kreuzberg 4.0.0.pre.rc.6
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 +7 -0
- data/.gitignore +14 -0
- data/.rspec +3 -0
- data/.rubocop.yaml +1 -0
- data/.rubocop.yml +538 -0
- data/Gemfile +8 -0
- data/Gemfile.lock +157 -0
- data/README.md +426 -0
- data/Rakefile +25 -0
- data/Steepfile +47 -0
- data/examples/async_patterns.rb +341 -0
- data/ext/kreuzberg_rb/extconf.rb +45 -0
- data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +44 -0
- data/ext/kreuzberg_rb/native/README.md +425 -0
- data/ext/kreuzberg_rb/native/build.rs +15 -0
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
- data/ext/kreuzberg_rb/native/include/strings.h +20 -0
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
- data/ext/kreuzberg_rb/native/src/lib.rs +2998 -0
- data/extconf.rb +28 -0
- data/kreuzberg.gemspec +148 -0
- data/lib/kreuzberg/api_proxy.rb +142 -0
- data/lib/kreuzberg/cache_api.rb +46 -0
- data/lib/kreuzberg/cli.rb +55 -0
- data/lib/kreuzberg/cli_proxy.rb +127 -0
- data/lib/kreuzberg/config.rb +691 -0
- data/lib/kreuzberg/error_context.rb +32 -0
- data/lib/kreuzberg/errors.rb +118 -0
- data/lib/kreuzberg/extraction_api.rb +85 -0
- data/lib/kreuzberg/mcp_proxy.rb +186 -0
- data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
- data/lib/kreuzberg/post_processor_protocol.rb +86 -0
- data/lib/kreuzberg/result.rb +216 -0
- data/lib/kreuzberg/setup_lib_path.rb +80 -0
- data/lib/kreuzberg/validator_protocol.rb +89 -0
- data/lib/kreuzberg/version.rb +5 -0
- data/lib/kreuzberg.rb +103 -0
- data/sig/kreuzberg/internal.rbs +184 -0
- data/sig/kreuzberg.rbs +520 -0
- data/spec/binding/cache_spec.rb +227 -0
- data/spec/binding/cli_proxy_spec.rb +85 -0
- data/spec/binding/cli_spec.rb +55 -0
- data/spec/binding/config_spec.rb +345 -0
- data/spec/binding/config_validation_spec.rb +283 -0
- data/spec/binding/error_handling_spec.rb +213 -0
- data/spec/binding/errors_spec.rb +66 -0
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
- data/spec/binding/plugins/postprocessor_spec.rb +269 -0
- data/spec/binding/plugins/validator_spec.rb +274 -0
- data/spec/fixtures/config.toml +39 -0
- data/spec/fixtures/config.yaml +41 -0
- data/spec/fixtures/invalid_config.toml +4 -0
- data/spec/smoke/package_spec.rb +178 -0
- data/spec/spec_helper.rb +42 -0
- data/vendor/kreuzberg/Cargo.toml +204 -0
- data/vendor/kreuzberg/README.md +175 -0
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
- data/vendor/kreuzberg/build.rs +474 -0
- data/vendor/kreuzberg/src/api/error.rs +81 -0
- data/vendor/kreuzberg/src/api/handlers.rs +199 -0
- data/vendor/kreuzberg/src/api/mod.rs +79 -0
- data/vendor/kreuzberg/src/api/server.rs +353 -0
- data/vendor/kreuzberg/src/api/types.rs +170 -0
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -0
- data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -0
- data/vendor/kreuzberg/src/core/config.rs +1032 -0
- data/vendor/kreuzberg/src/core/extractor.rs +1024 -0
- data/vendor/kreuzberg/src/core/io.rs +329 -0
- data/vendor/kreuzberg/src/core/mime.rs +605 -0
- data/vendor/kreuzberg/src/core/mod.rs +45 -0
- data/vendor/kreuzberg/src/core/pipeline.rs +984 -0
- data/vendor/kreuzberg/src/embeddings.rs +432 -0
- data/vendor/kreuzberg/src/error.rs +431 -0
- data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
- data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
- data/vendor/kreuzberg/src/extraction/email.rs +854 -0
- data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
- data/vendor/kreuzberg/src/extraction/html.rs +553 -0
- data/vendor/kreuzberg/src/extraction/image.rs +368 -0
