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 +1,420 @@
|
|
|
1
|
+
[
|
|
2
|
+
"aderton",
|
|
3
|
+
"adertonde",
|
|
4
|
+
"adjö",
|
|
5
|
+
"aldrig",
|
|
6
|
+
"alla",
|
|
7
|
+
"allas",
|
|
8
|
+
"allt",
|
|
9
|
+
"alltid",
|
|
10
|
+
"alltså",
|
|
11
|
+
"andra",
|
|
12
|
+
"andras",
|
|
13
|
+
"annan",
|
|
14
|
+
"annat",
|
|
15
|
+
"artonde",
|
|
16
|
+
"artonn",
|
|
17
|
+
"att",
|
|
18
|
+
"av",
|
|
19
|
+
"bakom",
|
|
20
|
+
"bara",
|
|
21
|
+
"behöva",
|
|
22
|
+
"behövas",
|
|
23
|
+
"behövde",
|
|
24
|
+
"behövt",
|
|
25
|
+
"beslut",
|
|
26
|
+
"beslutat",
|
|
27
|
+
"beslutit",
|
|
28
|
+
"bland",
|
|
29
|
+
"blev",
|
|
30
|
+
"bli",
|
|
31
|
+
"blir",
|
|
32
|
+
"blivit",
|
|
33
|
+
"bort",
|
|
34
|
+
"borta",
|
|
35
|
+
"bra",
|
|
36
|
+
"bäst",
|
|
37
|
+
"bättre",
|
|
38
|
+
"båda",
|
|
39
|
+
"bådas",
|
|
40
|
+
"dag",
|
|
41
|
+
"dagar",
|
|
42
|
+
"dagarna",
|
|
43
|
+
"dagen",
|
|
44
|
+
"de",
|
|
45
|
+
"del",
|
|
46
|
+
"delen",
|
|
47
|
+
"dem",
|
|
48
|
+
"den",
|
|
49
|
+
"denna",
|
|
50
|
+
"deras",
|
|
51
|
+
"dess",
|
|
52
|
+
"dessa",
|
|
53
|
+
"det",
|
|
54
|
+
"detta",
|
|
55
|
+
"dig",
|
|
56
|
+
"din",
|
|
57
|
+
"dina",
|
|
58
|
+
"dit",
|
|
59
|
+
"ditt",
|
|
60
|
+
"dock",
|
|
61
|
+
"dom",
|
|
62
|
+
"du",
|
|
63
|
+
"där",
|
|
64
|
+
"därför",
|
|
65
|
+
"då",
|
|
66
|
+
"e",
|
|
67
|
+
"efter",
|
|
68
|
+
"eftersom",
|
|
69
|
+
"ej",
|
|
70
|
+
"elfte",
|
|
71
|
+
"eller",
|
|
72
|
+
"elva",
|
|
73
|
+
"emot",
|
|
74
|
+
"en",
|
|
75
|
+
"enkel",
|
|
76
|
+
"enkelt",
|
|
77
|
+
"enkla",
|
|
78
|
+
"enligt",
|
|
79
|
+
"ens",
|
|
80
|
+
"er",
|
|
81
|
+
"era",
|
|
82
|
+
"ers",
|
|
83
|
+
"ert",
|
|
84
|
+
"ett",
|
|
85
|
+
"ettusen",
|
|
86
|
+
"fanns",
|
|
87
|
+
"fem",
|
|
88
|
+
"femte",
|
|
89
|
+
"femtio",
|
|
90
|
+
"femtionde",
|
|
91
|
+
"femton",
|
|
92
|
+
"femtonde",
|
|
93
|
+
"fick",
|
|
94
|
+
"fin",
|
|
95
|
+
"finnas",
|
|
96
|
+
"finns",
|
|
97
|
+
"fjorton",
|
|
98
|
+
"fjortonde",
|
|
99
|
+
"fjärde",
