Clean-up styling rules

DESCRIPTION

@@ -68,10 +68,10 @@ Collate:
     'roxygen-examples-find.R'
     'roxygen-examples-parse.R'
     'roxygen-examples.R'
-    'rules-line-break.R'
-    'rules-other.R'
-    'rules-replacement.R'
-    'rules-spacing.R'
+    'rules-indention.R'
+    'rules-line-breaks.R'
+    'rules-spaces.R'
+    'rules-tokens.R'
     'serialize.R'
     'set-assert-args.R'
     'style-guides.R'

NEWS.md

@@ -14,9 +14,12 @@
 - added an option for disabling all communication when using the package
   (`styler.quiet`) (#640).
 
-- `scope` in [tidyverse_style()] can now be specified with higher granularity
-  through [I()], e.g. `I(c('spaces', 'tokens'))` allows it to style tokens
-  without styling line breaks and indention (#704). 
+- `scope` in `tidyverse_style()` can now be specified with higher granularity
+  through `I()`, e.g. `I(c('spaces', 'tokens'))` allows us to style spaces and 
+  tokens without styling line breaks and indention. Previously, only a string 
+  was allowed and all less invasive scopes were included, e.g. if you wanted to 
+  style tokens, you had to always also style spaces, indention, line breaks as 
+  well (#705, #707).
 
 ## Major changes
 

R/indent.R

@@ -8,81 +8,6 @@
 #' @keywords internal
 NULL
 
-#' @describeIn update_indention Inserts indention based on round, square and
-#'   curly brackets.
-#' @keywords internal
-indent_braces <- function(pd, indent_by) {
-  indent_indices <- compute_indent_indices(
-    pd,
-    token_opening = c("'('", "'['", "'{'"),
-    token_closing = c("')'", "']'", "'}'")
-  )
-  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
-  set_unindention_child(pd, token = "')'", unindent_by = indent_by)
-}
-
-#' @describeIn update_indention Indents *all* tokens after `token` - including
-#'   the last token.
-#' @keywords internal
-indent_op <- function(pd,
-                      indent_by,
-                      token = c(
-                        math_token,
-                        logical_token,
-                        special_token,
-                        "LEFT_ASSIGN",
-                        "EQ_ASSIGN",
-                        "'$'"
-                      )) {
-  indent_indices <- compute_indent_indices(pd, token)
-  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
-  pd
-}
-
-#' Revert the indention of function declaration header
-#'
-#' Necessary for consistent indention of the function declaration header.
-#' @param pd A parse table.
-#' @seealso set_unindention_child update_indention_ref_fun_dec
-#' @keywords internal
-unindent_fun_dec <- function(pd) {
-  if (is_function_dec(pd)) {
-    idx_closing_brace <- which(pd$token %in% "')'")
-    fun_dec_head <- seq2(2L, idx_closing_brace)
-    pd$indent[fun_dec_head] <- 0L
-  }
-  pd
-}
-
-#' @describeIn update_indention Updates indention for token EQ_SUB. Only differs
-#'   from [indent_op()] in the sense that not all subsequent tokens in the parse
-#'   table are necessarily indented, as `EQ_SUB` and `EQ_FORMALS` can occur
-#'   multiple times in a parse table.
-#'   occurs is not indented (see[compute_indent_indices()])
-#' @keywords internal
-indent_eq_sub <- function(pd,
-                          indent_by,
-                          token = c("EQ_SUB", "EQ_FORMALS")) {
-  eq_sub <- which(pd$token %in% token)
-  if (length(eq_sub) == 0) {
-    return(pd)
-  }
-  has_line_break <- which(pd$lag_newlines > 0)
-  indent_indices <- intersect(eq_sub + 1, has_line_break)
-  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
-  pd
-}
-
-
-#' @describeIn update_indention Is used to indent for / while / if / if-else
-#'   statements that do not have curly parenthesis.
-#' @keywords internal
-indent_without_paren <- function(pd, indent_by = 2) {
-  pd %>%
-    indent_without_paren_for_while_fun(indent_by) %>%
-    indent_without_paren_if_else(indent_by)
-}
-
 #' @describeIn update_indention Is used to indent for and statements and function
 #'   definitions without parenthesis.
 #' @keywords internal
@@ -295,8 +220,8 @@ pd_is_multi_line <- function(pd) {
 #' Update the newlines attribute
 #'
 #' As we work only with the `lag_newlines` attribute for setting the line
-#' breaks, (R/rules-line_break.R) but we need `newlines` to determine
-#' whether or not to set `spaces` (R/rules-spacing.R), we have to update the
+#' breaks (`R/rules-line_breaks.R`), but we need `newlines` to determine
+#' whether or not to set `spaces` (`R/rules-spaces.R`), we have to update the
 #' attribute. We cannot simply use `dplyr::lead(pd$lag_newlines)` since we would
 #' lose information for the last token. `spaces` is left as is in
 #' R/rules-spacing.R for tokens at the end of a line since this allows styling

