assert!(result.is_ok(), "MIME override should work");
-    let result = result.unwrap();
-    assert_eq!(result.mime_type, "text/plain");
-    assert!(!result.content.is_empty(), "Should extract content");
-    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-}
-/// Test extraction of multiple file types.
-#[tokio::test]
-async fn test_extract_multiple_file_types() {
-    let dir = tempdir().unwrap();
-    let config = ExtractionConfig::default();
-    let test_files: Vec<(&str, &[u8], &str)> = vec![
-        ("test.txt", b"text content", "text/plain"),
-        ("test.json", b"{\"key\": \"value\"}", "application/json"),
-        #[cfg(feature = "xml")]
-        ("test.xml", b"<root>data</root>", "application/xml"),
-        #[cfg(feature = "html")]
-        ("test.html", b"<html><body>test</body></html>", "text/html"),
-    ];
-    for (filename, content, expected_mime) in test_files {
-        let file_path = dir.path().join(filename);
-        fs::write(&file_path, content).unwrap();
-        let result = extract_file(&file_path, None, &config).await.unwrap();
-        assert_eq!(result.mime_type, expected_mime, "MIME type mismatch for {}", filename);
-        assert!(
-            !result.content.is_empty(),
-            "Content should not be empty for {}",
-            filename
-        );
-        assert!(result.chunks.is_none(), "Chunks should be None for {}", filename);
-        assert!(
-            result.detected_languages.is_none(),
-            "Language detection not enabled for {}",
-            filename
-        );
-    }
-}
-/// Test extract_bytes with various MIME types.
-#[tokio::test]
-async fn test_extract_bytes_various_mime_types() {
-    let config = ExtractionConfig::default();
-    let test_cases: Vec<(&[u8], &str)> = vec![
-        (b"text content", "text/plain"),
-        (b"{\"key\": \"value\"}", "application/json"),
-        #[cfg(feature = "xml")]
-        (b"<root>data</root>", "application/xml"),
-    ];
-    for (content, mime_type) in test_cases {
-        let result = extract_bytes(content, mime_type, &config).await;
-        assert!(result.is_ok(), "Extract bytes failed for MIME type: {}", mime_type);
-        let result = result.unwrap();
-        assert_eq!(result.mime_type, mime_type, "MIME type mismatch");
-        assert!(
-            !result.content.is_empty(),
-            "Content should not be empty for {}",
-            mime_type
-        );
-        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-        assert!(result.detected_languages.is_none(), "Language detection not enabled");
-    }
-}
-/// Test batch extraction with concurrent processing.
-#[tokio::test]
-async fn test_batch_extract_file_concurrency() {
-    let dir = tempdir().unwrap();
-    let config = ExtractionConfig::default();
-    let num_files = 10;
-    let mut paths = Vec::new();
-    for i in 0..num_files {
-        let file_path = dir.path().join(format!("test_{}.txt", i));
-        fs::write(&file_path, format!("Content {}", i)).unwrap();
-        paths.push(file_path);
-    }
-    let results = batch_extract_file(paths.clone(), &config).await;
-    assert!(results.is_ok());
-    let results = results.unwrap();
-    assert_eq!(results.len(), num_files);
-    for (i, result) in results.iter().enumerate() {
-        assert!(
-            result.content.contains(&i.to_string()),
-            "Content should contain file number"
-        );
-        assert_eq!(result.mime_type, "text/plain", "MIME type should be text/plain");
-        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-        assert!(result.detected_languages.is_none(), "Language detection not enabled");
-        assert!(result.metadata.error.is_none(), "Should not have errors");
-    }
-}
-/// Test batch extraction with empty input.
-#[tokio::test]
-async fn test_batch_extract_empty() {
-    let config = ExtractionConfig::default();
-    let paths: Vec<std::path::PathBuf> = vec![];
-    let results = batch_extract_file(paths, &config).await;
-    assert!(results.is_ok());
-    assert_eq!(results.unwrap().len(), 0);
-}
-/// Test batch_extract_bytes with concurrent processing.
