kreuzberg 4.0.0.pre.rc.13 → 4.0.0.pre.rc.15
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 +538 -538
- data/Gemfile +8 -8
- data/Gemfile.lock +104 -2
- data/README.md +454 -454
- data/Rakefile +33 -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 +6750 -6941
- data/ext/kreuzberg_rb/native/Cargo.toml +53 -54
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +52 -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 -3158
- data/extconf.rb +28 -28
- data/kreuzberg.gemspec +214 -214
- data/lib/kreuzberg/api_proxy.rb +142 -142
- data/lib/kreuzberg/cache_api.rb +81 -81
- 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 -80
- data/lib/kreuzberg/errors.rb +118 -118
- data/lib/kreuzberg/extraction_api.rb +340 -340
- 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 -109
- data/lib/{pdfium.dll → libpdfium.so} +0 -0
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +546 -546
- 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 +2 -2
- data/vendor/kreuzberg/Cargo.toml +5 -5
- data/vendor/kreuzberg/README.md +230 -230
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
- data/vendor/kreuzberg/build.rs +887 -843
- 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 +87 -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 -1184
- data/vendor/kreuzberg/src/embeddings.rs +500 -500
- 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 +634 -601
- data/vendor/kreuzberg/src/extraction/image.rs +491 -491
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -574
- 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 -749
- 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 -44
- data/vendor/kreuzberg/src/pdf/bundled.rs +452 -346
- 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 -68
- data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
- data/vendor/kreuzberg/src/pdf/table.rs +420 -420
- 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 +165 -164
- 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-tesseract/.commitlintrc.json +13 -13
- data/vendor/kreuzberg-tesseract/.crate-ignore +2 -2
- data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -2933
- data/vendor/kreuzberg-tesseract/Cargo.toml +2 -2
- data/vendor/kreuzberg-tesseract/LICENSE +22 -22
- data/vendor/kreuzberg-tesseract/README.md +399 -399
- data/vendor/kreuzberg-tesseract/build.rs +1354 -1354
- data/vendor/kreuzberg-tesseract/patches/README.md +71 -71
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -199
- data/vendor/kreuzberg-tesseract/src/api.rs +1371 -1371
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -77
- data/vendor/kreuzberg-tesseract/src/enums.rs +297 -297
- data/vendor/kreuzberg-tesseract/src/error.rs +81 -81
- data/vendor/kreuzberg-tesseract/src/lib.rs +145 -145
- data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -57
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -197
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -253
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -286
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -183
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -211
- 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 +81 -22
- data/vendor/kreuzberg-ffi/Cargo.toml +0 -63
- data/vendor/kreuzberg-ffi/README.md +0 -851
- data/vendor/kreuzberg-ffi/build.rs +0 -176
- data/vendor/kreuzberg-ffi/cbindgen.toml +0 -27
- data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg.h +0 -1087
- data/vendor/kreuzberg-ffi/src/lib.rs +0 -3616
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -247
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
|
@@ -1,1339 +1,1339 @@
|
|
|
1
|
-
//! Plugin registration and discovery.
|
|
2
|
-
//!
|
|
3
|
-
//! This module provides registries for managing plugins of different types.
|
|
4
|
-
//! Each plugin type (OcrBackend, DocumentExtractor, etc.) has its own registry
|
|
5
|
-
//! with type-safe registration and lookup.
|
|
6
|
-
|
|
7
|
-
use crate::plugins::{DocumentExtractor, OcrBackend, PostProcessor, ProcessingStage, Validator};
|
|
8
|
-
use crate::{KreuzbergError, Result};
|
|
9
|
-
use indexmap::IndexMap;
|
|
10
|
-
use once_cell::sync::Lazy;
|
|
11
|
-
use std::collections::{BTreeMap, HashMap};
|
|
12
|
-
use std::sync::{Arc, RwLock};
|
|
13
|
-
|
|
14
|
-
/// Validate a plugin name before registration.
|
|
15
|
-
///
|
|
16
|
-
/// # Rules
|
|
17
|
-
///
|
|
18
|
-
/// - Name cannot be empty
|
|
19
|
-
/// - Name cannot contain whitespace
|
|
20
|
-
/// - Name should follow kebab-case convention (lowercase with hyphens)
|
|
21
|
-
///
|
|
22
|
-
/// # Errors
|
|
23
|
-
///
|
|
24
|
-
/// Returns `ValidationError` if the name is invalid.
|
|
25
|
-
fn validate_plugin_name(name: &str) -> Result<()> {
|
|
26
|
-
if name.is_empty() {
|
|
27
|
-
return Err(KreuzbergError::Validation {
|
|
28
|
-
message: "Plugin name cannot be empty".to_string(),
|
|
29
|
-
source: None,
|
|
30
|
-
});
|
|
31
|
-
}
|
|
32
|
-
|
|
33
|
-
if name.contains(char::is_whitespace) {
|
|
34
|
-
return Err(KreuzbergError::Validation {
|
|
35
|
-
message: format!("Plugin name '{}' cannot contain whitespace", name),
|
|
36
|
-
source: None,
|
|
37
|
-
});
|
|
38
|
-
}
|
|
39
|
-
|
|
40
|
-
Ok(())
|
|
41
|
-
}
|
|
42
|
-
|
|
43
|
-
/// Registry for OCR backend plugins.
|
|
44
|
-
///
|
|
45
|
-
/// Manages OCR backends with backend type and language-based selection.
|
|
46
|
-
///
|
|
47
|
-
/// # Thread Safety
|
|
48
|
-
///
|
|
49
|
-
/// The registry is thread-safe and can be accessed concurrently from multiple threads.
|
|
50
|
-
///
|
|
51
|
-
/// # Example
|
|
52
|
-
///
|
|
53
|
-
/// ```rust,no_run
|
|
54
|
-
/// use kreuzberg::plugins::registry::OcrBackendRegistry;
|
|
55
|
-
/// use std::sync::Arc;
|
|
56
|
-
///
|
|
57
|
-
/// let registry = OcrBackendRegistry::new();
|
|
58
|
-
/// // Register OCR backends
|
|
59
|
-
/// // registry.register(Arc::new(TesseractBackend::new()));
|
|
60
|
-
/// ```
|
|
61
|
-
pub struct OcrBackendRegistry {
|
|
62
|
-
backends: HashMap<String, Arc<dyn OcrBackend>>,
|
|
63
|
-
}
|
|
64
|
-
|
|
65
|
-
impl OcrBackendRegistry {
|
|
66
|
-
/// Create a new OCR backend registry with default backends.
|
|
67
|
-
///
|
|
68
|
-
/// Registers the Tesseract backend by default if the "ocr" feature is enabled.
|
|
69
|
-
pub fn new() -> Self {
|
|
70
|
-
#[cfg(feature = "ocr")]
|
|
71
|
-
let mut registry = Self {
|
|
72
|
-
backends: HashMap::new(),
|
|
73
|
-
};
|
|
74
|
-
|
|
75
|
-
#[cfg(not(feature = "ocr"))]
|
|
76
|
-
let registry = Self {
|
|
77
|
-
backends: HashMap::new(),
|
|
78
|
-
};
|
|
79
|
-
|
|
80
|
-
#[cfg(feature = "ocr")]
|
|
81
|
-
{
|
|
82
|
-
use crate::ocr::tesseract_backend::TesseractBackend;
|
|
83
|
-
if let Ok(backend) = TesseractBackend::new() {
|
|
84
|
-
let _ = registry.register(Arc::new(backend));
|
|
85
|
-
}
|
|
86
|
-
}
|
|
87
|
-
|
|
88
|
-
registry
|
|
89
|
-
}
|
|
90
|
-
|
|
91
|
-
/// Create a new empty OCR backend registry without default backends.
|
|
92
|
-
///
|
|
93
|
-
/// This is useful for testing or when you want full control over backend registration.
|
|
94
|
-
pub fn new_empty() -> Self {
|
|
95
|
-
Self {
|
|
96
|
-
backends: HashMap::new(),
|
|
97
|
-
}
|
|
98
|
-
}
|
|
99
|
-
|
|
100
|
-
/// Register an OCR backend.
|
|
101
|
-
///
|
|
102
|
-
/// # Arguments
|
|
103
|
-
///
|
|
104
|
-
/// * `backend` - The OCR backend to register
|
|
105
|
-
///
|
|
106
|
-
/// # Returns
|
|
107
|
-
///
|
|
108
|
-
/// - `Ok(())` if registration succeeded
|
|
109
|
-
/// - `Err(...)` if initialization failed
|
|
110
|
-
///
|
|
111
|
-
/// # Example
|
|
112
|
-
///
|
|
113
|
-
/// ```rust,no_run
|
|
114
|
-
/// # use kreuzberg::plugins::registry::OcrBackendRegistry;
|
|
115
|
-
/// # use std::sync::Arc;
|
|
116
|
-
/// let mut registry = OcrBackendRegistry::new();
|
|
117
|
-
/// // let backend = Arc::new(MyOcrBackend::new());
|
|
118
|
-
/// // registry.register(backend)?;
|
|
119
|
-
/// # Ok::<(), kreuzberg::KreuzbergError>(())
|
|
120
|
-
/// ```
|
|
121
|
-
pub fn register(&mut self, backend: Arc<dyn OcrBackend>) -> Result<()> {
|
|
122
|
-
let name = backend.name().to_string();
|
|
123
|
-
|
|
124
|
-
validate_plugin_name(&name)?;
|
|
125
|
-
|
|
126
|
-
backend.initialize()?;
|
|
127
|
-
|
|
128
|
-
self.backends.insert(name, backend);
|
|
129
|
-
Ok(())
|
|
130
|
-
}
|
|
131
|
-
|
|
132
|
-
/// Get an OCR backend by name.
|
|
133
|
-
///
|
|
134
|
-
/// # Arguments
|
|
135
|
-
///
|
|
136
|
-
/// * `name` - Backend name
|
|
137
|
-
///
|
|
138
|
-
/// # Returns
|
|
139
|
-
///
|
|
140
|
-
/// The backend if found, or an error if not registered.
|
|
141
|
-
pub fn get(&self, name: &str) -> Result<Arc<dyn OcrBackend>> {
|
|
142
|
-
self.backends.get(name).cloned().ok_or_else(|| KreuzbergError::Plugin {
|
|
143
|
-
message: format!("OCR backend '{}' not registered", name),
|
|
144
|
-
plugin_name: name.to_string(),
|
|
145
|
-
})
|
|
146
|
-
}
|
|
147
|
-
|
|
148
|
-
/// Get an OCR backend that supports a specific language.
|
|
149
|
-
///
|
|
150
|
-
/// Returns the first backend that supports the language.
|
|
151
|
-
///
|
|
152
|
-
/// # Arguments
|
|
153
|
-
///
|
|
154
|
-
/// * `language` - Language code (e.g., "eng", "deu")
|
|
155
|
-
///
|
|
156
|
-
/// # Returns
|
|
157
|
-
///
|
|
158
|
-
/// The first backend supporting the language, or an error if none found.
|
|
159
|
-
pub fn get_for_language(&self, language: &str) -> Result<Arc<dyn OcrBackend>> {
|
|
160
|
-
self.backends
|
|
161
|
-
.values()
|
|
162
|
-
.find(|backend| backend.supports_language(language))
|
|
163
|
-
.cloned()
|
|
164
|
-
.ok_or_else(|| KreuzbergError::Plugin {
|
|
165
|
-
message: format!("No OCR backend supports language '{}'", language),
|
|
166
|
-
plugin_name: language.to_string(),
|
|
167
|
-
})
|
|
168
|
-
}
|
|
169
|
-
|
|
170
|
-
/// List all registered backend names.
|
|
171
|
-
pub fn list(&self) -> Vec<String> {
|
|
172
|
-
self.backends.keys().cloned().collect()
|
|
173
|
-
}
|
|
174
|
-
|
|
175
|
-
/// Remove a backend from the registry.
|
|
176
|
-
///
|
|
177
|
-
/// Calls `shutdown()` on the backend before removing.
|
|
178
|
-
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
179
|
-
if let Some(backend) = self.backends.remove(name) {
|
|
180
|
-
backend.shutdown()?;
|
|
181
|
-
}
|
|
182
|
-
Ok(())
|
|
183
|
-
}
|
|
184
|
-
|
|
185
|
-
/// Shutdown all backends and clear the registry.
|
|
186
|
-
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
187
|
-
let names: Vec<_> = self.backends.keys().cloned().collect();
|
|
188
|
-
for name in names {
|
|
189
|
-
self.remove(&name)?;
|
|
190
|
-
}
|
|
191
|
-
Ok(())
|
|
192
|
-
}
|
|
193
|
-
}
|
|
194
|
-
|
|
195
|
-
impl Default for OcrBackendRegistry {
|
|
196
|
-
fn default() -> Self {
|
|
197
|
-
Self::new()
|
|
198
|
-
}
|
|
199
|
-
}
|
|
200
|
-
|
|
201
|
-
/// Registry for document extractor plugins.
|
|
202
|
-
///
|
|
203
|
-
/// Manages extractors with MIME type and priority-based selection.
|
|
204
|
-
///
|
|
205
|
-
/// # Thread Safety
|
|
206
|
-
///
|
|
207
|
-
/// The registry is thread-safe and can be accessed concurrently from multiple threads.
|
|
208
|
-
pub struct DocumentExtractorRegistry {
|
|
209
|
-
extractors: HashMap<String, BTreeMap<i32, Arc<dyn DocumentExtractor>>>,
|
|
210
|
-
name_index: HashMap<String, Vec<(String, i32)>>,
|
|
211
|
-
}
|
|
212
|
-
|
|
213
|
-
impl DocumentExtractorRegistry {
|
|
214
|
-
/// Create a new empty extractor registry.
|
|
215
|
-
pub fn new() -> Self {
|
|
216
|
-
Self {
|
|
217
|
-
extractors: HashMap::new(),
|
|
218
|
-
name_index: HashMap::new(),
|
|
219
|
-
}
|
|
220
|
-
}
|
|
221
|
-
|
|
222
|
-
/// Register a document extractor.
|
|
223
|
-
///
|
|
224
|
-
/// The extractor is registered for all MIME types it supports.
|
|
225
|
-
///
|
|
226
|
-
/// # Arguments
|
|
227
|
-
///
|
|
228
|
-
/// * `extractor` - The extractor to register
|
|
229
|
-
///
|
|
230
|
-
/// # Returns
|
|
231
|
-
///
|
|
232
|
-
/// - `Ok(())` if registration succeeded
|
|
233
|
-
/// - `Err(...)` if initialization failed
|
|
234
|
-
pub fn register(&mut self, extractor: Arc<dyn DocumentExtractor>) -> Result<()> {
|
|
235
|
-
let name = extractor.name().to_string();
|
|
236
|
-
let priority = extractor.priority();
|
|
237
|
-
let mime_types: Vec<String> = extractor.supported_mime_types().iter().map(|s| s.to_string()).collect();
|
|
238
|
-
|
|
239
|
-
validate_plugin_name(&name)?;
|
|
240
|
-
|
|
241
|
-
extractor.initialize()?;
|
|
242
|
-
|
|
243
|
-
let mut index_entries = Vec::new();
|
|
244
|
-
|
|
245
|
-
for mime_type in &mime_types {
|
|
246
|
-
self.extractors
|
|
247
|
-
.entry(mime_type.clone())
|
|
248
|
-
.or_default()
|
|
249
|
-
.insert(priority, Arc::clone(&extractor));
|
|
250
|
-
index_entries.push((mime_type.clone(), priority));
|
|
251
|
-
}
|
|
252
|
-
|
|
253
|
-
self.name_index.insert(name, index_entries);
|
|
254
|
-
|
|
255
|
-
Ok(())
|
|
256
|
-
}
|
|
257
|
-
|
|
258
|
-
/// Get the highest priority extractor for a MIME type.
|
|
259
|
-
///
|
|
260
|
-
/// # Arguments
|
|
261
|
-
///
|
|
262
|
-
/// * `mime_type` - MIME type to look up
|
|
263
|
-
///
|
|
264
|
-
/// # Returns
|
|
265
|
-
///
|
|
266
|
-
/// The highest priority extractor, or an error if none found.
