mittens 0.1.1 → 0.3.0
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/LICENSE.txt +1 -1
- data/README.md +4 -4
- data/lib/mittens/version.rb +1 -1
- data/mittens.gemspec +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 +8 -12
- 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
@@ -1,4 +1,5 @@
|
|
1
1
|
routines (
|
2
|
+
elisions
|
2
3
|
prelude postlude mark_regions
|
3
4
|
RV R1 R2
|
4
5
|
standard_suffix
|
@@ -13,7 +14,7 @@ externals ( stem )
|
|
13
14
|
|
14
15
|
integers ( pV p1 p2 )
|
15
16
|
|
16
|
-
groupings ( v keep_with_s )
|
17
|
+
groupings ( elision_char v keep_with_s oux_ending )
|
17
18
|
|
18
19
|
stringescapes {}
|
19
20
|
|
@@ -21,7 +22,7 @@ stringescapes {}
|
|
21
22
|
|
22
23
|
stringdef a^ '{U+00E2}' // a-circumflex
|
23
24
|
stringdef a` '{U+00E0}' // a-grave
|
24
|
-
stringdef
|
25
|
+
stringdef cc '{U+00E7}' // c-cedilla
|
25
26
|
|
26
27
|
stringdef e" '{U+00EB}' // e-diaeresis (rare)
|
27
28
|
stringdef e' '{U+00E9}' // e-acute
|
@@ -35,6 +36,17 @@ stringdef u` '{U+00F9}' // u-grave
|
|
35
36
|
|
36
37
|
define v 'aeiouy{a^}{a`}{e"}{e'}{e^}{e`}{i"}{i^}{o^}{u^}{u`}'
|
37
38
|
|
39
|
+
// Replace -oux with -ou if preceded by one of these letters.
|
40
|
+
define oux_ending 'bhjlnp'
|
41
|
+
|
42
|
+
// Single character elisions
|
43
|
+
define elision_char 'cdjlmnst'
|
44
|
+
|
45
|
+
define elisions as
|
46
|
+
(
|
47
|
+
[ (elision_char or 'qu') '{'}' ] not atlimit delete
|
48
|
+
)
|
49
|
+
|
38
50
|
define prelude as repeat goto (
|
39
51
|
|
40
52
|
( v [ ('u' ] v <- 'U') or
|
@@ -60,10 +72,12 @@ define mark_regions as (
|
|
60
72
|
do (
|
61
73
|
( v v next )
|
62
74
|
or
|
63
|
-
among ( //
|
64
|
-
'par'
|
65
|
-
'col'
|
66
|
-
'tap'
|
75
|
+
among ( // Exception list:
|
76
|
+
'par' // paris, parie, pari
|
77
|
+
'col' // colis
|
78
|
+
'tap' // tapis
|
79
|
+
()
|
80
|
+
'ni' (v) // niais/nierais/nié/niâmes/nièrent
|
67
81
|
// extensions possible here
|
68
82
|
)
|
69
83
|
or
|
@@ -125,8 +139,8 @@ backwardmode (
|
|
125
139
|
'eus' ((R2 delete) or (R1<-'eux'))
|
126
140
|
'abl' 'iqU'
|
127
141
|
(R2 delete)
|
128
|
-
'i{e`}r' 'I{e`}r'
|
129
|
-
(RV <-'i')
|
142
|
+
'i{e`}r' 'I{e`}r'
|
143
|
+
(RV <-'i')
|
130
144
|
)
|
131
145
|
)
|
132
146
|
)
|
@@ -150,6 +164,7 @@ backwardmode (
|
|
150
164
|
)
|
151
165
|
'eaux' (<- 'eau')
|
152
166
|
'aux' (R1 <- 'al')
|
167
|
+