-#[tokio::test]
-async fn test_batch_extract_bytes_concurrency() {
-    let config = ExtractionConfig::default();
-    let contents = vec![
-        (b"content 1".as_slice(), "text/plain"),
-        (b"content 2".as_slice(), "text/plain"),
-        (b"content 3".as_slice(), "text/plain"),
-        (b"content 4".as_slice(), "text/plain"),
-        (b"content 5".as_slice(), "text/plain"),
-    ];
-    let results = batch_extract_bytes(contents, &config).await;
-    assert!(results.is_ok());
-    let results = results.unwrap();
-    assert_eq!(results.len(), 5);
-    for (i, result) in results.iter().enumerate() {
-        let expected_content = format!("content {}", i + 1);
-        assert_eq!(
-            trim_trailing_newlines(&result.content),
-            expected_content,
-            "Content mismatch for item {}",
-            i
-        );
-        assert_eq!(result.mime_type, "text/plain", "MIME type should be text/plain");
-        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-        assert!(result.detected_languages.is_none(), "Language detection not enabled");
-        assert!(result.metadata.error.is_none(), "Should not have errors");
-    }
-}
-/// Test sync wrappers for extraction functions.
-#[test]
-fn test_sync_wrappers() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("sync_test.txt");
-    fs::write(&file_path, "sync content").unwrap();
-    let config = ExtractionConfig::default();
-    let result = extract_file_sync(&file_path, None, &config);
-    assert!(result.is_ok(), "Sync file extraction should succeed");
-    let extraction = result.unwrap();
-    assert_text_content(&extraction.content, "sync content");
-    assert!(extraction.chunks.is_none(), "Chunks should be None");
-    let result = extract_bytes_sync(b"test bytes", "text/plain", &config);
-    assert!(result.is_ok(), "Sync bytes extraction should succeed");
-    let extraction = result.unwrap();
-    assert_text_content(&extraction.content, "test bytes");
-    assert!(extraction.chunks.is_none(), "Chunks should be None");
-    let paths = vec![file_path];
-    let results = batch_extract_file_sync(paths, &config);
-    assert!(results.is_ok(), "Batch sync file should succeed");
-    let results = results.unwrap();
-    assert_eq!(results.len(), 1);
-    assert_text_content(&results[0].content, "sync content");
-    assert!(results[0].chunks.is_none(), "Chunks should be None");
-    let contents = vec![(b"test".as_slice(), "text/plain")];
-    let results = batch_extract_bytes_sync(contents, &config);
-    assert!(results.is_ok(), "Batch bytes sync should succeed");
-    let results = results.unwrap();
-    assert_eq!(results.len(), 1);
-    assert_text_content(&results[0].content, "test");
-    assert!(results[0].chunks.is_none(), "Chunks should be None");
-}
-/// Test MIME type detection for various extensions.
-#[test]
-fn test_mime_detection_comprehensive() {
-    let dir = tempdir().unwrap();
-    let test_cases = vec![
-        ("test.txt", "text/plain"),
-        ("test.md", "text/markdown"),
-        ("test.html", "text/html"),
-        ("test.json", "application/json"),
-        ("test.yaml", "application/x-yaml"),
-        ("test.toml", "application/toml"),
-        ("test.xml", "application/xml"),
-        ("test.pdf", "application/pdf"),
-        (
-            "test.xlsx",
-            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        ),
-        (
-            "test.docx",
-            "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-        ),
-        (
-            "test.pptx",
-            "application/vnd.openxmlformats-officedocument.presentationml.presentation",
-        ),
-        ("test.png", "image/png"),
-        ("test.jpg", "image/jpeg"),
-        ("test.gif", "image/gif"),
-        ("test.eml", "message/rfc822"),
-    ];
-    for (filename, expected_mime) in test_cases {
-        let file_path = dir.path().join(filename);
-        File::create(&file_path).unwrap();
-        let detected = detect_mime_type(&file_path, true).unwrap();
-        assert_eq!(detected, expected_mime, "Failed for {}", filename);
-        let validated = validate_mime_type(&detected);
-        assert!(validated.is_ok(), "Validation failed for {}", expected_mime);
-    }
-}
-/// Test MIME type validation.
