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 +1,634 @@
|
|
|
1
|
+
//! Native OPML (Outline Processor Markup Language) extractor using the `roxmltree` library.
|
|
2
|
+
//!
|
|
3
|
+
//! This extractor provides native Rust-based OPML extraction, parsing outline structures
|
|
4
|
+
//! commonly used for RSS feed lists, podcast directories, and general outlines.
|
|
5
|
+
//!
|
|
6
|
+
//! Extracts:
|
|
7
|
+
//! - Metadata from `<head>`: title, dateCreated, dateModified, ownerName, ownerEmail
|
|
8
|
+
//! - Content from `<body><outline>` hierarchy using text attributes
|
|
9
|
+
//! - Outline hierarchy structure preserved in plain text format with indentation
|
|
10
|
+
//! - Note: URLs (xmlUrl, htmlUrl) are extracted from attributes but not included in main content
|
|
11
|
+
//!
|
|
12
|
+
//! Example OPML structure:
|
|
13
|
+
//! ```xml
|
|
14
|
+
//! <opml version="2.0">
|
|
15
|
+
//! <head>
|
|
16
|
+
//! <title>My Feeds</title>
|
|
17
|
+
//! <ownerName>John</ownerName>
|
|
18
|
+
//! </head>
|
|
19
|
+
//! <body>
|
|
20
|
+
//! <outline text="Tech" type="folder">
|
|
21
|
+
//! <outline text="Hacker News" type="rss" xmlUrl="https://..." />
|
|
22
|
+
//! </outline>
|
|
23
|
+
//! </body>
|
|
24
|
+
//! </opml>
|
|
25
|
+
//! ```
|
|
26
|
+
|
|
27
|
+
use crate::Result;
|
|
28
|
+
use crate::core::config::ExtractionConfig;
|
|
29
|
+
use crate::plugins::{DocumentExtractor, Plugin};
|
|
30
|
+
use crate::types::{ExtractionResult, Metadata};
|
|
31
|
+
use async_trait::async_trait;
|
|
32
|
+
use std::collections::HashMap;
|
|
33
|
+
|
|
34
|
+
#[cfg(feature = "office")]
|
|
35
|
+
use roxmltree::Node;
|
|
36
|
+
|
|
37
|
+
/// OPML format extractor.
|
|
38
|
+
///
|
|
39
|
+
/// Extracts outline structure and metadata from OPML documents using native Rust parsing.
|
|
40
|
+
pub struct OpmlExtractor;
|
|
41
|
+
|
|
42
|
+
impl OpmlExtractor {
|
|
43
|
+
/// Create a new OPML extractor.
|
|
44
|
+
pub fn new() -> Self {
|
|
45
|
+
Self
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
/// Extract OPML content and structure
|
|
49
|
+
#[cfg(feature = "office")]
|
|
50
|
+
fn extract_content_and_metadata(content: &[u8]) -> Result<(String, HashMap<String, serde_json::Value>)> {
|
|
51
|
+
let doc = roxmltree::Document::parse(
|
|
52
|
+
std::str::from_utf8(content)
|
|
53
|
+
.map_err(|e| crate::KreuzbergError::Other(format!("Invalid UTF-8 in OPML: {}", e)))?,
|
|
54
|
+
)
|
|
55
|
+
.map_err(|e| crate::KreuzbergError::Other(format!("Failed to parse OPML: {}", e)))?;
|
|
56
|
+
|
|
57
|
+
let mut extracted_content = String::new();
|
|
58
|
+
let mut metadata = HashMap::new();
|
|
59
|
+
|
|
60
|
+
if let Some(opml) = doc.root().children().find(|n| n.tag_name().name() == "opml") {
|
|
61
|
+
if let Some(head) = opml.children().find(|n| n.tag_name().name() == "head") {
|
|
62
|
+
for child in head.children().filter(|n| n.is_element()) {