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -0
- data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +81 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
- data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
- data/vendor/kreuzberg/src/extraction/table.rs +328 -0
- data/vendor/kreuzberg/src/extraction/text.rs +269 -0
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
- data/vendor/kreuzberg/src/extractors/archive.rs +446 -0
- data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
- data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
- data/vendor/kreuzberg/src/extractors/docx.rs +367 -0
- data/vendor/kreuzberg/src/extractors/email.rs +143 -0
- data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +343 -0
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
- data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
- data/vendor/kreuzberg/src/extractors/html.rs +393 -0
- data/vendor/kreuzberg/src/extractors/image.rs +198 -0
- data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
- data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
- data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
- data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
- data/vendor/kreuzberg/src/extractors/mod.rs +365 -0
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
- data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
- data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +493 -0
- data/vendor/kreuzberg/src/extractors/pptx.rs +248 -0
- data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
- data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
- data/vendor/kreuzberg/src/extractors/security.rs +484 -0
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
- data/vendor/kreuzberg/src/extractors/structured.rs +140 -0
- data/vendor/kreuzberg/src/extractors/text.rs +260 -0
- data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +135 -0
- data/vendor/kreuzberg/src/image/dpi.rs +164 -0
- data/vendor/kreuzberg/src/image/mod.rs +6 -0
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
- data/vendor/kreuzberg/src/image/resize.rs +89 -0
- data/vendor/kreuzberg/src/keywords/config.rs +154 -0
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
- data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -0
- data/vendor/kreuzberg/src/keywords/types.rs +68 -0
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
- data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
- data/vendor/kreuzberg/src/lib.rs +105 -0
- data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
- data/vendor/kreuzberg/src/mcp/server.rs +1968 -0
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
- data/vendor/kreuzberg/src/ocr/error.rs +37 -0
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
- data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
- data/vendor/kreuzberg/src/ocr/processor.rs +863 -0
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
- data/vendor/kreuzberg/src/ocr/types.rs +393 -0
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
- data/vendor/kreuzberg/src/panic_context.rs +154 -0
- data/vendor/kreuzberg/src/pdf/error.rs +122 -0
- data/vendor/kreuzberg/src/pdf/images.rs +139 -0
- data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
- data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
- data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
- data/vendor/kreuzberg/src/pdf/table.rs +393 -0
- data/vendor/kreuzberg/src/pdf/text.rs +158 -0
- data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -0
- data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
