kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitignore +14 -14
- data/.rspec +3 -3
- data/.rubocop.yaml +1 -1
- data/.rubocop.yml +538 -538
- data/Gemfile +8 -8
- data/Gemfile.lock +4 -104
- data/README.md +454 -432
- data/Rakefile +25 -25
- data/Steepfile +47 -47
- data/examples/async_patterns.rb +341 -341
- data/ext/kreuzberg_rb/extconf.rb +45 -45
- data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
- data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
- data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +15 -15
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
- data/ext/kreuzberg_rb/native/include/strings.h +20 -20
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
- data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3135
- data/extconf.rb +28 -28
- data/kreuzberg.gemspec +214 -182
- data/lib/kreuzberg/api_proxy.rb +142 -142
- data/lib/kreuzberg/cache_api.rb +81 -46
- data/lib/kreuzberg/cli.rb +55 -55
- data/lib/kreuzberg/cli_proxy.rb +127 -127
- data/lib/kreuzberg/config.rb +724 -724
- data/lib/kreuzberg/error_context.rb +80 -32
- data/lib/kreuzberg/errors.rb +118 -118
- data/lib/kreuzberg/extraction_api.rb +340 -85
- data/lib/kreuzberg/mcp_proxy.rb +186 -186
- data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
- data/lib/kreuzberg/post_processor_protocol.rb +86 -86
- data/lib/kreuzberg/result.rb +279 -279
- data/lib/kreuzberg/setup_lib_path.rb +80 -80
- data/lib/kreuzberg/validator_protocol.rb +89 -89
- data/lib/kreuzberg/version.rb +5 -5
- data/lib/kreuzberg.rb +109 -103
- data/lib/pdfium.dll +0 -0
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +546 -537
- data/spec/binding/cache_spec.rb +227 -227
- data/spec/binding/cli_proxy_spec.rb +85 -85
- data/spec/binding/cli_spec.rb +55 -55
- data/spec/binding/config_spec.rb +345 -345
- data/spec/binding/config_validation_spec.rb +283 -283
- data/spec/binding/error_handling_spec.rb +213 -213
- data/spec/binding/errors_spec.rb +66 -66
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
- data/spec/binding/plugins/postprocessor_spec.rb +269 -269
- data/spec/binding/plugins/validator_spec.rb +274 -274
- data/spec/fixtures/config.toml +39 -39
- data/spec/fixtures/config.yaml +41 -41
- data/spec/fixtures/invalid_config.toml +4 -4
- data/spec/smoke/package_spec.rb +178 -178
- data/spec/spec_helper.rb +42 -42
- data/vendor/Cargo.toml +45 -0
- data/vendor/kreuzberg/Cargo.toml +61 -38
- data/vendor/kreuzberg/README.md +230 -221
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
- data/vendor/kreuzberg/build.rs +843 -891
- data/vendor/kreuzberg/src/api/error.rs +81 -81
- data/vendor/kreuzberg/src/api/handlers.rs +199 -199
- data/vendor/kreuzberg/src/api/mod.rs +79 -79
- data/vendor/kreuzberg/src/api/server.rs +353 -353
- data/vendor/kreuzberg/src/api/types.rs +170 -170
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
- data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
- data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
- data/vendor/kreuzberg/src/core/config.rs +1080 -1080
- data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
- data/vendor/kreuzberg/src/core/io.rs +329 -329
- data/vendor/kreuzberg/src/core/mime.rs +605 -605
- data/vendor/kreuzberg/src/core/mod.rs +47 -47
- data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
- data/vendor/kreuzberg/src/embeddings.rs +500 -432
- data/vendor/kreuzberg/src/error.rs +431 -431
- data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
- data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
- data/vendor/kreuzberg/src/extraction/email.rs +854 -854
- data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
- data/vendor/kreuzberg/src/extraction/html.rs +601 -569
- data/vendor/kreuzberg/src/extraction/image.rs +491 -491
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
- data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
- data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
- data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
- data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
- data/vendor/kreuzberg/src/extraction/table.rs +328 -328
- data/vendor/kreuzberg/src/extraction/text.rs +269 -269
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
- data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
- data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
- data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
- data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
- data/vendor/kreuzberg/src/extractors/email.rs +157 -157
- data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
- data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
- data/vendor/kreuzberg/src/extractors/html.rs +407 -407
- data/vendor/kreuzberg/src/extractors/image.rs +219 -219
- data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
- data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
- data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
- data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
- data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
- data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
- data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
- data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
- data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
- data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
- data/vendor/kreuzberg/src/extractors/security.rs +484 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
- data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
- data/vendor/kreuzberg/src/extractors/text.rs +265 -265
- data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
- data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
- data/vendor/kreuzberg/src/image/dpi.rs +164 -164
- data/vendor/kreuzberg/src/image/mod.rs +6 -6
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
- data/vendor/kreuzberg/src/image/resize.rs +89 -89
- data/vendor/kreuzberg/src/keywords/config.rs +154 -154
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
- data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
- data/vendor/kreuzberg/src/keywords/types.rs +68 -68
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
- data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
- data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
- data/vendor/kreuzberg/src/lib.rs +113 -113
- data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
- data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
- data/vendor/kreuzberg/src/ocr/error.rs +37 -37
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
- data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
- data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
- data/vendor/kreuzberg/src/ocr/types.rs +393 -393
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
- data/vendor/kreuzberg/src/panic_context.rs +154 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +44 -0
- data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
- data/vendor/kreuzberg/src/pdf/error.rs +130 -130
- data/vendor/kreuzberg/src/pdf/images.rs +139 -139
- data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
- data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
- data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
- data/vendor/kreuzberg/src/pdf/table.rs +420 -417
- data/vendor/kreuzberg/src/pdf/text.rs +240 -240
- data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
- data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
- data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
- data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
- data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
- data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
- data/vendor/kreuzberg/src/text/mod.rs +25 -25
- data/vendor/kreuzberg/src/text/quality.rs +697 -697
- data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
- data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
- data/vendor/kreuzberg/src/types.rs +1055 -1055
- data/vendor/kreuzberg/src/utils/mod.rs +17 -17
- data/vendor/kreuzberg/src/utils/quality.rs +959 -959
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
- data/vendor/kreuzberg/tests/api_tests.rs +966 -966
- data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
- data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
- data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
- data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
- data/vendor/kreuzberg/tests/config_features.rs +612 -612
- data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
- data/vendor/kreuzberg/tests/core_integration.rs +510 -510
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
- data/vendor/kreuzberg/tests/email_integration.rs +327 -327
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
- data/vendor/kreuzberg/tests/error_handling.rs +402 -402
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
- data/vendor/kreuzberg/tests/format_integration.rs +164 -161
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
- data/vendor/kreuzberg/tests/image_integration.rs +255 -255
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
- data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
- data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
- data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
- data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
- data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
- data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
- data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
- data/vendor/kreuzberg/tests/security_validation.rs +416 -416
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
- data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
- data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
- data/vendor/kreuzberg-ffi/README.md +851 -0
- data/vendor/kreuzberg-ffi/build.rs +176 -0
- data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -0
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
- data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
- data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +48 -0
- data/vendor/kreuzberg-tesseract/LICENSE +22 -0
- data/vendor/kreuzberg-tesseract/README.md +399 -0
- data/vendor/kreuzberg-tesseract/build.rs +1354 -0
- data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
- data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
- data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
- data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
- data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
- data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
- data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
- data/vendor/rb-sys/Cargo.lock +393 -393
- data/vendor/rb-sys/Cargo.toml +70 -70
- data/vendor/rb-sys/Cargo.toml.orig +57 -57
- data/vendor/rb-sys/LICENSE-APACHE +190 -190
- data/vendor/rb-sys/LICENSE-MIT +21 -21
- data/vendor/rb-sys/build/features.rs +111 -111
- data/vendor/rb-sys/build/main.rs +286 -286
- data/vendor/rb-sys/build/stable_api_config.rs +155 -155
- data/vendor/rb-sys/build/version.rs +50 -50
- data/vendor/rb-sys/readme.md +36 -36
- data/vendor/rb-sys/src/bindings.rs +21 -21
- data/vendor/rb-sys/src/hidden.rs +11 -11
- data/vendor/rb-sys/src/lib.rs +35 -35
- data/vendor/rb-sys/src/macros.rs +371 -371
- data/vendor/rb-sys/src/memory.rs +53 -53
- data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
- data/vendor/rb-sys/src/special_consts.rs +31 -31
- data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
- data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
- data/vendor/rb-sys/src/stable_api.rs +260 -260
- data/vendor/rb-sys/src/symbol.rs +31 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
- data/vendor/rb-sys/src/utils.rs +89 -89
- data/vendor/rb-sys/src/value_type.rs +7 -7
- metadata +44 -81
- data/vendor/rb-sys/bin/release.sh +0 -21
|
@@ -1,452 +1,452 @@
|
|
|
1
|
-
//! Native Tesseract OCR backend.