|
|
267
|
-
#[cfg_attr(feature = "otel", tracing::instrument(
|
|
268
|
-
skip(self),
|
|
269
|
-
fields(
|
|
270
|
-
registry.mime_type = %mime_type,
|
|
271
|
-
registry.found = tracing::field::Empty,
|
|
272
|
-
)
|
|
273
|
-
))]
|
|
274
|
-
pub fn get(&self, mime_type: &str) -> Result<Arc<dyn DocumentExtractor>> {
|
|
275
|
-
if let Some(priority_map) = self.extractors.get(mime_type)
|
|
276
|
-
&& let Some((_priority, extractor)) = priority_map.iter().next_back()
|
|
277
|
-
{
|
|
278
|
-
#[cfg(feature = "otel")]
|
|
279
|
-
tracing::Span::current().record("registry.found", true);
|
|
280
|
-
return Ok(Arc::clone(extractor));
|
|
281
|
-
}
|
|
282
|
-
|
|
283
|
-
let mut best_match: Option<(i32, Arc<dyn DocumentExtractor>)> = None;
|
|
284
|
-
|
|
285
|
-
for (registered_mime, priority_map) in &self.extractors {
|
|
286
|
-
if registered_mime.ends_with("/*") {
|
|
287
|
-
let prefix = ®istered_mime[..registered_mime.len() - 1];
|
|
288
|
-
if mime_type.starts_with(prefix)
|
|
289
|
-
&& let Some((_priority, extractor)) = priority_map.iter().next_back()
|
|
290
|
-
{
|
|
291
|
-
let priority = extractor.priority();
|
|
292
|
-
match &best_match {
|
|
293
|
-
None => best_match = Some((priority, Arc::clone(extractor))),
|
|
294
|
-
Some((current_priority, _)) => {
|
|
295
|
-
if priority > *current_priority {
|
|
296
|
-
best_match = Some((priority, Arc::clone(extractor)));
|
|
297
|
-
}
|
|
298
|
-
}
|
|
299
|
-
}
|
|
300
|
-
}
|
|
301
|
-
}
|
|
302
|
-
}
|
|
303
|
-
|
|
304
|
-
if let Some((_priority, extractor)) = best_match {
|
|
305
|
-
#[cfg(feature = "otel")]
|
|
306
|
-
tracing::Span::current().record("registry.found", true);
|
|
307
|
-
return Ok(extractor);
|
|
308
|
-
}
|
|
309
|
-
|
|
310
|
-
#[cfg(feature = "otel")]
|
|
311
|
-
tracing::Span::current().record("registry.found", false);
|
|
312
|
-
Err(KreuzbergError::UnsupportedFormat(mime_type.to_string()))
|
|
313
|
-
}
|
|
314
|
-
|
|
315
|
-
/// List all registered extractors.
|
|
316
|
-
pub fn list(&self) -> Vec<String> {
|
|
317
|
-
self.name_index.keys().cloned().collect()
|
|
318
|
-
}
|
|
319
|
-
|
|
320
|
-
/// Remove an extractor from the registry.
|
|
321
|
-
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
322
|
-
let index_entries = match self.name_index.remove(name) {
|
|
323
|
-
Some(entries) => entries,
|
|
324
|
-
None => return Ok(()),
|
|
325
|
-
};
|
|
326
|
-
|
|
327
|
-
let mut extractor_to_shutdown: Option<Arc<dyn DocumentExtractor>> = None;
|
|
328
|
-
|
|
329
|
-
for (mime_type, priority) in index_entries {
|
|
330
|
-
if let Some(priority_map) = self.extractors.get_mut(&mime_type) {
|
|
331
|
-
if let Some(extractor) = priority_map.remove(&priority)
|
|
332
|
-
&& extractor_to_shutdown.is_none()
|
|
333
|
-
{
|
|
334
|
-
extractor_to_shutdown = Some(extractor);
|
|
335
|
-
}
|
|
336
|
-
|
|
337
|
-
if priority_map.is_empty() {
|
|
338
|
-
self.extractors.remove(&mime_type);
|
|
339
|
-
}
|
|
340
|
-
}
|
|
341
|
-
}
|
|
342
|
-
|
|
343
|
-
if let Some(extractor) = extractor_to_shutdown {
|
|
344
|
-
extractor.shutdown()?;
|
|
345
|
-
}
|
|
346
|
-
|
|
347
|
-
Ok(())
|
|
348
|
-
}
|
|
349
|
-
|
|
350
|
-
/// Shutdown all extractors and clear the registry.
|
|
351
|
-
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
352
|
-
let names = self.list();
|
|
353
|
-
for name in names {
|
|
354
|
-
self.remove(&name)?;
|
|
355
|
-
}
|
|
356
|
-
Ok(())
|
|
357
|
-
}
|
|
358
|
-
}
|
|
359
|
-
|
|
360
|
-
impl Default for DocumentExtractorRegistry {
|
|
361
|
-
fn default() -> Self {
|
|
362
|
-
Self::new()
|
|
363
|
-
}
|
|
364
|
-
}
|
|
365
|
-
|
|
366
|
-
/// Registry for post-processor plugins.
|
|
367
|
-
///
|
|
368
|
-
/// Manages post-processors organized by processing stage.
|
|
369
|
-
pub struct PostProcessorRegistry {
|
|
370
|
-
processors: HashMap<ProcessingStage, BTreeMap<i32, Vec<Arc<dyn PostProcessor>>>>,
|
|
371
|
-
name_index: HashMap<String, (ProcessingStage, i32)>,
|
|
372
|
-
}
|
|
373
|
-
|
|
374
|
-
impl PostProcessorRegistry {
|
|
375
|
-
/// Create a new empty post-processor registry.
|
|
376
|
-
pub fn new() -> Self {
|
|
377
|
-
Self {
|
|
378
|
-
processors: HashMap::new(),
|
|
379
|
-
name_index: HashMap::new(),
|
|
380
|
-
}
|
|
381
|
-
}
|
|
382
|
-
|
|
383
|
-
/// Register a post-processor.
|
|
384
|
-
///
|
|
385
|
-
/// # Arguments
|
|
386
|
-
///
|
|
387
|
-
/// * `processor` - The post-processor to register
|
|
388
|
-
/// * `priority` - Execution priority (higher = runs first within stage)
|
|
389
|
-
pub fn register(&mut self, processor: Arc<dyn PostProcessor>, priority: i32) -> Result<()> {
|
|
390
|
-
let name = processor.name().to_string();
|
|
391
|
-
let stage = processor.processing_stage();
|
|
392
|
-
|
|
393
|
-
validate_plugin_name(&name)?;
|
|
394
|
-
|
|
395
|
-
processor.initialize()?;
|
|
396
|
-
|
|
397
|
-
if self.name_index.contains_key(&name) {
|
|
398
|
-
self.remove(&name)?;
|
|
399
|
-
}
|
|
400
|
-
|
|
401
|
-
self.processors
|
|
402
|
-
.entry(stage)
|
|
403
|
-
.or_default()
|
|
404
|
-
.entry(priority)
|
|
405
|
-
.or_default()
|
|
406
|
-
.push(Arc::clone(&processor));
|
|
407
|
-
|
|
408
|
-
self.name_index.insert(name, (stage, priority));
|
|
409
|
-
|
|
410
|
-
Ok(())
|
|
411
|
-
}
|
|
412
|
-
|
|
413
|
-
/// Get all processors for a specific stage, in priority order.
|
|
414
|
-
///
|
|
415
|
-
/// # Arguments
|
|
416
|
-
///
|
|
417
|
-
/// * `stage` - The processing stage
|
|
418
|
-
///
|
|
419
|
-
/// # Returns
|
|
420
|
-
///
|
|
421
|
-
/// Vector of processors in priority order (highest first).
|
|
422
|
-
pub fn get_for_stage(&self, stage: ProcessingStage) -> Vec<Arc<dyn PostProcessor>> {
|
|
423
|
-
let mut result = Vec::new();
|
|
424
|
-
|
|
425
|
-
if let Some(priority_map) = self.processors.get(&stage) {
|
|
426
|
-
for (_priority, processors) in priority_map.iter().rev() {
|
|
427
|
-
for processor in processors {
|
|
428
|
-
result.push(Arc::clone(processor));
|
|
429
|
-
}
|
|
430
|
-
}
|
|
431
|
-
}
|
|
432
|
-
|
|
433
|
-
result
|
|
434
|
-
}
|
|
435
|
-
|
|
436
|
-
/// List all registered processor names.
|
|
437
|
-
pub fn list(&self) -> Vec<String> {
|
|
438
|
-
self.name_index.keys().cloned().collect()
|
|
439
|
-
}
|
|
440
|
-
|
|
441
|
-
/// Remove a processor from the registry.
|
|
442
|
-
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
443
|
-
let (stage, priority) = match self.name_index.remove(name) {
|
|
444
|
-
Some(location) => location,
|
|
445
|
-
None => return Ok(()),
|
|
446
|
-
};
|
|
447
|
-
|
|
448
|
-
let processor_to_shutdown = if let Some(priority_map) = self.processors.get_mut(&stage) {
|
|
449
|
-
let processor = priority_map.get_mut(&priority).and_then(|processors| {
|
|
450
|
-
processors
|
|
451
|
-
.iter()
|
|
452
|
-
.position(|p| p.name() == name)
|
|
453
|
-
.map(|pos| processors.remove(pos))
|
|
454
|
-
});
|
|
455
|
-
|
|
456
|
-
if let Some(processors) = priority_map.get(&priority)
|
|
457
|
-
&& processors.is_empty()
|
|
458
|
-
{
|
|
459
|
-
priority_map.remove(&priority);
|
|
460
|
-
}
|
|
461
|
-
|
|
462
|
-
if priority_map.is_empty() {
|
|
463
|
-
self.processors.remove(&stage);
|
|
464
|
-
}
|
|
465
|
-
processor
|
|
466
|
-
} else {
|
|
467
|
-
None
|
|
468
|
-
};
|
|
469
|
-
|
|
470
|
-
if let Some(processor) = processor_to_shutdown {
|
|
471
|
-
processor.shutdown()?;
|
|
472
|
-
}
|
|
473
|
-
|
|
474
|
-
Ok(())
|
|
475
|
-
}
|
|
476
|
-
|
|
477
|
-
/// Shutdown all processors and clear the registry.
|
|
478
|
-
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
479
|
-
let names = self.list();
|
|
480
|
-
for name in names {
|
|
481
|
-
self.remove(&name)?;
|
|
482
|
-
}
|
|
483
|
-
Ok(())
|
|
484
|
-
}
|
|
485
|
-
}
|
|
486
|
-
|
|
487
|
-
impl Default for PostProcessorRegistry {
|
|
488
|
-
fn default() -> Self {
|
|
489
|
-
Self::new()
|
|
490
|
-
}
|
|
491
|
-
}
|
|
492
|
-
|
|
493
|
-
/// Registry for validator plugins.
|
|
494
|
-
///
|
|
495
|
-
/// Manages validators with priority-based execution order.
|
|
496
|
-
pub struct ValidatorRegistry {
|
|
497
|
-
validators: BTreeMap<i32, IndexMap<String, Arc<dyn Validator>>>,
|
|
498
|
-
}
|
|
499
|
-
|
|
500
|
-
impl ValidatorRegistry {
|
|
501
|
-
/// Create a new empty validator registry.
|
|
502
|
-
pub fn new() -> Self {
|
|
503
|
-
Self {
|
|
504
|
-
validators: BTreeMap::new(),
|
|
505
|
-
}
|
|
506
|
-
}
|
|
507
|
-
|
|
508
|
-
/// Register a validator.
|
|
509
|
-
///
|
|
510
|
-
/// # Arguments
|
|
511
|
-
///
|
|
512
|
-
/// * `validator` - The validator to register
|
|
513
|
-
pub fn register(&mut self, validator: Arc<dyn Validator>) -> Result<()> {
|
|
514
|
-
let name = validator.name().to_string();
|
|
515
|
-
let priority = validator.priority();
|
|
516
|
-
|
|
517
|
-
validate_plugin_name(&name)?;
|
|
518
|
-
|
|
519
|
-
validator.initialize()?;
|
|
520
|
-
|
|
521
|
-
self.validators.entry(priority).or_default().insert(name, validator);
|
|
522
|
-
|
|
523
|
-
Ok(())
|
|
524
|
-
}
|
|
525
|
-
|
|
526
|
-
/// Get all validators in priority order.
|
|
527
|
-
///
|
|
528
|
-
/// # Returns
|
|
529
|
-
///
|
|
530
|
-
/// Vector of validators in priority order (highest first).
|
|
531
|
-
pub fn get_all(&self) -> Vec<Arc<dyn Validator>> {
|
|
532
|
-
let mut result = Vec::new();
|
|
533
|
-
|
|
534
|
-
for (_priority, validators) in self.validators.iter().rev() {
|
|
535
|
-
for validator in validators.values() {
|
|
536
|
-
result.push(Arc::clone(validator));
|
|
537
|
-
}
|
|
538
|
-
}
|
|
539
|
-
|
|
540
|
-
result
|
|
541
|
-
}
|
|
542
|
-
|
|
543
|
-
/// List all registered validator names.
|
|
544
|
-
pub fn list(&self) -> Vec<String> {
|
|
545
|
-
let mut names = std::collections::HashSet::new();
|
|
546
|
-
for validators in self.validators.values() {
|
|
547
|
-
names.extend(validators.keys().cloned());
|
|
548
|
-
}
|
|
549
|
-
names.into_iter().collect()
|
|
550
|
-
}
|
|
551
|
-
|
|
552
|
-
/// Remove a validator from the registry.
|
|
553
|
-
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
554
|
-
let mut validator_to_shutdown: Option<Arc<dyn Validator>> = None;
|
|
555
|
-
|
|
556
|
-
for validators in self.validators.values_mut() {
|
|
557
|
-
if let Some(validator) = validators.shift_remove(name)
|
|
558
|
-
&& validator_to_shutdown.is_none()
|
|
559
|
-
{
|
|
560
|
-
validator_to_shutdown = Some(validator);
|
|
561
|
-
}
|
|
562
|
-
}
|
|
563
|
-
|
|
564
|
-
if let Some(validator) = validator_to_shutdown {
|
|
565
|
-
validator.shutdown()?;
|
|
566
|
-
}
|
|
567
|
-
|
|
568
|
-
self.validators.retain(|_, validators| !validators.is_empty());
|
|
569
|
-
|
|
570
|
-
Ok(())
|
|
571
|
-
}
|
|
572
|
-
|
|
573
|
-
/// Shutdown all validators and clear the registry.
|
|
574
|
-
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
575
|
-
let names = self.list();
|
|
576
|
-
for name in names {
|
|
577
|
-
self.remove(&name)?;
|
|
578
|
-
}
|
|
579
|
-
Ok(())
|
|
580
|
-
}
|
|
581
|
-
}
|
|
582
|
-
|
|
583
|
-
impl Default for ValidatorRegistry {
|
|
584
|
-
fn default() -> Self {
|
|
585
|
-
Self::new()
|
|
586
|
-
}
|
|
587
|
-
}
|
|
588
|
-
|
|
589
|
-
/// Global OCR backend registry singleton.
|
|
590
|
-
pub static OCR_BACKEND_REGISTRY: Lazy<Arc<RwLock<OcrBackendRegistry>>> =
|
|
591
|
-
Lazy::new(|| Arc::new(RwLock::new(OcrBackendRegistry::new())));
|
|
592
|
-
|
|
593
|
-
/// Global document extractor registry singleton.
|
|
594
|
-
pub static DOCUMENT_EXTRACTOR_REGISTRY: Lazy<Arc<RwLock<DocumentExtractorRegistry>>> =
|
|
595
|
-
Lazy::new(|| Arc::new(RwLock::new(DocumentExtractorRegistry::new())));
|
|
596
|
-
|
|
597
|
-
/// Global post-processor registry singleton.
|
|
598
|
-
pub static POST_PROCESSOR_REGISTRY: Lazy<Arc<RwLock<PostProcessorRegistry>>> =
|
|
599
|
-
Lazy::new(|| Arc::new(RwLock::new(PostProcessorRegistry::new())));
|
|
600
|
-
|
|
601
|
-
/// Global validator registry singleton.
|
|
602
|
-
pub static VALIDATOR_REGISTRY: Lazy<Arc<RwLock<ValidatorRegistry>>> =
|
|
603
|
-
Lazy::new(|| Arc::new(RwLock::new(ValidatorRegistry::new())));
|
|
604
|
-
|
|
605
|
-
/// Get the global OCR backend registry.
|
|
606
|
-
pub fn get_ocr_backend_registry() -> Arc<RwLock<OcrBackendRegistry>> {
|
|
607
|
-
OCR_BACKEND_REGISTRY.clone()
|
|
608
|
-
}
|
|
609
|
-
|
|
610
|
-
/// Get the global document extractor registry.
|
|
611
|
-
pub fn get_document_extractor_registry() -> Arc<RwLock<DocumentExtractorRegistry>> {
|
|
612
|
-
DOCUMENT_EXTRACTOR_REGISTRY.clone()
|
|
613
|
-
}
|
|
614
|
-
|
|
615
|
-
/// Get the global post-processor registry.
|
|
616
|
-
pub fn get_post_processor_registry() -> Arc<RwLock<PostProcessorRegistry>> {
|
|
617
|
-
POST_PROCESSOR_REGISTRY.clone()
|
|
618
|
-
}
|
|
619
|
-
|
|
620
|
-
/// Get the global validator registry.
