kreuzberg 4.0.7 → 4.1.0
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/Gemfile.lock +24 -16
- data/README.md +4 -1
- data/ext/kreuzberg_rb/native/Cargo.lock +94 -98
- data/ext/kreuzberg_rb/native/Cargo.toml +4 -2
- data/ext/kreuzberg_rb/native/src/batch.rs +139 -0
- data/ext/kreuzberg_rb/native/src/config/mod.rs +10 -0
- data/ext/kreuzberg_rb/native/src/config/types.rs +1058 -0
- data/ext/kreuzberg_rb/native/src/error_handling.rs +125 -0
- data/ext/kreuzberg_rb/native/src/extraction.rs +79 -0
- data/ext/kreuzberg_rb/native/src/gc_guarded_value.rs +35 -0
- data/ext/kreuzberg_rb/native/src/helpers.rs +176 -0
- data/ext/kreuzberg_rb/native/src/lib.rs +342 -3622
- data/ext/kreuzberg_rb/native/src/metadata.rs +34 -0
- data/ext/kreuzberg_rb/native/src/plugins/mod.rs +92 -0
- data/ext/kreuzberg_rb/native/src/plugins/ocr_backend.rs +159 -0
- data/ext/kreuzberg_rb/native/src/plugins/post_processor.rs +126 -0
- data/ext/kreuzberg_rb/native/src/plugins/validator.rs +99 -0
- data/ext/kreuzberg_rb/native/src/result.rs +326 -0
- data/ext/kreuzberg_rb/native/src/validation.rs +4 -0
- data/lib/kreuzberg/config.rb +66 -0
- data/lib/kreuzberg/result.rb +107 -2
- data/lib/kreuzberg/types.rb +104 -0
- data/lib/kreuzberg/version.rb +1 -1
- data/lib/kreuzberg.rb +0 -4
- data/sig/kreuzberg.rbs +105 -1
- data/vendor/Cargo.toml +3 -3
- data/vendor/kreuzberg/Cargo.toml +4 -3
- data/vendor/kreuzberg/README.md +1 -1
- data/vendor/kreuzberg/src/api/config.rs +69 -0
- data/vendor/kreuzberg/src/api/handlers.rs +99 -2
- data/vendor/kreuzberg/src/api/mod.rs +14 -7
- data/vendor/kreuzberg/src/api/router.rs +214 -0
- data/vendor/kreuzberg/src/api/startup.rs +243 -0
- data/vendor/kreuzberg/src/api/types.rs +78 -0
- data/vendor/kreuzberg/src/cache/cleanup.rs +277 -0
- data/vendor/kreuzberg/src/cache/core.rs +428 -0
- data/vendor/kreuzberg/src/cache/mod.rs +21 -843
- data/vendor/kreuzberg/src/cache/utilities.rs +156 -0
- data/vendor/kreuzberg/src/chunking/boundaries.rs +301 -0
- data/vendor/kreuzberg/src/chunking/builder.rs +294 -0
- data/vendor/kreuzberg/src/chunking/config.rs +52 -0
- data/vendor/kreuzberg/src/chunking/core.rs +1017 -0
- data/vendor/kreuzberg/src/chunking/mod.rs +14 -2211
- data/vendor/kreuzberg/src/chunking/processor.rs +10 -0
- data/vendor/kreuzberg/src/chunking/validation.rs +686 -0
- data/vendor/kreuzberg/src/core/config/extraction/core.rs +169 -0
- data/vendor/kreuzberg/src/core/config/extraction/env.rs +179 -0
- data/vendor/kreuzberg/src/core/config/extraction/loaders.rs +204 -0
- data/vendor/kreuzberg/src/core/config/extraction/mod.rs +42 -0
- data/vendor/kreuzberg/src/core/config/extraction/types.rs +93 -0
- data/vendor/kreuzberg/src/core/config/formats.rs +135 -0
- data/vendor/kreuzberg/src/core/config/mod.rs +20 -0
- data/vendor/kreuzberg/src/core/config/ocr.rs +73 -0
- data/vendor/kreuzberg/src/core/config/page.rs +57 -0
- data/vendor/kreuzberg/src/core/config/pdf.rs +111 -0
- data/vendor/kreuzberg/src/core/config/processing.rs +312 -0
- data/vendor/kreuzberg/src/core/config_validation/dependencies.rs +187 -0
- data/vendor/kreuzberg/src/core/config_validation/mod.rs +386 -0
- data/vendor/kreuzberg/src/core/config_validation/sections.rs +401 -0
- data/vendor/kreuzberg/src/core/extractor/batch.rs +246 -0
- data/vendor/kreuzberg/src/core/extractor/bytes.rs +116 -0
- data/vendor/kreuzberg/src/core/extractor/file.rs +240 -0
- data/vendor/kreuzberg/src/core/extractor/helpers.rs +71 -0
- data/vendor/kreuzberg/src/core/extractor/legacy.rs +62 -0
- data/vendor/kreuzberg/src/core/extractor/mod.rs +490 -0
- data/vendor/kreuzberg/src/core/extractor/sync.rs +208 -0
- data/vendor/kreuzberg/src/core/mod.rs +4 -1
- data/vendor/kreuzberg/src/core/pipeline/cache.rs +60 -0
- data/vendor/kreuzberg/src/core/pipeline/execution.rs +89 -0
- data/vendor/kreuzberg/src/core/pipeline/features.rs +108 -0
- data/vendor/kreuzberg/src/core/pipeline/format.rs +392 -0
- data/vendor/kreuzberg/src/core/pipeline/initialization.rs +67 -0
- data/vendor/kreuzberg/src/core/pipeline/mod.rs +135 -0
- data/vendor/kreuzberg/src/core/pipeline/tests.rs +975 -0
- data/vendor/kreuzberg/src/core/server_config/env.rs +90 -0
- data/vendor/kreuzberg/src/core/server_config/loader.rs +202 -0
- data/vendor/kreuzberg/src/core/server_config/mod.rs +380 -0
- data/vendor/kreuzberg/src/core/server_config/tests/basic_tests.rs +124 -0
- data/vendor/kreuzberg/src/core/server_config/tests/env_tests.rs +216 -0
- data/vendor/kreuzberg/src/core/server_config/tests/file_loading_tests.rs +341 -0
- data/vendor/kreuzberg/src/core/server_config/tests/mod.rs +5 -0
- data/vendor/kreuzberg/src/core/server_config/validation.rs +17 -0
- data/vendor/kreuzberg/src/embeddings.rs +136 -13
- data/vendor/kreuzberg/src/extraction/{archive.rs → archive/mod.rs} +45 -239
- data/vendor/kreuzberg/src/extraction/archive/sevenz.rs +98 -0
