mittens 0.2.0 → 0.3.1
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 +4 -4
- data/CHANGELOG.md +8 -0
- data/Gemfile +1 -1
- data/README.md +3 -3
- data/Rakefile +2 -2
- data/ext/mittens/extconf.rb +3 -1
- data/lib/mittens/version.rb +1 -1
- data/vendor/snowball/.github/workflows/ci.yml +216 -0
- data/vendor/snowball/CONTRIBUTING.rst +111 -62
- data/vendor/snowball/GNUmakefile +194 -136
- data/vendor/snowball/NEWS +798 -3
- data/vendor/snowball/README.rst +50 -1
- data/vendor/snowball/ada/src/stemmer.adb +25 -13
- data/vendor/snowball/ada/src/stemmer.ads +9 -9
- data/vendor/snowball/ada/stemmer_config.gpr +7 -7
- data/vendor/snowball/algorithms/basque.sbl +4 -19
- data/vendor/snowball/algorithms/catalan.sbl +2 -9
- data/vendor/snowball/algorithms/danish.sbl +1 -1
- data/vendor/snowball/algorithms/dutch.sbl +284 -122
- data/vendor/snowball/algorithms/dutch_porter.sbl +178 -0
- data/vendor/snowball/algorithms/english.sbl +52 -37
- data/vendor/snowball/algorithms/esperanto.sbl +157 -0
- data/vendor/snowball/algorithms/estonian.sbl +269 -0
- data/vendor/snowball/algorithms/finnish.sbl +2 -3
- data/vendor/snowball/algorithms/french.sbl +42 -16
- data/vendor/snowball/algorithms/german.sbl +35 -14
- data/vendor/snowball/algorithms/greek.sbl +76 -76
- data/vendor/snowball/algorithms/hungarian.sbl +8 -6
- data/vendor/snowball/algorithms/indonesian.sbl +14 -8
- data/vendor/snowball/algorithms/italian.sbl +11 -21
- data/vendor/snowball/algorithms/lithuanian.sbl +36 -37
- data/vendor/snowball/algorithms/lovins.sbl +0 -1
- data/vendor/snowball/algorithms/nepali.sbl +138 -37
- data/vendor/snowball/algorithms/norwegian.sbl +19 -5
- data/vendor/snowball/algorithms/porter.sbl +2 -2
- data/vendor/snowball/algorithms/portuguese.sbl +9 -13
- data/vendor/snowball/algorithms/romanian.sbl +17 -4
- data/vendor/snowball/algorithms/serbian.sbl +467 -468
- data/vendor/snowball/algorithms/spanish.sbl +5 -7
- data/vendor/snowball/algorithms/swedish.sbl +60 -6
- data/vendor/snowball/algorithms/tamil.sbl +207 -176
- data/vendor/snowball/algorithms/turkish.sbl +461 -445
- data/vendor/snowball/algorithms/yiddish.sbl +36 -38
- data/vendor/snowball/compiler/analyser.c +445 -192
- data/vendor/snowball/compiler/driver.c +109 -101
- data/vendor/snowball/compiler/generator.c +853 -464
- data/vendor/snowball/compiler/generator_ada.c +404 -366
- data/vendor/snowball/compiler/generator_csharp.c +297 -260
- data/vendor/snowball/compiler/generator_go.c +323 -254
- data/vendor/snowball/compiler/generator_java.c +326 -252