|
|
100
|
+
"fler",
|
|
101
|
+
"flera",
|
|
102
|
+
"flesta",
|
|
103
|
+
"fram",
|
|
104
|
+
"framför",
|
|
105
|
+
"från",
|
|
106
|
+
"fyra",
|
|
107
|
+
"fyrtio",
|
|
108
|
+
"fyrtionde",
|
|
109
|
+
"få",
|
|
110
|
+
"får",
|
|
111
|
+
"fått",
|
|
112
|
+
"följande",
|
|
113
|
+
"för",
|
|
114
|
+
"före",
|
|
115
|
+
"förlåt",
|
|
116
|
+
"förra",
|
|
117
|
+
"första",
|
|
118
|
+
"genast",
|
|
119
|
+
"genom",
|
|
120
|
+
"gick",
|
|
121
|
+
"gjorde",
|
|
122
|
+
"gjort",
|
|
123
|
+
"god",
|
|
124
|
+
"goda",
|
|
125
|
+
"godare",
|
|
126
|
+
"godast",
|
|
127
|
+
"gott",
|
|
128
|
+
"gälla",
|
|
129
|
+
"gäller",
|
|
130
|
+
"gällt",
|
|
131
|
+
"gärna",
|
|
132
|
+
"gå",
|
|
133
|
+
"går",
|
|
134
|
+
"gått",
|
|
135
|
+
"gör",
|
|
136
|
+
"göra",
|
|
137
|
+
"ha",
|
|
138
|
+
"hade",
|
|
139
|
+
"haft",
|
|
140
|
+
"han",
|
|
141
|
+
"hans",
|
|
142
|
+
"har",
|
|
143
|
+
"heller",
|
|
144
|
+
"hellre",
|
|
145
|
+
"helst",
|
|
146
|
+
"helt",
|
|
147
|
+
"henne",
|
|
148
|
+
"hennes",
|
|
149
|
+
"hit",
|
|
150
|
+
"hon",
|
|
151
|
+
"honom",
|
|
152
|
+
"hundra",
|
|
153
|
+
"hundraen",
|
|
154
|
+
"hundraett",
|
|
155
|
+
"hur",
|
|
156
|
+
"här",
|
|
157
|
+
"hög",
|
|
158
|
+
"höger",
|
|
159
|
+
"högre",
|
|
160
|
+
"högst",
|
|
161
|
+
"i",
|
|
162
|
+
"ibland",
|
|
163
|
+
"icke",
|
|
164
|
+
"idag",
|
|
165
|
+
"igen",
|
|
166
|
+
"igår",
|
|
167
|
+
"imorgon",
|
|
168
|
+
"in",
|
|
169
|
+
"inför",
|
|
170
|
+
"inga",
|
|
171
|
+
"ingen",
|
|
172
|
+
"ingenting",
|
|
173
|
+
"inget",
|
|
174
|
+
"innan",
|
|
175
|
+
"inne",
|
|
176
|
+
"inom",
|
|
177
|
+
"inte",
|
|
178
|
+
"inuti",
|
|
179
|
+
"ja",
|
|
180
|
+
"jag",
|
|
181
|
+
"jo",
|
|
182
|
+
"ju",
|
|
183
|
+
"just",
|
|
184
|
+
"jämfört",
|
|
185
|
+
"kan",
|
|
186
|
+
"kanske",
|
|
187
|
+
"knappast",
|
|
188
|
+
"kom",
|
|
189
|
+
"komma",
|
|
190
|
+
"kommer",
|
|
191
|
+
"kommit",
|
|
192
|
+
"kr",
|
|
193
|
+
"kunde",
|
|
194
|
+
"kunna",
|
|
195
|
+
"kunnat",
|
|
196
|
+
"kvar",
