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 +1,448 @@
|
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"ali",
|
|
4
|
+
"april",
|
|
5
|
+
"avgust",
|
|
6
|
+
"b",
|
|
7
|
+
"bi",
|
|
8
|
+
"bil",
|
|
9
|
+
"bila",
|
|
10
|
+
"bile",
|
|
11
|
+
"bili",
|
|
12
|
+
"bilo",
|
|
13
|
+
"biti",
|
|
14
|
+
"blizu",
|
|
15
|
+
"bo",
|
|
16
|
+
"bodo",
|
|
17
|
+
"bojo",
|
|
18
|
+
"bolj",
|
|
19
|
+
"bom",
|
|
20
|
+
"bomo",
|
|
21
|
+
"boste",
|
|
22
|
+
"bova",
|
|
23
|
+
"boš",
|
|
24
|
+
"brez",
|
|
25
|
+
"c",
|
|
26
|
+
"cel",
|
|
27
|
+
"cela",
|
|
28
|
+
"celi",
|
|
29
|
+
"celo",
|
|
30
|
+
"d",
|
|
31
|
+
"da",
|
|
32
|
+
"daleč",
|
|
33
|
+
"dan",
|
|
34
|
+
"danes",
|
|
35
|
+
"datum",
|
|
36
|
+
"december",
|
|
37
|
+
"deset",
|
|
38
|
+
"deseta",
|
|
39
|
+
"deseti",
|
|
40
|
+
"deseto",
|
|
41
|
+
"devet",
|
|
42
|
+
"deveta",
|
|
43
|
+
"deveti",
|
|
44
|
+
"deveto",
|
|
45
|
+
"do",
|
|
46
|
+
"dober",
|
|
47
|
+
"dobra",
|
|
48
|
+
"dobri",
|
|
49
|
+
"dobro",
|
|
50
|
+
"dokler",
|
|
51
|
+
"dol",
|
|
52
|
+
"dolg",
|
|
53
|
+
"dolga",
|
|
54
|
+
"dolgi",
|
|
55
|
+
"dovolj",
|
|
56
|
+
"drug",
|
|
57
|
+
"druga",
|
|
58
|
+
"drugi",
|
|
59
|
+
"drugo",
|
|
60
|
+
"dva",
|
|
61
|
+
"dve",
|
|
62
|
+
"e",
|
|
63
|
+
"eden",
|
|
64
|
+
"en",
|
|
65
|
+
"ena",
|
|
66
|
+
"ene",
|
|
67
|
+
"eni",
|
|
68
|
+
"enkrat",
|
|
69
|
+
"eno",
|
|
70
|
+
"etc.",
|
|
71
|
+
"f",
|
|
72
|
+
"februar",
|
|
73
|
+
"g",
|
|
74
|
+
"g.",
|
|
75
|
+
"ga",
|
|
76
|
+
"ga.",
|
|
77
|
+
"gor",
|
|
78
|
+
"gospa",
|
|
79
|
+
"gospod",
|
|
80
|
+
"h",
|
|
81
|
+
"halo",
|
|
82
|
+
"i",
|
|
83
|
+
"idr.",
|
|
84
|
+
"ii",
|
|
85
|
+
"iii",
|
|
86
|
+
"in",
|
|
87
|
+
"iv",
|
|
88
|
+
"ix",
|
|
89
|
+
"iz",
|
|
90
|
+
"j",
|
|
91
|
+
"januar",
|
|
92
|
+
"jaz",
|
|
93
|
+
"je",
|
|
94
|
+
"ji",
|
|
95
|
+
"jih",
|
|
96
|
+
"jim",
|
|
97
|
+
"jo",
|
|
98
|
+
"julij",
|
|
99
|
+
"junij",
|
|
100
|
+
"jutri",
|
|
101
|
+
"k",
|
|
102
|
+
"kadarkoli",
|
|
103
|
+
"kaj",
|
|
104
|
+
"kajti",
|
|
105
|
+
"kako",
|
|
106
|
+
