Add gender data to ProjectData comparison tests

- Add gender data to ProjectData comparison tests in test-data.R
- Rename gender files from 'gender' to 'gender.list'

Signed-off-by: Mirabdulla Yusifli <s8miyusi@stud.uni-saarland.de>

tests/test-data.R

@@ -40,6 +40,7 @@ test_that("Compare two ProjectData objects on empty data", {
     ## initialize a ProjectData object with the ProjectConf and clone it into another one
     proj.conf = ProjectConf$new(CF.DATA, CF.SELECTION.PROCESS, CASESTUDY_EMPTY, ARTIFACT)
     proj.conf$update.value("pasta", TRUE)
+    proj.conf$update.value("gender", TRUE)
     proj.data.one = ProjectData$new(project.conf = proj.conf)
     proj.data.two = proj.data.one$clone(deep = TRUE)
 
@@ -74,6 +75,11 @@ test_that("Compare two ProjectData objects on empty data", {
     proj.data.one$get.authors()
     expect_true(proj.data.one$equals(proj.data.two), "Two identical ProjectData objects (authors).")
 
+    proj.data.two$get.gender()
+    expect_true(proj.data.one$equals(proj.data.two), "Two identical ProjectData objects (gender).")
+    proj.data.one$get.gender()
+    expect_true(proj.data.one$equals(proj.data.two), "Two identical ProjectData objects (gender).")
+
     proj.data.one$set.project.conf.entry("synchronicity", TRUE)
     proj.data.one$set.project.conf.entry("synchronicity.time.window", 5)
     proj.data.one$get.synchronicity()
@@ -96,6 +102,7 @@ test_that("Compare two ProjectData objects on non-empty data", {
     ## initialize a ProjectData object with the ProjectConf and clone it into another one
     proj.conf = ProjectConf$new(CF.DATA, CF.SELECTION.PROCESS, CASESTUDY, ARTIFACT)
     proj.conf$update.value("pasta", TRUE)
+    proj.conf$update.value("gender", TRUE)
 
     proj.data.one = ProjectData$new(project.conf = proj.conf)
     proj.data.two = proj.data.one$clone(deep = TRUE)
@@ -145,6 +152,13 @@ test_that("Compare two ProjectData objects on non-empty data", {
     proj.data.two$get.issues()
     expect_true(proj.data.one$equals(proj.data.two), "Two identical ProjectData objects (issues.filtered).")
 
+    ## test 'equals' on gender
+    proj.data.two$get.gender()    
+    expect_false(proj.data.one$equals(proj.data.two), "Two non-identical ProjectData objects (gender).")
+
+    proj.data.one$get.gender()
+    expect_true(proj.data.one$equals(proj.data.two), "Two identical ProjectData objects (gender).")
+
     ## test 'equals' on authors
     proj.data.two$get.authors()
     expect_false(proj.data.one$equals(proj.data.two), "Two non-identical ProjectData objects (authors).")

tests/test-read.R

@@ -259,10 +259,12 @@ test_that("Read and parse the gender data.", {
 
     ## read the actual data
     gender.data.read = read.gender(proj.conf$get.value("datapath.gender"))
+
+    rownames(gender.data.read) = NULL
 
     ## build the expected data.frame
-    gender.data.expected = data.frame(author.name = c("Thomas", "Olaf", "Karl", "Max", "udo", "Björn", "georg", "Hans", "Fritz fritz@example.org"),
-                                     gender = c("male", "female", "male", "male", "female", "male", "male", "male", NA))
+    gender.data.expected = data.frame(author.name = c("Björn", "Fritz fritz@example.org", "georg", "Hans", "Karl", "Max", "Olaf", "Thomas", "udo"),
+                                     gender = c("male", "", "male", "male", "male", "male", "female", "male", "female"))
 
     ## check the results
     expect_identical(gender.data.read, gender.data.expected, info = "Gender data.")

util-data.R

@@ -1296,8 +1296,7 @@ ProjectData = R6::R6Class("ProjectData",
             if (private$project.conf$get.value("gender")) {
 
                 ## if data are not read already, read them
-                if (empty(private$gender)) {
-
+                if (!self$is.data.source.cached("gender")) {
                     ## read gender data from disk
                     gender.data = read.gender(self$get.data.path.gender())
                     self$set.gender(gender.data)
@@ -1323,8 +1322,6 @@ ProjectData = R6::R6Class("ProjectData",
 
                 author.name.contained = private$gender[["author.name"]] %in% private$authors[["author.name"]]
                 private$gender = private$gender[author.name.contained, ]
-                View(author.name.contained)
-                View(private$gender)
             }
         },
 
@@ -1516,7 +1513,9 @@ ProjectData = R6::R6Class("ProjectData",
             private$authors = data
             ## add gender data if wanted
             if (private$project.conf$get.value("gender")) {
-                if (empty(private$gender)) {
+
+                ## if data are not read already, read them
+                if (!self$is.data.source.cached("gender")) {
                     ## get data (no assignment because we just want to trigger anything gender-related)
                     self$get.gender()
                 } else {
@@ -1750,7 +1749,7 @@ ProjectData = R6::R6Class("ProjectData",
 
             ## define the data sources
             unfiltered.data.sources = c("commits.unfiltered", "mails.unfiltered", "issues.unfiltered")
-            additional.data.sources = c("authors", "commit.messages", "synchronicity", "pasta")
+            additional.data.sources = c("authors", "commit.messages", "synchronicity", "pasta","gender")
             main.data.sources = c("issues", "commits", "mails")
 
             ## set the right data sources to look for according to the argument