- data/vendor/kreuzberg/src/plugins/ocr.rs +620 -0
- data/vendor/kreuzberg/src/plugins/processor.rs +642 -0
- data/vendor/kreuzberg/src/plugins/registry.rs +1337 -0
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
- data/vendor/kreuzberg/src/plugins/validator.rs +956 -0
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
- data/vendor/kreuzberg/src/text/mod.rs +19 -0
- data/vendor/kreuzberg/src/text/quality.rs +697 -0
- data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
- data/vendor/kreuzberg/src/types.rs +903 -0
- data/vendor/kreuzberg/src/utils/mod.rs +17 -0
- data/vendor/kreuzberg/src/utils/quality.rs +959 -0
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
- data/vendor/kreuzberg/tests/api_tests.rs +966 -0
- data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
- data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +316 -0
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -0
- data/vendor/kreuzberg/tests/config_features.rs +598 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -0
- data/vendor/kreuzberg/tests/core_integration.rs +510 -0
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -0
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -0
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
- data/vendor/kreuzberg/tests/email_integration.rs +325 -0
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
- data/vendor/kreuzberg/tests/error_handling.rs +393 -0
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
- data/vendor/kreuzberg/tests/format_integration.rs +159 -0
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
- data/vendor/kreuzberg/tests/image_integration.rs +253 -0
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
- data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
- data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
- data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
- data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -0
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -0
- data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -0
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
- data/vendor/kreuzberg/tests/security_validation.rs +415 -0
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
- data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
- data/vendor/rb-sys/.cargo-ok +1 -0
- data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
- data/vendor/rb-sys/Cargo.lock +393 -0
- data/vendor/rb-sys/Cargo.toml +70 -0
- data/vendor/rb-sys/Cargo.toml.orig +57 -0
- data/vendor/rb-sys/LICENSE-APACHE +190 -0
- data/vendor/rb-sys/LICENSE-MIT +21 -0
- data/vendor/rb-sys/bin/release.sh +21 -0
- data/vendor/rb-sys/build/features.rs +108 -0
- data/vendor/rb-sys/build/main.rs +246 -0
- data/vendor/rb-sys/build/stable_api_config.rs +153 -0
- data/vendor/rb-sys/build/version.rs +48 -0
- data/vendor/rb-sys/readme.md +36 -0
- data/vendor/rb-sys/src/bindings.rs +21 -0
- data/vendor/rb-sys/src/hidden.rs +11 -0
- data/vendor/rb-sys/src/lib.rs +34 -0
- data/vendor/rb-sys/src/macros.rs +371 -0
- data/vendor/rb-sys/src/memory.rs +53 -0
- data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
- data/vendor/rb-sys/src/special_consts.rs +31 -0
- data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
- data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
- data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
- data/vendor/rb-sys/src/stable_api.rs +261 -0
- data/vendor/rb-sys/src/symbol.rs +31 -0
- data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
- data/vendor/rb-sys/src/utils.rs +89 -0
