Merge branch 'dev'

gluc · Nov 12, 2023 · 808dd38 · 808dd38
2 parents 4a6ec7a + 0f58f6c
commit 808dd38
Show file tree

Hide file tree

Showing 28 changed files with 336 additions and 96 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -3,11 +3,13 @@
 ^\.travis\.yml$
 data_gen
 cran-comments.md
-cheat-sheet.md
+publish-cheat-sheet.md
+getting-started-with-development.md
 appveyor.yml
 travis-tool.sh.cmd
 Rprof.out
 ^appveyor\.yml$
 revdep
 README.md
 ^CRAN-RELEASE$
+^\.github$
diff --git a/.github/.gitignore b/.github/.gitignore
@@ -0,0 +1 @@
+*.html
diff --git a/.github/workflows/R-CMD-check.yaml b/.github/workflows/R-CMD-check.yaml
@@ -0,0 +1,49 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+
+name: R-CMD-check
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: macos-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,   r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,   r: 'release'}
+          - {os: ubuntu-latest,   r: 'oldrel-1'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
diff --git a/CRAN-RELEASE b/CRAN-RELEASE
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: data.tree
 Type: Package
 Title: General Purpose Hierarchical Data Structure
-Version: 1.0.0
-Date: 2020-07-31
+Version: 1.1.0
+Date: 2023-11-11
 Authors@R: c(
       person(
         "Russ", "Hyde",
@@ -48,7 +48,7 @@ Authors@R: c(
         "Christoph", "Glur"
         , role = c("aut", "cre")
         , comment = "R interface"
-        , email = "christoph.glur@ipub.com"
+        , email = "christoph.glur@powerpartners.pro"
       )
     )
 VignetteBuilder: 
@@ -84,9 +84,9 @@ Description: Create tree structures from hierarchical data, and traverse the
     data.frame and more. Useful for decision trees, machine learning, finance,
     conversion from and to JSON, and many other applications.
 License: GPL (>= 2)
-URL: http://github.com/gluc/data.tree
-BugReports: http://github.com/gluc/data.tree/issues
+URL: https://github.com/gluc/data.tree
+BugReports: https://github.com/gluc/data.tree/issues
 Depends:
     R (>= 3.5)
-RoxygenNote: 7.1.1
+RoxygenNote: 7.2.3
 Encoding: UTF-8
diff --git a/NEWS b/NEWS
@@ -1,5 +1,12 @@
 # All changes to data.tree are documented here.
 
+## Version 1.1.0
+- IMPROVE: Node names may no longer be `NA`.  It was not fully supported, and now it is an error. (#152)
+- FIX: changed lock_object to lock_objects (#149 thx to Olly Beagly)
+- FIX: help('data.tree') works again
+- IMPROVE: FromListSimple and as.Node.list now have an additional parameter 'interpretNullAsList'. See #169 for details.
+- IMPROVE: added parameter `row.names = FALSE`in `print.Node()` to hide row numbers when printing a data.tree.
+
 ## Version 1.0.0
 - IMPROVE: Replaced dependency on stringr by dependency on stringi, which make data.tree even more light-weight
 - CHANGE: Node serialization changed. In many cases, you might still be able to load previously saved data.tree objects, but then they do not correspond to the latest version.