|
|
197
|
+
"legat",
|
|
198
|
+
"ligga",
|
|
199
|
+
"ligger",
|
|
200
|
+
"lika",
|
|
201
|
+
"likställd",
|
|
202
|
+
"likställda",
|
|
203
|
+
"lilla",
|
|
204
|
+
"lite",
|
|
205
|
+
"liten",
|
|
206
|
+
"litet",
|
|
207
|
+
"länge",
|
|
208
|
+
"längre",
|
|
209
|
+
"längst",
|
|
210
|
+
"lätt",
|
|
211
|
+
"lättare",
|
|
212
|
+
"lättast",
|
|
213
|
+
"långsam",
|
|
214
|
+
"långsammare",
|
|
215
|
+
"långsammast",
|
|
216
|
+
"långsamt",
|
|
217
|
+
"långt",
|
|
218
|
+
"låt",
|
|
219
|
+
"man",
|
|
220
|
+
"med",
|
|
221
|
+
"mej",
|
|
222
|
+
"mellan",
|
|
223
|
+
"men",
|
|
224
|
+
"mer",
|
|
225
|
+
"mera",
|
|
226
|
+
"mest",
|
|
227
|
+
"mig",
|
|
228
|
+
"min",
|
|
229
|
+
"mina",
|
|
230
|
+
"mindre",
|
|
231
|
+
"minst",
|
|
232
|
+
"mitt",
|
|
233
|
+
"mittemot",
|
|
234
|
+
"mot",
|
|
235
|
+
"mycket",
|
|
236
|
+
"många",
|
|
237
|
+
"måste",
|
|
238
|
+
"möjlig",
|
|
239
|
+
"möjligen",
|
|
240
|
+
"möjligt",
|
|
241
|
+
"möjligtvis",
|
|
242
|
+
"ned",
|
|
243
|
+
"nederst",
|
|
244
|
+
"nedersta",
|
|
245
|
+
"nedre",
|
|
246
|
+
"nej",
|
|
247
|
+
"ner",
|
|
248
|
+
"ni",
|
|
249
|
+
"nio",
|
|
250
|
+
"nionde",
|
|
251
|
+
"nittio",
|
|
252
|
+
"nittionde",
|
|
253
|
+
"nitton",
|
|
254
|
+
"nittonde",
|
|
255
|
+
"nog",
|
|
256
|
+
"noll",
|
|
257
|
+
"nr",
|
|
258
|
+
"nu",
|
|
259
|
+
"nummer",
|
|
260
|
+
"när",
|
|
261
|
+
"nästa",
|
|
262
|
+
"någon",
|
|
263
|
+
"någonting",
|
|
264
|
+
"något",
|
|
265
|
+
"några",
|
|
266
|
+
"nån",
|
|
267
|
+
"nånting",
|
|
268
|
+
"nåt",
|
|
269
|
+
"nödvändig",
|
|
270
|
+
"nödvändiga",
|
|
271
|
+
"nödvändigt",
|
|
272
|
+
"nödvändigtvis",
|
|
273
|
+
"och",
|
|
274
|
+
"också",
|
|
275
|
+
"ofta",
|
|
276
|
+
"oftast",
|
|
277
|
+
"olika",
|
|
278
|
+
"olikt",
|
|
279
|
+
"om",
|
|
280
|
+
"oss",
|
|
281
|
+
"på",
|
|
282
|
+
"rakt",
|
|
283
|
+
"redan",
|
|
284
|
+
"rätt",
|
|
285
|
+
"sa",
|
|
286
|
+
"sade",
|
|
287
|
+
"sagt",
|
|
288
|
+
"samma",
|
|
289
|
+
"sedan",
|
|
290
|
+
"senare",
