Fix issue #195 and update corresponding messages

epiverse-trace · Nov 12, 2024 · f496618 · f496618
1 parent e318a53
commit f496618
Show file tree

Hide file tree

Showing 7 changed files with 73 additions and 43 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -41,3 +41,5 @@
 * Use {cli} package for formatting messages in the package (#196, Karim-Mane).
 
 * Translate messages in the package into French using {potools} package (#196, Karim-Mane).
+
+* An additional column (**row_id**) with the row indices where the incorrect date sequences are found is now added to the report made from the `check_date_sequence()` function (#196, Karim-Mane).
diff --git a/R/check_date_sequence.R b/R/check_date_sequence.R
@@ -64,7 +64,7 @@ check_date_sequence <- function(data, target_columns) {
       cli::cli_abort(c(
         tr_("Insufficient number of columns to compare."),
         x = tr_("At least two columns of type {.cls Date} are required for this operation."), # nolint: line_length_linter
-        i = tr_("Did you enter an incorrect correct name?")
+        i = tr_("Have you provided an incorrect column name?")
       ), call = NULL)
     }
   }
@@ -75,16 +75,22 @@ check_date_sequence <- function(data, target_columns) {
   bad_order <- which(!order_date)
   if (!all(order_date)) {
     tmp_data <- tmp_data[bad_order, ]
+    # add the row numbers of incorrect records to the report
+    tmp_data <- data.frame(
+      cbind(row_id = bad_order, tmp_data)
+    )
     # adding incorrect records to the report
     data <- add_to_report(
       x = data,
       key = "incorrect_date_sequence",
       value = tmp_data
     )
-    cli::cli_alert_info(
-      tr_("Detected {.val {length(bad_order)}} incorrect date sequence{?s} at line{?s}: {.val {toString(bad_order)}}."), # nolint: line_length_linter
-      wrap = TRUE
-    )
+
+    # send a message about the presence of incorrect date sequence
+    cli::cli_inform(c(
+      "!" = tr_("Detected {.val {length(bad_order)}} incorrect date sequence{?s} at line{?s}: {.val {toString(bad_order)}}."), # nolint: line_length_linter
+      i = tr_("Enter {.code attr(dat, \"report\")[[\"incorrect_date_sequence\"]]} to access them, where {.val dat} is the object used to store the output from this operation.") # nolint: line_length_linter
+    ))
   }
 
   return(data)

