Github user sun-rui commented on a diff in the pull request: https://github.com/apache/spark/pull/8920#discussion_r40645086 --- Diff: R/pkg/R/DataFrame.R --- @@ -1848,3 +1848,78 @@ setMethod("crosstab", sct <- callJMethod(statFunctions, "crosstab", col1, col2) collect(dataFrame(sct)) }) + +#' Sort +#' +#' Sort a DataFrame by the specified column(s). +#' +#' @param x A DataFrame to be sorted. +#' @param by A character column or Column Object indicating the field to sort on. +#' If sorting column is a Column object, we need to embrace the column with asc or desc +#' keyword. The 'decreasing' argument does not apply to Column Object. It only applies to +#' character column names +#' @param decreasing Orderings for each sorting column +#' @param ... Additional sorting fields +#' @return A DataFrame where elements are sorted by input sorting columns. +#' @rdname sort +#' @name sort +#' @aliases orderby +#' @export +#' @examples +#'\dontrun{ +#' sc <- sparkR.init() +#' sqlContext <- sparkRSQL.init(sc) +#' path <- "path/to/file.json" +#' df <- jsonFile(sqlContext, path) +#' sort(df, col="col1") +#' sort(df, decreasing=FALSE, "col2") +#' sort(df, decreasing=TRUE, "col1") +#' sort(df, c(TRUE,FALSE), "col1","col2") +#' sort(df, col=list(asc(df$col1), desc(df$col2))) +#' sort(df, col=desc(df$col1)) +#' } +setMethod("sort", + signature(x = "DataFrame"), + function(x, decreasing=FALSE, col, ...) { + + # all sorting columns + by <- c(col, ...) + + if (class(by) == "character"){ + if (length(decreasing) == 1){ + # in case only 1 boolean argument - decreasing value is specified, it will be used for all columns + decreasing <- rep(decreasing,length(by)) + } else if (length(decreasing) != length(by)){ + stop("Arguments 'col' and 'decreasing' must have the same length") + } + + # creates a string array by replacing TRUE/FALSE correspondingly by "desc"/"asc" + sortOrder <- ifelse (decreasing == FALSE, "asc", decreasing) + sortOrder <- ifelse (decreasing == TRUE, "desc", sortOrder) + + # concatenates dataframe with the column names, example: c("x$Species", "x$Petal_Width") + colDFConcat <- paste("x", by, sep = "$") + + # embraces columns with order - asc/desc + # example: c("asc(x$Species)", "desc(x$Petal_Length)" ) + colDFOrderConcat <- paste(sortOrder, "(", colDFConcat, ")", collapse = ",") + + # concatenates all ordered columns to a list + # example: "list(asc(x$Species), desc(x$Petal_Length))" + colDFOrderConcatList <- paste("list(", colDFOrderConcat, ")", collapse = "") + + # builds columns of type Column, example: [[1]] Column Species ASC + # [[2]] Column Petal_Length DESC + resCols <- eval(parse(t=colDFOrderConcatList)) + jcols <- lapply(resCols, function(c) { + c@jc + }) + } else { + jcols <- lapply(by, function(c) { --- End diff -- If we support Column parameters, then the "decreasing" parameter makes no sense. I prefer we don't support Column parameters (As the existing arrange() and orderBy() is flexible enough for this usage)
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org