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
|
## Viewer methods for objects of class "cnlp_annotation" as obtained by
## cleanNLP::cnlp_annotate().
words.cnlp_annotation <-
function(x, ...)
{
x$token$token
}
sents.cnlp_annotation <-
function(x, ...)
{
x <- x$token
split(x$token, x$sid)
}
## paras.cnlp_annotation <-
## function(x, ...)
## {
## x <- x$token
## if(is.na(match("pid", names(x))))
## stop("unavailable paragraph ids")
## lapply(split(x, x$pid),
## function(e) split(e$token, e$sid))
## }
tagged_words.cnlp_annotation <-
function(x, which = c("upos", "pos"), ...)
{
x <- x$token
which <- match.arg(which)
Tagged_Token(x$token, x[[which]])
}
tagged_sents.cnlp_annotation <-
function(x, which = c("upos", "pos"), ...)
{
x <- x$token
which <- match.arg(which)
.tagged_sents_from_cnlp_token_frame(x, which)
}
.tagged_sents_from_cnlp_token_frame <-
function(x, which)
{
lapply(split(x, x$sid),
function(e) Tagged_Token(e$token, e[[which]]))
}
## tagged_paras.cnlp_annotation <-
## function(x, which = c("upos", "pos"), ...)
## {
## x <- x$token
## if(is.na(match("pid", names(x))))
## stop("unavailable paragraph ids")
## which <- match.arg(which)
## lapply(split(x, x$pid),
## .tagged_sents_from_cnlp_token_frame,
## which)
## }
|
