1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
|
routines (
prelude postlude mark_regions
RV R1 R2
step_0
standard_suffix combo_suffix
verb_suffix
vowel_suffix
)
externals ( stem )
integers ( pV p1 p2 )
groupings ( v )
booleans ( standard_suffix_removed )
stringescapes {}
/* special characters */
stringdef a^ '{U+00E2}' // a circumflex
stringdef i^ '{U+00EE}' // i circumflex
stringdef a+ '{U+0103}' // a breve
stringdef s, '{U+015F}' // s cedilla
stringdef t, '{U+0163}' // t cedilla
define v 'aeiou{a^}{i^}{a+}'
define prelude as (
repeat goto (
v [ ('u' ] v <- 'U') or
('i' ] v <- 'I')
)
)
define mark_regions as (
$pV = limit
$p1 = limit
$p2 = limit // defaults
do (
( v (non-v gopast v) or (v gopast non-v) )
or
( non-v (non-v gopast v) or (v next) )
setmark pV
)
do (
gopast v gopast non-v setmark p1
gopast v gopast non-v setmark p2
)
)
define postlude as repeat (
[substring] among(
'I' (<- 'i')
'U' (<- 'u')
'' (next)
)
)
backwardmode (
define RV as $pV <= cursor
define R1 as $p1 <= cursor
define R2 as $p2 <= cursor
define step_0 as (
[substring] R1 among(
'ul' 'ului'
( delete )
'aua'
( <-'a' )
'ea' 'ele' 'elor'
( <-'e' )
'ii' 'iua' 'iei' 'iile' 'iilor' 'ilor'
( <-'i')
'ile'
( not 'ab' <- 'i' )
'atei'
( <- 'at' )
'a{t,}ie' 'a{t,}ia'
( <- 'a{t,}i' )
)
)
define combo_suffix as test (
[substring] R1 (
among(
/* 'IST'. alternative: include the following
'alism' 'alisme'
'alist' 'alista' 'aliste' 'alisti' 'alist{a+}' 'ali{s,}ti' (
<- 'al'
)
*/
'abilitate' 'abilitati' 'abilit{a+}i' 'abilit{a+}{t,}i' (
<- 'abil'
)
'ibilitate' (
<- 'ibil'
)
'ivitate' 'ivitati' 'ivit{a+}i' 'ivit{a+}{t,}i' (
<- 'iv'
)
'icitate' 'icitati' 'icit{a+}i' 'icit{a+}{t,}i'
'icator' 'icatori'
'iciv' 'iciva' 'icive' 'icivi' 'iciv{a+}'
'ical' 'icala' 'icale' 'icali' 'ical{a+}' (
<- 'ic'
)
'ativ' 'ativa' 'ative' 'ativi' 'ativ{a+}' 'a{t,}iune'
'atoare' 'ator' 'atori'
'{a+}toare' '{a+}tor' '{a+}tori' (
<- 'at'
)
'itiv' 'itiva' 'itive' 'itivi' 'itiv{a+}' 'i{t,}iune'
'itoare' 'itor' 'itori' (
<- 'it'
)
)
set standard_suffix_removed
)
)
define standard_suffix as (
unset standard_suffix_removed
repeat combo_suffix
[substring] R2 (
among(
// past participle is treated here, rather than
// as a verb ending:
'at' 'ata' 'at{a+}' 'ati' 'ate'
'ut' 'uta' 'ut{a+}' 'uti' 'ute'
'it' 'ita' 'it{a+}' 'iti' 'ite'
'ic' 'ica' 'ice' 'ici' 'ic{a+}'
'abil' 'abila' 'abile' 'abili' 'abil{a+}'
'ibil' 'ibila' 'ibile' 'ibili' 'ibil{a+}'
'oasa' 'oas{a+}' 'oase' 'os' 'osi' 'o{s,}i'
'ant' 'anta' 'ante' 'anti' 'ant{a+}'
'ator' 'atori'
'itate' 'itati' 'it{a+}i' 'it{a+}{t,}i'
'iv' 'iva' 'ive' 'ivi' 'iv{a+}' (
delete
)
'iune' 'iuni' (
'{t,}'] <- 't'
)
'ism' 'isme'
'ist' 'ista' 'iste' 'isti' 'ist{a+}' 'i{s,}ti' (
<- 'ist'
/* 'IST'. alternative: remove with <- '' */
)
)
set standard_suffix_removed
)
)
define verb_suffix as setlimit tomark pV for (
[substring] among(
// 'long' infinitive:
'are' 'ere' 'ire' '{a^}re'
// gerund:
'ind' '{a^}nd'
'indu' '{a^}ndu'
'eze'
'easc{a+}'
// present:
'ez' 'ezi' 'eaz{a+}' 'esc' 'e{s,}ti'
'e{s,}te'
'{a+}sc' '{a+}{s,}ti'
'{a+}{s,}te'
// imperfect:
'am' 'ai' 'au'
'eam' 'eai' 'ea' 'ea{t,}i' 'eau'
'iam' 'iai' 'ia' 'ia{t,}i' 'iau'
// past: // (not 'ii')
'ui'
'a{s,}i' 'ar{a+}m' 'ar{a+}{t,}i' 'ar{a+}'
'u{s,}i' 'ur{a+}m' 'ur{a+}{t,}i' 'ur{a+}'
'i{s,}i' 'ir{a+}m' 'ir{a+}{t,}i' 'ir{a+}'
'{a^}i' '{a^}{s,}i' '{a^}r{a+}m' '{a^}r{a+}{t,}i' '{a^}r{a+}'
// pluferfect:
'asem' 'ase{s,}i' 'ase' 'aser{a+}m' 'aser{a+}{t,}i' 'aser{a+}'
'isem' 'ise{s,}i' 'ise' 'iser{a+}m' 'iser{a+}{t,}i' 'iser{a+}'
'{a^}sem' '{a^}se{s,}i' '{a^}se' '{a^}ser{a+}m' '{a^}ser{a+}{t,}i'
'{a^}ser{a+}'
'usem' 'use{s,}i' 'use' 'user{a+}m' 'user{a+}{t,}i' 'user{a+}'
( non-v or 'u' delete )
// present:
'{a+}m' 'a{t,}i'
'em' 'e{t,}i'
'im' 'i{t,}i'
'{a^}m' '{a^}{t,}i'
// past:
'se{s,}i' 'ser{a+}m' 'ser{a+}{t,}i' 'ser{a+}'
'sei' 'se'
// pluperfect:
'sesem' 'sese{s,}i' 'sese' 'seser{a+}m' 'seser{a+}{t,}i' 'seser{a+}'
(delete)
)
)
define vowel_suffix as (
[substring] RV among (
'a' 'e' 'i' 'ie' '{a+}' ( delete )
)
)
)
define stem as (
do prelude
do mark_regions
backwards (
do step_0
do standard_suffix
do ( standard_suffix_removed or verb_suffix )
do vowel_suffix
)
do postlude
)
|
