Add file parsing

.Rbuildignore

@@ -1,3 +1,3 @@
 ^\.lintr$
 ^LICENSE\.md$
-^\.github$
+^\.github$

.lintr

@@ -5,4 +5,3 @@ linters: linters_with_defaults(
 	object_name_linter = object_name_linter(styles = c("snake_case", "symbols", "SNAKE_CASE"))
   ) # see vignette("lintr")
 encoding: "UTF-8"
-

DESCRIPTION

@@ -14,6 +14,10 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.3.2
+Imports:
+    openxlsx,
+    readODS
 Suggests: 
-    testthat (>= 3.0.0)
+    testthat (>= 3.0.0),
+    mockr
 Config/testthat/edition: 3

LICENSE

@@ -1,2 +1,2 @@
 YEAR: 2024
-COPYRIGHT HOLDER: Hector Vernet, Marie Revol, Noemie Wawrzyniak, Amance Graindorge
+COPYRIGHT HOLDER: Hector Vernet, Marie Revol, Noemie Wawrzyniak, Amance Graindorge

NAMESPACE

@@ -1,2 +1,4 @@
 # Generated by roxygen2: do not edit by hand
 
+import(openxlsx)
+import(readODS)

R/ADSPlanner-package.R

@@ -0,0 +1,6 @@
+# This file is used to define the imports that will be updated by roxygen2 when running `devtools::document()`.
+
+#' @import openxlsx
+#' @import readODS
+NULL
+#> NULL

