TARGET:在导入和rbind之前检查文件列表是否具有相同的编码,如果不是相同的STOP运行
# files list & check encoding
FL_PATH <- list.files(path,pattern = "*.csv",full.name = T)
library(readr)
lapply(FL_PATH,guess_encoding)
# if there is "UTF-8" , STOP RUN , if "Shift_JIS" , RUN the next scripts below :
# import
library(rio)
DT <- rbindlist(lapply(FL_PATH ,import,sep=",",setclass = "data.table"))
# OVER 500 rows to run if the files are same encoding to rbind
DT[,"NEW_COL":="A"]
DT[,"NEW_COL_2":="B"]
.....
# result of --lapply(FL_PATH,guess_encoding)
> lapply(FL_PATH,guess_encoding)
[[1]]
# A tibble: 3 x 2
encoding confidence
<chr> <dbl>
1 Shift_JIS 0.8
2 GB18030 0.76
3 Big5 0.46
[[2]]
# A tibble: 3 x 2
encoding confidence
<chr> <dbl>
1 GB18030 0.82
2 UTF-8 0.8
3 Big5 0.44
首先,获得最可能的编码:
enc <- sapply(FL_PATH,function(x) guess_encoding(x)$encoding[1])
然后,如果任何文件是UTF-8,则停止执行。
if(any(grepl('UTF-8',enc)))
stop('UTF-8 present') # This will stop with an error if true
# Now, read files and rbind
dlist <- lapply(FL_PATH,read_csv)
DT <- rbindlist(dlist)