|
|
63
|
+
let tag = child.tag_name().name();
|
|
64
|
+
let text = child.text().unwrap_or("").trim();
|
|
65
|
+
|
|
66
|
+
match tag {
|
|
67
|
+
"title" => {
|
|
68
|
+
if !text.is_empty() {
|
|
69
|
+
metadata.insert("title".to_string(), serde_json::json!(text));
|
|
70
|
+
}
|
|
71
|
+
}
|
|
72
|
+
"dateCreated" => {
|
|
73
|
+
if !text.is_empty() {
|
|
74
|
+
metadata.insert("dateCreated".to_string(), serde_json::json!(text));
|
|
75
|
+
}
|
|
76
|
+
}
|
|
77
|
+
"dateModified" => {
|
|
78
|
+
if !text.is_empty() {
|
|
79
|
+
metadata.insert("dateModified".to_string(), serde_json::json!(text));
|
|
80
|
+
}
|
|
81
|
+
}
|
|
82
|
+
"ownerName" => {
|
|
83
|
+
if !text.is_empty() {
|
|
84
|
+
metadata.insert("ownerName".to_string(), serde_json::json!(text));
|
|
85
|
+
}
|
|
86
|
+
}
|
|
87
|
+
"ownerEmail" => {
|
|
88
|
+
if !text.is_empty() {
|
|
89
|
+
metadata.insert("ownerEmail".to_string(), serde_json::json!(text));
|
|
90
|
+
}
|
|
91
|
+
}
|
|
92
|
+
_ => {}
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
if let Some(body) = opml.children().find(|n| n.tag_name().name() == "body") {
|
|
98
|
+
if let Some(title) = metadata.get("title").and_then(|v| v.as_str()) {
|
|
99
|
+
extracted_content.push_str(title);
|
|
100
|
+
extracted_content.push('\n');
|
|
101
|
+
extracted_content.push('\n');
|
|
102
|
+
}
|
|
103
|
+
|
|
104
|
+
for outline in body.children().filter(|n| n.tag_name().name() == "outline") {
|
|
105
|
+
Self::process_outline(outline, 0, &mut extracted_content);
|
|
106
|
+
}
|
|
107
|
+
}
|
|
108
|
+
}
|
|
109
|
+
|
|
110
|
+
Ok((extracted_content.trim().to_string(), metadata))
|
|
111
|
+
}
|
|
112
|
+
|
|
113
|
+
/// Process outline elements recursively
|
|
114
|
+
///
|
|
115
|
+
/// Extracts text content from outline hierarchy while preserving nesting depth
|
|
116
|
+
/// through indentation. URL attributes are excluded from the main content.
|
|
117
|
+
#[cfg(feature = "office")]
|
|
118
|
+
fn process_outline(node: Node, depth: usize, output: &mut String) {
|
|
119
|
+
let text = node.attribute("text").unwrap_or("").trim();
|
|
120
|
+
|
|
121
|
+
if !text.is_empty() {
|
|
122
|
+
let indent = " ".repeat(depth);
|
|
123
|
+
output.push_str(&indent);
|
|
124
|
+
output.push_str(text);
|
|
125
|
+
output.push('\n');
|
|
126
|
+
}
|
|
127
|
+
|
|
128
|
+
for child in node.children().filter(|n| n.tag_name().name() == "outline") {
|
|
129
|
+
Self::process_outline(child, depth + 1, output);
|
|
130
|
+
}
|
|
131
|
+
}
|
|
132
|
+
}
|
|
133
|
+
|
|
134
|
+
impl Default for OpmlExtractor {
|
|
135
|
+
fn default() -> Self {
|
|
136
|
+
Self::new()
|
|
137
|
+
}
|
|
138
|
+
}
|
|
139
|
+
|
|
140
|
+
impl Plugin for OpmlExtractor {
|
|
141
|
+
fn name(&self) -> &str {
|
|
142
|
+
"opml-extractor"
|
|
143
|
+
}
|
|
144
|
+
|
|
145
|
+
fn version(&self) -> String {
|
|
146
|
+
env!("CARGO_PKG_VERSION").to_string()
