Allow : in select strings (#551)

* Allow : in select strings

* lintr

* fix test

* test. comment

* news item

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: datawizard
 Title: Easy Data Wrangling and Statistical Transformations
-Version: 0.13.0.1
+Version: 0.13.0.2
 Authors@R: c(
     person("Indrajeet", "Patil", , "[email protected]", role = "aut",
            comment = c(ORCID = "0000-0003-1995-6531")),

NEWS.md

@@ -1,5 +1,11 @@
 # datawizard (development)
 
+CHANGES
+
+* The `select` argument, which is available in different functions to select
+  variables, can now also be a character vector with quoted variable names,
+  including a colon to indicate a range of several variables (e.g. `"cyl:gear"`).
+
 BUG FIXES
 
 * `describe_distribution()` no longer errors if the sample was too sparse to compute

R/extract_column_names.R

@@ -9,8 +9,10 @@
 #'   tasks. Can be either
 #'
 #'   - a variable specified as a literal variable name (e.g., `column_name`),
-#'   - a string with the variable name (e.g., `"column_name"`), or a character
-#'     vector of variable names (e.g., `c("col1", "col2", "col3")`),
+#'   - a string with the variable name (e.g., `"column_name"`), a character
+#'     vector of variable names (e.g., `c("col1", "col2", "col3")`), or a
+#'     character vector of variable names including ranges specified via `:`
+#'     (e.g., `c("col1:col3", "col5")`),
 #'   - a formula with variable names (e.g., `~column_1 + column_2`),
 #'   - a vector of positive integers, giving the positions counting from the left
 #'     (e.g. `1` or `c(1, 3, 5)`),
@@ -116,7 +118,7 @@
 #' ```
 #'
 #' @examples
-#' # Find columns names by pattern
+#' # Find column names by pattern
 #' extract_column_names(iris, starts_with("Sepal"))
 #' extract_column_names(iris, ends_with("Width"))
 #' extract_column_names(iris, regex("\\."))
@@ -129,6 +131,9 @@
 #' numeric_mean_35 <- function(x) is.numeric(x) && mean(x, na.rm = TRUE) > 3.5
 #' extract_column_names(iris, numeric_mean_35)
 #'
+#' # find range of colum names by range, using character vector
+#' extract_column_names(mtcars, c("cyl:hp", "wt"))
+#'
 #' # rename returned columns for "data_select()"
 #' head(data_select(mtcars, c(`Miles per Gallon` = "mpg", Cylinders = "cyl")))
 #' @export

R/select_nse.R

@@ -139,38 +139,71 @@
 # Possibilities:
 # - quoted variable name
 # - quoted variable name with ignore case
+# - quoted variable name with colon, to indicate range
 # - character that should be regex-ed on variable names
 # - special word "all" to return all vars
 
 .select_char <- function(data, x, ignore_case, regex, verbose) {
   # use colnames because names() doesn't work for matrices
   columns <- colnames(data)
   if (isTRUE(regex)) {
+    # string is a regular expression
     grep(x, columns)
   } else if (length(x) == 1L && x == "all") {
+    # string is "all" - select all columns
     seq_along(data)
+  } else if (any(grepl(":", x, fixed = TRUE))) {
+    # special pattern, as string (e.g.select = c("cyl:hp", "am")). However,
+    # this will first go into `.eval_call()` and thus only single elements
+    # are passed in `x` - we have never a character *vector* here
+    # check for valid names
+    colon_vars <- unlist(strsplit(x, ":", fixed = TRUE))
+    colon_match <- match(colon_vars, columns)
+    if (anyNA(colon_match)) {
+      .warn_not_found(colon_vars, columns, colon_match, verbose)
+      matches <- NA
+    } else {
+      start_pos <- match(colon_vars[1], columns)
+      end_pos <- match(colon_vars[2], columns)
+      if (!is.na(start_pos) && !is.na(end_pos)) {
+        matches <- start_pos:end_pos
+      } else {
+        matches <- NA
+      }
+    }
+    matches[!is.na(matches)]
   } else if (isTRUE(ignore_case)) {
+    # find columns, case insensitive
     matches <- match(toupper(x), toupper(columns))
     matches[!is.na(matches)]
   } else {
+    # find columns, case sensitive
     matches <- match(x, columns)
-    if (anyNA(matches) && verbose) {
-      insight::format_warning(
-        paste0(
-          "Following variable(s) were not found: ",
-          toString(x[is.na(matches)])
-        ),
-        .misspelled_string(
-          columns,
-          x[is.na(matches)],
-          default_message = "Possibly misspelled?"
-        )
-      )
+    if (anyNA(matches)) {
+      .warn_not_found(x, columns, matches, verbose)
     }
     matches[!is.na(matches)]
   }
 }
 
+# small helper, to avoid duplicated code
+.warn_not_found <- function(x, columns, matches, verbose = TRUE) {
+  if (verbose) {
+    insight::format_warning(
+      paste0(
+        "Following variable(s) were not found: ",
+        toString(x[is.na(matches)])
+      ),
+      .misspelled_string(
+        columns,
+        x[is.na(matches)],
+        default_message = "Possibly misspelled?"
+      )
+    )
+  }
+}
+
+
 # 3 types of symbols:
 # - unquoted variables
 # - objects that need to be evaluated, e.g data_find(iris, i) where