|
|
2
|
-
//!
|
|
3
|
-
//! This module provides the native Tesseract backend that implements the OcrBackend
|
|
4
|
-
//! trait, bridging the plugin system with the low-level OcrProcessor.
|
|
5
|
-
|
|
6
|
-
use crate::Result;
|
|
7
|
-
use crate::core::config::OcrConfig;
|
|
8
|
-
use crate::ocr::processor::OcrProcessor;
|
|
9
|
-
use crate::plugins::{OcrBackend, OcrBackendType, Plugin};
|
|
10
|
-
use crate::types::ExtractionResult;
|
|
11
|
-
use async_trait::async_trait;
|
|
12
|
-
use std::path::Path;
|
|
13
|
-
use std::sync::Arc;
|
|
14
|
-
|
|
15
|
-
use crate::ocr::types::TesseractConfig as InternalTesseractConfig;
|
|
16
|
-
|
|
17
|
-
/// Native Tesseract OCR backend.
|
|
18
|
-
///
|
|
19
|
-
/// This backend wraps the OcrProcessor and implements the OcrBackend trait,
|
|
20
|
-
/// allowing it to be used through the plugin system.
|
|
21
|
-
///
|
|
22
|
-
/// # Thread Safety
|
|
23
|
-
///
|
|
24
|
-
/// Uses Arc for shared ownership and is thread-safe (Send + Sync).
|
|
25
|
-
pub struct TesseractBackend {
|
|
26
|
-
processor: Arc<OcrProcessor>,
|
|
27
|
-
}
|
|
28
|
-
|
|
29
|
-
impl TesseractBackend {
|
|
30
|
-
/// Create a new Tesseract backend with default cache directory.
|
|
31
|
-
pub fn new() -> Result<Self> {
|
|
32
|
-
let processor = OcrProcessor::new(None).map_err(|e| crate::KreuzbergError::Ocr {
|
|
33
|
-
message: format!("Failed to create Tesseract processor: {}", e),
|
|
34
|
-
source: Some(Box::new(e)),
|
|
35
|
-
})?;
|
|
36
|
-
Ok(Self {
|
|
37
|
-
processor: Arc::new(processor),
|
|
38
|
-
})
|
|
39
|
-
}
|
|
40
|
-
|
|
41
|
-
/// Create a new Tesseract backend with custom cache directory.
|
|
42
|
-
pub fn with_cache_dir(cache_dir: std::path::PathBuf) -> Result<Self> {
|
|
43
|
-
let processor = OcrProcessor::new(Some(cache_dir)).map_err(|e| crate::KreuzbergError::Ocr {
|
|
44
|
-
message: format!("Failed to create Tesseract processor: {}", e),
|
|
45
|
-
source: Some(Box::new(e)),
|
|
46
|
-
})?;
|
|
47
|
-
Ok(Self {
|
|
48
|
-
processor: Arc::new(processor),
|
|
49
|
-
})
|
|
50
|
-
}
|
|
51
|
-
|
|
52
|
-
/// Convert public API TesseractConfig to internal TesseractConfig.
|
|
53
|
-
///
|
|
54
|
-
/// The public API types (crate::types) use i32 for compatibility with PyO3,
|
|
55
|
-
/// while internal types (crate::ocr::types) use u8/u32 for efficiency.
|
|
56
|
-
fn convert_config(public_config: &crate::types::TesseractConfig) -> InternalTesseractConfig {
|
|
57
|
-
InternalTesseractConfig {
|
|
58
|
-
language: public_config.language.clone(),
|
|
59
|
-
psm: public_config.psm as u8,
|
|
60
|
-
output_format: public_config.output_format.clone(),
|
|
61
|
-
oem: public_config.oem as u8,
|
|
62
|
-
min_confidence: public_config.min_confidence,
|
|
63
|
-
preprocessing: public_config.preprocessing.clone(),
|
|
64
|
-
enable_table_detection: public_config.enable_table_detection,
|
|
65
|
-
table_min_confidence: public_config.table_min_confidence,
|
|
66
|
-
table_column_threshold: public_config.table_column_threshold as u32,
|
|
67
|
-
table_row_threshold_ratio: public_config.table_row_threshold_ratio,
|
|
68
|
-
use_cache: public_config.use_cache,
|
|
69
|
-
classify_use_pre_adapted_templates: public_config.classify_use_pre_adapted_templates,
|
|
70
|
-
language_model_ngram_on: public_config.language_model_ngram_on,
|
|
71
|
-
tessedit_dont_blkrej_good_wds: public_config.tessedit_dont_blkrej_good_wds,
|
|
72
|
-
tessedit_dont_rowrej_good_wds: public_config.tessedit_dont_rowrej_good_wds,
|
|
73
|
-
tessedit_enable_dict_correction: public_config.tessedit_enable_dict_correction,
|
|
74
|
-
tessedit_char_whitelist: public_config.tessedit_char_whitelist.clone(),
|
|
75
|
-
tessedit_char_blacklist: public_config.tessedit_char_blacklist.clone(),
|
|
76
|
-
tessedit_use_primary_params_model: public_config.tessedit_use_primary_params_model,
|
|
77
|
-
textord_space_size_is_variable: public_config.textord_space_size_is_variable,
|
|
78
|
-
thresholding_method: public_config.thresholding_method,
|
|
79
|
-
}
|
|
80
|
-
}
|
|
81
|
-
|
|
82
|
-
/// Convert OcrConfig to internal TesseractConfig.
|
|
83
|
-
///
|
|
84
|
-
/// Uses tesseract_config from OcrConfig if provided, otherwise uses defaults
|
|
85
|
-
/// with the language from OcrConfig.
