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
237
238
239
240
241
242
243
244
245
246
|
AnnotatedPlainTextDocument <-
function(s, annotations, meta = list())
{
s <- as.String(s)
## Be nice.
if(is.Annotation(annotations))
annotations <- list(annotations)
else {
annotations <- as.list(annotations)
if(!length(annotations) ||
!all(sapply(annotations, is.Annotation)))
stop("argument 'annotations' must give a positive number of Annotation objects")
}
doc <- list(content = s, meta = meta, annotations = annotations)
class(doc) <- c("AnnotatedPlainTextDocument",
"PlainTextDocument",
"TextDocument")
doc
}
format.AnnotatedPlainTextDocument <-
function(x, ...)
{
annotations <- x$annotations
c(.format_TextDocument(x),
sprintf("Annotations: %d, length(s): %s",
length(annotations),
paste(sapply(annotations, length), collapse = "/")),
sprintf("Content: chars: %d",
nchar(x$content)))
}
## print.AnnotatedPlainTextDocument <-
## function(x, ...)
## {
## annotations <- x$annotations
## writeLines(sprintf("<<AnnotatedPlainTextDocument (annotations: %d, length(s): %s)>>",
## length(annotations),
## paste(sapply(annotations, length),
## collapse = "/")))
## invisible(x)
## }
content.AnnotatedPlainTextDocument <-
function(x)
x$content
`content<-.AnnotatedPlainTextDocument` <-
function(x, value)
stop("content modification is not possible for AnnotatedPlainTextDocument objects")
## meta.AnnotatedPlainTextDocument <-
## function(x, tag = NULL, ...)
## if(is.null(tag)) x$meta else x$meta[[tag]]
## `meta<-.AnnotatedPlainTextDocument` <-
## function(x, tag = NULL, ..., value)
## {
## if(is.null(tag))
## x$meta <- value
## else
## x$meta[[tag]] <- value
## x
## }
as.character.AnnotatedPlainTextDocument <-
function(x, ...)
x$content
annotations <-
function(x)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
x$annotations
}
## NLTK style functions for high level access
words.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
## Could check for word token annotations ...
s[a[a$type == "word"]]
}
sents.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
.sents_from_annotation_and_text(a, s)
}
.sents_from_annotation_and_text <-
function(a, s)
{
## Could check for sentence and word token annotations ...
s[annotations_in_spans(a[a$type == "word"],
a[a$type == "sentence"])]
}
paras.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
## Could check for paragraph annotations ...
lapply(annotations_in_spans(a, a[a$type == "paragraph"]),
.sents_from_annotation_and_text, s)
}
tagged_words.AnnotatedPlainTextDocument <-
function(x, which = 1L, map = NULL, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
## Could check for word token annotations ...
a <- a[a$type == "word"]
if(!is.null(map))
a <- .map_POS_tags_Annotation(a, map)
.tagged_words_from_annotation_and_text(a, s)
}
.tagged_words_from_annotation_and_text <-
function(a, s)
{
## Could check for POS tag features ...
pos <- sapply(a$features, `[[`, "POS")
Tagged_Token(s[a], pos)
}
tagged_sents.AnnotatedPlainTextDocument <-
function(x, which = 1L, map = NULL, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
if(!is.null(map))
a <- .map_POS_tags_Annotation(a, map)
.tagged_sents_from_annotation_and_text(a, s)
}
.tagged_sents_from_annotation_and_text <-
function(a, s)
{
## Could check for word and sentence token annotations ...
lapply(annotations_in_spans(a[a$type == "word"],
a[a$type == "sentence"]),
.tagged_words_from_annotation_and_text, s)
}
tagged_paras.AnnotatedPlainTextDocument <-
function(x, which = 1L, map = NULL, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
if(!is.null(map))
a <- .map_POS_tags_Annotation(a, map)
## Could check for paragraph annotations ...
lapply(annotations_in_spans(a, a[a$type == "paragraph"]),
.tagged_sents_from_annotation_and_text, s)
}
parsed_sents.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
a <- annotations(x)[[which]]
.parsed_sents_from_annotation(a)
}
.parsed_sents_from_annotation <-
function(a)
{
## Could check for sentence token annotations and parse features ...
ptexts <- sapply(a[a$type == "sentence"]$features, `[[`, "parse")
lapply(ptexts, Tree_parse)
}
parsed_paras.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
a <- annotations(x)[[which]]
## Could check for paragraph annotations ...
lapply(annotations_in_spans(a, a[a$type == "paragraph"]),
.parsed_sents_from_annotation)
}
chunked_sents.AnnotatedPlainTextDocument <-
function(x, which = 1L, ...)
{
if(!inherits(x, "AnnotatedPlainTextDocument"))
stop("argument 'x' must be an AnnotatedPlainTextDocument object")
s <- x$content
a <- annotations(x)[[which]]
## Require annotations with POS and chunk_tag features, as obtained
## e.g. with the Apache OpenNLP POS tag and chunk annotators. We
## could alternatively use annotations with parse features and
## flatten the parse trees.
## Could check for word and sentence token annotations ...
lapply(annotations_in_spans(a[a$type == "word"],
a[a$type == "sentence"]),
function(a) {
## Could check for POS and chunk tag features ...
ptags <- sapply(a$features, `[[`, "POS")
ctags <- sapply(a$features, `[[`, "chunk_tag")
words <- s[a]
chunk_tree_from_chunk_info(words, ptags, ctags)
})
}
.map_POS_tags_Annotation <-
function(x, map)
{
map <- POS_tag_mapper(map, meta(x, "POS_tagset"))
x$features <-
lapply(x$features,
function(e) {
if(!is.null(pos <- e$POS))
e$POS <- map(pos)
e
})
x
}
|
