-
Notifications
You must be signed in to change notification settings - Fork 0
/
root.lexc
161 lines (144 loc) · 6.69 KB
/
root.lexc
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
! Divvun & Giellatekno - open source grammars for Klingon language
! Copyright © 2015 The University of Tromsø & the Norwegian Sámi Parliament
! http://giellatekno.uit.no & http://divvun.no
!
! This program is free software; you can redistribute and/or modify
! this file under the terms of the GNU General Public License as published by
! the Free Software Foundation, either version 3 of the License, or
! (at your option) any later version. The GNU General Public License
! is found at http://www.gnu.org/licenses/gpl.html. It is
! also available in the file $GTHOME/LICENSE.txt.
!
! Other licensing options are available upon request, please contact
! giellatekno@uit.no or feedback@divvun.no
!! # Morphology of tlhIngan HoI (Klingon)
!! This is an example morphology, for the purpose of demonstrating giellatekno
!! morphology infrastructure. The example language we use is a popular conlang
!! by the name of tlhIngan, popularly known by the English name Klingon. This
!! description uses latinised form, for yet-to-be encoded Klingon orthography,
!! a spelling variant rule is provided.
Multichar_Symbols !!≈ # Definitions for @CODE@
!! ## Analysis symbols
!! The morphological analyses of wordforms of Klingon language are presented
!! in this system in terms of following symbols.
!! The parts-of-speech are:
+N !! `@CODE@` for noun,
+V !! `@CODE@` for verb (and "adjectives"),
+Pron !! `@CODE@` for pronouns,
+Num !! `@CODE@` for numerals,
+Conj !! `@CODE@` for conjunctions,
+Adv !! `@CODE@` for adverbs,
+Intj !! `@CODE@` for interjections, and
+Pcle !! `@CODE@` for other, unclassified particles.
!! The nominals are inflected in following Numbers, cases and
!! augmentation:
+Sg !! `@CODE@` for singular,
+Pl !! `@CODE@` for plural,
+Loc !! `@CODE@` for locative,
+Sep !! `@CODE@` for instructive,
+Ins !! `@CODE@` for instrumental,
+Bnf !! `@CODE@` for benefactive,
+Aug !! `@CODE@` for augmentative, and
+Dim !! `@CODE@` for diminitive
!! The possession is marked as such:
+PxSg1 !! `@CODE@` for first singular (mine)
+PxSg2 !! `@CODE@` for second singular (yours)
+PxSg3 !! `@CODE@` for third singular (his/hers/its/theirs)
+PxPl1 !! `@CODE@` for first plural (ours)
+PxPl2 !! `@CODE@` for second plural (yours)
+PxPl3 !! `@CODE@` for third plural (theirs)
!! Verb moods are:
+Ind !! `@CODE@` for indicative
+Imprt !! `@CODE@` for imperative
!! Verb tenses or aspects are:
+Cont !! `@CODE@` for continuative
+Perf !! `@CODE@` for perfect tense
+Prog !! `@CODE@` for progressive
!! Verb personal forms in intransitives and unmarked objects are
Sg1+ !! `@CODE@` for first singular (I do [[myself, to someone])
Sg2+ !! `@CODE@` for second singular (you do [[yourself, to someone])
Sg3+ !! `@CODE@` for third singular (he/she/it/they do [[theirself, to someone])
Pl1+ !! `@CODE@` for first plural (we do [[ourself, to someone])
Pl2+ !! `@CODE@` for first singular (you do [[yourselves, to someone])
Pl3+ !! `@CODE@` for first singular (they do [[theirselves, to somone])
!! The verb personal forms objects are tagged separately:
Sg1O+ !! `@CODE@` for first singular (– – does to me)
Sg2O+ !! `@CODE@` for second singular (– – does to you])
Sg3O+ !! `@CODE@` for third singular (– – does to them)
Pl1O+ !! `@CODE@` for first plural (– – does to us)
Pl2O+ !! `@CODE@` for first singular (– – does to you)
Pl3O+ !! `@CODE@` for first singular (– – does to them)
!! Other verb forms are
+Neg !! `@CODE@` negated form
+Refl !! `@CODE@` reflexive form
+Reciproc !! `@CODE@` reciprocal form
! Abbreviated words are classified with:
+ABBR !! `@CODE@`
+Symbol !!≈ * @CODE@ = independent symbols in the text stream, like £, €, ©
!! Special symbols are classified with:
+CLB !! `@CODE@`
+PUNCT !! `@CODE@`
+LEFT !! `@CODE@`
+RIGHT !! `@CODE@`
!! The verbs are syntactically split according to transitivity:
+TV !! `@CODE@` transitive
+IV !! `@CODE@` intransitive
!! Question and Focus particles:
+Qst !! `@CODE@` for question form
+Foc !! `@CODE@` other focus
+Foc/this !! `@CODE@` contrastive this focus
+Foc/that !! `@CODE@` contrastive that focus
!! Derivations are classified under the morphophonetic form of the suffix, the
!! source and target part-of-speech.