|
|
147
|
+
}
|
|
148
|
+
|
|
149
|
+
fn initialize(&self) -> Result<()> {
|
|
150
|
+
Ok(())
|
|
151
|
+
}
|
|
152
|
+
|
|
153
|
+
fn shutdown(&self) -> Result<()> {
|
|
154
|
+
Ok(())
|
|
155
|
+
}
|
|
156
|
+
|
|
157
|
+
fn description(&self) -> &str {
|
|
158
|
+
"Extracts content and metadata from OPML (Outline Processor Markup Language) documents"
|
|
159
|
+
}
|
|
160
|
+
|
|
161
|
+
fn author(&self) -> &str {
|
|
162
|
+
"Kreuzberg Team"
|
|
163
|
+
}
|
|
164
|
+
}
|
|
165
|
+
|
|
166
|
+
#[cfg(feature = "office")]
|
|
167
|
+
#[async_trait]
|
|
168
|
+
impl DocumentExtractor for OpmlExtractor {
|
|
169
|
+
#[cfg_attr(
|
|
170
|
+
feature = "otel",
|
|
171
|
+
tracing::instrument(
|
|
172
|
+
skip(self, content, _config),
|
|
173
|
+
fields(
|
|
174
|
+
extractor.name = self.name(),
|
|
175
|
+
content.size_bytes = content.len(),
|
|
176
|
+
)
|
|
177
|
+
)
|
|
178
|
+
)]
|
|
179
|
+
async fn extract_bytes(
|
|
180
|
+
&self,
|
|
181
|
+
content: &[u8],
|
|
182
|
+
mime_type: &str,
|
|
183
|
+
_config: &ExtractionConfig,
|
|
184
|
+
) -> Result<ExtractionResult> {
|
|
185
|
+
let (extracted_content, metadata_map) = Self::extract_content_and_metadata(content)?;
|
|
186
|
+
|
|
187
|
+
Ok(ExtractionResult {
|
|
188
|
+
content: extracted_content,
|
|
189
|
+
mime_type: mime_type.to_string(),
|
|
190
|
+
metadata: Metadata {
|
|
191
|
+
additional: metadata_map,
|
|
192
|
+
..Default::default()
|
|
193
|
+
},
|
|
194
|
+
tables: vec![],
|
|
195
|
+
detected_languages: None,
|
|
196
|
+
chunks: None,
|
|
197
|
+
images: None,
|
|
198
|
+
})
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
fn supported_mime_types(&self) -> &[&str] {
|
|
202
|
+
&["text/x-opml", "application/xml+opml"]
|
|
203
|
+
}
|
|
204
|
+
|
|
205
|
+
fn priority(&self) -> i32 {
|
|
206
|
+
55
|
|
207
|
+
}
|
|
208
|
+
}
|
|
209
|
+
|
|
210
|
+
#[cfg(all(test, feature = "office"))]
|
|
211
|
+
mod tests {
|
|
212
|
+
use super::*;
|
|
213
|
+
|
|
214
|
+
#[test]
|
|
215
|
+
fn test_opml_extractor_plugin_interface() {
|
|
216
|
+
let extractor = OpmlExtractor::new();
|
|
217
|
+
assert_eq!(extractor.name(), "opml-extractor");
|
|
218
|
+
assert_eq!(extractor.version(), env!("CARGO_PKG_VERSION"));
|
|
219
|
+
assert_eq!(extractor.priority(), 55);
|
|
220
|
+
assert!(!extractor.supported_mime_types().is_empty());
|
|
221
|
+
}
|
|
222
|
+
|
|
223
|
+
#[test]
|
|
224
|
+
fn test_opml_extractor_default() {
|
|
225
|
+
let extractor = OpmlExtractor;
|
|
226
|
+
assert_eq!(extractor.name(), "opml-extractor");
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
#[tokio::test]
|
|
230
|
+
async fn test_opml_extractor_initialize_shutdown() {
|
|
231
|
+
let extractor = OpmlExtractor::new();
|
|
232
|
+
assert!(extractor.initialize().is_ok());
|
|
233
|
+
assert!(extractor.shutdown().is_ok());
|
|
234
|
+
}
|
|
235
|
+
|
|
236
|
+
#[test]
|
|
237
|
+