R/input.R

@@ -0,0 +1,104 @@
+library(openxlsx)
+library(readODS)
+
+# Prefixes of the head of the wishes columns
+Q2_PREFIX <- "Q02_Voeux->"
+Q3_PREFIX <- "Q03_VoeuxEMIR->"
+Q4_PREFIX <- "Q04_voeuxMICA->"
+
+#' Reads the file and selects the needed columns
+#'
+#' @param file_path The path to the file to parse
+#' @return The file as a data frame
+read_file <- function(file_path) {
+    # Check if file extension is supported (xlsx or ods)
+    if (grepl(".xlsx", file_path)) {
+        file_data <- openxlsx::read.xlsx(file_path, sheet = 1, skipEmptyRows = FALSE, skipEmptyCols = FALSE, colNames = TRUE, cols = (8:25), sep.names = " ")
+        file_data <- file_data[, c(8:25)]
+    } else if (grepl(".ods", file_path)) {
+        file_data <- readODS::read_ods(file_path, sheet = 1, col_names = TRUE, as_tibble = FALSE, na = "NULL")
+        file_data <- file_data[, c(8:25)]
+    } else {
+        stop("File type not supported")
+    }
+    return(file_data)
+}
+
+#' Synthesizes a student's wishes from multiple columns per filiere to 7 columns for all filieres
+#'
+#' @param wishes The wishes columns
+#' @return A vector with the filiere and the 7 wishes (NA if no wish)
+synthesize_wishes <- function(wishes) {
+    # Get the head of the columns
+    colnames <- colnames(wishes)
+    # Extract the filiere info
+    if (length(grep("FC_FIRE", wishes[1])) > 0) {
+        # Dataframe from rank number and speciality name
+        df <- data.frame(rank = unlist(wishes[2:8]), spe = sub(Q2_PREFIX, "", colnames[2:8]))
+        # Sort the dataframe by rank
+        df <- df[order(df$rank), ]
+        # Set result to the filiere and the specialities ordered by the student's preferences
+        result <- c("FC_FIRE", df$spe)
+    } else if (length(grep("EMIR", wishes[1])) > 0) {
+        df <- data.frame(rank = unlist(wishes[9:12]), spe = sub(Q3_PREFIX, "", colnames[9:12]))
+        df <- df[order(df$rank), ]
+        result <- c("EMIR", df$spe)
+    } else if (length(grep("MICA", wishes[1])) > 0) {
+        df <- data.frame(rank = unlist(wishes[13:16]), spe = sub(Q4_PREFIX, "", colnames[13:16]))
+        df <- df[order(df$rank), ]
+        result <- c("MICA", df$spe)
+    } else {
+        stop("Unknown filiere")
+    }
+    return(result)
+}
+
+#' Parses the file to build a clean data frame
+#'
+#' @param file_path The path to the file to parse
+#' @return A data frame with the cleaned data
+parse_file <- function(file_path) {
+    # Get file data as a data frame
+    tryCatch({
+        file_data <- read_file(file_path)
+    }, error = function(e) {
+        stop("Error while reading the file : ", conditionMessage(e))
+    })
+    # Build the result data frame
+    data <- data.frame(
+        Nom = rep(NA_character_, nrow(file_data)),
+        Prenom = rep(NA_character_, nrow(file_data)),
+        Filiere = rep(NA_character_, nrow(file_data)),
+        V1 = rep(NA_character_, nrow(file_data)),
+        V2 = rep(NA_character_, nrow(file_data)),
+        V3 = rep(NA_character_, nrow(file_data)),
+        V4 = rep(NA_character_, nrow(file_data)),
+        V5 = rep(NA_character_, nrow(file_data)),
+        V6 = rep(NA_character_, nrow(file_data)),
+        V7 = rep(NA_character_, nrow(file_data)),
+        Aff_V1_S1 = rep(NA_character_, nrow(file_data)),
+        Aff_V1_S2 = rep(NA_character_, nrow(file_data)),
+        Aff_V1_S3 = rep(NA_character_, nrow(file_data)),
+        Aff_V2_S1 = rep(NA_character_, nrow(file_data)),
+        Aff_V2_S2 = rep(NA_character_, nrow(file_data)),
+        Aff_V2_S3 = rep(NA_character_, nrow(file_data)),
+        Aff_V3_S1 = rep(NA_character_, nrow(file_data)),
+        Aff_V3_S2 = rep(NA_character_, nrow(file_data)),
+        Aff_V3_S3 = rep(NA_character_, nrow(file_data))
+    )
+    # Process each row of the file's data
+    for (i in seq_len(nrow(file_data))) {
+        # Name
+        name_split <- strsplit(file_data[i, 1], split = " ")[[1]] # We assume that the first and last name are separated by a space
+        data[i, 1] <- name_split[2]
+        data[i, 2] <- name_split[1]
+        # Wishes
+        tryCatch({
+            synthesized_wishes <- synthesize_wishes(file_data[i, 3:18])
+        }, error = function(e) {
+            stop("Error while synthesizing the wishes (l.", i, "): ", conditionMessage(e))
+        })
+        data[i, 3:(length(synthesized_wishes) + 2)] <- synthesized_wishes
+    }
+    return(data)
+}

tests/testthat.R

@@ -8,5 +8,8 @@
 
 library(testthat)
 library(ADSPlanner)
+library(mockr)
+library(openxlsx)
+library(readODS)
 
 test_check("ADSPlanner")

