kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.gitignore +0 -6
- data/.rubocop.yaml +534 -1
- data/Gemfile +2 -1
- data/Gemfile.lock +28 -116
- data/README.md +269 -629
- data/Rakefile +0 -9
- data/Steepfile +4 -8
- data/examples/async_patterns.rb +58 -1
- data/ext/kreuzberg_rb/extconf.rb +5 -35
- data/ext/kreuzberg_rb/native/Cargo.toml +16 -55
- data/ext/kreuzberg_rb/native/build.rs +14 -12
- data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
- data/ext/kreuzberg_rb/native/include/strings.h +2 -2
- data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
- data/ext/kreuzberg_rb/native/src/lib.rs +34 -897
- data/extconf.rb +6 -38
- data/kreuzberg.gemspec +20 -114
- data/lib/kreuzberg/api_proxy.rb +18 -2
- data/lib/kreuzberg/cache_api.rb +0 -22
- data/lib/kreuzberg/cli.rb +10 -2
- data/lib/kreuzberg/cli_proxy.rb +10 -0
- data/lib/kreuzberg/config.rb +22 -274
- data/lib/kreuzberg/errors.rb +7 -73
- data/lib/kreuzberg/extraction_api.rb +8 -237
- data/lib/kreuzberg/mcp_proxy.rb +11 -2
- data/lib/kreuzberg/ocr_backend_protocol.rb +73 -0
- data/lib/kreuzberg/post_processor_protocol.rb +71 -0
- data/lib/kreuzberg/result.rb +33 -151
- data/lib/kreuzberg/setup_lib_path.rb +2 -22
- data/lib/kreuzberg/validator_protocol.rb +73 -0
- data/lib/kreuzberg/version.rb +1 -1
- data/lib/kreuzberg.rb +13 -27
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg.rbs +12 -105
- data/spec/binding/cache_spec.rb +22 -22
- data/spec/binding/cli_proxy_spec.rb +4 -2
- data/spec/binding/cli_spec.rb +11 -12
- data/spec/binding/config_spec.rb +0 -74
- data/spec/binding/config_validation_spec.rb +6 -100
- data/spec/binding/error_handling_spec.rb +97 -283
- data/spec/binding/plugins/ocr_backend_spec.rb +8 -8
- data/spec/binding/plugins/postprocessor_spec.rb +11 -11
- data/spec/binding/plugins/validator_spec.rb +13 -12
- data/spec/examples.txt +104 -0
- data/spec/fixtures/config.toml +1 -0
- data/spec/fixtures/config.yaml +1 -0
- data/spec/fixtures/invalid_config.toml +1 -0
- data/spec/smoke/package_spec.rb +3 -2
- data/spec/spec_helper.rb +3 -1
- data/vendor/kreuzberg/Cargo.toml +67 -192
- data/vendor/kreuzberg/README.md +9 -97
- data/vendor/kreuzberg/build.rs +194 -516
- data/vendor/kreuzberg/src/api/handlers.rs +9 -130
- data/vendor/kreuzberg/src/api/mod.rs +3 -18
- data/vendor/kreuzberg/src/api/server.rs +71 -236
- data/vendor/kreuzberg/src/api/types.rs +7 -43
- data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +3 -27
- data/vendor/kreuzberg/src/chunking/mod.rs +79 -1705
- data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
- data/vendor/kreuzberg/src/core/config.rs +23 -905
- data/vendor/kreuzberg/src/core/extractor.rs +106 -403
- data/vendor/kreuzberg/src/core/io.rs +2 -4
- data/vendor/kreuzberg/src/core/mime.rs +12 -2
- data/vendor/kreuzberg/src/core/mod.rs +3 -22
- data/vendor/kreuzberg/src/core/pipeline.rs +78 -395
- data/vendor/kreuzberg/src/embeddings.rs +21 -169
- data/vendor/kreuzberg/src/error.rs +2 -2
- data/vendor/kreuzberg/src/extraction/archive.rs +31 -36
- data/vendor/kreuzberg/src/extraction/docx.rs +1 -365
- data/vendor/kreuzberg/src/extraction/email.rs +11 -12
- data/vendor/kreuzberg/src/extraction/excel.rs +129 -138
- data/vendor/kreuzberg/src/extraction/html.rs +170 -1447
- data/vendor/kreuzberg/src/extraction/image.rs +14 -138
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +3 -13
- data/vendor/kreuzberg/src/extraction/mod.rs +5 -21
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +94 -196
- data/vendor/kreuzberg/src/extraction/structured.rs +4 -5
- data/vendor/kreuzberg/src/extraction/table.rs +1 -2
- data/vendor/kreuzberg/src/extraction/text.rs +10 -18
- data/vendor/kreuzberg/src/extractors/archive.rs +0 -22
- data/vendor/kreuzberg/src/extractors/docx.rs +148 -69
- data/vendor/kreuzberg/src/extractors/email.rs +9 -37
- data/vendor/kreuzberg/src/extractors/excel.rs +40 -81
