natural 0.5.6 → 0.6.3
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.
- package/.dockerignore +2 -0
- package/.idea/misc.xml +6 -0
- package/.idea/modules.xml +8 -0
- package/.idea/natural.iml +12 -0
- package/.idea/vcs.xml +6 -0
- package/.idea/workspace.xml +511 -0
- package/.travis.yml +8 -1
- package/README.md +331 -40
- package/bayes_classifier.json +1 -1
- package/classifier.json +418 -0
- package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tagger.js +8 -9
- package/lib/natural/brill_pos_tagger/lib/Brill_POS_Tester.js +5 -5
- package/lib/natural/brill_pos_tagger/lib/Brill_POS_Trainer.js +10 -6
- package/lib/natural/brill_pos_tagger/lib/Corpus.js +21 -16
- package/lib/natural/brill_pos_tagger/lib/Lexicon.js +22 -13
- package/lib/natural/brill_pos_tagger/lib/Predicate.js +2 -2
- package/lib/natural/brill_pos_tagger/lib/RuleTemplate.js +2 -2
- package/lib/natural/brill_pos_tagger/lib/RuleTemplates.js +132 -146
- package/lib/natural/brill_pos_tagger/lib/Sentence.js +41 -0
- package/lib/natural/brill_pos_tagger/lib/TransformationRule.js +10 -11
- package/lib/natural/classifiers/classifier.js +5 -3
- package/lib/natural/classifiers/maxent/Classifier.js +125 -0
- package/lib/natural/classifiers/maxent/Context.js +33 -0
- package/lib/natural/classifiers/maxent/Distribution.js +145 -0
- package/lib/natural/classifiers/maxent/Element.js +34 -0
- package/lib/natural/classifiers/maxent/Feature.js +88 -0
- package/lib/natural/classifiers/maxent/FeatureSet.js +67 -0
- package/lib/natural/classifiers/maxent/GISScaler.js +148 -0
- package/lib/natural/classifiers/maxent/POS/ME_Corpus.js +56 -0
- package/lib/natural/classifiers/maxent/POS/ME_Sentence.js +73 -0
- package/lib/natural/classifiers/maxent/POS/POS_Element.js +172 -0
- package/lib/natural/classifiers/maxent/Sample.js +141 -0
- package/lib/natural/classifiers/maxent/SimpleExample/SE_Element.js +49 -0
- package/lib/natural/distance/hamming_distance.js +52 -0
- package/lib/natural/distance/jaro-winkler_distance.js +16 -6
- package/lib/natural/distance/levenshtein_distance.js +2 -2
- package/lib/natural/index.js +21 -2
- package/lib/natural/inflectors/noun_inflector.js +5 -3
- package/lib/natural/ngrams/ngrams.js +83 -25
- package/lib/natural/sentiment/Basque/senticon_eu.json +21557 -0
- package/lib/natural/sentiment/Catalan/senticon_ca.json +36352 -0
- package/lib/natural/sentiment/Dutch/negations_du.json +3 -0
- package/lib/natural/sentiment/Dutch/pattern-sentiment-nl.json +39650 -0
- package/lib/natural/sentiment/English/negations_en.json +3 -0
- package/lib/natural/sentiment/English/pattern-sentiment-en.json +16024 -0
- package/lib/natural/sentiment/English/senticon_en.json +124197 -0
