kreuzberg 4.0.8 → 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 +2 -2
- data/README.md +1 -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 +10 -0
- 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 +2 -2
- 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
|
@@ -0,0 +1,386 @@
|
|
|
1
|
+
//! Configuration validation module.
|
|
2
|
+
//!
|
|
3
|
+
//! Provides centralized validation for configuration values across all bindings.
|
|
4
|
+
//! This eliminates duplication of validation logic in Python, TypeScript, Java, Go, and other language bindings.
|
|
5
|
+
//!
|
|
6
|
+
//! All validation functions return `Result<()>` and produce detailed error messages
|
|
7
|
+
//! suitable for user-facing error handling.
|
|
8
|
+
//!
|
|
9
|
+
//! # Examples
|
|
10
|
+
//!
|
|
11
|
+
//! ```rust
|
|
12
|
+
//! use kreuzberg::core::config_validation::{
|
|
13
|
+
//! validate_binarization_method,
|
|
14
|
+
//! validate_token_reduction_level,
|
|
15
|
+
//! validate_language_code,
|
|
16
|
+
//! };
|
|
17
|
+
//!
|
|
18
|
+
//! // Valid values
|
|
19
|
+
//! assert!(validate_binarization_method("otsu").is_ok());
|
|
20
|
+
//! assert!(validate_token_reduction_level("moderate").is_ok());
|
|
21
|
+
//! assert!(validate_language_code("en").is_ok());
|
|
22
|
+
//!
|
|
23
|
+
//! // Invalid values
|
|
24
|
+
//! assert!(validate_binarization_method("invalid").is_err());
|
|
25
|
+
//! assert!(validate_token_reduction_level("extreme").is_err());
|
|
26
|
+
//! ```
|
|
27
|
+
|
|
28
|
+
mod dependencies;
|
|
29
|
+
mod sections;
|
|
30
|
+
|
|
31
|
+
// Re-export all validation functions for backward compatibility
|
|
32
|
+
pub use sections::{
|
|
33
|
+
validate_binarization_method, validate_chunking_params, validate_confidence, validate_dpi, validate_language_code,
|
|
34
|
+
validate_ocr_backend, validate_output_format, validate_tesseract_oem, validate_tesseract_psm,
|
|
35
|
+
validate_token_reduction_level,
|
|
36
|
+
};
|
|
37
|
+
|
|
38
|
+
pub use dependencies::{validate_cors_origin, validate_host, validate_port, validate_upload_size};
|
|
39
|
+
|
|
40
|
+
#[cfg(test)]
|
|
41
|
+
mod tests {
|
|
42
|
+
use super::*;
|
|
43
|
+
|
|
44
|
+
// Tests for section validation functions
|
|
45
|
+
#[test]
|
|
46
|
+
fn test_validate_binarization_method_valid() {
|
|
47
|
+
assert!(validate_binarization_method("otsu").is_ok());
|
|
48
|
+
assert!(validate_binarization_method("adaptive").is_ok());
|
|
49
|
+
assert!(validate_binarization_method("sauvola").is_ok());
|
|
50
|
+
}
|
|
51
|
+
|
|
52
|
+
#[test]
|
|
53
|
+
fn test_validate_binarization_method_case_insensitive() {
|
|
54
|
+
assert!(validate_binarization_method("OTSU").is_ok());
|
|
55
|
+
assert!(validate_binarization_method("Adaptive").is_ok());
|
|
56
|
+
assert!(validate_binarization_method("SAUVOLA").is_ok());
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
#[test]
|
|
60
|
+
fn test_validate_binarization_method_invalid() {
|
|
61
|
+
let result = validate_binarization_method("invalid");
|
|
62
|
+
assert!(result.is_err());
|
|
63
|
+
let msg = result.unwrap_err().to_string();
|
|
64
|
+
assert!(msg.contains("Invalid binarization method"));
|
|
65
|
+
assert!(msg.contains("otsu"));
|
|
66
|
+
}
|
|
67
|
+
|
|
68
|
+
#[test]