|
|
291
|
+
"senast",
|
|
292
|
+
"sent",
|
|
293
|
+
"sex",
|
|
294
|
+
"sextio",
|
|
295
|
+
"sextionde",
|
|
296
|
+
"sexton",
|
|
297
|
+
"sextonde",
|
|
298
|
+
"sig",
|
|
299
|
+
"sin",
|
|
300
|
+
"sina",
|
|
301
|
+
"sist",
|
|
302
|
+
"sista",
|
|
303
|
+
"siste",
|
|
304
|
+
"sitt",
|
|
305
|
+
"sitta",
|
|
306
|
+
"sju",
|
|
307
|
+
"sjunde",
|
|
308
|
+
"sjuttio",
|
|
309
|
+
"sjuttionde",
|
|
310
|
+
"sjutton",
|
|
311
|
+
"sjuttonde",
|
|
312
|
+
"själv",
|
|
313
|
+
"sjätte",
|
|
314
|
+
"ska",
|
|
315
|
+
"skall",
|
|
316
|
+
"skulle",
|
|
317
|
+
"slutligen",
|
|
318
|
+
"små",
|
|
319
|
+
"smått",
|
|
320
|
+
"snart",
|
|
321
|
+
"som",
|
|
322
|
+
"stor",
|
|
323
|
+
"stora",
|
|
324
|
+
"stort",
|
|
325
|
+
"större",
|
|
326
|
+
"störst",
|
|
327
|
+
"säga",
|
|
328
|
+
"säger",
|
|
329
|
+
"sämre",
|
|
330
|
+
"sämst",
|
|
331
|
+
"så",
|
|
332
|
+
"sådan",
|
|
333
|
+
"sådana",
|
|
334
|
+
"sådant",
|
|
335
|
+
"ta",
|
|
336
|
+
"tack",
|
|
337
|
+
"tar",
|
|
338
|
+
"tidig",
|
|
339
|
+
"tidigare",
|
|
340
|
+
"tidigast",
|
|
341
|
+
"tidigt",
|
|
342
|
+
"till",
|
|
343
|
+
"tills",
|
|
344
|
+
"tillsammans",
|
|
345
|
+
"tio",
|
|
346
|
+
"tionde",
|
|
347
|
+
"tjugo",
|
|
348
|
+
"tjugoen",
|
|
349
|
+
"tjugoett",
|
|
350
|
+
"tjugonde",
|
|
351
|
+
"tjugotre",
|
|
352
|
+
"tjugotvå",
|
|
353
|
+
"tjungo",
|
|
354
|
+
"tolfte",
|
|
355
|
+
"tolv",
|
|
356
|
+
"tre",
|
|
357
|
+
"tredje",
|
|
358
|
+
"trettio",
|
|
359
|
+
"trettionde",
|
|
360
|
+
"tretton",
|
|
361
|
+
"trettonde",
|
|
362
|
+
"två",
|
|
363
|
+
"tvåhundra",
|
|
364
|
+
"under",
|
|
365
|
+
"upp",
|
|
366
|
+
"ur",
|
|
367
|
+
"ursäkt",
|
|
368
|
+
"ut",
|
|
369
|
+
"utan",
|
|
370
|
+
"utanför",
|
|
371
|
+
"ute",
|
|
372
|
+
"va",
|
|
373
|
+
"vad",
|
|
374
|
+
"var",
|
|
375
|
+
"vara",
|
|
376
|
+
"varför",
|
|
377
|
+
"varifrån",
|
|
378
|
+
"varit",
|
|
379
|
+
"varje",
|
|
380
|
+
"varken",
|
|
381
|
+
"vars",
|
|
382
|
+
"varsågod",
|
|
383
|
+
"vart",
|
|
384
|
+
