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 +1,271 @@
|
|
|
1
|
+
//! Block-level container handlers for Djot parsing.
|
|
2
|
+
|
|
3
|
+
use super::state::{ExtractionState, push_block};
|
|
4
|
+
use crate::types::{Attributes, BlockType, FormattedBlock};
|
|
5
|
+
use jotdown::Container;
|
|
6
|
+
|
|
7
|
+
/// Handle start of block containers.
|
|
8
|
+
pub(super) fn handle_block_start(
|
|
9
|
+
state: &mut ExtractionState,
|
|
10
|
+
container: &Container,
|
|
11
|
+
_attrs: &jotdown::Attributes,
|
|
12
|
+
parsed_attrs: Option<Attributes>,
|
|
13
|
+
footnotes: &mut Vec<crate::types::Footnote>,
|
|
14
|
+
) -> bool {
|
|
15
|
+
match container {
|
|
16
|
+
Container::Heading { level, .. } => {
|
|
17
|
+
push_block(
|
|
18
|
+
state,
|
|
19
|
+
FormattedBlock {
|
|
20
|
+
block_type: BlockType::Heading,
|
|
21
|
+
level: Some(*level as usize),
|
|
22
|
+
inline_content: Vec::new(),
|
|
23
|
+
attributes: parsed_attrs,
|
|
24
|
+
language: None,
|
|
25
|
+
code: None,
|
|
26
|
+
children: Vec::new(),
|
|
27
|
+
},
|
|
28
|
+
);
|
|
29
|
+
true
|
|
30
|
+
}
|
|
31
|
+
Container::Paragraph => {
|
|
32
|
+
push_block(
|
|
33
|
+
state,
|
|
34
|
+
FormattedBlock {
|
|
35
|
+
block_type: BlockType::Paragraph,
|
|
36
|
+
level: None,
|
|
37
|
+
inline_content: Vec::new(),
|
|
38
|
+
attributes: parsed_attrs,
|
|
39
|
+
language: None,
|
|
40
|
+
code: None,
|
|
41
|
+
children: Vec::new(),
|
|
42
|
+
},
|
|
43
|
+
);
|
|
44
|
+
true
|
|
45
|
+
}
|
|
46
|
+
Container::Blockquote => {
|
|
47
|
+
push_block(
|
|
48
|
+
state,
|
|
49
|
+
FormattedBlock {
|
|
50
|
+
block_type: BlockType::Blockquote,
|
|
51
|
+
level: None,
|
|
52
|
+
inline_content: Vec::new(),
|
|
53
|
+
attributes: parsed_attrs,
|
|
54
|
+
language: None,
|
|
55
|
+
code: None,
|
|
56
|
+
children: Vec::new(),
|
|
57
|
+
},
|
|
58
|
+
);
|
|
59
|
+
true
|
|
60
|
+
}
|
|
61
|
+
Container::CodeBlock { language } => {
|
|
62
|
+
let lang_str = if language.is_empty() {
|
|
63
|
+
None
|
|
64
|
+
} else {
|
|
65
|
+
Some(language.to_string())
|
|
66
|
+
};
|
|
67
|
+
state.in_code_block = true;
|
|
68
|
+
state.code_content.clear();
|
|
69
|
+
push_block(
|
|
70
|
+
state,
|
|
71
|
+
FormattedBlock {
|
|
72
|
+
block_type: BlockType::CodeBlock,
|
|
73
|
+
level: None,
|
|
74
|
+
inline_content: Vec::new(),
|
|
75
|
+
attributes: parsed_attrs,
|
|
76
|
+
language: lang_str,
|
|
77
|
+
code: Some(String::new()),
|
|
78
|
+
children: Vec::new(),
|
|
79
|
+
},
|
|
80
|
+
);
|
|
81
|
+
true
|
|
82
|
+
}
|
|
83
|
+
Container::RawBlock { format } => {
|
|
84
|
+
state.in_raw_block = true;
|
|
85
|
+
state.raw_format = Some(format.to_string());
|
|
86
|
+
state.code_content.clear();
|
|
87
|
+
push_block(
|
|
88
|
+
state,
|
|
89
|
+
FormattedBlock {
|
|
90
|
+
block_type: BlockType::RawBlock,
|
|
91
|
+
level: None,
|
|
92
|
+
inline_content: Vec::new(),
|
|
93
|
+
attributes: parsed_attrs,
|
|
94
|
+
language: Some(format.to_string()),
|
|
95
|
+
code: Some(String::new()),
|
|
96
|
+
children: Vec::new(),
|
|
97
|
+
},
|
|
98
|
+
);
|
|
99
|
+
true
|
|
100
|
+
}
|
|
101
|
+