|
|
69
|
+
fn test_validate_token_reduction_level_valid() {
|
|
70
|
+
assert!(validate_token_reduction_level("off").is_ok());
|
|
71
|
+
assert!(validate_token_reduction_level("light").is_ok());
|
|
72
|
+
assert!(validate_token_reduction_level("moderate").is_ok());
|
|
73
|
+
assert!(validate_token_reduction_level("aggressive").is_ok());
|
|
74
|
+
assert!(validate_token_reduction_level("maximum").is_ok());
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
#[test]
|
|
78
|
+
fn test_validate_token_reduction_level_case_insensitive() {
|
|
79
|
+
assert!(validate_token_reduction_level("OFF").is_ok());
|
|
80
|
+
assert!(validate_token_reduction_level("Moderate").is_ok());
|
|
81
|
+
assert!(validate_token_reduction_level("MAXIMUM").is_ok());
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
#[test]
|
|
85
|
+
fn test_validate_token_reduction_level_invalid() {
|
|
86
|
+
let result = validate_token_reduction_level("extreme");
|
|
87
|
+
assert!(result.is_err());
|
|
88
|
+
let msg = result.unwrap_err().to_string();
|
|
89
|
+
assert!(msg.contains("Invalid token reduction level"));
|
|
90
|
+
}
|
|
91
|
+
|
|
92
|
+
#[test]
|
|
93
|
+
fn test_validate_ocr_backend_valid() {
|
|
94
|
+
assert!(validate_ocr_backend("tesseract").is_ok());
|
|
95
|
+
assert!(validate_ocr_backend("easyocr").is_ok());
|
|
96
|
+
assert!(validate_ocr_backend("paddleocr").is_ok());
|
|
97
|
+
}
|
|
98
|
+
|
|
99
|
+
#[test]
|
|
100
|
+
fn test_validate_ocr_backend_case_insensitive() {
|
|
101
|
+
assert!(validate_ocr_backend("TESSERACT").is_ok());
|
|
102
|
+
assert!(validate_ocr_backend("EasyOCR").is_ok());
|
|
103
|
+
assert!(validate_ocr_backend("PADDLEOCR").is_ok());
|
|
104
|
+
}
|
|
105
|
+
|
|
106
|
+
#[test]
|
|
107
|
+
fn test_validate_ocr_backend_invalid() {
|
|
108
|
+
let result = validate_ocr_backend("invalid_backend");
|
|
109
|
+
assert!(result.is_err());
|
|
110
|
+
let msg = result.unwrap_err().to_string();
|
|
111
|
+
assert!(msg.contains("Invalid OCR backend"));
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
#[test]
|
|
115
|
+
fn test_validate_language_code_valid_iso639_1() {
|
|
116
|
+
assert!(validate_language_code("en").is_ok());
|
|
117
|
+
assert!(validate_language_code("de").is_ok());
|
|
118
|
+
assert!(validate_language_code("fr").is_ok());
|
|
119
|
+
assert!(validate_language_code("es").is_ok());
|
|
120
|
+
assert!(validate_language_code("zh").is_ok());
|
|
121
|
+
assert!(validate_language_code("ja").is_ok());
|
|
122
|
+
assert!(validate_language_code("ko").is_ok());
|
|
123
|
+
}
|
|
124
|
+
|
|
125
|
+
#[test]
|
|
126
|
+
fn test_validate_language_code_valid_iso639_3() {
|
|
127
|
+
assert!(validate_language_code("eng").is_ok());
|
|
128
|
+
assert!(validate_language_code("deu").is_ok());
|
|
129
|
+
assert!(validate_language_code("fra").is_ok());
|
|
130
|
+
assert!(validate_language_code("spa").is_ok());
|
|
131
|
+
assert!(validate_language_code("zho").is_ok());
|
|
132
|
+
assert!(validate_language_code("jpn").is_ok());
|
|
133
|
+
assert!(validate_language_code("kor").is_ok());
|
|
134
|
+
}
|
|
135
|
+
|
|
136
|
+
#[test]
|
|
137
|
+
fn test_validate_language_code_case_insensitive() {
|
|
138
|
+
assert!(validate_language_code("EN").is_ok());
|
|
139
|
+
