keyphrase 0.1.2 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +5 -4
- data/lib/keyphrase/stoplist/afr.rb +14 -0
- data/lib/keyphrase/stoplist/aka.rb +10 -0
- data/lib/keyphrase/stoplist/amh.rb +10 -0
- data/lib/keyphrase/stoplist/ara.rb +490 -0
- data/lib/keyphrase/stoplist/aze.rb +175 -0
- data/lib/keyphrase/stoplist/bel.rb +11 -0
- data/lib/keyphrase/stoplist/ben.rb +408 -0
- data/lib/keyphrase/stoplist/bul.rb +528 -0
- data/lib/keyphrase/stoplist/cat.rb +711 -0
- data/lib/keyphrase/stoplist/ces.rb +560 -0
- data/lib/keyphrase/stoplist/cmn.rb +1119 -0
- data/lib/keyphrase/stoplist/dan.rb +25 -0
- data/lib/keyphrase/stoplist/deu.rb +631 -0
- data/lib/keyphrase/stoplist/ell.rb +275 -0
- data/lib/keyphrase/stoplist/eng.rb +2 -589
- data/lib/keyphrase/stoplist/epo.rb +183 -0
- data/lib/keyphrase/stoplist/est.rb +13 -0
- data/lib/keyphrase/stoplist/fin.rb +857 -0
- data/lib/keyphrase/stoplist/fra.rb +699 -0
- data/lib/keyphrase/stoplist/guj.rb +234 -0
- data/lib/keyphrase/stoplist/heb.rb +204 -0
- data/lib/keyphrase/stoplist/hin.rb +235 -0
- data/lib/keyphrase/stoplist/hrv.rb +25 -0
- data/lib/keyphrase/stoplist/hun.rb +1195 -0
- data/lib/keyphrase/stoplist/hye.rb +55 -0
- data/lib/keyphrase/stoplist/ind.rb +768 -0
- data/lib/keyphrase/stoplist/ita.rb +670 -0
- data/lib/keyphrase/stoplist/jav.rb +10 -0
- data/lib/keyphrase/stoplist/jpn.rb +144 -0
- data/lib/keyphrase/stoplist/kan.rb +92 -0
- data/lib/keyphrase/stoplist/kat.rb +383 -0
- data/lib/keyphrase/stoplist/khm.rb +245 -0
- data/lib/keyphrase/stoplist/kor.rb +610 -0
- data/lib/keyphrase/stoplist/lat.rb +14 -0
- data/lib/keyphrase/stoplist/lav.rb +171 -0
- data/lib/keyphrase/stoplist/lit.rb +484 -0
- data/lib/keyphrase/stoplist/mal.rb +11 -0
- data/lib/keyphrase/stoplist/mar.rb +109 -0
- data/lib/keyphrase/stoplist/mkd.rb +11 -0
- data/lib/keyphrase/stoplist/mya.rb +285 -0
- data/lib/keyphrase/stoplist/nep.rb +265 -0
- data/lib/keyphrase/stoplist/nld.rb +423 -0
- data/lib/keyphrase/stoplist/nob.rb +186 -0
- data/lib/keyphrase/stoplist/ori.rb +11 -0
- data/lib/keyphrase/stoplist/pan.rb +473 -0
- data/lib/keyphrase/stoplist/pes.rb +801 -0
- data/lib/keyphrase/stoplist/pol.rb +338 -0
- data/lib/keyphrase/stoplist/por.rb +570 -0
- data/lib/keyphrase/stoplist/ron.rb +444 -0
- data/lib/keyphrase/stoplist/rus.rb +569 -0
- data/lib/keyphrase/stoplist/sin.rb +10 -0
- data/lib/keyphrase/stoplist/slk.rb +428 -0
- data/lib/keyphrase/stoplist/slv.rb +456 -0
- data/lib/keyphrase/stoplist/sna.rb +11 -0
- data/lib/keyphrase/stoplist/spa.rb +731 -0
- data/lib/keyphrase/stoplist/srp.rb +11 -0
- data/lib/keyphrase/stoplist/swe.rb +428 -0
- data/lib/keyphrase/stoplist/tam.rb +135 -0
- data/lib/keyphrase/stoplist/tel.rb +10 -0
- data/lib/keyphrase/stoplist/tgl.rb +157 -0
- data/lib/keyphrase/stoplist/tha.rb +125 -0
- data/lib/keyphrase/stoplist/tuk.rb +11 -0
- data/lib/keyphrase/stoplist/tur.rb +514 -0
- data/lib/keyphrase/stoplist/ukr.rb +38 -0
- data/lib/keyphrase/stoplist/urd.rb +527 -0
- data/lib/keyphrase/stoplist/uzb.rb +10 -0
- data/lib/keyphrase/stoplist/vie.rb +655 -0
- data/lib/keyphrase/stoplist/yid.rb +204 -0
- data/lib/keyphrase/stoplist/zul.rb +39 -0
- data/lib/keyphrase/stoplist.rb +13 -10
- data/lib/keyphrase/version.rb +1 -1
- data/lib/keyphrase.rb +20 -12
- metadata +71 -3
@@ -0,0 +1,157 @@
|
|
1
|
+
class Keyphrase
|
2
|
+
module Stoplist
|
3
|
+
class Tgl
|
4
|
+
def self.stopwords
|
5
|
+
@@stopwords ||= [
|
6
|
+
"akin",
|
7
|
+
"aking",
|
8
|
+
"ako",
|
9
|
+
"alin",
|
10
|
+
"am",
|
11
|
+
"amin",
|
12
|
+
"aming",
|
13
|
+
"ang",
|
14
|
+
"ano",
|
15
|
+
"anumang",
|
16
|
+
"apat",
|
17
|
+
"at",
|
18
|
+
"atin",
|
19
|
+
"ating",
|
20
|
+
"ay",
|
21
|
+
"bababa",
|
22
|
+
"bago",
|
23
|
+
"bakit",
|
24
|
+
"bawat",
|
25
|
+
"bilang",
|
26
|
+
"dahil",
|
27
|
+
"dalawa",
|
28
|
+
"dapat",
|
29
|
+
"din",
|
30
|
+
"dito",
|
31
|
+
"doon",
|
32
|
+
"gagawin",
|
33
|
+
"gayunman",
|
34
|
+
"ginagawa",
|
35
|
+
"ginawa",
|
36
|
+
"ginawang",
|
37
|
+
"gumawa",
|
38
|
+
"gusto",
|
39
|
+
"habang",
|
40
|
+
"hanggang",
|
41
|
+
"hindi",
|
42
|
+
"huwag",
|
43
|
+
"iba",
|
44
|
+
"ibaba",
|
45
|
+
"ibabaw",
|
46
|
+
"ibig",
|
47
|
+
"ikaw",
|
48
|
+
"ilagay",
|
49
|
+
"ilalim",
|
50
|
+
"ilan",
|
51
|
+
"inyong",
|
52
|
+
"isa",
|
53
|
+
"isang",
|
54
|
+
"itaas",
|
55
|
+
"ito",
|
56
|
+
"iyo",
|
57
|
+
"iyon",
|
58
|
+
"iyong",
|
59
|
+
"ka",
|
60
|
+
"kahit",
|
61
|
+
"kailangan",
|
62
|
+
"kailanman",
|
63
|
+
"kami",
|
64
|
+
"kanila",
|
65
|
+
"kanilang",
|
66
|
+
"kanino",
|
67
|
+
"kanya",
|
68
|
+
"kanyang",
|
69
|
+
"kapag",
|
70
|
+
"kapwa",
|
71
|
+
"karamihan",
|
72
|
+
"katiyakan",
|
73
|
+
"katulad",
|
74
|
+
"kaya",
|
75
|
+
"kaysa",
|
76
|
+
"ko",
|
77
|
+
"kong",
|
78
|
+
"kulang",
|
79
|
+
"kumuha",
|
80
|
+
"kung",
|
81
|
+
"laban",
|
82
|
+
"lahat",
|
83
|
+
"lamang",
|
84
|
+
"likod",
|
85
|
+
"lima",
|
86
|
+
"maaari",
|
87
|
+
"maaaring",
|
88
|
+
"maging",
|
89
|
+
"mahusay",
|
90
|
+
"makita",
|
91
|
+
"marami",
|
92
|
+
"marapat",
|
93
|
+
"masyado",
|
94
|
+
"may",
|
95
|
+
"mayroon",
|
96
|
+
"mga",
|
97
|
+
"minsan",
|
98
|
+
"mismo",
|
99
|
+
"mula",
|
100
|
+
"muli",
|
101
|
+
"na",
|
102
|
+
"nabanggit",
|
103
|
+
"naging",
|
104
|
+
"nagkaroon",
|
105
|
+
"nais",
|
106
|
+
"nakita",
|
107
|
+
"namin",
|
108
|
+
"napaka",
|
109
|
+
"narito",
|
110
|
+
"nasaan",
|
111
|
+
"ng",
|
112
|
+
"ngayon",
|
113
|
+
"ni",
|
114
|
+
"nila",
|
115
|
+
"nilang",
|
116
|
+
"nito",
|
117
|
+
"niya",
|
118
|
+
"niyang",
|
119
|
+
"noon",
|
120
|
+
"o",
|
121
|
+
"pa",
|
122
|
+
"paano",
|
123
|
+
"pababa",
|
124
|