Container::List { kind, .. } => {
|
|
102
|
+
let block_type = match kind {
|
|
103
|
+
jotdown::ListKind::Ordered { .. } => BlockType::OrderedList,
|
|
104
|
+
jotdown::ListKind::Unordered(_) => BlockType::BulletList,
|
|
105
|
+
jotdown::ListKind::Task(_) => BlockType::TaskList,
|
|
106
|
+
};
|
|
107
|
+
push_block(
|
|
108
|
+
state,
|
|
109
|
+
FormattedBlock {
|
|
110
|
+
block_type,
|
|
111
|
+
level: None,
|
|
112
|
+
inline_content: Vec::new(),
|
|
113
|
+
attributes: parsed_attrs,
|
|
114
|
+
language: None,
|
|
115
|
+
code: None,
|
|
116
|
+
children: Vec::new(),
|
|
117
|
+
},
|
|
118
|
+
);
|
|
119
|
+
true
|
|
120
|
+
}
|
|
121
|
+
Container::ListItem => {
|
|
122
|
+
push_block(
|
|
123
|
+
state,
|
|
124
|
+
FormattedBlock {
|
|
125
|
+
block_type: BlockType::ListItem,
|
|
126
|
+
level: None,
|
|
127
|
+
inline_content: Vec::new(),
|
|
128
|
+
attributes: parsed_attrs,
|
|
129
|
+
language: None,
|
|
130
|
+
code: None,
|
|
131
|
+
children: Vec::new(),
|
|
132
|
+
},
|
|
133
|
+
);
|
|
134
|
+
true
|
|
135
|
+
}
|
|
136
|
+
Container::TaskListItem { checked } => {
|
|
137
|
+
let mut attrs = parsed_attrs.unwrap_or_default();
|
|
138
|
+
attrs.key_values.insert("checked".to_string(), checked.to_string());
|
|
139
|
+
push_block(
|
|
140
|
+
state,
|
|
141
|
+
FormattedBlock {
|
|
142
|
+
block_type: BlockType::ListItem,
|
|
143
|
+
level: None,
|
|
144
|
+
inline_content: Vec::new(),
|
|
145
|
+
attributes: Some(attrs),
|
|
146
|
+
language: None,
|
|
147
|
+
code: None,
|
|
148
|
+
children: Vec::new(),
|
|
149
|
+
},
|
|
150
|
+
);
|
|
151
|
+
true
|
|
152
|
+
}
|
|
153
|
+
Container::DescriptionList => {
|
|
154
|
+
push_block(
|
|
155
|
+
state,
|
|
156
|
+
FormattedBlock {
|
|
157
|
+
block_type: BlockType::DefinitionList,
|
|
158
|
+
level: None,
|
|
159
|
+
inline_content: Vec::new(),
|
|
160
|
+
attributes: parsed_attrs,
|
|
161
|
+
language: None,
|
|
162
|
+
code: None,
|
|
163
|
+
children: Vec::new(),
|
|
164
|
+
},
|
|
165
|
+
);
|
|
166
|
+
true
|
|
167
|
+
}
|
|
168
|
+
Container::DescriptionTerm => {
|
|
169
|
+
push_block(
|
|
170
|
+
state,
|
|
171
|
+
FormattedBlock {
|
|
172
|
+
block_type: BlockType::DefinitionTerm,
|
|
173
|
+
level: None,
|
|
174
|
+
inline_content: Vec::new(),
|
|
175
|
+
attributes: parsed_attrs,
|
|
176
|
+
language: None,
|
|
177
|
+
code: None,
|
|
178
|
+
children: Vec::new(),
|
|
179
|
+
},
|
|
180
|
+
);
|
|
181
|
+
true
|
|
182
|
+
}
|
|
183
|
+
Container::DescriptionDetails => {
|
|
184
|
+
push_block(
|
|
185
|
+
state,
|
|
186
|
+
FormattedBlock {
|
|
187
|
+
block_type: BlockType::DefinitionDescription,
|
|
188
|
+
level: None,
|
|
189
|
+
inline_content: Vec::new(),
|
|
190
|
+
attributes: parsed_attrs,
|
|
191
|
+
language: None,
|
|
192
|
+
code: None,
|
|
193
|
+
children: Vec::new(),
|
|
194
|
+
},
|
|
195
|
+
);
|
|
196
|
+
true
|
|
197
|
+
}
|
|
198
|
+
Container::Div { .. } => {
|
|
199
|
+
push_block(
|
|
200
|
+
state,
|
|
201
|
+
FormattedBlock {
|
|
202
|
+
block_type: BlockType::Div,
|
|
203
|
+
level: None,
|
|
204
|
+
inline_content: Vec::new(),
|
|
205
|
+
attributes: parsed_attrs,