+V→N
+Der/wi
!! ## Flag diacritics
!! We have manually optimised the structure of our lexicon using following
!! flag diacritics to restrict morhpological combinatorics - only allow compounds
!! with verbs if the verb is further derived into a noun again:
@P.NeedNoun.ON@ !!≈ | @CODE@ | (Dis)allow compounds with verbs unless nominalised
@D.NeedNoun.ON@ !!≈ | @CODE@ | (Dis)allow compounds with verbs unless nominalised
@C.NeedNoun@ !!≈ | @CODE@ | (Dis)allow compounds with verbs unless nominalised
!!
!! For languages that allow compounding, the following flag diacritics are needed
!! to control position-based compounding restrictions for nominals. Their use is
!! handled automatically if combined with +CmpN/xxx tags. If not used, they will
!! do no harm.
@P.CmpFrst.FALSE@ !!≈ | @CODE@ | Require that words tagged as such only appear first
@D.CmpPref.TRUE@ !!≈ | @CODE@ | Block such words from entering ENDLEX
@P.CmpPref.FALSE@ !!≈ | @CODE@ | Block these words from making further compounds
@D.CmpLast.TRUE@ !!≈ | @CODE@ | Block such words from entering R
@D.CmpNone.TRUE@ !!≈ | @CODE@ | Combines with the next tag to prohibit compounding
@U.CmpNone.FALSE@ !!≈ | @CODE@ | Combines with the prev tag to prohibit compounding
@P.CmpOnly.TRUE@ !!≈ | @CODE@ | Sets a flag to indicate that the word has passed R
@D.CmpOnly.FALSE@ !!≈ | @CODE@ | Disallow words coming directly from root.
!!
!! Use the following flag diacritics to control downcasing of derived proper
!! nouns (e.g. Finnish Pariisi -> pariisilainen). See e.g. North Sámi for how to use
!! these flags. There exists a ready-made regex that will do the actual down-casing
!! given the proper use of these flags.
@U.Cap.Obl@ !!≈ | @CODE@ | Allowing downcasing of derived names: deatnulasj.
@U.Cap.Opt@ !!≈ | @CODE@ | Allowing downcasing of derived names: deatnulasj.
LEXICON Root
!! The word forms in Klingon language start from the lexeme roots of basic
!! word classes.
!! €gt-norm: Klingon poses
!! € Sus Sus+N wind
!! € jIJ jIH+Pron I
!! € je je+Conj and
!! € batlh batlh+Adv with honor
!! € ghobe’ ghobe’+Intj no (as in discourse response)
0 Nouns ;
0 Adverbs ;
0 Conjunctions ;
0 Interjections ;
0 Pronouns ;
0 Numerals ;
Punctuation ;
Symbols ;
!! The verbs require obligatory prefix that is the personal inflection or
!! imperative mood
!!€gt-norm: Klingon verb example
!!€ Qong 3Sg+Qong+V sleeps
0 VerbalPrefixes ;
! vim: set ft=xfst-lexc: