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.
Files changed (265) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +8 -0
  3. data/.rspec +3 -0
  4. data/.rubocop.yaml +534 -0
  5. data/Gemfile +9 -0
  6. data/Gemfile.lock +157 -0
  7. data/README.md +421 -0
  8. data/Rakefile +25 -0
  9. data/Steepfile +47 -0
  10. data/examples/async_patterns.rb +340 -0
  11. data/ext/kreuzberg_rb/extconf.rb +35 -0
  12. data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
  13. data/ext/kreuzberg_rb/native/README.md +425 -0
  14. data/ext/kreuzberg_rb/native/build.rs +17 -0
  15. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
  16. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
  17. data/ext/kreuzberg_rb/native/include/strings.h +20 -0
  18. data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
  19. data/ext/kreuzberg_rb/native/src/lib.rs +2939 -0
  20. data/extconf.rb +28 -0
  21. data/kreuzberg.gemspec +105 -0
  22. data/lib/kreuzberg/api_proxy.rb +142 -0
  23. data/lib/kreuzberg/cache_api.rb +45 -0
  24. data/lib/kreuzberg/cli.rb +55 -0
  25. data/lib/kreuzberg/cli_proxy.rb +127 -0
  26. data/lib/kreuzberg/config.rb +684 -0
  27. data/lib/kreuzberg/errors.rb +50 -0
  28. data/lib/kreuzberg/extraction_api.rb +84 -0
  29. data/lib/kreuzberg/mcp_proxy.rb +186 -0
  30. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
  31. data/lib/kreuzberg/post_processor_protocol.rb +86 -0
  32. data/lib/kreuzberg/result.rb +216 -0
  33. data/lib/kreuzberg/setup_lib_path.rb +79 -0
  34. data/lib/kreuzberg/validator_protocol.rb +89 -0
  35. data/lib/kreuzberg/version.rb +5 -0
  36. data/lib/kreuzberg.rb +82 -0
  37. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  38. data/sig/kreuzberg/internal.rbs +184 -0
  39. data/sig/kreuzberg.rbs +468 -0
  40. data/spec/binding/cache_spec.rb +227 -0
  41. data/spec/binding/cli_proxy_spec.rb +87 -0
  42. data/spec/binding/cli_spec.rb +54 -0
  43. data/spec/binding/config_spec.rb +345 -0
  44. data/spec/binding/config_validation_spec.rb +283 -0
  45. data/spec/binding/error_handling_spec.rb +213 -0
  46. data/spec/binding/errors_spec.rb +66 -0
  47. data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
  48. data/spec/binding/plugins/postprocessor_spec.rb +269 -0
  49. data/spec/binding/plugins/validator_spec.rb +274 -0
  50. data/spec/examples.txt +104 -0
  51. data/spec/fixtures/config.toml +39 -0
  52. data/spec/fixtures/config.yaml +42 -0
  53. data/spec/fixtures/invalid_config.toml +4 -0
  54. data/spec/smoke/package_spec.rb +178 -0
  55. data/spec/spec_helper.rb +42 -0
  56. data/vendor/kreuzberg/Cargo.toml +134 -0
  57. data/vendor/kreuzberg/README.md +175 -0
  58. data/vendor/kreuzberg/build.rs +460 -0
  59. data/vendor/kreuzberg/src/api/error.rs +81 -0
  60. data/vendor/kreuzberg/src/api/handlers.rs +199 -0
  61. data/vendor/kreuzberg/src/api/mod.rs +79 -0
  62. data/vendor/kreuzberg/src/api/server.rs +353 -0
  63. data/vendor/kreuzberg/src/api/types.rs +170 -0
  64. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  65. data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
  66. data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
  67. data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
  68. data/vendor/kreuzberg/src/core/config.rs +1032 -0
  69. data/vendor/kreuzberg/src/core/extractor.rs +903 -0
  70. data/vendor/kreuzberg/src/core/io.rs +327 -0
  71. data/vendor/kreuzberg/src/core/mime.rs +615 -0
  72. data/vendor/kreuzberg/src/core/mod.rs +42 -0
  73. data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
  74. data/vendor/kreuzberg/src/embeddings.rs +323 -0
  75. data/vendor/kreuzberg/src/error.rs +431 -0
  76. data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
  77. data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
  78. data/vendor/kreuzberg/src/extraction/email.rs +854 -0
  79. data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
  80. data/vendor/kreuzberg/src/extraction/html.rs +553 -0
  81. data/vendor/kreuzberg/src/extraction/image.rs +368 -0
  82. data/vendor/kreuzberg/src/extraction/libreoffice.rs +564 -0