"kakor",
|
|
107
|
+
"kamor",
|
|
108
|
+
"kamorkoli",
|
|
109
|
+
"kar",
|
|
110
|
+
"karkoli",
|
|
111
|
+
"katerikoli",
|
|
112
|
+
"kdaj",
|
|
113
|
+
"kdo",
|
|
114
|
+
"kdorkoli",
|
|
115
|
+
"ker",
|
|
116
|
+
"ki",
|
|
117
|
+
"kje",
|
|
118
|
+
"kjer",
|
|
119
|
+
"kjerkoli",
|
|
120
|
+
"ko",
|
|
121
|
+
"koder",
|
|
122
|
+
"koderkoli",
|
|
123
|
+
"koga",
|
|
124
|
+
"komu",
|
|
125
|
+
"kot",
|
|
126
|
+
"kratek",
|
|
127
|
+
"kratka",
|
|
128
|
+
"kratke",
|
|
129
|
+
"kratki",
|
|
130
|
+
"l",
|
|
131
|
+
"lahka",
|
|
132
|
+
"lahke",
|
|
133
|
+
"lahki",
|
|
134
|
+
"lahko",
|
|
135
|
+
"le",
|
|
136
|
+
"lep",
|
|
137
|
+
"lepa",
|
|
138
|
+
"lepe",
|
|
139
|
+
"lepi",
|
|
140
|
+
"lepo",
|
|
141
|
+
"leto",
|
|
142
|
+
"m",
|
|
143
|
+
"maj",
|
|
144
|
+
"majhen",
|
|
145
|
+
"majhna",
|
|
146
|
+
"majhni",
|
|
147
|
+
"malce",
|
|
148
|
+
"malo",
|
|
149
|
+
"manj",
|
|
150
|
+
"marec",
|
|
151
|
+
"me",
|
|
152
|
+
"med",
|
|
153
|
+
"medtem",
|
|
154
|
+
"mene",
|
|
155
|
+
"mesec",
|
|
156
|
+
"mi",
|
|
157
|
+
"midva",
|
|
158
|
+
"midve",
|
|
159
|
+
"mnogo",
|
|
160
|
+
"moj",
|
|
161
|
+
"moja",
|
|
162
|
+
"moje",
|
|
163
|
+
"mora",
|
|
164
|
+
"morajo",
|
|
165
|
+
"moram",
|
|
166
|
+
"moramo",
|
|
167
|
+
"morate",
|
|
168
|
+
"moraš",
|
|
169
|
+
"morem",
|
|
170
|
+
"mu",
|
|
171
|
+
"n",
|
|
172
|
+
"na",
|
|
173
|
+
"nad",
|
|
174
|
+
"naj",
|
|
175
|
+
"najina",
|
|
176
|
+
"najino",
|
|
177
|
+
"najmanj",
|
|
178
|
+
"naju",
|
|
179
|
+
"največ",
|
|
180
|
+
"nam",
|
|
181
|
+
"narobe",
|
|
182
|
+
"nas",
|
|
183
|
+
"nato",
|
|
184
|
+
"nazaj",
|
|
185
|
+
"naš",
|
|
186
|
+
"naša",
|
|
187
|
+
"naše",
|
|
188
|
+
"ne",
|
|
189
|
+
"nedavno",
|
|
190
|
+
"nedelja",
|
|
191
|
+
"nek",
|
|
192
|
+
"neka",
|
|
193
|
+
"nekaj",
|
|
194
|
+
"nekatere",
|
|
195
|
+
"nekateri",
|
|
196
|
+
"nekatero",
|
|
197
|
+
"nekdo",
|
|
198
|
+
"neke",
|
|
199
|
+
"nekega",
|
|
200
|
+
"neki",
|
|
201
|
+
"nekje",
|
|
202
|
+
"neko",
|
|
203
|
+
"nekoga",
|
|
204
|
+
"nekoč",
|
|
205
|
+
"ni",
|
|
206
|
+