|
|
86
|
-
fn config_to_tesseract(&self, config: &OcrConfig) -> InternalTesseractConfig {
|
|
87
|
-
match &config.tesseract_config {
|
|
88
|
-
Some(tess_config) => Self::convert_config(tess_config),
|
|
89
|
-
None => InternalTesseractConfig {
|
|
90
|
-
language: config.language.clone(),
|
|
91
|
-
..Default::default()
|
|
92
|
-
},
|
|
93
|
-
}
|
|
94
|
-
}
|
|
95
|
-
}
|
|
96
|
-
|
|
97
|
-
impl Default for TesseractBackend {
|
|
98
|
-
fn default() -> Self {
|
|
99
|
-
Self::new().unwrap()
|
|
100
|
-
}
|
|
101
|
-
}
|
|
102
|
-
|
|
103
|
-
impl Plugin for TesseractBackend {
|
|
104
|
-
fn name(&self) -> &str {
|
|
105
|
-
"tesseract"
|
|
106
|
-
}
|
|
107
|
-
|
|
108
|
-
fn version(&self) -> String {
|
|
109
|
-
kreuzberg_tesseract::TesseractAPI::version()
|
|
110
|
-
}
|
|
111
|
-
|
|
112
|
-
fn initialize(&self) -> Result<()> {
|
|
113
|
-
Ok(())
|
|
114
|
-
}
|
|
115
|
-
|
|
116
|
-
fn shutdown(&self) -> Result<()> {
|
|
117
|
-
self.processor.clear_cache().map_err(|e| crate::KreuzbergError::Plugin {
|
|
118
|
-
message: format!("Failed to clear Tesseract cache: {}", e),
|
|
119
|
-
plugin_name: "tesseract".to_string(),
|
|
120
|
-
})
|
|
121
|
-
}
|
|
122
|
-
}
|
|
123
|
-
|
|
124
|
-
#[async_trait]
|
|
125
|
-
impl OcrBackend for TesseractBackend {
|
|
126
|
-
async fn process_image(&self, image_bytes: &[u8], config: &OcrConfig) -> Result<ExtractionResult> {
|
|
127
|
-
let tess_config = self.config_to_tesseract(config);
|
|
128
|
-
let tess_config_clone = tess_config.clone();
|
|
129
|
-
|
|
130
|
-
let processor = Arc::clone(&self.processor);
|
|
131
|
-
let image_bytes = image_bytes.to_vec();
|
|
132
|
-
|
|
133
|
-
let ocr_result = tokio::task::spawn_blocking(move || processor.process_image(&image_bytes, &tess_config_clone))
|
|
134
|
-
.await
|
|
135
|
-
.map_err(|e| crate::KreuzbergError::Plugin {
|
|
136
|
-
message: format!("Tesseract task panicked: {}", e),
|
|
137
|
-
plugin_name: "tesseract".to_string(),
|
|
138
|
-
})?
|
|
139
|
-
.map_err(|e| crate::KreuzbergError::Ocr {
|
|
140
|
-
message: format!("Tesseract OCR failed: {}", e),
|
|
141
|
-
source: Some(Box::new(e)),
|
|
142
|
-
})?;
|
|
143
|
-
|
|
144
|
-
let metadata = crate::types::Metadata {
|
|
145
|
-
format: Some(crate::types::FormatMetadata::Ocr(crate::types::OcrMetadata {
|
|
146
|
-
language: tess_config.language.clone(),
|
|
147
|
-
psm: tess_config.psm as i32,
|
|
148
|
-
output_format: tess_config.output_format.clone(),
|
|
149
|
-
table_count: ocr_result.tables.len(),
|
|
150
|
-
table_rows: ocr_result.tables.first().map(|t| t.cells.len()),
|
|
151
|
-
table_cols: ocr_result
|
|
152
|
-
.tables
|
|
153
|
-
.first()
|
|
154
|
-
.and_then(|t| t.cells.first().map(|row| row.len())),
|
|
155
|
-
})),
|
|
156
|
-
additional: ocr_result.metadata,
|
|
157
|
-
..Default::default()
|
|
158
|
-
};
|
|
159
|
-
|
|
160
|
-
Ok(ExtractionResult {
|
|
161
|
-
content: ocr_result.content,
|
|
162
|
-
mime_type: ocr_result.mime_type,
|
|
163
|
-
metadata,
|
|
164
|
-
pages: None,
|
|
165
|
-
tables: ocr_result
|
|
166
|
-
.tables
|
|
167
|
-
.into_iter()
|
|
168
|
-
.map(|t| crate::types::Table {
|
|
169
|
-
cells: t.cells,
|
|
170
|
-
markdown: t.markdown,
|
|
171
|
-
page_number: t.page_number,
|
|
172
|
-
})
|
|
173
|
-
.collect(),
|
|
174
|
-
detected_languages: None,
|
|
175
|
-
chunks: None,
|
|
176
|
-
images: None,
|
|
177
|
-
})
|
|
178
|
-
}
|
|
179
|
-
|
|
180
|
-
async fn process_file(&self, path: &Path, config: &OcrConfig) -> Result<ExtractionResult> {
|
|
181
|
-
let tess_config = self.config_to_tesseract(config);
|
|
182
|
-
let tess_config_clone = tess_config.clone();
|
|
183
|
-
|
|
184
|
-
let processor = Arc::clone(&self.processor);
|
|
185
|
-
let path_str = path.to_string_lossy().to_string();
|
|
186
|
-
|
|
187
|
-
let ocr_result = tokio::task::spawn_blocking(move || processor.process_file(&path_str, &tess_config_clone))
|
|
188
|
-
.await
|
|
189
|
-
.map_err(|e| crate::KreuzbergError::Plugin {
|
|
190
|
-
message: format!("Tesseract task panicked: {}", e),
|
|
191
|
-
plugin_name: "tesseract".to_string(),
|
|
192
|
-
})?
