kreuzberg 4.0.0.rc1
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 +8 -0
- data/.rspec +3 -0
- data/.rubocop.yaml +534 -0
- data/Gemfile +9 -0
- data/Gemfile.lock +157 -0
- data/README.md +421 -0
- data/Rakefile +25 -0
- data/Steepfile +47 -0
- data/examples/async_patterns.rb +340 -0
- data/ext/kreuzberg_rb/extconf.rb +35 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
- data/ext/kreuzberg_rb/native/README.md +425 -0
- data/ext/kreuzberg_rb/native/build.rs +17 -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 +2939 -0
- data/extconf.rb +28 -0
- data/kreuzberg.gemspec +105 -0
- data/lib/kreuzberg/api_proxy.rb +142 -0
- data/lib/kreuzberg/cache_api.rb +45 -0
- data/lib/kreuzberg/cli.rb +55 -0
- data/lib/kreuzberg/cli_proxy.rb +127 -0
- data/lib/kreuzberg/config.rb +684 -0
- data/lib/kreuzberg/errors.rb +50 -0
- data/lib/kreuzberg/extraction_api.rb +84 -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 +79 -0
- data/lib/kreuzberg/validator_protocol.rb +89 -0
- data/lib/kreuzberg/version.rb +5 -0
- data/lib/kreuzberg.rb +82 -0
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg/internal.rbs +184 -0
- data/sig/kreuzberg.rbs +468 -0
- data/spec/binding/cache_spec.rb +227 -0
- data/spec/binding/cli_proxy_spec.rb +87 -0
- data/spec/binding/cli_spec.rb +54 -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/examples.txt +104 -0
- data/spec/fixtures/config.toml +39 -0
- data/spec/fixtures/config.yaml +42 -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 +134 -0
- data/vendor/kreuzberg/README.md +175 -0
- data/vendor/kreuzberg/build.rs +460 -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/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
- data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
- data/vendor/kreuzberg/src/core/config.rs +1032 -0
- data/vendor/kreuzberg/src/core/extractor.rs +903 -0
- data/vendor/kreuzberg/src/core/io.rs +327 -0
- data/vendor/kreuzberg/src/core/mime.rs +615 -0
- data/vendor/kreuzberg/src/core/mod.rs +42 -0
- data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
- data/vendor/kreuzberg/src/embeddings.rs +323 -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 +564 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +77 -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 +128 -0
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -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 +425 -0
- data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