|
|
206
|
+
language: None,
|
|
207
|
+
code: None,
|
|
208
|
+
children: Vec::new(),
|
|
209
|
+
},
|
|
210
|
+
);
|
|
211
|
+
true
|
|
212
|
+
}
|
|
213
|
+
Container::Section { .. } => {
|
|
214
|
+
push_block(
|
|
215
|
+
state,
|
|
216
|
+
FormattedBlock {
|
|
217
|
+
block_type: BlockType::Section,
|
|
218
|
+
level: None,
|
|
219
|
+
inline_content: Vec::new(),
|
|
220
|
+
attributes: parsed_attrs,
|
|
221
|
+
language: None,
|
|
222
|
+
code: None,
|
|
223
|
+
children: Vec::new(),
|
|
224
|
+
},
|
|
225
|
+
);
|
|
226
|
+
true
|
|
227
|
+
}
|
|
228
|
+
Container::Footnote { label } => {
|
|
229
|
+
// Start tracking a footnote definition
|
|
230
|
+
footnotes.push(crate::types::Footnote {
|
|
231
|
+
label: label.to_string(),
|
|
232
|
+
content: Vec::new(),
|
|
233
|
+
});
|
|
234
|
+
// We'll collect the content as blocks
|
|
235
|
+
push_block(
|
|
236
|
+
state,
|
|
237
|
+
FormattedBlock {
|
|
238
|
+
block_type: BlockType::Paragraph,
|
|
239
|
+
level: None,
|
|
240
|
+
inline_content: Vec::new(),
|
|
241
|
+
attributes: parsed_attrs,
|
|
242
|
+
language: None,
|
|
243
|
+
code: None,
|
|
244
|
+
children: Vec::new(),
|
|
245
|
+
},
|
|
246
|
+
);
|
|
247
|
+
true
|
|
248
|
+
}
|
|
249
|
+
_ => false,
|
|
250
|
+
}
|
|
251
|
+
}
|
|
252
|
+
|
|
253
|
+
/// Handle end of block containers.
|
|
254
|
+
pub(super) fn handle_block_end(_state: &mut ExtractionState, container: &Container) -> bool {
|
|
255
|
+
matches!(
|
|
256
|
+
container,
|
|
257
|
+
Container::Heading { .. }
|
|
258
|
+
| Container::Paragraph
|
|
259
|
+
| Container::Blockquote
|
|
260
|
+
| Container::CodeBlock { .. }
|
|
261
|
+
| Container::RawBlock { .. }
|
|
262
|
+
| Container::Div { .. }
|
|
263
|
+
| Container::Section { .. }
|
|
264
|
+
| Container::List { .. }
|
|
265
|
+
| Container::ListItem
|
|
266
|
+
| Container::TaskListItem { .. }
|
|
267
|
+
| Container::DescriptionList
|
|
268
|
+
| Container::DescriptionTerm
|
|
269
|
+
| Container::DescriptionDetails
|
|
270
|
+
)
|
|
271
|
+
}
|
|
@@ -0,0 +1,257 @@
|
|
|
1
|
+
//! Complete Djot content extraction.
|
|
2
|
+
//!
|
|
3
|
+
//! Handles extraction of rich DjotContent structures from Djot events.
|
|
4
|
+
|
|
5
|
+
use super::block_handlers::{handle_block_end, handle_block_start};
|
|
6
|
+
use super::event_handlers::{
|
|
7
|
+
finalize_block_element, handle_footnote_end, handle_footnote_reference, handle_symbol, handle_thematic_break,
|
|
8
|
+
};
|
|
9
|
+
use super::inline_handlers::{
|
|
10
|
+
finalize_inline_element, handle_image_end, handle_inline_end, handle_inline_start, handle_link_end, handle_math_end,
|
|
11
|
+
};
|
|
12
|
+
use super::state::{ExtractionState, pop_block};
|
|
13
|
+
use super::text_extraction::extract_text_from_events;
|
|
14
|
+
use crate::extractors::djot_format::attributes::parse_jotdown_attributes;
|
|
15
|
+
use crate::types::{Attributes, DjotContent, DjotImage, DjotLink, FormattedBlock};
|
|
16
|
+
use jotdown::{Container, Event};
|
|
17
|
+
use std::collections::HashMap;
|
|
18
|
+
|
|
19
|
+
/// Extract complete djot content with 100% feature extraction.