- package/lib/natural/sentiment/French/pattern-sentiment-fr.json +40906 -0
- package/lib/natural/sentiment/Galician/senticon_gl.json +24427 -0
- package/lib/natural/sentiment/Italian/pattern-sentiment-it.json +24522 -0
- package/lib/natural/sentiment/SentimentAnalyzer.js +116 -0
- package/lib/natural/sentiment/Spanish/afinnShortSortedSpanish.json +1655 -0
- package/lib/natural/sentiment/Spanish/negations_es.json +3 -0
- package/lib/natural/sentiment/Spanish/senticon_es.json +56722 -0
- package/lib/natural/sentiment/tools/README.md +31 -0
- package/lib/natural/sentiment/tools/XmlParser4PatternData.js +31 -0
- package/lib/natural/sentiment/tools/sentimentXmlParser.js +30 -0
- package/lib/natural/stemmers/indonesian/data/kata-dasar.json +29935 -0
- package/lib/natural/stemmers/indonesian/prefix_rules.js +10 -9
- package/lib/natural/stemmers/indonesian/stemmer_id.js +16 -15
- package/lib/natural/stemmers/indonesian/suffix_rules.js +2 -2
- package/lib/natural/stemmers/porter_stemmer_es.js +265 -199
- package/lib/natural/stemmers/porter_stemmer_fr.js +1 -1
- package/lib/natural/stemmers/porter_stemmer_nl.js +362 -0
- package/lib/natural/stemmers/stemmer_es.js +18 -12
- package/lib/natural/stemmers/stemmer_nl.js +64 -0
- package/lib/natural/tfidf/tfidf.js +27 -4
- package/lib/natural/tokenizers/aggressive_tokenizer_sv.js +1 -1
- package/lib/natural/tokenizers/aggressive_tokenizer_vi.js +37 -0
- package/lib/natural/tokenizers/orthography_matchers.js +33 -0
- package/lib/natural/tokenizers/regexp_tokenizer.js +24 -4
- package/lib/natural/tokenizers/sentence_tokenizer.js +1 -1
- package/lib/natural/wordnet/wordnet_file.js +7 -1
- package/lr_classifier.json +1 -1
- package/package.json +35 -23
- package/.npmignore +0 -4
- package/.vscode/temp.sql +0 -0
- package/Makefile +0 -38
- package/data/kata-dasar.txt +0 -29933
- package/package-lock.json +0 -79
- package/tests/stemmer_id_test.js +0 -361
package/package-lock.json
DELETED
|
@@ -1,79 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"name": "natural",
|
|
3
|
-
"version": "0.5.4",
|
|
4
|
-
"lockfileVersion": 1,
|
|
5
|
-
"requires": true,
|
|
6
|
-
"dependencies": {
|
|
7
|
-
"apparatus": {
|
|
8
|
-
"version": "0.0.9",
|
|
9
|
-
"resolved": "https://registry.npmjs.org/apparatus/-/apparatus-0.0.9.tgz",
|
|
10
|
-
"integrity": "sha1-N9zSWDStC2UQdllikduCPusZCL0=",
|
|
11
|
-
"requires": {
|
|
12
|
-
"sylvester": "0.0.21"
|
|
13
|
-
}
|
|
14
|
-
},
|
|
15
|
-
"assertion-error": {
|
|
16
|
-
"version": "1.0.2",
|
|
17
|
-
"resolved": "https://registry.npmjs.org/assertion-error/-/assertion-error-1.0.2.tgz",
|
|
18
|
-
"integrity": "sha1-E8pRXYYgbaC6xm6DTdOX2HWBCUw=",
