kreuzberg 4.10.4 → 5.0.0.pre.rc.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Steepfile +14 -0
- data/ext/kreuzberg_rb/extconf.rb +1 -48
- data/ext/kreuzberg_rb/native/Cargo.lock +7315 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +15 -66
- data/ext/kreuzberg_rb/src/lib.rs +25709 -0
- data/lib/kreuzberg/native.rb +4193 -0
- data/lib/kreuzberg/version.rb +6 -1
- data/lib/kreuzberg.rb +7 -101
- data/lib/kreuzberg_rb.so +4 -0
- data/sig/types.rbs +1714 -0
- metadata +17 -1053
- data/README.md +0 -442
- data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -21
- data/ext/kreuzberg_rb/native/README.md +0 -448
- data/ext/kreuzberg_rb/native/build.rs +0 -13
- data/ext/kreuzberg_rb/native/include/ieeefp.h +0 -11
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +0 -14
- data/ext/kreuzberg_rb/native/include/strings.h +0 -20
- data/ext/kreuzberg_rb/native/include/unistd.h +0 -47
- data/ext/kreuzberg_rb/native/src/batch.rs +0 -223
- data/ext/kreuzberg_rb/native/src/config/mod.rs +0 -29
- data/ext/kreuzberg_rb/native/src/config/types.rs +0 -1210
- data/ext/kreuzberg_rb/native/src/embedding.rs +0 -79
- data/ext/kreuzberg_rb/native/src/error_handling.rs +0 -134
- data/ext/kreuzberg_rb/native/src/extraction.rs +0 -109
- data/ext/kreuzberg_rb/native/src/gc_guarded_value.rs +0 -35
- data/ext/kreuzberg_rb/native/src/helpers.rs +0 -176
- data/ext/kreuzberg_rb/native/src/lib.rs +0 -546
- data/ext/kreuzberg_rb/native/src/metadata.rs +0 -34
- data/ext/kreuzberg_rb/native/src/plugins/mod.rs +0 -79
- data/ext/kreuzberg_rb/native/src/plugins/ocr_backend.rs +0 -161
- data/ext/kreuzberg_rb/native/src/plugins/post_processor.rs +0 -130
- data/ext/kreuzberg_rb/native/src/plugins/validator.rs +0 -99
- data/ext/kreuzberg_rb/native/src/result.rs +0 -845
- data/ext/kreuzberg_rb/native/src/validation.rs +0 -4
- data/lib/kreuzberg/api_proxy.rb +0 -134
- data/lib/kreuzberg/cache_api.rb +0 -67
- data/lib/kreuzberg/cli.rb +0 -55
- data/lib/kreuzberg/cli_proxy.rb +0 -124
- data/lib/kreuzberg/config.rb +0 -1563
- data/lib/kreuzberg/djot_content.rb +0 -216
- data/lib/kreuzberg/document_structure.rb +0 -192
- data/lib/kreuzberg/error_context.rb +0 -136
- data/lib/kreuzberg/errors.rb +0 -130
- data/lib/kreuzberg/extraction_api.rb +0 -400
- data/lib/kreuzberg/mcp_proxy.rb +0 -184
- data/lib/kreuzberg/ocr_backend_protocol.rb +0 -40
- data/lib/kreuzberg/post_processor_protocol.rb +0 -15
- data/lib/kreuzberg/result.rb +0 -857
- data/lib/kreuzberg/setup_lib_path.rb +0 -101
- data/lib/kreuzberg/types.rb +0 -616
- data/lib/kreuzberg/validator_protocol.rb +0 -16
- data/sig/kreuzberg/internal.rbs +0 -184
- data/sig/kreuzberg.rbs +0 -1859
- data/spec/binding/async_operations_spec.rb +0 -468
- data/spec/binding/batch_operations_spec.rb +0 -670
- data/spec/binding/batch_spec.rb +0 -368
- data/spec/binding/cache_spec.rb +0 -228
- data/spec/binding/cli_proxy_spec.rb +0 -87
- data/spec/binding/cli_spec.rb +0 -55
- data/spec/binding/config_spec.rb +0 -423
- data/spec/binding/config_validation_spec.rb +0 -381
- data/spec/binding/embeddings_spec.rb +0 -134
- data/spec/binding/error_handling_spec.rb +0 -396
- data/spec/binding/error_recovery_spec.rb +0 -492
- data/spec/binding/errors_spec.rb +0 -67
- data/spec/binding/font_config_spec.rb +0 -220
- data/spec/binding/images_spec.rb +0 -156
- data/spec/binding/keywords_extraction_spec.rb +0 -52
- data/spec/binding/pages_extraction_spec.rb +0 -101
- data/spec/binding/plugins/ocr_backend_spec.rb +0 -311
- data/spec/binding/plugins/postprocessor_spec.rb +0 -273
- data/spec/binding/plugins/validator_spec.rb +0 -277
- data/spec/binding/render_spec.rb +0 -91
- data/spec/binding/tables_spec.rb +0 -183
- data/spec/spec_helper.rb +0 -42
- data/vendor/Cargo.toml +0 -62
- data/vendor/kreuzberg/Cargo.toml +0 -350
- data/vendor/kreuzberg/README.md +0 -354
- data/vendor/kreuzberg/build.rs +0 -791
- data/vendor/kreuzberg/src/api/config.rs +0 -68
- data/vendor/kreuzberg/src/api/error.rs +0 -205
- data/vendor/kreuzberg/src/api/handlers.rs +0 -1399
- data/vendor/kreuzberg/src/api/mod.rs +0 -113
- data/vendor/kreuzberg/src/api/openapi.rs +0 -185
- data/vendor/kreuzberg/src/api/openweb.rs +0 -169
- data/vendor/kreuzberg/src/api/router.rs +0 -256
- data/vendor/kreuzberg/src/api/startup.rs +0 -256
- data/vendor/kreuzberg/src/api/types.rs +0 -474
- data/vendor/kreuzberg/src/cache/cleanup.rs +0 -277
- data/vendor/kreuzberg/src/cache/core.rs +0 -527
- data/vendor/kreuzberg/src/cache/mod.rs +0 -348
- data/vendor/kreuzberg/src/cache/utilities.rs +0 -174
- data/vendor/kreuzberg/src/cache_dir.rs +0 -53
- data/vendor/kreuzberg/src/cancellation.rs +0 -105
- data/vendor/kreuzberg/src/chunking/boundaries.rs +0 -321
- data/vendor/kreuzberg/src/chunking/boundary_detection.rs +0 -440
- data/vendor/kreuzberg/src/chunking/builder.rs +0 -197
- data/vendor/kreuzberg/src/chunking/classifier.rs +0 -432
- data/vendor/kreuzberg/src/chunking/config.rs +0 -16
- data/vendor/kreuzberg/src/chunking/core.rs +0 -1380
- data/vendor/kreuzberg/src/chunking/headings.rs +0 -170
- data/vendor/kreuzberg/src/chunking/mod.rs +0 -109
- data/vendor/kreuzberg/src/chunking/processor.rs +0 -332
- data/vendor/kreuzberg/src/chunking/semantic/merge.rs +0 -452
- data/vendor/kreuzberg/src/chunking/semantic/mod.rs +0 -487
- data/vendor/kreuzberg/src/chunking/semantic/topic.rs +0 -212
- data/vendor/kreuzberg/src/chunking/tokenizer_cache.rs +0 -75
- data/vendor/kreuzberg/src/chunking/validation.rs +0 -684
- data/vendor/kreuzberg/src/chunking/yaml_section.rs +0 -594
- data/vendor/kreuzberg/src/core/batch_mode.rs +0 -94
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -393
- data/vendor/kreuzberg/src/core/config/acceleration.rs +0 -55
- data/vendor/kreuzberg/src/core/config/concurrency.rs +0 -138
- data/vendor/kreuzberg/src/core/config/content_filter.rs +0 -80
- data/vendor/kreuzberg/src/core/config/email.rs +0 -58
- data/vendor/kreuzberg/src/core/config/extraction/core.rs +0 -607
- data/vendor/kreuzberg/src/core/config/extraction/env.rs +0 -362
- data/vendor/kreuzberg/src/core/config/extraction/file_config.rs +0 -148
- data/vendor/kreuzberg/src/core/config/extraction/loaders.rs +0 -277
- data/vendor/kreuzberg/src/core/config/extraction/mod.rs +0 -43
- data/vendor/kreuzberg/src/core/config/extraction/types.rs +0 -152
- data/vendor/kreuzberg/src/core/config/formats.rs +0 -200
- data/vendor/kreuzberg/src/core/config/html_output.rs +0 -136
- data/vendor/kreuzberg/src/core/config/layout.rs +0 -179
- data/vendor/kreuzberg/src/core/config/llm.rs +0 -154
- data/vendor/kreuzberg/src/core/config/merge.rs +0 -149
- data/vendor/kreuzberg/src/core/config/mod.rs +0 -45
- data/vendor/kreuzberg/src/core/config/ocr.rs +0 -688
- data/vendor/kreuzberg/src/core/config/page.rs +0 -57
- data/vendor/kreuzberg/src/core/config/pdf.rs +0 -190
- data/vendor/kreuzberg/src/core/config/processing.rs +0 -733
- data/vendor/kreuzberg/src/core/config/tree_sitter.rs +0 -162
- data/vendor/kreuzberg/src/core/config_validation/dependencies.rs +0 -182
- data/vendor/kreuzberg/src/core/config_validation/mod.rs +0 -391
- data/vendor/kreuzberg/src/core/config_validation/sections.rs +0 -605
- data/vendor/kreuzberg/src/core/extractor/batch.rs +0 -316
- data/vendor/kreuzberg/src/core/extractor/bytes.rs +0 -143