fn test_opml_simple_outline_parsing() {
|
|
238
|
+
let opml = br#"<?xml version="1.0"?>
|
|
239
|
+
<opml version="2.0">
|
|
240
|
+
<head>
|
|
241
|
+
<title>Test</title>
|
|
242
|
+
</head>
|
|
243
|
+
<body>
|
|
244
|
+
<outline text="Item 1" />
|
|
245
|
+
<outline text="Item 2" />
|
|
246
|
+
</body>
|
|
247
|
+
</opml>"#;
|
|
248
|
+
|
|
249
|
+
let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse simple OPML");
|
|
250
|
+
|
|
251
|
+
assert!(content.contains("Item 1"), "Should extract first item");
|
|
252
|
+
assert!(content.contains("Item 2"), "Should extract second item");
|
|
253
|
+
assert_eq!(
|
|
254
|
+
metadata.get("title").and_then(|v| v.as_str()),
|
|
255
|
+
Some("Test"),
|
|
256
|
+
"Should extract title"
|
|
257
|
+
);
|
|
258
|
+
}
|
|
259
|
+
|
|
260
|
+
#[test]
|
|
261
|
+
fn test_opml_nested_hierarchy() {
|
|
262
|
+
let opml = br#"<?xml version="1.0"?>
|
|
263
|
+
<opml version="2.0">
|
|
264
|
+
<head>
|
|
265
|
+
<title>Hierarchy Test</title>
|
|
266
|
+
</head>
|
|
267
|
+
<body>
|
|
268
|
+
<outline text="Category">
|
|
269
|
+
<outline text="Subcategory">
|
|
270
|
+
<outline text="Item" />
|
|
271
|
+
</outline>
|
|
272
|
+
</outline>
|
|
273
|
+
</body>
|
|
274
|
+
</opml>"#;
|
|
275
|
+
|
|
276
|
+
let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse nested OPML");
|
|
277
|
+
|
|
278
|
+
assert!(content.contains("Category"), "Should contain top level");
|
|
279
|
+
assert!(content.contains("Subcategory"), "Should contain nested level");
|
|
280
|
+
assert!(content.contains("Item"), "Should contain deep item");
|
|
281
|
+
assert!(content.contains(" "), "Should have indentation for nested items");
|
|
282
|
+
}
|
|
283
|
+
|
|
284
|
+
#[test]
|
|
285
|
+
fn test_opml_rss_feeds() {
|
|
286
|
+
let opml = br#"<?xml version="1.0"?>
|
|
287
|
+
<opml version="2.0">
|
|
288
|
+
<head>
|
|
289
|
+
<title>Feeds</title>
|
|
290
|
+
</head>
|
|
291
|
+
<body>
|
|
292
|
+
<outline text="Tech">
|
|
293
|
+
<outline text="Hacker News" type="rss" xmlUrl="https://news.ycombinator.com/rss" htmlUrl="https://news.ycombinator.com/" />
|
|
294
|
+
<outline text="TechCrunch" type="rss" xmlUrl="https://techcrunch.com/feed/" />
|
|
295
|
+
</outline>
|
|
296
|
+
</body>
|
|
297
|
+
</opml>"#;
|
|
298
|
+
|
|
299
|
+
let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse RSS OPML");
|
|
300
|
+
|
|
301
|
+
assert!(content.contains("Hacker News"), "Should extract feed title");
|
|
302
|
+
assert!(
|
|
303
|
+
!content.contains("https://"),
|
|
304
|
+
"Should NOT extract feed URLs (text-only extraction)"
|
|
305
|
+
);
|
|
306
|
+
assert!(content.contains("TechCrunch"), "Should extract multiple feeds");
|
|
307
|
+
}
|
|
308
|
+
|
|
309
|
+
#[test]
|
|
310
|
+
fn test_opml_metadata_extraction() {
|
|
311
|
+
let opml = br#"<?xml version="1.0"?>
|
|
312
|
+
<opml version="2.0">
|
|
313
|
+
<head>
|
|
314
|
+
<title>My Feeds</title>