  83. data/vendor/kreuzberg/src/extraction/mod.rs +77 -0
  84. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
  85. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
  86. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
  87. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +128 -0
  88. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  89. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  90. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  91. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  92. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  93. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  94. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
  95. data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
  96. data/vendor/kreuzberg/src/extraction/table.rs +328 -0
  97. data/vendor/kreuzberg/src/extraction/text.rs +269 -0
  98. data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
  99. data/vendor/kreuzberg/src/extractors/archive.rs +425 -0
  100. data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
  101. data/vendor/kreuzberg/src/extractors/email.rs +129 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
  103. data/vendor/kreuzberg/src/extractors/html.rs +410 -0
  104. data/vendor/kreuzberg/src/extractors/image.rs +195 -0
  105. data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
  106. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  107. data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
  108. data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
  109. data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
  110. data/vendor/kreuzberg/src/extractors/text.rs +242 -0
  111. data/vendor/kreuzberg/src/extractors/xml.rs +128 -0
  112. data/vendor/kreuzberg/src/image/dpi.rs +164 -0
  113. data/vendor/kreuzberg/src/image/mod.rs +6 -0
  114. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
  115. data/vendor/kreuzberg/src/image/resize.rs +89 -0
  116. data/vendor/kreuzberg/src/keywords/config.rs +154 -0
  117. data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
  118. data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
  119. data/vendor/kreuzberg/src/keywords/rake.rs +294 -0
  120. data/vendor/kreuzberg/src/keywords/types.rs +68 -0
  121. data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
  122. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
  123. data/vendor/kreuzberg/src/lib.rs +102 -0
  124. data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
  125. data/vendor/kreuzberg/src/mcp/server.rs +1966 -0
  126. data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
  127. data/vendor/kreuzberg/src/ocr/error.rs +37 -0
  128. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
  129. data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
  130. data/vendor/kreuzberg/src/ocr/processor.rs +847 -0
  131. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
  132. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
  133. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
  134. data/vendor/kreuzberg/src/ocr/types.rs +393 -0
  135. data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
  136. data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
  137. data/vendor/kreuzberg/src/pdf/error.rs +122 -0
  138. data/vendor/kreuzberg/src/pdf/images.rs +139 -0
  139. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
  140. data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
  141. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
  142. data/vendor/kreuzberg/src/pdf/table.rs +420 -0
  143. data/vendor/kreuzberg/src/pdf/text.rs +161 -0
  144. data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
  145. data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
  146. data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
  147. data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
  148. data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
  149. data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
  150. data/vendor/kreuzberg/src/plugins/validator.rs +955 -0