-#[test]
-fn test_mime_validation() {
-    assert!(validate_mime_type("application/pdf").is_ok());
-    assert!(validate_mime_type("text/plain").is_ok());
-    assert!(validate_mime_type("image/png").is_ok());
-    assert!(validate_mime_type("image/custom-format").is_ok());
-    assert!(validate_mime_type("video/mp4").is_err());
-    assert!(validate_mime_type("application/unknown").is_err());
-}
-/// Test case-insensitive extension handling.
-#[test]
-fn test_case_insensitive_extensions() {
-    let dir = tempdir().unwrap();
-    let test_cases = vec![
-        ("test.PDF", "application/pdf"),
-        ("test.TXT", "text/plain"),
-        ("test.Json", "application/json"),
-        (
-            "test.XLSX",
-            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
-        ),
-    ];
-    for (filename, expected_mime) in test_cases {
-        let file_path = dir.path().join(filename);
-        File::create(&file_path).unwrap();
-        let detected = detect_mime_type(&file_path, true).unwrap();
-        assert_eq!(detected, expected_mime, "Failed for {}", filename);
-    }
-}
-/// Test config loading from TOML file.
-#[test]
-fn test_config_loading() {
-    let dir = tempdir().unwrap();
-    let config_path = dir.path().join("kreuzberg.toml");
-    fs::write(
-        &config_path,
-        r#"
-use_cache = false
-enable_quality_processing = true
-force_ocr = false
-[ocr]
-backend = "tesseract"
-language = "deu"
-[chunking]
-max_chars = 2000
-max_overlap = 300
-    "#,
-    )
-    .unwrap();
-    let config = ExtractionConfig::from_toml_file(&config_path).unwrap();
-    assert!(!config.use_cache);
-    assert!(config.enable_quality_processing);
-    assert!(!config.force_ocr);
-    let ocr_config = config.ocr.unwrap();
-    assert_eq!(ocr_config.backend, "tesseract");
-    assert_eq!(ocr_config.language, "deu");
-    let chunking_config = config.chunking.unwrap();
-    assert_eq!(chunking_config.max_chars, 2000);
-    assert_eq!(chunking_config.max_overlap, 300);
-}
-/// Test config discovery in parent directories.
-#[test]
-fn test_config_discovery() {
-    let dir = tempdir().unwrap();
-    let subdir = dir.path().join("subdir");
-    fs::create_dir(&subdir).unwrap();
-    let config_path = dir.path().join("kreuzberg.toml");
-    fs::write(
-        &config_path,
-        r#"
-use_cache = false
-enable_quality_processing = true
-    "#,
-    )
-    .unwrap();
-    let original_dir = std::env::current_dir().unwrap();
-    std::env::set_current_dir(&subdir).unwrap();
-    let config = ExtractionConfig::discover().unwrap();
-    assert!(config.is_some());
-    assert!(!config.unwrap().use_cache);
-    std::env::set_current_dir(original_dir).unwrap();
-}
-/// Test error handling for nonexistent files.
-#[tokio::test]
-async fn test_nonexistent_file_error() {
-    let config = ExtractionConfig::default();
-    let result = extract_file("/nonexistent/file.txt", None, &config).await;
-    assert!(result.is_err());
-    assert!(matches!(
-        result.unwrap_err(),
-        kreuzberg::KreuzbergError::Validation { .. }
-    ));
-}
-/// Test error handling for unsupported MIME types.
-#[tokio::test]
-async fn test_unsupported_mime_type_error() {
-    let config = ExtractionConfig::default();
-    let result = extract_bytes(b"test", "video/mp4", &config).await;
-    assert!(result.is_err());
-    assert!(matches!(
-        result.unwrap_err(),
-        kreuzberg::KreuzbergError::UnsupportedFormat(_)
-    ));
-}
-/// Test pipeline execution (currently stub, will be expanded in Phase 2).