- data/vendor/kreuzberg/src/core/extractor/file.rs +0 -260
- data/vendor/kreuzberg/src/core/extractor/helpers.rs +0 -91
- data/vendor/kreuzberg/src/core/extractor/legacy.rs +0 -74
- data/vendor/kreuzberg/src/core/extractor/mod.rs +0 -607
- data/vendor/kreuzberg/src/core/extractor/sync.rs +0 -198
- data/vendor/kreuzberg/src/core/formats.rs +0 -235
- data/vendor/kreuzberg/src/core/io.rs +0 -409
- data/vendor/kreuzberg/src/core/mime.rs +0 -1201
- data/vendor/kreuzberg/src/core/mod.rs +0 -65
- data/vendor/kreuzberg/src/core/path_resolver.rs +0 -270
- data/vendor/kreuzberg/src/core/pipeline/cache.rs +0 -45
- data/vendor/kreuzberg/src/core/pipeline/execution.rs +0 -128
- data/vendor/kreuzberg/src/core/pipeline/features.rs +0 -409
- data/vendor/kreuzberg/src/core/pipeline/format.rs +0 -202
- data/vendor/kreuzberg/src/core/pipeline/initialization.rs +0 -67
- data/vendor/kreuzberg/src/core/pipeline/mod.rs +0 -323
- data/vendor/kreuzberg/src/core/pipeline/tests.rs +0 -881
- data/vendor/kreuzberg/src/core/server_config/env.rs +0 -71
- data/vendor/kreuzberg/src/core/server_config/loader.rs +0 -182
- data/vendor/kreuzberg/src/core/server_config/mod.rs +0 -351
- data/vendor/kreuzberg/src/core/server_config/tests/basic_tests.rs +0 -87
- data/vendor/kreuzberg/src/core/server_config/tests/env_tests.rs +0 -185
- data/vendor/kreuzberg/src/core/server_config/tests/file_loading_tests.rs +0 -317
- data/vendor/kreuzberg/src/core/server_config/tests/mod.rs +0 -5
- data/vendor/kreuzberg/src/core/server_config/validation.rs +0 -4
- data/vendor/kreuzberg/src/doc_orientation.rs +0 -312
- data/vendor/kreuzberg/src/embeddings/engine.rs +0 -422
- data/vendor/kreuzberg/src/embeddings/mod.rs +0 -1082
- data/vendor/kreuzberg/src/error.rs +0 -448
- data/vendor/kreuzberg/src/extraction/archive/gzip.rs +0 -215
- data/vendor/kreuzberg/src/extraction/archive/mod.rs +0 -993
- data/vendor/kreuzberg/src/extraction/archive/sevenz.rs +0 -196
- data/vendor/kreuzberg/src/extraction/archive/tar.rs +0 -217
- data/vendor/kreuzberg/src/extraction/archive/zip.rs +0 -191
- data/vendor/kreuzberg/src/extraction/blank_detection.rs +0 -62
- data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
- data/vendor/kreuzberg/src/extraction/derive.rs +0 -948
- data/vendor/kreuzberg/src/extraction/doc/mod.rs +0 -715
- data/vendor/kreuzberg/src/extraction/docx/drawing.rs +0 -610
- data/vendor/kreuzberg/src/extraction/docx/math.rs +0 -1662
- data/vendor/kreuzberg/src/extraction/docx/mod.rs +0 -276
- data/vendor/kreuzberg/src/extraction/docx/parser.rs +0 -3570
- data/vendor/kreuzberg/src/extraction/docx/section.rs +0 -476
- data/vendor/kreuzberg/src/extraction/docx/styles.rs +0 -1472
- data/vendor/kreuzberg/src/extraction/docx/table.rs +0 -1042
- data/vendor/kreuzberg/src/extraction/docx/theme.rs +0 -479
- data/vendor/kreuzberg/src/extraction/email.rs +0 -2118
- data/vendor/kreuzberg/src/extraction/excel.rs +0 -1038
- data/vendor/kreuzberg/src/extraction/html/converter.rs +0 -747
- data/vendor/kreuzberg/src/extraction/html/image_handling.rs +0 -1
- data/vendor/kreuzberg/src/extraction/html/mod.rs +0 -52
- data/vendor/kreuzberg/src/extraction/html/processor.rs +0 -1
- data/vendor/kreuzberg/src/extraction/html/stack_management.rs +0 -103
- data/vendor/kreuzberg/src/extraction/html/structure.rs +0 -1396
- data/vendor/kreuzberg/src/extraction/html/types.rs +0 -29
- data/vendor/kreuzberg/src/extraction/hwp/error.rs +0 -54
- data/vendor/kreuzberg/src/extraction/hwp/mod.rs +0 -70
- data/vendor/kreuzberg/src/extraction/hwp/model.rs +0 -99
- data/vendor/kreuzberg/src/extraction/hwp/parser.rs +0 -172
- data/vendor/kreuzberg/src/extraction/hwp/reader.rs +0 -112
- data/vendor/kreuzberg/src/extraction/image.rs +0 -897
- data/vendor/kreuzberg/src/extraction/image_format.rs +0 -98
- data/vendor/kreuzberg/src/extraction/image_ocr.rs +0 -196
- data/vendor/kreuzberg/src/extraction/markdown.rs +0 -303
- data/vendor/kreuzberg/src/extraction/mod.rs +0 -123
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +0 -377
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +0 -240
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +0 -233
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -160
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -277
- data/vendor/kreuzberg/src/extraction/ooxml_constants.rs +0 -45
- data/vendor/kreuzberg/src/extraction/ooxml_embedded.rs +0 -132
- data/vendor/kreuzberg/src/extraction/ppt/mod.rs +0 -421
- data/vendor/kreuzberg/src/extraction/pptx/container.rs +0 -194
- data/vendor/kreuzberg/src/extraction/pptx/content_builder.rs +0 -233
- data/vendor/kreuzberg/src/extraction/pptx/elements.rs +0 -167
- data/vendor/kreuzberg/src/extraction/pptx/image_handling.rs +0 -37
- data/vendor/kreuzberg/src/extraction/pptx/metadata.rs +0 -171
- data/vendor/kreuzberg/src/extraction/pptx/mod.rs +0 -1124
- data/vendor/kreuzberg/src/extraction/pptx/parser.rs +0 -547
- data/vendor/kreuzberg/src/extraction/pst.rs +0 -460
- data/vendor/kreuzberg/src/extraction/structured.rs +0 -770
- data/vendor/kreuzberg/src/extraction/text.rs +0 -281
- data/vendor/kreuzberg/src/extraction/transform/content.rs +0 -490
- data/vendor/kreuzberg/src/extraction/transform/document_tree.rs +0 -724
- data/vendor/kreuzberg/src/extraction/transform/elements.rs +0 -214
- data/vendor/kreuzberg/src/extraction/transform/mod.rs +0 -628
- data/vendor/kreuzberg/src/extraction/transform/types.rs +0 -27
- data/vendor/kreuzberg/src/extraction/xml.rs +0 -623
- data/vendor/kreuzberg/src/extractors/annotation_utils.rs +0 -91
- data/vendor/kreuzberg/src/extractors/archive.rs +0 -749
- data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -645
- data/vendor/kreuzberg/src/extractors/citation.rs +0 -565
- data/vendor/kreuzberg/src/extractors/code.rs +0 -201
- data/vendor/kreuzberg/src/extractors/csv.rs +0 -713
- data/vendor/kreuzberg/src/extractors/dbf.rs +0 -222
- data/vendor/kreuzberg/src/extractors/djot_format/attributes.rs +0 -95
- data/vendor/kreuzberg/src/extractors/djot_format/conversion.rs +0 -210
- data/vendor/kreuzberg/src/extractors/djot_format/extractor.rs +0 -666
- data/vendor/kreuzberg/src/extractors/djot_format/mod.rs +0 -23
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/block_handlers.rs +0 -269
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/content_extraction.rs +0 -230
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/event_handlers.rs +0 -96
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/inline_handlers.rs +0 -199
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/mod.rs +0 -15
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/state.rs +0 -76
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/table_extraction.rs +0 -67
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/text_extraction.rs +0 -61
- data/vendor/kreuzberg/src/extractors/djot_format/rendering.rs +0 -443
- data/vendor/kreuzberg/src/extractors/doc.rs +0 -258
- data/vendor/kreuzberg/src/extractors/docbook.rs +0 -1263
- data/vendor/kreuzberg/src/extractors/docx.rs +0 -2354
- data/vendor/kreuzberg/src/extractors/email.rs +0 -416
- data/vendor/kreuzberg/src/extractors/epub/content.rs +0 -705
- data/vendor/kreuzberg/src/extractors/epub/metadata.rs +0 -309