|
|
621
|
-
pub fn get_validator_registry() -> Arc<RwLock<ValidatorRegistry>> {
|
|
622
|
-
VALIDATOR_REGISTRY.clone()
|
|
623
|
-
}
|
|
624
|
-
|
|
625
|
-
#[cfg(test)]
|
|
626
|
-
mod tests {
|
|
627
|
-
use super::*;
|
|
628
|
-
use crate::core::config::{ExtractionConfig, OcrConfig};
|
|
629
|
-
use crate::plugins::{Plugin, PostProcessor, ProcessingStage, Validator};
|
|
630
|
-
use crate::types::ExtractionResult;
|
|
631
|
-
use async_trait::async_trait;
|
|
632
|
-
|
|
633
|
-
struct MockOcrBackend {
|
|
634
|
-
name: String,
|
|
635
|
-
languages: Vec<String>,
|
|
636
|
-
}
|
|
637
|
-
|
|
638
|
-
impl Plugin for MockOcrBackend {
|
|
639
|
-
fn name(&self) -> &str {
|
|
640
|
-
&self.name
|
|
641
|
-
}
|
|
642
|
-
fn version(&self) -> String {
|
|
643
|
-
"1.0.0".to_string()
|
|
644
|
-
}
|
|
645
|
-
fn initialize(&self) -> Result<()> {
|
|
646
|
-
Ok(())
|
|
647
|
-
}
|
|
648
|
-
fn shutdown(&self) -> Result<()> {
|
|
649
|
-
Ok(())
|
|
650
|
-
}
|
|
651
|
-
}
|
|
652
|
-
|
|
653
|
-
#[async_trait]
|
|
654
|
-
impl OcrBackend for MockOcrBackend {
|
|
655
|
-
async fn process_image(&self, _: &[u8], _: &OcrConfig) -> Result<ExtractionResult> {
|
|
656
|
-
Ok(ExtractionResult {
|
|
657
|
-
content: "test".to_string(),
|
|
658
|
-
mime_type: "text/plain".to_string(),
|
|
659
|
-
metadata: crate::types::Metadata::default(),
|
|
660
|
-
tables: vec![],
|
|
661
|
-
detected_languages: None,
|
|
662
|
-
chunks: None,
|
|
663
|
-
images: None,
|
|
664
|
-
pages: None,
|
|
665
|
-
})
|
|
666
|
-
}
|
|
667
|
-
|
|
668
|
-
fn supports_language(&self, lang: &str) -> bool {
|
|
669
|
-
self.languages.iter().any(|l| l == lang)
|
|
670
|
-
}
|
|
671
|
-
|
|
672
|
-
fn backend_type(&self) -> crate::plugins::ocr::OcrBackendType {
|
|
673
|
-
crate::plugins::ocr::OcrBackendType::Custom
|
|
674
|
-
}
|
|
675
|
-
}
|
|
676
|
-
|
|
677
|
-
struct MockExtractor {
|
|
678
|
-
name: String,
|
|
679
|
-
mime_types: &'static [&'static str],
|
|
680
|
-
priority: i32,
|
|
681
|
-
}
|
|
682
|
-
|
|
683
|
-
impl Plugin for MockExtractor {
|
|
684
|
-
fn name(&self) -> &str {
|
|
685
|
-
&self.name
|
|
686
|
-
}
|
|
687
|
-
fn version(&self) -> String {
|
|
688
|
-
"1.0.0".to_string()
|
|
689
|
-
}
|
|
690
|
-
fn initialize(&self) -> Result<()> {
|
|
691
|
-
Ok(())
|
|
692
|
-
}
|
|
693
|
-
fn shutdown(&self) -> Result<()> {
|
|
694
|
-
Ok(())
|
|
695
|
-
}
|
|
696
|
-
}
|
|
697
|
-
|
|
698
|
-
#[async_trait]
|
|
699
|
-
impl DocumentExtractor for MockExtractor {
|
|
700
|
-
async fn extract_bytes(&self, _: &[u8], _: &str, _: &ExtractionConfig) -> Result<ExtractionResult> {
|
|
701
|
-
Ok(ExtractionResult {
|
|
702
|
-
content: "test".to_string(),
|
|
703
|
-
mime_type: "text/plain".to_string(),
|
|
704
|
-
metadata: crate::types::Metadata::default(),
|
|
705
|
-
tables: vec![],
|
|
706
|
-
detected_languages: None,
|
|
707
|
-
chunks: None,
|
|
708
|
-
images: None,
|
|
709
|
-
pages: None,
|
|
710
|
-
})
|
|
711
|
-
}
|
|
712
|
-
|
|
713
|
-
fn supported_mime_types(&self) -> &[&str] {
|
|
714
|
-
self.mime_types
|
|
715
|
-
}
|
|
716
|
-
|
|
717
|
-
fn priority(&self) -> i32 {
|
|
718
|
-
self.priority
|
|
719
|
-
}
|
|
720
|
-
}
|
|
721
|
-
|
|
722
|
-
struct MockPostProcessor {
|
|
723
|
-
name: String,
|
|
724
|
-
stage: ProcessingStage,
|
|
725
|
-
}
|
|
726
|
-
|
|
727
|
-
impl Plugin for MockPostProcessor {
|
|
728
|
-
fn name(&self) -> &str {
|
|
729
|
-
&self.name
|
|
730
|
-
}
|
|
731
|
-
fn version(&self) -> String {
|
|
732
|
-
"1.0.0".to_string()
|
|
733
|
-
}
|
|
734
|
-
fn initialize(&self) -> Result<()> {
|
|
735
|
-
Ok(())
|
|
736
|
-
}
|
|
737
|
-
fn shutdown(&self) -> Result<()> {
|
|
738
|
-
Ok(())
|
|
739
|
-
}
|
|
740
|
-
}
|
|
741
|
-
|
|
742
|
-
#[async_trait]
|
|
743
|
-
impl PostProcessor for MockPostProcessor {
|
|
744
|
-
async fn process(&self, _result: &mut ExtractionResult, _: &ExtractionConfig) -> Result<()> {
|
|
745
|
-
Ok(())
|
|
746
|
-
}
|
|
747
|
-
|
|
748
|
-
fn processing_stage(&self) -> ProcessingStage {
|
|
749
|
-
self.stage
|
|
750
|
-
}
|
|
751
|
-
}
|
|
752
|
-
|
|
753
|
-
struct MockValidator {
|
|
754
|
-
name: String,
|
|
755
|
-
priority: i32,
|
|
756
|
-
}
|
|
757
|
-
|
|
758
|
-
impl Plugin for MockValidator {
|
|
759
|
-
fn name(&self) -> &str {
|
|
760
|
-
&self.name
|
|
761
|
-
}
|
|
762
|
-
fn version(&self) -> String {
|
|
763
|
-
"1.0.0".to_string()
|
|
764
|
-
}
|
|
765
|
-
fn initialize(&self) -> Result<()> {
|
|
766
|
-
Ok(())
|
|
767
|
-
}
|
|
768
|
-
fn shutdown(&self) -> Result<()> {
|
|
769
|
-
Ok(())
|
|
770
|
-
}
|
|
771
|
-
}
|
|
772
|
-
|
|
773
|
-
#[async_trait]
|
|
774
|
-
impl Validator for MockValidator {
|
|
775
|
-
async fn validate(&self, _: &ExtractionResult, _: &ExtractionConfig) -> Result<()> {
|
|
776
|
-
Ok(())
|
|
777
|
-
}
|
|
778
|
-
|
|
779
|
-
fn priority(&self) -> i32 {
|
|
780
|
-
self.priority
|
|
781
|
-
}
|
|
782
|
-
}
|
|
783
|
-
|
|
784
|
-
#[test]
|
|
785
|
-
fn test_ocr_backend_registry() {
|
|
786
|
-
let mut registry = OcrBackendRegistry::new_empty();
|
|
787
|
-
|
|
788
|
-
let backend = Arc::new(MockOcrBackend {
|
|
789
|
-
name: "test-ocr".to_string(),
|
|
790
|
-
languages: vec!["eng".to_string(), "deu".to_string()],
|
|
791
|
-
});
|
|
792
|
-
|
|
793
|
-
registry.register(backend).unwrap();
|
|
794
|
-
|
|
795
|
-
let retrieved = registry.get("test-ocr").unwrap();
|
|
796
|
-
assert_eq!(retrieved.name(), "test-ocr");
|
|
797
|
-
|
|
798
|
-
let eng_backend = registry.get_for_language("eng").unwrap();
|
|
799
|
-
assert_eq!(eng_backend.name(), "test-ocr");
|
|
800
|
-
|
|
801
|
-
let names = registry.list();
|
|
802
|
-
assert_eq!(names.len(), 1);
|
|
803
|
-
assert!(names.contains(&"test-ocr".to_string()));
|
|
804
|
-
}
|
|
805
|
-
|
|
806
|
-
#[test]
|
|
807
|
-
fn test_post_processor_registry() {
|
|
808
|
-
let mut registry = PostProcessorRegistry::new();
|
|
809
|
-
|
|
810
|
-
let early = Arc::new(MockPostProcessor {
|
|
811
|
-
name: "early-processor".to_string(),
|
|
812
|
-
stage: ProcessingStage::Early,
|
|
813
|
-
});
|
|
814
|
-
|
|
815
|
-
let middle = Arc::new(MockPostProcessor {
|
|
816
|
-
name: "middle-processor".to_string(),
|
|
817
|
-
stage: ProcessingStage::Middle,
|
|
818
|
-
});
|
|
819
|
-
|
|
820
|
-
registry.register(early, 100).unwrap();
|
|
821
|
-
registry.register(middle, 50).unwrap();
|
|
822
|
-
|
|
823
|
-
let early_processors = registry.get_for_stage(ProcessingStage::Early);
|
|
824
|
-
assert_eq!(early_processors.len(), 1);
|
|
825
|
-
assert_eq!(early_processors[0].name(), "early-processor");
|
|
826
|
-
|
|
827
|
-
let middle_processors = registry.get_for_stage(ProcessingStage::Middle);
|
|
828
|
-
assert_eq!(middle_processors.len(), 1);
|
|
829
|
-
|
|
830
|
-
let names = registry.list();
|
|
831
|
-
assert_eq!(names.len(), 2);
|
|
832
|
-
}
|
|
833
|
-
|
|
834
|
-
#[test]
|
|
835
|
-
fn test_validator_registry() {
|
|
836
|
-
let mut registry = ValidatorRegistry::new();
|
|
837
|
-
|
|
838
|
-
let high_priority = Arc::new(MockValidator {
|
|
839
|
-
name: "high-priority".to_string(),
|
|
840
|
-
priority: 100,
|
|
841
|
-
});
|
|
842
|
-
|
|
843
|
-
let low_priority = Arc::new(MockValidator {
|
|
844
|
-
name: "low-priority".to_string(),
|
|
845
|
-
priority: 10,
|
|
846
|
-
});
|
|
847
|
-
|
|
848
|
-
registry.register(high_priority).unwrap();
|
|
849
|
-
registry.register(low_priority).unwrap();
|
|
850
|
-
|
|
851
|
-
let validators = registry.get_all();
|
|
852
|
-
assert_eq!(validators.len(), 2);
|
|
853
|
-
assert_eq!(validators[0].name(), "high-priority");
|
|
854
|
-
assert_eq!(validators[1].name(), "low-priority");
|
|
855
|
-
}
|
|
856
|
-
|
|
857
|
-
#[test]
|
|
858
|
-
fn test_document_extractor_registry_exact_match() {
|
|
859
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
860
|
-
|
|
861
|
-
let extractor = Arc::new(MockExtractor {
|
|
862
|
-
name: "pdf-extractor".to_string(),
|
|
863
|
-
mime_types: &["application/pdf"],
|
|
864
|
-
priority: 100,
|
|
865
|
-
});
|
|
866
|
-
|
|
867
|
-
registry.register(extractor).unwrap();
|
|
868
|
-
|
|
869
|
-
let retrieved = registry.get("application/pdf").unwrap();
|
|
870
|
-
assert_eq!(retrieved.name(), "pdf-extractor");
|
|
871
|
-
|
|
872
|
-
let names = registry.list();
|
|
873
|
-
assert_eq!(names.len(), 1);
|
|
874
|
-
assert!(names.contains(&"pdf-extractor".to_string()));
|
|
875
|
-
}
|
|
876
|
-
|
|
877
|
-
#[test]
|
|
878
|
-
fn test_document_extractor_registry_prefix_match() {
|
|
879
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
880
|
-
|
|
881
|
-
let image_extractor = Arc::new(MockExtractor {
|
|
882
|
-
name: "image-extractor".to_string(),
|
|
883
|
-
mime_types: &["image/*"],
|
|
884
|
-
priority: 50,
|
|
885
|
-
});
|
|
886
|
-
|
|
887
|
-
registry.register(image_extractor).unwrap();
|
|
888
|
-
|
|
889
|
-
let retrieved = registry.get("image/png").unwrap();
|
|
890
|
-
assert_eq!(retrieved.name(), "image-extractor");
|
|
891
|
-
|
|
892
|
-
let retrieved_jpg = registry.get("image/jpeg").unwrap();
|
|
893
|
-
assert_eq!(retrieved_jpg.name(), "image-extractor");
|
|
894
|
-
}
|
|
895
|
-
|
|
896
|
-
#[test]
|
|
897
|
-
fn test_document_extractor_registry_priority() {
|
|
898
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
899
|
-
|
|
900
|
-
let low_priority = Arc::new(MockExtractor {
|
|
901
|
-
name: "low-priority-pdf".to_string(),
|
|
902
|
-
mime_types: &["application/pdf"],
|
|
903
|
-
priority: 10,
|
|
904
|
-
});
|
|
905
|
-
|
|
906
|
-
let high_priority = Arc::new(MockExtractor {
|
|
907
|
-
name: "high-priority-pdf".to_string(),
|
|
908
|
-
mime_types: &["application/pdf"],
|
|
909
|
-
priority: 100,
|
|
910
|
-
});
|
|
911
|
-
|
|
912
|
-
registry.register(low_priority).unwrap();
|
|
913
|
-
registry.register(high_priority).unwrap();
|
|
914
|
-
|
|
915
|
-
let retrieved = registry.get("application/pdf").unwrap();
|
|
916
|
-
assert_eq!(retrieved.name(), "high-priority-pdf");
|
|
917
|
-
}
|
|
918
|
-
|
|
919
|
-
#[test]
|
|
920
|
-
fn test_document_extractor_registry_not_found() {
|
|
921
|
-
let registry = DocumentExtractorRegistry::new();
|
|
922
|
-
|
|
923
|
-
let result = registry.get("application/unknown");
|
|
924
|
-
assert!(matches!(result, Err(KreuzbergError::UnsupportedFormat(_))));
|
|
925
|
-
}
|
|
926
|
-
|
|
927
|
-
#[test]
|
|
928
|
-
fn test_document_extractor_registry_remove() {
|
|
929
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
930
|
-
|
|
931
|
-
let extractor = Arc::new(MockExtractor {
|
|
932
|
-
name: "test-extractor".to_string(),
|
|
933
|
-
mime_types: &["text/plain"],
|
|
934
|
-
priority: 50,
|
|
935
|
-
});
|
|
936
|
-
|
|
937
|
-
registry.register(extractor).unwrap();
|
|
938
|
-
assert!(registry.get("text/plain").is_ok());
|
|
939
|
-
|
|
940
|
-
registry.remove("test-extractor").unwrap();
|
|
941
|
-
assert!(registry.get("text/plain").is_err());
|
|
942
|
-
}
|
|
943
|
-
|
|
944
|
-
#[test]
|
|
945
|
-
fn test_document_extractor_registry_shutdown_all() {
|
|
946
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
947
|
-
|
|
948
|
-
let extractor1 = Arc::new(MockExtractor {
|
|
949
|
-
name: "extractor1".to_string(),
|
|
950
|
-
mime_types: &["text/plain"],
|
|
951
|
-
priority: 50,
|
|
952
|
-
});
|
|
953
|
-
|
|
954
|
-
let extractor2 = Arc::new(MockExtractor {
|
|
955
|
-
name: "extractor2".to_string(),
|
|
956
|
-
mime_types: &["application/pdf"],
|
|
957
|
-
priority: 50,
|
|
958
|
-
});
|
|
959
|
-
|
|
960
|
-
registry.register(extractor1).unwrap();
|
|
961
|
-
registry.register(extractor2).unwrap();
|
|
962
|
-
|
|
963
|
-
assert_eq!(registry.list().len(), 2);
|
|
964
|
-
|
|
965
|
-
registry.shutdown_all().unwrap();
|
|
966
|
-
assert_eq!(registry.list().len(), 0);
|
|
967
|
-
}
|
|
968
|
-
|
|
969
|
-
#[test]
|
|
970
|
-
fn test_ocr_backend_registry_not_found() {
|
|
971
|
-
let registry = OcrBackendRegistry::new();
|
|
972
|
-
|
|
973
|
-
let result = registry.get("nonexistent");
|
|
974
|
-
assert!(matches!(result, Err(KreuzbergError::Plugin { .. })));
|
|
975
|
-
}
|
|
976
|
-
|
|
977
|
-
#[test]
|
|
978
|
-
fn test_ocr_backend_registry_language_not_found() {
|
|
979
|
-
let registry = OcrBackendRegistry::new();
|
|
980
|
-
|
|
981
|
-
let result = registry.get_for_language("xyz");
|
|
982
|
-
assert!(matches!(result, Err(KreuzbergError::Plugin { .. })));
|
|
983
|
-
}
|
|
984
|
-
|
|
985
|
-
#[test]
|
|
986
|
-
fn test_ocr_backend_registry_remove() {
|
|
987
|
-
let mut registry = OcrBackendRegistry::new();
|
|
988
|
-
|
|
989
|
-
let backend = Arc::new(MockOcrBackend {
|
|
990
|
-
name: "test-ocr".to_string(),
|
|
991
|
-
languages: vec!["eng".to_string()],
|
|
992
|
-
});
|
|
993
|
-
|
|
994
|
-
registry.register(backend).unwrap();
|
|
995
|
-
assert!(registry.get("test-ocr").is_ok());
|
|
996
|
-
|
|
997
|
-
registry.remove("test-ocr").unwrap();
|
|
998
|
-