-#[tokio::test]
-async fn test_pipeline_execution() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("pipeline_test.txt");
-    fs::write(&file_path, "pipeline content").unwrap();
-    let config = ExtractionConfig {
-        enable_quality_processing: true,
-        ..Default::default()
-    };
-    let result = extract_file(&file_path, None, &config).await;
-    assert!(result.is_ok(), "Pipeline execution should succeed");
-    let result = result.unwrap();
-    assert_text_content(&result.content, "pipeline content");
-    assert_eq!(result.mime_type, "text/plain");
-    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
-    assert!(result.detected_languages.is_none(), "Language detection not enabled");
-}
-/// Test extraction with OCR config (placeholder test for Phase 2).
-#[tokio::test]
-async fn test_extraction_with_ocr_config() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("ocr_test.txt");
-    fs::write(&file_path, "ocr content").unwrap();
-    let config = ExtractionConfig {
-        ocr: Some(kreuzberg::OcrConfig {
-            tesseract_config: None,
-            backend: "tesseract".to_string(),
-            language: "eng".to_string(),
-        }),
-        force_ocr: true,
-        ..Default::default()
-    };
-    let result = extract_file(&file_path, None, &config).await;
-    assert!(result.is_ok());
-}
-/// Test extraction with chunking config.
-#[cfg(feature = "chunking")]
-#[tokio::test]
-async fn test_extraction_with_chunking_config() {
-    let dir = tempdir().unwrap();
-    let file_path = dir.path().join("chunking_test.txt");
-    let long_content = "content for chunking. ".repeat(100);
-    fs::write(&file_path, &long_content).unwrap();
-    let config = ExtractionConfig {
-        chunking: Some(kreuzberg::ChunkingConfig {
-            max_chars: 100,
-            max_overlap: 20,
-            embedding: None,
-            preset: None,
-        }),
-        ..Default::default()
-    };
-    let result = extract_file(&file_path, None, &config).await;
-    assert!(result.is_ok(), "Extraction with chunking should succeed");
-    let result = result.unwrap();
-    assert!(
-        result.chunks.is_some(),
-        "Chunks should be populated when chunking enabled"
-    );
-    let chunks = result.chunks.unwrap();
-    assert!(chunks.len() > 1, "Should have multiple chunks for long content");
-    assert!(result.metadata.additional.contains_key("chunk_count"));
-    let chunk_count = result.metadata.additional.get("chunk_count").unwrap();
-    assert_eq!(
-        chunks.len(),
-        chunk_count.as_u64().unwrap() as usize,
-        "chunk_count should match chunks length"
-    );
-    for chunk in &chunks {
-        assert!(
-            chunk.content.len() <= 100 + 20,
-            "Chunk length {} exceeds max_chars + overlap",
-            chunk.content.len()
-        );
-    }
-}
+//! Integration tests for core extraction functionality.
+//!
+//! These tests verify the end-to-end behavior of the extraction pipeline,
+//! config loading, MIME detection, and batch processing.
+use kreuzberg::{
+    ExtractionConfig, batch_extract_bytes, batch_extract_bytes_sync, batch_extract_file, batch_extract_file_sync,
+    detect_mime_type, extract_bytes, extract_bytes_sync, extract_file, extract_file_sync, validate_mime_type,
+};
+use std::fs::{self, File};
+use std::io::Write;
+use tempfile::tempdir;
+fn trim_trailing_newlines(value: &str) -> &str {
+    value.trim_end_matches(['\n', '\r'])
+}
+fn assert_text_content(actual: &str, expected: &str) {
+    assert_eq!(
+        trim_trailing_newlines(actual),
+        expected,
+        "Content mismatch after trimming trailing newlines"
+    );
+}
+/// Test basic file extraction with MIME detection.
+#[tokio::test]
+async fn test_extract_file_basic() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("test.txt");
+    let mut file = File::create(&file_path).unwrap();
+    file.write_all(b"Hello, Kreuzberg!").unwrap();
+    let config = ExtractionConfig::default();
+    let result = extract_file(&file_path, None, &config).await;
+    assert!(result.is_ok(), "Basic file extraction should succeed");
+    let result = result.unwrap();
+    assert_text_content(&result.content, "Hello, Kreuzberg!");
+    assert_eq!(result.mime_type, "text/plain");
+    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+    assert!(result.detected_languages.is_none(), "Language detection not enabled");
+    assert!(result.tables.is_empty(), "Text file should not have tables");
+}
+/// Test extraction with explicit MIME type override.
+#[tokio::test]
+async fn test_extract_file_with_mime_override() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("data.bin");
+    let mut file = File::create(&file_path).unwrap();
+    file.write_all(b"Binary content").unwrap();
+    let config = ExtractionConfig::default();
+    let result = extract_file(&file_path, Some("text/plain"), &config).await;
+    assert!(result.is_ok(), "MIME override should work");
+    let result = result.unwrap();
+    assert_eq!(result.mime_type, "text/plain");
+    assert!(!result.content.is_empty(), "Should extract content");
+    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+}
+/// Test extraction of multiple file types.
+#[tokio::test]
+async fn test_extract_multiple_file_types() {
+    let dir = tempdir().unwrap();
+    let config = ExtractionConfig::default();
+    let test_files: Vec<(&str, &[u8], &str)> = vec![
+        ("test.txt", b"text content", "text/plain"),
+        ("test.json", b"{\"key\": \"value\"}", "application/json"),
+        #[cfg(feature = "xml")]
+        ("test.xml", b"<root>data</root>", "application/xml"),
+        #[cfg(feature = "html")]
+        ("test.html", b"<html><body>test</body></html>", "text/html"),
+    ];
+    for (filename, content, expected_mime) in test_files {
+        let file_path = dir.path().join(filename);
+        fs::write(&file_path, content).unwrap();
+        let result = extract_file(&file_path, None, &config).await.unwrap();
+        assert_eq!(result.mime_type, expected_mime, "MIME type mismatch for {}", filename);
+        assert!(
+            !result.content.is_empty(),
+            "Content should not be empty for {}",
+            filename
+        );
+        assert!(result.chunks.is_none(), "Chunks should be None for {}", filename);
+        assert!(
+            result.detected_languages.is_none(),
+            "Language detection not enabled for {}",
+            filename
+        );
+    }
+}
+/// Test extract_bytes with various MIME types.
+#[tokio::test]
+async fn test_extract_bytes_various_mime_types() {
+    let config = ExtractionConfig::default();
+    let test_cases: Vec<(&[u8], &str)> = vec![
+        (b"text content", "text/plain"),
+        (b"{\"key\": \"value\"}", "application/json"),
+        #[cfg(feature = "xml")]
+        (b"<root>data</root>", "application/xml"),
+    ];
+    for (content, mime_type) in test_cases {
+        let result = extract_bytes(content, mime_type, &config).await;
+        assert!(result.is_ok(), "Extract bytes failed for MIME type: {}", mime_type);
+        let result = result.unwrap();
+        assert_eq!(result.mime_type, mime_type, "MIME type mismatch");
+        assert!(
+            !result.content.is_empty(),
+            "Content should not be empty for {}",
+            mime_type
+        );
+        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+        assert!(result.detected_languages.is_none(), "Language detection not enabled");
+    }
+}
+/// Test batch extraction with concurrent processing.
+#[tokio::test]
+async fn test_batch_extract_file_concurrency() {
+    let dir = tempdir().unwrap();
+    let config = ExtractionConfig::default();
+    let num_files = 10;
+    let mut paths = Vec::new();
+    for i in 0..num_files {
+        let file_path = dir.path().join(format!("test_{}.txt", i));
+        fs::write(&file_path, format!("Content {}", i)).unwrap();
+        paths.push(file_path);
+    }
+    let results = batch_extract_file(paths.clone(), &config).await;
+    assert!(results.is_ok());
+    let results = results.unwrap();
+    assert_eq!(results.len(), num_files);
+    for (i, result) in results.iter().enumerate() {
+        assert!(
+            result.content.contains(&i.to_string()),
+            "Content should contain file number"
+        );
+        assert_eq!(result.mime_type, "text/plain", "MIME type should be text/plain");
+        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+        assert!(result.detected_languages.is_none(), "Language detection not enabled");
+        assert!(result.metadata.error.is_none(), "Should not have errors");
+    }
+}
+/// Test batch extraction with empty input.
