欺负人的公共数据+1(编码方式utf-16)

a = read.delim("GSE309870_TPM_all_Sample.txt")

## Warning in read.table(file = file, header = header, sep =
## sep, quote = quote, : line 1 appears to contain embedded
## nulls

## Warning in read.table(file = file, header = header, sep =
## sep, quote = quote, : line 2 appears to contain embedded
## nulls

## Warning in read.table(file = file, header = header, sep =
## sep, quote = quote, : line 3 appears to contain embedded
## nulls

## Warning in read.table(file = file, header = header, sep =
## sep, quote = quote, : line 4 appears to contain embedded
## nulls

## Warning in read.table(file = file, header = header, sep =
## sep, quote = quote, : line 5 appears to contain embedded
## nulls

## Error in make.names(col.names, unique = TRUE): invalid multibyte string at '<ff><fe>e'

a = data.table::fread("GSE309870_TPM_all_Sample.txt")

## Error in data.table::fread("GSE309870_TPM_all_Sample.txt"): 文件编码是UTF-16，fread()不支持此编码。请 将文件转换为UTF-8。

a = rio::import("GSE309870_TPM_all_Sample.txt")

## Error in (function (input = "", file = NULL, text = NULL, cmd = NULL, : 文件编码是UTF-16，fread()不支持此编码。请 将文件转换为UTF-8。

library(readr)
a = read_table("GSE309870_TPM_all_Sample.txt",
               locale = locale(encoding = "UTF-16"))

## Error: Incomplete multibyte sequence

convert_utf16_to_utf8 <- function(src, dst,
                                  endian = c("little","big")) {
  endian  <- match.arg(endian)
  cs      <- if (endian == "little") "UTF-16LE"else"UTF-16BE"
  con_in  <- file(src,  "rb")
  con_out <- file(dst, "wb")
  open(con_in); open(con_out)
while (length(buf <- readBin(con_in, "raw", n = 1e6))) {
    txt <- iconv(list(buf), from = cs, to = "UTF-8")
    writeBin(charToRaw(txt), con_out)
  }
  close(con_in); close(con_out)
}

convert_utf16_to_utf8("GSE309870_TPM_all_Sample.txt", "GSE309870_TPM_all_Sample_utf8.txt")

## Warning in open.connection(con_in): connection is already
## open

## Warning in open.connection(con_out): connection is
## already open

library(data.table)

DT <- fread("GSE309870_TPM_all_Sample_utf8.txt")