tests/testthat/setup.R

@@ -0,0 +1,172 @@
+read_file_output <- data.frame(
+    "Nom complet" = c("Laurence Marchand", "Laurence ROZE", "Laurence Roze"),
+    "Nom d’utilisateur" = c("[email protected]", "[email protected]", "[email protected]"),
+    "Q01_Filiere" = c("1 : FC_FIRE (Filière classique ou filière internationale)", "2 : EMIR", "3 : MICA"),
+    "Q02_Voeux->EII" = c(1, NA, NA),
+    "Q02_Voeux->E&T" = c(2, NA, NA),
+    "Q02_Voeux->INFO" = c(5, NA, NA),
+    "Q02_Voeux->MA" = c(4, NA, NA),
+    "Q02_Voeux->GCU" = c(3, NA, NA),
+    "Q02_Voeux->GMA" = c(6, NA, NA),
+    "Q02_Voeux->GPM" = c(7, NA, NA),
+    "Q03_VoeuxEMIR->EII" = c(NA, 4, NA),
+    "Q03_VoeuxEMIR->INFO" = c(NA, 3, NA),
+    "Q03_VoeuxEMIR->GPM" = c(NA, 2, NA),
+    "Q03_VoeuxEMIR->E&T" = c(NA, 1, NA),
+    "Q04_voeuxMICA->GCU" = c(NA, NA, 4),
+    "Q04_voeuxMICA->MA" = c(NA, NA, 1),
+    "Q04_voeuxMICA->GMA" = c(NA, NA, 3),
+    "Q04_voeuxMICA->INFO" = c(NA, NA, 2),
+    check.names = FALSE
+)
+
+read_file_output_invalid <- data.frame(
+    "Nom complet" = c("Laurence Marchand", "Laurence ROZE", "Laurence Roze"),
+    "Nom d’utilisateur" = c("[email protected]", "[email protected]", "[email protected]"),
+    "Q01_Filiere" = c("1 : FC_FIRE (Filière classique ou filière internationale)", "4 : Filière that doesn't exist", "3 : MICA"),
+    "Q02_Voeux->EII" = c(1, NA, NA),
+    "Q02_Voeux->E&T" = c(2, NA, NA),
+    "Q02_Voeux->INFO" = c(5, NA, NA),
+    "Q02_Voeux->MA" = c(4, NA, NA),
+    "Q02_Voeux->GCU" = c(3, NA, NA),
+    "Q02_Voeux->GMA" = c(6, NA, NA),
+    "Q02_Voeux->GPM" = c(7, NA, NA),
+    "Q03_VoeuxEMIR->EII" = c(NA, 4, NA),
+    "Q03_VoeuxEMIR->INFO" = c(NA, 3, NA),
+    "Q03_VoeuxEMIR->GPM" = c(NA, 2, NA),
+    "Q03_VoeuxEMIR->E&T" = c(NA, 1, NA),
+    "Q04_voeuxMICA->GCU" = c(NA, NA, 4),
+    "Q04_voeuxMICA->MA" = c(NA, NA, 1),
+    "Q04_voeuxMICA->GMA" = c(NA, NA, 3),
+    "Q04_voeuxMICA->INFO" = c(NA, NA, 2),
+    check.names = FALSE
+)
+
+synth_wishes_input_fc_fire <- data.frame(
+    "Q01_Filiere" = "1 : FC_FIRE (Filière classique ou filière internationale)",
+    "Q02_Voeux->EII" = 1,
+    "Q02_Voeux->E&T" = 2,
+    "Q02_Voeux->INFO" = 5,
+    "Q02_Voeux->MA" = 4,
+    "Q02_Voeux->GCU" = 3,
+    "Q02_Voeux->GMA" = 6,
+    "Q02_Voeux->GPM" = 7,
+    "Q03_VoeuxEMIR->EII" = NA,
+    "Q03_VoeuxEMIR->INFO" = NA,
+    "Q03_VoeuxEMIR->GPM" = NA,
+    "Q03_VoeuxEMIR->E&T" = NA,
+    "Q04_voeuxMICA->GCU" = NA,
+    "Q04_voeuxMICA->MA" = NA,
+    "Q04_voeuxMICA->GMA" = NA,
+    "Q04_voeuxMICA->INFO" = NA,
+    check.names = FALSE
+)
+
+synth_wishes_output_fc_fire <- c(
+    "FC_FIRE",
+    "EII",
+    "E&T",
+    "GCU",
+    "MA",
+    "INFO",
+    "GMA",
+    "GPM"
+)
+
+synth_wishes_input_emir <- data.frame(
+    "Q01_Filiere" = "2 : EMIR",
+    "Q02_Voeux->EII" = NA,
