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.
- checksums.yaml +7 -0
- data/.rubocop.yml +13 -0
- data/CHANGELOG.md +5 -0
- data/CODE_OF_CONDUCT.md +132 -0
- data/Cargo.lock +547 -0
- data/Cargo.toml +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +113 -0
- data/Rakefile +23 -0
- data/ext/stemmers/Cargo.toml +16 -0
- data/ext/stemmers/extconf.rb +6 -0
- data/ext/stemmers/src/lib.rs +105 -0
- data/lib/stemmers/stopwords/af.json +53 -0
- data/lib/stemmers/stopwords/ar.json +482 -0
- data/lib/stemmers/stopwords/bg.json +261 -0
- data/lib/stemmers/stopwords/bn.json +400 -0
- data/lib/stemmers/stopwords/br.json +1205 -0
- data/lib/stemmers/stopwords/ca.json +280 -0
- data/lib/stemmers/stopwords/cs.json +425 -0
- data/lib/stemmers/stopwords/da.json +172 -0
- data/lib/stemmers/stopwords/de.json +622 -0
- data/lib/stemmers/stopwords/el.json +849 -0
- data/lib/stemmers/stopwords/en.json +1300 -0
- data/lib/stemmers/stopwords/eo.json +175 -0
- data/lib/stemmers/stopwords/es.json +734 -0
- data/lib/stemmers/stopwords/et.json +37 -0
- data/lib/stemmers/stopwords/eu.json +100 -0
- data/lib/stemmers/stopwords/fa.json +801 -0
- data/lib/stemmers/stopwords/fi.json +849 -0
- data/lib/stemmers/stopwords/fr.json +693 -0
- data/lib/stemmers/stopwords/ga.json +111 -0
- data/lib/stemmers/stopwords/gl.json +162 -0
- data/lib/stemmers/stopwords/gu.json +226 -0
- data/lib/stemmers/stopwords/ha.json +41 -0
- data/lib/stemmers/stopwords/he.json +196 -0
- data/lib/stemmers/stopwords/hi.json +227 -0
- data/lib/stemmers/stopwords/hr.json +181 -0
- data/lib/stemmers/stopwords/hu.json +791 -0
- data/lib/stemmers/stopwords/hy.json +47 -0
- data/lib/stemmers/stopwords/id.json +760 -0
- data/lib/stemmers/stopwords/it.json +634 -0
- data/lib/stemmers/stopwords/ja.json +136 -0
- data/lib/stemmers/stopwords/ko.json +681 -0
- data/lib/stemmers/stopwords/ku.json +64 -0
- data/lib/stemmers/stopwords/la.json +51 -0
- data/lib/stemmers/stopwords/lt.json +476 -0
- data/lib/stemmers/stopwords/lv.json +163 -0
- data/lib/stemmers/stopwords/mr.json +101 -0
- data/lib/stemmers/stopwords/ms.json +477 -0
- data/lib/stemmers/stopwords/nl.json +415 -0
- data/lib/stemmers/stopwords/no.json +223 -0
- data/lib/stemmers/stopwords/pl.json +331 -0
- data/lib/stemmers/stopwords/pt.json +562 -0
- data/lib/stemmers/stopwords/ro.json +436 -0
- data/lib/stemmers/stopwords/ru.json +561 -0
- data/lib/stemmers/stopwords/sk.json +420 -0
- data/lib/stemmers/stopwords/sl.json +448 -0
- data/lib/stemmers/stopwords/so.json +32 -0
- data/lib/stemmers/stopwords/st.json +33 -0
- data/lib/stemmers/stopwords/sv.json +420 -0
- data/lib/stemmers/stopwords/sw.json +76 -0
- data/lib/stemmers/stopwords/th.json +118 -0
- data/lib/stemmers/stopwords/tl.json +149 -0
- data/lib/stemmers/stopwords/tr.json +506 -0
- data/lib/stemmers/stopwords/uk.json +75 -0
- data/lib/stemmers/stopwords/ur.json +519 -0
- data/lib/stemmers/stopwords/vi.json +647 -0
- data/lib/stemmers/stopwords/yo.json +62 -0
- data/lib/stemmers/stopwords/zh.json +796 -0
- data/lib/stemmers/stopwords/zu.json +31 -0
- data/lib/stemmers/version.rb +5 -0
- data/lib/stemmers.rb +91 -0
- data/sig/stemmers.rbs +4 -0
- 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
|
+
]
|