- data/vendor/snowball/compiler/generator_js.c +362 -252
- data/vendor/snowball/compiler/generator_pascal.c +349 -197
- data/vendor/snowball/compiler/generator_python.c +257 -240
- data/vendor/snowball/compiler/generator_rust.c +423 -251
- data/vendor/snowball/compiler/header.h +117 -71
- data/vendor/snowball/compiler/space.c +137 -68
- data/vendor/snowball/compiler/syswords.h +2 -2
- data/vendor/snowball/compiler/tokeniser.c +125 -107
- data/vendor/snowball/csharp/Snowball/Among.cs +14 -14
- data/vendor/snowball/csharp/Snowball/AssemblyInfo.cs +7 -7
- data/vendor/snowball/csharp/Snowball/Stemmer.cs +57 -37
- data/vendor/snowball/csharp/Stemwords/App.config +2 -2
- data/vendor/snowball/csharp/Stemwords/Program.cs +16 -12
- data/vendor/snowball/doc/libstemmer_c_README +7 -4
- data/vendor/snowball/doc/libstemmer_csharp_README +4 -1
- data/vendor/snowball/doc/libstemmer_java_README +12 -1
- data/vendor/snowball/doc/libstemmer_js_README +6 -4
- data/vendor/snowball/doc/libstemmer_python_README +9 -4
- data/vendor/snowball/examples/stemwords.c +12 -12
- data/vendor/snowball/go/env.go +107 -31
- data/vendor/snowball/go/util.go +0 -4
- data/vendor/snowball/include/libstemmer.h +4 -0
- data/vendor/snowball/java/org/tartarus/snowball/Among.java +32 -15
- data/vendor/snowball/java/org/tartarus/snowball/SnowballProgram.java +347 -261
- data/vendor/snowball/java/org/tartarus/snowball/SnowballStemmer.java +3 -0
- data/vendor/snowball/java/org/tartarus/snowball/TestApp.java +52 -37
- data/vendor/snowball/javascript/base-stemmer.js +186 -2
- data/vendor/snowball/javascript/stemwords.js +3 -6
- data/vendor/snowball/libstemmer/libstemmer_c.in +1 -1
- data/vendor/snowball/libstemmer/mkalgorithms.pl +6 -6
- data/vendor/snowball/libstemmer/mkmodules.pl +2 -2
- data/vendor/snowball/libstemmer/modules.txt +13 -10
- data/vendor/snowball/libstemmer/test.c +1 -1
- data/vendor/snowball/pascal/SnowballProgram.pas +84 -2
- data/vendor/snowball/pascal/generate.pl +13 -13
- data/vendor/snowball/python/create_init.py +4 -1
- data/vendor/snowball/python/setup.cfg +0 -3
- data/vendor/snowball/python/setup.py +8 -3
- data/vendor/snowball/python/snowballstemmer/basestemmer.py +20 -54
- data/vendor/snowball/python/stemwords.py +8 -12
- data/vendor/snowball/runtime/api.c +10 -5
- data/vendor/snowball/runtime/header.h +10 -9
- data/vendor/snowball/runtime/utilities.c +9 -9
- data/vendor/snowball/rust/build.rs +1 -1
- data/vendor/snowball/rust/src/snowball/snowball_env.rs +83 -5