diff --git a/R/data.tree.R → R/data.tree-package.R b/R/data.tree.R → R/data.tree-package.R
@@ -32,7 +32,17 @@
 #' For more specialized conversions, see \code{\link{as.dendrogram.Node}}, \code{\link{as.Node.dendrogram}}, 
 #' \code{\link{as.phylo.Node}} and \code{\link{as.Node.phylo}}
 #' 
-#' Finally, easy conversion options from and to JSON, YAML, igraph, and more exist.
+#' Finally, easy conversion options from and to list, dataframe, JSON, YAML, igraph, ape, rpart, party and more exist:
+#' 
+#' \itemize{
+#'  \item{list: both directions}
+#'  \item{dataframe: both directions}
+#'  \item{JSON, YAML: both directions, via lists}
+#'  \item{igraph: from igraph to data.tree}
+#'  \item{ape: both directions}
+#'  \item{rpart: from rpart to data.tree}
+#'  \item{party: from party to data.tree}
+#' }
 #'  
 #' @section Node and Reference Semantics:
 #'  
@@ -93,6 +103,7 @@
 #' 
 #' @seealso \code{\link{Node}}
 #' @seealso For more details, see the \code{data.tree} vignette by running: \code{vignette("data.tree")}
-#' @docType package
 #' @name data.tree
+#' @keywords internal
+"_PACKAGE"
 NULL
diff --git a/R/node.R b/R/node.R
@@ -38,6 +38,7 @@ NODE_RESERVED_NAMES_CONST <- c(
                                 'path',
                                 'pathString',
                                 'position',
+                                'printFormatters',
                                 'Prune',
                                 'Revert',
                                 'RemoveAttribute',
@@ -138,13 +139,19 @@ Node <- R6Class("Node",
                       initialize=function(name, check = c("check", "no-warn", "no-check"), ...) {
                         if (!missing(name)) {
                           name <- as.character(name)
+                          if (length(name) != 1) {
+                            stop("Node name must be a scalar")
+                          } else if (is.na(name)) {
+                            stop("Node name must be a non-NA character scalar")
+                          }
                           name <- CheckNameReservedWord(name, check)
                           private$p_name <- name
                         }
                         if (!missing(...)) {
                           args <- list(...)
                           mapply(FUN = function(arg, nme) self[[nme]] <- arg, args, names(args))
                         }
+
                         invisible (self)
                       },
 
@@ -550,7 +557,8 @@ Node <- R6Class("Node",
 
                       # End Traversal
                       #######################
-
+
+
 
                     ),
 
@@ -563,6 +571,32 @@ Node <- R6Class("Node",
                         else private$p_name <- changeName(self, private$p_name, value)
                       },
 
+                      #' @field printFormatters gets or sets the formatters used to print a \code{Node}.
+                      #' Set this as a list to a root node.
+                      #' The different formatters are h (horizontal), v (vertical), l (L), j (junction), and s (separator). 
+                      #' For example, you can set the formatters to \code{list(h = "\u2500" , v = "\u2502", l = "\u2514",  j = "\u251C", s = " ")}
+                      #' to get a similar behavior as in \code{fs::dir_tree()}.
+                      #' The defaults are: \code{list(h = "--" , v = "\u00A6", l = "\u00B0", j = "\u00A6", s = " ")}
+                      printFormatters = function(value) {
+                        if (missing(value)) {
+                          # if private$p_print_formatters is not set, return default
+                          if (is.null(private$p_print_formatters)) {
+                            pf <- list(h = "--" , 
+                                       v = "\u00A6", 
+                                       l = "\u00B0", 
+                                       j = "\u00A6",
+                                       s = " "
+                                       )
+                          } else {
+                            pf <- private$p_print_formatters
+                          }
+
+                          return (pf)
+                        }
+                        private$p_print_formatters <- value
+                      },   
+
+
                       #' @field parent Gets or sets the parent \code{Node} of a \code{Node}. Only set this if you know what you are doing, as you might mess up the tree structure!
                       parent = function(value) {
                         if (missing(value)) return (private$p_parent)
@@ -618,15 +652,13 @@ Node <- R6Class("Node",
 
                       #' @field fields Will be deprecated, use \code{attributes} instead
                       fields = function() {
-                        print("Node$fields will be deprecated in the next release. Please use Node$attributes instead.")
-                        # .Deprecated("Node$attributes", old = "Node$fields")
+                        .Deprecated("Node$attributes", old = "Node$fields")
                         return(self$attributes)
                       },
 
                       #' @field fieldsAll Will be deprecated, use \code{attributesAll} instead
                       fieldsAll = function() {
-                        print("Node$fieldsAll will be deprecated in the next release. Please use Node$attributesAll instead.")
-                        # .Deprecated("Node$attributesAll", old = "Node$fieldsAll")
+                        .Deprecated("Node$attributesAll", old = "Node$fieldsAll")
                         return(self$attributesAll)
                       },
 

diff --git a/R/node_actives.R b/R/node_actives.R
@@ -37,7 +37,6 @@ isNotLeaf <- function(node) {
 }
 
 
-
 changeName <- function(node, oldName, newName) {
   if(!isRoot(node)) {
     rm(list = oldName, envir = node$parent)
@@ -47,27 +46,27 @@ changeName <- function(node, oldName, newName) {
   return (newName)
 }
 