assert!(registry.get("test-ocr").is_err());
|
|
999
|
-
}
|
|
1000
|
-
|
|
1001
|
-
#[test]
|
|
1002
|
-
fn test_post_processor_registry_remove() {
|
|
1003
|
-
let mut registry = PostProcessorRegistry::new();
|
|
1004
|
-
|
|
1005
|
-
let processor = Arc::new(MockPostProcessor {
|
|
1006
|
-
name: "test-processor".to_string(),
|
|
1007
|
-
stage: ProcessingStage::Early,
|
|
1008
|
-
});
|
|
1009
|
-
|
|
1010
|
-
registry.register(processor, 50).unwrap();
|
|
1011
|
-
assert_eq!(registry.get_for_stage(ProcessingStage::Early).len(), 1);
|
|
1012
|
-
|
|
1013
|
-
registry.remove("test-processor").unwrap();
|
|
1014
|
-
assert_eq!(registry.get_for_stage(ProcessingStage::Early).len(), 0);
|
|
1015
|
-
}
|
|
1016
|
-
|
|
1017
|
-
#[test]
|
|
1018
|
-
fn test_validator_registry_remove() {
|
|
1019
|
-
let mut registry = ValidatorRegistry::new();
|
|
1020
|
-
|
|
1021
|
-
let validator = Arc::new(MockValidator {
|
|
1022
|
-
name: "test-validator".to_string(),
|
|
1023
|
-
priority: 50,
|
|
1024
|
-
});
|
|
1025
|
-
|
|
1026
|
-
registry.register(validator).unwrap();
|
|
1027
|
-
assert_eq!(registry.get_all().len(), 1);
|
|
1028
|
-
|
|
1029
|
-
registry.remove("test-validator").unwrap();
|
|
1030
|
-
assert_eq!(registry.get_all().len(), 0);
|
|
1031
|
-
}
|
|
1032
|
-
|
|
1033
|
-
#[test]
|
|
1034
|
-
fn test_global_registry_access() {
|
|
1035
|
-
let ocr_registry = get_ocr_backend_registry();
|
|
1036
|
-
let _ = ocr_registry
|
|
1037
|
-
.read()
|
|
1038
|
-
.expect("Failed to acquire read lock on OCR registry in test")
|
|
1039
|
-
.list();
|
|
1040
|
-
|
|
1041
|
-
let extractor_registry = get_document_extractor_registry();
|
|
1042
|
-
let _ = extractor_registry
|
|
1043
|
-
.read()
|
|
1044
|
-
.expect("Failed to acquire read lock on extractor registry in test")
|
|
1045
|
-
.list();
|
|
1046
|
-
|
|
1047
|
-
let processor_registry = get_post_processor_registry();
|
|
1048
|
-
let _ = processor_registry
|
|
1049
|
-
.read()
|
|
1050
|
-
.expect("Failed to acquire read lock on processor registry in test")
|
|
1051
|
-
.list();
|
|
1052
|
-
|
|
1053
|
-
let validator_registry = get_validator_registry();
|
|
1054
|
-
let _ = validator_registry
|
|
1055
|
-
.read()
|
|
1056
|
-
.expect("Failed to acquire read lock on validator registry in test")
|
|
1057
|
-
.list();
|
|
1058
|
-
}
|
|
1059
|
-
|
|
1060
|
-
#[test]
|
|
1061
|
-
fn test_ocr_backend_registry_shutdown_all() {
|
|
1062
|
-
let mut registry = OcrBackendRegistry::new();
|
|
1063
|
-
let baseline = registry.list().len();
|
|
1064
|
-
|
|
1065
|
-
let backend1 = Arc::new(MockOcrBackend {
|
|
1066
|
-
name: "backend1".to_string(),
|
|
1067
|
-
languages: vec!["eng".to_string()],
|
|
1068
|
-
});
|
|
1069
|
-
|
|
1070
|
-
let backend2 = Arc::new(MockOcrBackend {
|
|
1071
|
-
name: "backend2".to_string(),
|
|
1072
|
-
languages: vec!["deu".to_string()],
|
|
1073
|
-
});
|
|
1074
|
-
|
|
1075
|
-
registry.register(backend1).unwrap();
|
|
1076
|
-
registry.register(backend2).unwrap();
|
|
1077
|
-
|
|
1078
|
-
assert_eq!(registry.list().len(), baseline + 2);
|
|
1079
|
-
|
|
1080
|
-
registry.shutdown_all().unwrap();
|
|
1081
|
-
assert_eq!(registry.list().len(), 0);
|
|
1082
|
-
}
|
|
1083
|
-
|
|
1084
|
-
#[test]
|
|
1085
|
-
fn test_post_processor_registry_shutdown_all() {
|
|
1086
|
-
let mut registry = PostProcessorRegistry::new();
|
|
1087
|
-
|
|
1088
|
-
let early = Arc::new(MockPostProcessor {
|
|
1089
|
-
name: "early".to_string(),
|
|
1090
|
-
stage: ProcessingStage::Early,
|
|
1091
|
-
});
|
|
1092
|
-
|
|
1093
|
-
let late = Arc::new(MockPostProcessor {
|
|
1094
|
-
name: "late".to_string(),
|
|
1095
|
-
stage: ProcessingStage::Late,
|
|
1096
|
-
});
|
|
1097
|
-
|
|
1098
|
-
registry.register(early, 100).unwrap();
|
|
1099
|
-
registry.register(late, 50).unwrap();
|
|
1100
|
-
|
|
1101
|
-
assert_eq!(registry.list().len(), 2);
|
|
1102
|
-
|
|
1103
|
-
registry.shutdown_all().unwrap();
|
|
1104
|
-
assert_eq!(registry.list().len(), 0);
|
|
1105
|
-
}
|
|
1106
|
-
|
|
1107
|
-
#[test]
|
|
1108
|
-
fn test_validator_registry_shutdown_all() {
|
|
1109
|
-
let mut registry = ValidatorRegistry::new();
|
|
1110
|
-
|
|
1111
|
-
let validator1 = Arc::new(MockValidator {
|
|
1112
|
-
name: "validator1".to_string(),
|
|
1113
|
-
priority: 100,
|
|
1114
|
-
});
|
|
1115
|
-
|
|
1116
|
-
let validator2 = Arc::new(MockValidator {
|
|
1117
|
-
name: "validator2".to_string(),
|
|
1118
|
-
priority: 50,
|
|
1119
|
-
});
|
|
1120
|
-
|
|
1121
|
-
registry.register(validator1).unwrap();
|
|
1122
|
-
registry.register(validator2).unwrap();
|
|
1123
|
-
|
|
1124
|
-
assert_eq!(registry.get_all().len(), 2);
|
|
1125
|
-
|
|
1126
|
-
registry.shutdown_all().unwrap();
|
|
1127
|
-
assert_eq!(registry.get_all().len(), 0);
|
|
1128
|
-
}
|
|
1129
|
-
|
|
1130
|
-
#[test]
|
|
1131
|
-
fn test_document_extractor_registry_multiple_mime_types() {
|
|
1132
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
1133
|
-
|
|
1134
|
-
let multi_extractor = Arc::new(MockExtractor {
|
|
1135
|
-
name: "multi-extractor".to_string(),
|
|
1136
|
-
mime_types: &["text/plain", "text/markdown", "text/html"],
|
|
1137
|
-
priority: 50,
|
|
1138
|
-
});
|
|
1139
|
-
|
|
1140
|
-
registry.register(multi_extractor).unwrap();
|
|
1141
|
-
|
|
1142
|
-
assert_eq!(registry.get("text/plain").unwrap().name(), "multi-extractor");
|
|
1143
|
-
assert_eq!(registry.get("text/markdown").unwrap().name(), "multi-extractor");
|
|
1144
|
-
assert_eq!(registry.get("text/html").unwrap().name(), "multi-extractor");
|
|
1145
|
-
}
|
|
1146
|
-
|
|
1147
|
-
#[test]
|
|
1148
|
-
fn test_post_processor_registry_priority_order() {
|
|
1149
|
-
let mut registry = PostProcessorRegistry::new();
|
|
1150
|
-
|
|
1151
|
-
let low = Arc::new(MockPostProcessor {
|
|
1152
|
-
name: "low-priority".to_string(),
|
|
1153
|
-
stage: ProcessingStage::Early,
|
|
1154
|
-
});
|
|
1155
|
-
|
|
1156
|
-
let high = Arc::new(MockPostProcessor {
|
|
1157
|
-
name: "high-priority".to_string(),
|
|
1158
|
-
stage: ProcessingStage::Early,
|
|
1159
|
-
});
|
|
1160
|
-
|
|
1161
|
-
registry.register(low, 10).unwrap();
|
|
1162
|
-
registry.register(high, 100).unwrap();
|
|
1163
|
-
|
|
1164
|
-
let processors = registry.get_for_stage(ProcessingStage::Early);
|
|
1165
|
-
assert_eq!(processors.len(), 2);
|
|
1166
|
-
assert_eq!(processors[0].name(), "high-priority");
|
|
1167
|
-
assert_eq!(processors[1].name(), "low-priority");
|
|
1168
|
-
}
|
|
1169
|
-
|
|
1170
|
-
#[test]
|
|
1171
|
-
fn test_post_processor_registry_empty_stage() {
|
|
1172
|
-
let registry = PostProcessorRegistry::new();
|
|
1173
|
-
|
|
1174
|
-
let processors = registry.get_for_stage(ProcessingStage::Late);
|
|
1175
|
-
assert_eq!(processors.len(), 0);
|
|
1176
|
-
}
|
|
1177
|
-
|
|
1178
|
-
#[test]
|
|
1179
|
-
fn test_ocr_backend_registry_default() {
|
|
1180
|
-
let registry = OcrBackendRegistry::default();
|
|
1181
|
-
#[cfg(feature = "ocr")]
|
|
1182
|
-
assert!(
|
|
1183
|
-
!registry.list().is_empty(),
|
|
1184
|
-
"expected at least one default OCR backend when the 'ocr' feature is enabled"
|
|
1185
|
-
);
|
|
1186
|
-
#[cfg(not(feature = "ocr"))]
|
|
1187
|
-
assert_eq!(registry.list().len(), 0);
|
|
1188
|
-
}
|
|
1189
|
-
|
|
1190
|
-
#[test]
|
|
1191
|
-
fn test_document_extractor_registry_default() {
|
|
1192
|
-
let registry = DocumentExtractorRegistry::default();
|
|
1193
|
-
assert_eq!(registry.list().len(), 0);
|
|
1194
|
-
}
|
|
1195
|
-
|
|
1196
|
-
#[test]
|
|
1197
|
-
fn test_post_processor_registry_default() {
|
|
1198
|
-
let registry = PostProcessorRegistry::default();
|
|
1199
|
-
assert_eq!(registry.list().len(), 0);
|
|
1200
|
-
}
|
|
1201
|
-
|
|
1202
|
-
#[test]
|
|
1203
|
-
fn test_validator_registry_default() {
|
|
1204
|
-
let registry = ValidatorRegistry::default();
|
|
1205
|
-
assert_eq!(registry.get_all().len(), 0);
|
|
1206
|
-
}
|
|
1207
|
-
|
|
1208
|
-
#[test]
|
|
1209
|
-
fn test_document_extractor_registry_exact_over_prefix() {
|
|
1210
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
1211
|
-
|
|
1212
|
-
let prefix_extractor = Arc::new(MockExtractor {
|
|
1213
|
-
name: "prefix-extractor".to_string(),
|
|
1214
|
-
mime_types: &["image/*"],
|
|
1215
|
-
priority: 100,
|
|
1216
|
-
});
|
|
1217
|
-
|
|
1218
|
-
let exact_extractor = Arc::new(MockExtractor {
|
|
1219
|
-
name: "exact-extractor".to_string(),
|
|
1220
|
-
mime_types: &["image/png"],
|
|
1221
|
-
priority: 50,
|
|
1222
|
-
});
|
|
1223
|
-
|
|
1224
|
-
registry.register(prefix_extractor).unwrap();
|
|
1225
|
-
registry.register(exact_extractor).unwrap();
|
|
1226
|
-
|
|
1227
|
-
let retrieved = registry.get("image/png").unwrap();
|
|
1228
|
-
assert_eq!(retrieved.name(), "exact-extractor");
|
|
1229
|
-
|
|
1230
|
-
let retrieved_jpg = registry.get("image/jpeg").unwrap();
|
|
1231
|
-
assert_eq!(retrieved_jpg.name(), "prefix-extractor");
|
|
1232
|
-
}
|
|
1233
|
-
|
|
1234
|
-
#[test]
|
|
1235
|
-
fn test_ocr_backend_registry_invalid_name_empty() {
|
|
1236
|
-
let mut registry = OcrBackendRegistry::new();
|
|
1237
|
-
|
|
1238
|
-
let backend = Arc::new(MockOcrBackend {
|
|
1239
|
-
name: "".to_string(),
|
|
1240
|
-
languages: vec!["eng".to_string()],
|
|
1241
|
-
});
|
|
1242
|
-
|
|
1243
|
-
let result = registry.register(backend);
|
|
1244
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1245
|
-
}
|
|
1246
|
-
|
|
1247
|
-
#[test]
|
|
1248
|
-
fn test_ocr_backend_registry_invalid_name_whitespace() {
|
|
1249
|
-
let mut registry = OcrBackendRegistry::new();
|
|
1250
|
-
|
|
1251
|
-
let backend = Arc::new(MockOcrBackend {
|
|
1252
|
-
name: "my ocr backend".to_string(),
|
|
1253
|
-
languages: vec!["eng".to_string()],
|
|
1254
|
-
});
|
|
1255
|
-
|
|
1256
|
-
let result = registry.register(backend);
|
|
1257
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1258
|
-
}
|
|
1259
|
-
|
|
1260
|
-
#[test]
|
|
1261
|
-
fn test_document_extractor_registry_invalid_name_empty() {
|
|
1262
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
1263
|
-
|
|
1264
|
-
let extractor = Arc::new(MockExtractor {
|
|
1265
|
-
name: "".to_string(),
|
|
1266
|
-
mime_types: &["text/plain"],
|
|
1267
|
-
priority: 50,
|
|
1268
|
-
});
|
|
1269
|
-
|
|
1270
|
-
let result = registry.register(extractor);
|
|
1271
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1272
|
-
}
|
|
1273
|
-
|
|
1274
|
-
#[test]
|
|
1275
|
-
fn test_document_extractor_registry_invalid_name_whitespace() {
|
|
1276
|
-
let mut registry = DocumentExtractorRegistry::new();
|
|
1277
|
-
|
|
1278
|
-
let extractor = Arc::new(MockExtractor {
|
|
1279
|
-
name: "my extractor".to_string(),
|
|
1280
|
-
mime_types: &["text/plain"],
|
|
1281
|
-
priority: 50,
|
|
1282
|
-
});
|
|
1283
|
-
|
|
1284
|
-
let result = registry.register(extractor);
|
|
1285
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1286
|
-
}
|
|
1287
|
-
|
|
1288
|
-
#[test]
|
|
1289
|
-
fn test_post_processor_registry_invalid_name_empty() {
|
|
1290
|
-
let mut registry = PostProcessorRegistry::new();
|
|
1291
|
-
|
|
1292
|
-
let processor = Arc::new(MockPostProcessor {
|
|
1293
|
-
name: "".to_string(),
|
|
1294
|
-
stage: ProcessingStage::Early,
|
|
1295
|
-
});
|
|
1296
|
-
|
|
1297
|
-
let result = registry.register(processor, 50);
|
|
1298
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1299
|
-
}
|
|
1300
|
-
|
|
1301
|
-
#[test]
|
|
1302
|
-
fn test_post_processor_registry_invalid_name_whitespace() {
|
|
1303
|
-
let mut registry = PostProcessorRegistry::new();
|
|
1304
|
-
|
|
1305
|
-
let processor = Arc::new(MockPostProcessor {
|
|
1306
|
-
name: "my processor".to_string(),
|
|
1307
|
-
stage: ProcessingStage::Early,
|
|
1308
|
-
});
|
|
1309
|
-
|
|
1310
|
-
let result = registry.register(processor, 50);
|
|
1311
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1312
|
-
}
|
|
1313
|
-
|
|
1314
|
-
#[test]
|
|
1315
|
-
fn test_validator_registry_invalid_name_empty() {
|
|
1316
|
-
let mut registry = ValidatorRegistry::new();
|
|
1317
|
-
|
|
1318
|
-
let validator = Arc::new(MockValidator {
|
|
1319
|
-
name: "".to_string(),
|
|
1320
|
-
priority: 50,
|
|
1321
|
-
});
|
|
1322
|
-
|
|
1323
|
-
let result = registry.register(validator);
|
|
1324
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1325
|
-
}
|
|
1326
|
-
|
|
1327
|
-
#[test]
|
|
1328
|
-
fn test_validator_registry_invalid_name_whitespace() {
|
|
1329
|
-
let mut registry = ValidatorRegistry::new();
|
|
1330
|
-
|
|
1331
|
-
let validator = Arc::new(MockValidator {
|
|
1332
|
-
name: "my validator".to_string(),
|
|
1333
|
-
priority: 50,
|
|
1334
|
-
});
|
|
1335
|
-
|
|
1336
|
-
let result = registry.register(validator);
|
|
1337
|
-
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1338
|
-
}
|
|
1339
|
-
}
|
|
1
|
+
//! Plugin registration and discovery.