- data/vendor/kreuzberg/src/extractors/html.rs +173 -182
- data/vendor/kreuzberg/src/extractors/image.rs +8 -32
- data/vendor/kreuzberg/src/extractors/mod.rs +10 -171
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +64 -329
- data/vendor/kreuzberg/src/extractors/pptx.rs +34 -79
- data/vendor/kreuzberg/src/extractors/structured.rs +0 -16
- data/vendor/kreuzberg/src/extractors/text.rs +7 -30
- data/vendor/kreuzberg/src/extractors/xml.rs +8 -27
- data/vendor/kreuzberg/src/keywords/processor.rs +1 -9
- data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
- data/vendor/kreuzberg/src/language_detection/mod.rs +51 -94
- data/vendor/kreuzberg/src/lib.rs +5 -17
- data/vendor/kreuzberg/src/mcp/mod.rs +1 -4
- data/vendor/kreuzberg/src/mcp/server.rs +21 -145
- data/vendor/kreuzberg/src/ocr/mod.rs +0 -2
- data/vendor/kreuzberg/src/ocr/processor.rs +8 -19
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -2
- data/vendor/kreuzberg/src/pdf/error.rs +1 -93
- data/vendor/kreuzberg/src/pdf/metadata.rs +100 -263
- data/vendor/kreuzberg/src/pdf/mod.rs +2 -33
- data/vendor/kreuzberg/src/pdf/rendering.rs +12 -12
- data/vendor/kreuzberg/src/pdf/table.rs +64 -61
- data/vendor/kreuzberg/src/pdf/text.rs +24 -416
- data/vendor/kreuzberg/src/plugins/extractor.rs +8 -40
- data/vendor/kreuzberg/src/plugins/mod.rs +0 -3
- data/vendor/kreuzberg/src/plugins/ocr.rs +14 -22
- data/vendor/kreuzberg/src/plugins/processor.rs +1 -10
- data/vendor/kreuzberg/src/plugins/registry.rs +0 -15
- data/vendor/kreuzberg/src/plugins/validator.rs +8 -20
- data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
- data/vendor/kreuzberg/src/text/mod.rs +0 -8
- data/vendor/kreuzberg/src/text/quality.rs +15 -28
- data/vendor/kreuzberg/src/text/string_utils.rs +10 -22
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +50 -86
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +16 -37
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +1 -2
- data/vendor/kreuzberg/src/types.rs +67 -907
- data/vendor/kreuzberg/src/utils/mod.rs +0 -14
- data/vendor/kreuzberg/src/utils/quality.rs +3 -12
- data/vendor/kreuzberg/tests/api_tests.rs +0 -506
- data/vendor/kreuzberg/tests/archive_integration.rs +0 -2
- data/vendor/kreuzberg/tests/batch_orchestration.rs +12 -57
- data/vendor/kreuzberg/tests/batch_processing.rs +8 -32
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +8 -40
- data/vendor/kreuzberg/tests/config_features.rs +1 -33
- data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -16
- data/vendor/kreuzberg/tests/core_integration.rs +9 -35
- data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
- data/vendor/kreuzberg/tests/email_integration.rs +1 -3
- data/vendor/kreuzberg/tests/error_handling.rs +34 -43
- data/vendor/kreuzberg/tests/format_integration.rs +1 -7
- data/vendor/kreuzberg/tests/helpers/mod.rs +0 -60
- data/vendor/kreuzberg/tests/image_integration.rs +0 -2
- data/vendor/kreuzberg/tests/mime_detection.rs +16 -17
- data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -4
- data/vendor/kreuzberg/tests/ocr_errors.rs +0 -22
- data/vendor/kreuzberg/tests/ocr_quality.rs +0 -2
- data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +0 -2
- data/vendor/kreuzberg/tests/pipeline_integration.rs +2 -36
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -5
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -17
- data/vendor/kreuzberg/tests/plugin_system.rs +0 -6
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -2
- data/vendor/kreuzberg/tests/security_validation.rs +1 -13
- data/vendor/kreuzberg/tests/test_fastembed.rs +23 -45
- metadata +25 -171
- data/.rubocop.yml +0 -543
- data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -23
- data/ext/kreuzberg_rb/native/Cargo.lock +0 -7619
- data/lib/kreuzberg/error_context.rb +0 -136
- data/lib/kreuzberg/types.rb +0 -170