'oux' (oux_ending <- 'ou')
|
153
168
|
'euse'
|
154
169
|
'euses'((R2 delete) or (R1<-'eux'))
|
155
170
|
|
@@ -178,8 +193,9 @@ backwardmode (
|
|
178
193
|
)
|
179
194
|
)
|
180
195
|
|
181
|
-
define verb_suffix as
|
182
|
-
[substring]
|
196
|
+
define verb_suffix as (
|
197
|
+
setlimit tomark pV for ([substring])
|
198
|
+
among (
|
183
199
|
'ions'
|
184
200
|
(R2 delete)
|
185
201
|
|
@@ -191,12 +207,22 @@ backwardmode (
|
|
191
207
|
|
192
208
|
(delete)
|
193
209
|
|
194
|
-
'{a^}mes' '{a^}t' '{a^}tes' 'a' 'ai' 'aIent' '
|
210
|
+
'{a^}mes' '{a^}t' '{a^}tes' 'a' 'ai' 'aIent' 'ait' 'ant'
|
195
211
|
'ante' 'antes' 'ants' 'as' 'asse' 'assent' 'asses' 'assiez'
|
196
212
|
'assions'
|
197
|
-
(delete
|
198
|
-
|
199
|
-
|
213
|
+
( try('e' RV]) delete )
|
214
|
+
|
215
|
+
'ais' 'aise' 'aises'
|
216
|
+
( not among (
|
217
|
+
'al' // balais, calais, galais, malais, palais, valais
|
218
|
+
(next atlimit)
|
219
|
+
'auv' // mauvais
|
220
|
+
'{e'}pl' // déplais
|
221
|
+
()
|
222
|
+
)
|
223
|
+
delete )
|
224
|
+
'eais'
|
225
|
+
(delete)
|
200
226
|
)
|
201
227
|
)
|
202
228
|
|
@@ -226,6 +252,7 @@ backwardmode (
|
|
226
252
|
|
227
253
|
define stem as (
|
228
254
|
|
255
|
+
do elisions
|
229
256
|
do prelude
|
230
257
|
do mark_regions
|
231
258
|
backwards (
|
@@ -238,7 +265,7 @@ define stem as (
|
|
238
265
|
)
|
239
266
|
and
|
240
267
|
try( [ ('Y' ] <- 'i' ) or
|
241
|
-
('{
|
268
|
+
('{cc}'] <- 'c' )
|
242
269
|
)
|
243
270
|
) or
|
244
271
|
residual_suffix
|
@@ -251,4 +278,3 @@ define stem as (
|
|
251
278
|
)
|
252
279
|
do postlude
|
253
280
|
)
|
254
|
-
|
@@ -1,8 +1,3 @@
|
|
1
|
-
|
2
|
-
/*
|
3
|
-
Extra rule for -nisse ending added 11 Dec 2009
|
4
|
-
*/
|
5
|
-
|
6
1
|
routines (
|
7
2
|
prelude postlude
|
8
3
|
mark_regions
|
@@ -14,7 +9,7 @@ externals ( stem )
|
|
14
9
|
|
15
10
|
integers ( p1 p2 x )
|
16
11
|
|
17
|
-
groupings ( v s_ending st_ending )
|
12
|
+
groupings ( v et_ending s_ending st_ending )
|
18
13
|
|
19
14
|
stringescapes {}
|
20
15
|
|
@@ -27,21 +22,28 @@ stringdef ss '{U+00DF}'
|
|
27
22
|
|
28
23
|
define v 'aeiouy{a"}{o"}{u"}'
|
29
24
|
|
25
|
+
define et_ending 'dfgklmnrstUz{a"}'
|
30
26
|
define s_ending 'bdfghklmnrt'
|
31
27
|
define st_ending s_ending - 'r'
|
32
28
|
|
33
29
|
define prelude as (
|
34
30
|
|
35
|
-
test repeat (
|
36
|
-
(
|
37
|
-
['{ss}'] <- 'ss'
|
38
|
-