diff --git a/inst/po/fr/LC_MESSAGES/R-cleanepi.mo b/inst/po/fr/LC_MESSAGES/R-cleanepi.mo
diff --git a/inst/rmarkdown/templates/printing-rmd/skeleton/skeleton.Rmd b/inst/rmarkdown/templates/printing-rmd/skeleton/skeleton.Rmd
@@ -66,24 +66,23 @@ incorrect_date_sequence <- params[["incorrect_date_sequence"]]
 are_incorrect_date_seq_found <- !is.null(incorrect_date_sequence)
 constant_data <- params[["constant_data"]]
 are_constant_data_found <- !is.null(constant_data)
-duplicated_rows      <- params[["duplicated_rows"]]
+duplicated_rows <- params[["duplicated_rows"]]
 are_duplicates_found <- !is.null(duplicated_rows)
-removed_duplicates     <- params[["removed_duplicates"]]
+removed_duplicates <- params[["removed_duplicates"]]
 are_duplicates_removed <- !is.null(removed_duplicates)
-misspelled_values           <- params[["misspelled_values"]]
+misspelled_values <- params[["misspelled_values"]]
 are_misspelled_values_found <- !is.null(misspelled_values)
-missing_values_replaced_at  <- params[["missing_values_replaced_at"]]
+missing_values_replaced_at <- params[["missing_values_replaced_at"]]
 are_missing_values_replaced <- !is.null(missing_values_replaced_at)
-incorrect_subject_id     <- params[["incorrect_subject_id"]]
+incorrect_subject_id <- params[["incorrect_subject_id"]]
 are_incorrect_subject_id <- !is.null(incorrect_subject_id)
-missing_ids     <- params[["missing_ids"]]
+missing_ids <- params[["missing_ids"]]
 are_missing_ids <- !is.null(missing_ids)
-duplicated_ids     <- params[["duplicated_ids"]]
+duplicated_ids <- params[["duplicated_ids"]]
 are_duplicated_ids <- !is.null(duplicated_ids)
-converted_into_numeric     <- params[["converted_into_numeric"]]
+converted_into_numeric <- params[["converted_into_numeric"]]
 are_converted_into_numeric <- !is.null(converted_into_numeric)
-incorrect_date_sequence     <- params[["incorrect_date_sequence"]]
-are_incorrect_date_sequence <- !is.null(incorrect_date_sequence)
+incorrect_date_sequence <- params[["incorrect_date_sequence"]]
 multi_format_dates <- params[["multi_format_dates"]]
 are_multi_format_dates <- !is.null(multi_format_dates)
 ```

diff --git a/po/R-cleanepi.pot b/po/R-cleanepi.pot
@@ -1,7 +1,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: cleanepi 1.0.2.9000\n"
-"POT-Creation-Date: 2024-11-12 13:40+0000\n"
+"POT-Creation-Date: 2024-11-12 16:13+0000\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <[email protected]>\n"
@@ -26,15 +26,22 @@ msgid ""
 msgstr ""
 
 #: check_date_sequence.R:67
-msgid "Did you enter an incorrect correct name?"
+msgid "Have you provided an incorrect column name?"
 msgstr ""
 
-#: check_date_sequence.R:85
+#: check_date_sequence.R:91
 msgid ""
 "Detected {.val {length(bad_order)}} incorrect date sequence{?s} at line{?s}: "
 "{.val {toString(bad_order)}}."
 msgstr ""
 
+#: check_date_sequence.R:92
+msgid ""
+"Enter {.code attr(dat, \"report\")[[\"incorrect_date_sequence\"]]} to access "
+"them, where {.val dat} is the object used to store the output from this "
+"operation."
+msgstr ""
+
 #: clean_data.R:139
 msgid "cleaning column names"
 msgstr ""

diff --git a/po/R-fr.po b/po/R-fr.po
@@ -1,7 +1,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: cleanepi 1.0.2.9000\n"
-"POT-Creation-Date: 2024-11-12 13:40+0000\n"
+"POT-Creation-Date: 2024-11-12 16:07+0000\n"
 "PO-Revision-Date: 2024-11-07 12:38+0000\n"
 "Last-Translator: Karim Mané\n"
 "Language-Team: none\n"
@@ -30,17 +30,27 @@ msgstr ""
 "Cette opération nécessite au moins deux noms de colonnes de type {.cls Date}."
 
 #: check_date_sequence.R:67
-msgid "Did you enter an incorrect correct name?"
+msgid "Have you provided an incorrect column name?"
 msgstr "Avez-vous fourni un nom de colonne incorrect?"
 
-#: check_date_sequence.R:85
+#: check_date_sequence.R:91
 msgid ""
 "Detected {.val {length(bad_order)}} incorrect date sequence{?s} at line{?s}: "
 "{.val {toString(bad_order)}}."
 msgstr ""
 "La séquence des dates est incorrecte à travers les {.val "
 "{length(bad_order)}} lignes suivantes: {.val {toString(bad_order)}}."
 
+#: check_date_sequence.R:92
+msgid ""
+"Enter {.code attr(dat, \"report\")[[\"incorrect_date_sequence\"]]} to access "
+"them, where {.val dat} is the object used to store the output from this "
+"operation."
+msgstr ""
+"Veuillez entrer {.code attr(dat, \"report\")[[\"incorrect_date_sequence\"]]} "
+"pour y accéder. {.val dat} represente ici l'object créé pour stocker le "
+"résultat de cette opération."
+
 #: clean_data.R:139
 msgid "cleaning column names"
 msgstr "nettoyage des noms de colonnes"

diff --git a/tests/testthat/test-check_date_sequence.R b/tests/testthat/test-check_date_sequence.R
