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 +1,163 @@
|
|
|
1
|
+
[
|
|
2
|
+
"aiz",
|
|
3
|
+
"ap",
|
|
4
|
+
"apakš",
|
|
5
|
+
"apakšpus",
|
|
6
|
+
"ar",
|
|
7
|
+
"arī",
|
|
8
|
+
"augšpus",
|
|
9
|
+
"bet",
|
|
10
|
+
"bez",
|
|
11
|
+
"bija",
|
|
12
|
+
"biji",
|
|
13
|
+
"biju",
|
|
14
|
+
"bijām",
|
|
15
|
+
"bijāt",
|
|
16
|
+
"būs",
|
|
17
|
+
"būsi",
|
|
18
|
+
"būsiet",
|
|
19
|
+
"būsim",
|
|
20
|
+
"būt",
|
|
21
|
+
"būšu",
|
|
22
|
+
"caur",
|
|
23
|
+
"diemžēl",
|
|
24
|
+
"diezin",
|
|
25
|
+
"droši",
|
|
26
|
+
"dēļ",
|
|
27
|
+
"esam",
|
|
28
|
+
"esat",
|
|
29
|
+
"esi",
|
|
30
|
+
"esmu",
|
|
31
|
+
"gan",
|
|
32
|
+
"gar",
|
|
33
|
+
"iekam",
|
|
34
|
+
"iekams",
|
|
35
|
+
"iekām",
|
|
36
|
+
"iekāms",
|
|
37
|
+
"iekš",
|
|
38
|
+
"iekšpus",
|
|
39
|
+
"ik",
|
|
40
|
+
"ir",
|
|
41
|
+
"it",
|
|
42
|
+
"itin",
|
|
43
|
+
"iz",
|
|
44
|
+
"ja",
|
|
45
|
+
"jau",
|
|
46
|
+
"jeb",
|
|
47
|
+
"jebšu",
|
|
48
|
+
"jel",
|
|
49
|
+
"jo",
|
|
50
|
+
"jā",
|
|
51
|
+
"ka",
|
|
52
|
+
"kamēr",
|
|
53
|
+
"kaut",
|
|
54
|
+
"kolīdz",
|
|
55
|
+
"kopš",
|
|
56
|
+
"kā",
|
|
57
|
+
"kļuva",
|
|
58
|
+
"kļuvi",
|
|
59
|
+
"kļuvu",
|
|
60
|
+
"kļuvām",
|
|
61
|
+
"kļuvāt",
|
|
62
|
+
"kļūs",
|
|
63
|
+
"kļūsi",
|
|
64
|
+
"kļūsiet",
|
|
65
|
+
"kļūsim",
|
|
66
|
+
"kļūst",
|
|
67
|
+
"kļūstam",
|
|
68
|
+
"kļūstat",
|
|
69
|
+
"kļūsti",
|
|
70
|
+
"kļūstu",
|
|
71
|
+
"kļūt",
|
|
72
|
+
"kļūšu",
|
|
73
|
+
"labad",
|
|
74
|
+
"lai",
|
|
75
|
+
"lejpus",
|
|
76
|
+
"līdz",
|
|
77
|
+
"līdzko",
|
|
78
|
+
"ne",
|
|
79
|
+
"nebūt",
|
|
80
|
+
"nedz",
|
|
81
|
+
"nekā",
|
|
82
|
+
"nevis",
|
|
83
|
+
"nezin",
|
|
84
|
+
"no",
|
|
85
|
+
"nu",
|
|
86
|
+
"nē",
|
|
87
|
+
"otrpus",
|
|
88
|
+
"pa",
|
|
89
|
+
"par",
|
|
90
|
+
"pat",
|
|
91
|
+
"pie",
|
|
92
|
+
"pirms",
|
|
93
|
+
"pret",
|
|
94
|
+
"priekš",
|
|
95
|
+
"pār",
|
|
96
|
+
"pēc",
|
|
97
|
+
"starp",
|
|
98
|
+
"tad",
|
|
99
|
+
"tak",
|
|
100
|
+
"tapi",
|
|
101
|
+
"taps",
|
|
102
|
+
"tapsi",
|
|
103
|
+
"tapsiet",
|
|
104
|
+
"tapsim",
|
|
105
|
+
"tapt",
|
|
106
|
+
"tapāt",
|
|
107
|
+
"tapšu",
|
|
108
|
+
"taču",
|
|
109
|
+
"te",
|
|
110
|
+
"tiec",
|
|
111
|
+
"tiek",
|
|
112
|
+
"tiekam",
|
|
113
|
+
"tiekat",
|
|
114
|
+
"tieku",
|
|
115
|
+
"tik",
|
|
116
|
+
"tika",
|
|
117
|
+
"tikai",
|
|
118
|
+
"tiki",
|
|
119
|
+
"tikko",
|
|
120
|
+
"tiklab",
|
|
121
|
+
"tiklīdz",
|
|
122
|
+
"tiks",
|
|
123
|
+
"tiksiet",
|
|
124
|
+
"tiksim",
|
|
125
|
+
"tikt",
|
|
126
|
+
"tiku",
|
|
127
|
+
"tikvien",
|
|
128
|
+
"tikām",
|
|
129
|
+
"tikāt",
|
|
130
|
+
"tikšu",
|
|
131
|
+
"tomēr",
|
|
132
|
+
"topat",
|
|
133
|
+
"turpretim",
|
|
134
|
+