|
|
20
|
+
///
|
|
21
|
+
/// Processes ALL djot events to build a rich DjotContent structure including:
|
|
22
|
+
/// - Block structure (headings, lists, blockquotes, divs, sections, code blocks)
|
|
23
|
+
/// - Inline formatting (strong, emphasis, highlight, subscript, superscript, insert, delete)
|
|
24
|
+
/// - Attributes (classes, IDs, key-value pairs)
|
|
25
|
+
/// - Links and images with full metadata (href, src, alt, title)
|
|
26
|
+
/// - Math blocks (inline & display)
|
|
27
|
+
/// - Definition lists (term/description pairs)
|
|
28
|
+
/// - Task lists with checked state
|
|
29
|
+
/// - Raw blocks (HTML/LaTeX)
|
|
30
|
+
/// - Footnotes (references and definitions)
|
|
31
|
+
/// - Captions
|
|
32
|
+
/// - Smart punctuation
|
|
33
|
+
/// - All other djot features
|
|
34
|
+
pub fn extract_complete_djot_content(
|
|
35
|
+
events: &[Event],
|
|
36
|
+
metadata: crate::types::Metadata,
|
|
37
|
+
tables: Vec<crate::types::Table>,
|
|
38
|
+
) -> DjotContent {
|
|
39
|
+
let plain_text = extract_text_from_events(events);
|
|
40
|
+
|
|
41
|
+
let mut blocks = Vec::new();
|
|
42
|
+
let mut images = Vec::new();
|
|
43
|
+
let mut links = Vec::new();
|
|
44
|
+
let mut footnotes = Vec::new();
|
|
45
|
+
let attributes_map: HashMap<String, Attributes> = HashMap::new();
|
|
46
|
+
|
|
47
|
+
let mut state = ExtractionState::new();
|
|
48
|
+
|
|
49
|
+
for event in events {
|
|
50
|
+
match event {
|
|
51
|
+
Event::Start(container, attrs) => {
|
|
52
|
+
handle_start_event(
|
|
53
|
+
&mut state,
|
|
54
|
+
container,
|
|
55
|
+
attrs,
|
|
56
|
+
&mut blocks,
|
|
57
|
+
&mut images,
|
|
58
|
+
&mut links,
|
|
59
|
+
&mut footnotes,
|
|
60
|
+
);
|
|
61
|
+
}
|
|
62
|
+
Event::End(container) => {
|
|
63
|
+
handle_end_event(
|
|
64
|
+
&mut state,
|
|
65
|
+
container,
|
|
66
|
+
&mut blocks,
|
|
67
|
+
&mut images,
|
|
68
|
+
&mut links,
|
|
69
|
+
&mut footnotes,
|
|
70
|
+
);
|
|
71
|
+
}
|
|
72
|
+
Event::Str(s) => {
|
|
73
|
+
if state.in_code_block || state.in_raw_block {
|
|
74
|
+
state.code_content.push_str(s);
|
|
75
|
+
} else if state.in_math {
|
|
76
|
+
state.math_content.push_str(s);
|
|
77
|
+
} else {
|
|
78
|
+
state.current_text.push_str(s);
|
|
79
|
+
}
|
|
80
|
+
}
|
|
81
|
+
Event::FootnoteReference(label) => {
|
|
82
|
+
handle_footnote_reference(&mut state, label);
|
|
83
|
+
}
|
|
84
|
+
Event::Symbol(sym) => {
|
|
85
|
+
handle_symbol(&mut state, sym);
|
|
86
|
+
}
|
|
87
|
+
Event::Attributes(attrs) => {
|
|
88
|
+
// Store attributes to be applied to the next element
|
|
89
|
+
state.pending_attributes = Some(parse_jotdown_attributes(attrs));
|
|
90
|
+
}
|
|
91
|
+
Event::Softbreak => {
|
|
92
|
+
if state.in_math {
|
|
93
|
+
state.math_content.push(' ');
|
|
94
|
+
} else if !state.inline_type_stack.is_empty() {
|
|
95
|
+
state.current_text.push(' ');
|
|
96
|
+
} else {
|
|
97
|
+
state.current_text.push('\n');
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
Event::Hardbreak => {
|
|
101
|
+
if state.in_math {
|
|
102
|
+
state.math_content.push('\n');
|
|
103
|
+
} else {
|
|
104
|
+
state.current_text.push('\n');
