kreuzberg 4.0.0.rc2 → 4.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitignore +14 -14
- data/.rspec +3 -3
- data/.rubocop.yaml +1 -1
- data/.rubocop.yml +543 -538
- data/Gemfile +8 -8
- data/Gemfile.lock +194 -6
- data/README.md +391 -426
- data/Rakefile +34 -25
- data/Steepfile +51 -47
- data/examples/async_patterns.rb +283 -341
- data/ext/kreuzberg_rb/extconf.rb +65 -45
- data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
- data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
- data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +15 -15
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
- data/ext/kreuzberg_rb/native/include/strings.h +20 -20
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
- data/ext/kreuzberg_rb/native/src/lib.rs +3802 -2998
- data/extconf.rb +60 -28
- data/kreuzberg.gemspec +199 -148
- data/lib/kreuzberg/api_proxy.rb +126 -142
- data/lib/kreuzberg/cache_api.rb +67 -46
- data/lib/kreuzberg/cli.rb +47 -55
- data/lib/kreuzberg/cli_proxy.rb +117 -127
- data/lib/kreuzberg/config.rb +936 -691
- data/lib/kreuzberg/error_context.rb +136 -32
- data/lib/kreuzberg/errors.rb +116 -118
- data/lib/kreuzberg/extraction_api.rb +313 -85
- data/lib/kreuzberg/mcp_proxy.rb +177 -186
- data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
- data/lib/kreuzberg/post_processor_protocol.rb +15 -86
- data/lib/kreuzberg/result.rb +334 -216
- data/lib/kreuzberg/setup_lib_path.rb +99 -80
- data/lib/kreuzberg/types.rb +170 -0
- data/lib/kreuzberg/validator_protocol.rb +16 -89
- data/lib/kreuzberg/version.rb +5 -5
- data/lib/kreuzberg.rb +96 -103
- data/lib/libpdfium.so +0 -0
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +561 -520
- data/spec/binding/async_operations_spec.rb +473 -0
- data/spec/binding/batch_operations_spec.rb +595 -0
- data/spec/binding/batch_spec.rb +359 -0
- data/spec/binding/cache_spec.rb +227 -227
- data/spec/binding/cli_proxy_spec.rb +85 -85
- data/spec/binding/cli_spec.rb +55 -55
- data/spec/binding/config_result_spec.rb +377 -0
- data/spec/binding/config_spec.rb +419 -345
- data/spec/binding/config_validation_spec.rb +377 -283
- data/spec/binding/embeddings_spec.rb +816 -0
- data/spec/binding/error_handling_spec.rb +399 -213
- data/spec/binding/error_recovery_spec.rb +488 -0
- data/spec/binding/errors_spec.rb +66 -66
- data/spec/binding/font_config_spec.rb +220 -0
- data/spec/binding/images_spec.rb +738 -0
- data/spec/binding/keywords_extraction_spec.rb +600 -0
- data/spec/binding/metadata_types_spec.rb +1228 -0
- data/spec/binding/pages_extraction_spec.rb +471 -0
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
- data/spec/binding/plugins/postprocessor_spec.rb +269 -269
- data/spec/binding/plugins/validator_spec.rb +273 -274
- data/spec/binding/tables_spec.rb +641 -0
- data/spec/fixtures/config.toml +38 -39
- data/spec/fixtures/config.yaml +41 -41
- data/spec/fixtures/invalid_config.toml +3 -4
- data/spec/smoke/package_spec.rb +177 -178
- data/spec/spec_helper.rb +40 -42
- data/spec/unit/config/chunking_config_spec.rb +213 -0
- data/spec/unit/config/embedding_config_spec.rb +343 -0
- data/spec/unit/config/extraction_config_spec.rb +438 -0
- data/spec/unit/config/font_config_spec.rb +285 -0
- data/spec/unit/config/hierarchy_config_spec.rb +314 -0
- data/spec/unit/config/image_extraction_config_spec.rb +209 -0
- data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
- data/spec/unit/config/keyword_config_spec.rb +229 -0
- data/spec/unit/config/language_detection_config_spec.rb +258 -0
- data/spec/unit/config/ocr_config_spec.rb +171 -0
- data/spec/unit/config/page_config_spec.rb +221 -0
- data/spec/unit/config/pdf_config_spec.rb +267 -0
- data/spec/unit/config/postprocessor_config_spec.rb +290 -0
- data/spec/unit/config/tesseract_config_spec.rb +181 -0
- data/spec/unit/config/token_reduction_config_spec.rb +251 -0
- data/test/metadata_types_test.rb +959 -0
- data/vendor/Cargo.toml +61 -0
- data/vendor/kreuzberg/Cargo.toml +259 -204
- data/vendor/kreuzberg/README.md +263 -175
- data/vendor/kreuzberg/build.rs +782 -474
- data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
- data/vendor/kreuzberg/src/api/error.rs +81 -81
- data/vendor/kreuzberg/src/api/handlers.rs +320 -199
- data/vendor/kreuzberg/src/api/mod.rs +94 -79
- data/vendor/kreuzberg/src/api/server.rs +518 -353
- data/vendor/kreuzberg/src/api/types.rs +206 -170
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
- data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
- data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
- data/vendor/kreuzberg/src/core/config.rs +1914 -1032
- data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
- data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
- data/vendor/kreuzberg/src/core/formats.rs +235 -0
- data/vendor/kreuzberg/src/core/io.rs +329 -329
- data/vendor/kreuzberg/src/core/mime.rs +605 -605
- data/vendor/kreuzberg/src/core/mod.rs +61 -45
- data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
- data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
- data/vendor/kreuzberg/src/embeddings.rs +471 -432
- data/vendor/kreuzberg/src/error.rs +431 -431
- data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
- data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
- data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
- data/vendor/kreuzberg/src/extraction/email.rs +855 -854