- data/lib/libpdfium.so +0 -0
- data/spec/binding/async_operations_spec.rb +0 -473
- data/spec/binding/batch_operations_spec.rb +0 -595
- data/spec/binding/batch_spec.rb +0 -359
- data/spec/binding/config_result_spec.rb +0 -377
- data/spec/binding/embeddings_spec.rb +0 -816
- data/spec/binding/error_recovery_spec.rb +0 -488
- data/spec/binding/font_config_spec.rb +0 -220
- data/spec/binding/images_spec.rb +0 -738
- data/spec/binding/keywords_extraction_spec.rb +0 -600
- data/spec/binding/metadata_types_spec.rb +0 -1228
- data/spec/binding/pages_extraction_spec.rb +0 -471
- data/spec/binding/tables_spec.rb +0 -641
- data/spec/unit/config/chunking_config_spec.rb +0 -213
- data/spec/unit/config/embedding_config_spec.rb +0 -343
- data/spec/unit/config/extraction_config_spec.rb +0 -438
- data/spec/unit/config/font_config_spec.rb +0 -285
- data/spec/unit/config/hierarchy_config_spec.rb +0 -314
- data/spec/unit/config/image_extraction_config_spec.rb +0 -209
- data/spec/unit/config/image_preprocessing_config_spec.rb +0 -249
- data/spec/unit/config/keyword_config_spec.rb +0 -229
- data/spec/unit/config/language_detection_config_spec.rb +0 -258
- data/spec/unit/config/ocr_config_spec.rb +0 -171
- data/spec/unit/config/page_config_spec.rb +0 -221
- data/spec/unit/config/pdf_config_spec.rb +0 -267
- data/spec/unit/config/postprocessor_config_spec.rb +0 -290
- data/spec/unit/config/tesseract_config_spec.rb +0 -181
- data/spec/unit/config/token_reduction_config_spec.rb +0 -251
- data/test/metadata_types_test.rb +0 -959
- data/vendor/Cargo.toml +0 -61
- data/vendor/kreuzberg/examples/bench_fixes.rs +0 -71
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +0 -62
- data/vendor/kreuzberg/src/chunking/processor.rs +0 -219
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -385
- data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
- data/vendor/kreuzberg/src/core/formats.rs +0 -235
- data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
- data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
- data/vendor/kreuzberg/src/extraction/markdown.rs +0 -216
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -284
- data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -470
- data/vendor/kreuzberg/src/extractors/docbook.rs +0 -504
- data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -492
- data/vendor/kreuzberg/src/extractors/jats.rs +0 -1054
- data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -368
- data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
- data/vendor/kreuzberg/src/extractors/markdown.rs +0 -701
- data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
- data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -529
- data/vendor/kreuzberg/src/extractors/rst.rs +0 -577
- data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
- data/vendor/kreuzberg/src/extractors/security.rs +0 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
- data/vendor/kreuzberg/src/extractors/typst.rs +0 -651
- data/vendor/kreuzberg/src/language_detection/processor.rs +0 -218
- data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -520
- data/vendor/kreuzberg/src/panic_context.rs +0 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +0 -306
- data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
- data/vendor/kreuzberg/src/pdf/fonts.rs +0 -358
- data/vendor/kreuzberg/src/pdf/hierarchy.rs +0 -903
- data/vendor/kreuzberg/src/text/quality_processor.rs +0 -231
- data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
- data/vendor/kreuzberg/src/utils/pool.rs +0 -503
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
- data/vendor/kreuzberg/src/utils/string_pool.rs +0 -761
- data/vendor/kreuzberg/tests/api_embed.rs +0 -360
- 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 -289
- data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
- data/vendor/kreuzberg/tests/config_integration_test.rs +0 -753