  151. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
  152. data/vendor/kreuzberg/src/text/mod.rs +19 -0
  153. data/vendor/kreuzberg/src/text/quality.rs +697 -0
  154. data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
  155. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
  156. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
  157. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
  158. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
  159. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
  160. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
  161. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
  162. data/vendor/kreuzberg/src/types.rs +873 -0
  163. data/vendor/kreuzberg/src/utils/mod.rs +17 -0
  164. data/vendor/kreuzberg/src/utils/quality.rs +959 -0
  165. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
  166. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
  167. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
  168. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
  169. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
  170. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
  171. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
  172. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
  173. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
  174. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
  175. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
  176. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
  177. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
  178. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
  179. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
  180. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
  181. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
  182. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
  183. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
  184. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
  185. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
  186. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
  187. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
  188. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
  189. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
  190. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
  191. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
  192. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
  193. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
  194. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
  195. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
  196. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
  197. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
  198. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
  199. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
  200. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
  201. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
  202. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
  203. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
  204. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
  205. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
  206. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
  207. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
  208. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
  209. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
  210. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
  211. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
  212. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
  213. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
  214. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
  215. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
  216. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
  217. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
  218. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
  219. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
  220. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
  221. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
  222. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
  223. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
  224. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
  225. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
  226. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
  227. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
  228. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
  229. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
  230. data/vendor/kreuzberg/tests/api_tests.rs +966 -0
  231. data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
  232. data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
  233. data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
  234. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  235. data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
  236. data/vendor/kreuzberg/tests/config_features.rs +580 -0
  237. data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
  238. data/vendor/kreuzberg/tests/core_integration.rs +493 -0
  239. data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
  240. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
  241. data/vendor/kreuzberg/tests/email_integration.rs +325 -0
  242. data/vendor/kreuzberg/tests/error_handling.rs +393 -0
  243. data/vendor/kreuzberg/tests/format_integration.rs +159 -0
  244. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
  245. data/vendor/kreuzberg/tests/image_integration.rs +253 -0
  246. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
  247. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
  248. data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
  249. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
  250. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
  251. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
  252. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
  253. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  254. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
  255. data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
  256. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
  257. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -0
  258. data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
  259. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
  260. data/vendor/kreuzberg/tests/registry_integration_tests.rs +607 -0
  261. data/vendor/kreuzberg/tests/security_validation.rs +404 -0
  262. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
  263. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
  264. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
  265. metadata +471 -0
@@ -0,0 +1,622 @@
1
+ [
2
+ "a",
3
+ "ab",
4
+ "aber",
5
+ "ach",
6
+ "acht",
7
+ "achte",
8
+ "achten",
9
+ "achter",
10
+ "achtes",
11
+ "ag",
12
+ "alle",
13
+ "allein",
14
+ "allem",
15
+ "allen",
16
+ "aller",
17
+ "allerdings",
18
+ "alles",
19
+ "allgemeinen",
20
+ "als",
21
+ "also",
22
+ "am",
23
+ "an",
24
+ "ander",
25
+ "andere",
26
+ "anderem",
27
+ "anderen",
28
+ "anderer",
29
+ "anderes",
30
+ "anderm",
31
+ "andern",
32
+ "anderr",
33
+ "anders",
34
+ "au",
35
+ "auch",
36
+ "auf",
37
+ "aus",
38
+ "ausser",
39
+ "ausserdem",
40
+ "außer",
41
+ "außerdem",
42
+ "b",
43
+ "bald",
44
+ "bei",
45
+ "beide",
46
+ "beiden",
47
+ "beim",
48
+ "beispiel",
49
+ "bekannt",
50
+ "bereits",
51
+ "besonders",
52
+ "besser",
53
+ "besten",
54
+ "bin",
55
+ "bis",
56
+ "bisher",
57
+ "bist",
58
+ "c",
59
+ "d",
60
+ "d.h",
61
+ "da",
62
+ "dabei",
63
+ "dadurch",
64
+ "dafür",
65
+ "dagegen",
66
+ "daher",
67
+ "dahin",
68
+ "dahinter",
69
+ "damals",
70
+ "damit",
71
+ "danach",
72
+ "daneben",
73
+ "dank",
74
+ "dann",
75
+ "daran",
76
+ "darauf",
77
+ "daraus",
78
+ "darf",
79
+ "darfst",
80
+ "darin",
81
+ "darum",
82
+ "darunter",
83
+ "darüber",
84
+ "das",
85
+ "dasein",
86
+ "daselbst",
87
+ "dass",