assert!(validate_language_code("ENG").is_ok());
|
|
140
|
+
assert!(validate_language_code("De").is_ok());
|
|
141
|
+
assert!(validate_language_code("DEU").is_ok());
|
|
142
|
+
}
|
|
143
|
+
|
|
144
|
+
#[test]
|
|
145
|
+
fn test_validate_language_code_invalid() {
|
|
146
|
+
let result = validate_language_code("invalid");
|
|
147
|
+
assert!(result.is_err());
|
|
148
|
+
let msg = result.unwrap_err().to_string();
|
|
149
|
+
assert!(msg.contains("Invalid language code"));
|
|
150
|
+
assert!(msg.contains("ISO 639"));
|
|
151
|
+
}
|
|
152
|
+
|
|
153
|
+
#[test]
|
|
154
|
+
fn test_validate_tesseract_psm_valid() {
|
|
155
|
+
for psm in 0..=13 {
|
|
156
|
+
assert!(validate_tesseract_psm(psm).is_ok(), "PSM {} should be valid", psm);
|
|
157
|
+
}
|
|
158
|
+
}
|
|
159
|
+
|
|
160
|
+
#[test]
|
|
161
|
+
fn test_validate_tesseract_psm_invalid() {
|
|
162
|
+
assert!(validate_tesseract_psm(-1).is_err());
|
|
163
|
+
assert!(validate_tesseract_psm(14).is_err());
|
|
164
|
+
assert!(validate_tesseract_psm(100).is_err());
|
|
165
|
+
}
|
|
166
|
+
|
|
167
|
+
#[test]
|
|
168
|
+
fn test_validate_tesseract_oem_valid() {
|
|
169
|
+
for oem in 0..=3 {
|
|
170
|
+
assert!(validate_tesseract_oem(oem).is_ok(), "OEM {} should be valid", oem);
|
|
171
|
+
}
|
|
172
|
+
}
|
|
173
|
+
|
|
174
|
+
#[test]
|
|
175
|
+
fn test_validate_tesseract_oem_invalid() {
|
|
176
|
+
assert!(validate_tesseract_oem(-1).is_err());
|
|
177
|
+
assert!(validate_tesseract_oem(4).is_err());
|
|
178
|
+
assert!(validate_tesseract_oem(10).is_err());
|
|
179
|
+
}
|
|
180
|
+
|
|
181
|
+
#[test]
|
|
182
|
+
fn test_validate_output_format_valid() {
|
|
183
|
+
assert!(validate_output_format("text").is_ok());
|
|
184
|
+
assert!(validate_output_format("markdown").is_ok());
|
|
185
|
+
}
|
|
186
|
+
|
|
187
|
+
#[test]
|
|
188
|
+
fn test_validate_output_format_case_insensitive() {
|
|
189
|
+
assert!(validate_output_format("TEXT").is_ok());
|
|
190
|
+
assert!(validate_output_format("Markdown").is_ok());
|
|
191
|
+
}
|
|
192
|
+
|
|
193
|
+
#[test]
|
|
194
|
+
fn test_validate_output_format_invalid() {
|
|
195
|
+
let result = validate_output_format("json");
|
|
196
|
+
assert!(result.is_err());
|
|
197
|
+
let msg = result.unwrap_err().to_string();
|
|
198
|
+
assert!(msg.contains("Invalid output format"));
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
#[test]
|
|
202
|
+
fn test_validate_confidence_valid() {
|
|
203
|
+
assert!(validate_confidence(0.0).is_ok());
|
|
204
|
+
assert!(validate_confidence(0.5).is_ok());
|
|
205
|
+
assert!(validate_confidence(1.0).is_ok());
|
|
206
|
+
assert!(validate_confidence(0.75).is_ok());
|
|
207
|
+
}
|
|
208
|
+
|
|
209
|
+
#[test]
|
|
210
|
+
fn test_validate_confidence_invalid() {
|
|
211
|
+
assert!(validate_confidence(-0.1).is_err());
|
|
212
|
+
assert!(validate_confidence(1.1).is_err());
|
|
213
|
+
assert!(validate_confidence(2.0).is_err());
|
|
214
|
+
}
|
|
215
|
+
|
|
216
|
+
#[test]
|
|
217
|
+
fn test_validate_dpi_valid() {
|
|
218
|
+
assert!(validate_dpi(72).is_ok());
|
|
219
|
+
assert!(validate_dpi(96).is_ok());
|
|
220
|
+
assert!(validate_dpi(300).is_ok());
|
|
221
|
+
assert!(validate_dpi(600).is_ok());
|
|
222
|
+
assert!(validate_dpi(1).is_ok());
|
|
223
|
+
}
|
|
224
|
+
|
|
225
|