R/reindent.R

@@ -1,11 +1,3 @@
-
-#' Update the indention reference
-#'
-#' @param pd_nested A nested parse table.
-#' @name update_indention_ref
-#' @keywords internal
-NULL
-
 # @describeIn update_indention_ref Updates the reference pos_id for all
 #   tokens in `pd_nested` if `pd_nested` contains a function call. Tokens that
 #   start on the same line as the opening parenthesis, are not themselves
@@ -45,28 +37,6 @@ NULL
 #   pd_nested
 # }
 
-#' @describeIn update_indention_ref Updates the reference pos_id for all
-#'   tokens in `pd_nested` if `pd_nested` contains a function declaration.
-#'   Tokens inside a function declaration are are re-indented,
-#'   that is, they are indented up to the level at which the token FUNCTION
-#'   ends in terms of col2.
-#' @examples
-#' \dontrun{
-#' a <- function(x,
-#'               y) {
-#'   x + y
-#' }
-#' }
-#' @importFrom rlang seq2
-#' @keywords internal
-update_indention_ref_fun_dec <- function(pd_nested) {
-  if (pd_nested$token[1] == "FUNCTION") {
-    seq <- seq2(3, nrow(pd_nested) - 2)
-    pd_nested$indention_ref_pos_id[seq] <- pd_nested$pos_id[2]
-  }
-  pd_nested
-}
-
 #' Apply reference indention to tokens
 #'
 #' Applies the reference indention created with functions

R/rules-indention.R

@@ -0,0 +1,102 @@
+#' @describeIn update_indention Inserts indention based on round, square and
+#'   curly brackets.
+#' @keywords internal
+indent_braces <- function(pd, indent_by) {
+  indent_indices <- compute_indent_indices(
+    pd,
+    token_opening = c("'('", "'['", "'{'"),
+    token_closing = c("')'", "']'", "'}'")
+  )
+  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
+  set_unindention_child(pd, token = "')'", unindent_by = indent_by)
+}
+
+#' Revert the indention of function declaration header
+#'
+#' Necessary for consistent indention of the function declaration header.
+#' @param pd A parse table.
+#' @seealso set_unindention_child update_indention_ref_fun_dec
+#' @keywords internal
+unindent_fun_dec <- function(pd) {
+  if (is_function_dec(pd)) {
+    idx_closing_brace <- which(pd$token %in% "')'")
+    fun_dec_head <- seq2(2L, idx_closing_brace)
+    pd$indent[fun_dec_head] <- 0L
+  }
+  pd
+}
+
+#' @describeIn update_indention Indents *all* tokens after `token` - including
+#'   the last token.
+#' @keywords internal
+indent_op <- function(pd,
+                      indent_by,
+                      token = c(
+                        math_token,
+                        logical_token,
+                        special_token,
+                        "LEFT_ASSIGN",
+                        "EQ_ASSIGN",
+                        "'$'"
+                      )) {
+  indent_indices <- compute_indent_indices(pd, token)
+  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
+  pd
+}
+
+#' @describeIn update_indention Updates indention for token EQ_SUB. Only differs
+#'   from [indent_op()] in the sense that not all subsequent tokens in the parse
+#'   table are necessarily indented, as `EQ_SUB` and `EQ_FORMALS` can occur
+#'   multiple times in a parse table.
+#'   occurs is not indented (see[compute_indent_indices()])
+#' @keywords internal
+indent_eq_sub <- function(pd,
+                          indent_by,
+                          token = c("EQ_SUB", "EQ_FORMALS")) {
+  eq_sub <- which(pd$token %in% token)
+  if (length(eq_sub) == 0) {
+    return(pd)
+  }
+  has_line_break <- which(pd$lag_newlines > 0)
+  indent_indices <- intersect(eq_sub + 1, has_line_break)
+  pd$indent[indent_indices] <- pd$indent[indent_indices] + indent_by
+  pd
+}
+
+#' @describeIn update_indention Is used to indent for / while / if / if-else
+#'   statements that do not have curly parenthesis.
+#' @keywords internal
+indent_without_paren <- function(pd, indent_by = 2) {
+  pd %>%
+    indent_without_paren_for_while_fun(indent_by) %>%
+    indent_without_paren_if_else(indent_by)
+}
+
+#' Update the indention reference
+#'
+#' @param pd_nested A nested parse table.
+#' @name update_indention_ref
+#' @keywords internal
+NULL
+
+#' @describeIn update_indention_ref Updates the reference pos_id for all
+#'   tokens in `pd_nested` if `pd_nested` contains a function declaration.
+#'   Tokens inside a function declaration are are re-indented,
+#'   that is, they are indented up to the level at which the token FUNCTION
+#'   ends in terms of col2.
+#' @examples
+#' \dontrun{
+#' a <- function(x,
+#'               y) {
+#'   x + y
+#' }
+#' }
+#' @importFrom rlang seq2
+#' @keywords internal
+update_indention_ref_fun_dec <- function(pd_nested) {
+  if (pd_nested$token[1] == "FUNCTION") {
+    seq <- seq2(3, nrow(pd_nested) - 2)
+    pd_nested$indention_ref_pos_id[seq] <- pd_nested$pos_id[2]
+  }
+  pd_nested
+}

