Merge pull request #151 from lorenzwalthert/rm_flat_relicts

Remove flat relicts completely (#151).

Author: lorenzwalthert

R/parsed.R

@@ -1,81 +1,3 @@
-#' Parse and pre-process character vector
-#'
-#' @description The function obtains detailed parse information for `text` via
-#'   [utils::getParseData()] and does some minimal pre-processing by calling
-#'   [enhance_parse_data()].
-#' @inheritSection enhance_parse_data Details
-#' @param text A character vector.
-#' @return A pre-processed parse table.
-#' @details Roughly speaking, this is the inverse operation of
-#'   [serialize_parse_data_flat()], which turns a parse table into a character
-#'   vector, since `compute_parse_data_flat_enhanced()` turns a character vector
-#'   into a parse table.
-compute_parse_data_flat_enhanced <- function(text) {
-  parse_data <- tokenize(text)
-  pd_flat <- enhance_parse_data(parse_data)
-  pd_flat
-}
-
-#' Pre-processing parse data
-#'
-#' Modifies the parse table minimally by applying some pre-processing steps.
-#' @section Details:
-#' Preprocessing includes
-#'   * removing non-terminal entries.
-#'   * removing columns id, parent and terminal.
-#'   * adding a start token.
-#'   * adding line-break and space information.
-#'   * removing spaces in comments at the end of the line.
-#' @param parse_data a parse table.
-#' @return a pre-processed parse table.
-enhance_parse_data <- function(parse_data) {
-  parse_data_filtered <-
-    parse_data %>%
-    filter_(~terminal) %>%
-    select_(~-id, ~-parent) %>%
-    arrange_(~line1, ~col1, ~line2, ~col2) %>%
-    bind_rows(
-      tibble(line1 = 1L, col1 = 0L, line2 = 1L, col2 = 0L,
-             token = "START", text = ""),
-      .
-    )
-
-  parse_data_filled <-
-    parse_data_filtered %>%
-    create_filler()
-
-  parse_data_comment_eol <- parse_data_filled
-
-  parse_data_comment_eol$text <-
-    if_else(parse_data_comment_eol$token == "COMMENT",
-            gsub(" +$", "", parse_data_comment_eol$text),
-            parse_data_comment_eol$text)
-
-  parse_data_comment_eol
-}
-
-#' Verify parse data modifications
-#'
-#' @description Check whether serializing the parse data results in the same
-#' number of lines as the initial data that should be styled.
-#' @param pd_flat A parse table.
-#' @param text A character vector with the initial text to compare against.
-#' @return If the verification is successful, `pd` is returned, with empty
-#'   lines at the end of `text` stripped. \cr
-#'   Otherwise, an error is thrown.
-#' @seealso [serialize_parse_data_flat()]
-verify_roundtrip <- function(pd_flat, text) {
-  roundtrip <- serialize_parse_data_flat(pd_flat)
-
-  if (length(roundtrip) < length(text)) {
-    stopifnot(text[-seq_along(roundtrip)] == "")
-    text <- text[seq_along(roundtrip)]
-  }
-
-  stopifnot(identical(text, roundtrip))
-  text
-}
-
 #' Enrich parse table with space and linebreak information
 #'
 #' This function computes difference (as column and line difference) between two

R/serialize.R

@@ -1,74 +1,3 @@
-#' Serialize a nested parse table
-#'
-#' Helper function that recursively extracts terminals from a nested tibble.
-#' @param pd_nested A nested parse table.
-#' @param pass_indent Level of indention of a token.
-#' @return A character vector with all terminal tokens in `pd_nested` plus
-#'   the appropriate amount of white spaces and line breaks are inserted between
-#'   them.
-#' @importFrom purrr pmap
-serialize_parse_data_nested_helper <- function(pd_nested, pass_indent) {
-  out <- pmap(list(pd_nested$terminal, pd_nested$text, pd_nested$child,
-                   pd_nested$spaces, pd_nested$lag_newlines, pd_nested$indent),
-              function(terminal, text, child, spaces, lag_newlines, indent) {
-                total_indent <- pass_indent + indent
-                preceding_linebreak <- if_else(lag_newlines > 0, 1, 0)
-                if (terminal) {
-                  c(add_newlines(lag_newlines),
-                    add_spaces(total_indent * preceding_linebreak),
-                    text,
-                    add_spaces(spaces))
-                } else {
-                  c(add_newlines(lag_newlines),
-                    add_spaces(total_indent * preceding_linebreak),
-                    serialize_parse_data_nested_helper(child, total_indent),
-                    add_spaces(spaces))
-                }
-              }
-  )
-  out
-}
-
-#' Serialize a nested parse table
-#'
-#' Collapses a nested parse table into its character vector representation.
-#' @param pd_nested A nested parse table with line break, spaces and indention
-#'   information.
-#' @return A character string.
-serialize_parse_data_nested <- function(pd_nested) {
-  out <- c(add_newlines(start_on_line(pd_nested) - 1),
-           serialize_parse_data_nested_helper(pd_nested, pass_indent = 0)) %>%
-    unlist() %>%
-    paste0(collapse = "") %>%
-    strsplit("\n", fixed = TRUE) %>%
-    .[[1L]] %>%
-    trimws(which = "right")
-  out
-}
-
-#' Serialize Flat Parse Data
-#'
-#' Collapses a parse table into character vector representation.
-#' @param pd_flat A parse table.
-#' @details
-#'   The function essentially collapses the column text of `pd_flat`
-#'   while taking into account space and linebreak information from the columns
-#'   newlines and spaces. \cr
-#'   Roughly speaking, this is the inverse operation of
-#'   [compute_parse_data_flat_enhanced()], which turns a character vector into a
-#'   parse table, since `serialize_parse_data_flat()` turns a parse table back
-#'   into a character vector.
-serialize_parse_data_flat <- function(pd_flat) {
-  pd_flat %>%
-    summarize_(
-      text_ws = ~paste0(
-        text, newlines_and_spaces(newlines, spaces),
-        collapse = "")) %>%
-    .[["text_ws"]] %>%
-    strsplit("\n", fixed = TRUE) %>%
-    .[[1L]]
-}
-
 #' Serialize flattened parse data
 #'
 #' Collapses a flattened parse table into character vector representation.

R/utils.R

@@ -9,21 +9,19 @@ rep_char <- function(char, times) {
   paste(rep.int(char, times), collapse = "")
 }
 
-#' concentrate newlines an spaces in a string
+#' Concentrate newlines or spaces in a string
 #'
-#' @param newlines Scalar indicating how many newlines ("\ n") should returned.
-#' @param spaces Scalar indicating how many spaces should be appended to the
-#'   newlines.
+#' @param n Scalar indicating how many characters should be concentrated
 #' @return A string.
-#' @importFrom purrr map2
-newlines_and_spaces <- function(newlines, spaces) {
-  map2(newlines, spaces, ~paste0(rep_char("\n", .x), rep_char(" ", .y)))
-}
+#' @name add_spaces_or_newlines
+NULL
 
+#' @rdname add_spaces_or_newlines
 add_newlines <- function(n) {
   rep_char("\n", n)
 }
 
+#' @rdname add_spaces_or_newlines
 add_spaces <- function(n) {
   rep_char(" ", n)
 }

R/visit.R

@@ -53,6 +53,7 @@ visit_one <- function(pd_flat, funs) {
 #'   relative in `pd_nested`) will be converted into absolute.
 #' @inherit context_towards_terminals
 #' @seealso context_towards_terminals visitors
+#' @importFrom purrr pmap
 context_to_terminals <- function(pd_nested,
                                  outer_lag_newlines,
                                  outer_indent,