- data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -500
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
- data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
- data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -674
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
- data/vendor/kreuzberg/tests/page_markers.rs +0 -297
- data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -589
- data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -301
- data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -475
- data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -775
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1260
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -648
- data/vendor/kreuzberg-ffi/Cargo.toml +0 -67
- data/vendor/kreuzberg-ffi/README.md +0 -851
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -227
- data/vendor/kreuzberg-ffi/build.rs +0 -168
- data/vendor/kreuzberg-ffi/cbindgen.toml +0 -37
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
- data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3012
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -588
- data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
- data/vendor/kreuzberg-ffi/src/error.rs +0 -901
- data/vendor/kreuzberg-ffi/src/extraction.rs +0 -555
- data/vendor/kreuzberg-ffi/src/helpers.rs +0 -879
- data/vendor/kreuzberg-ffi/src/lib.rs +0 -977
- data/vendor/kreuzberg-ffi/src/memory.rs +0 -493
- data/vendor/kreuzberg-ffi/src/mime.rs +0 -329
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -265
- data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -442
- data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -14
- data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -628
- data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -438
- data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -329
- data/vendor/kreuzberg-ffi/src/result.rs +0 -510
- data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -639
- data/vendor/kreuzberg-ffi/src/result_view.rs +0 -773
- data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -568
- data/vendor/kreuzberg-ffi/src/types.rs +0 -363
- data/vendor/kreuzberg-ffi/src/util.rs +0 -210
- data/vendor/kreuzberg-ffi/src/validation.rs +0 -848
- 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-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 -57
- data/vendor/kreuzberg-tesseract/LICENSE +0 -22
- data/vendor/kreuzberg-tesseract/README.md +0 -399
- data/vendor/kreuzberg-tesseract/build.rs +0 -1127
- data/vendor/kreuzberg-tesseract/patches/README.md +0 -71
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
- data/vendor/kreuzberg-tesseract/src/api.rs +0 -1371
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
- data/vendor/kreuzberg-tesseract/src/enums.rs +0 -297
- data/vendor/kreuzberg-tesseract/src/error.rs +0 -81
- data/vendor/kreuzberg-tesseract/src/lib.rs +0 -145
- data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -57
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -253
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -286
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -183
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211
|
@@ -1,235 +0,0 @@
|
|
|
1
|
-
//! Format field validation and metadata.
|
|
2
|
-
//!
|
|
3
|
-
//! This module provides a compile-time registry of known format fields used across
|
|
4
|
-
//! document extractors. It serves as the single source of truth for format validation
|
|
5
|
-
//! across all language bindings (Rust, Python, TypeScript, Ruby, Java, Go).
|
|
6
|
-
//!
|
|
7
|
-
//! # Known Format Fields
|
|
8
|
-
//!
|
|
9
|
-
//! The registry contains 58 standardized format fields organized by category:
|
|
10
|
-
//! - **Document Properties**: format_type, title, author, keywords, creator, producer, etc.
