RubyGems - kreuzberg - Versions diffs - 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13 - Mend

kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13

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 (370) hide show

checksums.yaml +4 -4
data/.gitignore +14 -14
data/.rspec +3 -3
data/.rubocop.yaml +1 -1
data/.rubocop.yml +538 -538
data/Gemfile +8 -8
data/Gemfile.lock +4 -104
data/README.md +454 -432
data/Rakefile +25 -25
data/Steepfile +47 -47
data/examples/async_patterns.rb +341 -341
data/ext/kreuzberg_rb/extconf.rb +45 -45
data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
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 +3158 -3135
data/extconf.rb +28 -28
data/kreuzberg.gemspec +214 -182
data/lib/kreuzberg/api_proxy.rb +142 -142
data/lib/kreuzberg/cache_api.rb +81 -46
data/lib/kreuzberg/cli.rb +55 -55
data/lib/kreuzberg/cli_proxy.rb +127 -127
data/lib/kreuzberg/config.rb +724 -724
data/lib/kreuzberg/error_context.rb +80 -32
data/lib/kreuzberg/errors.rb +118 -118
data/lib/kreuzberg/extraction_api.rb +340 -85
data/lib/kreuzberg/mcp_proxy.rb +186 -186
data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
data/lib/kreuzberg/post_processor_protocol.rb +86 -86
data/lib/kreuzberg/result.rb +279 -279
data/lib/kreuzberg/setup_lib_path.rb +80 -80
data/lib/kreuzberg/validator_protocol.rb +89 -89
data/lib/kreuzberg/version.rb +5 -5
data/lib/kreuzberg.rb +109 -103
data/lib/pdfium.dll +0 -0
data/sig/kreuzberg/internal.rbs +184 -184
data/sig/kreuzberg.rbs +546 -537
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_spec.rb +345 -345
data/spec/binding/config_validation_spec.rb +283 -283
data/spec/binding/error_handling_spec.rb +213 -213
data/spec/binding/errors_spec.rb +66 -66
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 +274 -274
data/spec/fixtures/config.toml +39 -39
data/spec/fixtures/config.yaml +41 -41
data/spec/fixtures/invalid_config.toml +4 -4
data/spec/smoke/package_spec.rb +178 -178
data/spec/spec_helper.rb +42 -42
data/vendor/Cargo.toml +45 -0
data/vendor/kreuzberg/Cargo.toml +61 -38
data/vendor/kreuzberg/README.md +230 -221
data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
data/vendor/kreuzberg/build.rs +843 -891
data/vendor/kreuzberg/src/api/error.rs +81 -81
data/vendor/kreuzberg/src/api/handlers.rs +199 -199
data/vendor/kreuzberg/src/api/mod.rs +79 -79
data/vendor/kreuzberg/src/api/server.rs +353 -353
data/vendor/kreuzberg/src/api/types.rs +170 -170
data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
data/vendor/kreuzberg/src/core/config.rs +1080 -1080
data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
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 +47 -47
data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
data/vendor/kreuzberg/src/embeddings.rs +500 -432
data/vendor/kreuzberg/src/error.rs +431 -431
data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
data/vendor/kreuzberg/src/extraction/email.rs +854 -854
data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
data/vendor/kreuzberg/src/extraction/html.rs +601 -569
data/vendor/kreuzberg/src/extraction/image.rs +491 -491
data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
data/vendor/kreuzberg/src/extraction/mod.rs +81 -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 -284
data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
data/vendor/kreuzberg/src/extraction/table.rs +328 -328
data/vendor/kreuzberg/src/extraction/text.rs +269 -269
data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
data/vendor/kreuzberg/src/extractors/email.rs +157 -157
data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
data/vendor/kreuzberg/src/extractors/html.rs +407 -407
data/vendor/kreuzberg/src/extractors/image.rs +219 -219
data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
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 -142
data/vendor/kreuzberg/src/extractors/text.rs +265 -265
data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
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 -275
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 -985
data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
data/vendor/kreuzberg/src/lib.rs +113 -113
data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