- data/vendor/kreuzberg/src/extraction/archive/tar.rs +118 -0
- data/vendor/kreuzberg/src/extraction/archive/zip.rs +101 -0
- data/vendor/kreuzberg/src/extraction/html/converter.rs +592 -0
- data/vendor/kreuzberg/src/extraction/html/image_handling.rs +95 -0
- data/vendor/kreuzberg/src/extraction/html/mod.rs +53 -0
- data/vendor/kreuzberg/src/extraction/html/processor.rs +659 -0
- data/vendor/kreuzberg/src/extraction/html/stack_management.rs +103 -0
- data/vendor/kreuzberg/src/extraction/html/types.rs +28 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +6 -2
- data/vendor/kreuzberg/src/extraction/pptx/container.rs +159 -0
- data/vendor/kreuzberg/src/extraction/pptx/content_builder.rs +168 -0
- data/vendor/kreuzberg/src/extraction/pptx/elements.rs +132 -0
- data/vendor/kreuzberg/src/extraction/pptx/image_handling.rs +57 -0
- data/vendor/kreuzberg/src/extraction/pptx/metadata.rs +160 -0
- data/vendor/kreuzberg/src/extraction/pptx/mod.rs +558 -0
- data/vendor/kreuzberg/src/extraction/pptx/parser.rs +379 -0
- data/vendor/kreuzberg/src/extraction/transform/content.rs +205 -0
- data/vendor/kreuzberg/src/extraction/transform/elements.rs +211 -0
- data/vendor/kreuzberg/src/extraction/transform/mod.rs +480 -0
- data/vendor/kreuzberg/src/extraction/transform/types.rs +27 -0
- data/vendor/kreuzberg/src/extractors/archive.rs +2 -0
- data/vendor/kreuzberg/src/extractors/bibtex.rs +2 -0
- data/vendor/kreuzberg/src/extractors/djot_format/attributes.rs +134 -0
- data/vendor/kreuzberg/src/extractors/djot_format/conversion.rs +223 -0
- data/vendor/kreuzberg/src/extractors/djot_format/extractor.rs +172 -0
- data/vendor/kreuzberg/src/extractors/djot_format/mod.rs +24 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/block_handlers.rs +271 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/content_extraction.rs +257 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/event_handlers.rs +101 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/inline_handlers.rs +201 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/mod.rs +16 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/state.rs +78 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/table_extraction.rs +68 -0
- data/vendor/kreuzberg/src/extractors/djot_format/parsing/text_extraction.rs +61 -0
- data/vendor/kreuzberg/src/extractors/djot_format/rendering.rs +452 -0
- data/vendor/kreuzberg/src/extractors/docbook.rs +2 -0
- data/vendor/kreuzberg/src/extractors/docx.rs +12 -1
- data/vendor/kreuzberg/src/extractors/email.rs +2 -0
- data/vendor/kreuzberg/src/extractors/epub/content.rs +333 -0
- data/vendor/kreuzberg/src/extractors/epub/metadata.rs +137 -0
- data/vendor/kreuzberg/src/extractors/epub/mod.rs +186 -0
- data/vendor/kreuzberg/src/extractors/epub/parsing.rs +86 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +4 -0
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +2 -0
- data/vendor/kreuzberg/src/extractors/frontmatter_utils.rs +466 -0
- data/vendor/kreuzberg/src/extractors/html.rs +80 -8
- data/vendor/kreuzberg/src/extractors/image.rs +8 -1
- data/vendor/kreuzberg/src/extractors/jats/elements.rs +350 -0
- data/vendor/kreuzberg/src/extractors/jats/metadata.rs +21 -0
- data/vendor/kreuzberg/src/extractors/{jats.rs → jats/mod.rs} +10 -412
- data/vendor/kreuzberg/src/extractors/jats/parser.rs +52 -0
- data/vendor/kreuzberg/src/extractors/jupyter.rs +2 -0
- data/vendor/kreuzberg/src/extractors/latex/commands.rs +93 -0
- data/vendor/kreuzberg/src/extractors/latex/environments.rs +157 -0
- data/vendor/kreuzberg/src/extractors/latex/metadata.rs +27 -0
- data/vendor/kreuzberg/src/extractors/latex/mod.rs +146 -0
- data/vendor/kreuzberg/src/extractors/latex/parser.rs +231 -0
- data/vendor/kreuzberg/src/extractors/latex/utilities.rs +126 -0
- data/vendor/kreuzberg/src/extractors/markdown.rs +39 -162
- data/vendor/kreuzberg/src/extractors/mod.rs +9 -1
- data/vendor/kreuzberg/src/extractors/odt.rs +2 -0
- data/vendor/kreuzberg/src/extractors/opml/core.rs +165 -0
- data/vendor/kreuzberg/src/extractors/opml/mod.rs +31 -0
- data/vendor/kreuzberg/src/extractors/opml/parser.rs +479 -0
- data/vendor/kreuzberg/src/extractors/orgmode.rs +2 -0
- data/vendor/kreuzberg/src/extractors/pdf/extraction.rs +106 -0
- data/vendor/kreuzberg/src/extractors/{pdf.rs → pdf/mod.rs} +25 -324
- data/vendor/kreuzberg/src/extractors/pdf/ocr.rs +214 -0
- data/vendor/kreuzberg/src/extractors/pdf/pages.rs +51 -0
- data/vendor/kreuzberg/src/extractors/pptx.rs +9 -2
- data/vendor/kreuzberg/src/extractors/rst.rs +2 -0
- data/vendor/kreuzberg/src/extractors/rtf/encoding.rs +116 -0
- data/vendor/kreuzberg/src/extractors/rtf/formatting.rs +24 -0
- data/vendor/kreuzberg/src/extractors/rtf/images.rs +72 -0
- data/vendor/kreuzberg/src/extractors/rtf/metadata.rs +216 -0
- data/vendor/kreuzberg/src/extractors/rtf/mod.rs +142 -0