|
|
19
|
-
"dev": true
|
|
20
|
-
},
|
|
21
|
-
"chai": {
|
|
22
|
-
"version": "4.1.2",
|
|
23
|
-
"resolved": "https://registry.npmjs.org/chai/-/chai-4.1.2.tgz",
|
|
24
|
-
"integrity": "sha1-D2RYS6ZC8PKs4oBiefTwbKI61zw=",
|
|
25
|
-
"dev": true,
|
|
26
|
-
"requires": {
|
|
27
|
-
"assertion-error": "1.0.2",
|
|
28
|
-
"check-error": "1.0.2",
|
|
29
|
-
"deep-eql": "3.0.1",
|
|
30
|
-
"get-func-name": "2.0.0",
|
|
31
|
-
"pathval": "1.1.0",
|
|
32
|
-
"type-detect": "4.0.3"
|
|
33
|
-
}
|
|
34
|
-
},
|
|
35
|
-
"check-error": {
|
|
36
|
-
"version": "1.0.2",
|
|
37
|
-
"resolved": "https://registry.npmjs.org/check-error/-/check-error-1.0.2.tgz",
|
|
38
|
-
"integrity": "sha1-V00xLt2Iu13YkS6Sht1sCu1KrII=",
|
|
39
|
-
"dev": true
|
|
40
|
-
},
|
|
41
|
-
"deep-eql": {
|
|
42
|
-
"version": "3.0.1",
|
|
43
|
-
"resolved": "https://registry.npmjs.org/deep-eql/-/deep-eql-3.0.1.tgz",
|
|
44
|
-
"integrity": "sha512-+QeIQyN5ZuO+3Uk5DYh6/1eKO0m0YmJFGNmFHGACpf1ClL1nmlV/p4gNgbl2pJGxgXb4faqo6UE+M5ACEMyVcw==",
|
|
45
|
-
"dev": true,
|
|
46
|
-
"requires": {
|
|
47
|
-
"type-detect": "4.0.3"
|
|
48
|
-
}
|
|
49
|
-
},
|
|
50
|
-
"get-func-name": {
|
|
51
|
-
"version": "2.0.0",
|
|
52
|
-
"resolved": "https://registry.npmjs.org/get-func-name/-/get-func-name-2.0.0.tgz",
|
|
53
|
-
"integrity": "sha1-6td0q+5y4gQJQzoGY2YCPdaIekE=",
|
|
54
|
-
"dev": true
|
|
55
|
-
},
|
|
56
|
-
"pathval": {
|
|
57
|
-
"version": "1.1.0",
|
|
58
|
-
"resolved": "https://registry.npmjs.org/pathval/-/pathval-1.1.0.tgz",
|
|
59
|
-
"integrity": "sha1-uULm1L3mUwBe9rcTYd74cn0GReA=",
|
|
60
|
-
"dev": true
|
|
61
|
-
},
|
|
62
|
-
"sylvester": {
|
|
63
|
-
"version": "0.0.21",
|
|
64
|
-
"resolved": "https://registry.npmjs.org/sylvester/-/sylvester-0.0.21.tgz",
|
|
65
|
-
"integrity": "sha1-KYexzivS84sNzio0OIiEv6RADqc="
|
|
66
|
-
},
|
|
67
|
-
"type-detect": {
|
|
68
|
-
"version": "4.0.3",
|
|
69
|
-
"resolved": "https://registry.npmjs.org/type-detect/-/type-detect-4.0.3.tgz",
|
|
70
|
-
"integrity": "sha1-Dj8mcLRAmbC0bChNE2p+9Jx0wuo=",
|
|
71
|
-
"dev": true
|
|
72
|
-
},
|
|
73
|
-
"underscore": {
|
|
74
|
-
"version": "1.8.3",
|
|
75
|
-
"resolved": "https://registry.npmjs.org/underscore/-/underscore-1.8.3.tgz",
|
|
76
|
-
"integrity": "sha1-Tz+1OxBuYJf8+ctBCfKl6b36UCI="
|
|
77
|
-
}
|
|
78
|
-
}
|
|
79
|
-
}
|
package/tests/stemmer_id_test.js
DELETED
|
@@ -1,361 +0,0 @@
|
|
|
1
|
-
/*
|
|
2
|
-
THIS TEST REQUIRE CHAI AND MOCHA
|
|
3
|
-
install chai --> npm install chai --save-dev
|
|
4
|
-
install mocha --> npm install mocha -g
|
|
5
|
-
to run --> mocha tests --watch
|
|
6
|
-
*/
|
|
7
|
-
var chai = require('chai');
|
|
8
|
-
var expect = chai.expect; // we are using the "expect" style of Chai
|
|
9
|
-
|
|
10
|
-
var natural = require('../lib/natural/');
|
|
11
|
-
var Stemmer = natural.StemmerId;
|
|
12
|
-
|
|
13
|
-
var data = []
|
|
14
|
-
|
|
15
|
-
// THE TESTCASES
|
|
16
|
-
// don't stem short words
|
|
17
|
-
data.push(['mei', 'mei'])
|
|
18
|
-
data.push(['bui', 'bui'])
|
|
19
|
-
|
|
20
|
-
// lookup up the dictionary, to prevent overstemming
|
|
21
|
-
// don't stem nilai to nila
|
|
22
|
-
data.push(['nilai', 'nilai'])
|
|
23
|
-
|
|
24
|
-
// lah|kah|tah|pun
|
|
25
|
-
data.push(['hancurlah', 'hancur'])
|
|
26
|
-
data.push(['benarkah', 'benar'])
|
|
27
|
-
data.push(['apatah', 'apa'])
|
|
28
|
-
data.push(['siapapun', 'siapa'])
|
|
29
|
-
|
|
30
|
-
// ku|mu|nya
|
|
31
|
-
data.push(['jubahku', 'jubah'])
|
|
32
|
-
data.push(['bajumu', 'baju'])
|
|
33
|
-
data.push(['celananya', 'celana'])
|
|
34
|
-
|
|
35
|
-
// i|kan|an
|
|
36
|
-
data.push(['hantui', 'hantu'])
|
|
37
|
-
data.push(['belikan', 'beli'])
|
|
38
|
-
data.push(['jualan', 'jual'])
|
|
39
|
-
|
|
40
|
-
// combination of suffixes
|
|
41
|
-
data.push(['bukumukah', 'buku']) //gagal karena -ku dianggap suffix dan dihilangkan
|
|
42
|
-
data.push(['miliknyalah', 'milik'])
|
|
43
|
-
data.push(['kulitkupun', 'kulit']) //gagal karena -ku dianggap suffix dan dihilangkan
|
|
44
|
-
data.push(['berikanku', 'beri'])
|
|
45
|
-
data.push(['sakitimu', 'sakit'])
|
|
46
|
-
data.push(['beriannya', 'beri'])
|
|
47
|
-
data.push(['kasihilah', 'kasih'])
|
|
48
|
-
|
|
49
|
-
// plain prefix
|
|
50
|
-
data.push(['dibuang', 'buang'])
|
|
51
|
-
data.push(['kesakitan', 'sakit'])
|
|
52
|
-
data.push(['sesuap', 'suap'])
|
|
53
|
-
|
|
54
|
-
//data.push(['teriakanmu', 'teriak']) // wtf? kok jadi ria?
|
|
55
|
-
//teriakanmu -> te-ria-kan-mu
|
|
56
|
-
|
|
57
|
-
// template formulas for derivation prefix rules (disambiguation) //
|
|
58
|
-
|
|
59
|
-
// rule 1a : berV -> ber-V
|
|
60
|
-
data.push(['beradu', 'adu'])
|
|
61
|
-
|
|
62
|
-
// rule 1b : berV -> be-rV
|
|
63
|
-
data.push(['berambut', 'rambut'])
|
|
64
|
-
|
|
65
|
-
// rule 2 : berCAP -> ber-CAP
|
|
66
|
-
data.push(['bersuara', 'suara'])
|
|
67
|
-
|
|
68
|
-
// rule 3 : berCAerV -> ber-CAerV where C != 'r'
|
|
69
|
-
data.push(['berdaerah', 'daerah'])
|
|
70
|
-
|
|
71
|
-
// rule 4 : belajar -> bel-ajar
|
|
72
|
-
data.push(['belajar', 'ajar'])
|
|
73
|
-
|
|
74
|
-
// rule 5 : beC1erC2 -> be-C1erC2 where C1 != {'r'|'l'}
|
|
75
|
-
data.push(['bekerja', 'kerja'])
|
|
76
|
-
data.push(['beternak', 'ternak'])
|
|
77
|
-
|
|
78
|
-
// rule 6a : terV -> ter-V
|
|
79
|
-
data.push(['terasing', 'asing'])
|
|
80
|
-
|
|
81
|
-
// rule 6b : terV -> te-rV
|