- data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
- data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
- data/vendor/kreuzberg/src/extraction/image.rs +492 -368
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
- data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
- data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
- data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
- data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
- data/vendor/kreuzberg/src/extraction/table.rs +329 -328
- data/vendor/kreuzberg/src/extraction/text.rs +277 -269
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
- data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
- data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
- data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
- data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
- data/vendor/kreuzberg/src/extractors/email.rs +157 -143
- data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
- data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
- data/vendor/kreuzberg/src/extractors/html.rs +419 -393
- data/vendor/kreuzberg/src/extractors/image.rs +219 -198
- data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
- data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
- data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
- data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
- data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
- data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
- data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
- data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
- data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
- data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
- data/vendor/kreuzberg/src/extractors/security.rs +484 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
- data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
- data/vendor/kreuzberg/src/extractors/text.rs +265 -260
- data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
- data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
- data/vendor/kreuzberg/src/image/dpi.rs +164 -164
- data/vendor/kreuzberg/src/image/mod.rs +6 -6
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
- data/vendor/kreuzberg/src/image/resize.rs +89 -89
- data/vendor/kreuzberg/src/keywords/config.rs +154 -154
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
- data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
- data/vendor/kreuzberg/src/keywords/types.rs +68 -68
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
- data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
- data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
- data/vendor/kreuzberg/src/lib.rs +114 -105
- data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
- data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
- data/vendor/kreuzberg/src/ocr/error.rs +37 -37
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
- data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
- data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
- data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
- data/vendor/kreuzberg/src/ocr/types.rs +393 -393
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
- data/vendor/kreuzberg/src/panic_context.rs +154 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
- data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
- data/vendor/kreuzberg/src/pdf/error.rs +214 -122
- data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
- data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
- data/vendor/kreuzberg/src/pdf/images.rs +139 -139
- data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
- data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
- data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
- data/vendor/kreuzberg/src/pdf/table.rs +417 -393
- data/vendor/kreuzberg/src/pdf/text.rs +553 -158
- data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
- data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
- data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
- data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
- data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
- data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
- data/vendor/kreuzberg/src/text/mod.rs +27 -19
- data/vendor/kreuzberg/src/text/quality.rs +710 -697
- data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
- data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
- data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
- data/vendor/kreuzberg/src/types.rs +1713 -903
- data/vendor/kreuzberg/src/utils/mod.rs +31 -17
- data/vendor/kreuzberg/src/utils/pool.rs +503 -0
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
- data/vendor/kreuzberg/src/utils/quality.rs +968 -959
- data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
- data/vendor/kreuzberg/tests/api_embed.rs +360 -0
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
- data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
- data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
- data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
- data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
- data/vendor/kreuzberg/tests/config_features.rs +612 -598
- data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