- data/vendor/kreuzberg/src/extractors/rtf/parser.rs +259 -0
- data/vendor/kreuzberg/src/extractors/rtf/tables.rs +83 -0
- data/vendor/kreuzberg/src/extractors/structured.rs +2 -0
- data/vendor/kreuzberg/src/extractors/text.rs +4 -0
- data/vendor/kreuzberg/src/extractors/typst.rs +2 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +2 -0
- data/vendor/kreuzberg/src/keywords/processor.rs +14 -0
- data/vendor/kreuzberg/src/language_detection/processor.rs +10 -0
- data/vendor/kreuzberg/src/lib.rs +2 -2
- data/vendor/kreuzberg/src/mcp/errors.rs +312 -0
- data/vendor/kreuzberg/src/mcp/format.rs +211 -0
- data/vendor/kreuzberg/src/mcp/mod.rs +9 -3
- data/vendor/kreuzberg/src/mcp/params.rs +196 -0
- data/vendor/kreuzberg/src/mcp/server.rs +39 -1438
- data/vendor/kreuzberg/src/mcp/tools/cache.rs +179 -0
- data/vendor/kreuzberg/src/mcp/tools/extraction.rs +403 -0
- data/vendor/kreuzberg/src/mcp/tools/mime.rs +150 -0
- data/vendor/kreuzberg/src/mcp/tools/mod.rs +11 -0
- data/vendor/kreuzberg/src/ocr/backends/easyocr.rs +96 -0
- data/vendor/kreuzberg/src/ocr/backends/mod.rs +7 -0
- data/vendor/kreuzberg/src/ocr/backends/paddleocr.rs +27 -0
- data/vendor/kreuzberg/src/ocr/backends/tesseract.rs +134 -0
- data/vendor/kreuzberg/src/ocr/hocr.rs +60 -16
- data/vendor/kreuzberg/src/ocr/language_registry.rs +11 -235
- data/vendor/kreuzberg/src/ocr/mod.rs +1 -0
- data/vendor/kreuzberg/src/ocr/processor/config.rs +203 -0
- data/vendor/kreuzberg/src/ocr/processor/execution.rs +494 -0
- data/vendor/kreuzberg/src/ocr/processor/mod.rs +265 -0
- data/vendor/kreuzberg/src/ocr/processor/validation.rs +145 -0
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +41 -24
- data/vendor/kreuzberg/src/pdf/bindings.rs +21 -8
- data/vendor/kreuzberg/src/pdf/hierarchy/bounding_box.rs +289 -0
- data/vendor/kreuzberg/src/pdf/hierarchy/clustering.rs +199 -0
- data/vendor/kreuzberg/src/pdf/{hierarchy.rs → hierarchy/extraction.rs} +6 -346
- data/vendor/kreuzberg/src/pdf/hierarchy/mod.rs +18 -0
- data/vendor/kreuzberg/src/plugins/extractor/mod.rs +319 -0
- data/vendor/kreuzberg/src/plugins/extractor/registry.rs +434 -0
- data/vendor/kreuzberg/src/plugins/extractor/trait.rs +391 -0
- data/vendor/kreuzberg/src/plugins/mod.rs +13 -0
- data/vendor/kreuzberg/src/plugins/ocr.rs +11 -0
- data/vendor/kreuzberg/src/plugins/processor/mod.rs +365 -0
- data/vendor/kreuzberg/src/plugins/processor/registry.rs +37 -0
- data/vendor/kreuzberg/src/plugins/processor/trait.rs +284 -0
- data/vendor/kreuzberg/src/plugins/registry/extractor.rs +416 -0
- data/vendor/kreuzberg/src/plugins/registry/mod.rs +116 -0
- data/vendor/kreuzberg/src/plugins/registry/ocr.rs +293 -0
- data/vendor/kreuzberg/src/plugins/registry/processor.rs +304 -0
- data/vendor/kreuzberg/src/plugins/registry/validator.rs +238 -0
- data/vendor/kreuzberg/src/plugins/validator/mod.rs +424 -0
- data/vendor/kreuzberg/src/plugins/validator/registry.rs +355 -0
- data/vendor/kreuzberg/src/plugins/validator/trait.rs +276 -0
- data/vendor/kreuzberg/src/stopwords/languages/asian.rs +40 -0
- data/vendor/kreuzberg/src/stopwords/languages/germanic.rs +36 -0
- data/vendor/kreuzberg/src/stopwords/languages/mod.rs +10 -0
- data/vendor/kreuzberg/src/stopwords/languages/other.rs +44 -0
- data/vendor/kreuzberg/src/stopwords/languages/romance.rs +36 -0
- data/vendor/kreuzberg/src/stopwords/languages/slavic.rs +36 -0
- data/vendor/kreuzberg/src/stopwords/mod.rs +7 -33
- data/vendor/kreuzberg/src/text/quality.rs +1 -1
- data/vendor/kreuzberg/src/text/quality_processor.rs +10 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/analysis.rs +238 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/mod.rs +8 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/punctuation.rs +54 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/reducer.rs +384 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/sentence_selection.rs +68 -0
- data/vendor/kreuzberg/src/text/token_reduction/core/word_filtering.rs +156 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters/general.rs +377 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters/html.rs +51 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters/markdown.rs +285 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +131 -246
- data/vendor/kreuzberg/src/types/djot.rs +209 -0
- data/vendor/kreuzberg/src/types/extraction.rs +301 -0
- data/vendor/kreuzberg/src/types/formats.rs +443 -0
- data/vendor/kreuzberg/src/types/metadata.rs +560 -0
- data/vendor/kreuzberg/src/types/mod.rs +281 -0
- data/vendor/kreuzberg/src/types/page.rs +182 -0
- data/vendor/kreuzberg/src/types/serde_helpers.rs +132 -0
- data/vendor/kreuzberg/src/types/tables.rs +39 -0
- data/vendor/kreuzberg/src/utils/quality/heuristics.rs +58 -0
- data/vendor/kreuzberg/src/utils/{quality.rs → quality/mod.rs} +168 -489
- data/vendor/kreuzberg/src/utils/quality/patterns.rs +117 -0