@@ -1,11 +1,11 @@
 test_that("is_date_sequence_ordered works as expected", {
-  x   <- as.Date(c("2023-10-02", "2023-10-10", "2023-10-20"))
+  x <- as.Date(c("2023-10-02", "2023-10-10", "2023-10-20"))
   res <- is_date_sequence_ordered(x)
   expect_true(res)
 })
 
 test_that("is_date_sequence_ordered works as expected", {
-  x   <- as.Date(c("2023-10-02", "2023-10-20", "2023-10-10"))
+  x <- as.Date(c("2023-10-02", "2023-10-20", "2023-10-10"))
   res <- is_date_sequence_ordered(x)
   expect_false(res)
 })
@@ -16,49 +16,54 @@ data <- readRDS(system.file("extdata", "test_df.RDS", package = "cleanepi"))
 # standardize the date values
 data <- data %>%
   standardize_dates(
-    target_columns  = c("date_first_pcr_positive_test",
-                        "date.of.admission"),
+    target_columns = c("date_first_pcr_positive_test", "date.of.admission"),
     error_tolerance = 0.4,
-    format          = NULL,
-    timeframe       = NULL
+    format = NULL,
+    timeframe = NULL
   )
 
 test_that("check_date_sequence sends a warning when incorrect column nams are
           found", {
             expect_message(
               check_date_sequence(
-                data           = data,
-                target_columns = c("date_first_pcr_positive_test",
-                                   "date.of.admission", "fake_name")
+                data = data,
+                target_columns = c(
+                  "date_first_pcr_positive_test", "date.of.admission",
+                  "fake_name"
+                )
               ),
               regexp = cat("Found the following unrecognised column name:
                            `fake_name`")
             )
 
             expect_message(
               check_date_sequence(
-                data           = data,
-                target_columns = c("date_first_pcr_positive_test",
-                                   "date.of.admission")              ),
+                data = data,
+                target_columns = c(
+                  "date_first_pcr_positive_test", "date.of.admission"
+                )
+              ),
               regexp = cat("Detected 2 incorrect date sequences at
                            lines: `6, 8`")
             )
 
             expect_error(
               check_date_sequence(
-                data           = data,
-                target_columns = c("date_first_pcr_positive_test",
-                                   "fake_name")),
+                data = data,
+                target_columns = c(
+                  "date_first_pcr_positive_test", "fake_name")
+                ),
               regexp = cat("Insufficient number of columns to compare.")
             )
 })
 
 test_that("check_date_sequence works as expected when target_column is provided
           as a vector", {
               good_date_sequence <- check_date_sequence(
-                data           = data,
-                target_columns = c("date_first_pcr_positive_test",
-                                   "date.of.admission")
+                data = data,
+                target_columns = c(
+                  "date_first_pcr_positive_test", "date.of.admission"
+                )
               )
               report <- attr(good_date_sequence, "report")
               expect_s3_class(good_date_sequence, "data.frame")
@@ -68,8 +73,9 @@ test_that("check_date_sequence works as expected when target_column is provided
                            c("multi_format_dates", "incorrect_date_sequence"))
               expect_s3_class(report[["incorrect_date_sequence"]], "data.frame")
               expect_identical(nrow(report[["incorrect_date_sequence"]]), 2L)
-              expect_identical(ncol(report[["incorrect_date_sequence"]]), 2L)
-              expect_identical(names(report[["incorrect_date_sequence"]]),
-                               c("date_first_pcr_positive_test",
-                                 "date.of.admission"))
+              expect_identical(ncol(report[["incorrect_date_sequence"]]), 3L)
+              expect_identical(
+                names(report[["incorrect_date_sequence"]]),
+                c("row_id", "date_first_pcr_positive_test", "date.of.admission")
+              )
 })
Original file line number	Diff line number	Diff line change
Expand Up		@@ -41,3 +41,5 @@
		* Use {cli} package for formatting messages in the package (#196, Karim-Mane).

		* Translate messages in the package into French using {potools} package (#196, Karim-Mane).

		* An additional column (row_id) with the row indices where the incorrect date sequences are found is now added to the report made from the `check_date_sequence()` function (#196, Karim-Mane).