"vem",
|
|
385
|
+
"vems",
|
|
386
|
+
"verkligen",
|
|
387
|
+
"vi",
|
|
388
|
+
"vid",
|
|
389
|
+
"vidare",
|
|
390
|
+
"viktig",
|
|
391
|
+
"viktigare",
|
|
392
|
+
"viktigast",
|
|
393
|
+
"viktigt",
|
|
394
|
+
"vilka",
|
|
395
|
+
"vilkas",
|
|
396
|
+
"vilken",
|
|
397
|
+
"vilket",
|
|
398
|
+
"vill",
|
|
399
|
+
"väl",
|
|
400
|
+
"vänster",
|
|
401
|
+
"vänstra",
|
|
402
|
+
"värre",
|
|
403
|
+
"vår",
|
|
404
|
+
"våra",
|
|
405
|
+
"vårt",
|
|
406
|
+
"än",
|
|
407
|
+
"ännu",
|
|
408
|
+
"är",
|
|
409
|
+
"även",
|
|
410
|
+
"åt",
|
|
411
|
+
"åtminstone",
|
|
412
|
+
"åtta",
|
|
413
|
+
"åttio",
|
|
414
|
+
"åttionde",
|
|
415
|
+
"åttonde",
|
|
416
|
+
"över",
|
|
417
|
+
"övermorgon",
|
|
418
|
+
"överst",
|
|
419
|
+
"övre"
|
|
420
|
+
]
|
|
@@ -0,0 +1,76 @@
|
|
|
1
|
+
[
|
|
2
|
+
"akasema",
|
|
3
|
+
"alikuwa",
|
|
4
|
+
"alisema",
|
|
5
|
+
"baada",
|
|
6
|
+
"basi",
|
|
7
|
+
"bila",
|
|
8
|
+
"cha",
|
|
9
|
+
"chini",
|
|
10
|
+
"hadi",
|
|
11
|
+
"hapo",
|
|
12
|
+
"hata",
|
|
13
|
+
"hivyo",
|
|
14
|
+
"hiyo",
|
|
15
|
+
"huku",
|
|
16
|
+
"huo",
|
|
17
|
+
"ili",
|
|
18
|
+
"ilikuwa",
|
|
19
|
+
"juu",
|
|
20
|
+
"kama",
|
|
21
|
+
"karibu",
|
|
22
|
+
"katika",
|
|
23
|
+
"kila",
|
|
24
|
+
"kima",
|
|
25
|
+
"kisha",
|
|
26
|
+
"kubwa",
|
|
27
|
+
"kutoka",
|
|
28
|
+
"kuwa",
|
|
29
|
+
"kwa",
|
|
30
|
+
"kwamba",
|
|
31
|
+
"kwenda",
|
|
32
|
+
"kwenye",
|
|
33
|
+
"la",
|
|
34
|
+
"lakini",
|
|
35
|
+
"mara",
|
|
36
|
+
"mdogo",
|
|
37
|
+
"mimi",
|
|
38
|
+
"mkubwa",
|
|
39
|
+
"mmoja",
|
|
40
|
+
"moja",
|
|
41
|
+
"muda",
|
|
42
|
+
"mwenye",
|
|
43
|
+
"na",
|
|
44
|
+
"naye",
|
|
45
|
+
"ndani",
|
|
46
|
+
"ng",
|
|
47
|
+
"ni",
|
|
48
|
+
"nini",
|
|
49
|
+
"nonkungu",
|
|
50
|
+
"pamoja",
|
|
51
|
+
"pia",
|
|
52
|
+
"sana",
|
|
53
|
+
"sasa",
|
|
54
|
+
"sauti",
|
|
55
|
+
"tafadhali",
|
|
56
|
+
"tena",
|
|
57
|
+
"tu",
|
|
58
|
+
"vile",
|
|
59
|
+
"wa",
|
|
60
|
+
"wakati",
|
|
61
|
+
"wake",
|
|
62
|
+
"walikuwa",
|
|
63
|
+
