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
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
|
parse_IETF_language_tag <-
function(x, expand = FALSE, strict = TRUE)
{
n <- length(x)
y <- rep.int(list(character()), n)
names(y) <- x
pos <- seq_along(x)
## How nice should we be?
## Allow for empty or missing elements ...
ind <- which(!is.na(x) & nzchar(x))
pos <- pos[ind]
x <- x[ind]
## See <https://www.ietf.org/rfc/rfc4646.txt>.
## Language tags can be of the form (in ABNF, see
## <https://tools.ietf.org/rfc/rfc4234.txt>):
## langtag / privateuse / grandfathered
## where
## privateuse = ("x"/"X") 1*("-" (1*8alphanum))
## grandfathered = 1*3ALPHA 1*2("-" (2*8alphanum))
re_privateuse <- "[xX]((-[[:alnum:]]{1,8}){1,})"
## Grandfathered tags must really be determined by exact matching.
ind <- !is.na(match(x,
IANA_language_subtag_registry_grandfathered_table$Tag))
if(any(ind)) {
y[pos[ind]] <- as.list(sprintf("Grandfathered=%s", x[ind]))
ind <- which(!ind)
pos <- pos[ind]
x <- x[ind]
}
if(length(pos)) {
pat <- sprintf("^%s$", re_privateuse)
ind <- grepl(pat, x, perl = TRUE)
if(any(ind)) {
y[pos[ind]] <-
as.list(sprintf("Privateuse=%s",
substring(x[ind], 3L)))
ind <- which(!ind)
pos <- pos[ind]
x <- x[ind]
}
}
## Now for the real thing.
## Remaining tags should now be as follows:
## (language
## ["-" script]
## ["-" region]
## *(["-" variant])
## *(["-" extension])
## ["-" privateuse]
## where
## language = (2*3ALPHA [-extlang]) ; shortest ISO 639 code
## / 4ALPHA ; reserved for future use
## / 5*8ALPHA ; registered language subtag
## extlang = *3("-" 3*ALPHA) ; reserved for future use
## script = 4ALPHA ; ISO 15924 code
## region = 2ALPHA ; ISO 3166 code
## / 3DIGIT ; UN M.49 code
## variant = 5*8alphanum ; registered variants
## / (DIGIT 3alphanum)
## extension = singleton 1*("-" (2*8alphanum))
## singleton = %x41-57 / %x59-5A / %x61-77 / %x79-7A / DIGIT
## ; "a"-"w" / "y"-"z" / "A"-"W" / "Y"-"Z" / "0"-"9"
## We handle language/extlang a bit differently (more generously).
re_extlang <- "[[:alpha:]]{3}"
re_language <-
sprintf("[[:alpha:]]{2,3}(-%s){0,3}|[[:alpha:]]{4,8}", re_extlang)
re_script <- "[[:alpha:]]{4}"
re_region <- "[[:alpha:]]{2}|[[:digit:]]{3}"
re_variant <- "[[:alnum:]]{5,8}|[[:digit:]][[:alnum:]]{3}"
re_singleton <- "[abcdefghijklmnopqrstuvwyzABCDEFGHIJKLMNOPQRSTUVWYZ0123456789]"
re_extension <- sprintf("(%s)(-[[:alnum:]]{2,8}){1,}", re_singleton)
bad <- integer()
if(length(pos)) {
pat <- sprintf("^(%s)(-.*|$)", re_language)
ind <- grepl(pat, x, perl = TRUE)
bad <- pos[!ind]
pos <- pos[ind]
x <- x[ind]
y[pos] <-
lapply(strsplit(sub(pat, "\\1", x, perl = TRUE),
"-", fixed = TRUE),
function(e) {
c(sprintf("Language=%s", e[1L]),
sprintf("Extension=%s", e[-1L]))
})
x <- sub(pat, "\\3", x, perl = TRUE)
ind <- which(nzchar(x))
pos <- pos[ind]
x <- x[ind]
}
if(length(pos)) {
repeat {
## Use a loop so that we can finally stop when done.
## Script.
pat <- sprintf("^-(%s)(-.*|$)", re_script)
if(any(ind <- grepl(pat, x, perl = TRUE))) {
y[pos[ind]] <-
Map(c,
y[pos[ind]],
sprintf("Script=%s",
sub(pat, "\\1", x[ind], perl = TRUE)))
x[ind] <- sub(pat, "\\2", x[ind], perl = TRUE)
ind <- which(nzchar(x))
pos <- pos[ind]
x <- x[ind]
if(!length(x)) break
}
## Region.
pat <- sprintf("^-(%s)(-.*|$)", re_region)
if(any(ind <- grepl(pat, x, perl = TRUE))) {
y[pos[ind]] <-
Map(c,
y[pos[ind]],
sprintf("Region=%s",
sub(pat, "\\1", x[ind], perl = TRUE)))
x[ind] <- sub(pat, "\\2", x[ind], perl = TRUE)
ind <- which(nzchar(x))
pos <- pos[ind]
x <- x[ind]
