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
|
Multichar_Symbols
% N
% Prop
% V
% Abbr
% PUNCT
@PMATCH_INPUT_MARK@
@PMATCH_BACKTRACK@
% ErrSpace
%#
% Adv
% Num
% Prn
% Cmp
LEXICON Root
skuvla% N:skuvla #;
busse% N:busse #;
busset% V:busse #;
< {skuvla} "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":" " {busse} " N":0 " ErrSpace":0 > # ;
logi% Num:logi #;
guokte% Num:guokte #;
njeallje% Num:njeallje #;
lo% Cmp#:lo GI;
lo% Num:lo UNSPACEGI;
! Silly example, but just to test that spaces on both sides work, as well as multiple backtracking points:
< {njeallje} "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":" " 0:" " 0:" " {logi} "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":" " {guokte} " Num":0 " ErrSpace":0 > # ;
Jan% N% Prop:Jan #;
.% PUNCT:. #;
Jan DOTABBR;
su% Prn:su #;
su% Adv% Abbr:su DOTNOTAG;
LEXICON DOTABBR
! This one should create a new backtrack-point before the dot, but *no* sub-reading:
< "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":0 {.} " N":0 " Abbr":0 > # ;
! This one should create a new backtrack-point before the dot, *as well as* a sub-reading:
< "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":0 {.}:0 " N":0 " Abbr":0 "@PMATCH_INPUT_MARK@":0 {.} " PUNCT":0 > # ;
! Want:
!"<Jan.>"
! "." PUNCT "<.>"
! "Jan." N Abbr "<Jan>"
! "Jan." N Abbr
! "." PUNCT "<.>"
! "Jan" N Prop "<Jan>"
LEXICON DOTNOTAG
! As the sub-reading-line of DOTABBR, but the two input-marks are right next to each other:
< "@PMATCH_INPUT_MARK@":0 "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":0 {.} " PUNCT":0 > # ;
! TODO: This doesn't give the sub-reading, however; should it?
!< "@PMATCH_BACKTRACK@":0 "@PMATCH_INPUT_MARK@":0 "@PMATCH_INPUT_MARK@":0 {.} " PUNCT":0 > # ;
LEXICON UNSPACEGI
@PMATCH_INPUT_MARK@:0 GI;
LEXICON GI
gi% N:gi #;
|