|
82
|
-
data.push(['teraup', 'raup'])
|
|
83
|
-
|
|
84
|
-
// rule 7 : terCerV -> ter-CerV where C != 'r'
|
|
85
|
-
data.push(['tergerak', 'gerak'])
|
|
86
|
-
|
|
87
|
-
// rule 8 : terCP -> ter-CP where C != 'r' and P != 'er'
|
|
88
|
-
data.push(['terpuruk', 'puruk'])
|
|
89
|
-
|
|
90
|
-
// rule 9 : teC1erC2 -> te-C1erC2 where C1 != 'r'
|
|
91
|
-
data.push(['teterbang', 'terbang'])
|
|
92
|
-
|
|
93
|
-
// rule 10 : me{l|r|w|y}V -> me-{l|r|w|y}V
|
|
94
|
-
data.push(['melipat', 'lipat'])
|
|
95
|
-
data.push(['meringkas', 'ringkas'])
|
|
96
|
-
data.push(['mewarnai', 'warna'])
|
|
97
|
-
data.push(['meyakinkan', 'yakin'])
|
|
98
|
-
|
|
99
|
-
// rule 11 : mem{b|f|v} -> mem-{b|f|v}
|
|
100
|
-
data.push(['membangun', 'bangun'])
|
|
101
|
-
data.push(['memfitnah', 'fitnah'])
|
|
102
|
-
data.push(['memvonis', 'vonis'])
|
|
103
|
-
|
|
104
|
-
// rule 12 : mempe{r|l} -> mem-pe
|
|
105
|
-
data.push(['memperbarui', 'baru'])
|
|
106
|
-
data.push(['mempelajari', 'ajar'])
|
|
107
|
-
|
|
108
|
-
// rule 13a : mem{rV|V} -> mem{rV|V}
|
|
109
|
-
data.push(['meminum', 'minum'])
|
|
110
|
-
|
|
111
|
-
// rule 13b : mem{rV|V} -> me-p{rV|V}
|
|
112
|
-
data.push(['memukul', 'pukul'])
|
|
113
|
-
|
|
114
|
-
// rule 14 : men{c|d|j|z} -> men-{c|d|j|z}
|
|
115
|
-
data.push(['mencinta', 'cinta'])
|
|
116
|
-
data.push(['mendua', 'dua'])
|
|
117
|
-
data.push(['menjauh', 'jauh'])
|
|
118
|
-
data.push(['menziarah', 'ziarah'])
|
|
119
|
-
|
|
120
|
-
// rule 15a : men{V} -> me-n{V}
|
|
121
|
-
data.push(['menuklir', 'nuklir'])
|
|
122
|
-
|
|
123
|
-
// rule 15b : men{V} -> me-t{V}
|
|
124
|
-
data.push(['menangkap', 'tangkap'])
|
|
125
|
-
|
|
126
|
-
// rule 16 : meng{g|h|q} -> meng-{g|h|q}
|
|
127
|
-
data.push(['menggila', 'gila'])
|
|
128
|
-
data.push(['menghajar', 'hajar'])
|
|
129
|
-
data.push(['mengqasar', 'qasar'])
|
|
130
|
-
|
|
131
|
-
// rule 17a : mengV -> meng-V
|
|
132
|
-
data.push(['mengudara', 'udara'])
|
|
133
|
-
|
|
134
|
-
// rule 17b : mengV -> meng-kV
|
|
135
|
-
data.push(['mengupas', 'kupas'])
|
|
136
|
-
|
|
137
|
-
// rule 18 : menyV -> meny-sV
|
|
138
|
-
data.push(['menyuarakan', 'suara'])
|
|
139
|
-
|
|
140
|
-
// rule 19 : mempV -> mem-pV where V != 'e'
|
|
141
|
-
data.push(['mempopulerkan', 'populer'])
|
|
142
|
-
|
|
143
|
-
// rule 20 : pe{w|y}V -> pe-{w|y}V
|
|
144
|
-
data.push(['pewarna', 'warna'])
|
|
145
|
-
data.push(['peyoga', 'yoga'])
|
|
146
|
-
|
|
147
|
-
// rule 21a : perV -> per-V
|
|
148
|
-
data.push(['peradilan', 'adil'])
|
|
149
|
-
|
|
150
|
-
// rule 21b : perV -> pe-rV
|
|
151
|
-
data.push(['perumahan', 'rumah'])
|
|
152
|
-
|
|
153
|
-
// rule 22 is missing in the document?