- data/vendor/snowball/tests/stemtest.c +7 -4
- metadata +7 -7
- data/vendor/snowball/.travis.yml +0 -112
- data/vendor/snowball/algorithms/german2.sbl +0 -145
- data/vendor/snowball/algorithms/kraaij_pohlmann.sbl +0 -240
- data/vendor/snowball/compiler/syswords2.h +0 -13
|
@@ -1,240 +0,0 @@
|
|
|
1
|
-
strings ( ch )
|
|
2
|
-
integers ( p1 p2 )
|
|
3
|
-
booleans ( Y_found stemmed GE_removed )
|
|
4
|
-
|
|
5
|
-
routines (
|
|
6
|
-
|
|
7
|
-
R1 R2
|
|
8
|
-
C V VX
|
|
9
|
-
lengthen_V
|
|
10
|
-
Step_1 Step_2 Step_3 Step_4 Step_7
|
|
11
|
-
Step_6 Step_1c
|
|
12
|
-
Lose_prefix
|
|
13
|
-
Lose_infix
|
|
14
|
-
measure
|
|
15
|
-
)
|
|
16
|
-
|
|
17
|
-
externals ( stem )
|
|
18
|
-
|
|
19
|
-
groupings ( v v_WX AOU AIOU )
|
|
20
|
-
|
|
21
|
-
stringescapes {}
|
|
22
|
-
|
|
23
|
-
define v 'aeiouy'
|
|
24
|
-
define v_WX v + 'wx'
|
|
25
|
-
define AOU 'aou'
|
|
26
|
-
define AIOU 'aiou'
|
|
27
|
-
|
|
28
|
-
backwardmode (
|
|
29
|
-
|
|
30
|
-
define R1 as ($p1 <= cursor)
|
|
31
|
-
define R2 as ($p2 <= cursor)
|
|
32
|
-
|
|
33
|
-
define V as test (v or 'ij')
|
|
34
|
-
define VX as test (next v or 'ij')
|
|
35
|
-
define C as test (not 'ij' non-v)
|
|
36
|
-
|
|
37
|
-
define lengthen_V as do (
|
|
38
|
-
non-v_WX [ (AOU] test (non-v or atlimit)) or
|
|
39
|
-
('e'] test (non-v or atlimit
|
|
40
|
-
not AIOU
|
|
41
|
-
not (next AIOU non-v)))
|
|
42
|
-
->ch insert ch
|
|
43
|
-
)
|
|
44
|
-
|
|
45
|
-
define Step_1 as
|
|
46
|
-
(
|
|
47
|
-
[substring] among (
|
|
48
|
-
|
|
49
|
-
'{'}s' (delete)
|
|
50
|
-
's' (R1 not ('t' R1) C delete)
|
|
51
|
-
'ies' (R1 <-'ie')
|
|
52
|
-
'es'
|
|
53
|
-
(('ar' R1 C ] delete lengthen_V) or
|
|
54
|
-
('er' R1 C ] delete) or
|
|
55
|
-
(R1 C <-'e'))
|
|
56
|
-
|
|
57
|
-
'aus' (R1 V <-'au')
|
|
58
|
-
'en' (('hed' R1 ] <-'heid') or
|
|
59
|
-
('nd' delete) or
|
|
60
|
-
('d' R1 C ] delete) or
|
|
61
|
-
('i' or 'j' V delete) or
|
|
62
|
-
(R1 C delete lengthen_V))
|
|
63
|
-
'nde' (<-'nd')
|
|
64
|
-
)
|
|
65
|
-
)
|
|
66
|
-
|
|
67
|
-
define Step_2 as
|
|
68
|
-
(
|
|
69
|
-
[substring] among (
|
|
70
|
-
'je' (('{'}t' ] delete) or
|
|
71
|
-
('et' ] R1 C delete) or
|
|
72
|
-
('rnt' ] <-'rn') or
|
|
73
|
-
('t' ] R1 VX delete) or
|
|
74
|
-
('ink' ] <-'ing') or
|
|
75
|
-
('mp' ] <-'m') or
|
|
76
|
-
('{'}' ] R1 delete) or
|
|
77
|
-
(] R1 C delete))
|
|
78
|
-
'ge' (R1 <-'g')
|
|
79
|
-
'lijke'(R1 <-'lijk')
|
|
80
|
-
'ische'(R1 <-'isch')
|
|
81
|
-
'de' (R1 C delete)
|
|
82
|
-
'te' (R1 <-'t')
|
|
83
|
-
'se' (R1 <-'s')
|
|
84
|
-