- data/vendor/kreuzberg/src/extractors/email.rs +129 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
- data/vendor/kreuzberg/src/extractors/html.rs +410 -0
- data/vendor/kreuzberg/src/extractors/image.rs +195 -0
- data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
- data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
- data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
- data/vendor/kreuzberg/src/extractors/text.rs +242 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +128 -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 +294 -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 +102 -0
- data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
- data/vendor/kreuzberg/src/mcp/server.rs +1966 -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 +847 -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/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 +420 -0
- data/vendor/kreuzberg/src/pdf/text.rs +161 -0
- data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
- data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
- data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
- data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
- data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
- data/vendor/kreuzberg/src/plugins/validator.rs +955 -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 +873 -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_tests.rs +966 -0
- data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
- data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
- data/vendor/kreuzberg/tests/config_features.rs +580 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
- data/vendor/kreuzberg/tests/core_integration.rs +493 -0
- data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
- data/vendor/kreuzberg/tests/email_integration.rs +325 -0
- data/vendor/kreuzberg/tests/error_handling.rs +393 -0
- data/vendor/kreuzberg/tests/format_integration.rs +159 -0
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
- data/vendor/kreuzberg/tests/image_integration.rs +253 -0
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -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/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -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 +607 -0
- data/vendor/kreuzberg/tests/security_validation.rs +404 -0
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