) or next
|
39
|
-
)
|
40
|
-
|
41
|
-
repeat goto (
|
31
|
+
test repeat goto (
|
42
32
|
v [('u'] v <- 'U') or
|
43
33
|
('y'] v <- 'Y')
|
44
34
|
)
|
35
|
+
|
36
|
+
repeat (
|
37
|
+
[substring] among(
|
38
|
+
'{ss}' (<- 'ss')
|
39
|
+
'ae' (<- '{a"}')
|
40
|
+
'oe' (<- '{o"}')
|
41
|
+
'ue' (<- '{u"}')
|
42
|
+
'qu' ()
|
43
|
+
'' (next)
|
44
|
+
)
|
45
|
+
)
|
46
|
+
|
45
47
|
)
|
46
48
|
|
47
49
|
define mark_regions as (
|
@@ -78,7 +80,12 @@ backwardmode (
|
|
78
80
|
define standard_suffix as (
|
79
81
|
do (
|
80
82
|
[substring] R1 among(
|
81
|
-
'em'
|
83
|
+
'em'
|
84
|
+
( not 'syst' // don't remove -em from words ending -system
|
85
|
+
delete
|
86
|
+
)
|
87
|
+
'ern' 'er'
|
88
|
+
'erin' 'erinnen' // conflate female versions of nouns
|
82
89
|
( delete
|
83
90
|
)
|
84
91
|
'e' 'en' 'es'
|
@@ -88,6 +95,9 @@ backwardmode (
|
|
88
95
|
's'
|
89
96
|
( s_ending delete
|
90
97
|
)
|
98
|
+
'ln' 'lns'
|
99
|
+
( <- 'l'
|
100
|
+
)
|
91
101
|
)
|
92
102
|
)
|
93
103
|
do (
|
@@ -98,6 +108,17 @@ backwardmode (
|
|
98
108
|
'st'
|
99
109
|
( st_ending hop 3 delete
|
100
110
|
)
|
111
|
+
'et'
|
112
|
+
( test et_ending
|
113
|
+
not among (
|
114
|
+
'geordn' // Still conflate untergeordnet/untergeordnetere, etc.
|
115
|
+
'intern' // Don't conflate Internet and internes.
|
116
|
+
'plan' // Don't conflate Plan and Planet.
|
117
|
+
'tick' // Don't conflate Tick and Ticket.
|
118
|
+
'tr' // Still conflate Vertreter/Vertretung, etc.
|
119
|
+
)
|
120
|
+
delete
|
121
|
+
)
|
101
122
|
)
|
102
123
|
)
|
103
124
|
do (
|
@@ -6,7 +6,7 @@
|
|
6
6
|
//
|
7
7
|
// Saroukos, Spyridon. Enhancing a Greek language stemmer.
|
8
8
|
// University of Tampere, 2008.
|
9
|
-
// https://
|
9
|
+
// https://trepo.tuni.fi/bitstream/handle/10024/80480/gradu03463.pdf
|
10
10
|
|
11
11
|
stringescapes {}
|
12
12
|
|
@@ -20,7 +20,7 @@ stringdef i '{U+03B7}' // eta
|
|
20
20
|
stringdef th '{U+03B8}' // theta
|
21
21
|
stringdef y '{U+03B9}' // iota
|
22
22
|
stringdef k '{U+03BA}' // kappa
|
23
|
-
stringdef l '{U+03BB}' //
|
23
|
+
stringdef l '{U+03BB}' // lambda
|
24
24
|
stringdef m '{U+03BC}' // mu
|
25
25
|
stringdef n '{U+03BD}' // nu
|
26
26
|
stringdef x '{U+03BE}' // xi
|
@@ -46,7 +46,7 @@ stringdef I '{U+0397}' // Eta
|
|
46
46
|
stringdef Th '{U+0398}' // Theta
|
47
47
|
stringdef Y '{U+0399}' // Iota
|
48
48
|
stringdef K '{U+039A}' // Kappa
