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 +1,452 @@
|
|
|
1
|
+
//! Djot content rendering to djot markup.
|
|
2
|
+
//!
|
|
3
|
+
//! Converts DjotContent structures back to valid djot markup with full formatting preservation.
|
|
4
|
+
|
|
5
|
+
use super::attributes::render_attributes;
|
|
6
|
+
use crate::types::{BlockType, FormattedBlock, InlineElement, InlineType};
|
|
7
|
+
|
|
8
|
+
/// Render a single block to djot markup.
|
|
9
|
+
pub fn render_block_to_djot(output: &mut String, block: &FormattedBlock, indent_level: usize) {
|
|
10
|
+
let indent = " ".repeat(indent_level);
|
|
11
|
+
|
|
12
|
+
// Render attributes if present
|
|
13
|
+
let attrs_str = block.attributes.as_ref().map(render_attributes).unwrap_or_default();
|
|
14
|
+
|
|
15
|
+
match block.block_type {
|
|
16
|
+
BlockType::Heading => {
|
|
17
|
+
let level = block.level.unwrap_or(1);
|
|
18
|
+
let hashes = "#".repeat(level);
|
|
19
|
+
output.push_str(&indent);
|
|
20
|
+
output.push_str(&hashes);
|
|
21
|
+
output.push(' ');
|
|
22
|
+
render_inline_content(output, &block.inline_content);
|
|
23
|
+
if !attrs_str.is_empty() {
|
|
24
|
+
output.push(' ');
|
|
25
|
+
output.push_str(&attrs_str);
|
|
26
|
+
}
|
|
27
|
+
output.push('\n');
|
|
28
|
+
output.push('\n');
|
|
29
|
+
}
|
|
30
|
+
BlockType::Paragraph => {
|
|
31
|
+
output.push_str(&indent);
|
|
32
|
+
render_inline_content(output, &block.inline_content);
|
|
33
|
+
if !attrs_str.is_empty() {
|
|
34
|
+
output.push(' ');
|
|
35
|
+
output.push_str(&attrs_str);
|
|
36
|
+
}
|
|
37
|
+
output.push('\n');
|
|
38
|
+
output.push('\n');
|
|
39
|
+
}
|
|
40
|
+
BlockType::CodeBlock => {
|
|
41
|
+
if !attrs_str.is_empty() {
|
|
42
|
+
output.push_str(&indent);
|
|
43
|
+
output.push_str(&attrs_str);
|
|
44
|
+
output.push('\n');
|
|
45
|
+
}
|
|
46
|
+
output.push_str(&indent);
|
|
47
|
+
output.push_str("```");
|
|
48
|
+
if let Some(ref lang) = block.language {
|
|
49
|
+
output.push(' ');
|
|
50
|
+
output.push_str(lang);
|
|
51
|
+
}
|
|
52
|
+
output.push('\n');
|
|
53
|
+
if let Some(ref code) = block.code {
|
|
54
|
+
for line in code.lines() {
|
|
55
|
+
output.push_str(&indent);
|
|
56
|
+
output.push_str(line);
|
|
57
|
+
output.push('\n');
|
|
58
|
+
}
|
|
59
|
+
} else {
|
|
60
|
+
// Fall back to inline content if code field is empty
|
|
61
|
+
for elem in &block.inline_content {
|
|
62
|
+
output.push_str(&indent);
|
|
63
|
+
output.push_str(&elem.content);
|
|
64
|
+
output.push('\n');
|
|
65
|
+
}
|
|
66
|
+
}
|
|
67
|
+
output.push_str(&indent);
|
|
68
|
+
output.push_str("```\n\n");
|
|
69
|
+
}
|
|
70
|
+
BlockType::Blockquote => {
|
|
71
|
+
if !attrs_str.is_empty() {
|
|
72
|
+
output.push_str(&indent);
|
|
73
|
+
output.push_str(&attrs_str);
|
|
74
|
+
output.push('\n');
|
|
75
|
+
}
|
|
76
|
+