- data/vendor/kreuzberg/src/utils/quality/scoring.rs +178 -0
- data/vendor/kreuzberg/src/utils/string_pool/buffer_pool.rs +325 -0
- data/vendor/kreuzberg/src/utils/string_pool/interned.rs +102 -0
- data/vendor/kreuzberg/src/utils/string_pool/language_pool.rs +119 -0
- data/vendor/kreuzberg/src/utils/string_pool/mime_pool.rs +235 -0
- data/vendor/kreuzberg/src/utils/string_pool/mod.rs +41 -0
- data/vendor/kreuzberg/tests/api_chunk.rs +313 -0
- data/vendor/kreuzberg/tests/api_embed.rs +6 -9
- data/vendor/kreuzberg/tests/batch_orchestration.rs +1 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +7 -0
- data/vendor/kreuzberg/tests/core_integration.rs +1 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +130 -0
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +5 -14
- data/vendor/kreuzberg/tests/format_integration.rs +2 -0
- data/vendor/kreuzberg/tests/helpers/mod.rs +1 -0
- data/vendor/kreuzberg/tests/html_table_test.rs +11 -11
- data/vendor/kreuzberg/tests/ocr_configuration.rs +16 -0
- data/vendor/kreuzberg/tests/ocr_errors.rs +18 -0
- data/vendor/kreuzberg/tests/ocr_quality.rs +9 -0
- data/vendor/kreuzberg/tests/ocr_stress.rs +1 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +50 -0
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +13 -0
- data/vendor/kreuzberg/tests/plugin_system.rs +12 -0
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +2 -0
- data/vendor/kreuzberg-ffi/Cargo.toml +2 -1
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +2 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +347 -178
- data/vendor/kreuzberg-ffi/src/config/html.rs +318 -0
- data/vendor/kreuzberg-ffi/src/config/loader.rs +154 -0
- data/vendor/kreuzberg-ffi/src/config/merge.rs +104 -0
- data/vendor/kreuzberg-ffi/src/config/mod.rs +385 -0
- data/vendor/kreuzberg-ffi/src/config/parse.rs +91 -0
- data/vendor/kreuzberg-ffi/src/config/serialize.rs +118 -0
- data/vendor/kreuzberg-ffi/src/config_builder.rs +598 -0
- data/vendor/kreuzberg-ffi/src/error.rs +46 -14
- data/vendor/kreuzberg-ffi/src/helpers.rs +26 -353
- data/vendor/kreuzberg-ffi/src/html_options.rs +421 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +16 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +11 -0
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +2 -0
- data/vendor/kreuzberg-ffi/src/result.rs +148 -122
- data/vendor/kreuzberg-ffi/src/result_view.rs +4 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +3 -3
- metadata +200 -28
- data/vendor/kreuzberg/src/api/server.rs +0 -518
- data/vendor/kreuzberg/src/core/config.rs +0 -1914
- data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
- data/vendor/kreuzberg/src/core/extractor.rs +0 -1200
- data/vendor/kreuzberg/src/core/pipeline.rs +0 -1223
- data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
- data/vendor/kreuzberg/src/extraction/html.rs +0 -1830
- data/vendor/kreuzberg/src/extraction/pptx.rs +0 -3102
- data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
- data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
- data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
- data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
- data/vendor/kreuzberg/src/ocr/processor.rs +0 -858
- data/vendor/kreuzberg/src/plugins/extractor.rs +0 -1042
- data/vendor/kreuzberg/src/plugins/processor.rs +0 -650
- data/vendor/kreuzberg/src/plugins/registry.rs +0 -1339
- data/vendor/kreuzberg/src/plugins/validator.rs +0 -967
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +0 -832
- data/vendor/kreuzberg/src/types.rs +0 -1713
- data/vendor/kreuzberg/src/utils/string_pool.rs +0 -762
- data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: kreuzberg
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 4.0
|
|
4
|
+
version: 4.1.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Na'aman Hirschfeld
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-01-
|
|
11
|
+
date: 2026-01-22 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -209,7 +209,21 @@ files:
|
|
|
209
209
|
- ext/kreuzberg_rb/native/include/msvc_compat/strings.h
|
|
210
210
|
- ext/kreuzberg_rb/native/include/strings.h
|
|
211
211
|
- ext/kreuzberg_rb/native/include/unistd.h
|
|
212
|
+
- ext/kreuzberg_rb/native/src/batch.rs
|
|
213
|
+
- ext/kreuzberg_rb/native/src/config/mod.rs
|
|
214
|
+
- ext/kreuzberg_rb/native/src/config/types.rs
|
|
215
|
+
- ext/kreuzberg_rb/native/src/error_handling.rs
|
|
216
|
+
- ext/kreuzberg_rb/native/src/extraction.rs
|
|
217
|
+
- ext/kreuzberg_rb/native/src/gc_guarded_value.rs
|
|
218
|
+
- ext/kreuzberg_rb/native/src/helpers.rs
|
|
212
219
|
- ext/kreuzberg_rb/native/src/lib.rs
|
|
220
|
+
- ext/kreuzberg_rb/native/src/metadata.rs
|
|
221
|
+
- ext/kreuzberg_rb/native/src/plugins/mod.rs
|
|
222
|
+
- ext/kreuzberg_rb/native/src/plugins/ocr_backend.rs
|
|
223
|
+
- ext/kreuzberg_rb/native/src/plugins/post_processor.rs
|
|
224
