Re-encode column names as UTF8

Author: hadley

NEWS.md

@@ -46,6 +46,9 @@
 
 * Made compatible with both dplyr 0.4 and 0.5.
 
+* tidyr functions that create new columns are more aggresive about re-encoding
+  the column names as UTF-8. 
+
 # tidyr 0.4.1
 
 * Fixed bug in `nest()` where nested data was ending up in the wrong row (#158).

R/extract.R

@@ -57,7 +57,7 @@ extract_.data.frame <- function(data, col, into, regex = "([[:alnum:]]+)",
   matches <- stringi::stri_match_first_regex(value, regex)[, -1, drop = FALSE]
   # Use as_data_frame post https://github.com/hadley/dplyr/issues/876
   l <- lapply(seq_len(ncol(matches)), function(i) matches[, i])
-  names(l) <- into
+  names(l) <- enc2utf8(into)
 
   if (convert) {
     l[] <- lapply(l, type.convert, as.is = TRUE)

R/nest.R

@@ -71,7 +71,7 @@ nest_impl <- function(data, key_col, group_cols, nest_cols) {
 
   if (length(group_cols) == 0) {
     df <- data_frame(list(data))
-    names(df) <- key_col
+    names(df) <- enc2utf8(key_col)
 
     return(df)
   }

R/separate.R

@@ -98,7 +98,7 @@ separate_.data.frame <- function(data, col, into, sep = "[^[:alnum:]]+",
     stop("'sep' must be either numeric or character", .call = FALSE)
   }
 
-  names(l) <- into
+  names(l) <- enc2utf8(into)
   if (convert) {
     l[] <- lapply(l, type.convert, as.is = TRUE)
   }

R/spread.R

@@ -125,7 +125,7 @@ spread_.data.frame <- function(data, key_col, value_col, fill = NA,
     ordered <- as.character(ordered)
   }
   dim(ordered) <- c(attr(row_id, "n"), attr(col_id, "n"))
-  colnames(ordered) <- col_names(col_labels, sep = sep)
+  colnames(ordered) <- enc2utf8(col_names(col_labels, sep = sep))
 
   ordered <- as_data_frame_matrix(ordered)
 

R/unite.R

@@ -52,7 +52,6 @@ unite_.data.frame <- function(data, col, from, sep = "_", remove = TRUE) {
     data2 <- data2[setdiff(names(data2), from)]
   }
 
-
   append_col(data2, united, col, after = first_col - 1)
 }
 

R/utils.R

@@ -16,6 +16,7 @@ append_df <- function(x, values, after = length(x)) {
 }
 
 append_col <- function(x, col, name, after = length(x)) {
+  name <- enc2utf8(name)
   append_df(x, setNames(list(col), name), after = after)
 }