|
|
193
|
-
.map_err(|e| crate::KreuzbergError::Ocr {
|
|
194
|
-
message: format!("Tesseract OCR failed: {}", e),
|
|
195
|
-
source: Some(Box::new(e)),
|
|
196
|
-
})?;
|
|
197
|
-
|
|
198
|
-
let metadata = crate::types::Metadata {
|
|
199
|
-
format: Some(crate::types::FormatMetadata::Ocr(crate::types::OcrMetadata {
|
|
200
|
-
language: tess_config.language.clone(),
|
|
201
|
-
psm: tess_config.psm as i32,
|
|
202
|
-
output_format: tess_config.output_format.clone(),
|
|
203
|
-
table_count: ocr_result.tables.len(),
|
|
204
|
-
table_rows: ocr_result.tables.first().map(|t| t.cells.len()),
|
|
205
|
-
table_cols: ocr_result
|
|
206
|
-
.tables
|
|
207
|
-
.first()
|
|
208
|
-
.and_then(|t| t.cells.first().map(|row| row.len())),
|
|
209
|
-
})),
|
|
210
|
-
additional: ocr_result.metadata,
|
|
211
|
-
..Default::default()
|
|
212
|
-
};
|
|
213
|
-
|
|
214
|
-
Ok(ExtractionResult {
|
|
215
|
-
content: ocr_result.content,
|
|
216
|
-
mime_type: ocr_result.mime_type,
|
|
217
|
-
metadata,
|
|
218
|
-
pages: None,
|
|
219
|
-
tables: ocr_result
|
|
220
|
-
.tables
|
|
221
|
-
.into_iter()
|
|
222
|
-
.map(|t| crate::types::Table {
|
|
223
|
-
cells: t.cells,
|
|
224
|
-
markdown: t.markdown,
|
|
225
|
-
page_number: t.page_number,
|
|
226
|
-
})
|
|
227
|
-
.collect(),
|
|
228
|
-
detected_languages: None,
|
|
229
|
-
chunks: None,
|
|
230
|
-
images: None,
|
|
231
|
-
})
|
|
232
|
-
}
|
|
233
|
-
|
|
234
|
-
fn supports_language(&self, lang: &str) -> bool {
|
|
235
|
-
// TODO: Query Tesseract for available languages
|
|
236
|
-
matches!(
|
|
237
|
-
lang,
|
|
238
|
-
"eng"
|
|
239
|
-
| "deu"
|
|
240
|
-
| "fra"
|
|
241
|
-
| "spa"
|
|
242
|
-
| "ita"
|
|
243
|
-
| "por"
|
|
244
|
-
| "rus"
|
|
245
|
-
| "chi_sim"
|
|
246
|
-
| "chi_tra"
|
|
247
|
-
| "jpn"
|
|
248
|
-
| "kor"
|
|
249
|
-
| "ara"
|
|
250
|
-
| "hin"
|
|
251
|
-
| "ben"
|
|
252
|
-
| "tha"
|
|
253
|
-
| "vie"
|
|
254
|
-
| "heb"
|
|
255
|
-
| "tur"
|
|
256
|
-
| "pol"
|
|
257
|
-
| "nld"
|
|
258
|
-
| "swe"
|
|
259
|
-
| "dan"
|
|
260
|
-
| "fin"
|
|
261
|
-
| "nor"
|
|
262
|
-
| "ces"
|
|
263
|
-
| "hun"
|
|
264
|
-
| "ron"
|
|
265
|
-
| "ukr"
|
|
266
|
-
| "bul"
|
|
267
|
-
| "hrv"
|
|
268
|
-
| "srp"
|
|
269
|
-
| "slk"
|
|
270
|
-
| "slv"
|
|
271
|
-
| "lit"
|
|
272
|
-
| "lav"
|
|
273
|
-
| "est"
|
|
274
|
-
)
|
|
275
|
-
}
|
|
276
|
-
|
|
277
|
-
fn backend_type(&self) -> OcrBackendType {
|
|
278
|
-
OcrBackendType::Tesseract
|
|
279
|
-
}
|
|
280
|
-
|
|
281
|
-
fn supported_languages(&self) -> Vec<String> {
|
|
282
|
-
// TODO: Query Tesseract API for available languages dynamically
|
|
283
|
-
vec![
|
|
284
|
-
"eng", "deu", "fra", "spa", "ita", "por", "rus", "chi_sim", "chi_tra", "jpn", "kor", "ara", "hin", "ben",
|
|
285
|
-
"tha", "vie", "heb", "tur", "pol", "nld", "swe", "dan", "fin", "nor", "ces", "hun", "ron", "ukr", "bul",
|
|
286
|
-
"hrv", "srp", "slk", "slv", "lit", "lav", "est",
|
|
287
|
-
]
|
|
288
|
-
.into_iter()
|
|
289
|
-
.map(String::from)
|
|
290
|
-
.collect()
|
|
291
|
-
}
|
|
292
|
-
|
|
293
|
-
fn supports_table_detection(&self) -> bool {
|
|
294
|
-
true
|
|
295
|
-
}
|
|
296
|
-
}
|
|
297
|
-
|
|
298
|
-
#[cfg(test)]
|
|
299
|
-
mod tests {
|
|
300
|
-
use super::*;
|
|
301
|
-
|
|
302
|
-
#[test]
|
|
303
|
-
fn test_tesseract_backend_creation() {
|
|
304
|
-
let backend = TesseractBackend::new();
|
|
305
|
-
assert!(backend.is_ok());
|
|
306
|
-
}
|
|
307
|
-
|
|
308
|
-
#[test]
|
|
309
|
-
fn test_tesseract_backend_plugin_interface() {
|
|
310
|
-
let backend = TesseractBackend::new().unwrap();
|
|
311
|
-
assert_eq!(backend.name(), "tesseract");
|
|
312
|
-
assert!(!backend.version().is_empty());
|
|
313
|
-
assert!(backend.initialize().is_ok());
|
|
314
|
-
}
|
|
315
|
-
|
|
316
|
-
#[test]
|
|
317
|
-
fn test_tesseract_backend_type() {
|
|
318
|
-
let backend = TesseractBackend::new().unwrap();
|
|
319
|
-
assert_eq!(backend.backend_type(), OcrBackendType::Tesseract);
|
|
320
|
-
}
|
|
321
|
-
|
|
322
|
-
#[test]
|
|
323
|
-
fn test_tesseract_backend_supports_language() {
|
|
324
|
-
let backend = TesseractBackend::new().unwrap();
|
|
325
|
-
assert!(backend.supports_language("eng"));
|
|
326
|
-
assert!(backend.supports_language("deu"));
|
|
327
|
-
assert!(backend.supports_language("fra"));
|
|
328
|
-
assert!(!backend.supports_language("xyz"));
|
|
329
|
-
}
|
|
330
|
-
|
|
331
|
-
#[test]
|
|
332
|
-
fn test_tesseract_backend_supports_table_detection() {
|
|
333
|
-
let backend = TesseractBackend::new().unwrap();
|
|
334
|
-
assert!(backend.supports_table_detection());
|
|
335
|
-
}
|
|
336
|
-
|
|
337
|
-
#[test]
|
|
338
|
-
fn test_tesseract_backend_supported_languages() {
|
|
339
|
-
let backend = TesseractBackend::new().unwrap();
|
|
340
|
-
let languages = backend.supported_languages();
|
|
341
|
-
assert!(languages.contains(&"eng".to_string()));
|
|
342
|
-
assert!(languages.contains(&"deu".to_string()));
|
|
343
|
-
assert!(languages.len() > 30);
|
|
344
|
-
}
|
|
345
|
-
|
|
346
|
-
#[test]
|
|
347
|
-
fn test_config_to_tesseract_with_none() {
|
|
348
|
-
let backend = TesseractBackend::new().unwrap();
|
|
349
|
-
let ocr_config = OcrConfig {
|
|
350
|
-
backend: "tesseract".to_string(),
|
|
351
|
-
language: "deu".to_string(),
|
|
352
|
-
tesseract_config: None,
|
|
353
|
-
};
|
|
354
|
-
|
|
355
|
-
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
356
|
-
assert_eq!(tess_config.language, "deu");
|
|
357
|
-
assert_eq!(tess_config.psm, InternalTesseractConfig::default().psm);
|
|
358
|
-
}
|
|
359
|
-
|
|
360
|
-
#[test]
|
|
361
|
-
fn test_config_to_tesseract_with_some() {
|
|
362