|
|
315
|
+
<dateCreated>Mon, 06 Nov 2023 00:00:00 GMT</dateCreated>
|
|
316
|
+
<dateModified>Fri, 01 Dec 2023 12:00:00 GMT</dateModified>
|
|
317
|
+
<ownerName>John Doe</ownerName>
|
|
318
|
+
<ownerEmail>john@example.com</ownerEmail>
|
|
319
|
+
</head>
|
|
320
|
+
<body>
|
|
321
|
+
<outline text="Item" />
|
|
322
|
+
</body>
|
|
323
|
+
</opml>"#;
|
|
324
|
+
|
|
325
|
+
let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should extract metadata");
|
|
326
|
+
|
|
327
|
+
assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("My Feeds"));
|
|
328
|
+
assert_eq!(metadata.get("ownerName").and_then(|v| v.as_str()), Some("John Doe"));
|
|
329
|
+
assert_eq!(
|
|
330
|
+
metadata.get("ownerEmail").and_then(|v| v.as_str()),
|
|
331
|
+
Some("john@example.com")
|
|
332
|
+
);
|
|
333
|
+
assert!(metadata.contains_key("dateCreated"));
|
|
334
|
+
assert!(metadata.contains_key("dateModified"));
|
|
335
|
+
}
|
|
336
|
+
|
|
337
|
+
#[test]
|
|
338
|
+
fn test_opml_supported_mime_types() {
|
|
339
|
+
let extractor = OpmlExtractor::new();
|
|
340
|
+
let supported = extractor.supported_mime_types();
|
|
341
|
+
assert!(supported.contains(&"text/x-opml"));
|
|
342
|
+
assert!(supported.contains(&"application/xml+opml"));
|
|
343
|
+
}
|
|
344
|
+
|
|
345
|
+
#[test]
|
|
346
|
+
fn test_opml_with_special_characters() {
|
|
347
|
+
let opml = br#"<?xml version="1.0"?>
|
|
348
|
+
<opml version="2.0">
|
|
349
|
+
<head>
|
|
350
|
+
<title>Test & Special</title>
|
|
351
|
+
</head>
|
|
352
|
+
<body>
|
|
353
|
+
<outline text="Business & Startups" />
|
|
354
|
+
<outline text="Science <Advanced>" />
|
|
355
|
+
</body>
|
|
356
|
+
</opml>"#;
|
|
357
|
+
|
|
358
|
+
let (content, metadata) =
|
|
359
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle special characters");
|
|
360
|
+
|
|
361
|
+
assert!(
|
|
362
|
+
content.contains("Business") && content.contains("Startups"),
|
|
363
|
+
"Should decode HTML entities"
|
|
364
|
+
);
|
|
365
|
+
let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
|
|
366
|
+
assert!(!title.is_empty(), "Should extract title");
|
|
367
|
+
}
|
|
368
|
+
|
|
369
|
+
#[test]
|
|
370
|
+
fn test_opml_empty_body() {
|
|
371
|
+
let opml = br#"<?xml version="1.0"?>
|
|
372
|
+
<opml version="2.0">
|
|
373
|
+
<head>
|
|
374
|
+
<title>Empty</title>
|
|
375
|
+
</head>
|
|
376
|
+
<body>
|
|
377
|
+
</body>
|
|
378
|
+
</opml>"#;
|
|
379
|
+
|
|
380
|
+
let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty body");
|
|
381
|
+
|
|
382
|
+
assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty"));
|
|
383
|
+
}
|
|
384
|
+
|
|
385
|
+
#[tokio::test]
|
|
386
|
+
async fn test_opml_extractor_async_extraction() {
|
|
387
|
+
let extractor = OpmlExtractor::new();
|
|
388
|
+
let opml = br#"<?xml version="1.0"?>
|
|
389
|
+
<opml version="2.0">
|
|
390
|
+
<head>
|
|
391
|
+
<title>Async Test</title>
|
|