// Render inline content as quoted
|
|
77
|
+
output.push_str(&indent);
|
|
78
|
+
output.push_str("> ");
|
|
79
|
+
render_inline_content(output, &block.inline_content);
|
|
80
|
+
output.push('\n');
|
|
81
|
+
// Render children (nested content)
|
|
82
|
+
for child in &block.children {
|
|
83
|
+
let child_output = {
|
|
84
|
+
let mut s = String::new();
|
|
85
|
+
render_block_to_djot(&mut s, child, 0);
|
|
86
|
+
s
|
|
87
|
+
};
|
|
88
|
+
for line in child_output.lines() {
|
|
89
|
+
output.push_str(&indent);
|
|
90
|
+
output.push_str("> ");
|
|
91
|
+
output.push_str(line);
|
|
92
|
+
output.push('\n');
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
output.push('\n');
|
|
96
|
+
}
|
|
97
|
+
BlockType::BulletList => {
|
|
98
|
+
if !attrs_str.is_empty() {
|
|
99
|
+
output.push_str(&indent);
|
|
100
|
+
output.push_str(&attrs_str);
|
|
101
|
+
output.push('\n');
|
|
102
|
+
}
|
|
103
|
+
for child in &block.children {
|
|
104
|
+
render_list_item(output, child, &indent, "- ");
|
|
105
|
+
}
|
|
106
|
+
output.push('\n');
|
|
107
|
+
}
|
|
108
|
+
BlockType::OrderedList => {
|
|
109
|
+
if !attrs_str.is_empty() {
|
|
110
|
+
output.push_str(&indent);
|
|
111
|
+
output.push_str(&attrs_str);
|
|
112
|
+
output.push('\n');
|
|
113
|
+
}
|
|
114
|
+
for (i, child) in block.children.iter().enumerate() {
|
|
115
|
+
let marker = format!("{}. ", i + 1);
|
|
116
|
+
render_list_item(output, child, &indent, &marker);
|
|
117
|
+
}
|
|
118
|
+
output.push('\n');
|
|
119
|
+
}
|
|
120
|
+
BlockType::TaskList => {
|
|
121
|
+
if !attrs_str.is_empty() {
|
|
122
|
+
output.push_str(&indent);
|
|
123
|
+
output.push_str(&attrs_str);
|
|
124
|
+
output.push('\n');
|
|
125
|
+
}
|
|
126
|
+
for child in &block.children {
|
|
127
|
+
// Task list items use [ ] or [x] syntax
|
|
128
|
+
render_list_item(output, child, &indent, "- [ ] ");
|
|
129
|
+
}
|
|
130
|
+
output.push('\n');
|
|
131
|
+
}
|
|
132
|
+
BlockType::ListItem => {
|
|
133
|
+
// List items are typically rendered by their parent list
|
|
134
|
+
output.push_str(&indent);
|
|
135
|
+
render_inline_content(output, &block.inline_content);
|
|
136
|
+
output.push('\n');
|
|
137
|
+
for child in &block.children {
|
|
138
|
+
render_block_to_djot(output, child, indent_level + 1);
|
|
139
|
+
}
|
|
140
|
+
}
|
|
141
|
+
BlockType::DefinitionList => {
|
|
142
|
+
if !attrs_str.is_empty() {
|
|
143
|
+
output.push_str(&indent);
|
|
144
|
+
output.push_str(&attrs_str);
|
|
145
|
+
output.push('\n');
|
|
146
|
+
}
|
|
147
|
+
for child in &block.children {
|
|
148
|
+
render_block_to_djot(output, child, indent_level);
|
|
149
|
+
}
|
|
150
|
+
output.push('\n');
|
|
151
|
+
}
|
|
152
|
+
BlockType::DefinitionTerm => {
|
|
153
|
+
output.push_str(&indent);
|
|
154
|
+
render_inline_content(output, &block.inline_content);
|
|
155
|
+