- data/vendor/rb-sys/src/value_type.rs +7 -0
- metadata +536 -0
|
@@ -0,0 +1,135 @@
|
|
|
1
|
+
//! XML extractor.
|
|
2
|
+
|
|
3
|
+
use crate::Result;
|
|
4
|
+
use crate::core::config::ExtractionConfig;
|
|
5
|
+
use crate::extraction::xml::parse_xml;
|
|
6
|
+
use crate::plugins::{DocumentExtractor, Plugin};
|
|
7
|
+
use crate::types::ExtractionResult;
|
|
8
|
+
use async_trait::async_trait;
|
|
9
|
+
|
|
10
|
+
/// XML extractor.
|
|
11
|
+
///
|
|
12
|
+
/// Extracts text content from XML files, preserving element structure information.
|
|
13
|
+
pub struct XmlExtractor;
|
|
14
|
+
|
|
15
|
+
impl XmlExtractor {
|
|
16
|
+
/// Create a new XML extractor.
|
|
17
|
+
pub fn new() -> Self {
|
|
18
|
+
Self
|
|
19
|
+
}
|
|
20
|
+
}
|
|
21
|
+
|
|
22
|
+
impl Default for XmlExtractor {
|
|
23
|
+
fn default() -> Self {
|
|
24
|
+
Self::new()
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
impl Plugin for XmlExtractor {
|
|
29
|
+
fn name(&self) -> &str {
|
|
30
|
+
"xml-extractor"
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
fn version(&self) -> String {
|
|
34
|
+
env!("CARGO_PKG_VERSION").to_string()
|
|
35
|
+
}
|
|
36
|
+
|
|
37
|
+
fn initialize(&self) -> Result<()> {
|
|
38
|
+
Ok(())
|
|
39
|
+
}
|
|
40
|
+
|
|
41
|
+
fn shutdown(&self) -> Result<()> {
|
|
42
|
+
Ok(())
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
fn description(&self) -> &str {
|
|
46
|
+
"Extracts text content from XML files with element metadata"
|
|
47
|
+
}
|
|
48
|
+
|
|
49
|
+
fn author(&self) -> &str {
|
|
50
|
+
"Kreuzberg Team"
|
|
51
|
+
}
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
#[async_trait]
|
|
55
|
+
impl DocumentExtractor for XmlExtractor {
|
|
56
|
+
#[cfg_attr(feature = "otel", tracing::instrument(
|
|
57
|
+
skip(self, content, _config),
|
|
58
|
+
fields(
|
|
59
|
+
extractor.name = self.name(),
|
|
60
|
+
content.size_bytes = content.len(),
|
|
61
|
+
)
|
|
62
|
+
))]
|
|
63
|
+
async fn extract_bytes(
|
|
64
|
+
&self,
|
|
65
|
+
content: &[u8],
|
|
66
|
+
mime_type: &str,
|
|
67
|
+
_config: &ExtractionConfig,
|
|
68
|
+
) -> Result<ExtractionResult> {
|
|
69
|
+
let xml_result = parse_xml(content, false)?;
|
|
70
|
+
|
|
71
|
+
Ok(ExtractionResult {
|
|
72
|
+
content: xml_result.content,
|
|
73
|
+
mime_type: mime_type.to_string(),
|
|
74
|
+
metadata: crate::types::Metadata {
|
|
75
|
+
format: Some(crate::types::FormatMetadata::Xml(crate::types::XmlMetadata {
|
|
76
|
+
element_count: xml_result.element_count,
|
|
77
|
+
unique_elements: xml_result.unique_elements,
|
|
78
|
+
})),
|
|
79
|
+
..Default::default()
|
|
80
|
+
},
|
|
81
|
+
tables: vec![],
|
|
82
|
+
detected_languages: None,
|
|
83
|
+
chunks: None,
|
|
84
|
+
images: None,
|
|
85
|
+
})
|
|
86
|
+
}
|
|
87
|
+
|
|
88
|
+
fn supported_mime_types(&self) -> &[&str] {
|
|
89
|
+
&["application/xml", "text/xml", "image/svg+xml"]
|
|
90
|
+
}
|
|
91
|
+
|
|
92
|
+
fn priority(&self) -> i32 {
|
|
93
|
+
50
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
#[cfg(test)]
|
|
98
|
+
mod tests {
|
|
99
|
+
use super::*;
|
|
100
|
+
|
|
101
|
+
#[tokio::test]
|
|
102
|
+
async fn test_xml_extractor() {
|
|
103
|
+
let extractor = XmlExtractor::new();
|
|
104
|
+
let content = b"<root><item>Hello</item><item>World</item></root>";
|
|
105
|
+
let config = ExtractionConfig::default();
|
|
106
|
+
|
|
107
|
+
let result = extractor
|
|
108
|
+
.extract_bytes(content, "application/xml", &config)
|
|
109
|
+
.await
|
|
110
|
+
.unwrap();
|
|
111
|
+
|
|
112
|
+
assert_eq!(result.mime_type, "application/xml");