- data/vendor/kreuzberg/tests/core_integration.rs +519 -510
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
- data/vendor/kreuzberg/tests/email_integration.rs +327 -325
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
- data/vendor/kreuzberg/tests/error_handling.rs +402 -393
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
- data/vendor/kreuzberg/tests/format_integration.rs +165 -159
- data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
- data/vendor/kreuzberg/tests/image_integration.rs +255 -253
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
- data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
- data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
- data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
- data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
- data/vendor/kreuzberg/tests/page_markers.rs +297 -0
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
- data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
- data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
- data/vendor/kreuzberg/tests/security_validation.rs +416 -415
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
- data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
- data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
- data/vendor/kreuzberg-ffi/README.md +851 -0
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
- data/vendor/kreuzberg-ffi/build.rs +168 -0
- data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
- data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
- data/vendor/kreuzberg-ffi/src/error.rs +901 -0
- data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
- data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
- data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
- data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
- data/vendor/kreuzberg-ffi/src/result.rs +510 -0
- data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
- data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
- data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
- data/vendor/kreuzberg-ffi/src/types.rs +363 -0
- data/vendor/kreuzberg-ffi/src/util.rs +210 -0
- data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
- data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
- data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
- data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
- data/vendor/kreuzberg-tesseract/README.md +399 -0
- data/vendor/kreuzberg-tesseract/build.rs +1127 -0
- data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
- data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
- data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
- data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
- data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
- data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
- metadata +196 -45
- data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
- data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
- data/vendor/rb-sys/.cargo-ok +0 -1
- data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
- data/vendor/rb-sys/Cargo.lock +0 -393
- data/vendor/rb-sys/Cargo.toml +0 -70
- data/vendor/rb-sys/Cargo.toml.orig +0 -57
- data/vendor/rb-sys/LICENSE-APACHE +0 -190
- data/vendor/rb-sys/bin/release.sh +0 -21
- data/vendor/rb-sys/build/features.rs +0 -108
- data/vendor/rb-sys/build/main.rs +0 -246
- data/vendor/rb-sys/build/stable_api_config.rs +0 -153
- data/vendor/rb-sys/build/version.rs +0 -48
- data/vendor/rb-sys/readme.md +0 -36
- data/vendor/rb-sys/src/bindings.rs +0 -21
- data/vendor/rb-sys/src/hidden.rs +0 -11
- data/vendor/rb-sys/src/lib.rs +0 -34
- data/vendor/rb-sys/src/macros.rs +0 -371
- data/vendor/rb-sys/src/memory.rs +0 -53
- data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
- data/vendor/rb-sys/src/special_consts.rs +0 -31
- data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
- data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
- data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
- data/vendor/rb-sys/src/stable_api.rs +0 -261
- data/vendor/rb-sys/src/symbol.rs +0 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
- data/vendor/rb-sys/src/utils.rs +0 -89
- data/vendor/rb-sys/src/value_type.rs +0 -7
|
@@ -0,0 +1,408 @@
|
|
|
1
|
+
//! Runtime extraction of bundled PDFium library.
|
|
2
|
+
//!
|
|
3
|
+
//! When the `bundled-pdfium` feature is enabled, the PDFium library is embedded in the binary
|
|
4
|
+
//! using `include_bytes!` during compilation. This module handles runtime extraction to a
|
|
5
|
+
//! temporary directory and provides the path for dynamic loading.
|
|
6
|
+
//!
|
|
7
|
+
//! # Thread Safety
|
|
8
|
+
//!
|
|
9
|
+
//! Extraction is protected by a `Mutex` to prevent race conditions during concurrent access.
|
|
10
|
+
//! The first thread to call `extract_bundled_pdfium()` will perform the extraction while
|
|
11
|
+
//! others wait for completion.
|
|
12
|
+
//!
|
|
13
|
+
//! To prevent the "file too short" race condition where one thread loads a partially-written
|
|
14
|
+
//! file, we use atomic file operations: write to a temporary file, then atomically rename to
|
|
15
|
+
//! the final location. This ensures other threads never observe a partial file.
|
|
16
|
+
//!
|
|
17
|
+
//! # How It Works
|
|
18
|
+
//!