- data/vendor/kreuzberg/src/extractors/epub/mod.rs +0 -673
- data/vendor/kreuzberg/src/extractors/epub/parsing.rs +0 -153
- data/vendor/kreuzberg/src/extractors/excel.rs +0 -288
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -1301
- data/vendor/kreuzberg/src/extractors/frontmatter_utils.rs +0 -438
- data/vendor/kreuzberg/src/extractors/html.rs +0 -1014
- data/vendor/kreuzberg/src/extractors/hwp.rs +0 -134
- data/vendor/kreuzberg/src/extractors/image.rs +0 -741
- data/vendor/kreuzberg/src/extractors/iwork/keynote.rs +0 -255
- data/vendor/kreuzberg/src/extractors/iwork/mod.rs +0 -377
- data/vendor/kreuzberg/src/extractors/iwork/numbers.rs +0 -238
- data/vendor/kreuzberg/src/extractors/iwork/pages.rs +0 -279
- data/vendor/kreuzberg/src/extractors/jats/elements.rs +0 -417
- data/vendor/kreuzberg/src/extractors/jats/metadata.rs +0 -29
- data/vendor/kreuzberg/src/extractors/jats/mod.rs +0 -1181
- data/vendor/kreuzberg/src/extractors/jats/parser.rs +0 -233
- data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -852
- data/vendor/kreuzberg/src/extractors/latex/commands.rs +0 -236
- data/vendor/kreuzberg/src/extractors/latex/environments.rs +0 -155
- data/vendor/kreuzberg/src/extractors/latex/metadata.rs +0 -32
- data/vendor/kreuzberg/src/extractors/latex/mod.rs +0 -1231
- data/vendor/kreuzberg/src/extractors/latex/parser.rs +0 -247
- data/vendor/kreuzberg/src/extractors/latex/utilities.rs +0 -189
- data/vendor/kreuzberg/src/extractors/markdown.rs +0 -1078
- data/vendor/kreuzberg/src/extractors/markdown_utils.rs +0 -169
- data/vendor/kreuzberg/src/extractors/mdx.rs +0 -1199
- data/vendor/kreuzberg/src/extractors/mod.rs +0 -536
- data/vendor/kreuzberg/src/extractors/odt.rs +0 -1215
- data/vendor/kreuzberg/src/extractors/opml/core.rs +0 -183
- data/vendor/kreuzberg/src/extractors/opml/mod.rs +0 -30
- data/vendor/kreuzberg/src/extractors/opml/parser.rs +0 -699
- data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -1362
- data/vendor/kreuzberg/src/extractors/pdf/extraction.rs +0 -708
- data/vendor/kreuzberg/src/extractors/pdf/mod.rs +0 -1406
- data/vendor/kreuzberg/src/extractors/pdf/ocr.rs +0 -1983
- data/vendor/kreuzberg/src/extractors/pdf/pages.rs +0 -103
- data/vendor/kreuzberg/src/extractors/ppt.rs +0 -314
- data/vendor/kreuzberg/src/extractors/pptx.rs +0 -433
- data/vendor/kreuzberg/src/extractors/pst.rs +0 -211
- data/vendor/kreuzberg/src/extractors/rst.rs +0 -1531
- data/vendor/kreuzberg/src/extractors/rtf/encoding.rs +0 -161
- data/vendor/kreuzberg/src/extractors/rtf/formatting.rs +0 -235
- data/vendor/kreuzberg/src/extractors/rtf/images.rs +0 -134
- data/vendor/kreuzberg/src/extractors/rtf/metadata.rs +0 -207
- data/vendor/kreuzberg/src/extractors/rtf/mod.rs +0 -771
- data/vendor/kreuzberg/src/extractors/rtf/parser.rs +0 -1772
- data/vendor/kreuzberg/src/extractors/rtf/tables.rs +0 -90
- data/vendor/kreuzberg/src/extractors/security.rs +0 -485
- data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
- data/vendor/kreuzberg/src/extractors/structured.rs +0 -251
- data/vendor/kreuzberg/src/extractors/text.rs +0 -164
- data/vendor/kreuzberg/src/extractors/typst.rs +0 -1130
- data/vendor/kreuzberg/src/extractors/xml.rs +0 -263
- data/vendor/kreuzberg/src/image/dpi.rs +0 -164
- data/vendor/kreuzberg/src/image/mod.rs +0 -6
- data/vendor/kreuzberg/src/image/preprocessing.rs +0 -417
- data/vendor/kreuzberg/src/image/resize.rs +0 -89
- data/vendor/kreuzberg/src/keywords/config.rs +0 -166
- data/vendor/kreuzberg/src/keywords/mod.rs +0 -231
- data/vendor/kreuzberg/src/keywords/processor.rs +0 -231
- data/vendor/kreuzberg/src/keywords/rake.rs +0 -293
- data/vendor/kreuzberg/src/keywords/types.rs +0 -70
- data/vendor/kreuzberg/src/keywords/yake/context.rs +0 -54
- data/vendor/kreuzberg/src/keywords/yake/counter.rs +0 -41
- data/vendor/kreuzberg/src/keywords/yake/mod.rs +0 -532
- data/vendor/kreuzberg/src/keywords/yake/plural_helper.rs +0 -40
- data/vendor/kreuzberg/src/keywords/yake/preprocessor.rs +0 -331
- data/vendor/kreuzberg/src/keywords/yake/result_item.rs +0 -111
- data/vendor/kreuzberg/src/keywords/yake/stats.rs +0 -102
- data/vendor/kreuzberg/src/keywords/yake/tag.rs +0 -171
- data/vendor/kreuzberg/src/language_detection/mod.rs +0 -979
- data/vendor/kreuzberg/src/language_detection/processor.rs +0 -193
- data/vendor/kreuzberg/src/layout/engine.rs +0 -276
- data/vendor/kreuzberg/src/layout/error.rs +0 -15
- data/vendor/kreuzberg/src/layout/inference_timings.rs +0 -40
- data/vendor/kreuzberg/src/layout/mod.rs +0 -221
- data/vendor/kreuzberg/src/layout/model_manager.rs +0 -325
- data/vendor/kreuzberg/src/layout/models/mod.rs +0 -43
- data/vendor/kreuzberg/src/layout/models/rtdetr.rs +0 -350
- data/vendor/kreuzberg/src/layout/models/slanet.rs +0 -491
- data/vendor/kreuzberg/src/layout/models/table_classifier.rs +0 -192
- data/vendor/kreuzberg/src/layout/models/tatr.rs +0 -1024
- data/vendor/kreuzberg/src/layout/models/yolo.rs +0 -330
- data/vendor/kreuzberg/src/layout/postprocessing/heuristics.rs +0 -169
- data/vendor/kreuzberg/src/layout/postprocessing/mod.rs +0 -2
- data/vendor/kreuzberg/src/layout/postprocessing/nms.rs +0 -35
- data/vendor/kreuzberg/src/layout/preprocessing.rs +0 -159
- data/vendor/kreuzberg/src/layout/session.rs +0 -38
- data/vendor/kreuzberg/src/layout/types.rs +0 -269
- data/vendor/kreuzberg/src/lib.rs +0 -191
- data/vendor/kreuzberg/src/llm/client.rs +0 -59
- data/vendor/kreuzberg/src/llm/mod.rs +0 -17
- data/vendor/kreuzberg/src/llm/prompts.rs +0 -52
- data/vendor/kreuzberg/src/llm/structured.rs +0 -189
- data/vendor/kreuzberg/src/llm/usage.rs +0 -40
- data/vendor/kreuzberg/src/llm/vlm_embeddings.rs +0 -113
- data/vendor/kreuzberg/src/llm/vlm_ocr.rs +0 -225
- data/vendor/kreuzberg/src/mcp/errors.rs +0 -353
- data/vendor/kreuzberg/src/mcp/format.rs +0 -315
- data/vendor/kreuzberg/src/mcp/mod.rs +0 -49
- data/vendor/kreuzberg/src/mcp/params.rs +0 -407
- data/vendor/kreuzberg/src/mcp/server.rs +0 -1458
- data/vendor/kreuzberg/src/model_cache.rs +0 -76
- data/vendor/kreuzberg/src/model_download.rs +0 -72
- data/vendor/kreuzberg/src/ocr/backends/easyocr.rs +0 -96
- data/vendor/kreuzberg/src/ocr/backends/mod.rs +0 -7
- data/vendor/kreuzberg/src/ocr/backends/paddleocr.rs +0 -27
- data/vendor/kreuzberg/src/ocr/backends/tesseract.rs +0 -134
- data/vendor/kreuzberg/src/ocr/cache.rs +0 -492
- data/vendor/kreuzberg/src/ocr/conversion.rs +0 -545
- data/vendor/kreuzberg/src/ocr/error.rs +0 -37
- data/vendor/kreuzberg/src/ocr/hocr_parser.rs +0 -1185
- data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -296
- data/vendor/kreuzberg/src/ocr/layout_assembly.rs +0 -1053
- data/vendor/kreuzberg/src/ocr/mod.rs +0 -69
- data/vendor/kreuzberg/src/ocr/processor/config.rs +0 -201
- data/vendor/kreuzberg/src/ocr/processor/execution.rs +0 -1439
- data/vendor/kreuzberg/src/ocr/processor/mod.rs +0 -299
- data/vendor/kreuzberg/src/ocr/processor/validation.rs +0 -291
- data/vendor/kreuzberg/src/ocr/table/mod.rs +0 -8
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +0 -144
- data/vendor/kreuzberg/src/ocr/tessdata_manager.rs +0 -244
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -546
- data/vendor/kreuzberg/src/ocr/types.rs +0 -410
- data/vendor/kreuzberg/src/ocr/utils.rs +0 -43