|
|
2
|
+
//!
|
|
3
|
+
//! This module provides registries for managing plugins of different types.
|
|
4
|
+
//! Each plugin type (OcrBackend, DocumentExtractor, etc.) has its own registry
|
|
5
|
+
//! with type-safe registration and lookup.
|
|
6
|
+
|
|
7
|
+
use crate::plugins::{DocumentExtractor, OcrBackend, PostProcessor, ProcessingStage, Validator};
|
|
8
|
+
use crate::{KreuzbergError, Result};
|
|
9
|
+
use indexmap::IndexMap;
|
|
10
|
+
use once_cell::sync::Lazy;
|
|
11
|
+
use std::collections::{BTreeMap, HashMap};
|
|
12
|
+
use std::sync::{Arc, RwLock};
|
|
13
|
+
|
|
14
|
+
/// Validate a plugin name before registration.
|
|
15
|
+
///
|
|
16
|
+
/// # Rules
|
|
17
|
+
///
|
|
18
|
+
/// - Name cannot be empty
|
|
19
|
+
/// - Name cannot contain whitespace
|
|
20
|
+
/// - Name should follow kebab-case convention (lowercase with hyphens)
|
|
21
|
+
///
|
|
22
|
+
/// # Errors
|
|
23
|
+
///
|
|
24
|
+
/// Returns `ValidationError` if the name is invalid.
|
|
25
|
+
fn validate_plugin_name(name: &str) -> Result<()> {
|
|
26
|
+
if name.is_empty() {
|
|
27
|
+
return Err(KreuzbergError::Validation {
|
|
28
|
+
message: "Plugin name cannot be empty".to_string(),
|
|
29
|
+
source: None,
|
|
30
|
+
});
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
if name.contains(char::is_whitespace) {
|
|
34
|
+
return Err(KreuzbergError::Validation {
|
|
35
|
+
message: format!("Plugin name '{}' cannot contain whitespace", name),
|
|
36
|
+
source: None,
|
|
37
|
+
});
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
Ok(())
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
/// Registry for OCR backend plugins.
|
|
44
|
+
///
|
|
45
|
+
/// Manages OCR backends with backend type and language-based selection.
|
|
46
|
+
///
|
|
47
|
+
/// # Thread Safety
|
|
48
|
+
///
|
|
49
|
+
/// The registry is thread-safe and can be accessed concurrently from multiple threads.
|
|
50
|
+
///
|
|
51
|
+
/// # Example
|
|
52
|
+
///
|
|
53
|
+
/// ```rust,no_run
|
|
54
|
+
/// use kreuzberg::plugins::registry::OcrBackendRegistry;
|
|
55
|
+
/// use std::sync::Arc;
|
|
56
|
+
///
|
|
57
|
+
/// let registry = OcrBackendRegistry::new();
|
|
58
|
+
/// // Register OCR backends
|
|
59
|
+
/// // registry.register(Arc::new(TesseractBackend::new()));
|
|
60
|
+
/// ```
|
|
61
|
+
pub struct OcrBackendRegistry {
|
|
62
|
+
backends: HashMap<String, Arc<dyn OcrBackend>>,
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
impl OcrBackendRegistry {
|
|
66
|
+
/// Create a new OCR backend registry with default backends.
|
|
67
|
+
///
|
|
68
|
+
/// Registers the Tesseract backend by default if the "ocr" feature is enabled.
|
|
69
|
+
pub fn new() -> Self {
|
|
70
|
+
#[cfg(feature = "ocr")]
|
|
71
|
+
let mut registry = Self {
|
|
72
|
+
backends: HashMap::new(),
|
|
73
|
+
};
|
|
74
|
+
|
|
75
|
+
#[cfg(not(feature = "ocr"))]
|
|
76
|
+
let registry = Self {
|
|
77
|
+
backends: HashMap::new(),
|
|
78
|
+
};
|
|
79
|
+
|
|
80
|
+
#[cfg(feature = "ocr")]
|
|
81
|
+
{
|
|
82
|
+
use crate::ocr::tesseract_backend::TesseractBackend;
|
|
83
|
+
if let Ok(backend) = TesseractBackend::new() {
|
|
84
|
+
let _ = registry.register(Arc::new(backend));
|
|
85
|
+
}
|
|
86
|
+
}
|
|
87
|
+
|
|
88
|
+
registry
|
|
89
|
+
}
|
|
90
|
+
|
|
91
|
+
/// Create a new empty OCR backend registry without default backends.
|
|
92
|
+
///
|
|
93
|
+
/// This is useful for testing or when you want full control over backend registration.
|
|
94
|
+
pub fn new_empty() -> Self {
|
|
95
|
+
Self {
|
|
96
|
+
backends: HashMap::new(),
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
|
|
100
|
+
/// Register an OCR backend.
|
|
101
|
+
///
|
|
102
|
+
/// # Arguments
|
|
103
|
+
///
|
|
104
|
+
/// * `backend` - The OCR backend to register
|
|
105
|
+
///
|
|
106
|
+
/// # Returns
|
|
107
|
+
///
|
|
108
|
+
/// - `Ok(())` if registration succeeded
|
|
109
|
+
/// - `Err(...)` if initialization failed
|
|
110
|
+
///
|
|
111
|
+
/// # Example
|
|
112
|
+
///
|
|
113
|
+
/// ```rust,no_run
|
|
114
|
+
/// # use kreuzberg::plugins::registry::OcrBackendRegistry;
|
|
115
|
+
/// # use std::sync::Arc;
|
|
116
|
+
/// let mut registry = OcrBackendRegistry::new();
|
|
117
|
+
/// // let backend = Arc::new(MyOcrBackend::new());
|
|
118
|
+
/// // registry.register(backend)?;
|
|
119
|
+
/// # Ok::<(), kreuzberg::KreuzbergError>(())
|
|
120
|
+
/// ```
|
|
121
|
+
pub fn register(&mut self, backend: Arc<dyn OcrBackend>) -> Result<()> {
|
|
122
|
+
let name = backend.name().to_string();
|
|
123
|
+
|
|
124
|
+
validate_plugin_name(&name)?;
|
|
125
|
+
|
|
126
|
+
backend.initialize()?;
|
|
127
|
+
|
|
128
|
+
self.backends.insert(name, backend);
|
|
129
|
+
Ok(())
|
|
130
|
+
}
|
|
131
|
+
|
|
132
|
+
/// Get an OCR backend by name.
|
|
133
|
+
///
|
|
134
|
+
/// # Arguments
|
|
135
|
+
///
|
|
136
|
+
/// * `name` - Backend name
|
|
137
|
+
///
|
|
138
|
+
/// # Returns
|
|
139
|
+
///
|
|
140
|
+
/// The backend if found, or an error if not registered.
|
|
141
|
+
pub fn get(&self, name: &str) -> Result<Arc<dyn OcrBackend>> {
|
|
142
|
+
self.backends.get(name).cloned().ok_or_else(|| KreuzbergError::Plugin {
|
|
143
|
+
message: format!("OCR backend '{}' not registered", name),
|
|
144
|
+
plugin_name: name.to_string(),
|
|
145
|
+
})
|
|
146
|
+
}
|
|
147
|
+
|
|
148
|
+
/// Get an OCR backend that supports a specific language.
|
|
149
|
+
///
|
|
150
|
+
/// Returns the first backend that supports the language.
|
|
151
|
+
///
|
|
152
|
+
/// # Arguments
|
|
153
|
+
///
|
|
154
|
+
/// * `language` - Language code (e.g., "eng", "deu")
|
|
155
|
+
///
|
|
156
|
+
/// # Returns
|
|
157
|
+
///
|
|
158
|
+
/// The first backend supporting the language, or an error if none found.
|
|
159
|
+
pub fn get_for_language(&self, language: &str) -> Result<Arc<dyn OcrBackend>> {
|
|
160
|
+
self.backends
|
|
161
|
+
.values()
|
|
162
|
+
.find(|backend| backend.supports_language(language))
|
|
163
|
+
.cloned()
|
|
164
|
+
.ok_or_else(|| KreuzbergError::Plugin {
|
|
165
|
+
message: format!("No OCR backend supports language '{}'", language),
|
|
166
|
+
plugin_name: language.to_string(),
|
|
167
|
+
})
|
|
168
|
+
}
|
|
169
|
+
|
|
170
|
+
/// List all registered backend names.
|
|
171
|
+
pub fn list(&self) -> Vec<String> {
|
|
172
|
+
self.backends.keys().cloned().collect()
|
|
173
|
+
}
|
|
174
|
+
|
|
175
|
+
/// Remove a backend from the registry.
|
|
176
|
+
///
|
|
177
|
+
/// Calls `shutdown()` on the backend before removing.
|
|
178
|
+
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
179
|
+
if let Some(backend) = self.backends.remove(name) {
|
|
180
|
+
backend.shutdown()?;
|
|
181
|
+
}
|
|
182
|
+
Ok(())
|
|
183
|
+
}
|
|
184
|
+
|
|
185
|
+
/// Shutdown all backends and clear the registry.
|
|
186
|
+
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
187
|
+
let names: Vec<_> = self.backends.keys().cloned().collect();
|
|
188
|
+
for name in names {
|
|
189
|
+
self.remove(&name)?;
|
|
190
|
+
}
|
|
191
|
+
Ok(())
|
|
192
|
+
}
|
|
193
|
+
}
|
|
194
|
+
|
|
195
|
+
impl Default for OcrBackendRegistry {
|
|
196
|
+
fn default() -> Self {
|
|
197
|
+
Self::new()
|
|
198
|
+
}
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
/// Registry for document extractor plugins.
|
|
202
|
+
///
|
|
203
|
+
/// Manages extractors with MIME type and priority-based selection.
|
|
204
|
+
///
|
|
205
|
+
/// # Thread Safety
|
|
206
|
+
///
|
|
207
|
+
/// The registry is thread-safe and can be accessed concurrently from multiple threads.
|
|
208
|
+
pub struct DocumentExtractorRegistry {
|
|
209
|
+
extractors: HashMap<String, BTreeMap<i32, Arc<dyn DocumentExtractor>>>,
|
|
210
|
+
name_index: HashMap<String, Vec<(String, i32)>>,
|
|
211
|
+
}
|
|
212
|
+
|
|
213
|
+
impl DocumentExtractorRegistry {
|
|
214
|
+
/// Create a new empty extractor registry.
|
|
215
|
+
pub fn new() -> Self {
|
|
216
|
+
Self {
|
|
217
|
+
extractors: HashMap::new(),
|
|
218
|
+
name_index: HashMap::new(),
|
|
219
|
+
}
|
|
220
|
+
}
|
|
221
|
+
|
|
222
|
+
/// Register a document extractor.
|
|
223
|
+
///
|
|
224
|
+
/// The extractor is registered for all MIME types it supports.
|
|
225
|
+
///
|
|
226
|
+
/// # Arguments
|
|
227
|
+
///
|
|
228
|
+
/// * `extractor` - The extractor to register
|
|
229
|
+
///
|
|
230
|
+
/// # Returns
|
|
231
|
+
///
|
|
232
|
+
/// - `Ok(())` if registration succeeded
|
|
233
|
+
/// - `Err(...)` if initialization failed
|
|
234
|
+
pub fn register(&mut self, extractor: Arc<dyn DocumentExtractor>) -> Result<()> {
|
|
235
|
+
let name = extractor.name().to_string();
|
|
236
|
+
let priority = extractor.priority();
|
|
237
|
+
let mime_types: Vec<String> = extractor.supported_mime_types().iter().map(|s| s.to_string()).collect();
|
|
238
|
+
|
|
239
|
+
validate_plugin_name(&name)?;
|
|
240
|
+
|
|
241
|
+
extractor.initialize()?;
|
|
242
|
+
|
|
243
|
+
let mut index_entries = Vec::new();
|
|
244
|
+
|
|
245
|
+
for mime_type in &mime_types {
|
|
246
|
+
self.extractors
|
|
247
|
+
.entry(mime_type.clone())
|
|
248
|
+
.or_default()
|
|
249
|
+
.insert(priority, Arc::clone(&extractor));
|
|
250
|
+
index_entries.push((mime_type.clone(), priority));
|
|
251
|
+
}
|
|
252
|
+
|
|
253
|
+
self.name_index.insert(name, index_entries);
|
|
254
|
+
|
|
255
|
+
Ok(())
|
|
256
|
+
}
|
|
257
|
+
|
|
258
|
+
/// Get the highest priority extractor for a MIME type.
|
|
259
|
+
///
|
|
260
|
+
/// # Arguments
|
|
261
|
+
///
|
|
262
|
+
/// * `mime_type` - MIME type to look up
|
|
263
|
+
///
|
|
264
|
+
/// # Returns
|
|
265
|
+
///
|
|
266
|
+
/// The highest priority extractor, or an error if none found.
|
|
267
|
+
#[cfg_attr(feature = "otel", tracing::instrument(
|
|
268
|
+
skip(self),
|
|
269
|
+
fields(
|
|
270
|
+
registry.mime_type = %mime_type,
|
|
271
|
+
registry.found = tracing::field::Empty,
|
|
272
|
+
)
|
|
273
|
+
))]
|
|
274
|
+
pub fn get(&self, mime_type: &str) -> Result<Arc<dyn DocumentExtractor>> {
|
|
275
|
+
if let Some(priority_map) = self.extractors.get(mime_type)
|
|
276
|
+
&& let Some((_priority, extractor)) = priority_map.iter().next_back()
|
|
277
|
+
{
|
|
278
|
+
#[cfg(feature = "otel")]
|
|
279
|
+
tracing::Span::current().record("registry.found", true);
|
|
280
|
+
return Ok(Arc::clone(extractor));
|
|
281
|
+
}
|
|
282
|
+
|
|
283
|
+
let mut best_match: Option<(i32, Arc<dyn DocumentExtractor>)> = None;
|
|
284
|
+
|
|
285
|
+
for (registered_mime, priority_map) in &self.extractors {
|
|
286
|
+
if registered_mime.ends_with("/*") {
|
|
287
|
+
let prefix = ®istered_mime[..registered_mime.len() - 1];
|
|
288
|
+
if mime_type.starts_with(prefix)
|
|
289
|
+
&& let Some((_priority, extractor)) = priority_map.iter().next_back()
|
|
290
|
+
{
|
|
291
|
+
let priority = extractor.priority();
|
|
292
|
+
match &best_match {
|
|
293
|
+
None => best_match = Some((priority, Arc::clone(extractor))),
|
|
294
|
+
Some((current_priority, _)) => {
|
|
295
|
+
if priority > *current_priority {
|
|
296
|
+
best_match = Some((priority, Arc::clone(extractor)));
|
|
297
|
+
}
|
|
298
|
+
}
|
|
299
|
+
}
|
|
300
|
+
}
|
|
301
|
+
}
|
|
302
|
+
}
|
|
303
|
+
|
|
304
|
+
if let Some((_priority, extractor)) = best_match {
|
|
305
|
+
#[cfg(feature = "otel")]
|
|
306
|
+
tracing::Span::current().record("registry.found", true);
|
|
307
|
+
return Ok(extractor);
|
|
308
|
+
}
|
|
309
|
+
|
|
310
|
+
#[cfg(feature = "otel")]
|
|
311
|
+
tracing::Span::current().record("registry.found", false);
|
|
312
|
+
Err(KreuzbergError::UnsupportedFormat(mime_type.to_string()))
|
|
313
|
+
}
|
|
314
|
+
|
|
315
|
+
/// List all registered extractors.