|
+
- ext/kreuzberg_rb/native/src/plugins/validator.rs
|
|
225
|
+
- ext/kreuzberg_rb/native/src/result.rs
|
|
226
|
+
- ext/kreuzberg_rb/native/src/validation.rs
|
|
213
227
|
- extconf.rb
|
|
214
228
|
- kreuzberg.gemspec
|
|
215
229
|
- lib/kreuzberg.rb
|
|
@@ -284,10 +298,17 @@ files:
|
|
|
284
298
|
- vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in
|
|
285
299
|
- vendor/kreuzberg-ffi/kreuzberg.h
|
|
286
300
|
- vendor/kreuzberg-ffi/src/batch_streaming.rs
|
|
287
|
-
- vendor/kreuzberg-ffi/src/config.rs
|
|
301
|
+
- vendor/kreuzberg-ffi/src/config/html.rs
|
|
302
|
+
- vendor/kreuzberg-ffi/src/config/loader.rs
|
|
303
|
+
- vendor/kreuzberg-ffi/src/config/merge.rs
|
|
304
|
+
- vendor/kreuzberg-ffi/src/config/mod.rs
|
|
305
|
+
- vendor/kreuzberg-ffi/src/config/parse.rs
|
|
306
|
+
- vendor/kreuzberg-ffi/src/config/serialize.rs
|
|
307
|
+
- vendor/kreuzberg-ffi/src/config_builder.rs
|
|
288
308
|
- vendor/kreuzberg-ffi/src/error.rs
|
|
289
309
|
- vendor/kreuzberg-ffi/src/extraction.rs
|
|
290
310
|
- vendor/kreuzberg-ffi/src/helpers.rs
|
|
311
|
+
- vendor/kreuzberg-ffi/src/html_options.rs
|
|
291
312
|
- vendor/kreuzberg-ffi/src/lib.rs
|
|
292
313
|
- vendor/kreuzberg-ffi/src/memory.rs
|
|
293
314
|
- vendor/kreuzberg-ffi/src/mime.rs
|
|
@@ -334,33 +355,82 @@ files:
|
|
|
334
355
|
- vendor/kreuzberg/build.rs
|
|
335
356
|
- vendor/kreuzberg/examples/bench_fixes.rs
|
|
336
357
|
- vendor/kreuzberg/examples/test_pdfium_fork.rs
|
|
358
|
+
- vendor/kreuzberg/src/api/config.rs
|
|
337
359
|
- vendor/kreuzberg/src/api/error.rs
|
|
338
360
|
- vendor/kreuzberg/src/api/handlers.rs
|
|
339
361
|
- vendor/kreuzberg/src/api/mod.rs
|
|
340
|
-
- vendor/kreuzberg/src/api/
|
|
362
|
+
- vendor/kreuzberg/src/api/router.rs
|
|
363
|
+
- vendor/kreuzberg/src/api/startup.rs
|
|
341
364
|
- vendor/kreuzberg/src/api/types.rs
|
|
365
|
+
- vendor/kreuzberg/src/cache/cleanup.rs
|
|
366
|
+
- vendor/kreuzberg/src/cache/core.rs
|
|
342
367
|
- vendor/kreuzberg/src/cache/mod.rs
|
|
368
|
+
- vendor/kreuzberg/src/cache/utilities.rs
|
|
369
|
+
- vendor/kreuzberg/src/chunking/boundaries.rs
|
|
370
|
+
- vendor/kreuzberg/src/chunking/builder.rs
|
|
371
|
+
- vendor/kreuzberg/src/chunking/config.rs
|
|
372
|
+
- vendor/kreuzberg/src/chunking/core.rs
|
|
343
373
|
- vendor/kreuzberg/src/chunking/mod.rs
|
|
344
374
|
- vendor/kreuzberg/src/chunking/processor.rs
|
|
375
|
+
- vendor/kreuzberg/src/chunking/validation.rs
|
|
345
376
|
- vendor/kreuzberg/src/core/batch_mode.rs
|
|
346
377
|
- vendor/kreuzberg/src/core/batch_optimizations.rs
|
|
347
|
-
- vendor/kreuzberg/src/core/config.rs
|
|
348
|
-
- vendor/kreuzberg/src/core/
|
|
349
|
-
- vendor/kreuzberg/src/core/
|
|
378
|
+
- vendor/kreuzberg/src/core/config/extraction/core.rs
|
|
379
|
+
- vendor/kreuzberg/src/core/config/extraction/env.rs
|
|
380
|
+
- vendor/kreuzberg/src/core/config/extraction/loaders.rs
|
|
381
|
+
- vendor/kreuzberg/src/core/config/extraction/mod.rs
|
|
382
|
+
- vendor/kreuzberg/src/core/config/extraction/types.rs
|
|
383
|
+
- vendor/kreuzberg/src/core/config/formats.rs
|
|
384
|
+
- vendor/kreuzberg/src/core/config/mod.rs
|
|
385
|
+
- vendor/kreuzberg/src/core/config/ocr.rs
|
|
386
|
+
- vendor/kreuzberg/src/core/config/page.rs
|
|
387
|
+
- vendor/kreuzberg/src/core/config/pdf.rs
|
|
388
|
+
- vendor/kreuzberg/src/core/config/processing.rs
|
|
389
|
+
- vendor/kreuzberg/src/core/config_validation/dependencies.rs
|
|
390
|
+
- vendor/kreuzberg/src/core/config_validation/mod.rs
|
|
391
|
+
- vendor/kreuzberg/src/core/config_validation/sections.rs
|
|
392
|
+
- vendor/kreuzberg/src/core/extractor/batch.rs
|
|
393
|
+
- vendor/kreuzberg/src/core/extractor/bytes.rs
|
|
394
|
+
- vendor/kreuzberg/src/core/extractor/file.rs
|
|
395
|
+
- vendor/kreuzberg/src/core/extractor/helpers.rs
|
|
396
|
+
- vendor/kreuzberg/src/core/extractor/legacy.rs
|
|
397
|
+
- vendor/kreuzberg/src/core/extractor/mod.rs
|
|
398
|
+
- vendor/kreuzberg/src/core/extractor/sync.rs
|
|
350
399
|
- vendor/kreuzberg/src/core/formats.rs
|
|
351
400
|
- vendor/kreuzberg/src/core/io.rs
|
|
352
401
|
- vendor/kreuzberg/src/core/mime.rs
|
|
353
402
|
- vendor/kreuzberg/src/core/mod.rs
|
|
354
|
-
- vendor/kreuzberg/src/core/pipeline.rs
|
|
355
|
-
- vendor/kreuzberg/src/core/
|
|
403
|
+
- vendor/kreuzberg/src/core/pipeline/cache.rs
|
|
404
|
+
- vendor/kreuzberg/src/core/pipeline/execution.rs
|
|
405
|
+
- vendor/kreuzberg/src/core/pipeline/features.rs
|
|
406
|
+
- vendor/kreuzberg/src/core/pipeline/format.rs
|
|
407
|
+
- vendor/kreuzberg/src/core/pipeline/initialization.rs
|
|
408
|
+
- vendor/kreuzberg/src/core/pipeline/mod.rs
|
|
409
|
+
- vendor/kreuzberg/src/core/pipeline/tests.rs
|
|
410
|
+
- vendor/kreuzberg/src/core/server_config/env.rs
|
|
411
|
+
- vendor/kreuzberg/src/core/server_config/loader.rs
|
|
412
|
+