-
 #' @export
 .separator <- function(self) {
   if (isRoot(self)) return("")
-  if (self$position == self$parent$count) mySeparator <- paste0(" ", "\u00B0", "--")
-  else mySeparator <- paste0(" ", "\u00A6", "--")
+  if (self$position == self$parent$count) mySeparator <- paste0(self$root$printFormatters$s, self$root$printFormatters$l, self$root$printFormatters$h)
+  else mySeparator <- paste0(self$root$printFormatters$s, self$root$printFormatters$j, self$root$printFormatters$h)
   return (paste0(.parentSeparator(self$parent), mySeparator))
 }
 
 #' @export
 .parentSeparator <- function(self) {
   if (isRoot(self)) return("")
-  if (self$position == self$parent$count) mySeparator <- "    "
-  else mySeparator <- paste0(" ", "\u00A6", "  ")
+
+  if (self$position == self$parent$count) mySeparator <- paste0(rep(self$root$printFormatters$s, 4), collapse = "")
+  else mySeparator <- paste0(self$root$printFormatters$s, self$root$printFormatters$v, self$root$printFormatters$s, self$root$printFormatters$s)
   paste0(.parentSeparator(self$parent), mySeparator)
-
+  
 }
 
 #' Calculate the average number of branches each non-leaf has
 #'
-#' @param node The node
+#' @param node The node to calculate the average branching factor for
 #' @export
 averageBranchingFactor <- function(node) {
   t <- Traverse(node, filterFun = isNotLeaf)

diff --git a/R/node_conversion_list.R b/R/node_conversion_list.R
@@ -8,6 +8,8 @@
 #' @param childrenName The name of the element that contains the child list (applies to mode 'explicit' only).
 #' @param nodeName A name suggestion for x, if the name cannot be deferred otherwise. This is for example the case for
 #' the root with mode explicit and named lists.
+#' @param interpretNullAsList If \code{TRUE}, then \code{NULL}-valued lists are interpreted as child nodes. Else, they are interpreted as attributes.
+#' This has only an effect if \code{mode} is "simple".
 #' @param ... Any other argument to be passed to generic sub implementations
 #' 
 #' @examples
@@ -57,7 +59,7 @@
 #' @family as.Node
 #' 
 #' @export
-as.Node.list <- function(x, mode = c("simple", "explicit"), nameName = "name", childrenName = "children", nodeName = NULL, check = c("check", "no-warn", "no-check"), ...) {
+as.Node.list <- function(x, mode = c("simple", "explicit"), nameName = "name", childrenName = "children", nodeName = NULL, interpretNullAsList = FALSE, check = c("check", "no-warn", "no-check"), ...) {
   mode <- mode[1]
   check <- check[1]
 
@@ -120,7 +122,10 @@ as.Node.list <- function(x, mode = c("simple", "explicit"), nameName = "name", c
 
   #children
   if (is.character(x)) return (n)
-  if (mode == 'simple') children <- x[vapply(x, is.list, logical(1))]
+  if (mode == 'simple') {
+    if (interpretNullAsList) children <- x[vapply(x, function(y) is.list(y) || is.null(y), logical(1))]
+    else children <- x[vapply(x, is.list, logical(1))]
+  }
   else if (mode == 'explicit') children <- x[[childrenName]]
 
   if (length(children) == 0) return (n)
@@ -138,7 +143,7 @@ as.Node.list <- function(x, mode = c("simple", "explicit"), nameName = "name", c
     if (nchar(childName) == 0) childName <- i
     child <- children[[i]]
 
-    childNode <- as.Node.list(child, mode, nameName, childrenName, nodeName = childName, check = check, ...)
+    childNode <- as.Node.list(child, mode, nameName, childrenName, nodeName = childName, interpretNullAsList = interpretNullAsList, check = check, ...)
     n$AddChildNode(childNode)
 
   }
@@ -164,8 +169,8 @@ FromListExplicit <- function(explicitList, nameName = "name", childrenName = "ch
 #' interpreted as a child \code{Node}
 #' 
 #' @export
-FromListSimple <- function(simpleList, nameName = "name", nodeName = NULL, check = c("check", "no-warn", "no-check")) {
-  as.Node.list(simpleList, mode = "simple", nameName = nameName, nodeName = nodeName, check = check)
+FromListSimple <- function(simpleList, nameName = "name", nodeName = NULL, interpretNullAsList = FALSE, check = c("check", "no-warn", "no-check")) {
+  as.Node.list(simpleList, mode = "simple", nameName = nameName, nodeName = nodeName, interpretNullAsList = interpretNullAsList, check = check)
 }
 