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/mod.rs +58 -58
data/vendor/kreuzberg/src/ocr/processor.rs +863 -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 +452 -452
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 +44 -0
data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
data/vendor/kreuzberg/src/pdf/error.rs +130 -130
data/vendor/kreuzberg/src/pdf/images.rs +139 -139
data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
data/vendor/kreuzberg/src/pdf/table.rs +420 -417
data/vendor/kreuzberg/src/pdf/text.rs +240 -240
data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
data/vendor/kreuzberg/src/text/mod.rs +25 -25
data/vendor/kreuzberg/src/text/quality.rs +697 -697
data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
data/vendor/kreuzberg/src/text/string_utils.rs +217 -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 +796 -796
data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -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 +147 -147
data/vendor/kreuzberg/src/types.rs +1055 -1055
data/vendor/kreuzberg/src/utils/mod.rs +17 -17
data/vendor/kreuzberg/src/utils/quality.rs +959 -959
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_extract_multipart.rs +52 -52
data/vendor/kreuzberg/tests/api_tests.rs +966 -966
data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
data/vendor/kreuzberg/tests/config_features.rs +612 -612
data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
data/vendor/kreuzberg/tests/core_integration.rs +510 -510
data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
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 -327
data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
data/vendor/kreuzberg/tests/error_handling.rs +402 -402
data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
data/vendor/kreuzberg/tests/format_integration.rs +164 -161
data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
data/vendor/kreuzberg/tests/image_integration.rs +255 -255
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 -429
data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
data/vendor/kreuzberg/tests/security_validation.rs +416 -416
data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
data/vendor/kreuzberg-ffi/README.md +851 -0
data/vendor/kreuzberg-ffi/build.rs +176 -0
data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -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 +48 -0
data/vendor/kreuzberg-tesseract/LICENSE +22 -0
data/vendor/kreuzberg-tesseract/README.md +399 -0
data/vendor/kreuzberg-tesseract/build.rs +1354 -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
data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
data/vendor/rb-sys/Cargo.lock +393 -393
data/vendor/rb-sys/Cargo.toml +70 -70
data/vendor/rb-sys/Cargo.toml.orig +57 -57
data/vendor/rb-sys/LICENSE-APACHE +190 -190
data/vendor/rb-sys/LICENSE-MIT +21 -21
data/vendor/rb-sys/build/features.rs +111 -111
data/vendor/rb-sys/build/main.rs +286 -286
data/vendor/rb-sys/build/stable_api_config.rs +155 -155
data/vendor/rb-sys/build/version.rs +50 -50
data/vendor/rb-sys/readme.md +36 -36
data/vendor/rb-sys/src/bindings.rs +21 -21
data/vendor/rb-sys/src/hidden.rs +11 -11
data/vendor/rb-sys/src/lib.rs +35 -35
data/vendor/rb-sys/src/macros.rs +371 -371
data/vendor/rb-sys/src/memory.rs +53 -53
data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
data/vendor/rb-sys/src/special_consts.rs +31 -31
data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
data/vendor/rb-sys/src/stable_api.rs +260 -260
data/vendor/rb-sys/src/symbol.rs +31 -31
data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
data/vendor/rb-sys/src/utils.rs +89 -89
data/vendor/rb-sys/src/value_type.rs +7 -7
metadata +44 -81
data/vendor/rb-sys/bin/release.sh +0 -21

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

@@ -1,327 +1,327 @@
-//! Email extraction integration tests.
-//!
-//! Tests for .eml (RFC822) email extraction.
-//! Validates metadata extraction, content extraction, HTML/plain text handling, and attachments.
-#![cfg(feature = "email")]
-use kreuzberg::core::config::ExtractionConfig;
-use kreuzberg::core::extractor::extract_bytes;
-mod helpers;
-/// Test basic EML extraction with subject, from, to, and body.