392
|
+
</head>
|
|
393
|
+
<body>
|
|
394
|
+
<outline text="Item" />
|
|
395
|
+
</body>
|
|
396
|
+
</opml>"#;
|
|
397
|
+
|
|
398
|
+
let result = extractor
|
|
399
|
+
.extract_bytes(opml, "text/x-opml", &ExtractionConfig::default())
|
|
400
|
+
.await
|
|
401
|
+
.expect("Should extract OPML asynchronously");
|
|
402
|
+
|
|
403
|
+
assert_eq!(result.mime_type, "text/x-opml");
|
|
404
|
+
assert!(result.content.contains("Item"));
|
|
405
|
+
assert_eq!(
|
|
406
|
+
result.metadata.additional.get("title").and_then(|v| v.as_str()),
|
|
407
|
+
Some("Async Test")
|
|
408
|
+
);
|
|
409
|
+
}
|
|
410
|
+
|
|
411
|
+
#[test]
|
|
412
|
+
fn test_opml_malformed_missing_closing_tag() {
|
|
413
|
+
let opml = br#"<?xml version="1.0"?>
|
|
414
|
+
<opml version="2.0">
|
|
415
|
+
<head>
|
|
416
|
+
<title>Broken</title>
|
|
417
|
+
</head>
|
|
418
|
+
<body>
|
|
419
|
+
<outline text="Unclosed"
|
|
420
|
+
</body>
|
|
421
|
+
</opml>"#;
|
|
422
|
+
|
|
423
|
+
let result = OpmlExtractor::extract_content_and_metadata(opml);
|
|
424
|
+
assert!(result.is_err(), "Should fail to parse OPML with missing closing tags");
|
|
425
|
+
}
|
|
426
|
+
|
|
427
|
+
#[test]
|
|
428
|
+
fn test_opml_malformed_invalid_nesting() {
|
|
429
|
+
let opml = br#"<?xml version="1.0"?>
|
|
430
|
+
<opml version="2.0">
|
|
431
|
+
<head>
|
|
432
|
+
<title>Invalid Nesting</title>
|
|
433
|
+
<body>
|
|
434
|
+
<outline text="Item" />
|
|
435
|
+
</body>
|
|
436
|
+
</opml>"#;
|
|
437
|
+
|
|
438
|
+
let result = OpmlExtractor::extract_content_and_metadata(opml);
|
|
439
|
+
assert!(result.is_err(), "Should fail to parse OPML with invalid nesting");
|
|
440
|
+
}
|
|
441
|
+
|
|
442
|
+
#[test]
|
|
443
|
+
fn test_opml_empty_outline_elements() {
|
|
444
|
+
let opml = br#"<?xml version="1.0"?>
|
|
445
|
+
<opml version="2.0">
|
|
446
|
+
<head>
|
|
447
|
+
<title>Empty Outlines</title>
|
|
448
|
+
</head>
|
|
449
|
+
<body>
|
|
450
|
+
<outline text="" />
|
|
451
|
+
<outline />
|
|
452
|
+
<outline text="Valid Item">
|
|
453
|
+
<outline text="" />
|
|
454
|
+
<outline text="Another Valid" />
|
|
455
|
+
</outline>
|
|
456
|
+
</body>
|
|
457
|
+
</opml>"#;
|
|
458
|
+
|
|
459
|
+
let (content, metadata) =
|
|
460
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty outline elements");
|
|
461
|
+
|
|
462
|
+
assert!(content.contains("Valid Item"), "Should extract valid items");
|
|
463
|
+
assert!(content.contains("Another Valid"), "Should extract nested valid items");
|
|
464
|
+
let empty_count = content.matches("\n\n").count();
|
|
465
|
+
assert!(empty_count < 3, "Should skip empty outline elements");
|
|
466
|
+
|
|
467
|
+
assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty Outlines"));
|
|
468
|
+
}
|
|
469
|
+
|
|
470
|
+
#[test]
|
|
471
|
+
fn test_opml_deeply_nested_empty_nodes() {
|
|
472
|
+
let opml = br#"<?xml version="1.0"?>
|
|
473
|
+