 

diff --git a/R/node_methods.R b/R/node_methods.R
@@ -16,6 +16,7 @@
 #' everywhere in the tree, according to their level. If pruneFun is provided, then pruneMethod is ignored.
 #' @param limit The maximum number of nodes to print. Can be \code{NULL} if the
 #' entire tree should be printed.
+#' @param row.names If \code{TRUE} (default), then the row names are printed out. Else, they are not.
 #'
 #' @inheritParams ToDataFrameTree
 #'
@@ -38,7 +39,7 @@
 #' 
 #'
 #' @export
-print.Node <- function(x, ..., pruneMethod = c("simple", "dist", NULL), limit = 100, pruneFun = NULL) {
+print.Node <- function(x, ..., pruneMethod = c("simple", "dist", NULL), limit = 100, pruneFun = NULL, row.names = T) {
   if (length(pruneFun) > 0) pruneMethod <- NULL
   pruneMethod <- pruneMethod[1]
   if (length(pruneMethod) > 0 && length(limit) > 0) {
@@ -56,7 +57,7 @@ print.Node <- function(x, ..., pruneMethod = c("simple", "dist", NULL), limit =
   }
 
   df <- ToDataFrameTree(x, format = TRUE, ..., pruneFun = pruneFun)
-  print(df, na.print = "")
+  print(df, na.print = "", row.names = row.names)
 }
 
 

diff --git a/README.md b/README.md
@@ -2,7 +2,10 @@ CRAN: [![CRAN Version](http://www.r-pkg.org/badges/version/data.tree)](https://c
 
 Master: [![Build Status master](https://travis-ci.org/gluc/data.tree.svg?branch=master)](https://travis-ci.org/gluc/data.tree) [![Windows Build status]( https://ci.appveyor.com/api/projects/status/github/gluc/data.tree?branch=master&svg=true)](https://ci.appveyor.com/project/gluc/data.tree) [![codecov.io](http://codecov.io/github/gluc/data.tree/coverage.svg?branch=master)](http://codecov.io/github/gluc/data.tree?branch=master)
 
-Dev: [![Build Status dev](https://travis-ci.org/gluc/data.tree.svg?branch=dev)](https://travis-ci.org/gluc/data.tree) [![Windows Build status]( https://ci.appveyor.com/api/projects/status/github/gluc/data.tree?branch=dev&svg=true)](https://ci.appveyor.com/project/gluc/data.tree) [![codecov.io](http://codecov.io/github/gluc/data.tree/coverage.svg?branch=dev)](http://codecov.io/github/gluc/data.tree?branch=dev)
+<!-- badges: start -->
+[![R-CMD-check](https://github.com/gluc/data.tree/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/gluc/data.tree/actions/workflows/R-CMD-check.yaml)
+<!-- badges: end -->
+
 
 # data.tree
 An R package to manage hierarchical data and tree structures

diff --git a/data/acme.rda b/data/acme.rda
diff --git a/data/mushroom.rda b/data/mushroom.rda
diff --git a/data_gen/mushroom.R b/data_gen/mushroom.R
@@ -4,3 +4,4 @@ points <- c('yes', 'no', 'yes', 'no', 'no')
 edible <- c('toxic', 'edible', 'edible', 'edible', 'edible')
 mushroom <- data.frame(color = color, size = size, points = points, edibility = edible)
 save(mushroom, file = "data/mushroom.rda", compress = "xz")
+
diff --git a/getting-started-with-development.md b/getting-started-with-development.md
@@ -0,0 +1,15 @@
+# Dev Guide
+
+To develop on a new environment, you need to:
+
+1. pull from CRAN (dev branch)
+2. install R
+3. install RStudio
+4. install RTools (https://cran.rstudio.com/bin/windows/Rtools/)
+4. install tinytex
+  1. install.packages('tinytex')
+  2. tinytex::install_tinytex()
+  3. tinytex:::install_yihui_pkgs()
+5. re-start RStudio
+6. install devtools by running `install.packages("devtools")`
+
diff --git a/man/NODE_RESERVED_NAMES_CONST.Rd b/man/NODE_RESERVED_NAMES_CONST.Rd