|
|
19
|
+
//! 1. During build (build.rs): PDFium is copied to OUT_DIR and the build script sets
|
|
20
|
+
//! `KREUZBERG_PDFIUM_BUNDLED_PATH` environment variable
|
|
21
|
+
//! 2. At compile time: `include_bytes!` embeds the library binary in the executable
|
|
22
|
+
//! 3. At runtime: `extract_bundled_pdfium()` extracts to `$TMPDIR/kreuzberg-pdfium/`
|
|
23
|
+
//! 4. Library is reused if already present (based on file size validation)
|
|
24
|
+
//! 5. Concurrent calls are serialized with a `Mutex` to prevent partial writes
|
|
25
|
+
//! 6. Atomic rename (write temp file → rename) prevents "file too short" race conditions
|
|
26
|
+
//!
|
|
27
|
+
//! # Example
|
|
28
|
+
//!
|
|
29
|
+
//! ```rust,ignore
|
|
30
|
+
//! # #[cfg(feature = "bundled-pdfium")]
|
|
31
|
+
//! # {
|
|
32
|
+
//! use kreuzberg::pdf::bundled::extract_bundled_pdfium;
|
|
33
|
+
//!
|
|
34
|
+
//! # fn example() -> kreuzberg::Result<()> {
|
|
35
|
+
//! let lib_path = extract_bundled_pdfium()?;
|
|
36
|
+
//! println!("Extracted to: {}", lib_path.display());
|
|
37
|
+
//! # Ok(())
|
|
38
|
+
//! # }
|
|
39
|
+
//! # }
|
|
40
|
+
//! ```
|
|
41
|
+
|
|
42
|
+
use std::fs;
|
|
43
|
+
use std::io;
|
|
44
|
+
use std::path::{Path, PathBuf};
|
|
45
|
+
use std::sync::Mutex;
|
|
46
|
+
|
|
47
|
+
#[cfg(unix)]
|
|
48
|
+
use std::os::unix::fs::PermissionsExt;
|
|
49
|
+
|
|
50
|
+
static EXTRACTION_LOCK: Mutex<()> = Mutex::new(());
|
|
51
|
+
|
|
52
|
+
/// Runtime library name and extraction directory for the bundled PDFium library.
|
|
53
|
+
///
|
|
54
|
+
/// Returns tuple of (library_name, extraction_directory)
|
|
55
|
+
fn bundled_library_info() -> (&'static str, &'static str) {
|
|
56
|
+
if cfg!(target_os = "windows") {
|
|
57
|
+
("pdfium.dll", "kreuzberg-pdfium")
|
|
58
|
+
} else if cfg!(target_os = "macos") {
|
|
59
|
+
("libpdfium.dylib", "kreuzberg-pdfium")
|
|
60
|
+
} else {
|
|
61
|
+
("libpdfium.so", "kreuzberg-pdfium")
|
|
62
|
+
}
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
/// Get the temporary directory for bundled PDFium extraction.
|
|
66
|
+
///
|
|
67
|
+
/// Uses `std::env::temp_dir()` on all platforms.
|
|
68
|
+
fn get_extraction_dir() -> io::Result<PathBuf> {
|
|
69
|
+
let (_, subdir) = bundled_library_info();
|
|
70
|
+
Ok(std::env::temp_dir().join(subdir))
|
|
71
|
+
}
|
|
72
|
+
|
|
73
|
+
/// Check if extracted library exists and is valid.
|
|
74
|
+
///
|
|
75
|
+
/// Verifies:
|
|
76
|
+
/// - File exists at expected path
|
|
77
|
+
/// - File size matches embedded size (basic validation)
|
|
78
|
+
///
|
|
79
|
+
/// Returns `true` if library can be safely reused, `false` if extraction is needed.
|
|
80
|
+
fn is_extracted_library_valid(lib_path: &Path, embedded_size: usize) -> bool {
|
|
81
|
+
if !lib_path.exists() {
|
|
82
|
+
return false;
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
match fs::metadata(lib_path) {
|
|
86
|
+
Ok(metadata) => {
|
|
87
|
+
let file_size = metadata.len() as usize;
|
|
88
|
+
let size_tolerance = (embedded_size as f64 * 0.01) as usize;
|
|
89
|
+
let min_size = embedded_size.saturating_sub(size_tolerance);
|
|
90
|
+
let max_size = embedded_size.saturating_add(size_tolerance);
|
|
91
|
+
file_size >= min_size && file_size <= max_size
|
|
92
|
+
}
|
|
93
|
+
Err(_) => false,
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
/// Extract bundled PDFium library to temporary directory.