"nikamor",
|
|
207
|
+
"nikdar",
|
|
208
|
+
"nikjer",
|
|
209
|
+
"nikoli",
|
|
210
|
+
"nič",
|
|
211
|
+
"nje",
|
|
212
|
+
"njega",
|
|
213
|
+
"njegov",
|
|
214
|
+
"njegova",
|
|
215
|
+
"njegovo",
|
|
216
|
+
"njej",
|
|
217
|
+
"njemu",
|
|
218
|
+
"njen",
|
|
219
|
+
"njena",
|
|
220
|
+
"njeno",
|
|
221
|
+
"nji",
|
|
222
|
+
"njih",
|
|
223
|
+
"njihov",
|
|
224
|
+
"njihova",
|
|
225
|
+
"njihovo",
|
|
226
|
+
"njiju",
|
|
227
|
+
"njim",
|
|
228
|
+
"njo",
|
|
229
|
+
"njun",
|
|
230
|
+
"njuna",
|
|
231
|
+
"njuno",
|
|
232
|
+
"no",
|
|
233
|
+
"nocoj",
|
|
234
|
+
"november",
|
|
235
|
+
"npr.",
|
|
236
|
+
"o",
|
|
237
|
+
"ob",
|
|
238
|
+
"oba",
|
|
239
|
+
"obe",
|
|
240
|
+
"oboje",
|
|
241
|
+
"od",
|
|
242
|
+
"odprt",
|
|
243
|
+
"odprta",
|
|
244
|
+
"odprti",
|
|
245
|
+
"okoli",
|
|
246
|
+
"oktober",
|
|
247
|
+
"on",
|
|
248
|
+
"onadva",
|
|
249
|
+
"one",
|
|
250
|
+
"oni",
|
|
251
|
+
"onidve",
|
|
252
|
+
"osem",
|
|
253
|
+
"osma",
|
|
254
|
+
"osmi",
|
|
255
|
+
"osmo",
|
|
256
|
+
"oz.",
|
|
257
|
+
"p",
|
|
258
|
+
"pa",
|
|
259
|
+
"pet",
|
|
260
|
+
"peta",
|
|
261
|
+
"petek",
|
|
262
|
+
"peti",
|
|
263
|
+
"peto",
|
|
264
|
+
"po",
|
|
265
|
+
"pod",
|
|
266
|
+
"pogosto",
|
|
267
|
+
"poleg",
|
|
268
|
+
"poln",
|
|
269
|
+
"polna",
|
|
270
|
+
"polni",
|
|
271
|
+
"polno",
|
|
272
|
+
"ponavadi",
|
|
273
|
+
"ponedeljek",
|
|
274
|
+
"ponovno",
|
|
275
|
+
"potem",
|
|
276
|
+
"povsod",
|
|
277
|
+
"pozdravljen",
|
|
278
|
+
"pozdravljeni",
|
|
279
|
+
"prav",
|
|
280
|
+
"prava",
|
|
281
|
+
"prave",
|
|
282
|
+
"pravi",
|
|
283
|
+
"pravo",
|
|
284
|
+
"prazen",
|
|
285
|
+
"prazna",
|
|
286
|
+
"prazno",
|
|
287
|
+
"prbl.",
|
|
288
|
+
"precej",
|
|
289
|
+
"pred",
|
|
290
|
+
"prej",
|
|
291
|
+
"preko",
|
|
292
|
+
"pri",
|
|
293
|
+
"pribl.",
|
|
294
|
+
"približno",
|
|
295
|
+
"primer",
|
|
296
|
+
"pripravljen",
|
|
297
|
+
"pripravljena",
|
|
298
|
+
"pripravljeni",
|
|
299
|
+
"proti",
|
|
300
|
+
"prva",
|
|
301
|
+
"prvi",
|
|
302
|
+
"prvo",
|
|
303
|
+
"r",
|
|
304