|
|
316
|
+
pub fn list(&self) -> Vec<String> {
|
|
317
|
+
self.name_index.keys().cloned().collect()
|
|
318
|
+
}
|
|
319
|
+
|
|
320
|
+
/// Remove an extractor from the registry.
|
|
321
|
+
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
322
|
+
let index_entries = match self.name_index.remove(name) {
|
|
323
|
+
Some(entries) => entries,
|
|
324
|
+
None => return Ok(()),
|
|
325
|
+
};
|
|
326
|
+
|
|
327
|
+
let mut extractor_to_shutdown: Option<Arc<dyn DocumentExtractor>> = None;
|
|
328
|
+
|
|
329
|
+
for (mime_type, priority) in index_entries {
|
|
330
|
+
if let Some(priority_map) = self.extractors.get_mut(&mime_type) {
|
|
331
|
+
if let Some(extractor) = priority_map.remove(&priority)
|
|
332
|
+
&& extractor_to_shutdown.is_none()
|
|
333
|
+
{
|
|
334
|
+
extractor_to_shutdown = Some(extractor);
|
|
335
|
+
}
|
|
336
|
+
|
|
337
|
+
if priority_map.is_empty() {
|
|
338
|
+
self.extractors.remove(&mime_type);
|
|
339
|
+
}
|
|
340
|
+
}
|
|
341
|
+
}
|
|
342
|
+
|
|
343
|
+
if let Some(extractor) = extractor_to_shutdown {
|
|
344
|
+
extractor.shutdown()?;
|
|
345
|
+
}
|
|
346
|
+
|
|
347
|
+
Ok(())
|
|
348
|
+
}
|
|
349
|
+
|
|
350
|
+
/// Shutdown all extractors and clear the registry.
|
|
351
|
+
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
352
|
+
let names = self.list();
|
|
353
|
+
for name in names {
|
|
354
|
+
self.remove(&name)?;
|
|
355
|
+
}
|
|
356
|
+
Ok(())
|
|
357
|
+
}
|
|
358
|
+
}
|
|
359
|
+
|
|
360
|
+
impl Default for DocumentExtractorRegistry {
|
|
361
|
+
fn default() -> Self {
|
|
362
|
+
Self::new()
|
|
363
|
+
}
|
|
364
|
+
}
|
|
365
|
+
|
|
366
|
+
/// Registry for post-processor plugins.
|
|
367
|
+
///
|
|
368
|
+
/// Manages post-processors organized by processing stage.
|
|
369
|
+
pub struct PostProcessorRegistry {
|
|
370
|
+
processors: HashMap<ProcessingStage, BTreeMap<i32, Vec<Arc<dyn PostProcessor>>>>,
|
|
371
|
+
name_index: HashMap<String, (ProcessingStage, i32)>,
|
|
372
|
+
}
|
|
373
|
+
|
|
374
|
+
impl PostProcessorRegistry {
|
|
375
|
+
/// Create a new empty post-processor registry.
|
|
376
|
+
pub fn new() -> Self {
|
|
377
|
+
Self {
|
|
378
|
+
processors: HashMap::new(),
|
|
379
|
+
name_index: HashMap::new(),
|
|
380
|
+
}
|
|
381
|
+
}
|
|
382
|
+
|
|
383
|
+
/// Register a post-processor.
|
|
384
|
+
///
|
|
385
|
+
/// # Arguments
|
|
386
|
+
///
|
|
387
|
+
/// * `processor` - The post-processor to register
|
|
388
|
+
/// * `priority` - Execution priority (higher = runs first within stage)
|
|
389
|
+
pub fn register(&mut self, processor: Arc<dyn PostProcessor>, priority: i32) -> Result<()> {
|
|
390
|
+
let name = processor.name().to_string();
|
|
391
|
+
let stage = processor.processing_stage();
|
|
392
|
+
|
|
393
|
+
validate_plugin_name(&name)?;
|
|
394
|
+
|
|
395
|
+
processor.initialize()?;
|
|
396
|
+
|
|
397
|
+
if self.name_index.contains_key(&name) {
|
|
398
|
+
self.remove(&name)?;
|
|
399
|
+
}
|
|
400
|
+
|
|
401
|
+
self.processors
|
|
402
|
+
.entry(stage)
|
|
403
|
+
.or_default()
|
|
404
|
+
.entry(priority)
|
|
405
|
+
.or_default()
|
|
406
|
+
.push(Arc::clone(&processor));
|
|
407
|
+
|
|
408
|
+
self.name_index.insert(name, (stage, priority));
|
|
409
|
+
|
|
410
|
+
Ok(())
|
|
411
|
+
}
|
|
412
|
+
|
|
413
|
+
/// Get all processors for a specific stage, in priority order.
|
|
414
|
+
///
|
|
415
|
+
/// # Arguments
|
|
416
|
+
///
|
|
417
|
+
/// * `stage` - The processing stage
|
|
418
|
+
///
|
|
419
|
+
/// # Returns
|
|
420
|
+
///
|
|
421
|
+
/// Vector of processors in priority order (highest first).
|
|
422
|
+
pub fn get_for_stage(&self, stage: ProcessingStage) -> Vec<Arc<dyn PostProcessor>> {
|
|
423
|
+
let mut result = Vec::new();
|
|
424
|
+
|
|
425
|
+
if let Some(priority_map) = self.processors.get(&stage) {
|
|
426
|
+
for (_priority, processors) in priority_map.iter().rev() {
|
|
427
|
+
for processor in processors {
|
|
428
|
+
result.push(Arc::clone(processor));
|
|
429
|
+
}
|
|
430
|
+
}
|
|
431
|
+
}
|
|
432
|
+
|
|
433
|
+
result
|
|
434
|
+
}
|
|
435
|
+
|
|
436
|
+
/// List all registered processor names.
|
|
437
|
+
pub fn list(&self) -> Vec<String> {
|
|
438
|
+
self.name_index.keys().cloned().collect()
|
|
439
|
+
}
|
|
440
|
+
|
|
441
|
+
/// Remove a processor from the registry.
|
|
442
|
+
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
443
|
+
let (stage, priority) = match self.name_index.remove(name) {
|
|
444
|
+
Some(location) => location,
|
|
445
|
+
None => return Ok(()),
|
|
446
|
+
};
|
|
447
|
+
|
|
448
|
+
let processor_to_shutdown = if let Some(priority_map) = self.processors.get_mut(&stage) {
|
|
449
|
+
let processor = priority_map.get_mut(&priority).and_then(|processors| {
|
|
450
|
+
processors
|
|
451
|
+
.iter()
|
|
452
|
+
.position(|p| p.name() == name)
|
|
453
|
+
.map(|pos| processors.remove(pos))
|
|
454
|
+
});
|
|
455
|
+
|
|
456
|
+
if let Some(processors) = priority_map.get(&priority)
|
|
457
|
+
&& processors.is_empty()
|
|
458
|
+
{
|
|
459
|
+
priority_map.remove(&priority);
|
|
460
|
+
}
|
|
461
|
+
|
|
462
|
+
if priority_map.is_empty() {
|
|
463
|
+
self.processors.remove(&stage);
|
|
464
|
+
}
|
|
465
|
+
processor
|
|
466
|
+
} else {
|
|
467
|
+
None
|
|
468
|
+
};
|
|
469
|
+
|
|
470
|
+
if let Some(processor) = processor_to_shutdown {
|
|
471
|
+
processor.shutdown()?;
|
|
472
|
+
}
|
|
473
|
+
|
|
474
|
+
Ok(())
|
|
475
|
+
}
|
|
476
|
+
|
|
477
|
+
/// Shutdown all processors and clear the registry.
|
|
478
|
+
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
479
|
+
let names = self.list();
|
|
480
|
+
for name in names {
|
|
481
|
+
self.remove(&name)?;
|
|
482
|
+
}
|
|
483
|
+
Ok(())
|
|
484
|
+
}
|
|
485
|
+
}
|
|
486
|
+
|
|
487
|
+
impl Default for PostProcessorRegistry {
|
|
488
|
+
fn default() -> Self {
|
|
489
|
+
Self::new()
|
|
490
|
+
}
|
|
491
|
+
}
|
|
492
|
+
|
|
493
|
+
/// Registry for validator plugins.
|
|
494
|
+
///
|
|
495
|
+
/// Manages validators with priority-based execution order.
|
|
496
|
+
pub struct ValidatorRegistry {
|
|
497
|
+
validators: BTreeMap<i32, IndexMap<String, Arc<dyn Validator>>>,
|
|
498
|
+
}
|
|
499
|
+
|
|
500
|
+
impl ValidatorRegistry {
|
|
501
|
+
/// Create a new empty validator registry.
|
|
502
|
+
pub fn new() -> Self {
|
|
503
|
+
Self {
|
|
504
|
+
validators: BTreeMap::new(),
|
|
505
|
+
}
|
|
506
|
+
}
|
|
507
|
+
|
|
508
|
+
/// Register a validator.
|
|
509
|
+
///
|
|
510
|
+
/// # Arguments
|
|
511
|
+
///
|
|
512
|
+
/// * `validator` - The validator to register
|
|
513
|
+
pub fn register(&mut self, validator: Arc<dyn Validator>) -> Result<()> {
|
|
514
|
+
let name = validator.name().to_string();
|
|
515
|
+
let priority = validator.priority();
|
|
516
|
+
|
|
517
|
+
validate_plugin_name(&name)?;
|
|
518
|
+
|
|
519
|
+
validator.initialize()?;
|
|
520
|
+
|
|
521
|
+
self.validators.entry(priority).or_default().insert(name, validator);
|
|
522
|
+
|
|
523
|
+
Ok(())
|
|
524
|
+
}
|
|
525
|
+
|
|
526
|
+
/// Get all validators in priority order.
|
|
527
|
+
///
|
|
528
|
+
/// # Returns
|
|
529
|
+
///
|
|
530
|
+
/// Vector of validators in priority order (highest first).
|
|
531
|
+
pub fn get_all(&self) -> Vec<Arc<dyn Validator>> {
|
|
532
|
+
let mut result = Vec::new();
|
|
533
|
+
|
|
534
|
+
for (_priority, validators) in self.validators.iter().rev() {
|
|
535
|
+
for validator in validators.values() {
|
|
536
|
+
result.push(Arc::clone(validator));
|
|
537
|
+
}
|
|
538
|
+
}
|
|
539
|
+
|
|
540
|
+
result
|
|
541
|
+
}
|
|
542
|
+
|
|
543
|
+
/// List all registered validator names.
|
|
544
|
+
pub fn list(&self) -> Vec<String> {
|
|
545
|
+
let mut names = std::collections::HashSet::new();
|
|
546
|
+
for validators in self.validators.values() {
|
|
547
|
+
names.extend(validators.keys().cloned());
|
|
548
|
+
}
|
|
549
|
+
names.into_iter().collect()
|
|
550
|
+
}
|
|
551
|
+
|
|
552
|
+
/// Remove a validator from the registry.
|
|
553
|
+
pub fn remove(&mut self, name: &str) -> Result<()> {
|
|
554
|
+
let mut validator_to_shutdown: Option<Arc<dyn Validator>> = None;
|
|
555
|
+
|
|
556
|
+
for validators in self.validators.values_mut() {
|
|
557
|
+
if let Some(validator) = validators.shift_remove(name)
|
|
558
|
+
&& validator_to_shutdown.is_none()
|
|
559
|
+
{
|
|
560
|
+
validator_to_shutdown = Some(validator);
|
|
561
|
+
}
|
|
562
|
+
}
|
|
563
|
+
|
|
564
|
+
if let Some(validator) = validator_to_shutdown {
|
|
565
|
+
validator.shutdown()?;
|
|
566
|
+
}
|
|
567
|
+
|
|
568
|
+
self.validators.retain(|_, validators| !validators.is_empty());
|
|
569
|
+
|
|
570
|
+
Ok(())
|
|
571
|
+
}
|
|
572
|
+
|
|
573
|
+
/// Shutdown all validators and clear the registry.
|
|
574
|
+
pub fn shutdown_all(&mut self) -> Result<()> {
|
|
575
|
+
let names = self.list();
|
|
576
|
+
for name in names {
|
|
577
|
+
self.remove(&name)?;
|
|
578
|
+
}
|
|
579
|
+
Ok(())
|
|
580
|
+
}
|
|
581
|
+
}
|
|
582
|
+
|
|
583
|
+
impl Default for ValidatorRegistry {
|
|
584
|
+
fn default() -> Self {
|
|
585
|
+
Self::new()
|
|
586
|
+
}
|
|
587
|
+
}
|
|
588
|
+
|
|
589
|
+
/// Global OCR backend registry singleton.
|
|
590
|
+
pub static OCR_BACKEND_REGISTRY: Lazy<Arc<RwLock<OcrBackendRegistry>>> =
|
|
591
|
+
Lazy::new(|| Arc::new(RwLock::new(OcrBackendRegistry::new())));
|
|
592
|
+
|
|
593
|
+
/// Global document extractor registry singleton.
|
|
594
|
+
pub static DOCUMENT_EXTRACTOR_REGISTRY: Lazy<Arc<RwLock<DocumentExtractorRegistry>>> =
|
|
595
|
+
Lazy::new(|| Arc::new(RwLock::new(DocumentExtractorRegistry::new())));
|
|
596
|
+
|
|
597
|
+
/// Global post-processor registry singleton.
|
|
598
|
+
pub static POST_PROCESSOR_REGISTRY: Lazy<Arc<RwLock<PostProcessorRegistry>>> =
|
|
599
|
+
Lazy::new(|| Arc::new(RwLock::new(PostProcessorRegistry::new())));
|
|
600
|
+
|
|
601
|
+
/// Global validator registry singleton.
|
|
602
|
+
pub static VALIDATOR_REGISTRY: Lazy<Arc<RwLock<ValidatorRegistry>>> =
|
|
603
|
+
Lazy::new(|| Arc::new(RwLock::new(ValidatorRegistry::new())));
|
|
604
|
+
|
|
605
|
+
/// Get the global OCR backend registry.
|
|
606
|
+
pub fn get_ocr_backend_registry() -> Arc<RwLock<OcrBackendRegistry>> {
|
|
607
|
+
OCR_BACKEND_REGISTRY.clone()
|
|
608
|
+
}
|
|
609
|
+
|
|
610
|
+
/// Get the global document extractor registry.
|
|
611
|
+
pub fn get_document_extractor_registry() -> Arc<RwLock<DocumentExtractorRegistry>> {
|
|
612
|
+
DOCUMENT_EXTRACTOR_REGISTRY.clone()
|
|
613
|
+
}
|
|
614
|
+
|
|
615
|
+
/// Get the global post-processor registry.
|
|
616
|
+
pub fn get_post_processor_registry() -> Arc<RwLock<PostProcessorRegistry>> {
|
|
617
|
+
POST_PROCESSOR_REGISTRY.clone()
|
|
618
|
+
}
|
|
619
|
+
|
|
620
|
+
/// Get the global validator registry.