're' (R1 <-'r')
|
|
85
|
-
'le' (R1 delete attach 'l' lengthen_V)
|
|
86
|
-
'ene' (R1 C delete attach 'en' lengthen_V)
|
|
87
|
-
'ieve' (R1 C <-'ief')
|
|
88
|
-
)
|
|
89
|
-
)
|
|
90
|
-
|
|
91
|
-
define Step_3 as
|
|
92
|
-
(
|
|
93
|
-
[substring] among (
|
|
94
|
-
'atie' (R1 <-'eer')
|
|
95
|
-
'iteit' (R1 delete lengthen_V)
|
|
96
|
-
'heid'
|
|
97
|
-
'sel'
|
|
98
|
-
'ster' (R1 delete)
|
|
99
|
-
'rder' (<-'r')
|
|
100
|
-
'ing'
|
|
101
|
-
'isme'
|
|
102
|
-
'erij' (R1 delete lengthen_V)
|
|
103
|
-
'arij' (R1 C <-'aar')
|
|
104
|
-
'fie' (R2 delete attach 'f' lengthen_V)
|
|
105
|
-
'gie' (R2 delete attach 'g' lengthen_V)
|
|
106
|
-
'tst' (R1 C <-'t')
|
|
107
|
-
'dst' (R1 C <-'d')
|
|
108
|
-
)
|
|
109
|
-
)
|
|
110
|
-
|
|
111
|
-
define Step_4 as
|
|
112
|
-
(
|
|
113
|
-
( [substring] among (
|
|
114
|
-
'ioneel' (R1 <-'ie')
|
|
115
|
-
'atief' (R1 <-'eer')
|
|
116
|
-
'baar' (R1 delete)
|
|
117
|
-
'naar' (R1 V <-'n')
|
|
118
|
-
'laar' (R1 V <-'l')
|
|
119
|
-
'raar' (R1 V <-'r')
|
|
120
|
-
'tant' (R1 <-'teer')
|
|
121
|
-
'lijker'
|
|
122
|
-
'lijkst' (R1 <-'lijk')
|
|
123
|
-
'achtig'
|
|
124
|
-
'achtiger'
|
|
125
|
-
'achtigst'(R1 delete)
|
|
126
|
-
'eriger'
|
|
127
|
-
'erigst'
|
|
128
|
-
'erig'
|
|
129
|
-
'end' (R1 C delete lengthen_V)
|
|
130
|
-
)
|
|
131
|
-
)
|
|
132
|
-
or
|
|
133
|
-
( [substring] among (
|
|
134
|
-
'iger'
|
|
135
|
-
'igst'
|
|
136
|
-
'ig' (R1 C delete lengthen_V)
|
|
137
|
-
)
|
|
138
|
-
)
|
|
139
|
-
)
|
|
140
|
-
|
|
141
|
-
define Step_7 as
|
|
142
|
-
(
|
|
143
|
-
[substring] among (
|
|
144
|
-
'kt' (<-'k')
|
|
145
|
-
'ft' (<-'f')
|
|
146
|
-
'pt' (<-'p')
|
|
147
|
-
)
|
|
148
|
-
)
|
|
149
|
-
|
|
150
|
-
define Step_6 as
|
|
151
|
-
(
|
|
152
|
-
[substring] among (
|
|
153
|
-
'bb' (<-'b')
|
|
154
|
-
'cc' (<-'c')
|
|
155
|
-
'dd' (<-'d')
|
|
156
|
-
'ff' (<-'f')
|
|
157
|
-
'gg' (<-'g')
|
|
158
|
-
'hh' (<-'h')
|
|
159
|
-
'jj' (<-'j')
|
|
160
|
-
'kk' (<-'k')
|
|
161
|
-
'll' (<-'l')
|
|
162
|
-
'mm' (<-'m')
|
|
163
|
-
'nn' (<-'n')
|
|
164
|
-
'pp' (<-'p')
|
|
165
|
-
'qq' (<-'q')
|
|
166
|
-
'rr' (<-'r')
|
|
167
|
-
'ss' (<-'s')
|
|
168
|
-
'tt' (<-'t')
|
|
169
|
-
'vv' (<-'v')
|
|
170
|
-
'ww' (<-'w')
|
|
171
|
-
'xx' (<-'x')
|
|
172
|
-
'zz' (<-'z')
|
|
173
|
-
'v' (<-'f')
|
|
174
|
-
'z' (<-'s')
|
|
175
|
-
)
|
|
176
|
-
)
|
|
177
|
-
|
|
178
|
-
define Step_1c as
|
|
179
|
-
(
|
|
180
|
-
[substring] among ( (R1 C)
|
|
181
|
-
'd' (not ('n' R1) delete)
|
|
182
|
-
't' (not ('h' R1) delete)
|
|
183
|
-