- data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
- metadata +471 -0
|
@@ -0,0 +1,193 @@
|
|
|
1
|
+
[
|
|
2
|
+
"අතර",
|
|
3
|
+
"අන්න",
|
|
4
|
+
"අනුව",
|
|
5
|
+
"අනුව",
|
|
6
|
+
"අනේ",
|
|
7
|
+
"අඳෝ",
|
|
8
|
+
"අපොයි",
|
|
9
|
+
"අපෝ",
|
|
10
|
+
"අයියෝ",
|
|
11
|
+
"අයුරින්",
|
|
12
|
+
"අයුරු",
|
|
13
|
+
"අරබයා",
|
|
14
|
+
"අහා",
|
|
15
|
+
"ආ",
|
|
16
|
+
"ආයි",
|
|
17
|
+
"ආහ්",
|
|
18
|
+
"ඇති",
|
|
19
|
+
"ඇතුලු",
|
|
20
|
+
"ඇතුළු",
|
|
21
|
+
"ඇයි",
|
|
22
|
+
"ඉක්බිති",
|
|
23
|
+
"ඉතා",
|
|
24
|
+
"ඉතා",
|
|
25
|
+
"ඉතින්",
|
|
26
|
+
"ඉඳුරා",
|
|
27
|
+
"උදෙසා",
|
|
28
|
+
"ඌයි",
|
|
29
|
+
"එ",
|
|
30
|
+
"එනමුත්",
|
|
31
|
+
"එනිසා",
|
|
32
|
+
"එබැවින්",
|
|
33
|
+
"එම",
|
|
34
|
+
"එම්බල",
|
|
35
|
+
"එම්බා",
|
|
36
|
+
"එහෙත්",
|
|
37
|
+
"එහෙන්",
|
|
38
|
+
"එහේ",
|
|
39
|
+
"ඒ",
|
|
40
|
+
"ඔන්න",
|
|
41
|
+
"ඕහෝ",
|
|
42
|
+
"ක",
|
|
43
|
+
"කලී",
|
|
44
|
+
"ක්",
|
|
45
|
+
"කිම",
|
|
46
|
+
"කිම්",
|
|
47
|
+
"ගානෙ",
|
|
48
|
+
"ගැන",
|
|
49
|
+
"ගැන",
|
|
50
|
+
"ගේ",
|
|
51
|
+
"චික්",
|
|
52
|
+
"චිහ්",
|
|
53
|
+
"චී",
|
|
54
|
+
"ට",
|
|
55
|
+
"තව",
|
|
56
|
+
"තව",
|
|
57
|
+
"තවත්",
|
|
58
|
+
"තාක්",
|
|
59
|
+
"තුරා",
|
|
60
|
+
"තුරාවට",
|
|
61
|
+
"තුරු",
|
|
62
|
+
"තුලින්",
|
|
63
|
+
"තුවක්",
|
|
64
|
+
"තුළ",
|
|
65
|
+
"තෙක්",
|
|
66
|
+
"තෙක්",
|
|
67
|
+
"ද",
|
|
68
|
+
"ද",
|
|
69
|
+
"දක්වා",
|
|
70
|
+
"දක්වා",
|
|
71
|
+
"දැනට",
|
|
72
|
+
"දැන්",
|
|
73
|
+
"දී",
|
|
74
|
+
"දෝ",
|
|
75
|
+
"දෝහෝ",
|
|
76
|
+
"නම්",
|
|
77
|
+
"නම්",
|
|
78
|
+
"නමුත්",
|
|
79
|
+
"නව",
|
|
80
|
+
"නෑ",
|
|
81
|
+
"නිතර",
|
|
82
|
+
"නිති",
|
|
83
|
+
"නිතිත්",
|
|
84
|
+
"නිතොර",
|
|
85
|
+
"නිසා",
|
|
86
|
+
"නිසා",
|
|
87
|
+
"නිසාවෙන්",
|
|
88
|
+
"නොහොත්",
|
|
89
|
+
"පටන්",
|
|
90
|
+
"පතා",
|
|
91
|
+
"පමණ",
|
|
92
|
+
"පමණින්",
|
|
93
|
+
"පමන",
|
|
94
|
+
"පරිදි",
|
|
95
|
+
"පරිදි",
|
|
96
|
+
"පවා",
|
|
97
|
+
"පාසා",
|
|
98
|
+
"පිණිස",
|
|
99
|
+
"පිළිබඳ",
|
|
100
|
+
"පිළිබඳ",
|
|
101
|
+
"පිළිබඳව",
|
|
102
|
+
"පුන",
|
|
103
|
+
"බඳු",
|
|
104
|
+
"බව",
|
|
105
|
+
"බව",
|
|
106
|
+
"බවට",
|
|
107
|
+
"බවත්",
|
|
108
|
+
"බවද",
|
|
109
|
+
"බවෙන්",
|
|
110
|
+
"බැවින්",
|
|
111
|
+
"බොල",
|
|
112
|
+
"බොහෝ",
|
|
113
|
+
"ම",
|
|
114
|
+
"මගින්",
|
|
115
|
+
"මත",
|
|
116
|
+
"මන්ද",
|
|
117
|
+
"මහ",
|
|
118
|
+
"මහ",
|
|
119
|
+
"මහා",
|
|
120
|
+
"මිස",
|
|
121
|
+
"මුත්",
|
|
122
|
+
"මෙතෙක්",
|
|
123
|
+
"මෙන්",
|
|
124
|
+
"මෙන්",
|
|
125
|
+
"මෙන්න",
|
|