|
|
154
|
-
|
|
155
|
-
// rule 23 : perCAP -> per-CAP where C != 'r' and P != 'er'
|
|
156
|
-
data.push(['permuka', 'muka'])
|
|
157
|
-
|
|
158
|
-
// rule 24 : perCAerV -> per-CAerV where C != 'r'
|
|
159
|
-
data.push(['perdaerah', 'daerah'])
|
|
160
|
-
|
|
161
|
-
// rule 25 : pem{b|f|v} -> pem-{b|f|v}
|
|
162
|
-
data.push(['pembangun', 'bangun'])
|
|
163
|
-
data.push(['pemfitnah', 'fitnah'])
|
|
164
|
-
data.push(['pemvonis', 'vonis'])
|
|
165
|
-
|
|
166
|
-
// rule 26a : pem{rV|V} -> pe-m{rV|V}
|
|
167
|
-
data.push(['peminum', 'minum'])
|
|
168
|
-
|
|
169
|
-
// rule 26b : pem{rV|V} -> pe-p{rV|V}
|
|
170
|
-
data.push(['pemukul', 'pukul'])
|
|
171
|
-
|
|
172
|
-
// rule 27 : men{c|d|j|z} -> men-{c|d|j|z}
|
|
173
|
-
data.push(['pencinta', 'cinta'])
|
|
174
|
-
data.push(['pendahulu', 'dahulu'])
|
|
175
|
-
data.push(['penjarah', 'jarah'])
|
|
176
|
-
data.push(['penziarah', 'ziarah'])
|
|
177
|
-
|
|
178
|
-
// rule 28a : pen{V} -> pe-n{V}
|
|
179
|
-
data.push(['penasihat', 'nasihat'])
|
|
180
|
-
|
|
181
|
-
// rule 28b : pen{V} -> pe-t{V}
|
|
182
|
-
data.push(['penangkap', 'tangkap'])
|
|
183
|
-
|
|
184
|
-
// rule 29 : peng{g|h|q} -> peng-{g|h|q}
|
|
185
|
-
data.push(['penggila', 'gila'])
|
|
186
|
-
data.push(['penghajar', 'hajar'])
|
|
187
|
-
data.push(['pengqasar', 'qasar'])
|
|
188
|
-
|
|
189
|
-
// rule 30a : pengV -> peng-V
|
|
190
|
-
data.push(['pengudara', 'udara'])
|
|
191
|
-
|
|
192
|
-
// rule 30b : pengV -> peng-kV
|
|
193
|
-
data.push(['pengupas', 'kupas'])
|
|
194
|
-
|
|
195
|
-
// rule 31 : penyV -> peny-sV
|
|
196
|
-
data.push(['penyuara', 'suara'])
|
|
197
|
-
|
|
198
|
-
// rule 32 : pelV -> pe-lV except pelajar -> ajar
|
|
199
|
-
data.push(['pelajar', 'ajar'])
|
|
200
|
-
data.push(['pelabuhan', 'labuh'])
|
|
201
|
-
|
|
202
|
-
// rule 33 : peCerV -> per-erV where C != {r|w|y|l|m|n}
|
|
203
|
-
// TODO : find the examples
|
|
204
|
-
|
|
205
|
-
// rule 34 : peCP -> pe-CP where C != {r|w|y|l|m|n} and P != 'er'
|
|
206
|
-
data.push(['petarung', 'tarung'])
|
|
207
|
-
|
|
208
|
-
// CS additional rules
|
|
209
|
-
|
|
210
|
-
// rule 35 : terC1erC2 -> ter-C1erC2 where C1 != 'r'
|
|
211
|
-
data.push(['terpercaya', 'percaya'])
|
|
212
|
-
|
|
213
|
-
// rule 36 : peC1erC2 -> pe-C1erC2 where C1 != {r|w|y|l|m|n}
|
|
214
|
-
data.push(['pekerja', 'kerja'])
|
|
215
|
-
data.push(['peserta', 'serta'])
|
|
216
|
-
|
|
217
|
-
// CS modify rule 12
|
|
218
|
-
data.push(['mempengaruhi', 'pengaruh'])
|
|
219
|
-
|
|
220
|
-
// CS modify rule 16
|
|
221
|
-
data.push(['mengkritik', 'kritik'])
|
|
222
|
-
|
|
223
|
-
// CS adjusting rule precedence
|
|
224
|
-
data.push(['bersekolah', 'sekolah']) //gagal sekolah -> seko why?