+#[tokio::test]
+async fn test_batch_extract_empty() {
+    let config = ExtractionConfig::default();
+    let paths: Vec<std::path::PathBuf> = vec![];
+    let results = batch_extract_file(paths, &config).await;
+    assert!(results.is_ok());
+    assert_eq!(results.unwrap().len(), 0);
+}
+/// Test batch_extract_bytes with concurrent processing.
+#[tokio::test]
+async fn test_batch_extract_bytes_concurrency() {
+    let config = ExtractionConfig::default();
+    let contents = vec![
+        (b"content 1".as_slice(), "text/plain"),
+        (b"content 2".as_slice(), "text/plain"),
+        (b"content 3".as_slice(), "text/plain"),
+        (b"content 4".as_slice(), "text/plain"),
+        (b"content 5".as_slice(), "text/plain"),
+    ];
+    let owned_contents: Vec<(Vec<u8>, String)> = contents
+        .into_iter()
+        .map(|(bytes, mime)| (bytes.to_vec(), mime.to_string()))
+        .collect();
+    let results = batch_extract_bytes(owned_contents, &config).await;
+    assert!(results.is_ok());
+    let results = results.unwrap();
+    assert_eq!(results.len(), 5);
+    for (i, result) in results.iter().enumerate() {
+        let expected_content = format!("content {}", i + 1);
+        assert_eq!(
+            trim_trailing_newlines(&result.content),
+            expected_content,
+            "Content mismatch for item {}",
+            i
+        );
+        assert_eq!(result.mime_type, "text/plain", "MIME type should be text/plain");
+        assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+        assert!(result.detected_languages.is_none(), "Language detection not enabled");
+        assert!(result.metadata.error.is_none(), "Should not have errors");
+    }
+}
+/// Test sync wrappers for extraction functions.
+#[test]
+fn test_sync_wrappers() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("sync_test.txt");
+    fs::write(&file_path, "sync content").unwrap();
+    let config = ExtractionConfig::default();
+    let result = extract_file_sync(&file_path, None, &config);
+    assert!(result.is_ok(), "Sync file extraction should succeed");
+    let extraction = result.unwrap();
+    assert_text_content(&extraction.content, "sync content");
+    assert!(extraction.chunks.is_none(), "Chunks should be None");
+    let result = extract_bytes_sync(b"test bytes", "text/plain", &config);
+    assert!(result.is_ok(), "Sync bytes extraction should succeed");
+    let extraction = result.unwrap();
+    assert_text_content(&extraction.content, "test bytes");
+    assert!(extraction.chunks.is_none(), "Chunks should be None");
+    let paths = vec![file_path];
+    let results = batch_extract_file_sync(paths, &config);
+    assert!(results.is_ok(), "Batch sync file should succeed");
+    let results = results.unwrap();
+    assert_eq!(results.len(), 1);
+    assert_text_content(&results[0].content, "sync content");
+    assert!(results[0].chunks.is_none(), "Chunks should be None");
+    let contents = vec![(b"test".as_slice(), "text/plain")];
+    let owned_contents: Vec<(Vec<u8>, String)> = contents
+        .into_iter()
+        .map(|(bytes, mime)| (bytes.to_vec(), mime.to_string()))
+        .collect();
+    let results = batch_extract_bytes_sync(owned_contents, &config);
+    assert!(results.is_ok(), "Batch bytes sync should succeed");
+    let results = results.unwrap();
+    assert_eq!(results.len(), 1);
+    assert_text_content(&results[0].content, "test");
+    assert!(results[0].chunks.is_none(), "Chunks should be None");
+}
+/// Test MIME type detection for various extensions.