- vendor/kreuzberg/src/core/server_config/mod.rs
|
|
413
|
+
- vendor/kreuzberg/src/core/server_config/tests/basic_tests.rs
|
|
414
|
+
- vendor/kreuzberg/src/core/server_config/tests/env_tests.rs
|
|
415
|
+
- vendor/kreuzberg/src/core/server_config/tests/file_loading_tests.rs
|
|
416
|
+
- vendor/kreuzberg/src/core/server_config/tests/mod.rs
|
|
417
|
+
- vendor/kreuzberg/src/core/server_config/validation.rs
|
|
356
418
|
- vendor/kreuzberg/src/embeddings.rs
|
|
357
419
|
- vendor/kreuzberg/src/error.rs
|
|
358
|
-
- vendor/kreuzberg/src/extraction/archive.rs
|
|
420
|
+
- vendor/kreuzberg/src/extraction/archive/mod.rs
|
|
421
|
+
- vendor/kreuzberg/src/extraction/archive/sevenz.rs
|
|
422
|
+
- vendor/kreuzberg/src/extraction/archive/tar.rs
|
|
423
|
+
- vendor/kreuzberg/src/extraction/archive/zip.rs
|
|
359
424
|
- vendor/kreuzberg/src/extraction/capacity.rs
|
|
360
425
|
- vendor/kreuzberg/src/extraction/docx.rs
|
|
361
426
|
- vendor/kreuzberg/src/extraction/email.rs
|
|
362
427
|
- vendor/kreuzberg/src/extraction/excel.rs
|
|
363
|
-
- vendor/kreuzberg/src/extraction/html.rs
|
|
428
|
+
- vendor/kreuzberg/src/extraction/html/converter.rs
|
|
429
|
+
- vendor/kreuzberg/src/extraction/html/image_handling.rs
|
|
430
|
+
- vendor/kreuzberg/src/extraction/html/mod.rs
|
|
431
|
+
- vendor/kreuzberg/src/extraction/html/processor.rs
|
|
432
|
+
- vendor/kreuzberg/src/extraction/html/stack_management.rs
|
|
433
|
+
- vendor/kreuzberg/src/extraction/html/types.rs
|
|
364
434
|
- vendor/kreuzberg/src/extraction/image.rs
|
|
365
435
|
- vendor/kreuzberg/src/extraction/libreoffice.rs
|
|
366
436
|
- vendor/kreuzberg/src/extraction/markdown.rs
|
|
@@ -370,33 +440,79 @@ files:
|
|
|
370
440
|
- vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs
|
|
371
441
|
- vendor/kreuzberg/src/extraction/office_metadata/mod.rs
|
|
372
442
|
- vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs
|
|
373
|
-
- vendor/kreuzberg/src/extraction/pptx.rs
|
|
443
|
+
- vendor/kreuzberg/src/extraction/pptx/container.rs
|
|
444
|
+
- vendor/kreuzberg/src/extraction/pptx/content_builder.rs
|
|
445
|
+
- vendor/kreuzberg/src/extraction/pptx/elements.rs
|
|
446
|
+
- vendor/kreuzberg/src/extraction/pptx/image_handling.rs
|
|
447
|
+
- vendor/kreuzberg/src/extraction/pptx/metadata.rs
|
|
448
|
+
- vendor/kreuzberg/src/extraction/pptx/mod.rs
|
|
449
|
+
- vendor/kreuzberg/src/extraction/pptx/parser.rs
|
|
374
450
|
- vendor/kreuzberg/src/extraction/structured.rs
|
|
375
451
|
- vendor/kreuzberg/src/extraction/table.rs
|
|
376
452
|
- vendor/kreuzberg/src/extraction/text.rs
|
|
453
|
+
- vendor/kreuzberg/src/extraction/transform/content.rs
|
|
454
|
+
- vendor/kreuzberg/src/extraction/transform/elements.rs
|
|
455
|
+
- vendor/kreuzberg/src/extraction/transform/mod.rs
|
|
456
|
+
- vendor/kreuzberg/src/extraction/transform/types.rs
|
|
377
457
|
- vendor/kreuzberg/src/extraction/xml.rs
|
|
378
458
|
- vendor/kreuzberg/src/extractors/archive.rs
|
|
379
459
|
- vendor/kreuzberg/src/extractors/bibtex.rs
|
|
460
|
+
- vendor/kreuzberg/src/extractors/djot_format/attributes.rs
|
|
461
|
+
- vendor/kreuzberg/src/extractors/djot_format/conversion.rs
|
|
462
|
+
- vendor/kreuzberg/src/extractors/djot_format/extractor.rs
|
|
463
|
+
- vendor/kreuzberg/src/extractors/djot_format/mod.rs
|
|
464
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/block_handlers.rs
|
|
465
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/content_extraction.rs
|
|
466
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/event_handlers.rs
|
|
467
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/inline_handlers.rs
|
|
468
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/mod.rs
|
|
469
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/state.rs
|
|
470
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/table_extraction.rs
|
|
471
|
+
- vendor/kreuzberg/src/extractors/djot_format/parsing/text_extraction.rs
|
|
472
|
+
- vendor/kreuzberg/src/extractors/djot_format/rendering.rs
|
|
380
473
|
- vendor/kreuzberg/src/extractors/docbook.rs
|
|
381
474
|
- vendor/kreuzberg/src/extractors/docx.rs
|
|
382
475
|
- vendor/kreuzberg/src/extractors/email.rs
|
|
383
|
-
- vendor/kreuzberg/src/extractors/epub.rs
|
|
476
|
+
- vendor/kreuzberg/src/extractors/epub/content.rs
|
|
477
|
+
- vendor/kreuzberg/src/extractors/epub/metadata.rs
|
|
478
|
+
- vendor/kreuzberg/src/extractors/epub/mod.rs
|
|
479
|
+
- vendor/kreuzberg/src/extractors/epub/parsing.rs
|
|
384
480
|
- vendor/kreuzberg/src/extractors/excel.rs
|
|
385
481
|
- vendor/kreuzberg/src/extractors/fictionbook.rs
|
|
482
|
+
- vendor/kreuzberg/src/extractors/frontmatter_utils.rs
|
|
386
483
|
- vendor/kreuzberg/src/extractors/html.rs
|
|
387
484
|
- vendor/kreuzberg/src/extractors/image.rs
|
|
388
|
-
- vendor/kreuzberg/src/extractors/jats.rs
|
|
485
|
+