|
|
98
|
+
///
|
|
99
|
+
/// # Behavior
|
|
100
|
+
///
|
|
101
|
+
/// - Embeds PDFium library using `include_bytes!`
|
|
102
|
+
/// - Extracts to `$TMPDIR/kreuzberg-pdfium/` (non-WASM only)
|
|
103
|
+
/// - Reuses extracted library if size matches
|
|
104
|
+
/// - Sets permissions to 0755 on Unix
|
|
105
|
+
/// - Returns path to extracted library
|
|
106
|
+
/// - **Thread-safe**: Synchronized with a global `Mutex` to prevent concurrent writes
|
|
107
|
+
///
|
|
108
|
+
/// # Concurrency
|
|
109
|
+
///
|
|
110
|
+
/// This function is fully thread-safe. When multiple threads call it simultaneously,
|
|
111
|
+
/// only the first thread performs the actual extraction while others wait. This prevents
|
|
112
|
+
/// the "file too short" error that occurs when one thread reads a partially-written file.
|
|
113
|
+
///
|
|
114
|
+
/// # WASM Handling
|
|
115
|
+
///
|
|
116
|
+
/// On WASM targets (wasm32-*), this function returns an error with a helpful
|
|
117
|
+
/// message directing users to use WASM-specific initialization. WASM PDFium
|
|
118
|
+
/// is initialized through the runtime, not via file extraction.
|
|
119
|
+
///
|
|
120
|
+
/// # Errors
|
|
121
|
+
///
|
|
122
|
+
/// Returns `std::io::Error` if:
|
|
123
|
+
/// - Cannot create extraction directory
|
|
124
|
+
/// - Cannot write library file
|
|
125
|
+
/// - Cannot set file permissions (Unix only)
|
|
126
|
+
/// - Target is WASM (filesystem access not available)
|
|
127
|
+
///
|
|
128
|
+
/// # Platform-Specific Library Names
|
|
129
|
+
///
|
|
130
|
+
/// - Linux: `libpdfium.so`
|
|
131
|
+
/// - macOS: `libpdfium.dylib`
|
|
132
|
+
/// - Windows: `pdfium.dll`
|
|
133
|
+
pub fn extract_bundled_pdfium() -> io::Result<PathBuf> {
|
|
134
|
+
#[cfg(target_arch = "wasm32")]
|
|
135
|
+
{
|
|
136
|
+
return Err(io::Error::new(
|
|
137
|
+
io::ErrorKind::Unsupported,
|
|
138
|
+
"File extraction is not available in WASM. \
|
|
139
|
+
PDFium for WASM must be initialized via the WebAssembly runtime. \
|
|
140
|
+
Use a WASM-compatible environment with proper module initialization.",
|
|
141
|
+
));
|
|
142
|
+
}
|
|
143
|
+
|
|
144
|
+
let (lib_name, _) = bundled_library_info();
|
|
145
|
+
let extract_dir = get_extraction_dir()?;
|
|
146
|
+
|
|
147
|
+
fs::create_dir_all(&extract_dir).map_err(|e| {
|
|
148
|
+
io::Error::new(
|
|
149
|
+
e.kind(),
|
|
150
|
+
format!(
|
|
151
|
+
"Failed to create bundled pdfium extraction directory '{}': {}",
|
|
152
|
+
extract_dir.display(),
|
|
153
|
+
e
|
|
154
|
+
),
|
|
155
|
+
)
|
|
156
|
+
})?;
|
|
157
|
+
|
|
158
|
+
let lib_path = extract_dir.join(lib_name);
|
|
159
|
+
|
|
160
|
+
let bundled_lib = include_bytes!(env!("KREUZBERG_PDFIUM_BUNDLED_PATH"));
|
|
161
|
+
|
|
162
|
+
if is_extracted_library_valid(&lib_path, bundled_lib.len()) {
|
|
163
|
+
return Ok(lib_path);
|
|
164
|
+
}
|
|
165
|
+
|
|
166
|
+