|
-
let backend = TesseractBackend::new().unwrap();
|
|
363
|
-
let custom_tess_config = crate::types::TesseractConfig {
|
|
364
|
-
language: "fra".to_string(),
|
|
365
|
-
psm: 6,
|
|
366
|
-
enable_table_detection: true,
|
|
367
|
-
..Default::default()
|
|
368
|
-
};
|
|
369
|
-
|
|
370
|
-
let ocr_config = OcrConfig {
|
|
371
|
-
backend: "tesseract".to_string(),
|
|
372
|
-
language: "eng".to_string(),
|
|
373
|
-
tesseract_config: Some(custom_tess_config),
|
|
374
|
-
};
|
|
375
|
-
|
|
376
|
-
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
377
|
-
assert_eq!(tess_config.language, "fra");
|
|
378
|
-
assert_eq!(tess_config.psm, 6);
|
|
379
|
-
assert!(tess_config.enable_table_detection);
|
|
380
|
-
}
|
|
381
|
-
|
|
382
|
-
#[test]
|
|
383
|
-
fn test_tesseract_backend_default() {
|
|
384
|
-
let backend = TesseractBackend::default();
|
|
385
|
-
assert_eq!(backend.name(), "tesseract");
|
|
386
|
-
}
|
|
387
|
-
|
|
388
|
-
#[test]
|
|
389
|
-
fn test_config_conversion_with_new_fields() {
|
|
390
|
-
let backend = TesseractBackend::new().unwrap();
|
|
391
|
-
|
|
392
|
-
let preprocessing = crate::types::ImagePreprocessingConfig {
|
|
393
|
-
target_dpi: 600,
|
|
394
|
-
auto_rotate: false,
|
|
395
|
-
deskew: true,
|
|
396
|
-
denoise: true,
|
|
397
|
-
contrast_enhance: true,
|
|
398
|
-
binarization_method: "adaptive".to_string(),
|
|
399
|
-
invert_colors: false,
|
|
400
|
-
};
|
|
401
|
-
|
|
402
|
-
let custom_tess_config = crate::types::TesseractConfig {
|
|
403
|
-
language: "eng".to_string(),
|
|
404
|
-
psm: 6,
|
|
405
|
-
output_format: "markdown".to_string(),
|
|
406
|
-
oem: 1,
|
|
407
|
-
min_confidence: 80.0,
|
|
408
|
-
preprocessing: Some(preprocessing.clone()),
|
|
409
|
-
tessedit_char_blacklist: "!@#$".to_string(),
|
|
410
|
-
..Default::default()
|
|
411
|
-
};
|
|
412
|
-
|
|
413
|
-
let ocr_config = OcrConfig {
|
|
414
|
-
backend: "tesseract".to_string(),
|
|
415
|
-
language: "eng".to_string(),
|
|
416
|
-
tesseract_config: Some(custom_tess_config),
|
|
417
|
-
};
|
|
418
|
-
|
|
419
|
-
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
420
|
-
|
|
421
|
-
assert_eq!(tess_config.oem, 1);
|
|
422
|
-
assert_eq!(tess_config.min_confidence, 80.0);
|
|
423
|
-
assert_eq!(tess_config.tessedit_char_blacklist, "!@#$");
|
|
424
|
-
|
|
425
|
-
assert!(tess_config.preprocessing.is_some());
|
|
426
|
-
let preproc = tess_config.preprocessing.unwrap();
|
|
427
|
-
assert_eq!(preproc.target_dpi, 600);
|
|
428
|
-
assert!(!preproc.auto_rotate);
|
|
429
|
-
assert!(preproc.deskew);
|
|
430
|
-
assert!(preproc.denoise);
|
|
431
|
-
assert!(preproc.contrast_enhance);
|
|
432
|
-
assert_eq!(preproc.binarization_method, "adaptive");
|
|
433
|
-
assert!(!preproc.invert_colors);
|
|
434
|
-
}
|
|
435
|
-
|
|
436
|
-
#[test]
|
|
437
|
-
fn test_convert_config_type_conversions() {
|
|
438
|
-
let public_config = crate::types::TesseractConfig {
|
|
439
|
-
language: "eng".to_string(),
|
|
440
|
-
psm: 6,
|
|
441
|
-
oem: 3,
|
|
442
|
-
table_column_threshold: 100,
|
|
443
|
-
..Default::default()
|
|
444
|
-
};
|
|
445
|
-
|
|
446
|
-
let internal_config = TesseractBackend::convert_config(&public_config);
|
|
447
|
-
|
|
448
|
-
assert_eq!(internal_config.psm, 6u8);
|
|
449
|
-
assert_eq!(internal_config.oem, 3u8);
|
|
450
|
-
assert_eq!(internal_config.table_column_threshold, 100u32);
|
|
451
|
-
}
|
|
452
|
-
}
|
|
1
|
+
//! Native Tesseract OCR backend.
|
|
2
|
+
//!
|
|
3
|
+
//! This module provides the native Tesseract backend that implements the OcrBackend
|
|
4
|
+
//! trait, bridging the plugin system with the low-level OcrProcessor.
|
|
5
|
+
|
|
6
|
+
use crate::Result;
|
|
7
|
+
use crate::core::config::OcrConfig;
|
|
8
|
+
use crate::ocr::processor::OcrProcessor;
|
|
9
|
+
use crate::plugins::{OcrBackend, OcrBackendType, Plugin};
|
|
10
|
+
use crate::types::ExtractionResult;
|
|
11
|
+
use async_trait::async_trait;
|
|
12
|
+
use std::path::Path;
|
|
13
|
+
use std::sync::Arc;
|
|
14
|
+
|
|
15
|
+
use crate::ocr::types::TesseractConfig as InternalTesseractConfig;
|
|
16
|
+
|
|
17
|
+
/// Native Tesseract OCR backend.
|
|
18
|
+
///
|
|
19
|
+
/// This backend wraps the OcrProcessor and implements the OcrBackend trait,
|
|
20
|
+
/// allowing it to be used through the plugin system.
|
|
21
|
+
///
|
|
22
|
+
/// # Thread Safety
|
|
23
|
+
///
|
|
24
|
+
/// Uses Arc for shared ownership and is thread-safe (Send + Sync).
|
|
25
|
+
pub struct TesseractBackend {
|
|
26
|
+
processor: Arc<OcrProcessor>,
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
impl TesseractBackend {
|
|
30
|
+
/// Create a new Tesseract backend with default cache directory.
|
|
31
|
+
pub fn new() -> Result<Self> {
|
|
32
|
+
let processor = OcrProcessor::new(None).map_err(|e| crate::KreuzbergError::Ocr {
|
|
33
|
+
message: format!("Failed to create Tesseract processor: {}", e),
|
|
34
|
+
source: Some(Box::new(e)),
|
|
35
|
+
})?;
|
|
36
|
+
Ok(Self {
|
|
37
|
+
processor: Arc::new(processor),
|
|
38
|
+
})
|
|
39
|
+
}
|
|
40
|
+
|
|
41
|
+
/// Create a new Tesseract backend with custom cache directory.
|
|
42
|
+
pub fn with_cache_dir(cache_dir: std::path::PathBuf) -> Result<Self> {
|
|
43
|
+
let processor = OcrProcessor::new(Some(cache_dir)).map_err(|e| crate::KreuzbergError::Ocr {
|
|
44
|
+
message: format!("Failed to create Tesseract processor: {}", e),
|
|
45
|
+
source: Some(Box::new(e)),
|
|
46
|
+
})?;
|
|
47
|
+
Ok(Self {
|
|
48
|
+
processor: Arc::new(processor),
|
|
49
|
+
})
|
|
50
|
+
}
|
|
51
|
+
|
|
52
|
+
/// Convert public API TesseractConfig to internal TesseractConfig.