|
49
|
-
stringdef L '{U+039B}' //
|
49
|
+
stringdef L '{U+039B}' // Lambda
|
50
50
|
stringdef M '{U+039C}' // Mu
|
51
51
|
stringdef N '{U+039D}' // Nu
|
52
52
|
stringdef X '{U+039E}' // Xi
|
@@ -93,13 +93,13 @@ booleans ( test1 )
|
|
93
93
|
groupings ( v v2 )
|
94
94
|
|
95
95
|
routines ( tolower has_min_length
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
96
|
+
step_s1 step_s2 step_s3 step_s4 step_s5 step_s6 step_s7
|
97
|
+
step_s8 step_s9 step_s10
|
98
|
+
step_1 step_2a step_2b step_2c step_2d step_3 step_4
|
99
|
+
step_5a step_5b step_5c step_5d step_5e step_5f
|
100
|
+
step_5g step_5h step_5i
|
101
|
+
step_5j step_5k step_5l step_5m
|
102
|
+
step_6 step_7 )
|
103
103
|
|
104
104
|
define v '{a}{e}{i}{y}{o}{u}{oo}'
|
105
105
|
define v2 '{a}{e}{i}{y}{o}{oo}'
|
@@ -162,7 +162,7 @@ backwardmode (
|
|
162
162
|
)
|
163
163
|
)
|
164
164
|
|
165
|
-
define
|
165
|
+
define step_1 as (
|
166
166
|
[substring] among (
|
167
167
|
'{f}{a}{g}{y}{a}' '{f}{a}{g}{y}{o}{u}' '{f}{a}{g}{y}{oo}{n}' (<- '{f}{a}')
|
168
168
|
'{s}{k}{a}{g}{y}{a}' '{s}{k}{a}{g}{y}{o}{u}' '{s}{k}{a}{g}{y}{oo}{n}' (<- '{s}{k}{a}')
|
@@ -179,7 +179,7 @@ backwardmode (
|
|
179
179
|
unset test1
|
180
180
|
)
|
181
181
|
|
182
|
-
define
|
182
|
+
define step_s1 as (
|
183
183
|
[substring] among (
|
184
184
|
'{y}{z}{a}' '{y}{z}{e}{s}' '{y}{z}{e}' '{y}{z}{a}{m}{e}' '{y}{z}{a}{t}{e}' '{y}{z}{a}{n}' '{y}{z}{a}{n}{e}' '{y}{z}{oo}' '{y}{z}{e}{y}{s}' '{y}{z}{e}{y}'
|
185
185
|
'{y}{z}{o}{u}{m}{e}' '{y}{z}{e}{t}{e}' '{y}{z}{o}{u}{n}' '{y}{z}{o}{u}{n}{e}' (
|
@@ -197,7 +197,7 @@ backwardmode (
|
|
197
197
|
)
|
198
198
|
)
|
199
199
|
|
200
|
-
define
|
200
|
+
define step_s2 as (
|
201
201
|
[substring] among (
|
202
202
|
'{oo}{th}{i}{k}{a}' '{oo}{th}{i}{k}{e}{s}' '{oo}{th}{i}{k}{e}' '{oo}{th}{i}{k}{a}{m}{e}' '{oo}{th}{i}{k}{a}{t}{e}' '{oo}{th}{i}{k}{a}{n}' '{oo}{th}{i}{k}{a}{n}{e}' (
|
203
203
|
delete
|
@@ -209,12 +209,12 @@ backwardmode (
|
|
209
209
|
)
|
210
210
|
)
|
211
211
|
|
212
|
-
define
|
212
|
+
define step_s3 as (
|
213
|
+
(['{y}{s}{a}'] atlimit <- '{y}{s}') or
|
213
214
|
[substring] among (
|
214
215
|
'{y}{s}{a}' '{y}{s}{e}{s}' '{y}{s}{e}' '{y}{s}{a}{m}{e}' '{y}{s}{a}{t}{e}' '{y}{s}{a}{n}' '{y}{s}{a}{n}{e}' (
|
215
216
|
delete
|
216
217
|
unset test1
|
217
|
-
('{y}{s}{a}' atlimit <- '{y}{s}') or
|
218
218
|