|
|
113
|
+
assert_eq!(result.content, "Hello World");
|
|
114
|
+
assert!(result.metadata.format.is_some());
|
|
115
|
+
let xml_meta = match result.metadata.format.as_ref().unwrap() {
|
|
116
|
+
crate::types::FormatMetadata::Xml(meta) => meta,
|
|
117
|
+
_ => panic!("Expected Xml metadata"),
|
|
118
|
+
};
|
|
119
|
+
assert_eq!(xml_meta.element_count, 3);
|
|
120
|
+
assert!(xml_meta.unique_elements.contains(&"root".to_string()));
|
|
121
|
+
assert!(xml_meta.unique_elements.contains(&"item".to_string()));
|
|
122
|
+
}
|
|
123
|
+
|
|
124
|
+
#[test]
|
|
125
|
+
fn test_xml_plugin_interface() {
|
|
126
|
+
let extractor = XmlExtractor::new();
|
|
127
|
+
assert_eq!(extractor.name(), "xml-extractor");
|
|
128
|
+
assert_eq!(extractor.version(), env!("CARGO_PKG_VERSION"));
|
|
129
|
+
assert_eq!(
|
|
130
|
+
extractor.supported_mime_types(),
|
|
131
|
+
&["application/xml", "text/xml", "image/svg+xml"]
|
|
132
|
+
);
|
|
133
|
+
assert_eq!(extractor.priority(), 50);
|
|
134
|
+
}
|
|
135
|
+
}
|
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
/// PDF points per inch constant
|
|
2
|
+
const PDF_POINTS_PER_INCH: f64 = 72.0;
|
|
3
|
+
|
|
4
|
+
/// Calculate smart DPI based on page dimensions, memory constraints, and target DPI
|
|
5
|
+
#[allow(clippy::cast_possible_truncation)]
|
|
6
|
+
pub fn calculate_smart_dpi(
|
|
7
|
+
page_width: f64,
|
|
8
|
+
page_height: f64,
|
|
9
|
+
target_dpi: i32,
|
|
10
|
+
max_dimension: i32,
|
|
11
|
+
max_memory_mb: f64,
|
|
12
|
+
) -> i32 {
|
|
13
|
+
let width_inches = page_width / PDF_POINTS_PER_INCH;
|
|
14
|
+
let height_inches = page_height / PDF_POINTS_PER_INCH;
|
|
15
|
+
|
|
16
|
+
let max_pixels = (max_memory_mb * 1024.0 * 1024.0 / 3.0).sqrt().round() as i32;
|
|
17
|
+
|
|
18
|
+
let max_dpi_for_memory_width = if width_inches > 0.0 {
|
|
19
|
+
(f64::from(max_pixels) / width_inches).round() as i32
|
|
20
|
+
} else {
|
|
21
|
+
target_dpi
|
|
22
|
+
};
|
|
23
|
+
|
|
24
|
+
let max_dpi_for_memory_height = if height_inches > 0.0 {
|
|
25
|
+
(f64::from(max_pixels) / height_inches).round() as i32
|
|
26
|
+
} else {
|
|
27
|
+
target_dpi
|
|
28
|
+
};
|
|
29
|
+
|
|
30
|
+
let memory_constrained_dpi = max_dpi_for_memory_width.min(max_dpi_for_memory_height);
|
|
31
|
+
|
|
32
|
+
let dimension_constrained_dpi =
|
|
33
|
+
calculate_dimension_constrained_dpi(width_inches, height_inches, target_dpi, max_dimension);
|
|
34
|
+
|
|
35
|
+
let final_dpi = target_dpi.min(memory_constrained_dpi).min(dimension_constrained_dpi);
|
|
36
|
+
|
|
37
|
+
final_dpi.max(72)
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
/// Calculate DPI constrained by maximum dimension
|
|
41
|
+
#[allow(clippy::cast_possible_truncation)]
|
|
42
|
+
fn calculate_dimension_constrained_dpi(
|
|
43
|
+
width_inches: f64,
|
|
44
|
+
height_inches: f64,
|
|
45
|
+
target_dpi: i32,
|
|
46
|
+
max_dimension: i32,
|
|
47
|
+
) -> i32 {
|
|
48
|
+
let target_width_pixels = (width_inches * f64::from(target_dpi)).round() as i32;
|
|
49
|
+
let target_height_pixels = (height_inches * f64::from(target_dpi)).round() as i32;
|
|
50
|
+
let max_pixel_dimension = target_width_pixels.max(target_height_pixels);
|
|
51
|
+
|
|
52
|
+
if max_pixel_dimension > max_dimension {
|
|
53
|
+
let max_dpi_for_width = if width_inches > 0.0 {
|
|
54
|
+
(f64::from(max_dimension) / width_inches).round() as i32
|
|
55
|
+
} else {
|
|
56
|
+
target_dpi
|
|
57
|
+
};
|
|
58
|
+
|
|
59
|
+
let max_dpi_for_height = if height_inches > 0.0 {
|
|
60
|
+
(f64::from(max_dimension) / height_inches).round() as i32
|