126
|
+
"මෙම",
|
|
127
|
+
"මෙයින්",
|
|
128
|
+
"මෙලෙස",
|
|
129
|
+
"මෙසේ",
|
|
130
|
+
"මෙහි",
|
|
131
|
+
"මෙහෙන්",
|
|
132
|
+
"මෙහේ",
|
|
133
|
+
"මේ",
|
|
134
|
+
"මේ",
|
|
135
|
+
"මේතාක්",
|
|
136
|
+
"ය",
|
|
137
|
+
"යන",
|
|
138
|
+
"යලි",
|
|
139
|
+
"ලෙස",
|
|
140
|
+
"ලෙස",
|
|
141
|
+
"ලෙස",
|
|
142
|
+
"වඩා",
|
|
143
|
+
"වඩාත්ම",
|
|
144
|
+
"වත්",
|
|
145
|
+
"වන",
|
|
146
|
+
"වන්",
|
|
147
|
+
"වනාහි",
|
|
148
|
+
"වශයෙන්",
|
|
149
|
+
"වස්",
|
|
150
|
+
"වහා",
|
|
151
|
+
"වැඩි",
|
|
152
|
+
"වැඩි",
|
|
153
|
+
"වැනි",
|
|
154
|
+
"වැනි",
|
|
155
|
+
"විට",
|
|
156
|
+
"විට",
|
|
157
|
+
"විටින්",
|
|
158
|
+
"විනා",
|
|
159
|
+
"විශේෂ",
|
|
160
|
+
"විසින්",
|
|
161
|
+
"වෙත",
|
|
162
|
+
"වෙතට",
|
|
163
|
+
"වෙතින්",
|
|
164
|
+
"වෙන",
|
|
165
|
+
"වෙනුවට",
|
|
166
|
+
"වෙනුවෙන්",
|
|
167
|
+
"ශ්රී",
|
|
168
|
+
"සඳහා",
|
|
169
|
+
"සඳහා",
|
|
170
|
+
"සමග",
|
|
171
|
+
"සමග",
|
|
172
|
+
"සමඟ",
|
|
173
|
+
"සහ",
|
|
174
|
+
"සහ",
|
|
175
|
+
"සා",
|
|
176
|
+
"සැනින්",
|
|
177
|
+
"සිට",
|
|
178
|
+
"සිට",
|
|
179
|
+
"සිටන්",
|
|
180
|
+
"සිදු",
|
|
181
|
+
"සෙද",
|
|
182
|
+
"සේ",
|
|
183
|
+
"සේක",
|
|
184
|
+
"සේක්",
|
|
185
|
+
"හනික",
|
|
186
|
+
"හා",
|
|
187
|
+
"හැර",
|
|
188
|
+
"හෙයින්",
|
|
189
|
+
"හෙවත්",
|
|
190
|
+
"හෝ",
|
|
191
|
+
"හෝ",
|
|
192
|
+
"හෝ"
|
|
193
|
+
]
|
|
@@ -0,0 +1,420 @@
|
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"aby",
|
|
4
|
+
"aj",
|
|
5
|
+
"ak",
|
|
6
|
+
"akej",
|
|
7
|
+
"akejže",
|
|
8
|
+
"ako",
|
|
9
|
+
"akom",
|
|
10
|
+
"akomže",
|
|
11
|
+
"akou",
|
|
12
|
+
"akouže",
|
|
13
|
+
"akože",
|
|
14
|
+
"aká",
|
|
15
|
+
"akáže",
|
|
16
|
+
"aké",
|
|
17
|
+
"akého",
|
|
18
|
+
"akéhože",
|
|
19
|
+
"akému",
|
|
20
|
+
"akémuže",
|
|
21
|
+
"akéže",
|
|
22
|
+
"akú",
|
|
23
|
+
"akúže",
|
|
24
|
+
"aký",
|
|
25
|
+
"akých",
|
|
26
|
+
"akýchže",
|
|
27
|
+
"akým",
|
|
28
|
+
"akými",
|
|
29
|
+
"akýmiže",
|
|
30
|
+
"akýmže",
|
|
31
|
+
"akýže",
|
|
32
|
+
"ale",
|
|
33
|
+
"alebo",
|
|
34
|
+
"ani",
|
|
35
|
+
"asi",
|
|
36
|
+
"avšak",
|
|
37
|
+
"až",
|
|
38
|
+
"ba",
|
|
39
|
+
"bez",
|
|
40
|
+
"bezo",
|
|
41
|
+
"bol",
|
|
42
|
+
"bola",
|
|
43
|
+
"boli",
|
|
44
|
+
"bolo",
|
|
45
|
+
"bude",
|
|
46
|
+
"budem",
|
|
47
|
+
"budeme",
|
|
48
|
+
"budete",
|
|
49
|
+
"budeš",
|
|
50
|
+
"budú",
|
|
51
|
+
"buď",
|
|
52
|
+
"by",
|
|
53
|
+
"byť",
|
|
54
|
+
"cez",
|
|
55
|
+
"cezo",
|
|
56
|
+
"dnes",
|
|
57
|
+
"do",
|
|
58