|
|
225
|
-
data.push(['bertahan', 'tahan'])
|
|
226
|
-
data.push(['mencapai', 'capai']) //gagal mencapai -> capa
|
|
227
|
-
data.push(['dimulai', 'mulai'])
|
|
228
|
-
data.push(['petani', 'tani']) //gagal petani -> petan
|
|
229
|
-
data.push(['terabai', 'abai']) //gagal terabai -> aba
|
|
230
|
-
|
|
231
|
-
// ECS
|
|
232
|
-
data.push(['mensyaratkan', 'syarat'])
|
|
233
|
-
data.push(['mensyukuri', 'syukur'])
|
|
234
|
-
data.push(['mengebom', 'bom'])
|
|
235
|
-
data.push(['mempromosikan', 'promosi'])
|
|
236
|
-
data.push(['memproteksi', 'proteksi'])
|
|
237
|
-
data.push(['memprediksi', 'prediksi'])
|
|
238
|
-
data.push(['pengkajian', 'kaji'])
|
|
239
|
-
data.push(['pengebom', 'bom'])
|
|
240
|
-
|
|
241
|
-
// ECS loop pengembalian akhiran
|
|
242
|
-
data.push(['bersembunyi', 'sembunyi'])
|
|
243
|
-
data.push(['bersembunyilah', 'sembunyi'])
|
|
244
|
-
data.push(['pelanggan', 'langgan'])
|
|
245
|
-
data.push(['pelaku', 'laku'])
|
|
246
|
-
data.push(['pelangganmukah', 'langgan'])
|
|
247
|
-
data.push(['pelakunyalah', 'laku'])
|
|
248
|
-
|
|
249
|
-
data.push(['perbaikan', 'baik'])
|
|
250
|
-
data.push(['kebaikannya', 'baik'])
|
|
251
|
-
data.push(['bisikan', 'bisik'])
|
|
252
|
-
data.push(['menerangi', 'terang'])
|
|
253
|
-
data.push(['berimanlah', 'iman'])
|
|
254
|
-
|
|
255
|
-
data.push(['memuaskan', 'puas'])
|
|
256
|
-
data.push(['berpelanggan', 'langgan'])
|
|
257
|
-
data.push(['bermakanan', 'makan'])
|
|
258
|
-
|
|
259
|
-
// CC (Modified ECS)
|
|
260
|
-
data.push(['menyala', 'nyala'])
|
|
261
|
-
data.push(['menyanyikan', 'nyanyi'])
|
|
262
|
-
data.push(['menyatakannya', 'nyata'])
|
|
263
|
-
|
|
264
|
-
data.push(['penyanyi', 'nyanyi'])
|
|
265
|
-
data.push(['penyawaan', 'nyawa'])
|
|
266
|
-
|
|
267
|
-
// CC infix
|
|
268
|
-
data.push(['rerata', 'rata'])
|
|
269
|
-
data.push(['lelembut', 'lembut'])
|
|
270
|
-
data.push(['lemigas', 'ligas'])
|
|
271
|
-
data.push(['kinerja', 'kerja'])
|
|
272
|
-
|
|
273
|
-
// plurals
|
|
274
|
-
data.push(['buku-buku', 'buku'])
|
|
275
|
-
data.push(['berbalas-balasan', 'balas'])
|
|
276
|
-
data.push(['bolak-balik', 'bolak-balik'])
|
|
277
|
-
|
|
278
|
-
// combination of prefix + suffix
|
|
279
|
-
data.push(['bertebaran', 'tebar'])
|
|
280
|
-
data.push(['terasingkan', 'asing'])
|
|
281
|
-
data.push(['membangunkan', 'bangun'])
|
|
282
|
-
data.push(['mencintai', 'cinta'])
|
|
283
|
-
data.push(['menduakan', 'dua'])
|
|
284
|
-
data.push(['menjauhi', 'jauh'])
|
|
285
|
-
data.push(['menggilai', 'gila'])
|
|
286
|
-
data.push(['pembangunan', 'bangun'])
|
|
287
|
-
|
|
288
|
-
// return the word if not found in the dictionary
|
|
289
|
-
data.push(['marwan', 'marwan'])
|
|
290
|
-
data.push(['subarkah', 'subarkah'])
|
|
291
|
-
|
|
292
|
-
// recursively remove prefix
|
|
293
|
-
