-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathutils.R
186 lines (160 loc) · 6.03 KB
/
utils.R
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
# utils.R
u_chars = function(s, encodings) {
stopifnot(class(s) == "character")
stopifnot(length(s)==1)
if (Encoding(s) != 'UTF-8' && Encoding(s) != "unknown") {
s = iconv(s, from = Encoding(s), to='UTF-8') }
dat = data.frame(ch = unlist(strsplit(s, ""))) # 글자 단위로 분리
cps = sapply(dat$ch, utf8ToInt) # unicode codepoint
cps_hex = sprintf("%02x", cps) # 16진수로 변환
# 16진수 표현 방법 " ..ff", " a1ff", "011f3e"
# 처음 두 자리수는 거의 사용되지 않으므로 0일 때 공란으로 표시
# 다음 두 자리수는 ASCII의 경우 사용되지 않으므로 0일 때 .으로 표시
cps_hex =
ifelse(nchar(cps_hex) > 2,
stringi::stri_pad(cps_hex, width = 4, side = 'left', pad = '0'),
stringi::stri_pad(cps_hex, width = 4, side = 'left', pad = '.'))
dat$codepoint =
ifelse(nchar(cps_hex) > 4,
stringi::stri_pad(cps_hex, width=6, side='left', pad='0'),
stringi::stri_pad(cps_hex, width=6, side='left', pad=' '))
# encodings가 주어졌다면, 주어진 인코딩으로 변환 결과
if (!missing(encodings)) {
for (encoding in encodings) {
ch_enc = vector(mode='character', length=nrow(dat))
for (i in 1:nrow(dat)) {
ch = dat$ch[i]
ch_enc[i] =
paste0(sprintf("%02x",
as.integer(unlist(
iconv(ch, from = 'UTF-8',
to=encoding, toRaw=TRUE)))),
collapse = ' ')
}
dat$enc = ch_enc
names(dat)[length(names(dat))] = paste0('enc.', encoding)
}
}
dat$label = Unicode::u_char_label(cps);
dat
}
# get_printlocales = function() {
# lc_sys <- Sys.info()[["sysname"]]
# lc_sep <- switch(lc_sys,
# "Darwin"=, "SunOS" = "/",
# "Linux" =, "Windows" = ";")
#
# printlocales = function(category = "LC_ALL") {
# mat = Sys.getlocale("LC_ALL") %>%
# strsplit(lc_sep) %>%
# unlist %>% strsplit('=') %>% do.call(rbind, .)
# apply(mat, 1, function(x) sprintf("%12s = %-20s", x[1], x[2])) %>%
# paste0(collapse= '\n') %>% cat
# invisible(mat)
# }
#
# return(printlocales)
# }
# %>% 를 사용하지 않은 버전
# R 4.0 이상에서는 |> 를 사용해보는 것도 좋겠다.
get_printlocales = function() {
lc_sys <- Sys.info()[["sysname"]]
lc_sep <- switch(lc_sys,
"Darwin"=, "SunOS" = "/",
"Linux" =, "Windows" = ";")
printlocales = function(category = "LC_ALL") {
mat =
do.call(rbind, strsplit(unlist(strsplit(Sys.getlocale("LC_ALL"), lc_sep)), '='))
lc_category = mat[,1]
cat(
paste0(
apply(mat, 1, function(x) sprintf("%12s = %-20s", x[1], x[2])),
collapse='\n'))
invisible(mat)
}
return(printlocales)
}
printlocales = get_printlocales()
encoding = Encoding
`encoding<-` = function(x, value) {
stopifnot(value %in% c("latin1", "UTF-8", "bytes", "", "unknown"))
Encoding(x) = value
x
}
## GGPLOT2 관련
x_label_vertical = function() {
theme(axis.text.x = element_text(angle=90, vjust=0.5, hjust=1))