-#[tokio::test]
-async fn test_eml_basic_extraction() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: Test Email Subject\r\n\
-Date: Mon, 1 Jan 2024 12:00:00 +0000\r\n\
-Message-ID: <unique123@example.com>\r\n\
-\r\n\
-This is the email body content.";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract EML successfully");
-    assert_eq!(result.mime_type, "message/rfc822");
-    assert_eq!(result.metadata.subject, Some("Test Email Subject".to_string()));
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
-    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
-    assert!(email_meta.cc_emails.is_empty(), "CC should be empty");
-    assert!(email_meta.bcc_emails.is_empty(), "BCC should be empty");
-    assert!(email_meta.message_id.is_some());
-    let msg_id = email_meta.message_id.clone().unwrap();
-    assert!(
-        msg_id.contains("unique123@example.com"),
-        "Message ID should contain unique123@example.com"
-    );
-    assert!(email_meta.attachments.is_empty(), "Should have no attachments");
-    assert!(result.metadata.date.is_some());
-    assert!(result.content.contains("Subject: Test Email Subject"));
-    assert!(result.content.contains("From: sender@example.com"));
-    assert!(result.content.contains("To: recipient@example.com"));
-    assert!(result.content.contains("This is the email body content"));
-}
-/// Test EML with attachments - metadata extraction.
-#[tokio::test]
-async fn test_eml_with_attachments() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: Email with Attachment\r\n\
-Content-Type: multipart/mixed; boundary=\"----boundary\"\r\n\
-\r\n\
-------boundary\r\n\
-Content-Type: text/plain\r\n\
-\r\n\
-Email body text.\r\n\
-------boundary\r\n\
-Content-Type: text/plain; name=\"file.txt\"\r\n\
-Content-Disposition: attachment; filename=\"file.txt\"\r\n\
-\r\n\
-Attachment content here.\r\n\
-------boundary--\r\n";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract EML with attachment");
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    if !email_meta.attachments.is_empty() {
-        assert!(result.content.contains("Attachments:"));
-    }
-    assert!(result.content.contains("Email body text") || result.content.contains("Attachment content"));
-}
-/// Test EML with HTML body.
-#[tokio::test]
-async fn test_eml_html_body() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: HTML Email\r\n\
-Content-Type: text/html; charset=utf-8\r\n\
-\r\n\
-<html>\r\n\
-<head><style>body { color: blue; }</style></head>\r\n\
-<body>\r\n\
-<h1>HTML Heading</h1>\r\n\
-<p>This is <b>bold</b> text in HTML.</p>\r\n\
-<script>alert('test');</script>\r\n\
-</body>\r\n\
-</html>";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract HTML email");
-    assert!(!result.content.contains("<script>"));
-    assert!(!result.content.contains("<style>"));
-    assert!(result.content.contains("HTML Heading") || result.content.contains("bold"));
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
-    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
-    assert_eq!(result.metadata.subject, Some("HTML Email".to_string()));
-}
-/// Test EML with plain text body.
-#[tokio::test]
-async fn test_eml_plain_text_body() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: Plain Text Email\r\n\
-Content-Type: text/plain; charset=utf-8\r\n\
-\r\n\
-This is a plain text email.\r\n\
-It has multiple lines.\r\n\
-And preserves formatting.";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract plain text email");
-    assert!(result.content.contains("This is a plain text email"));
-    assert!(result.content.contains("multiple lines"));
-    assert!(result.content.contains("preserves formatting"));
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
-    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
-    assert_eq!(result.metadata.subject, Some("Plain Text Email".to_string()));
-}
-/// Test EML multipart (HTML + plain text).
-#[tokio::test]
-async fn test_eml_multipart() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: Multipart Email\r\n\
-Content-Type: multipart/alternative; boundary=\"----boundary\"\r\n\
-\r\n\
-------boundary\r\n\
-Content-Type: text/plain\r\n\
-\r\n\
-Plain text version of the email.\r\n\
-------boundary\r\n\
-Content-Type: text/html\r\n\
-\r\n\
-<html><body><p>HTML version of the email.</p></body></html>\r\n\
-------boundary--\r\n";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract multipart email");
-    assert!(
-        result.content.contains("Plain text version") || result.content.contains("HTML version"),
-        "Should extract either plain text or HTML content"
-    );
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
-    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
-    assert_eq!(result.metadata.subject, Some("Multipart Email".to_string()));
-}
-/// Test MSG file extraction (Outlook format).
-///
-/// Note: Creating valid MSG files programmatically is complex.
-/// This test verifies error handling for invalid MSG format.
-#[tokio::test]
-async fn test_msg_file_extraction() {
-    let config = ExtractionConfig::default();
-    let invalid_msg = b"This is not a valid MSG file";
-    let result = extract_bytes(invalid_msg, "application/vnd.ms-outlook", &config).await;
-    assert!(result.is_err(), "Invalid MSG should fail gracefully");
-}
-/// Test email thread with quoted replies.