88
+ "dasselbe",
89
+ "davon",
90
+ "davor",
91
+ "dazu",
92
+ "dazwischen",
93
+ "daß",
94
+ "dein",
95
+ "deine",
96
+ "deinem",
97
+ "deinen",
98
+ "deiner",
99
+ "deines",
100
+ "dem",
101
+ "dementsprechend",
102
+ "demgegenüber",
103
+ "demgemäss",
104
+ "demgemäß",
105
+ "demselben",
106
+ "demzufolge",
107
+ "den",
108
+ "denen",
109
+ "denn",
110
+ "denselben",
111
+ "der",
112
+ "deren",
113
+ "derer",
114
+ "derjenige",
115
+ "derjenigen",
116
+ "dermassen",
117
+ "dermaßen",
118
+ "derselbe",
119
+ "derselben",
120
+ "des",
121
+ "deshalb",
122
+ "desselben",
123
+ "dessen",
124
+ "deswegen",
125
+ "dich",
126
+ "die",
127
+ "diejenige",
128
+ "diejenigen",
129
+ "dies",
130
+ "diese",
131
+ "dieselbe",
132
+ "dieselben",
133
+ "diesem",
134
+ "diesen",
135
+ "dieser",
136
+ "dieses",
137
+ "dir",
138
+ "doch",
139
+ "dort",
140
+ "drei",
141
+ "drin",
142
+ "dritte",
143
+ "dritten",
144
+ "dritter",
145
+ "drittes",
146
+ "du",
147
+ "durch",
148
+ "durchaus",
149
+ "durfte",
150
+ "durften",
151
+ "dürfen",
152
+ "dürft",
153
+ "e",
154
+ "eben",
155
+ "ebenso",
156
+ "ehrlich",
157
+ "ei",
158
+ "ei,",
159
+ "eigen",
160
+ "eigene",
161
+ "eigenen",
162
+ "eigener",
163
+ "eigenes",
164
+ "ein",
165
+ "einander",
166
+ "eine",
167
+ "einem",
168
+ "einen",
169
+ "einer",
170
+ "eines",
171
+ "einig",
172
+ "einige",
173
+ "einigem",
174
+ "einigen",
175
+ "einiger",
176
+ "einiges",
177
+ "einmal",
178
+ "eins",
179
+ "elf",
180
+ "en",
181
+ "ende",
182
+ "endlich",
183
+ "entweder",
184
+ "er",
185
+ "ernst",
186
+ "erst",
187
+ "erste",
188
+ "ersten",
189
+ "erster",
190
+ "erstes",
191
+ "es",
192
+ "etwa",
193
+ "etwas",
194
+ "euch",
195
+ "euer",
196
+ "eure",
197
+ "eurem",
198
+ "euren",
199
+ "eurer",
200
+ "eures",
201
+ "f",
202
+ "folgende",
203
+ "früher",
204
+ "fünf",
205
+ "fünfte",
206
+ "fünften",
207
+ "fünfter",
208
+ "fünftes",
209
+ "für",
210
+ "g",
211
+ "gab",
212
+ "ganz",
213
+ "ganze",
214
+ "ganzen",
215
+ "ganzer",
216
+ "ganzes",
217
+ "gar",
218
+ "gedurft",
219
+ "gegen",
220
+ "gegenüber",
221
+ "gehabt",
222
+ "gehen",
223
+ "geht",
224
+ "gekannt",
225
+ "gekonnt",
226
+ "gemacht",
227
+ "gemocht",
228
+ "gemusst",
229
+ "genug",
230
+ "gerade",
231
+ "gern",
232
+ "gesagt",
233
+ "geschweige",
234
+ "gewesen",
235
+ "gewollt",
236
+ "geworden",
237
+ "gibt",
238
+ "ging",
239
+ "gleich",
240
+ "gott",
241
+ "gross",
242
+ "grosse",
243
+ "grossen",
244
+ "grosser",
245
+ "grosses",
246
+ "groß",
247
+ "große",
248
+ "großen",
249
+ "großer",
250
+ "großes",
251
+ "gut",
252
+ "gute",
253
+ "guter",
254
+ "gutes",
255
+ "h",
256
+ "hab",
257
+ "habe",
258
+ "haben",
259
+ "habt",
260
+ "hast",
261
+ "hat",
262
+ "hatte",
263
+ "hatten",
264
+ "hattest",
265
+ "hattet",
266
+ "heisst",
267
+ "her",
268
+ "heute",
269
+ "hier",
270
+ "hin",
271
+ "hinter",
272
+ "hoch",
273
+ "hätte",
274
+ "hätten",
275
+ "i",
276
+ "ich",
277
+ "ihm",
278
+ "ihn",
279
+ "ihnen",
280
+ "ihr",
281
+ "ihre",
282
+ "ihrem",
283
+ "ihren",
284
+ "ihrer",
285
+ "ihres",
286
+ "im",
287
+ "immer",
288
+ "in",
289
+ "indem",
290
+ "infolgedessen",
291
+ "ins",
292
+ "irgend",
293
+ "ist",
294
+ "j",
295
+ "ja",
296
+ "jahr",
297
+ "jahre",
298
+ "jahren",
299
+ "je",
300
+ "jede",
301
+ "jedem",
302
+ "jeden",
303
+ "jeder",
304
+ "jedermann",
305
+ "jedermanns",
306
+ "jedes",
307
+ "jedoch",
308
+ "jemand",
309
+ "jemandem",
310
+ "jemanden",
311
+ "jene",
312
+ "jenem",
313
+ "jenen",
314
+ "jener",
315
+ "jenes",
316
+ "jetzt",
317
+ "k",
318
+ "kam",
319
+ "kann",
320
+ "kannst",
321
+ "kaum",
322
+ "kein",
323
+ "keine",
324
+ "keinem",
325
+ "keinen",
326
+ "keiner",
327
+ "keines",
328
+ "kleine",
329
+ "kleinen",
330
+ "kleiner",
331
+ "kleines",
332
+ "kommen",
333
+ "kommt",
334
+ "konnte",
335
+ "konnten",
336
+ "kurz",
337
+ "können",
338
+ "könnt",
339
+ "könnte",
340
+ "l",
341
+ "lang",
342
+ "lange",
343
+ "leicht",
344
+ "leide",
345
+ "lieber",
346
+ "los",
347
+ "m",
348
+ "machen",
349
+ "macht",
350
+ "machte",
351
+ "mag",
352
+ "magst",
353
+ "mahn",
354