|
|
53
|
+
///
|
|
54
|
+
/// The public API types (crate::types) use i32 for compatibility with PyO3,
|
|
55
|
+
/// while internal types (crate::ocr::types) use u8/u32 for efficiency.
|
|
56
|
+
fn convert_config(public_config: &crate::types::TesseractConfig) -> InternalTesseractConfig {
|
|
57
|
+
InternalTesseractConfig {
|
|
58
|
+
language: public_config.language.clone(),
|
|
59
|
+
psm: public_config.psm as u8,
|
|
60
|
+
output_format: public_config.output_format.clone(),
|
|
61
|
+
oem: public_config.oem as u8,
|
|
62
|
+
min_confidence: public_config.min_confidence,
|
|
63
|
+
preprocessing: public_config.preprocessing.clone(),
|
|
64
|
+
enable_table_detection: public_config.enable_table_detection,
|
|
65
|
+
table_min_confidence: public_config.table_min_confidence,
|
|
66
|
+
table_column_threshold: public_config.table_column_threshold as u32,
|
|
67
|
+
table_row_threshold_ratio: public_config.table_row_threshold_ratio,
|
|
68
|
+
use_cache: public_config.use_cache,
|
|
69
|
+
classify_use_pre_adapted_templates: public_config.classify_use_pre_adapted_templates,
|
|
70
|
+
language_model_ngram_on: public_config.language_model_ngram_on,
|
|
71
|
+
tessedit_dont_blkrej_good_wds: public_config.tessedit_dont_blkrej_good_wds,
|
|
72
|
+
tessedit_dont_rowrej_good_wds: public_config.tessedit_dont_rowrej_good_wds,
|
|
73
|
+
tessedit_enable_dict_correction: public_config.tessedit_enable_dict_correction,
|
|
74
|
+
tessedit_char_whitelist: public_config.tessedit_char_whitelist.clone(),
|
|
75
|
+
tessedit_char_blacklist: public_config.tessedit_char_blacklist.clone(),
|
|
76
|
+
tessedit_use_primary_params_model: public_config.tessedit_use_primary_params_model,
|
|
77
|
+
textord_space_size_is_variable: public_config.textord_space_size_is_variable,
|
|
78
|
+
thresholding_method: public_config.thresholding_method,
|
|
79
|
+
}
|
|
80
|
+
}
|
|
81
|
+
|
|
82
|
+
/// Convert OcrConfig to internal TesseractConfig.
|
|
83
|
+
///
|
|
84
|
+
/// Uses tesseract_config from OcrConfig if provided, otherwise uses defaults
|
|
85
|
+
/// with the language from OcrConfig.
|
|
86
|
+
fn config_to_tesseract(&self, config: &OcrConfig) -> InternalTesseractConfig {
|
|
87
|
+
match &config.tesseract_config {
|
|
88
|
+
Some(tess_config) => Self::convert_config(tess_config),
|
|
89
|
+
None => InternalTesseractConfig {
|
|
90
|
+
language: config.language.clone(),
|
|
91
|
+
..Default::default()
|
|
92
|
+
},
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
impl Default for TesseractBackend {
|
|
98
|
+
fn default() -> Self {
|
|
99
|
+
Self::new().unwrap()
|
|
100
|
+
}
|
|
101
|
+
}
|
|
102
|
+
|
|
103
|
+
impl Plugin for TesseractBackend {
|
|
104
|
+
fn name(&self) -> &str {
|
|
105
|
+
"tesseract"
|
|
106
|
+
}
|
|
107
|
+
|
|
108
|
+
fn version(&self) -> String {
|
|
109
|
+
kreuzberg_tesseract::TesseractAPI::version()
|
|
110
|
+
}
|
|
111
|
+
|
|
112
|
+
fn initialize(&self) -> Result<()> {
|
|
113
|
+
Ok(())
|
|
114
|
+
}
|
|
115
|
+
|
|
116
|
+
fn shutdown(&self) -> Result<()> {
|
|
117
|
+
self.processor.clear_cache().map_err(|e| crate::KreuzbergError::Plugin {
|
|
118
|
+
message: format!("Failed to clear Tesseract cache: {}", e),
|
|
119
|
+
plugin_name: "tesseract".to_string(),
|
|
120
|
+
})
|
|
121
|
+
}
|
|
122
|
+
}
|
|
123
|
+
|
|
124
|
+
#[async_trait]
|
|
125
|
+
impl OcrBackend for TesseractBackend {
|
|
126
|
+
async fn process_image(&self, image_bytes: &[u8], config: &OcrConfig) -> Result<ExtractionResult> {
|
|
127
|
+
let tess_config = self.config_to_tesseract(config);
|
|
128
|
+
let tess_config_clone = tess_config.clone();
|
|
129
|
+
|
|
130
|
+
let processor = Arc::clone(&self.processor);
|
|
131
|
+
let image_bytes = image_bytes.to_vec();
|
|
132
|
+
|
|
133
|
+
let ocr_result = tokio::task::spawn_blocking(move || processor.process_image(&image_bytes, &tess_config_clone))
|
|
134
|
+
.await
|
|
135
|
+
.map_err(|e| crate::KreuzbergError::Plugin {
|
|
136
|
+
message: format!("Tesseract task panicked: {}", e),
|
|
137
|
+
plugin_name: "tesseract".to_string(),
|
|
138
|
+
})?
|
|
139
|
+
.map_err(|e| crate::KreuzbergError::Ocr {
|
|
140
|
+
message: format!("Tesseract OCR failed: {}", e),
|
|
141
|
+
source: Some(Box::new(e)),
|
|
142
|
+
})?;
|
|
143
|
+
|
|
144
|
+
let metadata = crate::types::Metadata {
|
|
145
|
+
format: Some(crate::types::FormatMetadata::Ocr(crate::types::OcrMetadata {
|
|
146
|
+
language: tess_config.language.clone(),
|
|
147
|
+
psm: tess_config.psm as i32,
|
|
148
|
+
output_format: tess_config.output_format.clone(),
|
|
149
|
+
table_count: ocr_result.tables.len(),
|
|
150
|
+
table_rows: ocr_result.tables.first().map(|t| t.cells.len()),
|
|
151
|
+
table_cols: ocr_result
|
|
152
|
+
.tables
|
|
153
|
+
.first()
|
|
154
|
+
.and_then(|t| t.cells.first().map(|row| row.len())),
|
|
155
|
+
})),
|
|
156
|
+
additional: ocr_result.metadata,
|
|
157
|
+
..Default::default()
|
|
158
|
+
};
|
|
159
|
+
|
|
160
|
+
Ok(ExtractionResult {
|
|
161
|
+
content: ocr_result.content,
|
|
162
|
+
mime_type: ocr_result.mime_type,
|
|
163
|
+
metadata,
|
|
164
|
+
pages: None,
|
|
165
|
+
tables: ocr_result
|
|
166
|
+
.tables
|
|
167
|
+
.into_iter()
|
|
168
|
+
.map(|t| crate::types::Table {
|
|
169
|
+
cells: t.cells,
|
|
170
|
+
markdown: t.markdown,
|
|
171
|
+
page_number: t.page_number,
|
|
172
|
+
})
|
|
173
|
+
.collect(),
|
|
174
|
+
detected_languages: None,
|
|
175
|
+
chunks: None,
|
|
176
|
+
images: None,
|
|
177
|
+
})
|
|
178
|
+
}
|
|
179
|
+
|
|
180
|
+
async fn process_file(&self, path: &Path, config: &OcrConfig) -> Result<ExtractionResult> {
|
|
181
|
+
let tess_config = self.config_to_tesseract(config);
|
|
182
|
+
let tess_config_clone = tess_config.clone();
|
|
183
|
+
|
|
184
|
+
let processor = Arc::clone(&self.processor);
|
|
185
|
+
let path_str = path.to_string_lossy().to_string();
|
|
186
|
+
|
|
187
|
+
let ocr_result = tokio::task::spawn_blocking(move || processor.process_file(&path_str, &tess_config_clone))
|
|
188
|
+
.await
|
|
189
|
+
.map_err(|e| crate::KreuzbergError::Plugin {
|
|
190
|
+
message: format!("Tesseract task panicked: {}", e),
|
|
191
|
+
plugin_name: "tesseract".to_string(),
|
|
192
|
+
})?