<opml version="2.0">
|
|
474
|
+
<head>
|
|
475
|
+
<title>Deep Nesting</title>
|
|
476
|
+
</head>
|
|
477
|
+
<body>
|
|
478
|
+
<outline text="Level 1">
|
|
479
|
+
<outline text="">
|
|
480
|
+
<outline text="">
|
|
481
|
+
<outline text="Deep Item">
|
|
482
|
+
<outline text="" />
|
|
483
|
+
</outline>
|
|
484
|
+
</outline>
|
|
485
|
+
</outline>
|
|
486
|
+
<outline text="Level 1 Sibling" />
|
|
487
|
+
</outline>
|
|
488
|
+
</body>
|
|
489
|
+
</opml>"#;
|
|
490
|
+
|
|
491
|
+
let (content, _) =
|
|
492
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle deeply nested structures");
|
|
493
|
+
|
|
494
|
+
assert!(content.contains("Level 1"), "Should extract top-level item");
|
|
495
|
+
assert!(content.contains("Deep Item"), "Should extract deeply nested item");
|
|
496
|
+
assert!(content.contains("Level 1 Sibling"), "Should extract sibling items");
|
|
497
|
+
}
|
|
498
|
+
|
|
499
|
+
#[test]
|
|
500
|
+
fn test_opml_outline_with_missing_text_attribute() {
|
|
501
|
+
let opml = br#"<?xml version="1.0"?>
|
|
502
|
+
<opml version="2.0">
|
|
503
|
+
<head>
|
|
504
|
+
<title>Missing Attributes</title>
|
|
505
|
+
</head>
|
|
506
|
+
<body>
|
|
507
|
+
<outline type="folder" />
|
|
508
|
+
<outline text="Valid Item" type="rss" />
|
|
509
|
+
<outline type="rss" xmlUrl="https://example.com/feed" />
|
|
510
|
+
</body>
|
|
511
|
+
</opml>"#;
|
|
512
|
+
|
|
513
|
+
let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml)
|
|
514
|
+
.expect("Should handle outline with missing text attribute");
|
|
515
|
+
|
|
516
|
+
assert!(content.contains("Valid Item"), "Should extract item with text");
|
|
517
|
+
assert!(!content.contains("https://"), "Should not extract URLs");
|
|
518
|
+
|
|
519
|
+
assert_eq!(
|
|
520
|
+
metadata.get("title").and_then(|v| v.as_str()),
|
|
521
|
+
Some("Missing Attributes")
|
|
522
|
+
);
|
|
523
|
+
}
|
|
524
|
+
|
|
525
|
+
#[test]
|
|
526
|
+
fn test_opml_whitespace_only_text_attribute() {
|
|
527
|
+
let opml = br#"<?xml version="1.0"?>
|
|
528
|
+
<opml version="2.0">
|
|
529
|
+
<head>
|
|
530
|
+
<title>Whitespace Test</title>
|
|
531
|
+
</head>
|
|
532
|
+
<body>
|
|
533
|
+
<outline text=" " />
|
|
534
|
+
<outline text="
|
|
535
|
+
" />
|
|
536
|
+
<outline text="Real Content" />
|
|
537
|
+
</body>
|
|
538
|
+
</opml>"#;
|
|
539
|
+
|
|
540
|
+
let (content, _) =
|
|
541
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle whitespace-only text");
|
|
542
|
+
|
|
543
|
+
assert!(
|
|
544
|
+
content.contains("Real Content"),
|
|
545
|
+
"Should extract non-whitespace content"
|
|
546
|
+
);
|
|
547
|
+
let trimmed = content.trim();
|
|
548
|
+
assert!(trimmed.contains("Whitespace Test"), "Should have title");
|
|
549
|
+
assert!(trimmed.contains("Real Content"), "Should have real content");
|
|
550
|
+
}
|
|
551
|
+
|
|
552
|
+
#[test]
|
|
553
|
+
fn test_opml_html_entity_in_nested_structure() {