|
61
|
+
} else {
|
|
62
|
+
target_dpi
|
|
63
|
+
};
|
|
64
|
+
|
|
65
|
+
max_dpi_for_width.min(max_dpi_for_height)
|
|
66
|
+
} else {
|
|
67
|
+
target_dpi
|
|
68
|
+
}
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
/// Calculate optimal DPI with min/max constraints
|
|
72
|
+
pub fn calculate_optimal_dpi(
|
|
73
|
+
page_width: f64,
|
|
74
|
+
page_height: f64,
|
|
75
|
+
target_dpi: i32,
|
|
76
|
+
max_dimension: i32,
|
|
77
|
+
min_dpi: i32,
|
|
78
|
+
max_dpi: i32,
|
|
79
|
+
) -> i32 {
|
|
80
|
+
let smart_dpi = calculate_smart_dpi(page_width, page_height, target_dpi, max_dimension, 2048.0);
|
|
81
|
+
|
|
82
|
+
min_dpi.max(smart_dpi.min(max_dpi))
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
#[cfg(test)]
|
|
86
|
+
mod tests {
|
|
87
|
+
use super::*;
|
|
88
|
+
|
|
89
|
+
#[test]
|
|
90
|
+
fn test_calculate_smart_dpi_basic() {
|
|
91
|
+
let dpi = calculate_smart_dpi(612.0, 792.0, 300, 4096, 2048.0);
|
|
92
|
+
assert!(dpi >= 72);
|
|
93
|
+
assert!(dpi <= 300);
|
|
94
|
+
}
|
|
95
|
+
|
|
96
|
+
#[test]
|
|
97
|
+
fn test_calculate_smart_dpi_memory_constrained() {
|
|
98
|
+
let dpi = calculate_smart_dpi(1224.0, 1584.0, 300, 8192, 10.0);
|
|
99
|
+
assert!(dpi < 300);
|
|
100
|
+
assert!(dpi >= 72);
|
|
101
|
+
}
|
|
102
|
+
|
|
103
|
+
#[test]
|
|
104
|
+
fn test_calculate_smart_dpi_dimension_constrained() {
|
|
105
|
+
let dpi = calculate_smart_dpi(612.0, 792.0, 300, 1000, 2048.0);
|
|
106
|
+
assert!(dpi < 300);
|
|
107
|
+
}
|
|
108
|
+
|
|
109
|
+
#[test]
|
|
110
|
+
fn test_calculate_smart_dpi_minimum_dpi() {
|
|
111
|
+
let dpi = calculate_smart_dpi(10000.0, 10000.0, 300, 100, 1.0);
|
|
112
|
+
assert_eq!(dpi, 72);
|
|
113
|
+
}
|
|
114
|
+
|
|
115
|
+
#[test]
|
|
116
|
+
fn test_calculate_smart_dpi_zero_dimensions() {
|
|
117
|
+
let dpi = calculate_smart_dpi(0.0, 792.0, 300, 4096, 2048.0);
|
|
118
|
+
assert!(dpi >= 72);
|
|
119
|
+
|
|
120
|
+
let dpi = calculate_smart_dpi(612.0, 0.0, 300, 4096, 2048.0);
|
|
121
|
+
assert!(dpi >= 72);
|
|
122
|
+
|
|
123
|
+
let dpi = calculate_smart_dpi(0.0, 0.0, 300, 4096, 2048.0);
|
|
124
|
+
assert_eq!(dpi, 300);
|
|
125
|
+
}
|
|
126
|
+
|
|
127
|
+
#[test]
|
|
128
|
+
fn test_calculate_dimension_constrained_dpi() {
|
|
129
|
+
let dpi = calculate_dimension_constrained_dpi(8.5, 11.0, 300, 4096);
|
|
130
|
+
assert!(dpi <= 300);
|
|
131
|
+
|
|
132
|
+
let dpi = calculate_dimension_constrained_dpi(8.5, 11.0, 600, 2000);
|
|
133
|
+
assert!(dpi < 600);
|
|
134
|
+
}
|
|
135
|
+
|
|
136
|
+
#[test]
|
|
137
|
+
fn test_calculate_optimal_dpi() {
|
|
138
|
+
let dpi = calculate_optimal_dpi(612.0, 792.0, 300, 4096, 72, 600);
|
|
139
|
+
assert!(dpi >= 72);
|
|
140
|
+
assert!(dpi <= 600);
|
|
141
|
+
|
|
142
|
+
let dpi = calculate_optimal_dpi(10000.0, 10000.0, 300, 100, 100, 600);
|
|
143
|
+
assert_eq!(dpi, 100);
|
|
144
|
+
|
|
145
|
+
let dpi = calculate_optimal_dpi(72.0, 72.0, 1000, 10000, 72, 600);
|
|
146
|
+
assert_eq!(dpi, 600);
|
|
147
|
+
}
|
|
148
|
+
|
|
149
|
+
#[test]
|
|
150
|
+
fn test_memory_calculation() {
|
|
151
|
+
let dpi = calculate_smart_dpi(612.0, 792.0, 10000, 100000, 2048.0);
|
|
152
|
+
assert!(dpi < 10000);
|
|
153
|
+
assert!(dpi >= 72);
|
|
154
|
+
}
|
|
155
|
+
|
|
156
|
+
#[test]
|
|
157
|
+
fn test_aspect_ratio_preservation() {
|
|
158
|
+
let wide_dpi = calculate_smart_dpi(1224.0, 396.0, 300, 4096, 2048.0);
|
|
159
|
+
let tall_dpi = calculate_smart_dpi(396.0, 1224.0, 300, 4096, 2048.0);
|
|
160
|
+
|
|
161
|
+
assert!(wide_dpi >= 72);
|
|
162
|
+
assert!(tall_dpi >= 72);
|
|
163
|
+
}
|
|
164
|
+
}
|