|
|
193
|
+
.map_err(|e| crate::KreuzbergError::Ocr {
|
|
194
|
+
message: format!("Tesseract OCR failed: {}", e),
|
|
195
|
+
source: Some(Box::new(e)),
|
|
196
|
+
})?;
|
|
197
|
+
|
|
198
|
+
let metadata = crate::types::Metadata {
|
|
199
|
+
format: Some(crate::types::FormatMetadata::Ocr(crate::types::OcrMetadata {
|
|
200
|
+
language: tess_config.language.clone(),
|
|
201
|
+
psm: tess_config.psm as i32,
|
|
202
|
+
output_format: tess_config.output_format.clone(),
|
|
203
|
+
table_count: ocr_result.tables.len(),
|
|
204
|
+
table_rows: ocr_result.tables.first().map(|t| t.cells.len()),
|
|
205
|
+
table_cols: ocr_result
|
|
206
|
+
.tables
|
|
207
|
+
.first()
|
|
208
|
+
.and_then(|t| t.cells.first().map(|row| row.len())),
|
|
209
|
+
})),
|
|
210
|
+
additional: ocr_result.metadata,
|
|
211
|
+
..Default::default()
|
|
212
|
+
};
|
|
213
|
+
|
|
214
|
+
Ok(ExtractionResult {
|
|
215
|
+
content: ocr_result.content,
|
|
216
|
+
mime_type: ocr_result.mime_type,
|
|
217
|
+
metadata,
|
|
218
|
+
pages: None,
|
|
219
|
+
tables: ocr_result
|
|
220
|
+
.tables
|
|
221
|
+
.into_iter()
|
|
222
|
+
.map(|t| crate::types::Table {
|
|
223
|
+
cells: t.cells,
|
|
224
|
+
markdown: t.markdown,
|
|
225
|
+
page_number: t.page_number,
|
|
226
|
+
})
|
|
227
|
+
.collect(),
|
|
228
|
+
detected_languages: None,
|
|
229
|
+
chunks: None,
|
|
230
|
+
images: None,
|
|
231
|
+
})
|
|
232
|
+
}
|
|
233
|
+
|
|
234
|
+
fn supports_language(&self, lang: &str) -> bool {
|
|
235
|
+
// TODO: Query Tesseract for available languages
|
|
236
|
+
matches!(
|
|
237
|
+
lang,
|
|
238
|
+
"eng"
|
|
239
|
+
| "deu"
|
|
240
|
+
| "fra"
|
|
241
|
+
| "spa"
|
|
242
|
+
| "ita"
|
|
243
|
+
| "por"
|
|
244
|
+
| "rus"
|
|
245
|
+
| "chi_sim"
|
|
246
|
+
| "chi_tra"
|
|
247
|
+
| "jpn"
|
|
248
|
+
| "kor"
|
|
249
|
+
| "ara"
|
|
250
|
+
| "hin"
|
|
251
|
+
| "ben"
|
|
252
|
+
| "tha"
|
|
253
|
+
| "vie"
|
|
254
|
+
| "heb"
|
|
255
|
+
| "tur"
|
|
256
|
+
| "pol"
|
|
257
|
+
| "nld"
|
|
258
|
+
| "swe"
|
|
259
|
+
| "dan"
|
|
260
|
+
| "fin"
|
|
261
|
+
| "nor"
|
|
262
|
+
| "ces"
|
|
263
|
+
| "hun"
|
|
264
|
+
| "ron"
|
|
265
|
+
| "ukr"
|
|
266
|
+
| "bul"
|
|
267
|
+
| "hrv"
|
|
268
|
+
| "srp"
|
|
269
|
+
| "slk"
|
|
270
|
+
| "slv"
|
|
271
|
+
| "lit"
|
|
272
|
+
| "lav"
|
|
273
|
+
| "est"
|
|
274
|
+
)
|
|
275
|
+
}
|
|
276
|
+
|
|
277
|
+
fn backend_type(&self) -> OcrBackendType {
|
|
278
|
+
OcrBackendType::Tesseract
|
|
279
|
+
}
|
|
280
|
+
|
|
281
|
+
fn supported_languages(&self) -> Vec<String> {
|
|
282
|
+
// TODO: Query Tesseract API for available languages dynamically
|
|
283
|
+
vec![
|
|
284
|
+
"eng", "deu", "fra", "spa", "ita", "por", "rus", "chi_sim", "chi_tra", "jpn", "kor", "ara", "hin", "ben",
|
|
285
|
+
"tha", "vie", "heb", "tur", "pol", "nld", "swe", "dan", "fin", "nor", "ces", "hun", "ron", "ukr", "bul",
|
|
286
|
+
"hrv", "srp", "slk", "slv", "lit", "lav", "est",
|
|
287
|
+
]
|
|
288
|
+
.into_iter()
|
|
289
|
+
.map(String::from)
|
|
290
|
+
.collect()
|
|
291
|
+
}
|
|
292
|
+
|
|
293
|
+
fn supports_table_detection(&self) -> bool {
|
|
294
|
+
true
|
|
295
|
+
}
|
|
296
|
+
}
|
|
297
|
+
|
|
298
|
+
#[cfg(test)]
|
|
299
|
+
mod tests {
|
|
300
|
+
use super::*;
|
|
301
|
+
|
|
302
|
+
#[test]
|
|
303
|
+
fn test_tesseract_backend_creation() {
|
|
304
|
+
let backend = TesseractBackend::new();
|
|
305
|
+
assert!(backend.is_ok());
|
|
306
|
+
}
|
|
307
|
+
|
|
308
|
+
#[test]
|
|
309
|
+
fn test_tesseract_backend_plugin_interface() {
|
|
310
|
+
let backend = TesseractBackend::new().unwrap();
|
|
311
|
+
assert_eq!(backend.name(), "tesseract");
|
|
312
|
+
assert!(!backend.version().is_empty());
|
|
313
|
+
assert!(backend.initialize().is_ok());
|
|
314
|
+
}
|
|
315
|
+
|
|
316
|
+
#[test]
|
|
317
|
+
fn test_tesseract_backend_type() {
|
|
318
|
+
let backend = TesseractBackend::new().unwrap();
|
|
319
|
+
assert_eq!(backend.backend_type(), OcrBackendType::Tesseract);
|
|
320
|
+
}
|
|
321
|
+
|
|
322
|
+
#[test]
|
|
323
|
+
fn test_tesseract_backend_supports_language() {
|
|
324
|
+
let backend = TesseractBackend::new().unwrap();
|
|
325
|
+
assert!(backend.supports_language("eng"));
|
|
326
|
+
assert!(backend.supports_language("deu"));
|
|
327
|
+
assert!(backend.supports_language("fra"));
|
|
328
|
+
assert!(!backend.supports_language("xyz"));
|
|
329
|
+
}
|
|
330
|
+
|
|
331
|
+
#[test]
|
|
332
|
+
fn test_tesseract_backend_supports_table_detection() {
|
|
333
|
+
let backend = TesseractBackend::new().unwrap();