|
|
105
|
+
}
|
|
106
|
+
}
|
|
107
|
+
Event::NonBreakingSpace => {
|
|
108
|
+
state.current_text.push(' ');
|
|
109
|
+
}
|
|
110
|
+
Event::Blankline => {
|
|
111
|
+
// Blank lines are typically ignored in block processing
|
|
112
|
+
}
|
|
113
|
+
Event::ThematicBreak(attrs) => {
|
|
114
|
+
handle_thematic_break(&mut state, attrs, &mut blocks);
|
|
115
|
+
}
|
|
116
|
+
// Smart punctuation events
|
|
117
|
+
Event::LeftSingleQuote => {
|
|
118
|
+
state.current_text.push('\'');
|
|
119
|
+
}
|
|
120
|
+
Event::RightSingleQuote => {
|
|
121
|
+
state.current_text.push('\'');
|
|
122
|
+
}
|
|
123
|
+
Event::LeftDoubleQuote => {
|
|
124
|
+
state.current_text.push('"');
|
|
125
|
+
}
|
|
126
|
+
Event::RightDoubleQuote => {
|
|
127
|
+
state.current_text.push('"');
|
|
128
|
+
}
|
|
129
|
+
Event::Ellipsis => {
|
|
130
|
+
state.current_text.push_str("...");
|
|
131
|
+
}
|
|
132
|
+
Event::EnDash => {
|
|
133
|
+
state.current_text.push_str("--");
|
|
134
|
+
}
|
|
135
|
+
Event::EmDash => {
|
|
136
|
+
state.current_text.push_str("---");
|
|
137
|
+
}
|
|
138
|
+
Event::Escape => {
|
|
139
|
+
// Escape is a marker, doesn't produce output
|
|
140
|
+
}
|
|
141
|
+
}
|
|
142
|
+
}
|
|
143
|
+
|
|
144
|
+
// Finalize any remaining content
|
|
145
|
+
state.flush_text();
|
|
146
|
+
|
|
147
|
+
// Pop any remaining blocks
|
|
148
|
+
while !state.block_stack.is_empty() {
|
|
149
|
+
pop_block(&mut state, &mut blocks);
|
|
150
|
+
}
|
|
151
|
+
|
|
152
|
+
// Add any remaining inline elements to the last block if exists
|
|
153
|
+
if !state.current_inline_elements.is_empty()
|
|
154
|
+
&& let Some(last_block) = blocks.last_mut()
|
|
155
|
+
{
|
|
156
|
+
last_block.inline_content.append(&mut state.current_inline_elements);
|
|
157
|
+
}
|
|
158
|
+
|
|
159
|
+
DjotContent {
|
|
160
|
+
plain_text,
|
|
161
|
+
blocks,
|
|
162
|
+
metadata,
|
|
163
|
+
tables,
|
|
164
|
+
images,
|
|
165
|
+
links,
|
|
166
|
+
footnotes,
|
|
167
|
+
attributes: attributes_map,
|
|
168
|
+
}
|
|
169
|
+
}
|
|
170
|
+
|
|
171
|
+
/// Handle start of a container event.
|
|
172
|
+
fn handle_start_event(
|
|
173
|
+
state: &mut ExtractionState,
|
|
174
|
+
container: &Container,
|
|
175
|
+
attrs: &jotdown::Attributes,
|
|
176
|
+
_blocks: &mut Vec<FormattedBlock>,
|
|
177
|
+
images: &mut Vec<DjotImage>,
|
|
178
|
+
links: &mut Vec<DjotLink>,
|
|
179
|
+
footnotes: &mut Vec<crate::types::Footnote>,
|
|
180
|
+
) {
|
|
181
|
+
// Parse attributes from jotdown's Attributes type
|
|
182
|
+
let parsed_attrs = if attrs.is_empty() {
|
|
183
|
+
state.pending_attributes.take()
|
|
184
|
+
} else {
|
|
185
|
+
Some(parse_jotdown_attributes(attrs))
|
|
186
|
+
};
|
|
187
|
+
|
|
188
|
+
// Try block handlers first
|
|
189
|
+
if handle_block_start(state, container, attrs, parsed_attrs.clone(), footnotes) {
|
|
190
|
+
return;
|
|
191
|
+
}
|
|
192
|
+
|
|
193
|
+
// Try inline handlers
|
|
194
|
+
if handle_inline_start(state, container, parsed_attrs, images, links) {
|
|
195
|
+
return;
|
|
196
|
+
}
|
|
197
|
+
|
|
198
|
+
// Handle remaining containers (tables, link definitions, etc.)