"turpretī",
|
|
135
|
+
"tā",
|
|
136
|
+
"tādēļ",
|
|
137
|
+
"tālab",
|
|
138
|
+
"tāpēc",
|
|
139
|
+
"un",
|
|
140
|
+
"uz",
|
|
141
|
+
"vai",
|
|
142
|
+
"var",
|
|
143
|
+
"varat",
|
|
144
|
+
"varēja",
|
|
145
|
+
"varēji",
|
|
146
|
+
"varēju",
|
|
147
|
+
"varējām",
|
|
148
|
+
"varējāt",
|
|
149
|
+
"varēs",
|
|
150
|
+
"varēsi",
|
|
151
|
+
"varēsiet",
|
|
152
|
+
"varēsim",
|
|
153
|
+
"varēt",
|
|
154
|
+
"varēšu",
|
|
155
|
+
"vien",
|
|
156
|
+
"virs",
|
|
157
|
+
"virspus",
|
|
158
|
+
"vis",
|
|
159
|
+
"viņpus",
|
|
160
|
+
"zem",
|
|
161
|
+
"ārpus",
|
|
162
|
+
"šaipus"
|
|
163
|
+
]
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
["അത്", "അന്നേരം", "അന്ന്", "ആകുന്നു", "ആണ്", "ആയിരുന്നു", "ഇത്", "ഇന്ന്", "വരെ"]
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
[
|
|
2
|
+
"अधिक",
|
|
3
|
+
"अनेक",
|
|
4
|
+
"अशी",
|
|
5
|
+
"असलयाचे",
|
|
6
|
+
"असलेल्या",
|
|
7
|
+
"असा",
|
|
8
|
+
"असून",
|
|
9
|
+
"असे",
|
|
10
|
+
"आज",
|
|
11
|
+
"आणि",
|
|
12
|
+
"आता",
|
|
13
|
+
"आपल्या",
|
|
14
|
+
"आला",
|
|
15
|
+
"आली",
|
|
16
|
+
"आले",
|
|
17
|
+
"आहे",
|
|
18
|
+
"आहेत",
|
|
19
|
+
"एक",
|
|
20
|
+
"एका",
|
|
21
|
+
"कमी",
|
|
22
|
+
"करणयात",
|
|
23
|
+
"करून",
|
|
24
|
+
"का",
|
|
25
|
+
"काम",
|
|
26
|
+
"काय",
|
|
27
|
+
"काही",
|
|
28
|
+
"किवा",
|
|
29
|
+
"की",
|
|
30
|
+
"केला",
|
|
31
|
+
"केली",
|
|
32
|
+
"केले",
|
|
33
|
+
"कोटी",
|
|
34
|
+
"गेल्या",
|
|
35
|
+
"घेऊन",
|
|
36
|
+
"जात",
|
|
37
|
+
"झाला",
|
|
38
|
+
"झाली",
|
|
39
|
+
"झाले",
|
|
40
|
+
"झालेल्या",
|
|
41
|
+
"टा",
|
|
42
|
+
"डॉ",
|
|
43
|
+
"तर",
|
|
44
|
+
"तरी",
|
|
45
|
+
"तसेच",
|
|
46
|
+
"ता",
|
|
47
|
+
"ती",
|
|
48
|
+
"तीन",
|
|
49
|
+
"ते",
|
|
50
|
+
"तो",
|
|
51
|
+
"त्या",
|
|
52
|
+
"त्याचा",
|
|
53
|
+
"त्याची",
|
|
54
|
+
"त्याच्या",
|
|
55
|
+
"त्याना",
|
|
56
|
+
"त्यानी",
|
|
57
|
+
"त्यामुळे",
|
|
58
|
+
"त्री",
|
|
59
|
+
"दिली",
|
|
60
|
+
"दोन",
|
|
61
|
+
"न",
|
|
62
|
+
"नाही",
|
|
63
|
+
"निर्ण्य",
|
|
64
|
+
"पण",
|
|
65
|
+
"पम",
|
|
66
|
+
"परयतन",
|
|
67
|
+
"पाटील",
|
|
68
|
+
"म",
|
|
69
|
+
"मात्र",
|
|
70
|
+
"माहिती",
|
|
71
|
+
"मी",
|
|
72
|
+
"मुबी",
|
|
73
|
+
"म्हणजे",
|
|
74
|
+
"म्हणाले",
|
|
75
|
+
"म्हणून",
|
|
76
|
+
"या",
|
|
77
|
+
"याचा",
|
|
78
|
+
"याची",
|
|
79
|
+
"याच्या",
|
|
80
|
+
"याना",
|
|
81
|
+
"यानी",
|
|
82
|
+
"येणार",
|
|
83
|
+
"येत",
|
|
84
|
+
"येथील",
|
|
85
|
+
"येथे",
|
|
86
|
+
"लाख",
|
|
87
|
+
"व",
|
|
88
|
+
"व्यकत",
|
|
89
|
+
"सर्व",
|
|
90
|
+
"सागित्ले",
|
|
91
|
+
"सुरू",
|
|
92
|
+
"हजार",
|
|
93
|
+
"हा",
|
|
94
|
+
"ही",
|
|
95
|
+
"हे",
|
|
96
|
+
"होणार",
|
|
97
|
+
"होत",
|
|
98
|
+
"होता",
|
|
99
|
+
"होती",
|
|
100
|
+
"होते"
|
|
101
|
+
]
|