let _guard = EXTRACTION_LOCK.lock().unwrap_or_else(|poisoned| poisoned.into_inner());
|
|
167
|
+
|
|
168
|
+
if is_extracted_library_valid(&lib_path, bundled_lib.len()) {
|
|
169
|
+
return Ok(lib_path);
|
|
170
|
+
}
|
|
171
|
+
|
|
172
|
+
let temp_path = lib_path.with_extension(format!("tmp.{}", std::process::id()));
|
|
173
|
+
|
|
174
|
+
fs::write(&temp_path, bundled_lib).map_err(|e| {
|
|
175
|
+
io::Error::new(
|
|
176
|
+
e.kind(),
|
|
177
|
+
format!(
|
|
178
|
+
"Failed to write bundled pdfium library to temp file '{}': {}",
|
|
179
|
+
temp_path.display(),
|
|
180
|
+
e
|
|
181
|
+
),
|
|
182
|
+
)
|
|
183
|
+
})?;
|
|
184
|
+
|
|
185
|
+
#[cfg(unix)]
|
|
186
|
+
{
|
|
187
|
+
let perms = fs::Permissions::from_mode(0o755);
|
|
188
|
+
fs::set_permissions(&temp_path, perms).map_err(|e| {
|
|
189
|
+
let _ = fs::remove_file(&temp_path);
|
|
190
|
+
io::Error::new(
|
|
191
|
+
e.kind(),
|
|
192
|
+
format!(
|
|
193
|
+
"Failed to set permissions on bundled pdfium temp file '{}': {}",
|
|
194
|
+
temp_path.display(),
|
|
195
|
+
e
|
|
196
|
+
),
|
|
197
|
+
)
|
|
198
|
+
})?;
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
fs::rename(&temp_path, &lib_path).map_err(|e| {
|
|
202
|
+
let _ = fs::remove_file(&temp_path);
|
|
203
|
+
io::Error::new(
|
|
204
|
+
e.kind(),
|
|
205
|
+
format!(
|
|
206
|
+
"Failed to rename bundled pdfium library from '{}' to '{}': {}",
|
|
207
|
+
temp_path.display(),
|
|
208
|
+
lib_path.display(),
|
|
209
|
+
e
|
|
210
|
+
),
|
|
211
|
+
)
|
|
212
|
+
})?;
|
|
213
|
+
|
|
214
|
+
Ok(lib_path)
|
|
215
|
+
}
|
|
216
|
+
|
|
217
|
+
#[cfg(test)]
|
|
218
|
+
mod tests {
|
|
219
|
+
use super::*;
|
|
220
|
+
|
|
221
|
+
#[test]
|
|
222
|
+
fn test_bundled_library_info_windows() {
|
|
223
|
+
if cfg!(target_os = "windows") {
|
|
224
|
+
let (name, dir) = bundled_library_info();
|
|
225
|
+
assert_eq!(name, "pdfium.dll");
|
|
226
|
+
assert_eq!(dir, "kreuzberg-pdfium");
|
|
227
|
+
}
|
|
228
|
+
}
|
|
229
|
+
|
|
230
|
+
#[test]
|
|
231
|
+
fn test_bundled_library_info_macos() {
|
|
232
|
+
if cfg!(target_os = "macos") {
|
|
233
|
+
let (name, dir) = bundled_library_info();
|
|
234
|
+
assert_eq!(name, "libpdfium.dylib");
|
|
235
|
+
assert_eq!(dir, "kreuzberg-pdfium");
|
|
236
|
+
}
|
|
237
|
+
}
|
|
238
|
+
|
|
239
|
+
#[test]
|
|
240
|
+
fn test_bundled_library_info_linux() {
|
|
241
|
+
if cfg!(target_os = "linux") {
|
|
242
|
+
let (name, dir) = bundled_library_info();
|
|
243
|
+
assert_eq!(name, "libpdfium.so");
|
|
244
|
+
assert_eq!(dir, "kreuzberg-pdfium");
|
|
245
|
+
}
|
|
246
|
+
}
|
|
247
|
+
|
|
248
|
+
#[test]
|
|
249
|
+
fn test_get_extraction_dir() {
|
|
250
|
+
let result = get_extraction_dir();
|
|
251
|
+
assert!(result.is_ok());
|
|
252
|
+
let dir = result.unwrap();
|
|
253
|
+
assert!(dir.to_str().is_some());
|
|
254
|
+
assert!(dir.ends_with("kreuzberg-pdfium"));
|
|
255
|
+
}
|
|
256
|
+
|
|
