简介：解决读入外部数据时，由于编码格式问题导致的字符乱码及数据分析报错情况。

所用R包：stringi

#查找变量
character_columns <- names(data)[sapply(data, function(x) inherits(x, "character"))]
#or data %>% select(where(~!is.character(.)))
labelled_columns <- names(data_cleaned)[sapply(data_cleaned, function(x) inherits(x, "haven_labelled"))]
date_columns <- names(data_cleaned)[sapply(data_cleaned, function(x) inherits(x, c("Date", "POSIXct")))]

# 检查是否所有字符列都被转换为 UTF-8 编码
for (col in colnames(adam1)) {
  if (is.character(adam1[[col]])) {
    if (!all(stri_enc_isutf8(adam1[[col]]))) {
      stop(paste("Column", col, "contains non-UTF-8 encoded data."))
    }
  }
}
#查找非UTF-8 编码列
non_code <- data %>% select(where(~!all(stri_enc_isutf8(.))&& is.character(.))) %>% colnames()

# 尝试寻找变量的编码格式并转换字符列为 UTF-8 编码
possible_encodings <- c("GB2312", "GBK", "BIG5")
for (encoding in possible_encodings) {
  print(paste("Trying encoding:", encoding))
  try({
    adam1$ar01 <- stri_encode(adam1$ar01, encoding, "UTF-8")
    if (all(stri_enc_isutf8(adam1$ar01))) {
      print(paste("Successfully converted using encoding:", encoding))
      break
    }
  }, silent = TRUE)
}

#确定乱码的变量格式后将所有字符串转换为UTF-8 编码
data <- data %>% mutate(across(non_code,~ stri_encode(.,"GB2312", "UTF-8")))



# 检查是否所有字符列都被转换为 UTF-8 编码
for (col in colnames(adam1)) {
  if (is.character(adam1[[col]])) {
    if (!all(stri_enc_isutf8(adam1[[col]]))) {
      stop(paste("Column", col, "contains non-UTF-8 encoded data."))
    }
  }
}