+
#[test]
|
|
226
|
+
fn test_validate_dpi_invalid() {
|
|
227
|
+
assert!(validate_dpi(0).is_err());
|
|
228
|
+
assert!(validate_dpi(-1).is_err());
|
|
229
|
+
assert!(validate_dpi(2401).is_err());
|
|
230
|
+
}
|
|
231
|
+
|
|
232
|
+
#[test]
|
|
233
|
+
fn test_validate_chunking_params_valid() {
|
|
234
|
+
assert!(validate_chunking_params(1000, 200).is_ok());
|
|
235
|
+
assert!(validate_chunking_params(500, 50).is_ok());
|
|
236
|
+
assert!(validate_chunking_params(1, 0).is_ok());
|
|
237
|
+
}
|
|
238
|
+
|
|
239
|
+
#[test]
|
|
240
|
+
fn test_validate_chunking_params_zero_chars() {
|
|
241
|
+
let result = validate_chunking_params(0, 100);
|
|
242
|
+
assert!(result.is_err());
|
|
243
|
+
assert!(result.unwrap_err().to_string().contains("max_chars"));
|
|
244
|
+
}
|
|
245
|
+
|
|
246
|
+
#[test]
|
|
247
|
+
fn test_validate_chunking_params_overlap_too_large() {
|
|
248
|
+
let result = validate_chunking_params(100, 100);
|
|
249
|
+
assert!(result.is_err());
|
|
250
|
+
assert!(result.unwrap_err().to_string().contains("overlap"));
|
|
251
|
+
|
|
252
|
+
let result = validate_chunking_params(100, 150);
|
|
253
|
+
assert!(result.is_err());
|
|
254
|
+
}
|
|
255
|
+
|
|
256
|
+
#[test]
|
|
257
|
+
fn test_error_messages_are_helpful() {
|
|
258
|
+
let err = validate_binarization_method("bad").unwrap_err().to_string();
|
|
259
|
+
assert!(err.contains("otsu"));
|
|
260
|
+
assert!(err.contains("adaptive"));
|
|
261
|
+
assert!(err.contains("sauvola"));
|
|
262
|
+
|
|
263
|
+
let err = validate_token_reduction_level("bad").unwrap_err().to_string();
|
|
264
|
+
assert!(err.contains("off"));
|
|
265
|
+
assert!(err.contains("moderate"));
|
|
266
|
+
|
|
267
|
+
let err = validate_language_code("bad").unwrap_err().to_string();
|
|
268
|
+
assert!(err.contains("ISO 639"));
|
|
269
|
+
assert!(err.contains("en"));
|
|
270
|
+
}
|
|
271
|
+
|
|
272
|
+
// Tests for dependency validation functions
|
|
273
|
+
#[test]
|
|
274
|
+
fn test_validate_port_valid() {
|
|
275
|
+
assert!(validate_port(1).is_ok());
|
|
276
|
+
assert!(validate_port(80).is_ok());
|
|
277
|
+
assert!(validate_port(443).is_ok());
|
|
278
|
+
assert!(validate_port(8000).is_ok());
|
|
279
|
+
assert!(validate_port(65535).is_ok());
|
|
280
|
+
}
|
|
281
|
+
|
|
282
|
+
#[test]
|
|
283
|
+
fn test_validate_port_invalid() {
|
|
284
|
+
let result = validate_port(0);
|
|
285
|
+
assert!(result.is_err());
|
|
286
|
+
let msg = result.unwrap_err().to_string();
|
|
287
|
+
assert!(msg.contains("Port must be 1-65535"));
|
|
288
|
+
assert!(msg.contains("0"));
|
|
289
|
+
}
|
|
290
|
+
|
|
291
|
+
#[test]
|
|
292
|
+
fn test_validate_host_ipv4() {
|
|
293
|
+
assert!(validate_host("127.0.0.1").is_ok());
|
|
294
|
+
assert!(validate_host("0.0.0.0").is_ok());
|
|
295
|
+
assert!(validate_host("192.168.1.1").is_ok());
|
|
296
|
+
assert!(validate_host("10.0.0.1").is_ok());
|
|
297
|
+
assert!(validate_host("255.255.255.255").is_ok());
|
|
298
|
+
}
|
|
299
|
+
|
|
300
|
+
#[test]
|
|
301
|
+
fn test_validate_host_ipv6() {
|
|
302
|
+
assert!(validate_host("::1").is_ok());
|
|
303
|
+
assert!(validate_host("::").is_ok());
|
|
304
|
+
assert!(validate_host("2001:db8::1").is_ok());
|
|
305
|
+
assert!(validate_host("fe80::1").is_ok());
|
|
306
|