-#[tokio::test]
-async fn test_email_thread() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: person2@example.com\r\n\
-To: person1@example.com\r\n\
-Subject: Re: Original Subject\r\n\
-In-Reply-To: <original@example.com>\r\n\
-\r\n\
-This is my reply.\r\n\
-\r\n\
-On Mon, 1 Jan 2024, person1@example.com wrote:\r\n\
-> Original message text here.\r\n\
-> This was the first message.";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract email thread");
-    assert!(result.content.contains("This is my reply"));
-    assert!(result.content.contains("Original message text") || result.content.contains(">"));
-}
-/// Test email with various encodings (UTF-8, quoted-printable).
-#[tokio::test]
-async fn test_email_encodings() {
-    let config = ExtractionConfig::default();
-    let eml_content = "From: sender@example.com\r\n\
-To: recipient@example.com\r\n\
-Subject: Email with Unicode: 你好世界 🌍\r\n\
-Content-Type: text/plain; charset=utf-8\r\n\
-\r\n\
-Email body with special chars: café, naïve, résumé.\r\n\
-Emoji: 🎉 🚀 ✅"
-        .as_bytes();
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract UTF-8 email");
-    assert!(result.content.contains("café") || result.content.contains("naive") || !result.content.is_empty());
-    if let Some(subject) = result.metadata.subject {
-        assert!(subject.contains("Unicode") || subject.contains("Email"));
-    }
-}
-/// Test email with multiple recipients (To, CC, BCC).
-#[tokio::test]
-async fn test_email_large_attachments() {
-    let config = ExtractionConfig::default();
-    let eml_content = b"From: sender@example.com\r\n\
-To: r1@example.com, r2@example.com, r3@example.com\r\n\
-Cc: cc1@example.com, cc2@example.com\r\n\
-Bcc: bcc@example.com\r\n\
-Subject: Multiple Recipients\r\n\
-\r\n\
-Email to multiple recipients.";
-    let result = extract_bytes(eml_content, "message/rfc822", &config)
-        .await
-        .expect("Should extract email with multiple recipients");
-    assert!(result.metadata.format.is_some());
-    let email_meta = match result.metadata.format.as_ref().unwrap() {
-        kreuzberg::FormatMetadata::Email(meta) => meta,
-        _ => panic!("Expected Email metadata"),
-    };
-    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
-    assert_eq!(email_meta.to_emails.len(), 3, "Should have 3 To recipients");
-    assert!(email_meta.to_emails.contains(&"r1@example.com".to_string()));
-    assert!(email_meta.to_emails.contains(&"r2@example.com".to_string()));
-    assert!(email_meta.to_emails.contains(&"r3@example.com".to_string()));
-    assert_eq!(email_meta.cc_emails.len(), 2, "Should have 2 CC recipients");
-    assert!(email_meta.cc_emails.contains(&"cc1@example.com".to_string()));
-    assert!(email_meta.cc_emails.contains(&"cc2@example.com".to_string()));
-    assert_eq!(result.metadata.subject, Some("Multiple Recipients".to_string()));
-    assert!(email_meta.attachments.is_empty(), "Should have no attachments");
-}
-/// Test malformed email structure.
-#[tokio::test]
-async fn test_malformed_email() {
-    let config = ExtractionConfig::default();
-    let malformed_eml = b"This is not a valid email at all.";
-    let result = extract_bytes(malformed_eml, "message/rfc822", &config).await;
-    assert!(
-        result.is_ok() || result.is_err(),
-        "Should handle malformed email gracefully"
-    );
-}
+//! Email extraction integration tests.
+//!
+//! Tests for .eml (RFC822) email extraction.
+//! Validates metadata extraction, content extraction, HTML/plain text handling, and attachments.
+#![cfg(feature = "email")]
+use kreuzberg::core::config::ExtractionConfig;
+use kreuzberg::core::extractor::extract_bytes;
+mod helpers;
+/// Test basic EML extraction with subject, from, to, and body.