+
"paggawa",
|
125
|
+
"pagitan",
|
126
|
+
"pagkakaroon",
|
127
|
+
"pagkatapos",
|
128
|
+
"palabas",
|
129
|
+
"pamamagitan",
|
130
|
+
"panahon",
|
131
|
+
"pangalawa",
|
132
|
+
"para",
|
133
|
+
"paraan",
|
134
|
+
"pareho",
|
135
|
+
"pataas",
|
136
|
+
"pero",
|
137
|
+
"pumunta",
|
138
|
+
"pumupunta",
|
139
|
+
"sa",
|
140
|
+
"saan",
|
141
|
+
"sabi",
|
142
|
+
"sabihin",
|
143
|
+
"sarili",
|
144
|
+
"sila",
|
145
|
+
"sino",
|
146
|
+
"siya",
|
147
|
+
"tatlo",
|
148
|
+
"tayo",
|
149
|
+
"tulad",
|
150
|
+
"tungkol",
|
151
|
+
"una",
|
152
|
+
"walang",
|
153
|
+
]
|
154
|
+
end
|
155
|
+
end
|
156
|
+
end
|
157
|
+
end
|
@@ -0,0 +1,125 @@
|
|
1
|
+
class Keyphrase
|
2
|
+
module Stoplist
|
3
|
+
class Tha
|
4
|
+
def self.stopwords
|
5
|
+
@@stopwords ||= [
|
6
|
+
"กล่าว",
|
7
|
+
"กว่า",
|
8
|
+
"กัน",
|
9
|
+
"กับ",
|
10
|
+
"การ",
|
11
|
+
"ก็",
|
12
|
+
"ก่อน",
|
13
|
+
"ขณะ",
|
14
|
+
"ขอ",
|
15
|
+
"ของ",
|
16
|
+
"ขึ้น",
|
17
|
+
"คง",
|
18
|
+
"ครั้ง",
|
19
|
+
"ความ",
|
20
|
+
"คือ",
|
21
|
+
"จะ",
|
22
|
+
"จัด",
|
23
|
+
"จาก",
|
24
|
+
"จึง",
|
25
|
+
"ช่วง",
|
26
|
+
"ซึ่ง",
|
27
|
+
"ดัง",
|
28
|
+
"ด้วย",
|
29
|
+
"ด้าน",
|
30
|
+
"ตั้ง",
|
31
|
+
"ตั้งแต่",
|
32
|
+
"ตาม",
|
33
|
+
"ต่อ",
|
34
|
+
"ต่าง",
|
35
|
+
"ต่างๆ",
|
36
|
+
"ต้อง",
|
37
|
+
"ถึง",
|
38
|
+
"ถูก",
|
39
|
+
"ถ้า",
|
40
|
+
"ทั้ง",
|
41
|
+
"ทั้งนี้",
|
42
|
+
"ทาง",
|
43
|
+
"ทำ",
|
44
|
+
"ทำให้",
|
45
|
+
"ที่",
|
46
|
+
"ที่สุด",
|
47
|
+
"ทุก",
|
48
|
+
"นอกจาก",
|
49
|
+
"นัก",
|
50
|
+
"นั้น",
|
51
|
+
"นำ",
|
52
|
+
"นี้",
|
53
|
+
"น่า",
|
54
|
+
"บาง",
|
55
|
+
"ผล",
|
56
|
+
"ผ่าน",
|
57
|
+
"พบ",
|
58
|
+
"พร้อม",
|
59
|
+
"มา",
|
60
|
+
"มาก",
|
61
|
+
"มี",
|
62
|
+
"ยัง",
|
63
|
+
"รวม",
|
64
|
+
"ระหว่าง",
|
65
|
+
"รับ",
|
66
|
+
"ราย",
|
67
|
+
"ร่วม",
|
68
|
+
"ลง",
|
69
|
+
"วัน",
|
70
|
+
"ว่า",
|
71
|
+
"สำหรับ",
|
72
|
+
"สุด",
|
73
|
+
"ส่ง",
|
74
|
+
"ส่วน",
|
75
|
+
"หนึ่ง",
|
76
|
+
"หรือ",
|
77
|
+
"หลัง",
|
78
|
+
"หลังจาก",
|
79
|
+
"หลาย",
|
80
|
+
"หาก",
|
81
|
+
"อยาก",
|
82
|
+
"อยู่",
|
83
|
+
"อย่าง",
|
84
|
+
"ออก",
|
85
|
+
"อะไร",
|
86
|
+
"อาจ",
|
87
|
+
"อีก",
|
88
|
+
"เขา",
|
89
|
+
"เข้า",
|
90
|
+
"เคย",
|
91
|
+
"เฉพาะ",
|
92
|
+
"เช่น",
|
93
|
+
"เดียว",
|
94
|
+
"เดียวกัน",
|
95
|
+
"เนื่องจาก",
|
96
|
+
"เปิด",
|
97
|
+
"เปิดเผย",
|
98
|
+
"เป็น",
|
99
|
+
"เป็นการ",
|
100
|
+
"เพราะ",
|
101
|
+
"เพื่อ",
|
102
|
+
"เมื่อ",
|
103
|
+
"เรา",
|
104
|
+
"เริ่ม",
|
105
|
+
"เลย",
|
106
|
+
"เห็น",
|
107
|
+
"เอง",
|
108
|
+
"แต่",
|
109
|
+
"แบบ",
|
110
|
+
"แรก",
|
111
|
+
"และ",
|
112
|
+
"แล้ว",
|
113
|
+
"แห่ง",
|
114
|
+
"โดย",
|
115
|
+
"ใน",
|
116
|
+
"ให้",
|
117
|
+
"ได้",
|
118
|
+
"ไป",
|
119
|
+
"ไม่",
|
120
|
+
"ไว้",
|
121
|
+
]
|
122
|
+
end
|
123
|
+
end
|
124
|
+
end
|
125
|
+
end
|