([] substring atlimit among (
|
219
219
|
'{a}{n}{a}{m}{p}{a}' '{a}{th}{r}{o}' '{e}{m}{p}{a}' '{e}{s}{e}' '{e}{s}{oo}{k}{l}{e}' '{e}{p}{a}' '{x}{a}{n}{a}{p}{a}' '{e}{p}{e}' '{p}{e}{r}{y}{p}{a}'
|
220
220
|
'{s}{u}{n}{a}{th}{r}{o}' '{d}{a}{n}{e}' '{k}{l}{e}' '{ch}{a}{r}{t}{o}{p}{a}' '{e}{x}{a}{r}{ch}{a}' '{m}{e}{t}{e}{p}{e}' '{a}{p}{o}{k}{l}{e}'
|
@@ -228,7 +228,7 @@ backwardmode (
|
|
228
228
|
)
|
229
229
|
)
|
230
230
|
|
231
|
-
define
|
231
|
+
define step_s4 as (
|
232
232
|
[substring] among (
|
233
233
|
'{y}{s}{oo}' '{y}{s}{e}{y}{s}' '{y}{s}{e}{y}' '{y}{s}{o}{u}{m}{e}' '{y}{s}{e}{t}{e}' '{y}{s}{o}{u}{n}' '{y}{s}{o}{u}{n}{e}' (
|
234
234
|
delete
|
@@ -243,7 +243,7 @@ backwardmode (
|
|
243
243
|
)
|
244
244
|
)
|
245
245
|
|
246
|
-
define
|
246
|
+
define step_s5 as (
|
247
247
|
[substring] among (
|
248
248
|
'{y}{s}{t}{o}{s}' '{y}{s}{t}{o}{u}' '{y}{s}{t}{o}' '{y}{s}{t}{e}' '{y}{s}{t}{o}{y}' '{y}{s}{t}{oo}{n}' '{y}{s}{t}{o}{u}{s}' '{y}{s}{t}{i}' '{y}{s}{t}{i}{s}'
|
249
249
|
'{y}{s}{t}{a}' '{y}{s}{t}{e}{s}' (
|
@@ -261,7 +261,7 @@ backwardmode (
|
|
261
261
|
)
|
262
262
|
)
|
263
263
|
|
264
|
-
define
|
264
|
+
define step_s6 as (
|
265
265
|
[substring] among (
|
266
266
|
'{y}{s}{m}{o}' '{y}{s}{m}{o}{y}' '{y}{s}{m}{o}{s}' '{y}{s}{m}{o}{u}' '{y}{s}{m}{o}{u}{s}' '{y}{s}{m}{oo}{n}' (
|
267
267
|
delete
|
@@ -288,7 +288,7 @@ backwardmode (
|
|
288
288
|
)
|
289
289
|
)
|
290
290
|
|
291
|
-
define
|
291
|
+
define step_s7 as (
|
292
292
|
[substring] among (
|
293
293
|
'{a}{r}{a}{k}{y}' '{a}{r}{a}{k}{y}{a}' '{o}{u}{d}{a}{k}{y}' '{o}{u}{d}{a}{k}{y}{a}' (
|
294
294
|
delete
|
@@ -301,7 +301,7 @@ backwardmode (
|
|
301
301
|
)
|
302
302
|
)
|
303
303
|
|
304
|
-
define
|
304
|
+
define step_s8 as (
|
305
305
|
[substring] among (
|
306
306
|
'{a}{k}{y}' '{a}{k}{y}{a}' '{y}{t}{s}{a}' '{y}{t}{s}{a}{s}' '{y}{t}{s}{e}{s}' '{y}{t}{s}{oo}{n}' '{a}{r}{a}{k}{y}' '{a}{r}{a}{k}{y}{a}' (
|
307
307
|
delete
|
@@ -326,7 +326,7 @@ backwardmode (
|
|
326
326
|
)
|
327
327
|
)
|
328
328
|
|
329
|
-
define
|
329
|
+
define step_s9 as (
|
330
330
|
[substring] among (
|
331
331
|
'{y}{d}{y}{o}' '{y}{d}{y}{a}' '{y}{d}{y}{oo}{n}' (
|
332
332
|
delete
|
@@ -341,7 +341,7 @@ backwardmode (
|
|
341
341
|
)
|
342
342
|
)
|
343
343
|
|
344
|
-
define
|
344
|
+
define step_s10 as (
|
345
345
|
[substring] among (
|
346
346
|