)
|
|
184
|
-
)
|
|
185
|
-
)
|
|
186
|
-
|
|
187
|
-
define Lose_prefix as (
|
|
188
|
-
['ge'] test hop 3 (goto v goto non-v)
|
|
189
|
-
set GE_removed
|
|
190
|
-
delete
|
|
191
|
-
)
|
|
192
|
-
|
|
193
|
-
define Lose_infix as (
|
|
194
|
-
next
|
|
195
|
-
gopast (['ge']) test hop 3 (goto v goto non-v)
|
|
196
|
-
set GE_removed
|
|
197
|
-
delete
|
|
198
|
-
)
|
|
199
|
-
|
|
200
|
-
define measure as (
|
|
201
|
-
$p1 = limit
|
|
202
|
-
$p2 = limit
|
|
203
|
-
do(
|
|
204
|
-
repeat non-v atleast 1 ('ij' or v) non-v setmark p1
|
|
205
|
-
repeat non-v atleast 1 ('ij' or v) non-v setmark p2
|
|
206
|
-
)
|
|
207
|
-
|
|
208
|
-
)
|
|
209
|
-
define stem as (
|
|
210
|
-
|
|
211
|
-
unset Y_found
|
|
212
|
-
unset stemmed
|
|
213
|
-
do ( ['y'] <-'Y' set Y_found )
|
|
214
|
-
do repeat(goto (v ['y'])<-'Y' set Y_found )
|
|
215
|
-
|
|
216
|
-
measure
|
|
217
|
-
|
|
218
|
-
backwards (
|
|
219
|
-
do (Step_1 set stemmed )
|
|
220
|
-
do (Step_2 set stemmed )
|
|
221
|
-
do (Step_3 set stemmed )
|
|
222
|
-
do (Step_4 set stemmed )
|
|
223
|
-
)
|
|
224
|
-
unset GE_removed
|
|
225
|
-
do (Lose_prefix and measure)
|
|
226
|
-
backwards (
|
|
227
|
-
do (GE_removed Step_1c)
|
|
228
|
-
)
|
|
229
|
-
unset GE_removed
|
|
230
|
-
do (Lose_infix and measure)
|
|
231
|
-
backwards (
|
|
232
|
-
do (GE_removed Step_1c)
|
|
233
|
-
)
|
|
234
|
-
backwards (
|
|
235
|
-
do (Step_7 set stemmed )
|
|
236
|
-
do (stemmed or GE_removed Step_6)
|
|
237
|
-
)
|
|
238
|
-
do(Y_found repeat(goto (['Y']) <-'y'))
|
|
239
|
-
)
|
|
240
|
-
|
|
@@ -1,13 +0,0 @@
|
|
|
1
|
-
c_among = 4, c_and, c_as, c_assign, c_assignto, c_atleast,
|
|
2
|
-
c_atlimit, c_atmark, c_attach, c_backwardmode, c_backwards,
|
|
3
|
-
c_booleans, c_bra, c_comment1, c_comment2, c_cursor, c_debug,
|
|
4
|
-
c_decimal, c_define, c_delete, c_divide, c_divideassign, c_do,
|
|
5
|
-
c_dollar, c_eq, c_externals, c_fail, c_false, c_for, c_ge, c_get,
|
|
6
|
-
c_gopast, c_goto, c_gr, c_groupings, c_hex, c_hop, c_insert,
|
|
7
|
-
c_integers, c_ket, c_le, c_leftslice, c_len, c_lenof, c_limit, c_loop,
|
|
8
|
-
c_ls, c_maxint, c_minint, c_minus, c_minusassign, c_multiply,
|
|
9
|
-
c_multiplyassign, c_ne, c_next, c_non, c_not, c_or, c_plus,
|
|
10
|
-
c_plusassign, c_repeat, c_reverse, c_rightslice, c_routines,
|
|
11
|
-
c_set, c_setlimit, c_setmark, c_size, c_sizeof, c_slicefrom,
|
|
12
|
-
c_sliceto, c_stringdef, c_stringescapes, c_strings, c_substring,
|
|
13
|
-
c_test, c_tolimit, c_tomark, c_true, c_try, c_unset,
|