|
|
199
|
+
match container {
|
|
200
|
+
Container::Table | Container::TableRow { .. } | Container::TableCell { .. } | Container::Caption => {
|
|
201
|
+
// Tables are extracted separately
|
|
202
|
+
}
|
|
203
|
+
Container::LinkDefinition { .. } => {
|
|
204
|
+
// Link definitions are resolved by jotdown, not needed in output
|
|
205
|
+
}
|
|
206
|
+
_ => {}
|
|
207
|
+
}
|
|
208
|
+
}
|
|
209
|
+
|
|
210
|
+
/// Handle end of a container event.
|
|
211
|
+
fn handle_end_event(
|
|
212
|
+
state: &mut ExtractionState,
|
|
213
|
+
container: &Container,
|
|
214
|
+
blocks: &mut Vec<FormattedBlock>,
|
|
215
|
+
images: &mut [DjotImage],
|
|
216
|
+
links: &mut [DjotLink],
|
|
217
|
+
footnotes: &mut [crate::types::Footnote],
|
|
218
|
+
) {
|
|
219
|
+
// Check if it's a block container
|
|
220
|
+
if handle_block_end(state, container) {
|
|
221
|
+
finalize_block_element(state, blocks);
|
|
222
|
+
return;
|
|
223
|
+
}
|
|
224
|
+
|
|
225
|
+
// Handle special cases
|
|
226
|
+
match container {
|
|
227
|
+
Container::Footnote { .. } => {
|
|
228
|
+
handle_footnote_end(state, footnotes);
|
|
229
|
+
}
|
|
230
|
+
Container::Math { display } => {
|
|
231
|
+
handle_math_end(state, *display);
|
|
232
|
+
}
|
|
233
|
+
Container::Link(url, _) => {
|
|
234
|
+
handle_link_end(state, url, links);
|
|
235
|
+
}
|
|
236
|
+
Container::Image(src, _) => {
|
|
237
|
+
handle_image_end(state, src, images);
|
|
238
|
+
}
|
|
239
|
+
_ => {
|
|
240
|
+
// Check if it's an inline element
|
|
241
|
+
if handle_inline_end(state, container) {
|
|
242
|
+
finalize_inline_element(state, container);
|
|
243
|
+
}
|
|
244
|
+
}
|
|
245
|
+
}
|
|
246
|
+
|
|
247
|
+
// Handle remaining containers (tables, link definitions, etc.)
|
|
248
|
+
match container {
|
|
249
|
+
Container::Table | Container::TableRow { .. } | Container::TableCell { .. } | Container::Caption => {
|
|
250
|
+
// Tables are handled separately
|
|
251
|
+
}
|
|
252
|
+
Container::LinkDefinition { .. } => {
|
|
253
|
+
// Link definitions don't produce output
|
|
254
|
+
}
|
|
255
|
+
_ => {}
|
|
256
|
+
}
|
|
257
|
+
}
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
//! Event handlers for special Djot elements.
|
|
2
|
+
|
|
3
|
+
use super::state::{ExtractionState, pop_block};
|
|
4
|
+
use crate::extractors::djot_format::attributes::parse_jotdown_attributes;
|
|
5
|
+
use crate::types::{BlockType, FormattedBlock, InlineElement, InlineType};
|
|
6
|
+
use std::collections::HashMap;
|
|
7
|
+
|
|
8
|
+
/// Handle footnote reference event.