|
|
621
|
+
pub fn get_validator_registry() -> Arc<RwLock<ValidatorRegistry>> {
|
|
622
|
+
VALIDATOR_REGISTRY.clone()
|
|
623
|
+
}
|
|
624
|
+
|
|
625
|
+
#[cfg(test)]
|
|
626
|
+
mod tests {
|
|
627
|
+
use super::*;
|
|
628
|
+
use crate::core::config::{ExtractionConfig, OcrConfig};
|
|
629
|
+
use crate::plugins::{Plugin, PostProcessor, ProcessingStage, Validator};
|
|
630
|
+
use crate::types::ExtractionResult;
|
|
631
|
+
use async_trait::async_trait;
|
|
632
|
+
|
|
633
|
+
struct MockOcrBackend {
|
|
634
|
+
name: String,
|
|
635
|
+
languages: Vec<String>,
|
|
636
|
+
}
|
|
637
|
+
|
|
638
|
+
impl Plugin for MockOcrBackend {
|
|
639
|
+
fn name(&self) -> &str {
|
|
640
|
+
&self.name
|
|
641
|
+
}
|
|
642
|
+
fn version(&self) -> String {
|
|
643
|
+
"1.0.0".to_string()
|
|
644
|
+
}
|
|
645
|
+
fn initialize(&self) -> Result<()> {
|
|
646
|
+
Ok(())
|
|
647
|
+
}
|
|
648
|
+
fn shutdown(&self) -> Result<()> {
|
|
649
|
+
Ok(())
|
|
650
|
+
}
|
|
651
|
+
}
|
|
652
|
+
|
|
653
|
+
#[async_trait]
|
|
654
|
+
impl OcrBackend for MockOcrBackend {
|
|
655
|
+
async fn process_image(&self, _: &[u8], _: &OcrConfig) -> Result<ExtractionResult> {
|
|
656
|
+
Ok(ExtractionResult {
|
|
657
|
+
content: "test".to_string(),
|
|
658
|
+
mime_type: "text/plain".to_string(),
|
|
659
|
+
metadata: crate::types::Metadata::default(),
|
|
660
|
+
tables: vec![],
|
|
661
|
+
detected_languages: None,
|
|
662
|
+
chunks: None,
|
|
663
|
+
images: None,
|
|
664
|
+
pages: None,
|
|
665
|
+
})
|
|
666
|
+
}
|
|
667
|
+
|
|
668
|
+
fn supports_language(&self, lang: &str) -> bool {
|
|
669
|
+
self.languages.iter().any(|l| l == lang)
|
|
670
|
+
}
|
|
671
|
+
|
|
672
|
+
fn backend_type(&self) -> crate::plugins::ocr::OcrBackendType {
|
|
673
|
+
crate::plugins::ocr::OcrBackendType::Custom
|
|
674
|
+
}
|
|
675
|
+
}
|
|
676
|
+
|
|
677
|
+
struct MockExtractor {
|
|
678
|
+
name: String,
|
|
679
|
+
mime_types: &'static [&'static str],
|
|
680
|
+
priority: i32,
|
|
681
|
+
}
|
|
682
|
+
|
|
683
|
+
impl Plugin for MockExtractor {
|
|
684
|
+
fn name(&self) -> &str {
|
|
685
|
+
&self.name
|
|
686
|
+
}
|
|
687
|
+
fn version(&self) -> String {
|
|
688
|
+
"1.0.0".to_string()
|
|
689
|
+
}
|
|
690
|
+
fn initialize(&self) -> Result<()> {
|
|
691
|
+
Ok(())
|
|
692
|
+
}
|
|
693
|
+
fn shutdown(&self) -> Result<()> {
|
|
694
|
+
Ok(())
|
|
695
|
+
}
|
|
696
|
+
}
|
|
697
|
+
|
|
698
|
+
#[async_trait]
|
|
699
|
+
impl DocumentExtractor for MockExtractor {
|
|
700
|
+
async fn extract_bytes(&self, _: &[u8], _: &str, _: &ExtractionConfig) -> Result<ExtractionResult> {
|
|
701
|
+
Ok(ExtractionResult {
|
|
702
|
+
content: "test".to_string(),
|
|
703
|
+
mime_type: "text/plain".to_string(),
|
|
704
|
+
metadata: crate::types::Metadata::default(),
|
|
705
|
+
tables: vec![],
|
|
706
|
+
detected_languages: None,
|
|
707
|
+
chunks: None,
|
|
708
|
+
images: None,
|
|
709
|
+
pages: None,
|
|
710
|
+
})
|
|
711
|
+
}
|
|
712
|
+
|
|
713
|
+
fn supported_mime_types(&self) -> &[&str] {
|
|
714
|
+
self.mime_types
|
|
715
|
+
}
|
|
716
|
+
|
|
717
|
+
fn priority(&self) -> i32 {
|
|
718
|
+
self.priority
|
|
719
|
+
}
|
|
720
|
+
}
|
|
721
|
+
|
|
722
|
+
struct MockPostProcessor {
|
|
723
|
+
name: String,
|
|
724
|
+
stage: ProcessingStage,
|
|
725
|
+
}
|
|
726
|
+
|
|
727
|
+
impl Plugin for MockPostProcessor {
|
|
728
|
+
fn name(&self) -> &str {
|
|
729
|
+
&self.name
|
|
730
|
+
}
|
|
731
|
+
fn version(&self) -> String {
|
|
732
|
+
"1.0.0".to_string()
|
|
733
|
+
}
|
|
734
|
+
fn initialize(&self) -> Result<()> {
|
|
735
|
+
Ok(())
|
|
736
|
+
}
|
|
737
|
+
fn shutdown(&self) -> Result<()> {
|
|
738
|
+
Ok(())
|
|
739
|
+
}
|
|
740
|
+
}
|
|
741
|
+
|
|
742
|
+
#[async_trait]
|
|
743
|
+
impl PostProcessor for MockPostProcessor {
|
|
744
|
+
async fn process(&self, _result: &mut ExtractionResult, _: &ExtractionConfig) -> Result<()> {
|
|
745
|
+
Ok(())
|
|
746
|
+
}
|
|
747
|
+
|
|
748
|
+
fn processing_stage(&self) -> ProcessingStage {
|
|
749
|
+
self.stage
|
|
750
|
+
}
|
|
751
|
+
}
|
|
752
|
+
|
|
753
|
+
struct MockValidator {
|
|
754
|
+
name: String,
|
|
755
|
+
priority: i32,
|
|
756
|
+
}
|
|
757
|
+
|
|
758
|
+
impl Plugin for MockValidator {
|
|
759
|
+
fn name(&self) -> &str {
|
|
760
|
+
&self.name
|
|
761
|
+
}
|
|
762
|
+
fn version(&self) -> String {
|
|
763
|
+
"1.0.0".to_string()
|
|
764
|
+
}
|
|
765
|
+
fn initialize(&self) -> Result<()> {
|
|
766
|
+
Ok(())
|
|
767
|
+
}
|
|
768
|
+
fn shutdown(&self) -> Result<()> {
|
|
769
|
+
Ok(())
|
|
770
|
+
}
|
|
771
|
+
}
|
|
772
|
+
|
|
773
|
+
#[async_trait]
|
|
774
|
+
impl Validator for MockValidator {
|
|
775
|
+
async fn validate(&self, _: &ExtractionResult, _: &ExtractionConfig) -> Result<()> {
|
|
776
|
+
Ok(())
|
|
777
|
+
}
|
|
778
|
+
|
|
779
|
+
fn priority(&self) -> i32 {
|
|
780
|
+
self.priority
|
|
781
|
+
}
|
|
782
|
+
}
|
|
783
|
+
|
|
784
|
+
#[test]
|
|
785
|
+
fn test_ocr_backend_registry() {
|
|
786
|
+
let mut registry = OcrBackendRegistry::new_empty();
|
|
787
|
+
|
|
788
|
+
let backend = Arc::new(MockOcrBackend {
|
|
789
|
+
name: "test-ocr".to_string(),
|
|
790
|
+
languages: vec!["eng".to_string(), "deu".to_string()],
|
|
791
|
+
});
|
|
792
|
+
|
|
793
|
+
registry.register(backend).unwrap();
|
|
794
|
+
|
|
795
|
+
let retrieved = registry.get("test-ocr").unwrap();
|
|
796
|
+
assert_eq!(retrieved.name(), "test-ocr");
|
|
797
|
+
|
|
798
|
+
let eng_backend = registry.get_for_language("eng").unwrap();
|
|
799
|
+
assert_eq!(eng_backend.name(), "test-ocr");
|
|
800
|
+
|
|
801
|
+
let names = registry.list();
|
|
802
|
+
assert_eq!(names.len(), 1);
|
|
803
|
+
assert!(names.contains(&"test-ocr".to_string()));
|
|
804
|
+
}
|
|
805
|
+
|
|
806
|
+
#[test]
|
|
807
|
+
fn test_post_processor_registry() {
|
|
808
|
+
let mut registry = PostProcessorRegistry::new();
|
|
809
|
+
|
|
810
|
+
let early = Arc::new(MockPostProcessor {
|
|
811
|
+
name: "early-processor".to_string(),
|
|
812
|
+
stage: ProcessingStage::Early,
|
|
813
|
+
});
|
|
814
|
+
|
|
815
|
+
let middle = Arc::new(MockPostProcessor {
|
|
816
|
+
name: "middle-processor".to_string(),
|
|
817
|
+
stage: ProcessingStage::Middle,
|
|
818
|
+
});
|
|
819
|
+
|
|
820
|
+
registry.register(early, 100).unwrap();
|
|
821
|
+
registry.register(middle, 50).unwrap();
|
|
822
|
+
|
|
823
|
+
let early_processors = registry.get_for_stage(ProcessingStage::Early);
|
|
824
|
+
assert_eq!(early_processors.len(), 1);
|
|
825
|
+
assert_eq!(early_processors[0].name(), "early-processor");
|
|
826
|
+
|
|
827
|
+
let middle_processors = registry.get_for_stage(ProcessingStage::Middle);
|
|
828
|
+
assert_eq!(middle_processors.len(), 1);
|
|
829
|
+
|
|
830
|
+
let names = registry.list();
|
|
831
|
+
assert_eq!(names.len(), 2);
|
|
832
|
+
}
|
|
833
|
+
|
|
834
|
+
#[test]
|
|
835
|
+
fn test_validator_registry() {
|
|
836
|
+
let mut registry = ValidatorRegistry::new();
|
|
837
|
+
|
|
838
|
+
let high_priority = Arc::new(MockValidator {
|
|
839
|
+
name: "high-priority".to_string(),
|
|
840
|
+
priority: 100,
|
|
841
|
+
});
|
|
842
|
+
|
|
843
|
+
let low_priority = Arc::new(MockValidator {
|
|
844
|
+
name: "low-priority".to_string(),
|
|
845
|
+
priority: 10,
|
|
846
|
+
});
|
|
847
|
+
|
|
848
|
+
registry.register(high_priority).unwrap();
|
|
849
|
+
registry.register(low_priority).unwrap();
|
|
850
|
+
|
|
851
|
+
let validators = registry.get_all();
|
|
852
|
+
assert_eq!(validators.len(), 2);
|
|
853
|
+
assert_eq!(validators[0].name(), "high-priority");
|
|
854
|
+
assert_eq!(validators[1].name(), "low-priority");
|
|
855
|
+
}
|
|
856
|
+
|
|
857
|
+
#[test]
|
|
858
|
+
fn test_document_extractor_registry_exact_match() {
|
|
859
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
860
|
+
|
|
861
|
+
let extractor = Arc::new(MockExtractor {
|
|
862
|
+
name: "pdf-extractor".to_string(),
|
|
863
|
+
mime_types: &["application/pdf"],
|
|
864
|
+
priority: 100,
|
|
865
|
+
});
|
|
866
|
+
|
|
867
|
+
registry.register(extractor).unwrap();
|
|
868
|
+
|
|
869
|
+
let retrieved = registry.get("application/pdf").unwrap();
|
|
870
|
+
assert_eq!(retrieved.name(), "pdf-extractor");
|
|
871
|
+
|
|
872
|
+
let names = registry.list();
|
|
873
|
+
assert_eq!(names.len(), 1);
|
|
874
|
+
assert!(names.contains(&"pdf-extractor".to_string()));
|
|
875
|
+
}
|
|
876
|
+
|
|
877
|
+
#[test]
|
|
878
|
+
fn test_document_extractor_registry_prefix_match() {
|
|
879
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
880
|
+
|
|
881
|
+
let image_extractor = Arc::new(MockExtractor {
|
|
882
|
+
name: "image-extractor".to_string(),
|
|
883
|
+
mime_types: &["image/*"],
|
|
884
|
+
priority: 50,
|
|
885
|
+
});
|
|
886
|
+
|
|
887
|
+
registry.register(image_extractor).unwrap();
|
|
888
|
+
|
|
889
|
+
let retrieved = registry.get("image/png").unwrap();
|
|
890
|
+
assert_eq!(retrieved.name(), "image-extractor");
|
|
891
|
+
|
|
892
|
+
let retrieved_jpg = registry.get("image/jpeg").unwrap();
|
|
893
|
+
assert_eq!(retrieved_jpg.name(), "image-extractor");
|
|
894
|
+
}
|
|
895
|
+
|
|
896
|
+
#[test]
|
|
897
|
+
fn test_document_extractor_registry_priority() {
|
|
898
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
899
|
+
|
|
900
|
+
let low_priority = Arc::new(MockExtractor {
|
|
901
|
+
name: "low-priority-pdf".to_string(),
|
|
902
|
+
mime_types: &["application/pdf"],
|
|
903
|
+
priority: 10,
|
|
904
|
+
});
|
|
905
|
+
|
|
906
|
+
let high_priority = Arc::new(MockExtractor {
|
|
907
|
+
name: "high-priority-pdf".to_string(),
|
|
908
|
+
mime_types: &["application/pdf"],
|
|
909
|
+
priority: 100,
|
|
910
|
+
});
|
|
911
|
+
|
|
912
|
+
registry.register(low_priority).unwrap();
|
|
913
|
+
registry.register(high_priority).unwrap();
|
|
914
|
+
|
|
915
|
+
let retrieved = registry.get("application/pdf").unwrap();
|
|
916
|
+
assert_eq!(retrieved.name(), "high-priority-pdf");
|
|
917
|
+
}
|
|
918
|
+
|
|
919
|
+
#[test]
|
|
920
|
+
fn test_document_extractor_registry_not_found() {
|
|
921
|
+
let registry = DocumentExtractorRegistry::new();
|
|
922
|
+
|
|
923
|
+
let result = registry.get("application/unknown");
|
|
924
|
+
assert!(matches!(result, Err(KreuzbergError::UnsupportedFormat(_))));
|
|
925
|
+
}
|
|
926
|
+
|
|
927
|
+
#[test]
|
|
928
|
+
fn test_document_extractor_registry_remove() {
|
|
929
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
930
|
+
|
|
931
|
+
let extractor = Arc::new(MockExtractor {
|
|
932
|
+
name: "test-extractor".to_string(),
|
|
933
|
+
mime_types: &["text/plain"],
|
|
934
|
+
priority: 50,
|
|
935
|
+
});
|
|
936
|
+
|
|
937
|
+
registry.register(extractor).unwrap();
|
|
938
|
+
assert!(registry.get("text/plain").is_ok());
|
|
939
|
+
|
|
940
|
+
registry.remove("test-extractor").unwrap();
|
|
941
|
+
assert!(registry.get("text/plain").is_err());
|
|
942
|
+
}
|
|
943
|
+
|
|
944
|
+
#[test]
|
|
945
|
+
fn test_document_extractor_registry_shutdown_all() {
|
|
946
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
947
|
+
|
|
948
|
+
let extractor1 = Arc::new(MockExtractor {
|
|
949
|
+
name: "extractor1".to_string(),
|
|
950
|
+
mime_types: &["text/plain"],
|
|
951
|
+
priority: 50,
|
|
952
|
+
});
|
|
953
|
+
|
|
954
|
+
let extractor2 = Arc::new(MockExtractor {
|
|
955
|
+
name: "extractor2".to_string(),
|
|
956
|
+
mime_types: &["application/pdf"],
|
|
957
|
+
priority: 50,
|
|
958
|
+
});
|
|
959
|
+
|
|
960
|
+
registry.register(extractor1).unwrap();
|
|
961
|
+
registry.register(extractor2).unwrap();
|
|
962
|
+
|
|
963
|
+
assert_eq!(registry.list().len(), 2);
|
|
964
|
+
|
|
965
|
+
registry.shutdown_all().unwrap();
|
|
966
|
+
assert_eq!(registry.list().len(), 0);
|
|
967
|
+
}
|
|
968
|
+
|
|
969
|
+
#[test]
|
|
970
|
+
fn test_ocr_backend_registry_not_found() {
|
|
971
|
+
let registry = OcrBackendRegistry::new();
|
|
972
|
+
|
|
973
|
+
let result = registry.get("nonexistent");
|
|
974
|
+
assert!(matches!(result, Err(KreuzbergError::Plugin { .. })));
|
|
975
|
+
}
|
|
976
|
+
|
|
977
|
+
#[test]
|
|
978
|
+
fn test_ocr_backend_registry_language_not_found() {
|
|
979
|
+
let registry = OcrBackendRegistry::new();
|
|
980
|
+
|
|
981
|
+
let result = registry.get_for_language("xyz");
|
|
982
|
+
assert!(matches!(result, Err(KreuzbergError::Plugin { .. })));
|
|
983
|
+
}
|
|
984
|
+
|
|
985
|
+
#[test]
|
|
986
|
+
fn test_ocr_backend_registry_remove() {
|
|
987
|
+
let mut registry = OcrBackendRegistry::new();
|
|
988
|
+
|
|
989
|
+
let backend = Arc::new(MockOcrBackend {
|
|
990
|
+
name: "test-ocr".to_string(),
|
|
991
|
+
languages: vec!["eng".to_string()],
|
|
992
|
+
});
|
|
993
|
+
|
|
994
|
+
registry.register(backend).unwrap();
|
|
995
|
+
assert!(registry.get("test-ocr").is_ok());
|
|
996
|
+
|
|
997
|
+
registry.remove("test-ocr").unwrap();