|
|
11
|
-
//! - **Dates**: creation_date, modification_date
|
|
12
|
-
//! - **Pagination**: page_count, sheet_count, sheet_names
|
|
13
|
-
//! - **Email Metadata**: from_email, from_name, to_emails, cc_emails, bcc_emails, message_id
|
|
14
|
-
//! - **Attachments**: attachments
|
|
15
|
-
//! - **Descriptions**: description, summary
|
|
16
|
-
//! - **Typography**: fonts
|
|
17
|
-
//! - **Archive/Compression**: format, file_count, file_list, total_size, compressed_size
|
|
18
|
-
//! - **Images**: width, height
|
|
19
|
-
//! - **Content Metrics**: element_count, unique_elements, line_count, word_count, character_count
|
|
20
|
-
//! - **HTML Structure**: headers, links, code_blocks
|
|
21
|
-
//! - **Meta Tags**: canonical, base_href, og_*, twitter_*, link_*
|
|
22
|
-
//! - **OCR**: psm, output_format
|
|
23
|
-
//! - **Tables**: table_count, table_rows, table_cols
|
|
24
|
-
//!
|
|
25
|
-
//! # Example
|
|
26
|
-
//!
|
|
27
|
-
//! ```rust
|
|
28
|
-
//! use kreuzberg::core::formats::{KNOWN_FORMATS, is_valid_format_field};
|
|
29
|
-
//!
|
|
30
|
-
//! assert!(is_valid_format_field("title"));
|
|
31
|
-
//! assert!(!is_valid_format_field("invalid_field"));
|
|
32
|
-
//! assert_eq!(KNOWN_FORMATS.len(), 58);
|
|
33
|
-
//! ```
|
|
34
|
-
|
|
35
|
-
use ahash::AHashSet;
|
|
36
|
-
use once_cell::sync::Lazy;
|
|
37
|
-
|
|
38
|
-
/// All known format field names across all extractors.
|
|
39
|
-
///
|
|
40
|
-
/// This is a compile-time constant array of standardized field names used by document
|
|
41
|
-
/// extractors. Each binding (Python, TypeScript, Ruby, Java, Go) should reference this
|
|
42
|
-
/// as the single source of truth for format field validation.
|
|
43
|
-
///
|
|
44
|
-
/// Format fields are organized by document type:
|
|
45
|
-
/// - PDF/Office: title, author, creation_date, page_count, etc.
|
|
46
|
-
/// - Email: from_email, to_emails, cc_emails, bcc_emails, etc.
|
|
47
|
-
/// - Web: og_title, twitter_card, canonical, headers, links, etc.
|
|
48
|
-
/// - Images: width, height, format
|
|
49
|
-
/// - Archives: file_count, file_list, total_size, etc.