|
+
"ešte",
|
|
59
|
+
"ho",
|
|
60
|
+
"hoci",
|
|
61
|
+
"i",
|
|
62
|
+
"iba",
|
|
63
|
+
"ich",
|
|
64
|
+
"im",
|
|
65
|
+
"inej",
|
|
66
|
+
"inom",
|
|
67
|
+
"iná",
|
|
68
|
+
"iné",
|
|
69
|
+
"iného",
|
|
70
|
+
"inému",
|
|
71
|
+
"iní",
|
|
72
|
+
"inú",
|
|
73
|
+
"iný",
|
|
74
|
+
"iných",
|
|
75
|
+
"iným",
|
|
76
|
+
"inými",
|
|
77
|
+
"ja",
|
|
78
|
+
"je",
|
|
79
|
+
"jeho",
|
|
80
|
+
"jej",
|
|
81
|
+
"jemu",
|
|
82
|
+
"ju",
|
|
83
|
+
"k",
|
|
84
|
+
"kam",
|
|
85
|
+
"kamže",
|
|
86
|
+
"každou",
|
|
87
|
+
"každá",
|
|
88
|
+
"každé",
|
|
89
|
+
"každého",
|
|
90
|
+
"každému",
|
|
91
|
+
"každí",
|
|
92
|
+
"každú",
|
|
93
|
+
"každý",
|
|
94
|
+
"každých",
|
|
95
|
+
"každým",
|
|
96
|
+
"každými",
|
|
97
|
+
"kde",
|
|
98
|
+
"kej",
|
|
99
|
+
"kejže",
|
|
100
|
+
"keď",
|
|
101
|
+
"keďže",
|
|
102
|
+
"kie",
|
|
103
|
+
"kieho",
|
|
104
|
+
"kiehože",
|
|
105
|
+
"kiemu",
|
|
106
|
+
"kiemuže",
|
|
107
|
+
"kieže",
|
|
108
|
+
"koho",
|
|
109
|
+
"kom",
|
|
110
|
+
"komu",
|
|
111
|
+
"kou",
|
|
112
|
+
"kouže",
|
|
113
|
+
"kto",
|
|
114
|
+
"ktorej",
|
|
115
|
+
"ktorou",
|
|
116
|
+
"ktorá",
|
|
117
|
+
"ktoré",
|
|
118
|
+
"ktorí",
|
|
119
|
+
"ktorú",
|
|
120
|
+
"ktorý",
|
|
121
|
+
"ktorých",
|
|
122
|
+
"ktorým",
|
|
123
|
+
"ktorými",
|
|
124
|
+
"ku",
|
|
125
|
+
"ká",
|
|
126
|
+
"káže",
|
|
127
|
+
"ké",
|
|
128
|
+
"kéže",
|
|
129
|
+
"kú",
|
|
130
|
+
"kúže",
|
|
131
|
+
"ký",
|
|
132
|
+
"kýho",
|
|
133
|
+
"kýhože",
|
|
134
|
+
"kým",
|
|
135
|
+
"kýmu",
|
|
136
|
+
"kýmuže",
|
|
137
|
+
"kýže",
|
|
138
|
+
"lebo",
|
|
139
|
+
"leda",
|
|
140
|
+
"ledaže",
|
|
141
|
+
"len",
|
|
142
|
+
"ma",
|
|
143
|
+
"majú",
|
|
144
|
+
"mal",
|
|
145
|
+
"mala",
|
|
146
|
+
"mali",
|
|
147
|
+
"mať",
|
|
148
|
+
"medzi",
|
|
149
|
+
"mi",
|
|
150
|
+
"mne",
|
|
151
|
+
"mnou",
|
|
152
|
+
"moja",
|
|
153
|
+
"moje",
|
|
154
|
+
"mojej",
|
|
155
|
+
"mojich",
|
|
156
|
+
"mojim",
|
|
157
|
+
"mojimi",
|
|
158
|
+
"mojou",
|
|
159
|
+
"moju",
|
|
160
|
+
"možno",
|
|
161
|
+
"mu",
|
|
162
|
+
"musia",
|
|
163
|
+
"musieť",
|
|
164
|
+
"musí",
|
|
165
|
+
"musím",
|
|
166
|
+
"musíme",
|
|
167
|
+
"musíte",
|
|
168
|
+
"musíš",
|
|
169
|
+
"my",
|
|
170
|
+
"má",
|
|
171
|
+
"mám",
|
|
172
|
+
"máme",
|
|
173
|
+
"máte",
|
|
174
|
+
"máš",
|
|
175
|
+
"môcť",
|
|
176
|
+
"môj",
|
|
177
|
+
"môjho",
|
|
178
|
+
"môže",
|
|
179
|
+
"môžem",
|
|
180
|
+
"môžeme",
|
|
181
|
+
"môžete",