data.push(['memberdayakan', 'daya'])
|
|
294
|
-
data.push(['persemakmuran', 'makmur'])
|
|
295
|
-
data.push(['keberuntunganmu', 'untung'])
|
|
296
|
-
data.push(['kesepersepuluhnya', 'sepuluh'])
|
|
297
|
-
|
|
298
|
-
// test stem sentence
|
|
299
|
-
data.push(['siapakah memberdayakan pembangunan', 'siapa daya bangun'])
|
|
300
|
-
|
|
301
|
-
// issues
|
|
302
|
-
data.push(['Perekonomian', 'ekonomi'])
|
|
303
|
-
data.push(['menahan', 'tahan'])
|
|
304
|
-
|
|
305
|
-
// test stem multiple sentences
|
|
306
|
-
multipleSentence1 = 'Cinta telah bertebaran.Keduanya saling mencintai.';
|
|
307
|
-
multipleSentence2 = "(Cinta telah bertebaran)\n\n\n\nKeduanya saling mencintai.";
|
|
308
|
-
data.push([multipleSentence1, 'cinta telah tebar dua saling cinta'])
|
|
309
|
-
data.push([multipleSentence2, 'cinta telah tebar dua saling cinta'])
|
|
310
|
-
|
|
311
|
-
// failed on other method / algorithm but we should succeed
|
|
312
|
-
data.push(['peranan', 'peran'])
|
|
313
|
-
data.push(['memberikan', 'beri'])
|
|
314
|
-
data.push(['medannya', 'medan'])
|
|
315
|
-
|
|
316
|
-
// TODO:
|
|
317
|
-
//data.push(['sebagai', 'bagai'])
|
|
318
|
-
//data.push(['bagian', 'bagian'])
|
|
319
|
-
//data.push(['berbadan', 'badan'])
|
|
320
|
-
//data.push(['abdullah', 'abdullah'])
|
|
321
|
-
|
|
322
|
-
// adopted foreign suffixes
|
|
323
|
-
//data.push(['budayawan', 'budaya'])
|
|
324
|
-
//data.push(['karyawati', 'karya'])
|
|
325
|
-
data.push(['idealis', 'ideal'])
|
|
326
|
-
data.push(['idealisme', 'ideal'])
|
|
327
|
-
data.push(['finalisasi', 'final'])
|
|
328
|
-
|
|
329
|
-
// sastrawi additional rules
|
|
330
|
-
data.push(['penstabilan', 'stabil'])
|
|
331
|
-
data.push(['pentranskripsi', 'transkripsi'])
|
|
332
|
-
|
|
333
|
-
data.push(['mentaati', 'taat'])
|
|
334
|
-
data.push(['meniru-nirukan', 'tiru'])
|
|
335
|
-
data.push(['menyepak-nyepak', 'sepak'])
|
|
336
|
-
|
|
337
|
-
data.push(['melewati', 'lewat'])
|
|
338
|
-
data.push(['menganga', 'nganga'])
|
|
339
|
-
|
|
340
|
-
data.push(['kupukul', 'pukul'])
|
|
341
|
-
data.push(['kauhajar', 'hajar'])
|
|
342
|
-
|
|
343
|
-
data.push(['kuasa-Mu', 'kuasa'])
|
|
344
|
-
data.push(['malaikat-malaikat-Nya', 'malaikat'])
|
|
345
|
-
data.push(['nikmat-Ku', 'nikmat'])
|
|
346
|
-
data.push(['allah-lah', 'allah'])
|
|
347
|
-
|
|
348
|
-
|
|
349
|
-
function mochaSyncTest(data, i){
|
|
350
|
-
it("Stemming " + data[i][0] + " to " + data[i][1] , function() {
|
|
351
|
-
var output = Stemmer.tokenizeAndStem(data[i][0]);
|
|
352
|
-
output = output.join(" ");
|
|
353
|
-
console.log(output);
|
|
354
|
-
expect(output).to.equal(data[i][1]);
|
|
355
|
-
});
|
|
356
|
-
}
|
|
357
|
-
for(var i in data){
|
|
358
|
-
describe("tryStem-" + i, function() {
|
|
359
|
-
mochaSyncTest(data, i);
|
|
360
|
-
});
|
|
361
|
-
}
|