|
|
9
|
+
pub(super) fn handle_footnote_reference(state: &mut ExtractionState, label: &str) {
|
|
10
|
+
state.flush_text();
|
|
11
|
+
|
|
12
|
+
let mut meta = HashMap::new();
|
|
13
|
+
meta.insert("label".to_string(), label.to_string());
|
|
14
|
+
|
|
15
|
+
state.current_inline_elements.push(InlineElement {
|
|
16
|
+
element_type: InlineType::FootnoteRef,
|
|
17
|
+
content: label.to_string(),
|
|
18
|
+
attributes: None,
|
|
19
|
+
metadata: Some(meta),
|
|
20
|
+
});
|
|
21
|
+
}
|
|
22
|
+
|
|
23
|
+
/// Handle symbol event.
|
|
24
|
+
pub(super) fn handle_symbol(state: &mut ExtractionState, sym: &str) {
|
|
25
|
+
state.flush_text();
|
|
26
|
+
|
|
27
|
+
state.current_inline_elements.push(InlineElement {
|
|
28
|
+
element_type: InlineType::Symbol,
|
|
29
|
+
content: sym.to_string(),
|
|
30
|
+
attributes: None,
|
|
31
|
+
metadata: None,
|
|
32
|
+
});
|
|
33
|
+
}
|
|
34
|
+
|
|
35
|
+
/// Handle thematic break event.
|
|
36
|
+
pub(super) fn handle_thematic_break(
|
|
37
|
+
state: &mut ExtractionState,
|
|
38
|
+
attrs: &jotdown::Attributes,
|
|
39
|
+
blocks: &mut Vec<FormattedBlock>,
|
|
40
|
+
) {
|
|
41
|
+
state.flush_text();
|
|
42
|
+
|
|
43
|
+
let parsed_attrs = if attrs.is_empty() {
|
|
44
|
+
None
|
|
45
|
+
} else {
|
|
46
|
+
Some(parse_jotdown_attributes(attrs))
|
|
47
|
+
};
|
|
48
|
+
|
|
49
|
+
let hr_block = FormattedBlock {
|
|
50
|
+
block_type: BlockType::ThematicBreak,
|
|
51
|
+
level: None,
|
|
52
|
+
inline_content: Vec::new(),
|
|
53
|
+
attributes: parsed_attrs,
|
|
54
|
+
language: None,
|
|
55
|
+
code: None,
|
|
56
|
+
children: Vec::new(),
|
|
57
|
+
};
|
|
58
|
+
|
|
59
|
+
if let Some(parent) = state.block_stack.last_mut() {
|
|
60
|
+
parent.children.push(hr_block);
|
|
61
|
+
} else {
|
|
62
|
+
blocks.push(hr_block);
|
|
63
|
+
}
|
|
64
|
+
}
|
|
65
|
+
|
|
66
|
+
/// Handle end of footnote definition.
|
|
67
|
+
pub(super) fn handle_footnote_end(state: &mut ExtractionState, footnotes: &mut [crate::types::Footnote]) {
|
|
68
|
+
state.flush_text();
|
|
69
|
+
// Pop the footnote content block and add to the last footnote
|
|
70
|
+
if let Some(mut block) = state.block_stack.pop() {
|
|
71
|
+
block.inline_content.append(&mut state.current_inline_elements);
|
|
72
|
+
if let Some(footnote) = footnotes.last_mut() {
|
|
73
|
+
footnote.content.push(block);
|
|
74
|
+
}
|
|
75
|
+
}
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
/// Finalize block element content and pop from stack.
|
|
79
|
+
pub(super) fn finalize_block_element(state: &mut ExtractionState, blocks: &mut Vec<FormattedBlock>) {
|
|
80
|
+
// Flush any remaining text
|
|
81
|
+
state.flush_text();
|
|
82
|
+
|
|
83
|
+
// For code blocks, set the accumulated code content
|
|
84
|
+
if state.in_code_block {
|
|
85
|
+
if let Some(block) = state.block_stack.last_mut() {
|
|
86
|
+
block.code = Some(std::mem::take(&mut state.code_content));
|
|
87
|
+
}
|
|
88
|
+
state.in_code_block = false;
|
|
89
|
+
}
|
|
90
|
+
|
|
91
|
+
// For raw blocks
|
|
92
|
+
if state.in_raw_block {
|
|
93
|
+
if let Some(block) = state.block_stack.last_mut() {
|
|
94
|
+
block.code = Some(std::mem::take(&mut state.code_content));
|
|
95
|
+
}
|
|
96
|
+
state.in_raw_block = false;
|
|
97
|
+
state.raw_format = None;
|
|
98
|
+
}
|
|
99
|
+
|
|
100
|
+
pop_block(state, blocks);
|
|
101
|
+
}
|