- data/vendor/kreuzberg/src/ocr/validation.rs +0 -218
- data/vendor/kreuzberg/src/ort_discovery.rs +0 -213
- data/vendor/kreuzberg/src/paddle_ocr/backend.rs +0 -846
- data/vendor/kreuzberg/src/paddle_ocr/config.rs +0 -580
- data/vendor/kreuzberg/src/paddle_ocr/mod.rs +0 -141
- data/vendor/kreuzberg/src/paddle_ocr/model_manager.rs +0 -1099
- data/vendor/kreuzberg/src/panic_context.rs +0 -154
- data/vendor/kreuzberg/src/pdf/annotations.rs +0 -171
- data/vendor/kreuzberg/src/pdf/bindings.rs +0 -322
- data/vendor/kreuzberg/src/pdf/bookmarks.rs +0 -232
- data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
- data/vendor/kreuzberg/src/pdf/embedded_files.rs +0 -230
- data/vendor/kreuzberg/src/pdf/error.rs +0 -235
- data/vendor/kreuzberg/src/pdf/fonts.rs +0 -360
- data/vendor/kreuzberg/src/pdf/hierarchy/bounding_box.rs +0 -288
- data/vendor/kreuzberg/src/pdf/hierarchy/clustering.rs +0 -370
- data/vendor/kreuzberg/src/pdf/hierarchy/extraction.rs +0 -732
- data/vendor/kreuzberg/src/pdf/hierarchy/mod.rs +0 -18
- data/vendor/kreuzberg/src/pdf/images.rs +0 -830
- data/vendor/kreuzberg/src/pdf/layout_runner.rs +0 -732
- data/vendor/kreuzberg/src/pdf/metadata.rs +0 -527
- data/vendor/kreuzberg/src/pdf/mod.rs +0 -96
- data/vendor/kreuzberg/src/pdf/rendering.rs +0 -767
- data/vendor/kreuzberg/src/pdf/structure/adapters.rs +0 -587
- data/vendor/kreuzberg/src/pdf/structure/assembly.rs +0 -860
- data/vendor/kreuzberg/src/pdf/structure/bridge.rs +0 -1265
- data/vendor/kreuzberg/src/pdf/structure/classify.rs +0 -1925
- data/vendor/kreuzberg/src/pdf/structure/columns.rs +0 -176
- data/vendor/kreuzberg/src/pdf/structure/constants.rs +0 -24
- data/vendor/kreuzberg/src/pdf/structure/content.rs +0 -72
- data/vendor/kreuzberg/src/pdf/structure/content_convert.rs +0 -967
- data/vendor/kreuzberg/src/pdf/structure/geometry.rs +0 -278
- data/vendor/kreuzberg/src/pdf/structure/layout_classify.rs +0 -889
- data/vendor/kreuzberg/src/pdf/structure/lines.rs +0 -52
- data/vendor/kreuzberg/src/pdf/structure/mod.rs +0 -28
- data/vendor/kreuzberg/src/pdf/structure/paragraphs.rs +0 -452
- data/vendor/kreuzberg/src/pdf/structure/pipeline.rs +0 -2194
- data/vendor/kreuzberg/src/pdf/structure/regions/heading.rs +0 -49
- data/vendor/kreuzberg/src/pdf/structure/regions/layout_validation.rs +0 -138
- data/vendor/kreuzberg/src/pdf/structure/regions/mod.rs +0 -16
- data/vendor/kreuzberg/src/pdf/structure/regions/table_recognition.rs +0 -669
- data/vendor/kreuzberg/src/pdf/structure/regions/tables.rs +0 -408
- data/vendor/kreuzberg/src/pdf/structure/text_repair.rs +0 -1289
- data/vendor/kreuzberg/src/pdf/structure/types.rs +0 -83
- data/vendor/kreuzberg/src/pdf/table.rs +0 -398
- data/vendor/kreuzberg/src/pdf/table_reconstruct.rs +0 -1295
- data/vendor/kreuzberg/src/pdf/text.rs +0 -801
- data/vendor/kreuzberg/src/pdf/text_data.rs +0 -48
- data/vendor/kreuzberg/src/plugins/extractor/instrumented.rs +0 -164
- data/vendor/kreuzberg/src/plugins/extractor/mod.rs +0 -315
- data/vendor/kreuzberg/src/plugins/extractor/registry.rs +0 -406
- data/vendor/kreuzberg/src/plugins/extractor/trait.rs +0 -198
- data/vendor/kreuzberg/src/plugins/mod.rs +0 -200
- data/vendor/kreuzberg/src/plugins/ocr.rs +0 -630
- data/vendor/kreuzberg/src/plugins/processor/mod.rs +0 -310
- data/vendor/kreuzberg/src/plugins/processor/registry.rs +0 -35
- data/vendor/kreuzberg/src/plugins/processor/trait.rs +0 -284
- data/vendor/kreuzberg/src/plugins/registry/extractor.rs +0 -650
- data/vendor/kreuzberg/src/plugins/registry/mod.rs +0 -119
- data/vendor/kreuzberg/src/plugins/registry/ocr.rs +0 -518
- data/vendor/kreuzberg/src/plugins/registry/processor.rs +0 -512
- data/vendor/kreuzberg/src/plugins/registry/renderer.rs +0 -361
- data/vendor/kreuzberg/src/plugins/registry/validator.rs +0 -454
- data/vendor/kreuzberg/src/plugins/renderer.rs +0 -199
- data/vendor/kreuzberg/src/plugins/startup_validation.rs +0 -363
- data/vendor/kreuzberg/src/plugins/traits.rs +0 -258
- data/vendor/kreuzberg/src/plugins/validator/mod.rs +0 -348
- data/vendor/kreuzberg/src/plugins/validator/registry.rs +0 -347
- data/vendor/kreuzberg/src/plugins/validator/trait.rs +0 -276
- data/vendor/kreuzberg/src/rendering/common.rs +0 -779
- data/vendor/kreuzberg/src/rendering/comrak_bridge.rs +0 -1205
- data/vendor/kreuzberg/src/rendering/djot.rs +0 -889
- data/vendor/kreuzberg/src/rendering/html.rs +0 -23
- data/vendor/kreuzberg/src/rendering/html_styled.rs +0 -652
- data/vendor/kreuzberg/src/rendering/json.rs +0 -547
- data/vendor/kreuzberg/src/rendering/markdown.rs +0 -136
- data/vendor/kreuzberg/src/rendering/mod.rs +0 -25
- data/vendor/kreuzberg/src/rendering/plain.rs +0 -427
- data/vendor/kreuzberg/src/service/extraction.rs +0 -118
- data/vendor/kreuzberg/src/service/layers/metrics.rs +0 -79
- data/vendor/kreuzberg/src/service/layers/mod.rs +0 -6
- data/vendor/kreuzberg/src/service/layers/tracing.rs +0 -97
- data/vendor/kreuzberg/src/service/mod.rs +0 -240
- data/vendor/kreuzberg/src/service/request.rs +0 -117
- data/vendor/kreuzberg/src/stopwords/languages/asian.rs +0 -40
- data/vendor/kreuzberg/src/stopwords/languages/germanic.rs +0 -36
- data/vendor/kreuzberg/src/stopwords/languages/mod.rs +0 -10
- data/vendor/kreuzberg/src/stopwords/languages/other.rs +0 -44
- data/vendor/kreuzberg/src/stopwords/languages/romance.rs +0 -36
- data/vendor/kreuzberg/src/stopwords/languages/slavic.rs +0 -36
- data/vendor/kreuzberg/src/stopwords/mod.rs +0 -1444
- data/vendor/kreuzberg/src/table_core.rs +0 -458
- data/vendor/kreuzberg/src/telemetry/conventions.rs +0 -177
- data/vendor/kreuzberg/src/telemetry/metrics.rs +0 -110
- data/vendor/kreuzberg/src/telemetry/mod.rs +0 -20
- data/vendor/kreuzberg/src/telemetry/spans.rs +0 -79
- data/vendor/kreuzberg/src/text/mod.rs +0 -27
- data/vendor/kreuzberg/src/text/quality.rs +0 -714
- data/vendor/kreuzberg/src/text/quality_processor.rs +0 -202
- data/vendor/kreuzberg/src/text/string_utils.rs +0 -1
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +0 -164
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +0 -100
- data/vendor/kreuzberg/src/text/token_reduction/core/analysis.rs +0 -238
- data/vendor/kreuzberg/src/text/token_reduction/core/mod.rs +0 -7
- data/vendor/kreuzberg/src/text/token_reduction/core/punctuation.rs +0 -54
- data/vendor/kreuzberg/src/text/token_reduction/core/reducer.rs +0 -402
- data/vendor/kreuzberg/src/text/token_reduction/core/sentence_selection.rs +0 -68
- data/vendor/kreuzberg/src/text/token_reduction/core/word_filtering.rs +0 -156
- data/vendor/kreuzberg/src/text/token_reduction/filters/general.rs +0 -369
- data/vendor/kreuzberg/src/text/token_reduction/filters/html.rs +0 -51
- data/vendor/kreuzberg/src/text/token_reduction/filters/markdown.rs +0 -253
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +0 -796
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +0 -160
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +0 -592
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +0 -148
- data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
- data/vendor/kreuzberg/src/types/annotations.rs +0 -41
- data/vendor/kreuzberg/src/types/builder.rs +0 -920
- data/vendor/kreuzberg/src/types/djot.rs +0 -219
- data/vendor/kreuzberg/src/types/document_structure.rs +0 -1202