|
|
182
|
+
"môžeš",
|
|
183
|
+
"môžu",
|
|
184
|
+
"mňa",
|
|
185
|
+
"na",
|
|
186
|
+
"nad",
|
|
187
|
+
"nado",
|
|
188
|
+
"najmä",
|
|
189
|
+
"nami",
|
|
190
|
+
"naša",
|
|
191
|
+
"naše",
|
|
192
|
+
"našej",
|
|
193
|
+
"naši",
|
|
194
|
+
"našich",
|
|
195
|
+
"našim",
|
|
196
|
+
"našimi",
|
|
197
|
+
"našou",
|
|
198
|
+
"ne",
|
|
199
|
+
"nech",
|
|
200
|
+
"neho",
|
|
201
|
+
"nej",
|
|
202
|
+
"nejakej",
|
|
203
|
+
"nejakom",
|
|
204
|
+
"nejakou",
|
|
205
|
+
"nejaká",
|
|
206
|
+
"nejaké",
|
|
207
|
+
"nejakého",
|
|
208
|
+
"nejakému",
|
|
209
|
+
"nejakú",
|
|
210
|
+
"nejaký",
|
|
211
|
+
"nejakých",
|
|
212
|
+
"nejakým",
|
|
213
|
+
"nejakými",
|
|
214
|
+
"nemu",
|
|
215
|
+
"než",
|
|
216
|
+
"nich",
|
|
217
|
+
"nie",
|
|
218
|
+
"niektorej",
|
|
219
|
+
"niektorom",
|
|
220
|
+
"niektorou",
|
|
221
|
+
"niektorá",
|
|
222
|
+
"niektoré",
|
|
223
|
+
"niektorého",
|
|
224
|
+
"niektorému",
|
|
225
|
+
"niektorú",
|
|
226
|
+
"niektorý",
|
|
227
|
+
"niektorých",
|
|
228
|
+
"niektorým",
|
|
229
|
+
"niektorými",
|
|
230
|
+
"nielen",
|
|
231
|
+
"niečo",
|
|
232
|
+
"nim",
|
|
233
|
+
"nimi",
|
|
234
|
+
"nič",
|
|
235
|
+
"ničoho",
|
|
236
|
+
"ničom",
|
|
237
|
+
"ničomu",
|
|
238
|
+
"ničím",
|
|
239
|
+
"no",
|
|
240
|
+
"nám",
|
|
241
|
+
"nás",
|
|
242
|
+
"náš",
|
|
243
|
+
"nášho",
|
|
244
|
+
"ním",
|
|
245
|
+
"o",
|
|
246
|
+
"od",
|
|
247
|
+
"odo",
|
|
248
|
+
"on",
|
|
249
|
+
"ona",
|
|
250
|
+
"oni",
|
|
251
|
+
"ono",
|
|
252
|
+
"ony",
|
|
253
|
+
"oň",
|
|
254
|
+
"oňho",
|
|
255
|
+
"po",
|
|
256
|
+
"pod",
|
|
257
|
+
"podo",
|
|
258
|
+
"podľa",
|
|
259
|
+
"pokiaľ",
|
|
260
|
+
"popod",
|
|
261
|
+
"popri",
|
|
262
|
+
"potom",
|
|
263
|
+
"poza",
|
|
264
|
+
"pre",
|
|
265
|
+
"pred",
|
|
266
|
+
"predo",
|
|
267
|
+
"preto",
|
|
268
|
+
"pretože",
|
|
269
|
+
"prečo",
|
|
270
|
+
"pri",
|
|
271
|
+
"práve",
|
|
272
|
+
"s",
|
|
273
|
+
"sa",
|
|
274
|
+
"seba",
|
|
275
|
+
"sebe",
|
|
276
|
+
"sebou",
|
|
277
|
+
"sem",
|
|
278
|
+
"si",
|
|
279
|
+
"sme",
|
|
280
|
+
"so",
|
|
281
|
+
"som",
|
|
282
|
+
"ste",
|
|
283
|
+
"svoj",
|
|
284
|
+
"svoja",
|
|
285
|
+
"svoje",
|
|
286
|
+
"svojho",
|
|
287
|
+
"svojich",
|
|
288
|
+
"svojim",
|
|
289
|
+
"svojimi",
|
|
290
|
+
"svojou",
|
|
291
|
+
"svoju",
|
|
292
|
+
"svojím",
|
|
293
|
+
"sú",
|
|
294
|
+
"ta",
|
|
295
|
+
"tak",
|
|
296
|
+
"takej",
|
|
297
|
+
"takejto",
|
|
298
|
+
"taká",
|
|
299
|
+
