stemmers 0.0.1

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 (74) hide show
  1. checksums.yaml +7 -0
  2. data/.rubocop.yml +13 -0
  3. data/CHANGELOG.md +5 -0
  4. data/CODE_OF_CONDUCT.md +132 -0
  5. data/Cargo.lock +547 -0
  6. data/Cargo.toml +7 -0
  7. data/LICENSE.txt +21 -0
  8. data/README.md +113 -0
  9. data/Rakefile +23 -0
  10. data/ext/stemmers/Cargo.toml +16 -0
  11. data/ext/stemmers/extconf.rb +6 -0
  12. data/ext/stemmers/src/lib.rs +105 -0
  13. data/lib/stemmers/stopwords/af.json +53 -0
  14. data/lib/stemmers/stopwords/ar.json +482 -0
  15. data/lib/stemmers/stopwords/bg.json +261 -0
  16. data/lib/stemmers/stopwords/bn.json +400 -0
  17. data/lib/stemmers/stopwords/br.json +1205 -0
  18. data/lib/stemmers/stopwords/ca.json +280 -0
  19. data/lib/stemmers/stopwords/cs.json +425 -0
  20. data/lib/stemmers/stopwords/da.json +172 -0
  21. data/lib/stemmers/stopwords/de.json +622 -0
  22. data/lib/stemmers/stopwords/el.json +849 -0
  23. data/lib/stemmers/stopwords/en.json +1300 -0
  24. data/lib/stemmers/stopwords/eo.json +175 -0
  25. data/lib/stemmers/stopwords/es.json +734 -0
  26. data/lib/stemmers/stopwords/et.json +37 -0
  27. data/lib/stemmers/stopwords/eu.json +100 -0
  28. data/lib/stemmers/stopwords/fa.json +801 -0
  29. data/lib/stemmers/stopwords/fi.json +849 -0
  30. data/lib/stemmers/stopwords/fr.json +693 -0
  31. data/lib/stemmers/stopwords/ga.json +111 -0
  32. data/lib/stemmers/stopwords/gl.json +162 -0
  33. data/lib/stemmers/stopwords/gu.json +226 -0
  34. data/lib/stemmers/stopwords/ha.json +41 -0
  35. data/lib/stemmers/stopwords/he.json +196 -0
  36. data/lib/stemmers/stopwords/hi.json +227 -0
  37. data/lib/stemmers/stopwords/hr.json +181 -0
  38. data/lib/stemmers/stopwords/hu.json +791 -0
  39. data/lib/stemmers/stopwords/hy.json +47 -0
  40. data/lib/stemmers/stopwords/id.json +760 -0
  41. data/lib/stemmers/stopwords/it.json +634 -0
  42. data/lib/stemmers/stopwords/ja.json +136 -0
  43. data/lib/stemmers/stopwords/ko.json +681 -0
  44. data/lib/stemmers/stopwords/ku.json +64 -0
  45. data/lib/stemmers/stopwords/la.json +51 -0
  46. data/lib/stemmers/stopwords/lt.json +476 -0
  47. data/lib/stemmers/stopwords/lv.json +163 -0
  48. data/lib/stemmers/stopwords/mr.json +101 -0
  49. data/lib/stemmers/stopwords/ms.json +477 -0
  50. data/lib/stemmers/stopwords/nl.json +415 -0
  51. data/lib/stemmers/stopwords/no.json +223 -0
  52. data/lib/stemmers/stopwords/pl.json +331 -0
  53. data/lib/stemmers/stopwords/pt.json +562 -0
  54. data/lib/stemmers/stopwords/ro.json +436 -0
  55. data/lib/stemmers/stopwords/ru.json +561 -0
  56. data/lib/stemmers/stopwords/sk.json +420 -0