- vendor/kreuzberg/src/extractors/jats/elements.rs
|
|
486
|
+
- vendor/kreuzberg/src/extractors/jats/metadata.rs
|
|
487
|
+
- vendor/kreuzberg/src/extractors/jats/mod.rs
|
|
488
|
+
- vendor/kreuzberg/src/extractors/jats/parser.rs
|
|
389
489
|
- vendor/kreuzberg/src/extractors/jupyter.rs
|
|
390
|
-
- vendor/kreuzberg/src/extractors/latex.rs
|
|
490
|
+
- vendor/kreuzberg/src/extractors/latex/commands.rs
|
|
491
|
+
- vendor/kreuzberg/src/extractors/latex/environments.rs
|
|
492
|
+
- vendor/kreuzberg/src/extractors/latex/metadata.rs
|
|
493
|
+
- vendor/kreuzberg/src/extractors/latex/mod.rs
|
|
494
|
+
- vendor/kreuzberg/src/extractors/latex/parser.rs
|
|
495
|
+
- vendor/kreuzberg/src/extractors/latex/utilities.rs
|
|
391
496
|
- vendor/kreuzberg/src/extractors/markdown.rs
|
|
392
497
|
- vendor/kreuzberg/src/extractors/mod.rs
|
|
393
498
|
- vendor/kreuzberg/src/extractors/odt.rs
|
|
394
|
-
- vendor/kreuzberg/src/extractors/opml.rs
|
|
499
|
+
- vendor/kreuzberg/src/extractors/opml/core.rs
|
|
500
|
+
- vendor/kreuzberg/src/extractors/opml/mod.rs
|
|
501
|
+
- vendor/kreuzberg/src/extractors/opml/parser.rs
|
|
395
502
|
- vendor/kreuzberg/src/extractors/orgmode.rs
|
|
396
|
-
- vendor/kreuzberg/src/extractors/pdf.rs
|
|
503
|
+
- vendor/kreuzberg/src/extractors/pdf/extraction.rs
|
|
504
|
+
- vendor/kreuzberg/src/extractors/pdf/mod.rs
|
|
505
|
+
- vendor/kreuzberg/src/extractors/pdf/ocr.rs
|
|
506
|
+
- vendor/kreuzberg/src/extractors/pdf/pages.rs
|
|
397
507
|
- vendor/kreuzberg/src/extractors/pptx.rs
|
|
398
508
|
- vendor/kreuzberg/src/extractors/rst.rs
|
|
399
|
-
- vendor/kreuzberg/src/extractors/rtf.rs
|
|
509
|
+
- vendor/kreuzberg/src/extractors/rtf/encoding.rs
|
|
510
|
+
- vendor/kreuzberg/src/extractors/rtf/formatting.rs
|
|
511
|
+
- vendor/kreuzberg/src/extractors/rtf/images.rs
|
|
512
|
+
- vendor/kreuzberg/src/extractors/rtf/metadata.rs
|
|
513
|
+
- vendor/kreuzberg/src/extractors/rtf/mod.rs
|
|
514
|
+
- vendor/kreuzberg/src/extractors/rtf/parser.rs
|
|
515
|
+
- vendor/kreuzberg/src/extractors/rtf/tables.rs
|
|
400
516
|
- vendor/kreuzberg/src/extractors/security.rs
|
|
401
517
|
- vendor/kreuzberg/src/extractors/security_tests.rs
|
|
402
518
|
- vendor/kreuzberg/src/extractors/structured.rs
|
|
@@ -416,14 +532,28 @@ files:
|
|
|
416
532
|
- vendor/kreuzberg/src/language_detection/mod.rs
|
|
417
533
|
- vendor/kreuzberg/src/language_detection/processor.rs
|
|
418
534
|
- vendor/kreuzberg/src/lib.rs
|
|
535
|
+
- vendor/kreuzberg/src/mcp/errors.rs
|
|
536
|
+
- vendor/kreuzberg/src/mcp/format.rs
|
|
419
537
|
- vendor/kreuzberg/src/mcp/mod.rs
|
|
538
|
+
- vendor/kreuzberg/src/mcp/params.rs
|
|
420
539
|
- vendor/kreuzberg/src/mcp/server.rs
|
|
540
|
+
- vendor/kreuzberg/src/mcp/tools/cache.rs
|
|
541
|
+
- vendor/kreuzberg/src/mcp/tools/extraction.rs
|
|
542
|
+
- vendor/kreuzberg/src/mcp/tools/mime.rs
|
|
543
|
+
- vendor/kreuzberg/src/mcp/tools/mod.rs
|
|
544
|
+
- vendor/kreuzberg/src/ocr/backends/easyocr.rs
|
|
545
|
+
- vendor/kreuzberg/src/ocr/backends/mod.rs
|
|
546
|
+
- vendor/kreuzberg/src/ocr/backends/paddleocr.rs
|
|
547
|
+
- vendor/kreuzberg/src/ocr/backends/tesseract.rs
|
|
421
548
|
- vendor/kreuzberg/src/ocr/cache.rs
|
|
422
549
|
- vendor/kreuzberg/src/ocr/error.rs
|
|
423
550
|
- vendor/kreuzberg/src/ocr/hocr.rs
|
|
424
551
|
- vendor/kreuzberg/src/ocr/language_registry.rs
|
|
425
552
|
- vendor/kreuzberg/src/ocr/mod.rs
|
|
426
|
-
- vendor/kreuzberg/src/ocr/processor.rs
|
|
553
|
+
- vendor/kreuzberg/src/ocr/processor/config.rs
|
|
554
|
+
- vendor/kreuzberg/src/ocr/processor/execution.rs
|
|
555
|
+
- vendor/kreuzberg/src/ocr/processor/mod.rs
|
|
556
|
+
- vendor/kreuzberg/src/ocr/processor/validation.rs
|
|
427
557
|
- vendor/kreuzberg/src/ocr/table/mod.rs
|
|
428
558
|
- vendor/kreuzberg/src/ocr/table/tsv_parser.rs
|
|
429
559
|
- vendor/kreuzberg/src/ocr/tesseract_backend.rs
|
|
@@ -435,20 +565,39 @@ files:
|
|
|
435
565
|
- vendor/kreuzberg/src/pdf/bundled.rs
|
|
436
566
|
- vendor/kreuzberg/src/pdf/error.rs
|
|
437
567
|
- vendor/kreuzberg/src/pdf/fonts.rs
|
|
438
|
-
- vendor/kreuzberg/src/pdf/hierarchy.rs
|
|
568
|
+
- vendor/kreuzberg/src/pdf/hierarchy/bounding_box.rs
|
|
569
|
+
- vendor/kreuzberg/src/pdf/hierarchy/clustering.rs
|
|
570
|
+
- vendor/kreuzberg/src/pdf/hierarchy/extraction.rs
|
|
571
|
+
- vendor/kreuzberg/src/pdf/hierarchy/mod.rs
|
|
439
572
|
- vendor/kreuzberg/src/pdf/images.rs
|
|
440
573
|
- vendor/kreuzberg/src/pdf/metadata.rs
|
|
441
574
|
- vendor/kreuzberg/src/pdf/mod.rs
|
|
442
575
|
- vendor/kreuzberg/src/pdf/rendering.rs
|
|
443
576
|
- vendor/kreuzberg/src/pdf/table.rs
|
|
444
577
|
- vendor/kreuzberg/src/pdf/text.rs
|
|
445
|
-
- vendor/kreuzberg/src/plugins/extractor.rs
|
|
578
|
+
- vendor/kreuzberg/src/plugins/extractor/mod.rs
|
|
579
|
+
- vendor/kreuzberg/src/plugins/extractor/registry.rs