'{y}{s}{k}{o}{s}' '{y}{s}{k}{o}{u}' '{y}{s}{k}{o}' '{y}{s}{k}{e}' (
|
347
347
|
delete
|
@@ -354,7 +354,7 @@ backwardmode (
|
|
354
354
|
)
|
355
355
|
)
|
356
356
|
|
357
|
-
define
|
357
|
+
define step_2a as (
|
358
358
|
[substring] among (
|
359
359
|
'{a}{d}{e}{s}' '{a}{d}{oo}{n}' (delete)
|
360
360
|
)
|
@@ -364,7 +364,7 @@ backwardmode (
|
|
364
364
|
insert '{a}{d}'
|
365
365
|
)
|
366
366
|
|
367
|
-
define
|
367
|
+
define step_2b as (
|
368
368
|
[substring] among (
|
369
369
|
'{e}{d}{e}{s}' '{e}{d}{oo}{n}' (delete)
|
370
370
|
)
|
@@ -373,7 +373,7 @@ backwardmode (
|
|
373
373
|
)
|
374
374
|
)
|
375
375
|
|
376
|
-
define
|
376
|
+
define step_2c as (
|
377
377
|
[substring] among (
|
378
378
|
'{o}{u}{d}{e}{s}' '{o}{u}{d}{oo}{n}' (delete)
|
379
379
|
)
|
@@ -383,7 +383,7 @@ backwardmode (
|
|
383
383
|
)
|
384
384
|
)
|
385
385
|
|
386
|
-
define
|
386
|
+
define step_2d as (
|
387
387
|
[substring] among (
|
388
388
|
'{e}{oo}{s}' '{e}{oo}{n}' (delete unset test1)
|
389
389
|
)
|
@@ -392,14 +392,14 @@ backwardmode (
|
|
392
392
|
)
|
393
393
|
)
|
394
394
|
|
395
|
-
define
|
395
|
+
define step_3 as (
|
396
396
|
[substring] among (
|
397
397
|
'{y}{a}' '{y}{o}{u}' '{y}{oo}{n}' (delete unset test1)
|
398
398
|
)
|
399
399
|
([] v <- '{y}')
|
400
400
|
)
|
401
401
|
|
402
|
-
define
|
402
|
+
define step_4 as (
|
403
403
|
[substring] among (
|
404
404
|
'{y}{k}{a}' '{y}{k}{o}' '{y}{k}{o}{u}' '{y}{k}{oo}{n}' (delete unset test1)
|
405
405
|
)
|
@@ -413,8 +413,8 @@ backwardmode (
|
|
413
413
|
)
|
414
414
|
)
|
415
415
|
|
416
|
-
define
|
417
|
-
do ('{a}{g}{a}{m}{e}' atlimit <- '{a}{g}{a}{m}')
|
416
|
+
define step_5a as (
|
417
|
+
do (['{a}{g}{a}{m}{e}'] atlimit <- '{a}{g}{a}{m}')
|
418
418
|
do (
|
419
419
|
[substring] among (
|
420
420
|
'{a}{g}{a}{m}{e}' '{i}{s}{a}{m}{e}' '{o}{u}{s}{a}{m}{e}' '{i}{k}{a}{m}{e}' '{i}{th}{i}{k}{a}{m}{e}' (delete unset test1)
|
@@ -429,7 +429,7 @@ backwardmode (
|
|
429
429
|
)
|
430
430
|
)
|
431
431
|
|
432
|
-
define
|
432
|
+
define step_5b as (
|
433
433
|
do (
|
434
434
|
[substring] among (
|
435
435
|
'{a}{g}{a}{n}{e}' '{i}{s}{a}{n}{e}' '{o}{u}{s}{a}{n}{e}' '{y}{o}{n}{t}{a}{n}{e}' '{y}{o}{t}{a}{n}{e}' '{y}{o}{u}{n}{t}{a}{n}{e}' '{o}{n}{t}{a}{n}{e}' '{o}{t}{a}{n}{e}'
|
@@ -467,7 +467,7 @@ backwardmode (
|
|
467
467
|
)
|
468
468
|
)
|
469
469
|
|
470
|
-
define
|
470
|
+
define step_5c as (