"wao",
|
|
64
|
+
"watu",
|
|
65
|
+
"wengine",
|
|
66
|
+
"wote",
|
|
67
|
+
"ya",
|
|
68
|
+
"yake",
|
|
69
|
+
"yangu",
|
|
70
|
+
"yao",
|
|
71
|
+
"yeye",
|
|
72
|
+
"yule",
|
|
73
|
+
"za",
|
|
74
|
+
"zaidi",
|
|
75
|
+
"zake"
|
|
76
|
+
]
|
|
@@ -0,0 +1,129 @@
|
|
|
1
|
+
[
|
|
2
|
+
"அங்கு",
|
|
3
|
+
"அங்கே",
|
|
4
|
+
"அடுத்த",
|
|
5
|
+
"அதனால்",
|
|
6
|
+
"அதன்",
|
|
7
|
+
"அதற்கு",
|
|
8
|
+
"அதிக",
|
|
9
|
+
"அதில்",
|
|
10
|
+
"அது",
|
|
11
|
+
"அதே",
|
|
12
|
+
"அதை",
|
|
13
|
+
"அந்த",
|
|
14
|
+
"அந்தக்",
|
|
15
|
+
"அந்தப்",
|
|
16
|
+
"அன்று",
|
|
17
|
+
"அல்லது",
|
|
18
|
+
"அவன்",
|
|
19
|
+
"அவரது",
|
|
20
|
+
"அவர்",
|
|
21
|
+
"அவர்கள்",
|
|
22
|
+
"அவள்",
|
|
23
|
+
"அவை",
|
|
24
|
+
"ஆகிய",
|
|
25
|
+
"ஆகியோர்",
|
|
26
|
+
"ஆகும்",
|
|
27
|
+
"ஆனால்",
|
|
28
|
+
"இங்கு",
|
|
29
|
+
"இங்கே",
|
|
30
|
+
"இடத்தில்",
|
|
31
|
+
"இடம்",
|
|
32
|
+
"இதனால்",
|
|
33
|
+
"இதனை",
|
|
34
|
+
"இதன்",
|
|
35
|
+
"இதற்கு",
|
|
36
|
+
"இதில்",
|
|
37
|
+
"இது",
|
|
38
|
+
"இதை",
|
|
39
|
+
"இந்த",
|
|
40
|
+
"இந்தக்",
|
|
41
|
+
"இந்தத்",
|
|
42
|
+
"இந்தப்",
|
|
43
|
+
"இன்னும்",
|
|
44
|
+
"இப்போது",
|
|
45
|
+
"இரு",
|
|
46
|
+
"இருக்கும்",
|
|
47
|
+
"இருந்த",
|
|
48
|
+
"இருந்தது",
|
|
49
|
+
"இருந்து",
|
|
50
|
+
"இல்லை",
|
|
51
|
+
"இவர்",
|
|
52
|
+
"இவை",
|
|
53
|
+
"உன்",
|
|
54
|
+
"உள்ள",
|
|
55
|
+
"உள்ளது",
|
|
56
|
+
"உள்ளன",
|
|
57
|
+
"எந்த",
|
|
58
|
+
"என",
|
|
59
|
+
"எனக்",
|
|
60
|
+
"எனக்கு",
|
|
61
|
+
"எனப்படும்",
|
|
62
|
+
"எனவும்",
|
|
63
|
+
"எனவே",
|
|
64
|
+
"எனினும்",
|
|
65
|
+
"எனும்",
|
|
66
|
+
"என்",
|
|
67
|
+
"என்ன",
|
|
68
|
+
"என்னும்",
|
|
69
|
+
"என்பது",
|
|
70
|
+
"என்பதை",
|
|
71
|
+
"என்ற",
|
|
72
|
+
"என்று",
|
|
73
|
+
"என்றும்",
|
|
74
|
+
"எல்லாம்",
|
|
75
|
+
"ஏன்",
|
|
76
|
+
"ஒரு",
|
|
77
|
+
"ஒரே",
|
|
78
|
+
"ஓர்",
|
|
79
|
+
"கொண்ட",
|
|
80
|
+
"கொண்டு",
|
|
81
|
+
"கொள்ள",
|
|
82
|
+
"சற்று",
|
|
83
|
+
"சிறு",
|
|
84
|
+
"சில",
|
|
85
|
+
"சேர்ந்த",
|
|
86
|
+
"தனது",
|
|
87
|
+
"தன்",
|
|
88
|