+#[test]
+fn test_mime_detection_comprehensive() {
+    let dir = tempdir().unwrap();
+    let test_cases = vec![
+        ("test.txt", "text/plain"),
+        ("test.md", "text/markdown"),
+        ("test.html", "text/html"),
+        ("test.json", "application/json"),
+        ("test.yaml", "application/x-yaml"),
+        ("test.toml", "application/toml"),
+        ("test.xml", "application/xml"),
+        ("test.pdf", "application/pdf"),
+        (
+            "test.xlsx",
+            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+        ),
+        (
+            "test.docx",
+            "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+        ),
+        (
+            "test.pptx",
+            "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+        ),
+        ("test.png", "image/png"),
+        ("test.jpg", "image/jpeg"),
+        ("test.gif", "image/gif"),
+        ("test.eml", "message/rfc822"),
+    ];
+    for (filename, expected_mime) in test_cases {
+        let file_path = dir.path().join(filename);
+        File::create(&file_path).unwrap();
+        let detected = detect_mime_type(&file_path, true).unwrap();
+        assert_eq!(detected, expected_mime, "Failed for {}", filename);
+        let validated = validate_mime_type(&detected);
+        assert!(validated.is_ok(), "Validation failed for {}", expected_mime);
+    }
+}
+/// Test MIME type validation.
+#[test]
+fn test_mime_validation() {
+    assert!(validate_mime_type("application/pdf").is_ok());
+    assert!(validate_mime_type("text/plain").is_ok());
+    assert!(validate_mime_type("image/png").is_ok());
+    assert!(validate_mime_type("image/custom-format").is_ok());
+    assert!(validate_mime_type("video/mp4").is_err());
+    assert!(validate_mime_type("application/unknown").is_err());
+}
+/// Test case-insensitive extension handling.
+#[test]
+fn test_case_insensitive_extensions() {
+    let dir = tempdir().unwrap();
+    let test_cases = vec![
+        ("test.PDF", "application/pdf"),
+        ("test.TXT", "text/plain"),
+        ("test.Json", "application/json"),
+        (
+            "test.XLSX",
+            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+        ),
+    ];
+    for (filename, expected_mime) in test_cases {
+        let file_path = dir.path().join(filename);
+        File::create(&file_path).unwrap();
+        let detected = detect_mime_type(&file_path, true).unwrap();
+        assert_eq!(detected, expected_mime, "Failed for {}", filename);
+    }
+}
+/// Test config loading from TOML file.
+#[test]
+fn test_config_loading() {
+    let dir = tempdir().unwrap();
+    let config_path = dir.path().join("kreuzberg.toml");
+    fs::write(
+        &config_path,
+        r#"
+use_cache = false
+enable_quality_processing = true
+force_ocr = false
+[ocr]
+backend = "tesseract"
+language = "deu"
+[chunking]
+max_chars = 2000
+max_overlap = 300
+    "#,
+    )
+    .unwrap();
+    let config = ExtractionConfig::from_toml_file(&config_path).unwrap();
+    assert!(!config.use_cache);
+    assert!(config.enable_quality_processing);
+    assert!(!config.force_ocr);
+    let ocr_config = config.ocr.unwrap();
+    assert_eq!(ocr_config.backend, "tesseract");
+    assert_eq!(ocr_config.language, "deu");
+    let chunking_config = config.chunking.unwrap();
+    assert_eq!(chunking_config.max_chars, 2000);
+    assert_eq!(chunking_config.max_overlap, 300);
+}
+/// Test config discovery in parent directories.
+#[test]
+fn test_config_discovery() {
+    let dir = tempdir().unwrap();
+    let subdir = dir.path().join("subdir");
+    fs::create_dir(&subdir).unwrap();
+    let config_path = dir.path().join("kreuzberg.toml");
+    fs::write(
+        &config_path,
+        r#"
+use_cache = false
+enable_quality_processing = true
+    "#,
+    )
+    .unwrap();
+    let original_dir = std::env::current_dir().unwrap();
+    std::env::set_current_dir(&subdir).unwrap();
+    let config = ExtractionConfig::discover().unwrap();
+    assert!(config.is_some());
+    assert!(!config.unwrap().use_cache);
+    std::env::set_current_dir(original_dir).unwrap();
+}
+/// Test error handling for nonexistent files.