output.push('\n');
|
|
156
|
+
}
|
|
157
|
+
BlockType::DefinitionDescription => {
|
|
158
|
+
output.push_str(&indent);
|
|
159
|
+
output.push_str(": ");
|
|
160
|
+
render_inline_content(output, &block.inline_content);
|
|
161
|
+
output.push('\n');
|
|
162
|
+
}
|
|
163
|
+
BlockType::Div => {
|
|
164
|
+
output.push_str(&indent);
|
|
165
|
+
output.push_str(":::");
|
|
166
|
+
if !attrs_str.is_empty() {
|
|
167
|
+
output.push(' ');
|
|
168
|
+
output.push_str(&attrs_str);
|
|
169
|
+
}
|
|
170
|
+
output.push('\n');
|
|
171
|
+
for child in &block.children {
|
|
172
|
+
render_block_to_djot(output, child, indent_level);
|
|
173
|
+
}
|
|
174
|
+
output.push_str(&indent);
|
|
175
|
+
output.push_str(":::\n\n");
|
|
176
|
+
}
|
|
177
|
+
BlockType::Section => {
|
|
178
|
+
// Sections don't have special syntax, just render children
|
|
179
|
+
if !attrs_str.is_empty() {
|
|
180
|
+
output.push_str(&indent);
|
|
181
|
+
output.push_str(&attrs_str);
|
|
182
|
+
output.push('\n');
|
|
183
|
+
}
|
|
184
|
+
for child in &block.children {
|
|
185
|
+
render_block_to_djot(output, child, indent_level);
|
|
186
|
+
}
|
|
187
|
+
}
|
|
188
|
+
BlockType::ThematicBreak => {
|
|
189
|
+
output.push_str(&indent);
|
|
190
|
+
output.push_str("---\n\n");
|
|
191
|
+
}
|
|
192
|
+
BlockType::RawBlock => {
|
|
193
|
+
// Raw blocks use ``` with format specifier
|
|
194
|
+
output.push_str(&indent);
|
|
195
|
+
output.push_str("```");
|
|
196
|
+
if let Some(ref lang) = block.language {
|
|
197
|
+
output.push('=');
|
|
198
|
+
output.push_str(lang);
|
|
199
|
+
}
|
|
200
|
+
output.push('\n');
|
|
201
|
+
for elem in &block.inline_content {
|
|
202
|
+
output.push_str(&indent);
|
|
203
|
+
output.push_str(&elem.content);
|
|
204
|
+
output.push('\n');
|
|
205
|
+
}
|
|
206
|
+
output.push_str(&indent);
|
|
207
|
+
output.push_str("```\n\n");
|
|
208
|
+
}
|
|
209
|
+
BlockType::MathDisplay => {
|
|
210
|
+
output.push_str(&indent);
|
|
211
|
+
output.push_str("$$\n");
|
|
212
|
+
for elem in &block.inline_content {
|
|
213
|
+
output.push_str(&indent);
|
|
214
|
+
output.push_str(&elem.content);
|
|
215
|
+
output.push('\n');
|
|
216
|
+
}
|
|
217
|
+
output.push_str(&indent);
|
|
218
|
+
output.push_str("$$\n\n");
|
|
219
|
+
}
|
|
220
|
+
}
|
|
221
|
+
}
|
|
222
|
+
|
|
223
|
+
/// Render a list item with the given marker.
|
|
224
|
+
pub fn render_list_item(output: &mut String, item: &FormattedBlock, indent: &str, marker: &str) {
|
|
225
|
+
output.push_str(indent);
|
|
226
|
+
output.push_str(marker);
|
|
227
|
+
render_inline_content(output, &item.inline_content);
|
|
228
|
+
output.push('\n');
|
|
229
|
+
for child in &item.children {
|
|
230
|
+
render_block_to_djot(output, child, 1);
|
|
231
|
+
}
|
|
232
|
+
}
|
|
233
|
+
|
|
234
|
+
/// Render inline content to djot markup.