R/rules-spacing.R → R/rules-spaces.R

@@ -121,45 +121,6 @@ remove_space_after_unary_pm_nested <- function(pd) {
   pd
 }
 
-#' Replace single quotes with double quotes
-#'
-#' We do not use `deparse()` as in previous implementations but `paste0()` since
-#' the former approach escapes the reverse backslash in the line break character
-#' `\\n` whereas the solution with `paste0()` does not.
-#' @examples
-#' style_text("'here
-#' is a string
-#' '")
-#' @importFrom purrr map map_chr
-#' @param pd_flat A flat parse table.
-#' @importFrom rlang is_empty
-#' @keywords internal
-fix_quotes <- function(pd_flat) {
-  str_const <- which(pd_flat$token == "STR_CONST")
-  if (is_empty(str_const)) {
-    return(pd_flat)
-  }
-
-  pd_flat$text[str_const] <- map(pd_flat$text[str_const], fix_quotes_one)
-  pd_flat
-}
-
-#' @importFrom rlang is_empty
-fix_quotes_one <- function(x) {
-  rx <- "^'([^\"]*)'$"
-  i <- grep(rx, x)
-  if (is_empty(i)) {
-    return(x)
-  }
-
-  # replace outer single quotes
-  xi <- gsub(rx, '"\\1"', x[i])
-
-  # Replace inner escaped quotes (\') by ' and keep all other instances of \., including \\
-  x[i] <- gsub("\\\\(')|(\\\\[^'])", "\\1\\2", xi)
-  x
-}
-
 remove_space_before_opening_paren <- function(pd_flat) {
   paren_after <- pd_flat$token == "'('"
   if (!any(paren_after)) {

R/rules-other.R → R/rules-tokens.R

@@ -1,3 +1,21 @@
+force_assignment_op <- function(pd) {
+  to_replace <- pd$token == "EQ_ASSIGN"
+  pd$token[to_replace] <- "LEFT_ASSIGN"
+  pd$text[to_replace] <- "<-"
+  pd
+}
+
+
+resolve_semicolon <- function(pd) {
+  is_semicolon <- pd$token == "';'"
+  if (!any(is_semicolon)) {
+    return(pd)
+  }
+  pd$lag_newlines[lag(is_semicolon)] <- 1L
+  pd <- pd[!is_semicolon, ]
+  pd
+}
+
 add_brackets_in_pipe <- function(pd) {
   is_pipe <- pd$token == "SPECIAL-PIPE"
   Reduce(add_brackets_in_pipe_one, which(is_pipe), init = pd)
@@ -149,3 +167,42 @@ if_for_while_part_requires_braces <- function(pd, key_token) {
   child <- pd$child[[next_non_comment(pd, pos_first_key_token)]]
   pd_is_multi_line(pd) && !is_curly_expr(child)
 }
+
+#' Replace single quotes with double quotes
+#'
+#' We do not use `deparse()` as in previous implementations but `paste0()` since
+#' the former approach escapes the reverse backslash in the line break character
+#' `\\n` whereas the solution with `paste0()` does not.
+#' @examples
+#' style_text("'here
+#' is a string
+#' '")
+#' @importFrom purrr map map_chr
+#' @param pd_flat A flat parse table.
+#' @importFrom rlang is_empty
+#' @keywords internal
+fix_quotes <- function(pd_flat) {
+  str_const <- which(pd_flat$token == "STR_CONST")
+  if (is_empty(str_const)) {
+    return(pd_flat)
+  }
+
+  pd_flat$text[str_const] <- map(pd_flat$text[str_const], fix_quotes_one)
+  pd_flat
+}
+
+#' @importFrom rlang is_empty
+fix_quotes_one <- function(x) {
+  rx <- "^'([^\"]*)'$"
+  i <- grep(rx, x)
+  if (is_empty(i)) {
+    return(x)
+  }
+
+  # replace outer single quotes
+  xi <- gsub(rx, '"\\1"', x[i])
+
+  # Replace inner escaped quotes (\') by ' and keep all other instances of \., including \\
+  x[i] <- gsub("\\\\(')|(\\\\[^'])", "\\1\\2", xi)
+  x
+}