"takáto",
|
|
300
|
+
"také",
|
|
301
|
+
"takého",
|
|
302
|
+
"takéhoto",
|
|
303
|
+
"takému",
|
|
304
|
+
"takémuto",
|
|
305
|
+
"takéto",
|
|
306
|
+
"takí",
|
|
307
|
+
"takú",
|
|
308
|
+
"takúto",
|
|
309
|
+
"taký",
|
|
310
|
+
"takýto",
|
|
311
|
+
"takže",
|
|
312
|
+
"tam",
|
|
313
|
+
"teba",
|
|
314
|
+
"tebe",
|
|
315
|
+
"tebou",
|
|
316
|
+
"teda",
|
|
317
|
+
"tej",
|
|
318
|
+
"tejto",
|
|
319
|
+
"ten",
|
|
320
|
+
"tento",
|
|
321
|
+
"ti",
|
|
322
|
+
"tie",
|
|
323
|
+
"tieto",
|
|
324
|
+
"tiež",
|
|
325
|
+
"to",
|
|
326
|
+
"toho",
|
|
327
|
+
"tohoto",
|
|
328
|
+
"tohto",
|
|
329
|
+
"tom",
|
|
330
|
+
"tomto",
|
|
331
|
+
"tomu",
|
|
332
|
+
"tomuto",
|
|
333
|
+
"toto",
|
|
334
|
+
"tou",
|
|
335
|
+
"touto",
|
|
336
|
+
"tu",
|
|
337
|
+
"tvoj",
|
|
338
|
+
"tvoja",
|
|
339
|
+
"tvoje",
|
|
340
|
+
"tvojej",
|
|
341
|
+
"tvojho",
|
|
342
|
+
"tvoji",
|
|
343
|
+
"tvojich",
|
|
344
|
+
"tvojim",
|
|
345
|
+
"tvojimi",
|
|
346
|
+
"tvojím",
|
|
347
|
+
"ty",
|
|
348
|
+
"tá",
|
|
349
|
+
"táto",
|
|
350
|
+
"tí",
|
|
351
|
+
"títo",
|
|
352
|
+
"tú",
|
|
353
|
+
"túto",
|
|
354
|
+
"tých",
|
|
355
|
+
"tým",
|
|
356
|
+
"tými",
|
|
357
|
+
"týmto",
|
|
358
|
+
"u",
|
|
359
|
+
"už",
|
|
360
|
+
"v",
|
|
361
|
+
"vami",
|
|
362
|
+
"vaša",
|
|
363
|
+
"vaše",
|
|
364
|
+
"vašej",
|
|
365
|
+
"vaši",
|
|
366
|
+
"vašich",
|
|
367
|
+
"vašim",
|
|
368
|
+
"vaším",
|
|
369
|
+
"veď",
|
|
370
|
+
"viac",
|
|
371
|
+
"vo",
|
|
372
|
+
"vy",
|
|
373
|
+
"vám",
|
|
374
|
+
"vás",
|
|
375
|
+
"váš",
|
|
376
|
+
"vášho",
|
|
377
|
+
"však",
|
|
378
|
+
"všetci",
|
|
379
|
+
"všetka",
|
|
380
|
+
"všetko",
|
|
381
|
+
"všetky",
|
|
382
|
+
"všetok",
|
|
383
|
+
"z",
|
|
384
|
+
"za",
|
|
385
|
+
"začo",
|
|
386
|
+
"začože",
|
|
387
|
+
"zo",
|
|
388
|
+
"áno",
|
|
389
|
+
"čej",
|
|
390
|
+
"či",
|
|
391
|
+
"čia",
|
|
392
|
+
"čie",
|
|
393
|
+
"čieho",
|
|
394
|
+
"čiemu",
|
|
395
|
+
"čiu",
|
|
396
|
+
"čo",
|
|
397
|
+
"čoho",
|
|
398
|
+
"čom",
|
|
399
|
+
"čomu",
|
|
400
|
+
"čou",
|
|
401
|
+
"čože",
|
|
402
|
+
"čí",
|
|
403
|
+
"čím",
|
|
404
|
+
"čími",
|
|
405
|
+
"ďalšia",
|
|
406
|
+
"ďalšie",
|
|
407
|
+
"ďalšieho",
|
|
408
|
+
"ďalšiemu",
|
|
409
|
+
"ďalšiu",
|
|
410
|
+
"ďalšom",
|
|
411
|
+
"ďalšou",
|
|
412
|
+
"ďalší",
|
|
413
|
+
"ďalších",
|
|
414
|
+
"ďalším",
|
|
415
|
+
"ďalšími",
|
|
416
|
+
"ňom",
|
|
417
|
+
"ňou",
|
|
418
|
+
"ňu",
|
|
419
|
+
"že"
|
|
420
|
+
]
|