|
|
235
|
+
pub fn render_inline_content(output: &mut String, elements: &[InlineElement]) {
|
|
236
|
+
for elem in elements {
|
|
237
|
+
let attrs_str = elem.attributes.as_ref().map(render_attributes).unwrap_or_default();
|
|
238
|
+
|
|
239
|
+
match elem.element_type {
|
|
240
|
+
InlineType::Text => {
|
|
241
|
+
output.push_str(&elem.content);
|
|
242
|
+
}
|
|
243
|
+
InlineType::Strong => {
|
|
244
|
+
output.push('*');
|
|
245
|
+
output.push_str(&elem.content);
|
|
246
|
+
output.push('*');
|
|
247
|
+
if !attrs_str.is_empty() {
|
|
248
|
+
output.push_str(&attrs_str);
|
|
249
|
+
}
|
|
250
|
+
}
|
|
251
|
+
InlineType::Emphasis => {
|
|
252
|
+
output.push('_');
|
|
253
|
+
output.push_str(&elem.content);
|
|
254
|
+
output.push('_');
|
|
255
|
+
if !attrs_str.is_empty() {
|
|
256
|
+
output.push_str(&attrs_str);
|
|
257
|
+
}
|
|
258
|
+
}
|
|
259
|
+
InlineType::Highlight => {
|
|
260
|
+
output.push_str("{=");
|
|
261
|
+
output.push_str(&elem.content);
|
|
262
|
+
output.push_str("=}");
|
|
263
|
+
if !attrs_str.is_empty() {
|
|
264
|
+
output.push_str(&attrs_str);
|
|
265
|
+
}
|
|
266
|
+
}
|
|
267
|
+
InlineType::Subscript => {
|
|
268
|
+
output.push('~');
|
|
269
|
+
output.push_str(&elem.content);
|
|
270
|
+
output.push('~');
|
|
271
|
+
if !attrs_str.is_empty() {
|
|
272
|
+
output.push_str(&attrs_str);
|
|
273
|
+
}
|
|
274
|
+
}
|
|
275
|
+
InlineType::Superscript => {
|
|
276
|
+
output.push('^');
|
|
277
|
+
output.push_str(&elem.content);
|
|
278
|
+
output.push('^');
|
|
279
|
+
if !attrs_str.is_empty() {
|
|
280
|
+
output.push_str(&attrs_str);
|
|
281
|
+
}
|
|
282
|
+
}
|
|
283
|
+
InlineType::Insert => {
|
|
284
|
+
output.push_str("{+");
|
|
285
|
+
output.push_str(&elem.content);
|
|
286
|
+
output.push_str("+}");
|
|
287
|
+
if !attrs_str.is_empty() {
|
|
288
|
+
output.push_str(&attrs_str);
|
|
289
|
+
}
|
|
290
|
+
}
|
|
291
|
+
InlineType::Delete => {
|
|
292
|
+
output.push_str("{-");
|
|
293
|
+
output.push_str(&elem.content);
|
|
294
|
+
output.push_str("-}");
|
|
295
|
+
if !attrs_str.is_empty() {
|
|
296
|
+
output.push_str(&attrs_str);
|
|
297
|
+
}
|
|
298
|
+
}
|
|
299
|
+
InlineType::Code => {
|
|
300
|
+
output.push('`');
|
|
301
|
+
output.push_str(&elem.content);
|
|
302
|
+
output.push('`');
|
|
303
|
+
if !attrs_str.is_empty() {
|
|
304
|
+
output.push_str(&attrs_str);
|
|
305
|
+
}
|
|
306
|
+
}
|
|
307
|
+
InlineType::Link => {
|
|
308
|
+
let href = elem
|
|
309
|
+
.metadata
|
|
310
|
+
.as_ref()
|
|
311
|
+
.and_then(|m| m.get("href"))
|
|
312
|
+
.map(|s| s.as_str())
|
|
313
|
+
.unwrap_or("");
|
|
314
|
+
output.push('[');
|
|
315
|
+
output.push_str(&elem.content);
|
|
316
|
+
output.push_str("](");
|
|
317
|
+
output.push_str(href);
|
|
318
|
+
output.push(')');
|
|
319
|
+
if !attrs_str.is_empty() {
|
|
320
|
+
output.push_str(&attrs_str);