|
|
50
|
-
pub const KNOWN_FORMATS: &[&str] = &[
|
|
51
|
-
"format_type",
|
|
52
|
-
"title",
|
|
53
|
-
"author",
|
|
54
|
-
"keywords",
|
|
55
|
-
"creator",
|
|
56
|
-
"producer",
|
|
57
|
-
"creation_date",
|
|
58
|
-
"modification_date",
|
|
59
|
-
"page_count",
|
|
60
|
-
"sheet_count",
|
|
61
|
-
"sheet_names",
|
|
62
|
-
"from_email",
|
|
63
|
-
"from_name",
|
|
64
|
-
"to_emails",
|
|
65
|
-
"cc_emails",
|
|
66
|
-
"bcc_emails",
|
|
67
|
-
"message_id",
|
|
68
|
-
"attachments",
|
|
69
|
-
"description",
|
|
70
|
-
"summary",
|
|
71
|
-
"fonts",
|
|
72
|
-
"format",
|
|
73
|
-
"file_count",
|
|
74
|
-
"file_list",
|
|
75
|
-
"total_size",
|
|
76
|
-
"compressed_size",
|
|
77
|
-
"width",
|
|
78
|
-
"height",
|
|
79
|
-
"element_count",
|
|
80
|
-
"unique_elements",
|
|
81
|
-
"line_count",
|
|
82
|
-
"word_count",
|
|
83
|
-
"character_count",
|
|
84
|
-
"headers",
|
|
85
|
-
"links",
|
|
86
|
-
"code_blocks",
|
|
87
|
-
"canonical",
|
|
88
|
-
"base_href",
|
|
89
|
-
"og_title",
|
|
90
|
-
"og_description",
|
|
91
|
-
"og_image",
|
|
92
|
-
"og_url",
|
|
93
|
-
"og_type",
|
|
94
|
-
"og_site_name",
|
|
95
|
-
"twitter_card",
|
|
96
|
-
"twitter_title",
|
|
97
|
-
"twitter_description",
|
|
98
|
-
"twitter_image",
|
|
99
|
-
"twitter_site",
|
|
100
|
-
"twitter_creator",
|
|
101
|
-
"link_author",
|
|
102
|
-
"link_license",
|
|
103
|
-
"link_alternate",
|
|
104
|
-
"psm",
|
|
105
|
-
"output_format",
|
|
106
|
-
"table_count",
|
|
107
|
-
"table_rows",
|
|
108
|
-
"table_cols",
|
|
109
|
-
];
|
|
110
|
-
|
|
111
|
-
/// Cached format field set for fast O(1) lookups.
|
|
112
|
-
///
|
|
113
|
-
/// Uses AHashSet for its excellent cache locality and performance characteristics
|
|
114
|
-
/// with string keys. Built lazily on first use with minimal overhead.
|
|
115
|
-
static FORMAT_FIELD_SET: Lazy<AHashSet<&'static str>> = Lazy::new(|| KNOWN_FORMATS.iter().copied().collect());
|
|
116
|
-
|
|
117
|
-
/// Validates whether a field name is in the known formats registry.
|
|
118
|
-
///
|
|
119
|
-
/// This uses a pre-built hash set for O(1) lookups instead of linear search,
|
|
120
|
-
/// providing significant performance improvements for repeated validations.
|
|
121
|
-
///
|
|
122
|
-
/// # Arguments
|
|
123
|
-
///
|
|
124
|
-
/// * `field` - The field name to validate
|
|
125
|
-
///
|
|
126
|
-
/// # Returns
|
|
127
|
-
///
|
|
128
|
-
/// `true` if the field is in KNOWN_FORMATS, `false` otherwise.
|
|
129
|
-
///
|
|
130
|
-
/// # Example
|
|
131
|
-
///
|
|
132
|
-
/// ```rust
|
|
133
|
-
/// use kreuzberg::core::formats::is_valid_format_field;
|
|
134
|
-
///
|
|
135
|
-
/// assert!(is_valid_format_field("title"));
|
|
136
|
-
/// assert!(is_valid_format_field("creation_date"));
|
|
137
|
-
/// assert!(!is_valid_format_field("invalid_field"));
|
|
138
|
-
/// ```
|
|
139
|
-
#[inline]
|
|
140
|
-
pub fn is_valid_format_field(field: &str) -> bool {
|
|
141
|
-
FORMAT_FIELD_SET.contains(field)
|
|
142
|
-
}
|
|
143
|
-
|
|
144
|
-
#[cfg(test)]
|
|
145
|
-
mod tests {
|
|
146
|
-
use super::*;
|
|
147
|
-
|
|
148
|
-