|
|
334
|
+
assert!(backend.supports_table_detection());
|
|
335
|
+
}
|
|
336
|
+
|
|
337
|
+
#[test]
|
|
338
|
+
fn test_tesseract_backend_supported_languages() {
|
|
339
|
+
let backend = TesseractBackend::new().unwrap();
|
|
340
|
+
let languages = backend.supported_languages();
|
|
341
|
+
assert!(languages.contains(&"eng".to_string()));
|
|
342
|
+
assert!(languages.contains(&"deu".to_string()));
|
|
343
|
+
assert!(languages.len() > 30);
|
|
344
|
+
}
|
|
345
|
+
|
|
346
|
+
#[test]
|
|
347
|
+
fn test_config_to_tesseract_with_none() {
|
|
348
|
+
let backend = TesseractBackend::new().unwrap();
|
|
349
|
+
let ocr_config = OcrConfig {
|
|
350
|
+
backend: "tesseract".to_string(),
|
|
351
|
+
language: "deu".to_string(),
|
|
352
|
+
tesseract_config: None,
|
|
353
|
+
};
|
|
354
|
+
|
|
355
|
+
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
356
|
+
assert_eq!(tess_config.language, "deu");
|
|
357
|
+
assert_eq!(tess_config.psm, InternalTesseractConfig::default().psm);
|
|
358
|
+
}
|
|
359
|
+
|
|
360
|
+
#[test]
|
|
361
|
+
fn test_config_to_tesseract_with_some() {
|
|
362
|
+
let backend = TesseractBackend::new().unwrap();
|
|
363
|
+
let custom_tess_config = crate::types::TesseractConfig {
|
|
364
|
+
language: "fra".to_string(),
|
|
365
|
+
psm: 6,
|
|
366
|
+
enable_table_detection: true,
|
|
367
|
+
..Default::default()
|
|
368
|
+
};
|
|
369
|
+
|
|
370
|
+
let ocr_config = OcrConfig {
|
|
371
|
+
backend: "tesseract".to_string(),
|
|
372
|
+
language: "eng".to_string(),
|
|
373
|
+
tesseract_config: Some(custom_tess_config),
|
|
374
|
+
};
|
|
375
|
+
|
|
376
|
+
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
377
|
+
assert_eq!(tess_config.language, "fra");
|
|
378
|
+
assert_eq!(tess_config.psm, 6);
|
|
379
|
+
assert!(tess_config.enable_table_detection);
|
|
380
|
+
}
|
|
381
|
+
|
|
382
|
+
#[test]
|
|
383
|
+
fn test_tesseract_backend_default() {
|
|
384
|
+
let backend = TesseractBackend::default();
|
|
385
|
+
assert_eq!(backend.name(), "tesseract");
|
|
386
|
+
}
|
|
387
|
+
|
|
388
|
+
#[test]
|
|
389
|
+
fn test_config_conversion_with_new_fields() {
|
|
390
|
+
let backend = TesseractBackend::new().unwrap();
|
|
391
|
+
|
|
392
|
+
let preprocessing = crate::types::ImagePreprocessingConfig {
|
|
393
|
+
target_dpi: 600,
|
|
394
|
+
auto_rotate: false,
|
|
395
|
+
deskew: true,
|
|
396
|
+
denoise: true,
|
|
397
|
+
contrast_enhance: true,
|
|
398
|
+
binarization_method: "adaptive".to_string(),
|
|
399
|
+
invert_colors: false,
|
|
400
|
+
};
|
|
401
|
+
|
|
402
|
+
let custom_tess_config = crate::types::TesseractConfig {
|
|
403
|
+
language: "eng".to_string(),
|
|
404
|
+
psm: 6,
|
|
405
|
+
output_format: "markdown".to_string(),
|
|
406
|
+
oem: 1,
|
|
407
|
+
min_confidence: 80.0,
|
|
408
|
+
preprocessing: Some(preprocessing.clone()),
|
|
409
|
+
tessedit_char_blacklist: "!@#$".to_string(),
|
|
410
|
+
..Default::default()
|
|
411
|
+
};
|
|
412
|
+
|
|
413
|
+
let ocr_config = OcrConfig {
|
|
414
|
+
backend: "tesseract".to_string(),
|
|
415
|
+
language: "eng".to_string(),
|
|
416
|
+
tesseract_config: Some(custom_tess_config),
|
|
417
|
+
};
|
|
418
|
+
|
|
419
|
+
let tess_config = backend.config_to_tesseract(&ocr_config);
|
|
420
|
+
|
|
421
|
+
assert_eq!(tess_config.oem, 1);
|
|
422
|
+
assert_eq!(tess_config.min_confidence, 80.0);
|
|
423
|
+
assert_eq!(tess_config.tessedit_char_blacklist, "!@#$");
|
|
424
|
+
|
|
425
|
+
assert!(tess_config.preprocessing.is_some());
|
|
426
|
+
let preproc = tess_config.preprocessing.unwrap();
|
|
427
|
+
assert_eq!(preproc.target_dpi, 600);
|
|
428
|
+
assert!(!preproc.auto_rotate);
|
|
429
|
+
assert!(preproc.deskew);
|
|
430
|
+
assert!(preproc.denoise);
|
|
431
|
+
assert!(preproc.contrast_enhance);
|
|
432
|
+
assert_eq!(preproc.binarization_method, "adaptive");
|
|
433
|
+
assert!(!preproc.invert_colors);
|
|
434
|
+
}
|
|
435
|
+
|
|
436
|
+
#[test]
|
|
437
|
+
fn test_convert_config_type_conversions() {
|
|
438
|
+
let public_config = crate::types::TesseractConfig {
|
|
439
|
+
language: "eng".to_string(),
|
|
440
|
+
psm: 6,
|
|
441
|
+
oem: 3,
|
|
442
|
+
table_column_threshold: 100,
|
|
443
|
+
..Default::default()
|
|
444
|
+
};
|
|
445
|
+
|
|
446
|
+
let internal_config = TesseractBackend::convert_config(&public_config);
|
|
447
|
+
|
|
448
|
+
assert_eq!(internal_config.psm, 6u8);
|
|
449
|
+
assert_eq!(internal_config.oem, 3u8);
|
|
450
|
+
assert_eq!(internal_config.table_column_threshold, 100u32);
|
|
451
|
+
}
|
|
452
|
+
}
|