|
|
580
|
+
- vendor/kreuzberg/src/plugins/extractor/trait.rs
|
|
446
581
|
- vendor/kreuzberg/src/plugins/mod.rs
|
|
447
582
|
- vendor/kreuzberg/src/plugins/ocr.rs
|
|
448
|
-
- vendor/kreuzberg/src/plugins/processor.rs
|
|
449
|
-
- vendor/kreuzberg/src/plugins/registry.rs
|
|
583
|
+
- vendor/kreuzberg/src/plugins/processor/mod.rs
|
|
584
|
+
- vendor/kreuzberg/src/plugins/processor/registry.rs
|
|
585
|
+
- vendor/kreuzberg/src/plugins/processor/trait.rs
|
|
586
|
+
- vendor/kreuzberg/src/plugins/registry/extractor.rs
|
|
587
|
+
- vendor/kreuzberg/src/plugins/registry/mod.rs
|
|
588
|
+
- vendor/kreuzberg/src/plugins/registry/ocr.rs
|
|
589
|
+
- vendor/kreuzberg/src/plugins/registry/processor.rs
|
|
590
|
+
- vendor/kreuzberg/src/plugins/registry/validator.rs
|
|
450
591
|
- vendor/kreuzberg/src/plugins/traits.rs
|
|
451
|
-
- vendor/kreuzberg/src/plugins/validator.rs
|
|
592
|
+
- vendor/kreuzberg/src/plugins/validator/mod.rs
|
|
593
|
+
- vendor/kreuzberg/src/plugins/validator/registry.rs
|
|
594
|
+
- vendor/kreuzberg/src/plugins/validator/trait.rs
|
|
595
|
+
- vendor/kreuzberg/src/stopwords/languages/asian.rs
|
|
596
|
+
- vendor/kreuzberg/src/stopwords/languages/germanic.rs
|
|
597
|
+
- vendor/kreuzberg/src/stopwords/languages/mod.rs
|
|
598
|
+
- vendor/kreuzberg/src/stopwords/languages/other.rs
|
|
599
|
+
- vendor/kreuzberg/src/stopwords/languages/romance.rs
|
|
600
|
+
- vendor/kreuzberg/src/stopwords/languages/slavic.rs
|
|
452
601
|
- vendor/kreuzberg/src/stopwords/mod.rs
|
|
453
602
|
- vendor/kreuzberg/src/text/mod.rs
|
|
454
603
|
- vendor/kreuzberg/src/text/quality.rs
|
|
@@ -456,18 +605,40 @@ files:
|
|
|
456
605
|
- vendor/kreuzberg/src/text/string_utils.rs
|
|
457
606
|
- vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs
|
|
458
607
|
- vendor/kreuzberg/src/text/token_reduction/config.rs
|
|
459
|
-
- vendor/kreuzberg/src/text/token_reduction/core.rs
|
|
608
|
+
- vendor/kreuzberg/src/text/token_reduction/core/analysis.rs
|
|
609
|
+
- vendor/kreuzberg/src/text/token_reduction/core/mod.rs
|
|
610
|
+
- vendor/kreuzberg/src/text/token_reduction/core/punctuation.rs
|
|
611
|
+
- vendor/kreuzberg/src/text/token_reduction/core/reducer.rs
|
|
612
|
+
- vendor/kreuzberg/src/text/token_reduction/core/sentence_selection.rs
|
|
613
|
+
- vendor/kreuzberg/src/text/token_reduction/core/word_filtering.rs
|
|
460
614
|
- vendor/kreuzberg/src/text/token_reduction/filters.rs
|
|
615
|
+
- vendor/kreuzberg/src/text/token_reduction/filters/general.rs
|
|
616
|
+
- vendor/kreuzberg/src/text/token_reduction/filters/html.rs
|
|
617
|
+
- vendor/kreuzberg/src/text/token_reduction/filters/markdown.rs
|
|
461
618
|
- vendor/kreuzberg/src/text/token_reduction/mod.rs
|
|
462
619
|
- vendor/kreuzberg/src/text/token_reduction/semantic.rs
|
|
463
620
|
- vendor/kreuzberg/src/text/token_reduction/simd_text.rs
|
|
464
621
|
- vendor/kreuzberg/src/text/utf8_validation.rs
|
|
465
|
-
- vendor/kreuzberg/src/types.rs
|
|
622
|
+
- vendor/kreuzberg/src/types/djot.rs
|
|
623
|
+
- vendor/kreuzberg/src/types/extraction.rs
|
|
624
|
+
- vendor/kreuzberg/src/types/formats.rs
|
|
625
|
+
- vendor/kreuzberg/src/types/metadata.rs
|
|
626
|
+
- vendor/kreuzberg/src/types/mod.rs
|
|
627
|
+
- vendor/kreuzberg/src/types/page.rs
|
|
628
|
+
- vendor/kreuzberg/src/types/serde_helpers.rs
|
|
629
|
+
- vendor/kreuzberg/src/types/tables.rs
|
|
466
630
|
- vendor/kreuzberg/src/utils/mod.rs
|
|
467
631
|
- vendor/kreuzberg/src/utils/pool.rs
|
|
468
632
|
- vendor/kreuzberg/src/utils/pool_sizing.rs
|
|
469
|
-
- vendor/kreuzberg/src/utils/quality.rs
|
|
470
|
-
- vendor/kreuzberg/src/utils/
|
|
633
|
+
- vendor/kreuzberg/src/utils/quality/heuristics.rs
|
|
634
|
+
- vendor/kreuzberg/src/utils/quality/mod.rs
|
|
635
|
+
- vendor/kreuzberg/src/utils/quality/patterns.rs
|
|
636
|
+
- vendor/kreuzberg/src/utils/quality/scoring.rs
|
|
637
|
+
- vendor/kreuzberg/src/utils/string_pool/buffer_pool.rs
|
|
638
|
+
- vendor/kreuzberg/src/utils/string_pool/interned.rs
|
|
639
|
+
- vendor/kreuzberg/src/utils/string_pool/language_pool.rs
|
|
640
|
+
- vendor/kreuzberg/src/utils/string_pool/mime_pool.rs
|
|
641
|
+
- vendor/kreuzberg/src/utils/string_pool/mod.rs
|
|
471
642
|
- vendor/kreuzberg/src/utils/string_utils.rs
|
|
472
643
|
- vendor/kreuzberg/stopwords/af_stopwords.json
|
|
473
644
|
- vendor/kreuzberg/stopwords/ar_stopwords.json
|
|
@@ -533,6 +704,7 @@ files:
|
|
|
533
704
|
- vendor/kreuzberg/stopwords/yo_stopwords.json
|
|
534
705
|
- vendor/kreuzberg/stopwords/zh_stopwords.json
|
|
535
706
|
- vendor/kreuzberg/stopwords/zu_stopwords.json
|
|
707
|
+
- vendor/kreuzberg/tests/api_chunk.rs
|
|
536
708
|
- vendor/kreuzberg/tests/api_embed.rs
|
|
537
709
|
- vendor/kreuzberg/tests/api_extract_multipart.rs
|
|
538
710
|
- vendor/kreuzberg/tests/api_large_pdf_extraction.rs
|