|
+
"ravno",
|
|
305
|
+
"redko",
|
|
306
|
+
"res",
|
|
307
|
+
"reč",
|
|
308
|
+
"s",
|
|
309
|
+
"saj",
|
|
310
|
+
"sam",
|
|
311
|
+
"sama",
|
|
312
|
+
"same",
|
|
313
|
+
"sami",
|
|
314
|
+
"samo",
|
|
315
|
+
"se",
|
|
316
|
+
"sebe",
|
|
317
|
+
"sebi",
|
|
318
|
+
"sedaj",
|
|
319
|
+
"sedem",
|
|
320
|
+
"sedma",
|
|
321
|
+
"sedmi",
|
|
322
|
+
"sedmo",
|
|
323
|
+
"sem",
|
|
324
|
+
"september",
|
|
325
|
+
"seveda",
|
|
326
|
+
"si",
|
|
327
|
+
"sicer",
|
|
328
|
+
"skoraj",
|
|
329
|
+
"skozi",
|
|
330
|
+
"slab",
|
|
331
|
+
"smo",
|
|
332
|
+
"so",
|
|
333
|
+
"sobota",
|
|
334
|
+
"spet",
|
|
335
|
+
"sreda",
|
|
336
|
+
"srednja",
|
|
337
|
+
"srednji",
|
|
338
|
+
"sta",
|
|
339
|
+
"ste",
|
|
340
|
+
"stran",
|
|
341
|
+
"stvar",
|
|
342
|
+
"sva",
|
|
343
|
+
"t",
|
|
344
|
+
"ta",
|
|
345
|
+
"tak",
|
|
346
|
+
"taka",
|
|
347
|
+
"take",
|
|
348
|
+
"taki",
|
|
349
|
+
"tako",
|
|
350
|
+
"takoj",
|
|
351
|
+
"tam",
|
|
352
|
+
"te",
|
|
353
|
+
"tebe",
|
|
354
|
+
"tebi",
|
|
355
|
+
"tega",
|
|
356
|
+
"težak",
|
|
357
|
+
"težka",
|
|
358
|
+
"težki",
|
|
359
|
+
"težko",
|
|
360
|
+
"ti",
|
|
361
|
+
"tista",
|
|
362
|
+
"tiste",
|
|
363
|
+
"tisti",
|
|
364
|
+
"tisto",
|
|
365
|
+
"tj.",
|
|
366
|
+
"tja",
|
|
367
|
+
"to",
|
|
368
|
+
"toda",
|
|
369
|
+
"torek",
|
|
370
|
+
"tretja",
|
|
371
|
+
"tretje",
|
|
372
|
+
"tretji",
|
|
373
|
+
"tri",
|
|
374
|
+
"tu",
|
|
375
|
+
"tudi",
|
|
376
|
+
"tukaj",
|
|
377
|
+
"tvoj",
|
|
378
|
+
"tvoja",
|
|
379
|
+
"tvoje",
|
|
380
|
+
"u",
|
|
381
|
+
"v",
|
|
382
|
+
"vaju",
|
|
383
|
+
"vam",
|
|
384
|
+
"vas",
|
|
385
|
+
"vaš",
|
|
386
|
+
"vaša",
|
|
387
|
+
"vaše",
|
|
388
|
+
"ve",
|
|
389
|
+
"vedno",
|
|
390
|
+
"velik",
|
|
391
|
+
"velika",
|
|
392
|
+
"veliki",
|
|
393
|
+
"veliko",
|
|
394
|
+
"vendar",
|
|
395
|
+
"ves",
|
|
396
|
+
"več",
|
|
397
|
+
"vi",
|
|
398
|
+
"vidva",
|
|
399
|
+
"vii",
|
|
400
|
+
"viii",
|
|
401
|
+
"visok",
|
|
402
|
+
"visoka",
|
|
403
|
+
"visoke",
|
|
404
|
+
"visoki",
|
|
405
|
+
"vsa",
|
|
406
|
+