|
|
321
|
+
}
|
|
322
|
+
}
|
|
323
|
+
InlineType::Image => {
|
|
324
|
+
let src = elem
|
|
325
|
+
.metadata
|
|
326
|
+
.as_ref()
|
|
327
|
+
.and_then(|m| m.get("src"))
|
|
328
|
+
.map(|s| s.as_str())
|
|
329
|
+
.unwrap_or("");
|
|
330
|
+
output.push_str(";
|
|
333
|
+
output.push_str(src);
|
|
334
|
+
output.push(')');
|
|
335
|
+
if !attrs_str.is_empty() {
|
|
336
|
+
output.push_str(&attrs_str);
|
|
337
|
+
}
|
|
338
|
+
}
|
|
339
|
+
InlineType::Span => {
|
|
340
|
+
output.push('[');
|
|
341
|
+
output.push_str(&elem.content);
|
|
342
|
+
output.push(']');
|
|
343
|
+
if !attrs_str.is_empty() {
|
|
344
|
+
output.push_str(&attrs_str);
|
|
345
|
+
}
|
|
346
|
+
}
|
|
347
|
+
InlineType::Math => {
|
|
348
|
+
output.push('$');
|
|
349
|
+
output.push_str(&elem.content);
|
|
350
|
+
output.push('$');
|
|
351
|
+
}
|
|
352
|
+
InlineType::RawInline => {
|
|
353
|
+
// Raw inline uses `content`{=format}
|
|
354
|
+
let format = elem
|
|
355
|
+
.metadata
|
|
356
|
+
.as_ref()
|
|
357
|
+
.and_then(|m| m.get("format"))
|
|
358
|
+
.map(|s| s.as_str())
|
|
359
|
+
.unwrap_or("html");
|
|
360
|
+
output.push('`');
|
|
361
|
+
output.push_str(&elem.content);
|
|
362
|
+
output.push_str("`{=");
|
|
363
|
+
output.push_str(format);
|
|
364
|
+
output.push('}');
|
|
365
|
+
}
|
|
366
|
+
InlineType::FootnoteRef => {
|
|
367
|
+
output.push_str("[^");
|
|
368
|
+
output.push_str(&elem.content);
|
|
369
|
+
output.push(']');
|
|
370
|
+
}
|
|
371
|
+
InlineType::Symbol => {
|
|
372
|
+
output.push(':');
|
|
373
|
+
output.push_str(&elem.content);
|
|
374
|
+
output.push(':');
|
|
375
|
+
}
|
|
376
|
+
}
|
|
377
|
+
}
|
|
378
|
+
}
|
|
379
|
+
|
|
380
|
+
#[cfg(test)]
|
|
381
|
+
mod tests {
|
|
382
|
+
use super::*;
|
|
383
|
+
use crate::types::{DjotContent, Metadata};
|
|
384
|
+
|
|
385
|
+
#[test]
|
|
386
|
+
fn test_render_heading() {
|
|
387
|
+
let content = DjotContent {
|
|
388
|
+
plain_text: "Test Heading".to_string(),
|
|
389
|
+
blocks: vec![FormattedBlock {
|
|
390
|
+
block_type: BlockType::Heading,
|
|
391
|
+
level: Some(1),
|
|
392
|
+
inline_content: vec![InlineElement {
|
|
393
|
+
element_type: InlineType::Text,
|
|
394
|
+
content: "Test Heading".to_string(),
|
|
395
|
+
attributes: None,
|
|
396
|
+
metadata: None,
|
|
397
|
+
}],
|
|
398
|
+
attributes: None,
|
|
399
|
+
language: None,
|
|
400
|
+
code: None,
|
|
401
|
+
children: vec![],
|
|
402
|
+
}],
|
|
403
|
+
metadata: Metadata::default(),
|
|
404
|
+
tables: vec![],
|
|
405
|
+
images: vec![],
|
|
406
|
+
links: vec![],
|
|
407
|
+
footnotes: vec![],
|
|
408
|
+
attributes: Default::default(),
|
|
409
|
+
};
|
|
410
|
+
|
|
411
|
+
let mut output = String::new();
|
|
412
|
+
for block in &content.blocks {
|
|
413
|
+
render_block_to_djot(&mut output, block, 0);
|
|
414
|
+
}
|
|
415
|
+
|
|
416
|
+