+
}
|
|
307
|
+
|
|
308
|
+
#[test]
|
|
309
|
+
fn test_validate_host_hostname() {
|
|
310
|
+
assert!(validate_host("localhost").is_ok());
|
|
311
|
+
assert!(validate_host("example.com").is_ok());
|
|
312
|
+
assert!(validate_host("sub.example.com").is_ok());
|
|
313
|
+
assert!(validate_host("api-server").is_ok());
|
|
314
|
+
assert!(validate_host("app123").is_ok());
|
|
315
|
+
}
|
|
316
|
+
|
|
317
|
+
#[test]
|
|
318
|
+
fn test_validate_host_invalid() {
|
|
319
|
+
let result = validate_host("");
|
|
320
|
+
assert!(result.is_err());
|
|
321
|
+
let msg = result.unwrap_err().to_string();
|
|
322
|
+
assert!(msg.contains("Invalid host"));
|
|
323
|
+
|
|
324
|
+
let result = validate_host("not a valid host");
|
|
325
|
+
assert!(result.is_err());
|
|
326
|
+
|
|
327
|
+
let result = validate_host("256.256.256.256");
|
|
328
|
+
assert!(result.is_err());
|
|
329
|
+
}
|
|
330
|
+
|
|
331
|
+
#[test]
|
|
332
|
+
fn test_validate_cors_origin_https() {
|
|
333
|
+
assert!(validate_cors_origin("https://example.com").is_ok());
|
|
334
|
+
assert!(validate_cors_origin("https://localhost:3000").is_ok());
|
|
335
|
+
assert!(validate_cors_origin("https://sub.example.com").is_ok());
|
|
336
|
+
assert!(validate_cors_origin("https://192.168.1.1").is_ok());
|
|
337
|
+
assert!(validate_cors_origin("https://example.com/path").is_ok());
|
|
338
|
+
}
|
|
339
|
+
|
|
340
|
+
#[test]
|
|
341
|
+
fn test_validate_cors_origin_http() {
|
|
342
|
+
assert!(validate_cors_origin("http://example.com").is_ok());
|
|
343
|
+
assert!(validate_cors_origin("http://localhost:3000").is_ok());
|
|
344
|
+
assert!(validate_cors_origin("http://127.0.0.1:8000").is_ok());
|
|
345
|
+
}
|
|
346
|
+
|
|
347
|
+
#[test]
|
|
348
|
+
fn test_validate_cors_origin_wildcard() {
|
|
349
|
+
assert!(validate_cors_origin("*").is_ok());
|
|
350
|
+
}
|
|
351
|
+
|
|
352
|
+
#[test]
|
|
353
|
+
fn test_validate_cors_origin_invalid() {
|
|
354
|
+
let result = validate_cors_origin("not-a-url");
|
|
355
|
+
assert!(result.is_err());
|
|
356
|
+
let msg = result.unwrap_err().to_string();
|
|
357
|
+
assert!(msg.contains("Invalid CORS origin"));
|
|
358
|
+
|
|
359
|
+
let result = validate_cors_origin("ftp://example.com");
|
|
360
|
+
assert!(result.is_err());
|
|
361
|
+
|
|
362
|
+
let result = validate_cors_origin("example.com");
|
|
363
|
+
assert!(result.is_err());
|
|
364
|
+
|
|
365
|
+
let result = validate_cors_origin("http://");
|
|
366
|
+
assert!(result.is_err());
|
|
367
|
+
}
|
|
368
|
+
|
|
369
|
+
#[test]
|
|
370
|
+
fn test_validate_upload_size_valid() {
|
|
371
|
+
assert!(validate_upload_size(1).is_ok());
|
|
372
|
+
assert!(validate_upload_size(1024).is_ok());
|
|
373
|
+
assert!(validate_upload_size(1_000_000).is_ok());
|
|
374
|
+
assert!(validate_upload_size(1_000_000_000).is_ok());
|
|
375
|
+
assert!(validate_upload_size(usize::MAX).is_ok());
|
|
376
|
+
}
|
|
377
|
+
|
|
378
|
+
#[test]
|
|
379
|
+
fn test_validate_upload_size_invalid() {
|
|
380
|
+
let result = validate_upload_size(0);
|
|
381
|
+
assert!(result.is_err());
|
|
382
|
+
let msg = result.unwrap_err().to_string();
|
|
383
|
+
assert!(msg.contains("Upload size must be greater than 0"));
|
|
384
|
+
assert!(msg.contains("0"));
|
|
385
|
+
}
|
|
386
|
+
}
|