|
|
998
|
+
assert!(registry.get("test-ocr").is_err());
|
|
999
|
+
}
|
|
1000
|
+
|
|
1001
|
+
#[test]
|
|
1002
|
+
fn test_post_processor_registry_remove() {
|
|
1003
|
+
let mut registry = PostProcessorRegistry::new();
|
|
1004
|
+
|
|
1005
|
+
let processor = Arc::new(MockPostProcessor {
|
|
1006
|
+
name: "test-processor".to_string(),
|
|
1007
|
+
stage: ProcessingStage::Early,
|
|
1008
|
+
});
|
|
1009
|
+
|
|
1010
|
+
registry.register(processor, 50).unwrap();
|
|
1011
|
+
assert_eq!(registry.get_for_stage(ProcessingStage::Early).len(), 1);
|
|
1012
|
+
|
|
1013
|
+
registry.remove("test-processor").unwrap();
|
|
1014
|
+
assert_eq!(registry.get_for_stage(ProcessingStage::Early).len(), 0);
|
|
1015
|
+
}
|
|
1016
|
+
|
|
1017
|
+
#[test]
|
|
1018
|
+
fn test_validator_registry_remove() {
|
|
1019
|
+
let mut registry = ValidatorRegistry::new();
|
|
1020
|
+
|
|
1021
|
+
let validator = Arc::new(MockValidator {
|
|
1022
|
+
name: "test-validator".to_string(),
|
|
1023
|
+
priority: 50,
|
|
1024
|
+
});
|
|
1025
|
+
|
|
1026
|
+
registry.register(validator).unwrap();
|
|
1027
|
+
assert_eq!(registry.get_all().len(), 1);
|
|
1028
|
+
|
|
1029
|
+
registry.remove("test-validator").unwrap();
|
|
1030
|
+
assert_eq!(registry.get_all().len(), 0);
|
|
1031
|
+
}
|
|
1032
|
+
|
|
1033
|
+
#[test]
|
|
1034
|
+
fn test_global_registry_access() {
|
|
1035
|
+
let ocr_registry = get_ocr_backend_registry();
|
|
1036
|
+
let _ = ocr_registry
|
|
1037
|
+
.read()
|
|
1038
|
+
.expect("Failed to acquire read lock on OCR registry in test")
|
|
1039
|
+
.list();
|
|
1040
|
+
|
|
1041
|
+
let extractor_registry = get_document_extractor_registry();
|
|
1042
|
+
let _ = extractor_registry
|
|
1043
|
+
.read()
|
|
1044
|
+
.expect("Failed to acquire read lock on extractor registry in test")
|
|
1045
|
+
.list();
|
|
1046
|
+
|
|
1047
|
+
let processor_registry = get_post_processor_registry();
|
|
1048
|
+
let _ = processor_registry
|
|
1049
|
+
.read()
|
|
1050
|
+
.expect("Failed to acquire read lock on processor registry in test")
|
|
1051
|
+
.list();
|
|
1052
|
+
|
|
1053
|
+
let validator_registry = get_validator_registry();
|
|
1054
|
+
let _ = validator_registry
|
|
1055
|
+
.read()
|
|
1056
|
+
.expect("Failed to acquire read lock on validator registry in test")
|
|
1057
|
+
.list();
|
|
1058
|
+
}
|
|
1059
|
+
|
|
1060
|
+
#[test]
|
|
1061
|
+
fn test_ocr_backend_registry_shutdown_all() {
|
|
1062
|
+
let mut registry = OcrBackendRegistry::new();
|
|
1063
|
+
let baseline = registry.list().len();
|
|
1064
|
+
|
|
1065
|
+
let backend1 = Arc::new(MockOcrBackend {
|
|
1066
|
+
name: "backend1".to_string(),
|
|
1067
|
+
languages: vec!["eng".to_string()],
|
|
1068
|
+
});
|
|
1069
|
+
|
|
1070
|
+
let backend2 = Arc::new(MockOcrBackend {
|
|
1071
|
+
name: "backend2".to_string(),
|
|
1072
|
+
languages: vec!["deu".to_string()],
|
|
1073
|
+
});
|
|
1074
|
+
|
|
1075
|
+
registry.register(backend1).unwrap();
|
|
1076
|
+
registry.register(backend2).unwrap();
|
|
1077
|
+
|
|
1078
|
+
assert_eq!(registry.list().len(), baseline + 2);
|
|
1079
|
+
|
|
1080
|
+
registry.shutdown_all().unwrap();
|
|
1081
|
+
assert_eq!(registry.list().len(), 0);
|
|
1082
|
+
}
|
|
1083
|
+
|
|
1084
|
+
#[test]
|
|
1085
|
+
fn test_post_processor_registry_shutdown_all() {
|
|
1086
|
+
let mut registry = PostProcessorRegistry::new();
|
|
1087
|
+
|
|
1088
|
+
let early = Arc::new(MockPostProcessor {
|
|
1089
|
+
name: "early".to_string(),
|
|
1090
|
+
stage: ProcessingStage::Early,
|
|
1091
|
+
});
|
|
1092
|
+
|
|
1093
|
+
let late = Arc::new(MockPostProcessor {
|
|
1094
|
+
name: "late".to_string(),
|
|
1095
|
+
stage: ProcessingStage::Late,
|
|
1096
|
+
});
|
|
1097
|
+
|
|
1098
|
+
registry.register(early, 100).unwrap();
|
|
1099
|
+
registry.register(late, 50).unwrap();
|
|
1100
|
+
|
|
1101
|
+
assert_eq!(registry.list().len(), 2);
|
|
1102
|
+
|
|
1103
|
+
registry.shutdown_all().unwrap();
|
|
1104
|
+
assert_eq!(registry.list().len(), 0);
|
|
1105
|
+
}
|
|
1106
|
+
|
|
1107
|
+
#[test]
|
|
1108
|
+
fn test_validator_registry_shutdown_all() {
|
|
1109
|
+
let mut registry = ValidatorRegistry::new();
|
|
1110
|
+
|
|
1111
|
+
let validator1 = Arc::new(MockValidator {
|
|
1112
|
+
name: "validator1".to_string(),
|
|
1113
|
+
priority: 100,
|
|
1114
|
+
});
|
|
1115
|
+
|
|
1116
|
+
let validator2 = Arc::new(MockValidator {
|
|
1117
|
+
name: "validator2".to_string(),
|
|
1118
|
+
priority: 50,
|
|
1119
|
+
});
|
|
1120
|
+
|
|
1121
|
+
registry.register(validator1).unwrap();
|
|
1122
|
+
registry.register(validator2).unwrap();
|
|
1123
|
+
|
|
1124
|
+
assert_eq!(registry.get_all().len(), 2);
|
|
1125
|
+
|
|
1126
|
+
registry.shutdown_all().unwrap();
|
|
1127
|
+
assert_eq!(registry.get_all().len(), 0);
|
|
1128
|
+
}
|
|
1129
|
+
|
|
1130
|
+
#[test]
|
|
1131
|
+
fn test_document_extractor_registry_multiple_mime_types() {
|
|
1132
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
1133
|
+
|
|
1134
|
+
let multi_extractor = Arc::new(MockExtractor {
|
|
1135
|
+
name: "multi-extractor".to_string(),
|
|
1136
|
+
mime_types: &["text/plain", "text/markdown", "text/html"],
|
|
1137
|
+
priority: 50,
|
|
1138
|
+
});
|
|
1139
|
+
|
|
1140
|
+
registry.register(multi_extractor).unwrap();
|
|
1141
|
+
|
|
1142
|
+
assert_eq!(registry.get("text/plain").unwrap().name(), "multi-extractor");
|
|
1143
|
+
assert_eq!(registry.get("text/markdown").unwrap().name(), "multi-extractor");
|
|
1144
|
+
assert_eq!(registry.get("text/html").unwrap().name(), "multi-extractor");
|
|
1145
|
+
}
|
|
1146
|
+
|
|
1147
|
+
#[test]
|
|
1148
|
+
fn test_post_processor_registry_priority_order() {
|
|
1149
|
+
let mut registry = PostProcessorRegistry::new();
|
|
1150
|
+
|
|
1151
|
+
let low = Arc::new(MockPostProcessor {
|
|
1152
|
+
name: "low-priority".to_string(),
|
|
1153
|
+
stage: ProcessingStage::Early,
|
|
1154
|
+
});
|
|
1155
|
+
|
|
1156
|
+
let high = Arc::new(MockPostProcessor {
|
|
1157
|
+
name: "high-priority".to_string(),
|
|
1158
|
+
stage: ProcessingStage::Early,
|
|
1159
|
+
});
|
|
1160
|
+
|
|
1161
|
+
registry.register(low, 10).unwrap();
|
|
1162
|
+
registry.register(high, 100).unwrap();
|
|
1163
|
+
|
|
1164
|
+
let processors = registry.get_for_stage(ProcessingStage::Early);
|
|
1165
|
+
assert_eq!(processors.len(), 2);
|
|
1166
|
+
assert_eq!(processors[0].name(), "high-priority");
|
|
1167
|
+
assert_eq!(processors[1].name(), "low-priority");
|
|
1168
|
+
}
|
|
1169
|
+
|
|
1170
|
+
#[test]
|
|
1171
|
+
fn test_post_processor_registry_empty_stage() {
|
|
1172
|
+
let registry = PostProcessorRegistry::new();
|
|
1173
|
+
|
|
1174
|
+
let processors = registry.get_for_stage(ProcessingStage::Late);
|
|
1175
|
+
assert_eq!(processors.len(), 0);
|
|
1176
|
+
}
|
|
1177
|
+
|
|
1178
|
+
#[test]
|
|
1179
|
+
fn test_ocr_backend_registry_default() {
|
|
1180
|
+
let registry = OcrBackendRegistry::default();
|
|
1181
|
+
#[cfg(feature = "ocr")]
|
|
1182
|
+
assert!(
|
|
1183
|
+
!registry.list().is_empty(),
|
|
1184
|
+
"expected at least one default OCR backend when the 'ocr' feature is enabled"
|
|
1185
|
+
);
|
|
1186
|
+
#[cfg(not(feature = "ocr"))]
|
|
1187
|
+
assert_eq!(registry.list().len(), 0);
|
|
1188
|
+
}
|
|
1189
|
+
|
|
1190
|
+
#[test]
|
|
1191
|
+
fn test_document_extractor_registry_default() {
|
|
1192
|
+
let registry = DocumentExtractorRegistry::default();
|
|
1193
|
+
assert_eq!(registry.list().len(), 0);
|
|
1194
|
+
}
|
|
1195
|
+
|
|
1196
|
+
#[test]
|
|
1197
|
+
fn test_post_processor_registry_default() {
|
|
1198
|
+
let registry = PostProcessorRegistry::default();
|
|
1199
|
+
assert_eq!(registry.list().len(), 0);
|
|
1200
|
+
}
|
|
1201
|
+
|
|
1202
|
+
#[test]
|
|
1203
|
+
fn test_validator_registry_default() {
|
|
1204
|
+
let registry = ValidatorRegistry::default();
|
|
1205
|
+
assert_eq!(registry.get_all().len(), 0);
|
|
1206
|
+
}
|
|
1207
|
+
|
|
1208
|
+
#[test]
|
|
1209
|
+
fn test_document_extractor_registry_exact_over_prefix() {
|
|
1210
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
1211
|
+
|
|
1212
|
+
let prefix_extractor = Arc::new(MockExtractor {
|
|
1213
|
+
name: "prefix-extractor".to_string(),
|
|
1214
|
+
mime_types: &["image/*"],
|
|
1215
|
+
priority: 100,
|
|
1216
|
+
});
|
|
1217
|
+
|
|
1218
|
+
let exact_extractor = Arc::new(MockExtractor {
|
|
1219
|
+
name: "exact-extractor".to_string(),
|
|
1220
|
+
mime_types: &["image/png"],
|
|
1221
|
+
priority: 50,
|
|
1222
|
+
});
|
|
1223
|
+
|
|
1224
|
+
registry.register(prefix_extractor).unwrap();
|
|
1225
|
+
registry.register(exact_extractor).unwrap();
|
|
1226
|
+
|
|
1227
|
+
let retrieved = registry.get("image/png").unwrap();
|
|
1228
|
+
assert_eq!(retrieved.name(), "exact-extractor");
|
|
1229
|
+
|
|
1230
|
+
let retrieved_jpg = registry.get("image/jpeg").unwrap();
|
|
1231
|
+
assert_eq!(retrieved_jpg.name(), "prefix-extractor");
|
|
1232
|
+
}
|
|
1233
|
+
|
|
1234
|
+
#[test]
|
|
1235
|
+
fn test_ocr_backend_registry_invalid_name_empty() {
|
|
1236
|
+
let mut registry = OcrBackendRegistry::new();
|
|
1237
|
+
|
|
1238
|
+
let backend = Arc::new(MockOcrBackend {
|
|
1239
|
+
name: "".to_string(),
|
|
1240
|
+
languages: vec!["eng".to_string()],
|
|
1241
|
+
});
|
|
1242
|
+
|
|
1243
|
+
let result = registry.register(backend);
|
|
1244
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1245
|
+
}
|
|
1246
|
+
|
|
1247
|
+
#[test]
|
|
1248
|
+
fn test_ocr_backend_registry_invalid_name_whitespace() {
|
|
1249
|
+
let mut registry = OcrBackendRegistry::new();
|
|
1250
|
+
|
|
1251
|
+
let backend = Arc::new(MockOcrBackend {
|
|
1252
|
+
name: "my ocr backend".to_string(),
|
|
1253
|
+
languages: vec!["eng".to_string()],
|
|
1254
|
+
});
|
|
1255
|
+
|
|
1256
|
+
let result = registry.register(backend);
|
|
1257
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1258
|
+
}
|
|
1259
|
+
|
|
1260
|
+
#[test]
|
|
1261
|
+
fn test_document_extractor_registry_invalid_name_empty() {
|
|
1262
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
1263
|
+
|
|
1264
|
+
let extractor = Arc::new(MockExtractor {
|
|
1265
|
+
name: "".to_string(),
|
|
1266
|
+
mime_types: &["text/plain"],
|
|
1267
|
+
priority: 50,
|
|
1268
|
+
});
|
|
1269
|
+
|
|
1270
|
+
let result = registry.register(extractor);
|
|
1271
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1272
|
+
}
|
|
1273
|
+
|
|
1274
|
+
#[test]
|
|
1275
|
+
fn test_document_extractor_registry_invalid_name_whitespace() {
|
|
1276
|
+
let mut registry = DocumentExtractorRegistry::new();
|
|
1277
|
+
|
|
1278
|
+
let extractor = Arc::new(MockExtractor {
|
|
1279
|
+
name: "my extractor".to_string(),
|
|
1280
|
+
mime_types: &["text/plain"],
|
|
1281
|
+
priority: 50,
|
|
1282
|
+
});
|
|
1283
|
+
|
|
1284
|
+
let result = registry.register(extractor);
|
|
1285
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1286
|
+
}
|
|
1287
|
+
|
|
1288
|
+
#[test]
|
|
1289
|
+
fn test_post_processor_registry_invalid_name_empty() {
|
|
1290
|
+
let mut registry = PostProcessorRegistry::new();
|
|
1291
|
+
|
|
1292
|
+
let processor = Arc::new(MockPostProcessor {
|
|
1293
|
+
name: "".to_string(),
|
|
1294
|
+
stage: ProcessingStage::Early,
|
|
1295
|
+
});
|
|
1296
|
+
|
|
1297
|
+
let result = registry.register(processor, 50);
|
|
1298
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1299
|
+
}
|
|
1300
|
+
|
|
1301
|
+
#[test]
|
|
1302
|
+
fn test_post_processor_registry_invalid_name_whitespace() {
|
|
1303
|
+
let mut registry = PostProcessorRegistry::new();
|
|
1304
|
+
|
|
1305
|
+
let processor = Arc::new(MockPostProcessor {
|
|
1306
|
+
name: "my processor".to_string(),
|
|
1307
|
+
stage: ProcessingStage::Early,
|
|
1308
|
+
});
|
|
1309
|
+
|
|
1310
|
+
let result = registry.register(processor, 50);
|
|
1311
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1312
|
+
}
|
|
1313
|
+
|
|
1314
|
+
#[test]
|
|
1315
|
+
fn test_validator_registry_invalid_name_empty() {
|
|
1316
|
+
let mut registry = ValidatorRegistry::new();
|
|
1317
|
+
|
|
1318
|
+
let validator = Arc::new(MockValidator {
|
|
1319
|
+
name: "".to_string(),
|
|
1320
|
+
priority: 50,
|
|
1321
|
+
});
|
|
1322
|
+
|
|
1323
|
+
let result = registry.register(validator);
|
|
1324
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1325
|
+
}
|
|
1326
|
+
|
|
1327
|
+
#[test]
|
|
1328
|
+
fn test_validator_registry_invalid_name_whitespace() {
|
|
1329
|
+
let mut registry = ValidatorRegistry::new();
|
|
1330
|
+
|
|
1331
|
+
let validator = Arc::new(MockValidator {
|
|
1332
|
+
name: "my validator".to_string(),
|
|
1333
|
+
priority: 50,
|
|
1334
|
+
});
|
|
1335
|
+
|
|
1336
|
+
let result = registry.register(validator);
|
|
1337
|
+
assert!(matches!(result, Err(KreuzbergError::Validation { .. })));
|
|
1338
|
+
}
|
|
1339
|
+
}
|