257
|
+
#[test]
|
|
258
|
+
fn test_is_extracted_library_valid_missing() {
|
|
259
|
+
let nonexistent = PathBuf::from("/tmp/nonexistent-pdfium-test");
|
|
260
|
+
assert!(!is_extracted_library_valid(&nonexistent, 1000));
|
|
261
|
+
}
|
|
262
|
+
|
|
263
|
+
#[test]
|
|
264
|
+
fn test_is_extracted_library_valid_size_match() {
|
|
265
|
+
let temp_dir = std::env::temp_dir();
|
|
266
|
+
let test_file = temp_dir.join("test-pdfium-size.dll");
|
|
267
|
+
let test_size = 5_000_000;
|
|
268
|
+
let test_data = vec![0u8; test_size];
|
|
269
|
+
|
|
270
|
+
if fs::write(&test_file, &test_data).is_ok() {
|
|
271
|
+
let is_valid = is_extracted_library_valid(&test_file, test_size);
|
|
272
|
+
assert!(is_valid);
|
|
273
|
+
let _ = fs::remove_file(&test_file);
|
|
274
|
+
}
|
|
275
|
+
}
|
|
276
|
+
|
|
277
|
+
#[test]
|
|
278
|
+
fn test_is_extracted_library_valid_size_tolerance() {
|
|
279
|
+
let temp_dir = std::env::temp_dir();
|
|
280
|
+
let test_file = temp_dir.join("test-pdfium-tolerance.dll");
|
|
281
|
+
let original_size = 10_000_000;
|
|
282
|
+
let tolerance = (original_size as f64 * 0.01) as usize;
|
|
283
|
+
|
|
284
|
+
let actual_size = original_size - tolerance / 2;
|
|
285
|
+
let test_data = vec![0u8; actual_size];
|
|
286
|
+
|
|
287
|
+
if fs::write(&test_file, &test_data).is_ok() {
|
|
288
|
+
let is_valid = is_extracted_library_valid(&test_file, original_size);
|
|
289
|
+
assert!(is_valid);
|
|
290
|
+
let _ = fs::remove_file(&test_file);
|
|
291
|
+
}
|
|
292
|
+
}
|
|
293
|
+
|
|
294
|
+
#[test]
|
|
295
|
+
fn test_is_extracted_library_valid_size_mismatch() {
|
|
296
|
+
let temp_dir = std::env::temp_dir();
|
|
297
|
+
let test_file = temp_dir.join("test-pdfium-mismatch.dll");
|
|
298
|
+
let original_size = 10_000_000;
|
|
299
|
+
|
|
300
|
+
let actual_size = (original_size as f64 * 0.85) as usize;
|
|
301
|
+
let test_data = vec![0u8; actual_size];
|
|
302
|
+
|
|
303
|
+
if fs::write(&test_file, &test_data).is_ok() {
|
|
304
|
+
let is_valid = is_extracted_library_valid(&test_file, original_size);
|
|
305
|
+
assert!(!is_valid);
|
|
306
|
+
let _ = fs::remove_file(&test_file);
|
|
307
|
+
}
|
|
308
|
+
}
|
|
309
|
+
|
|
310
|
+
#[test]
|
|
311
|
+
#[cfg(feature = "bundled-pdfium")]
|
|
312
|
+
fn test_extract_bundled_pdfium() {
|
|
313
|
+
let result = extract_bundled_pdfium();
|
|
314
|
+
assert!(result.is_ok());
|
|
315
|
+
|
|
316
|
+
let lib_path = result.unwrap();
|
|
317
|
+
assert!(
|
|
318
|
+
lib_path.exists(),
|
|
319
|
+
"Extracted library should exist at: {}",
|
|
320
|
+
lib_path.display()
|
|
321
|
+
);
|
|
322
|
+
assert!(lib_path.file_name().is_some(), "Library path should have filename");
|
|
323
|
+
|
|
324
|
+
let (expected_name, _) = bundled_library_info();
|
|
325
|
+
assert_eq!(lib_path.file_name().unwrap(), expected_name);
|
|
326
|
+
}
|
|
327
|
+
|
|
328
|
+
#[test]
|
|
329
|
+