|
471
471
|
do (
|
472
472
|
[substring] among (
|
473
473
|
'{i}{s}{e}{t}{e}' (delete unset test1)
|
@@ -491,7 +491,7 @@ backwardmode (
|
|
491
491
|
)
|
492
492
|
)
|
493
493
|
|
494
|
-
define
|
494
|
+
define step_5d as (
|
495
495
|
[substring] among (
|
496
496
|
'{o}{n}{t}{a}{s}' '{oo}{n}{t}{a}{s}' (
|
497
497
|
delete
|
@@ -502,7 +502,7 @@ backwardmode (
|
|
502
502
|
)
|
503
503
|
)
|
504
504
|
|
505
|
-
define
|
505
|
+
define step_5e as (
|
506
506
|
[substring] among (
|
507
507
|
'{o}{m}{a}{s}{t}{e}' '{y}{o}{m}{a}{s}{t}{e}' (
|
508
508
|
delete
|
@@ -512,7 +512,7 @@ backwardmode (
|
|
512
512
|
)
|
513
513
|
)
|
514
514
|
|
515
|
-
define
|
515
|
+
define step_5f as (
|
516
516
|
do (
|
517
517
|
['{y}{e}{s}{t}{e}']
|
518
518
|
delete
|
@@ -530,7 +530,7 @@ backwardmode (
|
|
530
530
|
)
|
531
531
|
)
|
532
532
|
|
533
|
-
define
|
533
|
+
define step_5g as (
|
534
534
|
do (
|
535
535
|
[substring] among (
|
536
536
|
'{i}{th}{i}{k}{a}' '{i}{th}{i}{k}{e}{s}' '{i}{th}{i}{k}{e}' (delete unset test1)
|
@@ -550,7 +550,7 @@ backwardmode (
|
|
550
550
|
)
|
551
551
|
)
|
552
552
|
|
553
|
-
define
|
553
|
+
define step_5h as (
|
554
554
|
[substring] among (
|
555
555
|
'{o}{u}{s}{a}' '{o}{u}{s}{e}{s}' '{o}{u}{s}{e}' (
|
556
556
|
delete
|
@@ -570,7 +570,7 @@ backwardmode (
|
|
570
570
|
)
|
571
571
|
)
|
572
572
|
|
573
|
-
define
|
573
|
+
define step_5i as (
|
574
574
|
[substring] among (
|
575
575
|
'{a}{g}{a}' '{a}{g}{e}{s}' '{a}{g}{e}' (
|
576
576
|
delete
|
@@ -594,7 +594,7 @@ backwardmode (
|
|
594
594
|
)
|
595
595
|
)
|
596
596
|
|
597
|
-
define
|
597
|
+
define step_5j as (
|
598
598
|
[substring] among (
|
599
599
|
'{i}{s}{e}' '{i}{s}{o}{u}' '{i}{s}{a}' (delete unset test1)
|
600
600
|
)
|
@@ -603,7 +603,7 @@ backwardmode (
|
|
603
603
|
)
|
604
604
|
)
|
605
605
|
|
606
|
-
define
|
606
|
+
define step_5k as (
|
607
607
|
[substring] among (
|
608
608
|
'{i}{s}{t}{e}' (delete unset test1)
|
609
609
|
)
|
@@ -613,7 +613,7 @@ backwardmode (
|
|
613
613
|
)
|
614
614
|
)
|
615
615
|
|
616
|
-
define
|
616
|
+
define step_5l as (
|
617
617
|
[substring] among (
|
618
618
|
'{o}{u}{n}{e}' '{i}{s}{o}{u}{n}{e}' '{i}{th}{o}{u}{n}{e}' (delete unset test1)
|
619
619
|
)
|
@@ -622,7 +622,7 @@ backwardmode (
|
|
622
622
|
)
|
623
623
|
)
|
624
624
|
|
625
|
-
define
|
625
|
+
define step_5m as (
|
626
626