|
|
554
|
+
let opml = br#"<?xml version="1.0"?>
|
|
555
|
+
<opml version="2.0">
|
|
556
|
+
<head>
|
|
557
|
+
<title>Entities & Nesting</title>
|
|
558
|
+
</head>
|
|
559
|
+
<body>
|
|
560
|
+
<outline text="News & Updates">
|
|
561
|
+
<outline text="Tech < Science" />
|
|
562
|
+
<outline text="Health > Wealth" />
|
|
563
|
+
</outline>
|
|
564
|
+
</body>
|
|
565
|
+
</opml>"#;
|
|
566
|
+
|
|
567
|
+
let (content, metadata) =
|
|
568
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle HTML entities");
|
|
569
|
+
|
|
570
|
+
assert!(
|
|
571
|
+
content.contains("News") && content.contains("Updates"),
|
|
572
|
+
"Should decode & entity"
|
|
573
|
+
);
|
|
574
|
+
assert!(content.contains("Tech"), "Should handle < entity");
|
|
575
|
+
assert!(content.contains("Science"), "Should decode entity properly");
|
|
576
|
+
|
|
577
|
+
let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
|
|
578
|
+
assert!(
|
|
579
|
+
title.contains("&") && title.contains("Nesting"),
|
|
580
|
+
"Title should have decoded entity"
|
|
581
|
+
);
|
|
582
|
+
}
|
|
583
|
+
|
|
584
|
+
#[test]
|
|
585
|
+
fn test_opml_single_outline_no_children() {
|
|
586
|
+
let opml = br#"<?xml version="1.0"?>
|
|
587
|
+
<opml version="2.0">
|
|
588
|
+
<head>
|
|
589
|
+
<title>Single</title>
|
|
590
|
+
</head>
|
|
591
|
+
<body>
|
|
592
|
+
<outline text="Only Item" />
|
|
593
|
+
</body>
|
|
594
|
+
</opml>"#;
|
|
595
|
+
|
|
596
|
+
let (content, metadata) =
|
|
597
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle single outline");
|
|
598
|
+
|
|
599
|
+
assert!(content.contains("Only Item"), "Should extract single item");
|
|
600
|
+
assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Single"));
|
|
601
|
+
}
|
|
602
|
+
|
|
603
|
+
#[test]
|
|
604
|
+
fn test_opml_head_without_body() {
|
|
605
|
+
let opml = br#"<?xml version="1.0"?>
|
|
606
|
+
<opml version="2.0">
|
|
607
|
+
<head>
|
|
608
|
+
<title>No Body</title>
|
|
609
|
+
</head>
|
|
610
|
+
</opml>"#;
|
|
611
|
+
|
|
612
|
+
let (content, metadata) =
|
|
613
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without body");
|
|
614
|
+
|
|
615
|
+
assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("No Body"));
|
|
616
|
+
assert!(content.is_empty() || content.trim() == "No Body");
|
|
617
|
+
}
|
|
618
|
+
|
|
619
|
+
#[test]
|
|
620
|
+
fn test_opml_body_without_head() {
|
|
621
|
+
let opml = br#"<?xml version="1.0"?>
|
|
622
|
+
<opml version="2.0">
|
|
623
|
+
<body>
|
|
624
|
+
<outline text="Item" />
|
|
625
|
+
</body>
|
|
626
|
+
</opml>"#;
|
|
627
|
+
|
|
628
|
+
let (content, metadata) =
|
|
629
|
+
OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without head");
|
|
630
|
+
|
|
631
|
+
assert!(content.contains("Item"), "Should extract body content");
|
|
632
|
+
assert!(metadata.is_empty(), "Should have no metadata without head");
|
|
633
|
+
}
|
|
634
|
+
}
|