- data/vendor/kreuzberg/src/types/extraction.rs +0 -599
- data/vendor/kreuzberg/src/types/formats.rs +0 -472
- data/vendor/kreuzberg/src/types/internal.rs +0 -580
- data/vendor/kreuzberg/src/types/internal_builder.rs +0 -1048
- data/vendor/kreuzberg/src/types/metadata.rs +0 -845
- data/vendor/kreuzberg/src/types/mod.rs +0 -475
- data/vendor/kreuzberg/src/types/ocr_elements.rs +0 -487
- data/vendor/kreuzberg/src/types/page.rs +0 -231
- data/vendor/kreuzberg/src/types/serde_helpers.rs +0 -70
- data/vendor/kreuzberg/src/types/tables.rs +0 -155
- data/vendor/kreuzberg/src/types/uri.rs +0 -173
- data/vendor/kreuzberg/src/utils/image_decode.rs +0 -96
- data/vendor/kreuzberg/src/utils/json_utils.rs +0 -135
- data/vendor/kreuzberg/src/utils/markdown_utils.rs +0 -40
- data/vendor/kreuzberg/src/utils/mod.rs +0 -94
- data/vendor/kreuzberg/src/utils/pool.rs +0 -503
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
- data/vendor/kreuzberg/src/utils/quality/heuristics.rs +0 -53
- data/vendor/kreuzberg/src/utils/quality/mod.rs +0 -627
- data/vendor/kreuzberg/src/utils/quality/patterns.rs +0 -99
- data/vendor/kreuzberg/src/utils/quality/scoring.rs +0 -166
- data/vendor/kreuzberg/src/utils/string_pool/buffer_pool.rs +0 -303
- data/vendor/kreuzberg/src/utils/string_pool/interned.rs +0 -102
- data/vendor/kreuzberg/src/utils/string_pool/language_pool.rs +0 -119
- data/vendor/kreuzberg/src/utils/string_pool/mime_pool.rs +0 -233
- data/vendor/kreuzberg/src/utils/string_pool/mod.rs +0 -40
- data/vendor/kreuzberg/src/utils/string_utils.rs +0 -381
- data/vendor/kreuzberg/src/utils/timing.rs +0 -59
- data/vendor/kreuzberg/src/utils/xml_utils.rs +0 -7
- data/vendor/kreuzberg/stopwords/af_stopwords.json +0 -53
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +0 -482
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +0 -261
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +0 -400
- data/vendor/kreuzberg/stopwords/br_stopwords.json +0 -1205
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +0 -280
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +0 -425
- data/vendor/kreuzberg/stopwords/da_stopwords.json +0 -172
- data/vendor/kreuzberg/stopwords/de_stopwords.json +0 -622
- data/vendor/kreuzberg/stopwords/el_stopwords.json +0 -849
- data/vendor/kreuzberg/stopwords/en_stopwords.json +0 -1300
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +0 -175
- data/vendor/kreuzberg/stopwords/es_stopwords.json +0 -734
- data/vendor/kreuzberg/stopwords/et_stopwords.json +0 -37
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +0 -100
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +0 -801
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +0 -849
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +0 -693
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +0 -111
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +0 -162
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +0 -226
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +0 -41
- data/vendor/kreuzberg/stopwords/he_stopwords.json +0 -196
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +0 -227
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +0 -181
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +0 -791
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +0 -47
- data/vendor/kreuzberg/stopwords/id_stopwords.json +0 -760
- data/vendor/kreuzberg/stopwords/it_stopwords.json +0 -634
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +0 -136
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +0 -84
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +0 -681
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +0 -64
- data/vendor/kreuzberg/stopwords/la_stopwords.json +0 -51
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +0 -476
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +0 -163
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +0 -1
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +0 -101
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +0 -477
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +0 -490
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +0 -415
- data/vendor/kreuzberg/stopwords/no_stopwords.json +0 -223
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +0 -331
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +0 -562
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +0 -436
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +0 -561
- data/vendor/kreuzberg/stopwords/si_stopwords.json +0 -193
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +0 -420
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +0 -448
- data/vendor/kreuzberg/stopwords/so_stopwords.json +0 -32
- data/vendor/kreuzberg/stopwords/st_stopwords.json +0 -33
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +0 -420
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +0 -76
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +0 -129
- data/vendor/kreuzberg/stopwords/te_stopwords.json +0 -54
- data/vendor/kreuzberg/stopwords/th_stopwords.json +0 -118
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +0 -149
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +0 -506
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +0 -75
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +0 -519
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +0 -647
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +0 -62
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +0 -796
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +0 -31
- data/vendor/kreuzberg/test_data/hocr/english_pdf_default.hocr +0 -97
- data/vendor/kreuzberg/test_data/hocr/german_pdf_default.hocr +0 -492
- data/vendor/kreuzberg/test_data/hocr/invoice_image_default.hocr +0 -72
- data/vendor/kreuzberg/test_data/hocr/utf8_encoding.hocr +0 -12
- data/vendor/kreuzberg/test_data/hocr/v4_code_formula.hocr +0 -541
- data/vendor/kreuzberg/test_data/hocr/v4_embedded_tables.hocr +0 -420
- data/vendor/kreuzberg/test_data/hocr/word_confidence.hocr +0 -21
- data/vendor/kreuzberg/test_documents/jsonl/simple.jsonl +0 -3
- data/vendor/kreuzberg/test_documents/jsonl/with_blanks.jsonl +0 -5
- data/vendor/kreuzberg/tests/api_chunk.rs +0 -340
- data/vendor/kreuzberg/tests/api_consistency.rs +0 -579
- data/vendor/kreuzberg/tests/api_embed.rs +0 -444
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +0 -471
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +0 -295
- data/vendor/kreuzberg/tests/api_openweb.rs +0 -325
- data/vendor/kreuzberg/tests/api_tests.rs +0 -1714
- data/vendor/kreuzberg/tests/archive_integration.rs +0 -552
- data/vendor/kreuzberg/tests/batch_orchestration.rs +0 -612
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
- data/vendor/kreuzberg/tests/batch_processing.rs +0 -346
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -456
- data/vendor/kreuzberg/tests/concurrency_stress.rs +0 -546
- data/vendor/kreuzberg/tests/config_behavioral.rs +0 -394
- data/vendor/kreuzberg/tests/config_features.rs +0 -738
- data/vendor/kreuzberg/tests/config_integration_test.rs +0 -649
- data/vendor/kreuzberg/tests/config_loading_tests.rs +0 -427
- data/vendor/kreuzberg/tests/contract_mcp.rs +0 -289
- data/vendor/kreuzberg/tests/core_integration.rs +0 -521