+#[tokio::test]
+async fn test_nonexistent_file_error() {
+    let config = ExtractionConfig::default();
+    let result = extract_file("/nonexistent/file.txt", None, &config).await;
+    assert!(result.is_err());
+    assert!(matches!(
+        result.unwrap_err(),
+        kreuzberg::KreuzbergError::Validation { .. }
+    ));
+}
+/// Test error handling for unsupported MIME types.
+#[tokio::test]
+async fn test_unsupported_mime_type_error() {
+    let config = ExtractionConfig::default();
+    let result = extract_bytes(b"test", "video/mp4", &config).await;
+    assert!(result.is_err());
+    assert!(matches!(
+        result.unwrap_err(),
+        kreuzberg::KreuzbergError::UnsupportedFormat(_)
+    ));
+}
+/// Test pipeline execution (currently stub, will be expanded in Phase 2).
+#[tokio::test]
+async fn test_pipeline_execution() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("pipeline_test.txt");
+    fs::write(&file_path, "pipeline content").unwrap();
+    let config = ExtractionConfig {
+        enable_quality_processing: true,
+        ..Default::default()
+    };
+    let result = extract_file(&file_path, None, &config).await;
+    assert!(result.is_ok(), "Pipeline execution should succeed");
+    let result = result.unwrap();
+    assert_text_content(&result.content, "pipeline content");
+    assert_eq!(result.mime_type, "text/plain");
+    assert!(result.chunks.is_none(), "Chunks should be None without chunking config");
+    assert!(result.detected_languages.is_none(), "Language detection not enabled");
+}
+/// Test extraction with OCR config (placeholder test for Phase 2).
+#[tokio::test]
+async fn test_extraction_with_ocr_config() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("ocr_test.txt");
+    fs::write(&file_path, "ocr content").unwrap();
+    let config = ExtractionConfig {
+        ocr: Some(kreuzberg::OcrConfig {
+            tesseract_config: None,
+            backend: "tesseract".to_string(),
+            language: "eng".to_string(),
+        }),
+        force_ocr: true,
+        ..Default::default()
+    };
+    let result = extract_file(&file_path, None, &config).await;
+    assert!(result.is_ok());
+}
+/// Test extraction with chunking config.
+#[cfg(feature = "chunking")]
+#[tokio::test]
+async fn test_extraction_with_chunking_config() {
+    let dir = tempdir().unwrap();
+    let file_path = dir.path().join("chunking_test.txt");
+    let long_content = "content for chunking. ".repeat(100);
+    fs::write(&file_path, &long_content).unwrap();
+    let config = ExtractionConfig {
+        chunking: Some(kreuzberg::ChunkingConfig {
+            max_chars: 100,
+            max_overlap: 20,
+            embedding: None,
+            preset: None,
+        }),
+        ..Default::default()
+    };
+    let result = extract_file(&file_path, None, &config).await;
+    assert!(result.is_ok(), "Extraction with chunking should succeed");
+    let result = result.unwrap();
+    assert!(
+        result.chunks.is_some(),
+        "Chunks should be populated when chunking enabled"
+    );
+    let chunks = result.chunks.unwrap();
+    assert!(chunks.len() > 1, "Should have multiple chunks for long content");
+    assert!(result.metadata.additional.contains_key("chunk_count"));
+    let chunk_count = result.metadata.additional.get("chunk_count").unwrap();
+    assert_eq!(
+        chunks.len(),
+        chunk_count.as_u64().unwrap() as usize,
+        "chunk_count should match chunks length"
+    );
+    for chunk in &chunks {
+        assert!(
+            chunk.content.len() <= 100 + 20,
+            "Chunk length {} exceeds max_chars + overlap",
+            chunk.content.len()
+        );
+    }
+}