+#[tokio::test]
+async fn test_eml_basic_extraction() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: Test Email Subject\r\n\
+Date: Mon, 1 Jan 2024 12:00:00 +0000\r\n\
+Message-ID: <unique123@example.com>\r\n\
+\r\n\
+This is the email body content.";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract EML successfully");
+    assert_eq!(result.mime_type, "message/rfc822");
+    assert_eq!(result.metadata.subject, Some("Test Email Subject".to_string()));
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
+    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
+    assert!(email_meta.cc_emails.is_empty(), "CC should be empty");
+    assert!(email_meta.bcc_emails.is_empty(), "BCC should be empty");
+    assert!(email_meta.message_id.is_some());
+    let msg_id = email_meta.message_id.clone().unwrap();
+    assert!(
+        msg_id.contains("unique123@example.com"),
+        "Message ID should contain unique123@example.com"
+    );
+    assert!(email_meta.attachments.is_empty(), "Should have no attachments");
+    assert!(result.metadata.date.is_some());
+    assert!(result.content.contains("Subject: Test Email Subject"));
+    assert!(result.content.contains("From: sender@example.com"));
+    assert!(result.content.contains("To: recipient@example.com"));
+    assert!(result.content.contains("This is the email body content"));
+}
+/// Test EML with attachments - metadata extraction.
+#[tokio::test]
+async fn test_eml_with_attachments() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: Email with Attachment\r\n\
+Content-Type: multipart/mixed; boundary=\"----boundary\"\r\n\
+\r\n\
+------boundary\r\n\
+Content-Type: text/plain\r\n\
+\r\n\
+Email body text.\r\n\
+------boundary\r\n\
+Content-Type: text/plain; name=\"file.txt\"\r\n\
+Content-Disposition: attachment; filename=\"file.txt\"\r\n\
+\r\n\
+Attachment content here.\r\n\
+------boundary--\r\n";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract EML with attachment");
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    if !email_meta.attachments.is_empty() {
+        assert!(result.content.contains("Attachments:"));
+    }
+    assert!(result.content.contains("Email body text") || result.content.contains("Attachment content"));
+}
+/// Test EML with HTML body.
+#[tokio::test]
+async fn test_eml_html_body() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: HTML Email\r\n\
+Content-Type: text/html; charset=utf-8\r\n\
+\r\n\
+<html>\r\n\
+<head><style>body { color: blue; }</style></head>\r\n\
+<body>\r\n\
+<h1>HTML Heading</h1>\r\n\
+<p>This is <b>bold</b> text in HTML.</p>\r\n\
+<script>alert('test');</script>\r\n\
+</body>\r\n\
+</html>";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract HTML email");
+    assert!(!result.content.contains("<script>"));
+    assert!(!result.content.contains("<style>"));
+    assert!(result.content.contains("HTML Heading") || result.content.contains("bold"));
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
+    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
+    assert_eq!(result.metadata.subject, Some("HTML Email".to_string()));
+}
+/// Test EML with plain text body.
+#[tokio::test]
+async fn test_eml_plain_text_body() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: Plain Text Email\r\n\
+Content-Type: text/plain; charset=utf-8\r\n\
+\r\n\
+This is a plain text email.\r\n\
+It has multiple lines.\r\n\
+And preserves formatting.";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract plain text email");
+    assert!(result.content.contains("This is a plain text email"));
+    assert!(result.content.contains("multiple lines"));
+    assert!(result.content.contains("preserves formatting"));
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
+    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
+    assert_eq!(result.metadata.subject, Some("Plain Text Email".to_string()));
+}
+/// Test EML multipart (HTML + plain text).
+#[tokio::test]
+async fn test_eml_multipart() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: Multipart Email\r\n\
+Content-Type: multipart/alternative; boundary=\"----boundary\"\r\n\
+\r\n\
+------boundary\r\n\
+Content-Type: text/plain\r\n\
+\r\n\
+Plain text version of the email.\r\n\
+------boundary\r\n\
+Content-Type: text/html\r\n\
+\r\n\
+<html><body><p>HTML version of the email.</p></body></html>\r\n\
+------boundary--\r\n";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract multipart email");
+    assert!(
+        result.content.contains("Plain text version") || result.content.contains("HTML version"),
+        "Should extract either plain text or HTML content"
+    );
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
+    assert_eq!(email_meta.to_emails, vec!["recipient@example.com".to_string()]);
+    assert_eq!(result.metadata.subject, Some("Multipart Email".to_string()));
+}
+/// Test MSG file extraction (Outlook format).