#[test]
|
|
149
|
-
fn test_known_formats_count() {
|
|
150
|
-
assert_eq!(KNOWN_FORMATS.len(), 58, "Expected 58 known format fields");
|
|
151
|
-
}
|
|
152
|
-
|
|
153
|
-
#[test]
|
|
154
|
-
fn test_known_formats_no_duplicates() {
|
|
155
|
-
let mut seen = std::collections::HashSet::new();
|
|
156
|
-
for field in KNOWN_FORMATS {
|
|
157
|
-
assert!(seen.insert(field), "Duplicate format field found: {}", field);
|
|
158
|
-
}
|
|
159
|
-
}
|
|
160
|
-
|
|
161
|
-
#[test]
|
|
162
|
-
fn test_is_valid_format_field_true_cases() {
|
|
163
|
-
assert!(is_valid_format_field("title"));
|
|
164
|
-
assert!(is_valid_format_field("author"));
|
|
165
|
-
assert!(is_valid_format_field("creation_date"));
|
|
166
|
-
assert!(is_valid_format_field("page_count"));
|
|
167
|
-
assert!(is_valid_format_field("from_email"));
|
|
168
|
-
assert!(is_valid_format_field("og_title"));
|
|
169
|
-
assert!(is_valid_format_field("twitter_card"));
|
|
170
|
-
}
|
|
171
|
-
|
|
172
|
-
#[test]
|
|
173
|
-
fn test_is_valid_format_field_false_cases() {
|
|
174
|
-
assert!(!is_valid_format_field("invalid_field"));
|
|
175
|
-
assert!(!is_valid_format_field("unknown_metadata"));
|
|
176
|
-
assert!(!is_valid_format_field(""));
|
|
177
|
-
assert!(!is_valid_format_field("TITLE"));
|
|
178
|
-
assert!(!is_valid_format_field("title "));
|
|
179
|
-
}
|
|
180
|
-
|
|
181
|
-
#[test]
|
|
182
|
-
fn test_all_document_property_fields() {
|
|
183
|
-
let doc_fields = ["format_type", "title", "author", "keywords", "creator", "producer"];
|
|
184
|
-
for field in &doc_fields {
|
|
185
|
-
assert!(is_valid_format_field(field), "Missing field: {}", field);
|
|
186
|
-
}
|
|
187
|
-
}
|
|
188
|
-
|
|
189
|
-
#[test]
|
|
190
|
-
fn test_all_email_fields() {
|
|
191
|
-
let email_fields = [
|
|
192
|
-
"from_email",
|
|
193
|
-
"from_name",
|
|
194
|
-
"to_emails",
|
|
195
|
-
"cc_emails",
|
|
196
|
-
"bcc_emails",
|
|
197
|
-
"message_id",
|
|
198
|
-
"attachments",
|
|
199
|
-
];
|
|
200
|
-
for field in &email_fields {
|
|
201
|
-
assert!(is_valid_format_field(field), "Missing email field: {}", field);
|
|
202
|
-
}
|
|
203
|
-
}
|
|
204
|
-
|
|
205
|
-
#[test]
|
|
206
|
-
fn test_all_web_meta_fields() {
|
|
207
|
-
let web_fields = [
|
|
208
|
-
"og_title",
|
|
209
|
-
"og_description",
|
|
210
|
-
"og_image",
|
|
211
|
-
"og_url",
|
|
212
|
-
"og_type",
|
|
213
|
-
"og_site_name",
|
|
214
|
-
"twitter_card",
|
|
215
|
-
"twitter_title",
|
|
216
|
-
"twitter_description",
|
|
217
|
-
"twitter_image",
|
|
218
|
-
"twitter_site",
|
|
219
|
-
"twitter_creator",
|
|
220
|
-
"canonical",
|
|
221
|
-
"base_href",
|
|
222
|
-
];
|
|
223
|
-
for field in &web_fields {
|
|
224
|
-
assert!(is_valid_format_field(field), "Missing web field: {}", field);
|
|
225
|
-
}
|
|
226
|
-
}
|
|
227
|
-
|
|
228
|
-
#[test]
|
|
229
|
-
fn test_all_table_fields() {
|
|
230
|
-
let table_fields = ["table_count", "table_rows", "table_cols"];
|
|
231
|
-
for field in &table_fields {
|
|
232
|
-
assert!(is_valid_format_field(field), "Missing table field: {}", field);
|
|
233
|
-
}
|
|
234
|
-
}
|
|
235
|
-
}
|