#[cfg(feature = "bundled-pdfium")]
|
|
330
|
+
fn test_extract_bundled_pdfium_reuses_existing() {
|
|
331
|
+
let result1 = extract_bundled_pdfium();
|
|
332
|
+
assert!(result1.is_ok());
|
|
333
|
+
let path1 = result1.unwrap();
|
|
334
|
+
|
|
335
|
+
let metadata1 = fs::metadata(&path1).expect("Should be able to read metadata");
|
|
336
|
+
let size1 = metadata1.len();
|
|
337
|
+
|
|
338
|
+
let result2 = extract_bundled_pdfium();
|
|
339
|
+
assert!(result2.is_ok());
|
|
340
|
+
let path2 = result2.unwrap();
|
|
341
|
+
|
|
342
|
+
assert_eq!(path1, path2, "Extraction should return same path on second call");
|
|
343
|
+
|
|
344
|
+
let metadata2 = fs::metadata(&path2).expect("Should be able to read metadata");
|
|
345
|
+
let size2 = metadata2.len();
|
|
346
|
+
assert_eq!(size1, size2, "Reused library should have same file size");
|
|
347
|
+
}
|
|
348
|
+
|
|
349
|
+
#[test]
|
|
350
|
+
#[cfg(feature = "bundled-pdfium")]
|
|
351
|
+
fn test_extract_bundled_pdfium_concurrent_access() {
|
|
352
|
+
use std::thread;
|
|
353
|
+
|
|
354
|
+
let handles: Vec<_> = (0..10)
|
|
355
|
+
.map(|_| {
|
|
356
|
+
thread::spawn(|| {
|
|
357
|
+
let result = extract_bundled_pdfium();
|
|
358
|
+
assert!(result.is_ok(), "Concurrent extraction should succeed");
|
|
359
|
+
result.unwrap()
|
|
360
|
+
})
|
|
361
|
+
})
|
|
362
|
+
.collect();
|
|
363
|
+
|
|
364
|
+
let paths: Vec<PathBuf> = handles
|
|
365
|
+
.into_iter()
|
|
366
|
+
.map(|h| h.join().expect("Thread should complete"))
|
|
367
|
+
.collect();
|
|
368
|
+
|
|
369
|
+
let first_path = &paths[0];
|
|
370
|
+
assert!(
|
|
371
|
+
paths.iter().all(|p| p == first_path),
|
|
372
|
+
"All concurrent extractions should return the same path"
|
|
373
|
+
);
|
|
374
|
+
|
|
375
|
+
assert!(
|
|
376
|
+
first_path.exists(),
|
|
377
|
+
"Extracted library should exist at: {}",
|
|
378
|
+
first_path.display()
|
|
379
|
+
);
|
|
380
|
+
|
|
381
|
+
let metadata = fs::metadata(first_path).expect("Should be able to read metadata");
|
|
382
|
+
let file_size = metadata.len();
|
|
383
|
+
assert!(
|
|
384
|
+
file_size > 1_000_000,
|
|
385
|
+
"PDFium library should be at least 1MB, got {} bytes",
|
|
386
|
+
file_size
|
|
387
|
+
);
|
|
388
|
+
}
|
|
389
|
+
|
|
390
|
+
#[test]
|
|
391
|
+
#[cfg(unix)]
|
|
392
|
+
#[cfg(feature = "bundled-pdfium")]
|
|
393
|
+
fn test_extract_bundled_pdfium_permissions() {
|
|
394
|
+
let result = extract_bundled_pdfium();
|
|
395
|
+
assert!(result.is_ok());
|
|
396
|
+
|
|
397
|
+
let lib_path = result.unwrap();
|
|
398
|
+
let metadata = fs::metadata(&lib_path).expect("Should be able to read metadata");
|
|
399
|
+
let perms = metadata.permissions();
|
|
400
|
+
let mode = perms.mode();
|
|
401
|
+
|
|
402
|
+
assert!(
|
|
403
|
+
mode & 0o111 != 0,
|
|
404
|
+
"Library should have executable bit set, got mode: {:#o}",
|
|
405
|
+
mode
|
|
406
|
+
);
|
|
407
|
+
}
|
|
408
|
+
}
|