|
[substring] among (
|
627
627
|
'{o}{u}{m}{e}' '{i}{s}{o}{u}{m}{e}' '{i}{th}{o}{u}{m}{e}' (delete unset test1)
|
628
628
|
)
|
@@ -632,7 +632,7 @@ backwardmode (
|
|
632
632
|
)
|
633
633
|
)
|
634
634
|
|
635
|
-
define
|
635
|
+
define step_6 as (
|
636
636
|
do (
|
637
637
|
[substring] among (
|
638
638
|
'{m}{a}{t}{a}' '{m}{a}{t}{oo}{n}' '{m}{a}{t}{o}{s}' (<- '{m}{a}')
|
@@ -653,7 +653,7 @@ backwardmode (
|
|
653
653
|
)
|
654
654
|
)
|
655
655
|
|
656
|
-
define
|
656
|
+
define step_7 as (
|
657
657
|
[substring] among (
|
658
658
|
'{e}{s}{t}{e}{r}' '{e}{s}{t}{a}{t}' '{o}{t}{e}{r}' '{o}{t}{a}{t}' '{u}{t}{e}{r}' '{u}{t}{a}{t}' '{oo}{t}{e}{r}' '{oo}{t}{a}{t}' (delete)
|
659
659
|
)
|
@@ -665,37 +665,37 @@ define stem as (
|
|
665
665
|
do tolower
|
666
666
|
has_min_length
|
667
667
|
set test1
|
668
|
-
do
|
669
|
-
do
|
670
|
-
do
|
671
|
-
do
|
672
|
-
do
|
673
|
-
do
|
674
|
-
do
|
675
|
-
do
|
676
|
-
do
|
677
|
-
do
|
678
|
-
do
|
679
|
-
do
|
680
|
-
do
|
681
|
-
do
|
682
|
-
do
|
683
|
-
do
|
684
|
-
do
|
685
|
-
do
|
686
|
-
do
|
687
|
-
do
|
688
|
-
do
|
689
|
-
do
|
690
|
-
do
|
691
|
-
do
|
692
|
-
do
|
693
|
-
do
|
694
|
-
do
|
695
|
-
do
|
696
|
-
do
|
697
|
-
do
|
698
|
-
do
|
699
|
-
do
|
668
|
+
do step_1
|
669
|
+
do step_s1
|
670
|
+
do step_s2
|
671
|
+
do step_s3
|
672
|
+
do step_s4
|
673
|
+
do step_s5
|
674
|
+
do step_s6
|
675
|
+
do step_s7
|
676
|
+
do step_s8
|
677
|
+
do step_s9
|
678
|
+
do step_s10
|
679
|
+
do step_2a
|
680
|
+
do step_2b
|
681
|
+
do step_2c
|
682
|
+
do step_2d
|
683
|
+
do step_3
|
684
|
+
do step_4
|
685
|
+
do step_5a
|
686
|
+
do step_5b
|
687
|
+
do step_5c
|
688
|
+
do step_5d
|
689
|
+
do step_5e
|
690
|
+
do step_5f
|
691
|
+
do step_5g
|
692
|
+
do step_5h
|
693
|
+
do step_5j
|
694
|
+
do step_5i
|
695
|
+
do step_5k
|
696
|
+
do step_5l
|
697
|
+
do step_5m
|
698
|
+
do step_6
|
699
|
+
do step_7
|
700
700
|
)
|
701
701
|
)
|
@@ -45,12 +45,14 @@ define mark_regions as (
|
|
45
45
|
|
46
46
|
$p1 = limit
|
47
47
|
|
48
|
-
(
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
48
|
+
(
|
49
|
+
// Word start with a vowel, start R1 after: V...C
|
50
|
+
v
|
51
|
+
do (gopast non-v setmark p1)
|
52
|
+
) or (
|
53
|
+
// Word start with a non-vowel, start R1 after: C...V
|
54
|
+
gopast v setmark p1
|
55
|
+
)
|
54
56
|
)
|
55
57
|
|
56
58
|
backwardmode (
|