if(!length(x)) break
}
## Variant(s).
pat <- sprintf("^-(%s)(-.*|$)", re_variant)
while(any(ind <- grepl(pat, x, perl = TRUE))) {
y[pos[ind]] <-
Map(c,
y[pos[ind]],
sprintf("Variant=%s",
sub(pat, "\\1", x[ind], perl = TRUE)))
x[ind] <- sub(pat, "\\2", x[ind], perl = TRUE)
ind <- which(nzchar(x))
pos <- pos[ind]
x <- x[ind]
}
if(!length(x)) break
## Extension(s).
pat <- sprintf("^-%s(-.*|$)", re_extension)
while(any(ind <- grepl(pat, x, perl = TRUE))) {
## <NOTE>
## We keep the singleton prefix: this could be used in
## expansions of registered extensions: currently,
## BCP 47 Extension U <https://tools.ietf.org/html/rfc6067>
## BCP 47 Extension T <https://tools.ietf.org/html/rfc6497>
y[pos[ind]] <-
Map(c,
y[pos[ind]],
sprintf("Extension=%s",
sub(pat, "\\1\\2", x[ind], perl = TRUE)))
## </NOTE>
x[ind] <- sub(pat, "\\3", x[ind], perl = TRUE)
ind <- which(nzchar(x))
pos <- pos[ind]
x <- x[ind]
}
if(!length(x)) break
## Private use.
pat <- sprintf("^-%s(-.*|$)", re_privateuse)
if(any(ind <- grepl(pat, x, perl = TRUE))) {
y[pos[ind]] <-
Map(c,
y[pos[ind]],
sprintf("Privateuse=%s",
substring(sub(pat, "\\1", x[ind],
perl = TRUE),
2L)))
x[ind] <- sub(pat, "\\4", x[ind], perl = TRUE)
}
break
}
}
## Be a nuisance: singletons for extensions must not be duplicated.
ind <- vapply(y,
function(e) {
e <- grep("^Extension=", e, value = TRUE)
if(!length(e)) return(FALSE)
any(duplicated(sub("^Extension=(.).*", "\\1", e)))
},
NA)
if(any(ind))
bad <- c(bad, which(ind))
if(any(ind <- nzchar(x))) {
bad <- c(bad, pos[ind])
}
if(length(bad) && strict) {
stop("Invalid language tag(s):",
paste("\n ", sQuote(names(y)[bad]), collapse = " "),
call. = FALSE)
}
if(!expand) return(y)
n <- lengths(y)
i <- (n > 0L)
x <- tolower(unlist(y, use.names = FALSE))
p <- match(x, IANA_language_subtag_registry$Index)
z <- IANA_language_subtag_registry$Description[p]
## Special case private use ranges.
if(!all(lengths(z))) {
p <- match(x, IANA_language_subtag_registry_private_use_index_table)
z[p > 0L | grepl("^privateuse=", x)] <- "Private use"
}
z <- Map(`names<-`, split(z, rep.int(seq_along(y), n)), y[i])
y[i] <- z
y
}
get_IANA_language_subtag_registry <-
function(con = "https://www.iana.org/assignments/language-subtag-registry")
{
## This is a collection of records in tag-value format, but
## unfortunately separated by '%%' lines rather than empty lines, so
## we cannot use read.dcf() directly. Let us keep things simple:
## extract the records, write them out as DCF, and call read.dcf().
lines <- readLines(con)
## The first line is something like
## File-Date: 2009-03-13
## which we drop for reading the records.
fdate <- sub(".*: *", "", lines[1L])
pos <- grep("^%%", lines)
lines[c(seq_len(pos[1L]), pos[-1L])] <- ""
tcon <- textConnection(lines, encoding = "UTF-8")
on.exit(close(tcon))
db <- read.dcf(tcon, all = TRUE)
## Add index for lookups.
subtag <- db$Subtag
db$Index <-
tolower(sprintf("%s=%s",
db$Type,
ifelse(is.na(subtag), db$Tag, subtag)))
db$Type <- factor(db$Type)
attr(db, "File_Date") <- fdate
db
}
IANA_language_subtag_registry_language_private_use_subtags <-
outer(letters[1L : 20L], letters,
function(u, v) sprintf("q%s%s", u, v))
IANA_language_subtag_registry_script_private_use_subtags <-
outer(c("a", "b"), letters[1L : 24L],
function(u, v) sprintf("Qa%s%s", u, v))
IANA_language_subtag_registry_region_private_use_subtags <-
c(sprintf("Q%s", LETTERS[13L : 26L]),
sprintf("X%s", LETTERS))
IANA_language_subtag_registry_private_use_index_table <-
tolower(c(sprintf("Language=%s",
IANA_language_subtag_registry_language_private_use_subtags),
sprintf("Script=%s",
IANA_language_subtag_registry_script_private_use_subtags),
sprintf("Region=%s",
IANA_language_subtag_registry_region_private_use_subtags)))
|