- data/vendor/kreuzberg/tests/cross_format_parity.rs +0 -1230
- data/vendor/kreuzberg/tests/csv_embedding_quality.rs +0 -138
- data/vendor/kreuzberg/tests/csv_integration.rs +0 -474
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -502
- data/vendor/kreuzberg/tests/docx_formatting_test.rs +0 -326
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +0 -236
- data/vendor/kreuzberg/tests/docx_mime_detection_test.rs +0 -73
- data/vendor/kreuzberg/tests/docx_ocr_integration_test.rs +0 -73
- data/vendor/kreuzberg/tests/email_integration.rs +0 -495
- data/vendor/kreuzberg/tests/epub_markdown_headings_tests.rs +0 -183
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -274
- data/vendor/kreuzberg/tests/epub_spine_semantics_tests.rs +0 -721
- data/vendor/kreuzberg/tests/error_handling.rs +0 -404
- data/vendor/kreuzberg/tests/extraction_timeout_tests.rs +0 -114
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -257
- data/vendor/kreuzberg/tests/format_integration.rs +0 -165
- data/vendor/kreuzberg/tests/gpu_acceleration.rs +0 -394
- data/vendor/kreuzberg/tests/helpers/mod.rs +0 -204
- data/vendor/kreuzberg/tests/html_output_quality.rs +0 -218
- data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
- data/vendor/kreuzberg/tests/image_integration.rs +0 -255
- data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -144
- data/vendor/kreuzberg/tests/issue_350_regression_test.rs +0 -42
- data/vendor/kreuzberg/tests/issue_359_list_whitespace_test.rs +0 -33
- data/vendor/kreuzberg/tests/issue_670_content_filter_layout_regression.rs +0 -146
- data/vendor/kreuzberg/tests/issue_671_pptx_image_config_regression.rs +0 -159
- data/vendor/kreuzberg/tests/issue_797_preset_embedding_regression.rs +0 -74
- data/vendor/kreuzberg/tests/iwork_integration.rs +0 -204
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -692
- data/vendor/kreuzberg/tests/json_schema_validation.rs +0 -163
- data/vendor/kreuzberg/tests/jsonl_integration.rs +0 -81
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
- data/vendor/kreuzberg/tests/keywords_integration.rs +0 -479
- data/vendor/kreuzberg/tests/keywords_quality.rs +0 -509
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -512
- data/vendor/kreuzberg/tests/llm_integration.rs +0 -280
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -513
- data/vendor/kreuzberg/tests/markdown_lint_quality.rs +0 -226
- data/vendor/kreuzberg/tests/mcp_integration.rs +0 -797
- data/vendor/kreuzberg/tests/mime_detection.rs +0 -460
- data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -525
- data/vendor/kreuzberg/tests/ocr_content_integrity.rs +0 -140
- data/vendor/kreuzberg/tests/ocr_errors.rs +0 -713
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
- data/vendor/kreuzberg/tests/ocr_quality.rs +0 -632
- data/vendor/kreuzberg/tests/ocr_stress.rs +0 -469
- data/vendor/kreuzberg/tests/ocr_table_inline.rs +0 -271
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -677
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -826
- data/vendor/kreuzberg/tests/paddle_ocr_integration.rs +0 -780
- data/vendor/kreuzberg/tests/paddle_ocr_multilang.rs +0 -551
- data/vendor/kreuzberg/tests/page_markers.rs +0 -392
- data/vendor/kreuzberg/tests/path_resolution/fixtures/djot_with_images.djot +0 -9
- data/vendor/kreuzberg/tests/path_resolution/fixtures/images/subfolder/nested.png +0 -0
- data/vendor/kreuzberg/tests/path_resolution/fixtures/images/test_image.png +0 -0
- data/vendor/kreuzberg/tests/path_resolution/fixtures/latex_with_images.tex +0 -15
- data/vendor/kreuzberg/tests/path_resolution/fixtures/markdown_with_images.md +0 -13
- data/vendor/kreuzberg/tests/path_resolution/fixtures/orgmode_with_images.org +0 -9
- data/vendor/kreuzberg/tests/path_resolution/fixtures/rst_with_images.rst +0 -12
- data/vendor/kreuzberg/tests/path_resolution/fixtures/typst_with_images.typ +0 -9
- data/vendor/kreuzberg/tests/path_resolution.rs +0 -127
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -297
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -565
- data/vendor/kreuzberg/tests/pdf_image_extraction_tests.rs +0 -265
- data/vendor/kreuzberg/tests/pdf_integration.rs +0 -106
- data/vendor/kreuzberg/tests/pdf_markdown_extraction.rs +0 -167
- data/vendor/kreuzberg/tests/pdf_markdown_quality.rs +0 -152
- data/vendor/kreuzberg/tests/pdf_markdown_regression.rs +0 -786
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -288
- data/vendor/kreuzberg/tests/pdf_output_quality.rs +0 -185
- data/vendor/kreuzberg/tests/pdf_table_detection.rs +0 -281
- data/vendor/kreuzberg/tests/pdf_table_ground_truth.rs +0 -380
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -431
- data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
- data/vendor/kreuzberg/tests/pipeline_integration.rs +0 -1203
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -1061
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +0 -597
- data/vendor/kreuzberg/tests/plugin_system.rs +0 -900
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +0 -795
- data/vendor/kreuzberg/tests/pptx_regression_tests.rs +0 -750
- data/vendor/kreuzberg/tests/pst_integration.rs +0 -81
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +0 -590
- data/vendor/kreuzberg/tests/rendering_integration_tests.rs +0 -339
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -833
- data/vendor/kreuzberg/tests/security_validation.rs +0 -417
- data/vendor/kreuzberg/tests/serialization_integration.rs +0 -100
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +0 -888
- data/vendor/kreuzberg/tests/test_batch_extract_schema.rs +0 -51
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1244
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -645
- data/vendor/kreuzberg/tests/xlsb_extraction_test.rs +0 -44
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +0 -177
- data/vendor/kreuzberg/tests/xml_embedding_quality.rs +0 -134
- data/vendor/kreuzberg-ffi/Cargo.toml +0 -50
- data/vendor/kreuzberg-ffi/README.md +0 -971
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -228
- data/vendor/kreuzberg-ffi/build.rs +0 -195
- data/vendor/kreuzberg-ffi/cbindgen.toml +0 -57
- data/vendor/kreuzberg-ffi/cmake/kreuzberg-ffi-config-version.cmake +0 -25
- data/vendor/kreuzberg-ffi/cmake/kreuzberg-ffi-config.cmake +0 -105
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3848
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -602
- data/vendor/kreuzberg-ffi/src/cancellation.rs +0 -164
- data/vendor/kreuzberg-ffi/src/config/html.rs +0 -297
- data/vendor/kreuzberg-ffi/src/config/loader.rs +0 -175
- data/vendor/kreuzberg-ffi/src/config/merge.rs +0 -114
- data/vendor/kreuzberg-ffi/src/config/mod.rs +0 -384
- data/vendor/kreuzberg-ffi/src/config/parse.rs +0 -90
- data/vendor/kreuzberg-ffi/src/config/serialize.rs +0 -120
- data/vendor/kreuzberg-ffi/src/config_builder.rs +0 -1121
- data/vendor/kreuzberg-ffi/src/embedding.rs +0 -94
- data/vendor/kreuzberg-ffi/src/error.rs +0 -1039
- data/vendor/kreuzberg-ffi/src/extraction.rs +0 -583
- data/vendor/kreuzberg-ffi/src/helpers.rs +0 -708
- data/vendor/kreuzberg-ffi/src/html_options.rs +0 -421
- data/vendor/kreuzberg-ffi/src/lib.rs +0 -978
- data/vendor/kreuzberg-ffi/src/memory.rs +0 -588
- data/vendor/kreuzberg-ffi/src/mime.rs +0 -328
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -278
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -435
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -13
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -621
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -415
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -307
- data/vendor/kreuzberg-ffi/src/rendering.rs +0 -325
- data/vendor/kreuzberg-ffi/src/result.rs +0 -609
- data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -649
- data/vendor/kreuzberg-ffi/src/result_view.rs +0 -768
- data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -572
- data/vendor/kreuzberg-ffi/src/types.rs +0 -394
- data/vendor/kreuzberg-ffi/src/util.rs +0 -207
- data/vendor/kreuzberg-ffi/src/validation.rs +0 -908
- data/vendor/kreuzberg-ffi/tests/c/.gitignore +0 -5
- data/vendor/kreuzberg-ffi/tests/c/Makefile +0 -83
- data/vendor/kreuzberg-ffi/tests/c/run_tests.sh +0 -32
- data/vendor/kreuzberg-ffi/tests/c/test_batch.c +0 -101
- data/vendor/kreuzberg-ffi/tests/c/test_concurrent.c +0 -111
- data/vendor/kreuzberg-ffi/tests/c/test_config.c +0 -56
- data/vendor/kreuzberg-ffi/tests/c/test_config_builder.c +0 -67
- data/vendor/kreuzberg-ffi/tests/c/test_error.c +0 -40
- data/vendor/kreuzberg-ffi/tests/c/test_error_extended.c +0 -135
- data/vendor/kreuzberg-ffi/tests/c/test_extraction.c +0 -53
- data/vendor/kreuzberg-ffi/tests/c/test_html_options.c +0 -114
- data/vendor/kreuzberg-ffi/tests/c/test_mime.c +0 -52
- data/vendor/kreuzberg-ffi/tests/c/test_plugins.c +0 -224
- data/vendor/kreuzberg-ffi/tests/c/test_plugins_errors.c +0 -181
- data/vendor/kreuzberg-ffi/tests/c/test_result_inspect.c +0 -92
- data/vendor/kreuzberg-ffi/tests/c/test_result_pool.c +0 -81
- data/vendor/kreuzberg-ffi/tests/c/test_string_intern.c +0 -45
- data/vendor/kreuzberg-ffi/tests/c/test_validation.c +0 -76
- data/vendor/kreuzberg-ffi/tests/c/test_version.c +0 -20
- 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
- data/vendor/kreuzberg-paddle-ocr/Cargo.toml +0 -41
- data/vendor/kreuzberg-paddle-ocr/LICENSE +0 -22
- data/vendor/kreuzberg-paddle-ocr/README.md +0 -55
- data/vendor/kreuzberg-paddle-ocr/src/angle_net.rs +0 -132
- data/vendor/kreuzberg-paddle-ocr/src/base_net.rs +0 -74
- data/vendor/kreuzberg-paddle-ocr/src/constants.rs +0 -33
- data/vendor/kreuzberg-paddle-ocr/src/crnn_net.rs +0 -357
- data/vendor/kreuzberg-paddle-ocr/src/db_net.rs +0 -411
- data/vendor/kreuzberg-paddle-ocr/src/lib.rs +0 -32
- data/vendor/kreuzberg-paddle-ocr/src/ocr_error.rs +0 -13
- data/vendor/kreuzberg-paddle-ocr/src/ocr_lite.rs +0 -437
- data/vendor/kreuzberg-paddle-ocr/src/ocr_result.rs +0 -104
- data/vendor/kreuzberg-paddle-ocr/src/ocr_utils.rs +0 -194
- data/vendor/kreuzberg-paddle-ocr/src/scale_param.rs +0 -69
- data/vendor/kreuzberg-paddle-ocr/tests/diagnostic.rs +0 -413
- data/vendor/kreuzberg-pdfium-render/Cargo.toml +0 -65
- data/vendor/kreuzberg-pdfium-render/LICENSE +0 -22
- data/vendor/kreuzberg-pdfium-render/README.md +0 -17
- data/vendor/kreuzberg-pdfium-render/build.rs +0 -169
- data/vendor/kreuzberg-pdfium-render/config.toml +0 -4
- data/vendor/kreuzberg-pdfium-render/include/pdfium_7678/rust-import-wrapper.h +0 -0
- data/vendor/kreuzberg-pdfium-render/src/bindgen/pdfium_7678.rs +0 -4976
- data/vendor/kreuzberg-pdfium-render/src/bindings/dynamic_bindings.rs +0 -5539
- data/vendor/kreuzberg-pdfium-render/src/bindings/static_bindings.rs +0 -3832
- data/vendor/kreuzberg-pdfium-render/src/bindings/version.rs +0 -14
- data/vendor/kreuzberg-pdfium-render/src/bindings/wasm_bindings.rs +0 -14993
- data/vendor/kreuzberg-pdfium-render/src/bindings.rs +0 -8081
- data/vendor/kreuzberg-pdfium-render/src/error.rs +0 -239
- data/vendor/kreuzberg-pdfium-render/src/font_provider.rs +0 -358
- data/vendor/kreuzberg-pdfium-render/src/lib.rs +0 -317
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/embedded_destination.rs +0 -31
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/launch.rs +0 -31
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/local_destination.rs +0 -52
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/private.rs +0 -16
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/remote_destination.rs +0 -31
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/unsupported.rs +0 -31
- data/vendor/kreuzberg-pdfium-render/src/pdf/action/uri.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/action.rs +0 -307
- data/vendor/kreuzberg-pdfium-render/src/pdf/bitmap.rs +0 -389
- data/vendor/kreuzberg-pdfium-render/src/pdf/color.rs +0 -384
- data/vendor/kreuzberg-pdfium-render/src/pdf/color_space.rs +0 -162
- data/vendor/kreuzberg-pdfium-render/src/pdf/destination.rs +0 -268
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/fonts.rs +0 -552
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/form.rs +0 -185
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/metadata.rs +0 -165
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/attachment_points.rs +0 -171
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/circle.rs +0 -64
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/free_text.rs +0 -64
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/highlight.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/ink.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/link.rs +0 -106
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/objects.rs +0 -111
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/private.rs +0 -484
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/square.rs +0 -64
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/squiggly.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/stamp.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/strikeout.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/text.rs +0 -64
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/underline.rs +0 -70
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation/unsupported.rs +0 -75
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotation.rs +0 -1156
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/annotations.rs +0 -535
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/boundaries.rs +0 -320
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/extraction.rs +0 -787
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/index_cache.rs +0 -864
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/links.rs +0 -174
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/content_mark.rs +0 -165
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/content_marks.rs +0 -78
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/group.rs +0 -953
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/image.rs +0 -1008
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/ownership.rs +0 -135
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/path.rs +0 -967
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/private.rs +0 -498
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/shading.rs +0 -92
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/text.rs +0 -432
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/unsupported.rs +0 -93
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object/x_object_form.rs +0 -217
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/object.rs +0 -1363
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/objects/common.rs +0 -642
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/objects/private.rs +0 -32
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/objects.rs +0 -179
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/paragraph.rs +0 -808
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/render_config.rs +0 -873
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/size.rs +0 -510
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/struct_element.rs +0 -668
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/struct_tree.rs +0 -122
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text/char.rs +0 -572
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text/chars.rs +0 -164
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text/search.rs +0 -177
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text/segment.rs +0 -94
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text/segments.rs +0 -156
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page/text.rs +0 -626
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/page.rs +0 -1011
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/pages.rs +0 -657
- data/vendor/kreuzberg-pdfium-render/src/pdf/document/permissions.rs +0 -221
- data/vendor/kreuzberg-pdfium-render/src/pdf/document.rs +0 -354
- data/vendor/kreuzberg-pdfium-render/src/pdf/font/glyph.rs +0 -114
- data/vendor/kreuzberg-pdfium-render/src/pdf/font/glyphs.rs +0 -157
- data/vendor/kreuzberg-pdfium-render/src/pdf/font.rs +0 -1032
- data/vendor/kreuzberg-pdfium-render/src/pdf/link.rs +0 -135
- data/vendor/kreuzberg-pdfium-render/src/pdf/matrix.rs +0 -351
- data/vendor/kreuzberg-pdfium-render/src/pdf/path/clip_path.rs +0 -180
- data/vendor/kreuzberg-pdfium-render/src/pdf/path/segment.rs +0 -229
- data/vendor/kreuzberg-pdfium-render/src/pdf/path/segments.rs +0 -72
- data/vendor/kreuzberg-pdfium-render/src/pdf/path.rs +0 -3
- data/vendor/kreuzberg-pdfium-render/src/pdf/points.rs +0 -196
- data/vendor/kreuzberg-pdfium-render/src/pdf/quad_points.rs +0 -336
- data/vendor/kreuzberg-pdfium-render/src/pdf/rect.rs +0 -339
- data/vendor/kreuzberg-pdfium-render/src/pdf/transform.rs +0 -440
- data/vendor/kreuzberg-pdfium-render/src/pdf.rs +0 -14
- data/vendor/kreuzberg-pdfium-render/src/pdfium.rs +0 -550
- data/vendor/kreuzberg-pdfium-render/src/utils.rs +0 -546
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +0 -13
- data/vendor/kreuzberg-tesseract/.crate-ignore +0 -2
- data/vendor/kreuzberg-tesseract/Cargo.lock +0 -2933
- data/vendor/kreuzberg-tesseract/Cargo.toml +0 -61
- data/vendor/kreuzberg-tesseract/LICENSE +0 -22
- data/vendor/kreuzberg-tesseract/README.md +0 -403
- data/vendor/kreuzberg-tesseract/build.rs +0 -1727
- data/vendor/kreuzberg-tesseract/patches/README.md +0 -74
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
- data/vendor/kreuzberg-tesseract/src/api.rs +0 -1903
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
- data/vendor/kreuzberg-tesseract/src/enums.rs +0 -373
- data/vendor/kreuzberg-tesseract/src/error.rs +0 -85
- data/vendor/kreuzberg-tesseract/src/leptonica.rs +0 -713
- data/vendor/kreuzberg-tesseract/src/lib.rs +0 -193
- data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -68
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -406
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -474
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -212
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 1a69253c4b216e8cde6ee74a09384688fb16d3d6feffc038f6ce08799aa8e4d1
|
|
4
|
+
data.tar.gz: 6341d37dc7bfe4073461b89ae53ec5ccb6924f95745190299a3809ed2e3514ec
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: c3127d63e11cd51f5b961d9ccc15b822af486f16ae3fc67cd651d3403f6192f6d12ea550070d2ce4c45bc2a0472e1e4ff930853315c03f6a32a91883e7ae7f59
|
|
7
|
+
data.tar.gz: 2b4a0bb3d9a44a2d66c7b58f4b91f2d51bd7ef59e5d0f69bd3561e012580c3548372f0ae007f9a9b07381509992bf01dca80116d3f828a3b54a44396e9c73e5d
|
data/Steepfile
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
target :lib do
|
|
4
|
+
signature "sig"
|
|
5
|
+
check "lib"
|
|
6
|
+
# The generated `lib/kreuzberg/native.rb` carries inline Sorbet
|
|
7
|
+
# `sig { ... }` blocks on tagged-enum variant Data classes. Sorbet's runtime
|
|
8
|
+
# provides those via `extend T::Sig`, but Steep does not understand the
|
|
9
|
+
# extension (it relies on RBS, not Sorbet sigs) and reports
|
|
10
|
+
# `Type `self` does not have method `sig`` on every block. RBS coverage
|
|
11
|
+
# for the same surface lives in `sig/types.rbs`, so we steer Steep to the
|
|
12
|
+
# RBS file by ignoring the .rb.
|
|
13
|
+
ignore "lib/kreuzberg/native.rb"
|
|
14
|
+
end
|
data/ext/kreuzberg_rb/extconf.rb
CHANGED
|
@@ -2,57 +2,10 @@
|
|
|
2
2
|
|
|
3
3
|
require "mkmf"
|
|
4
4
|
require "rb_sys/mkmf"
|
|
5
|
-
require "rbconfig"
|
|
6
|
-
require "fileutils"
|
|
7
|
-
|
|
8
|
-
if Gem.win_platform?
|
|
9
|
-
if ENV["CARGO_TARGET_DIR"]
|
|
10
|
-
puts("Windows detected: Using existing CARGO_TARGET_DIR=#{ENV["CARGO_TARGET_DIR"]}")
|
|
11
|
-
else
|
|
12
|
-
short_target_dir = Dir.exist?("C:/t") ? "C:/t" : "C:/kz-build"
|
|
13
|
-
begin
|
|
14
|
-
FileUtils.mkdir_p(short_target_dir)
|
|
15
|
-
ENV["CARGO_TARGET_DIR"] = short_target_dir
|
|
16
|
-
ENV["OUT_DIR"] = short_target_dir
|
|
17
|
-
puts("Windows detected: Using short build path #{short_target_dir}")
|
|
18
|
-
rescue StandardError => e
|
|
19
|
-
puts("Warning: Could not create short path #{short_target_dir}: #{e.message}")
|
|
20
|
-
end
|
|
21
|
-
end
|
|
22
|
-
end
|
|
23
|
-
|
|
24
|
-
if /mswin|mingw/.match?(RbConfig::CONFIG["host_os"])
|
|
25
|
-
devkit = ENV.fetch("RI_DEVKIT", nil)
|
|
26
|
-
prefix = ENV["MSYSTEM_PREFIX"] || "/ucrt64"
|
|
27
|
-
|
|
28
|
-
native_include = File.expand_path("native/include", __dir__).tr("\\", "/")
|
|
29
|
-
compat_include = File.expand_path("native/include/msvc_compat", __dir__).tr("\\", "/")
|
|
30
|
-
|
|
31
|
-
extra_args = []
|
|
32
|
-
extra_args << "-I#{native_include}"
|
|
33
|
-
extra_args << "-I#{compat_include}"
|
|
34
|
-
|
|
35
|
-
extra_args << "-fms-extensions"
|
|
36
|
-
extra_args << "-fno-omit-frame-pointer"
|
|
37
|
-
|
|
38
|
-
if devkit
|
|
39
|
-
sysroot = "#{devkit}#{prefix}".tr("\\", "/")
|
|
40
|
-
extra_args.push("--target=x86_64-pc-windows-gnu", "--sysroot=#{sysroot}")
|
|
41
|
-
end
|
|
42
|
-
|
|
43
|
-
unless extra_args.empty?
|
|
44
|
-
existing = ENV["BINDGEN_EXTRA_CLANG_ARGS"].to_s.split(/\s+/).reject(&:empty?)
|
|
45
|
-
ENV["BINDGEN_EXTRA_CLANG_ARGS"] = (existing + extra_args).uniq.join(" ")
|
|
46
|
-
puts("BINDGEN_EXTRA_CLANG_ARGS set to: #{ENV.fetch("BINDGEN_EXTRA_CLANG_ARGS", nil)}")
|
|
47
|
-
end
|
|
48
|
-
|
|
49
|
-
ENV["CARGO_BUILD_TARGET"] ||= "x86_64-pc-windows-gnu" if devkit || ENV["MSYSTEM"]
|
|
50
|
-
end
|
|
51
5
|
|
|
52
6
|
default_profile = ENV.fetch("CARGO_PROFILE", "release")
|
|
53
|
-
native_dir = "native"
|
|
54
7
|
|
|
55
8
|
create_rust_makefile("kreuzberg_rb") do |config|
|
|
56
9
|
config.profile = default_profile.to_sym
|
|
57
|
-
config.ext_dir =
|
|
10
|
+
config.ext_dir = "native"
|
|
58
11
|
end
|