Add functionality to read and merge gender data to author data

util-data.R

@@ -23,6 +23,7 @@
 ## Copyright 2019-2020 by Anselm Fehnker <anselm@muenster.de>
 ## Copyright 2020-2021 by Niklas Schneider <s8nlschn@stud.uni-saarland.de>
 ## Copyright 2021 by Johannes Hostert <s8johost@stud.uni-saarland.de>
+## Copyright 2021 by Mirabdulla Yusifli <s8miyusi@stud.uni-saarland.de>
 ## All Rights Reserved.
 
 
@@ -167,6 +168,7 @@ ProjectData = R6::R6Class("ProjectData",
         pasta = create.empty.pasta.list(), # data.frame
         pasta.mails = create.empty.pasta.list(), # data.frame
         pasta.commits = create.empty.pasta.list(), # data.frame
+        gender = create.empty.gender.list(), # data.frame
         ## timestamps of mail, issue and commit data
         data.timestamps = data.frame(start = numeric(0), end = numeric(0)), # data.frame
 
@@ -633,6 +635,28 @@ ProjectData = R6::R6Class("ProjectData",
             logging::logdebug("update.pasta.data: finished.")
         },
 
+        #' Update the gender related fields of: \code{authors}
+        #'
+        #' This method should be called whenever the field \code{gender} is changed.
+        update.gender.data = function() {
+            logging::logdebug("update.gender.data: starting.")
+
+            ## update author data by attaching gender data
+            if (!is.null(private$authors)) {
+
+                ## remove previous gender data
+                private$authors["gender"] = NULL
+
+                ## merge gender data
+                private$authors = merge(private$authors, private$gender,
+                                    by = "author.name", all.x = TRUE, sort = FALSE)
+
+            }
+
+            logging::logdebug("update.gender.data: finished.")
+        },
+
+
         ## * * synchronicity data ------------------------------------------
 
         #' Update the column \code{synchronicity} that is appended to commits using the currently available
@@ -790,6 +814,7 @@ ProjectData = R6::R6Class("ProjectData",
             private$pasta.mails = create.empty.pasta.list()
             private$pasta.commits = create.empty.pasta.list()
             private$synchronicity = create.empty.synchronicity.list()
+            private$gender = create.empty.gender.list()
         },
 
         ## * * configuration -----------------------------------------------
@@ -923,6 +948,14 @@ ProjectData = R6::R6Class("ProjectData",
             return(data.path)
         },
 
+        #' Get the absolute path to the result folder for gender data.
+        #'
+        #' @return the path to the gender data
+        get.data.path.gender = function() {
+            data.path = private$project.conf$get.value("datapath.gender")
+            return(data.path)
+        },
+
         #' Get the absolute path to the range's result folder for synchronicity data.
         #'
         #' @return the path to the synchronicity files
@@ -1249,6 +1282,33 @@ ProjectData = R6::R6Class("ProjectData",
             return(private$pasta)
         },
 
+        #' Get the gender data. If it is not already stored in the ProjectData, this function triggers a read
+        #' from disk.
+        #'
+        #' @return the gender data
+        get.gender = function() {
+            logging::loginfo("Getting gender data.")
+
+            ## if gender data are to be read, do this
+            if (private$project.conf$get.value("gender")) {
+
+                ## if data are not read already, read them
+                if (is.null(private$gender)) {
+
+                    ## read gender data from disk
+                    gender.data = read.gender(self$get.data.path.gender())
+                    self$set.gender(gender.data)
+                }
+            } else {
+                logging::logwarn("You have not set the ProjectConf parameter 'gender' to 'TRUE'! Ignoring...")
+
+                ## mark gender data as empty
+                self$set.gender(NULL)
+            }
+
+            return(private$gender)
+        },
+
         #' Set the PaStA data to the given new data and,
         #' if configured in the field \code{project.conf},
         #' also update it for the mail and commit data.
@@ -1279,6 +1339,30 @@ ProjectData = R6::R6Class("ProjectData",
             }
         },
 
+
+        #' Set the gender data to the given new data and,
+        #' if configured in the field \code{project.conf},
+        #' also update it for the author data.
+        #'
+        #' @param data the new gender data
+        set.gender = function(data) {
+            logging::loginfo("Setting gender data.")
+
+            if (is.null(data)) {
+                data = create.empty.gender.list()
+            }
+
+            ## set the actual data
+            private$gender = data
+
+            ## add gender data to author data if configured
+            if (private$project.conf$get.value("gender")) {
+
+                ## update all gender-related data
+                private$update.gender.data()
+
+            }
+        },
         #' Remove lines in the PaStA data that contain message ids or commit hashes
         #' that don't appear in the commit or mail data.
         cleanup.pasta.data = function() {
@@ -1394,18 +1478,35 @@ ProjectData = R6::R6Class("ProjectData",
 
             ## if authors are not read already, do this
             if (!self$is.data.source.cached("authors")) {
-                private$authors = read.authors(self$get.data.path())
+
+                # read gender data
+                author.data = read.authors(self$get.data.path());
+
+                # set author data and add gender data (if configured in the 'project.conf')
+                self$set.authors(author.data)
             }
 
             return(private$authors)
         },
 
-        #' Set the atuhor data to the given new data.
+        #' Set the author data to the given new data.
         #'
         #' @param data the new author data
         set.authors = function(data) {
             logging::loginfo("Setting author data.")
             private$authors = data
+
+            ## add gender data if wanted
+            if (private$project.conf$get.value("gender")) {
+                if (is.null(private$gender)) {
+                    ## get data (no assignment because we just want to trigger anything gender-related)
+                    self$get.gender()
+                } else {
+                    ## update all gender-related data
+                    private$update.gender.data()
+                }
+            }
+
         },
 
         #' Filter bots from given data.