+    "Q02_Voeux->E&T" = NA,
+    "Q02_Voeux->INFO" = NA,
+    "Q02_Voeux->MA" = NA,
+    "Q02_Voeux->GCU" = NA,
+    "Q02_Voeux->GMA" = NA,
+    "Q02_Voeux->GPM" = NA,
+    "Q03_VoeuxEMIR->EII" = 4,
+    "Q03_VoeuxEMIR->INFO" = 3,
+    "Q03_VoeuxEMIR->GPM" = 2,
+    "Q03_VoeuxEMIR->E&T" = 1,
+    "Q04_voeuxMICA->GCU" = NA,
+    "Q04_voeuxMICA->MA" = NA,
+    "Q04_voeuxMICA->GMA" = NA,
+    "Q04_voeuxMICA->INFO" = NA,
+    check.names = FALSE
+)
+
+synth_wishes_output_emir <- c(
+    "EMIR",
+    "E&T",
+    "GPM",
+    "INFO",
+    "EII"
+)
+
+synth_wishes_input_mica <- data.frame(
+    "Q01_Filiere" = "3 : MICA",
+    "Q02_Voeux->EII" = NA,
+    "Q02_Voeux->E&T" = NA,
+    "Q02_Voeux->INFO" = NA,
+    "Q02_Voeux->MA" = NA,
+    "Q02_Voeux->GCU" = NA,
+    "Q02_Voeux->GMA" = NA,
+    "Q02_Voeux->GPM" = NA,
+    "Q03_VoeuxEMIR->EII" = NA,
+    "Q03_VoeuxEMIR->INFO" = NA,
+    "Q03_VoeuxEMIR->GPM" = NA,
+    "Q03_VoeuxEMIR->E&T" = NA,
+    "Q04_voeuxMICA->GCU" = 4,
+    "Q04_voeuxMICA->MA" = 1,
+    "Q04_voeuxMICA->GMA" = 3,
+    "Q04_voeuxMICA->INFO" = 2,
+    check.names = FALSE
+)
+
+synth_wishes_output_mica <- c(
+    "MICA",
+    "MA",
+    "INFO",
+    "GMA",
+    "GCU"
+)
+
+synth_wishes_input_invalid <- data.frame(
+    "Q01_Filiere" = "4 : Filière that doesn't exist",
+    "Q02_Voeux->EII" = NA,
+    "Q02_Voeux->E&T" = NA,
+    "Q02_Voeux->INFO" = NA,
+    "Q02_Voeux->MA" = NA,
+    "Q02_Voeux->GCU" = NA,
+    "Q02_Voeux->GMA" = NA,
+    "Q02_Voeux->GPM" = NA,
+    "Q03_VoeuxEMIR->EII" = NA,
+    "Q03_VoeuxEMIR->INFO" = NA,
+    "Q03_VoeuxEMIR->GPM" = NA,
+    "Q03_VoeuxEMIR->E&T" = NA,
+    "Q04_voeuxMICA->GCU" = 4,
+    "Q04_voeuxMICA->MA" = 1,
+    "Q04_voeuxMICA->GMA" = 3,
+    "Q04_voeuxMICA->INFO" = 2,
+    check.names = FALSE
+)
+
+parse_file_output <- data.frame(
+    Nom = c("Marchand", "ROZE", "Roze"),
+    Prenom = c("Laurence", "Laurence", "Laurence"),
+    Filiere = c("FC_FIRE", "EMIR", "MICA"),
+    V1 = c("EII", "E&T", "MA"),
+    V2 = c("E&T", "GPM", "INFO"),
+    V3 = c("GCU", "INFO", "GMA"),
+    V4 = c("MA", "EII", "GCU"),
+    V5 = c("INFO", NA_character_, NA_character_),
+    V6 = c("GMA", NA_character_, NA_character_),
+    V7 = c("GPM", NA_character_, NA_character_),
+    Aff_V1_S1 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V1_S2 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V1_S3 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V2_S1 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V2_S2 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V2_S3 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V3_S1 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V3_S2 = c(NA_character_, NA_character_, NA_character_),
+    Aff_V3_S3 = c(NA_character_, NA_character_, NA_character_)
+)