+
"தவிர",
|
|
89
|
+
"தான்",
|
|
90
|
+
"நான்",
|
|
91
|
+
"நாம்",
|
|
92
|
+
"நீ",
|
|
93
|
+
"பற்றி",
|
|
94
|
+
"பற்றிய",
|
|
95
|
+
"பல",
|
|
96
|
+
"பலரும்",
|
|
97
|
+
"பல்வேறு",
|
|
98
|
+
"பின்",
|
|
99
|
+
"பின்னர்",
|
|
100
|
+
"பிற",
|
|
101
|
+
"பிறகு",
|
|
102
|
+
"பெரும்",
|
|
103
|
+
"பேர்",
|
|
104
|
+
"போது",
|
|
105
|
+
"போன்ற",
|
|
106
|
+
"போல",
|
|
107
|
+
"போல்",
|
|
108
|
+
"மட்டுமே",
|
|
109
|
+
"மட்டும்",
|
|
110
|
+
"மற்ற",
|
|
111
|
+
"மற்றும்",
|
|
112
|
+
"மிக",
|
|
113
|
+
"மிகவும்",
|
|
114
|
+
"மீது",
|
|
115
|
+
"முதல்",
|
|
116
|
+
"முறை",
|
|
117
|
+
"மேலும்",
|
|
118
|
+
"மேல்",
|
|
119
|
+
"யார்",
|
|
120
|
+
"வந்த",
|
|
121
|
+
"வந்து",
|
|
122
|
+
"வரும்",
|
|
123
|
+
"வரை",
|
|
124
|
+
"வரையில்",
|
|
125
|
+
"விட",
|
|
126
|
+
"விட்டு",
|
|
127
|
+
"வேண்டும்",
|
|
128
|
+
"வேறு"
|
|
129
|
+
]
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
[
|
|
2
|
+
"అందరూ",
|
|
3
|
+
"అందుబాటులో",
|
|
4
|
+
"అడగండి",
|
|
5
|
+
"అడగడం",
|
|
6
|
+
"అడ్డంగా",
|
|
7
|
+
"అనుగుణంగా",
|
|
8
|
+
"అనుమతించు",
|
|
9
|
+
"అనుమతిస్తుంది",
|
|
10
|
+
"అయితే",
|
|
11
|
+
"ఇప్పటికే",
|
|
12
|
+
"ఉన్నారు",
|
|
13
|
+
"ఎక్కడైనా",
|
|
14
|
+
"ఎప్పుడు",
|
|
15
|
+
"ఎవరైనా",
|
|
16
|
+
"ఎవరో",
|
|
17
|
+
"ఏ",
|
|
18
|
+
"ఏదైనా",
|
|
19
|
+
"ఏమైనప్పటికి",
|
|
20
|
+
"ఏమైనప్పటికి",
|
|
21
|
+
"ఒక",
|
|
22
|
+
"ఒక",
|
|
23
|
+
"ఒకరు",
|
|
24
|
+
"కనిపిస్తాయి",
|
|
25
|
+
"కాదు",
|
|
26
|
+
"కాదు",
|
|
27
|
+
"కూడా",
|
|
28
|
+
"గా",
|
|
29
|
+
"గురించి",
|
|
30
|
+
"చుట్టూ",
|
|
31
|
+
"చేయగలిగింది",
|
|
32
|
+
"తగిన",
|
|
33
|
+
"తర్వాత",
|
|
34
|
+
"తర్వాత",
|
|
35
|
+
"దాదాపు",
|
|
36
|
+
"దూరంగా",
|
|
37
|
+
"నిజంగా",
|
|
38
|
+
"పై",
|
|
39
|
+
"ప్రకారం",
|
|
40
|
+
"ప్రక్కన",
|
|
41
|
+
"మధ్య",
|
|
42
|
+
"మధ్య",
|
|
43
|
+
"మరియు",
|
|
44
|
+
"మరొక",
|
|
45
|
+
"మళ్ళీ",
|
|
46
|
+
"మాత్రమే",
|
|
47
|
+
"మెచ్చుకో",
|
|
48
|
+
"వద్ద",
|
|
49
|
+
"వద్ద",
|
|
50
|
+
"వెంట",
|
|
51
|
+
"వేరుగా",
|
|
52
|
+
"వ్యతిరేకంగా",
|
|
53
|
+
"సంబంధం"
|
|
54
|
+
]
|