assert!(output.contains("# Test Heading"));
|
|
417
|
+
}
|
|
418
|
+
|
|
419
|
+
#[test]
|
|
420
|
+
fn test_render_paragraph() {
|
|
421
|
+
let content = DjotContent {
|
|
422
|
+
plain_text: "Test paragraph".to_string(),
|
|
423
|
+
blocks: vec![FormattedBlock {
|
|
424
|
+
block_type: BlockType::Paragraph,
|
|
425
|
+
level: None,
|
|
426
|
+
inline_content: vec![InlineElement {
|
|
427
|
+
element_type: InlineType::Text,
|
|
428
|
+
content: "Test paragraph".to_string(),
|
|
429
|
+
attributes: None,
|
|
430
|
+
metadata: None,
|
|
431
|
+
}],
|
|
432
|
+
attributes: None,
|
|
433
|
+
language: None,
|
|
434
|
+
code: None,
|
|
435
|
+
children: vec![],
|
|
436
|
+
}],
|
|
437
|
+
metadata: Metadata::default(),
|
|
438
|
+
tables: vec![],
|
|
439
|
+
images: vec![],
|
|
440
|
+
links: vec![],
|
|
441
|
+
footnotes: vec![],
|
|
442
|
+
attributes: Default::default(),
|
|
443
|
+
};
|
|
444
|
+
|
|
445
|
+
let mut output = String::new();
|
|
446
|
+
for block in &content.blocks {
|
|
447
|
+
render_block_to_djot(&mut output, block, 0);
|
|
448
|
+
}
|
|
449
|
+
|
|
450
|
+
assert!(output.contains("Test paragraph"));
|
|
451
|
+
}
|
|
452
|
+
}
|
|
@@ -182,6 +182,7 @@ impl DocumentExtractor for DocxExtractor {
|
|
|
182
182
|
};
|
|
183
183
|
|
|
184
184
|
let mut metadata_map = std::collections::HashMap::new();
|
|
185
|
+
let mut parsed_keywords: Option<Vec<String>> = None;
|
|
185
186
|
|
|
186
187
|
if let Ok(core) = office_metadata::extract_core_properties(&mut archive) {
|
|
187
188
|
if let Some(title) = core.title {
|
|
@@ -198,7 +199,14 @@ impl DocumentExtractor for DocxExtractor {
|
|
|
198
199
|
metadata_map.insert("subject".to_string(), serde_json::Value::String(subject));
|
|
199
200
|
}
|
|
200
201
|
if let Some(keywords) = core.keywords {
|
|
201
|
-
|
|
202
|
+
// Parse comma-separated keywords into Vec<String>
|
|
203
|
+
parsed_keywords = Some(
|
|
204
|
+
keywords
|
|
205
|
+
.split(',')
|
|
206
|
+
.map(|s| s.trim().to_string())
|
|
207
|
+
.filter(|s| !s.is_empty())
|
|
208
|
+
.collect(),
|
|
209
|
+
);
|
|
202
210
|
}
|
|
203
211
|
if let Some(description) = core.description {
|
|
204
212
|
metadata_map.insert("description".to_string(), serde_json::Value::String(description));
|
|
@@ -296,6 +304,7 @@ impl DocumentExtractor for DocxExtractor {
|
|
|
296
304
|
mime_type: mime_type.to_string(),
|
|
297
305
|
metadata: Metadata {
|
|
298
306
|
pages: page_structure,
|
|
307
|
+
keywords: parsed_keywords,
|
|
299
308
|
additional: metadata_map,
|
|
300
309
|
..Default::default()
|
|
301
310
|
},
|
|
@@ -304,6 +313,8 @@ impl DocumentExtractor for DocxExtractor {
|
|
|
304
313
|
detected_languages: None,
|
|
305
314
|
chunks: None,
|
|
306
315
|
images: Some(vec![]),
|
|
316
|
+
djot_content: None,
|
|
317
|
+
elements: None,
|
|
307
318
|
})
|
|
308
319
|
}
|
|
309
320
|
|