}
# x-축의 레이블의 방향을 수직으로 바꾼다.
# 사용 방법 예)
# ggplot(mtcars, aes(x=cyl, y=mpg)) + geom_point() + x_label_vertical()
legend_alpha1 = function() {
guides(colur = guide_legend(override.aes = list(alpha=1)))
}
# 범례에서 알파를 1로 고정
# aes(alpha=)를 쓸 경우에 범례의 색이 흐려져서 식별하지 못하는 경우에 유용
# 사용 방법 예)
# ggplot(mtcars, aes(x=cyl, y=hp, alpha=mpg)) + geom_point() + legend_alpha1()
BOM_UTF8 <- as.raw(c(0xef, 0xbb, 0xbf))
BOM_UTF16BE <- as.raw(c(0xfe, 0xff))
BOM_UTF16LE <- as.raw(c(0xff, 0xfe))
BOM_UTF32BE <- as.raw(c(0x00, 0x00, 0xfe, 0xff))
BOM_UTF32LE <- as.raw(c(0xff, 0xfe, 0x00, 0x00))
BOM_UTF7 <- as.raw(c(0x2b, 0x2f, 0x76))
BOM_UTF1 <- as.raw(c(0xf7, 0x64, 0x4c))
BOM_UTF_EBCDIC <- as.raw(c(0xdd, 0x73, 0x66, 0x73))
BOM_SCSU <- as.raw(c(0x0e, 0xfe, 0xff))
BOM_BOCU1 <- as.raw(c(0xfb, 0xee, 0x28))
BOM_GB18030 <- as.raw(c(0x84, 0x31, 0x95, 0x33))
BOMs = list("UTF8"=BOM_UTF8,
"UTF16BE"=BOM_UTF16BE, "UTF16LE"=BOM_UTF16LE,
"UTF32BE"=BOM_UTF32BE, "UTF32LE"=BOM_UTF32LE,
"UTF7"=BOM_UTF7, "UTF1"=BOM_UTF1,
"UTF-EBCDIC"=BOM_UTF_EBCDIC,
"SCSU"=BOM_SCSU,
"BOCU-1"=BOM_BOCU1,
"GB-18030"=BOM_GB18030)
check_marks = function(BOM) {
if (all(marks[1:length(BOM)] == BOM)) return(TRUE) else return(FALSE)
}
checkBOM0 = function(filename) {
check_marks = function(BOM) {
if (all(marks[1:length(BOM)] == BOM)) return(TRUE) else return(FALSE)
}
f <- file(filename, "rb")
marks <- readBin(f, "raw", n=10)
names(BOMs)[sapply(BOMs, check_marks)]
}
checkBOM = function(filename) {
marks <- readBin(filename, "raw", n=4)
BOM_UTF8 <- as.raw(c(0xef, 0xbb, 0xbf))
BOM_UTF16BE <- as.raw(c(0xfe, 0xff))
BOM_UTF16LE <- as.raw(c(0xff, 0xfe))
BOM_UTF32BE <- as.raw(c(0x00, 0x00, 0xfe, 0xff))
BOM_UTF32LE <- as.raw(c(0xff, 0xfe, 0x00, 0x00))
BOM_UTF7 <- as.raw(c(0x2b, 0x2f, 0x76))
BOM_UTF1 <- as.raw(c(0xf7, 0x64, 0x4c))
BOM_UTF_EBCDIC <- as.raw(c(0xdd, 0x73, 0x66, 0x73))
BOM_SCSU <- as.raw(c(0x0e, 0xfe, 0xff))
BOM_BOCU1 <- as.raw(c(0xfb, 0xee, 0x28))
BOM_GB18030 <- as.raw(c(0x84, 0x31, 0x95, 0x33))
BOMs = list("UTF8"=BOM_UTF8,
"UTF16BE"=BOM_UTF16BE, "UTF16LE"=BOM_UTF16LE,
"UTF32BE"=BOM_UTF32BE, "UTF32LE"=BOM_UTF32LE,
"UTF7"=BOM_UTF7, "UTF1"=BOM_UTF1,
"UTF-EBCDIC"=BOM_UTF_EBCDIC,
"SCSU"=BOM_SCSU,
"BOCU-1"=BOM_BOCU1,
"GB-18030"=BOM_GB18030)
check_marks = function(BOM) {
if (all(marks[1:length(BOM)] == BOM)) return(TRUE) else return(FALSE)
}
res = names(BOMs)[sapply(BOMs, check_marks)]
if (length(res)>0) {
con = file(filename, "rb")
readBin(con, "raw", n = length(BOMs[[res]]))
return(list(BOM=res, con=con))
} else {
return(list(BOM="", con=file(filename), "rb"))
}
}