+///
+/// Note: Creating valid MSG files programmatically is complex.
+/// This test verifies error handling for invalid MSG format.
+#[tokio::test]
+async fn test_msg_file_extraction() {
+    let config = ExtractionConfig::default();
+    let invalid_msg = b"This is not a valid MSG file";
+    let result = extract_bytes(invalid_msg, "application/vnd.ms-outlook", &config).await;
+    assert!(result.is_err(), "Invalid MSG should fail gracefully");
+}
+/// Test email thread with quoted replies.
+#[tokio::test]
+async fn test_email_thread() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: person2@example.com\r\n\
+To: person1@example.com\r\n\
+Subject: Re: Original Subject\r\n\
+In-Reply-To: <original@example.com>\r\n\
+\r\n\
+This is my reply.\r\n\
+\r\n\
+On Mon, 1 Jan 2024, person1@example.com wrote:\r\n\
+> Original message text here.\r\n\
+> This was the first message.";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract email thread");
+    assert!(result.content.contains("This is my reply"));
+    assert!(result.content.contains("Original message text") || result.content.contains(">"));
+}
+/// Test email with various encodings (UTF-8, quoted-printable).
+#[tokio::test]
+async fn test_email_encodings() {
+    let config = ExtractionConfig::default();
+    let eml_content = "From: sender@example.com\r\n\
+To: recipient@example.com\r\n\
+Subject: Email with Unicode: 你好世界 🌍\r\n\
+Content-Type: text/plain; charset=utf-8\r\n\
+\r\n\
+Email body with special chars: café, naïve, résumé.\r\n\
+Emoji: 🎉 🚀 ✅"
+        .as_bytes();
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract UTF-8 email");
+    assert!(result.content.contains("café") || result.content.contains("naive") || !result.content.is_empty());
+    if let Some(subject) = result.metadata.subject {
+        assert!(subject.contains("Unicode") || subject.contains("Email"));
+    }
+}
+/// Test email with multiple recipients (To, CC, BCC).
+#[tokio::test]
+async fn test_email_large_attachments() {
+    let config = ExtractionConfig::default();
+    let eml_content = b"From: sender@example.com\r\n\
+To: r1@example.com, r2@example.com, r3@example.com\r\n\
+Cc: cc1@example.com, cc2@example.com\r\n\
+Bcc: bcc@example.com\r\n\
+Subject: Multiple Recipients\r\n\
+\r\n\
+Email to multiple recipients.";
+    let result = extract_bytes(eml_content, "message/rfc822", &config)
+        .await
+        .expect("Should extract email with multiple recipients");
+    assert!(result.metadata.format.is_some());
+    let email_meta = match result.metadata.format.as_ref().unwrap() {
+        kreuzberg::FormatMetadata::Email(meta) => meta,
+        _ => panic!("Expected Email metadata"),
+    };
+    assert_eq!(email_meta.from_email, Some("sender@example.com".to_string()));
+    assert_eq!(email_meta.to_emails.len(), 3, "Should have 3 To recipients");
+    assert!(email_meta.to_emails.contains(&"r1@example.com".to_string()));
+    assert!(email_meta.to_emails.contains(&"r2@example.com".to_string()));
+    assert!(email_meta.to_emails.contains(&"r3@example.com".to_string()));
+    assert_eq!(email_meta.cc_emails.len(), 2, "Should have 2 CC recipients");
+    assert!(email_meta.cc_emails.contains(&"cc1@example.com".to_string()));
+    assert!(email_meta.cc_emails.contains(&"cc2@example.com".to_string()));
+    assert_eq!(result.metadata.subject, Some("Multiple Recipients".to_string()));
+    assert!(email_meta.attachments.is_empty(), "Should have no attachments");
+}
+/// Test malformed email structure.
+#[tokio::test]
+async fn test_malformed_email() {
+    let config = ExtractionConfig::default();
+    let malformed_eml = b"This is not a valid email at all.";
+    let result = extract_bytes(malformed_eml, "message/rfc822", &config).await;
+    assert!(
+        result.is_ok() || result.is_err(),
+        "Should handle malformed email gracefully"
+    );
+}