+ "mal",
355
+ "man",
356
+ "manche",
357
+ "manchem",
358
+ "manchen",
359
+ "mancher",
360
+ "manches",
361
+ "mann",
362
+ "mehr",
363
+ "mein",
364
+ "meine",
365
+ "meinem",
366
+ "meinen",
367
+ "meiner",
368
+ "meines",
369
+ "mensch",
370
+ "menschen",
371
+ "mich",
372
+ "mir",
373
+ "mit",
374
+ "mittel",
375
+ "mochte",
376
+ "mochten",
377
+ "morgen",
378
+ "muss",
379
+ "musst",
380
+ "musste",
381
+ "mussten",
382
+ "muß",
383
+ "mußt",
384
+ "möchte",
385
+ "mögen",
386
+ "möglich",
387
+ "mögt",
388
+ "müssen",
389
+ "müsst",
390
+ "müßt",
391
+ "n",
392
+ "na",
393
+ "nach",
394
+ "nachdem",
395
+ "nahm",
396
+ "natürlich",
397
+ "neben",
398
+ "nein",
399
+ "neue",
400
+ "neuen",
401
+ "neun",
402
+ "neunte",
403
+ "neunten",
404
+ "neunter",
405
+ "neuntes",
406
+ "nicht",
407
+ "nichts",
408
+ "nie",
409
+ "niemand",
410
+ "niemandem",
411
+ "niemanden",
412
+ "noch",
413
+ "nun",
414
+ "nur",
415
+ "o",
416
+ "ob",
417
+ "oben",
418
+ "oder",
419
+ "offen",
420
+ "oft",
421
+ "ohne",
422
+ "ordnung",
423
+ "p",
424
+ "q",
425
+ "r",
426
+ "recht",
427
+ "rechte",
428
+ "rechten",
429
+ "rechter",
430
+ "rechtes",
431
+ "richtig",
432
+ "rund",
433
+ "s",
434
+ "sa",
435
+ "sache",
436
+ "sagt",
437
+ "sagte",
438
+ "sah",
439
+ "satt",
440
+ "schlecht",
441
+ "schluss",
442
+ "schon",
443
+ "sechs",
444
+ "sechste",
445
+ "sechsten",
446
+ "sechster",
447
+ "sechstes",
448
+ "sehr",
449
+ "sei",
450
+ "seid",
451
+ "seien",
452
+ "sein",
453
+ "seine",
454
+ "seinem",
455
+ "seinen",
456
+ "seiner",
457
+ "seines",
458
+ "seit",
459
+ "seitdem",
460
+ "selbst",
461
+ "sich",
462
+ "sie",
463
+ "sieben",
464
+ "siebente",
465
+ "siebenten",
466
+ "siebenter",
467
+ "siebentes",
468
+ "sind",
469
+ "so",
470
+ "solang",
471
+ "solche",
472
+ "solchem",
473
+ "solchen",
474
+ "solcher",
475
+ "solches",
476
+ "soll",
477
+ "sollen",
478
+ "sollst",
479
+ "sollt",
480
+ "sollte",
481
+ "sollten",
482
+ "sondern",
483
+ "sonst",
484
+ "soweit",
485
+ "sowie",
486
+ "später",
487
+ "startseite",
488
+ "statt",
489
+ "steht",
490
+ "suche",
491
+ "t",
492
+ "tag",
493
+ "tage",
494
+ "tagen",
495
+ "tat",
496
+ "teil",
497
+ "tel",
498
+ "tritt",
499
+ "trotzdem",
500
+ "tun",
501
+ "u",
502
+ "uhr",
503
+ "um",
504
+ "und",
505
+ "uns",
506
+ "unse",
507
+ "unsem",
508
+ "unsen",
509
+ "unser",
510
+ "unsere",
511
+ "unserer",
512
+ "unses",
513
+ "unter",
514
+ "v",
515
+ "vergangenen",
516
+ "viel",
517
+ "viele",
518
+ "vielem",
519
+ "vielen",
520
+ "vielleicht",
521
+ "vier",
522
+ "vierte",
523
+ "vierten",
524
+ "vierter",
525
+ "viertes",
526
+ "vom",
527
+ "von",
528
+ "vor",
529
+ "w",
530
+ "wahr",
531
+ "wann",
532
+ "war",
533
+ "waren",
534
+ "warst",
535
+ "wart",
536
+ "warum",
537
+ "was",
538
+ "weg",
539
+ "wegen",
540
+ "weil",
541
+ "weit",
542
+ "weiter",
543
+ "weitere",
544
+ "weiteren",
545
+ "weiteres",
546
+ "welche",
547
+ "welchem",
548
+ "welchen",
549
+ "welcher",
550
+ "welches",
551
+ "wem",
552
+ "wen",
553
+ "wenig",
554
+ "wenige",
555
+ "weniger",
556
+ "weniges",
557
+ "wenigstens",
558
+ "wenn",
559
+ "wer",
560
+ "werde",
561
+ "werden",
562
+ "werdet",
563
+ "weshalb",
564
+ "wessen",
565
+ "wie",
566
+ "wieder",
567
+ "wieso",
568
+ "will",
569
+ "willst",
570
+ "wir",
571
+ "wird",
572
+ "wirklich",
573
+ "wirst",
574
+ "wissen",
575
+ "wo",
576
+ "woher",
577
+ "wohin",
578
+ "wohl",
579
+ "wollen",
580
+ "wollt",
581
+ "wollte",
582
+ "wollten",
583
+ "worden",
584
+ "wurde",
585
+ "wurden",
586
+ "während",
587
+ "währenddem",
588
+ "währenddessen",
589
+ "wäre",
590
+ "würde",
591
+ "würden",
592
+ "x",
593
+ "y",
594
+ "z",
595
+ "z.b",
596
+ "zehn",
597
+ "zehnte",
598
+ "zehnten",
599
+ "zehnter",
600
+ "zehntes",
601
+ "zeit",
602
+ "zu",
603
+ "zuerst",
604
+ "zugleich",
605
+ "zum",
606
+ "zunächst",
607
+ "zur",
608
+ "zurück",
609
+ "zusammen",
610
+ "zwanzig",
611
+ "zwar",
612
+ "zwei",
613
+ "zweite",
614
+ "zweiten",
615
+ "zweiter",
616
+ "zweites",
617
+ "zwischen",
618
+ "zwölf",
619
+ "über",
620
+ "überhaupt",
621
+ "übrigens"
622
+ ]