  57. data/lib/stemmers/stopwords/sl.json +448 -0
  58. data/lib/stemmers/stopwords/so.json +32 -0
  59. data/lib/stemmers/stopwords/st.json +33 -0
  60. data/lib/stemmers/stopwords/sv.json +420 -0
  61. data/lib/stemmers/stopwords/sw.json +76 -0
  62. data/lib/stemmers/stopwords/th.json +118 -0
  63. data/lib/stemmers/stopwords/tl.json +149 -0
  64. data/lib/stemmers/stopwords/tr.json +506 -0
  65. data/lib/stemmers/stopwords/uk.json +75 -0
  66. data/lib/stemmers/stopwords/ur.json +519 -0
  67. data/lib/stemmers/stopwords/vi.json +647 -0
  68. data/lib/stemmers/stopwords/yo.json +62 -0
  69. data/lib/stemmers/stopwords/zh.json +796 -0
  70. data/lib/stemmers/stopwords/zu.json +31 -0
  71. data/lib/stemmers/version.rb +5 -0
  72. data/lib/stemmers.rb +91 -0
  73. data/sig/stemmers.rbs +4 -0
  74. metadata +131 -0
@@ -0,0 +1,37 @@
1
+ [
2
+ "aga",
3
+ "ei",
4
+ "et",
5
+ "ja",
6
+ "jah",
7
+ "kas",
8
+ "kui",
9
+ "kõik",
10
+ "ma",
11
+ "me",
12
+ "mida",
13
+ "midagi",
14
+ "mind",
15
+ "minu",
16
+ "mis",
17
+ "mu",
18
+ "mul",
19
+ "mulle",
20
+ "nad",
21
+ "nii",
22
+ "oled",
23
+ "olen",
24
+ "oli",
25
+ "oma",
26
+ "on",
27
+ "pole",
28
+ "sa",
29
+ "seda",
30
+ "see",
31
+ "selle",
32
+ "siin",
33
+ "siis",
34
+ "ta",
35
+ "te",
36
+ "ära"
37
+ ]
@@ -0,0 +1,100 @@
1
+ [
2
+ "al",
3
+ "anitz",
4
+ "arabera",
5
+ "asko",
6
+ "baina",
7
+ "bat",
8
+ "batean",
9
+ "batek",
10
+ "bati",
11
+ "batzuei",
12
+ "batzuek",
13
+ "batzuetan",
14
+ "batzuk",
15
+ "bera",
16
+ "beraiek",
17
+ "berau",
18
+ "berauek",
19
+ "bere",
20
+ "berori",
21
+ "beroriek",
22
+ "beste",
23
+ "bezala",
24
+ "da",
25
+ "dago",
26
+ "dira",
27
+ "ditu",
28
+ "du",
29
+ "dute",
30
+ "edo",
31
+ "egin",
32
+ "ere",
33
+ "eta",
34
+ "eurak",
35
+ "ez",
36
+ "gainera",
37
+ "gu",
38
+ "gutxi",
39
+ "guzti",
40
+ "haiei",
41
+ "haiek",
42
+ "haietan",
43
+ "hainbeste",
44
+ "hala",
45
+ "han",
46
+ "handik",
47
+ "hango",
48
+ "hara",
49
+ "hari",
50
+ "hark",
51
+ "hartan",
52
+ "hau",
53
+ "hauei",
54
+ "hauek",
55
+ "hauetan",
56
+ "hemen",
57
+ "hemendik",
58
+ "hemengo",
59
+ "hi",
60
+ "hona",
61
+ "honek",
62
+ "honela",
63
+ "honetan",
64
+ "honi",
65
+ "hor",
66
+ "hori",
67
+ "horiei",
68
+ "horiek",
69
+ "horietan",
70
+ "horko",
71
+ "horra",
72
+ "horrek",
73
+ "horrela",
74
+ "horretan",
75
+ "horri",
76
+ "hortik",
77
+ "hura",
78
+ "izan",
79
+ "ni",
80
+ "noiz",
81
+ "nola",
82
+ "non",
83
+ "nondik",
84
+ "nongo",
85
+ "nor",
86
+ "nora",
87
+ "ze",
88
+ "zein",
89
+ "zen",
90
+ "zenbait",
91
+ "zenbat",
92
+ "zer",
93
+ "zergatik",
94
+ "ziren",
95
+ "zituen",
96
+ "zu",
97
+ "zuek",
98
+ "zuen",
99
+ "zuten"
100
+ ]