"vsaj",
|
|
407
|
+
"vsak",
|
|
408
|
+
"vsaka",
|
|
409
|
+
"vsakdo",
|
|
410
|
+
"vsake",
|
|
411
|
+
"vsaki",
|
|
412
|
+
"vsakomur",
|
|
413
|
+
"vse",
|
|
414
|
+
"vsega",
|
|
415
|
+
"vsi",
|
|
416
|
+
"vso",
|
|
417
|
+
"včasih",
|
|
418
|
+
"včeraj",
|
|
419
|
+
"x",
|
|
420
|
+
"z",
|
|
421
|
+
"za",
|
|
422
|
+
"zadaj",
|
|
423
|
+
"zadnji",
|
|
424
|
+
"zakaj",
|
|
425
|
+
"zaprta",
|
|
426
|
+
"zaprti",
|
|
427
|
+
"zaprto",
|
|
428
|
+
"zdaj",
|
|
429
|
+
"zelo",
|
|
430
|
+
"zunaj",
|
|
431
|
+
"č",
|
|
432
|
+
"če",
|
|
433
|
+
"često",
|
|
434
|
+
"četrta",
|
|
435
|
+
"četrtek",
|
|
436
|
+
"četrti",
|
|
437
|
+
"četrto",
|
|
438
|
+
"čez",
|
|
439
|
+
"čigav",
|
|
440
|
+
"š",
|
|
441
|
+
"šest",
|
|
442
|
+
"šesta",
|
|
443
|
+
"šesti",
|
|
444
|
+
"šesto",
|
|
445
|
+
"štiri",
|
|
446
|
+
"ž",
|
|
447
|
+
"že"
|
|
448
|
+
]
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
[
|
|
2
|
+
"aad",
|
|
3
|
+
"albaabkii",
|
|
4
|
+
"atabo",
|
|
5
|
+
"ay",
|
|
6
|
+
"ayaa",
|
|
7
|
+
"ayee",
|
|
8
|
+
"ayuu",
|
|
9
|
+
"dhan",
|
|
10
|
+
"hadana",
|
|
11
|
+
"in",
|
|
12
|
+
"inuu",
|
|
13
|
+
"isku",
|
|
14
|
+
"jiray",
|
|
15
|
+
"jirtay",
|
|
16
|
+
"ka",
|
|
17
|
+
"kale",
|
|
18
|
+
"kasoo",
|
|
19
|
+
"ku",
|
|
20
|
+
"kuu",
|
|
21
|
+
"lakin",
|
|
22
|
+
"markii",
|
|
23
|
+
"oo",
|
|
24
|
+
"si",
|
|
25
|
+
"soo",
|
|
26
|
+
"uga",
|
|
27
|
+
"ugu",
|
|
28
|
+
"uu",
|
|
29
|
+
"waa",
|
|
30
|
+
"waxa",
|
|
31
|
+
"waxuu"
|
|
32
|
+
]
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"ba",
|
|
4
|
+
"bane",
|
|
5
|
+
"bona",
|
|
6
|
+
"e",
|
|
7
|
+
"ea",
|
|
8
|
+
"eaba",
|
|
9
|
+
"empa",
|
|
10
|
+
"ena",
|
|
11
|
+
"ha",
|
|
12
|
+
"hae",
|
|
13
|
+
"hape",
|
|
14
|
+
"ho",
|
|
15
|
+
"hore",
|
|
16
|
+
"ka",
|
|
17
|
+
"ke",
|
|
18
|
+
"la",
|
|
19
|
+
"le",
|
|
20
|
+
"li",
|
|
21
|
+
"me",
|
|
22
|
+
"mo",
|
|
23
|
+
"moo",
|
|
24
|
+
"ne",
|
|
25
|
+
"o",
|
|
26
|
+
"oa",
|
|
27
|
+
"re",
|
|
28
|
+
"sa",
|
|
29
|
+
"se",
|
|
30
|
+
"tloha",
|
|
31
|
+
"tsa",
|
|
32
|
+
"tse"
|
|
33
|
+
]
|