Merge pull request #120 from RobLBaker/main

Increment DPchecker version

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: DPchecker
 Title: Checks Data Packages for Congruence
-Version: 0.3.2
+Version: 0.3.3
 Authors@R: c(
     person("Rob", "Baker", email = "robert_baker@nps.gov", role = c("cre", "aut"), comment = c(ORCID = "0000-0001-7591-5035")),
     person(c("Sarah", "E."), "Wright", email = "sarah_wright@nps.gov", role = "aut"),
@@ -33,7 +33,8 @@ Imports:
     httr,
     jsonlite,
     stats,
-    QCkit
+    QCkit,
+    lifecycle
 Remotes: 
     https://github.com/NCEAS/arcticdatautils,
     https://github.com/nationalparkservice/QCkit

NAMESPACE

@@ -49,4 +49,5 @@ export(test_valid_fieldnames)
 export(test_valid_filenames)
 export(test_validate_schema)
 importFrom(QCkit,convert_datetime_format)
+importFrom(lifecycle,deprecated)
 importFrom(magrittr,"%>%")

NEWS.md

@@ -2,6 +2,8 @@
 
 * Bug fixes for `test_date_range()` and `test_dates_parse()`.
 * Adjusted `test_datatable_urls()` and `test_datatable_urls_doi()` so that they work properly when there are no data table urls present in metadata.
+* Move convert_datetime_format to QCkit; add QCkit as re-export to DPchecker
+* Updated tabular_data_congruence.R for speed and stability as per codefactor suggests
 
 # DPchecker 0.3.2
 

R/DPchecker-package.R

@@ -2,6 +2,7 @@
 "_PACKAGE"
 
 ## usethis namespace: start
+#' @importFrom lifecycle deprecated
 #' @importFrom magrittr %>%
 ## usethis namespace: end
 NULL

R/tabular_data_congruence.R

@@ -153,7 +153,7 @@ test_validate_schema <- function(metadata = load_metadata(here::here())) {
     cli::cli_inform(c("v" = "Your metadata is schema valid."))
   } else {
     attribs <- attributes(val)
-    issues <- c()
+    issues <- NULL
     if ("errors" %in% names(attribs)) {
       names(attribs$errors) <- rep("x", length(attribs$errors))
       issues <- c(issues, attribs$errors)
@@ -703,7 +703,7 @@ test_dates_parse <- function(directory = here::here(),
   # Check if temporal coverage info is complete. Throw a warning if it's missing entirely and an error if it's only partially complete.
   # The logic being that maybe there's a scenario where temporal coverage isn't relevant to the dataset at all, but if it has date/time info, it has to have both a start and end.
   if (missing_temporal) {
-    cli::cli_warn(c("!" = "Could not check date range. Metadata does not contain temporal coverage information."))
+    cli::cli_warn(c("!" = "Could not check date formats. Metadata does not contain temporal coverage information."))
     return(invisible(metadata))
   }
 
@@ -732,7 +732,7 @@ test_dates_parse <- function(directory = here::here(),
   #log errors. Assume none until one is found.
   error_log <- NULL
 
-  for(i in 1:length(seq_along(data_files))){
+  for(i in seq_along(data_files)){
     data_file <- data_tbl[[i]][["physical"]][["objectName"]]
 
     dttm_col_names <- dttm_attrs[[data_file]]$attributeName
@@ -771,6 +771,7 @@ test_dates_parse <- function(directory = here::here(),
         col_types = do.call(readr::cols, dttm_col_spec),
         show_col_types = FALSE))
 
+
     #Arooo?
     char_data <- suppressWarnings(
       readr::read_csv(file.path(directory, data_file),
@@ -779,14 +780,31 @@ test_dates_parse <- function(directory = here::here(),
                       col_types = rep("c", length(dttm_col_names)),
                       show_col_types = FALSE))
 
-    for(j in 1:length(seq_along(dttm_col_names))){
+    for(j in seq_along(dttm_col_names)){
 
       col_data <- dttm_data[[j]]
       orig_na_count <- sum(is.na(char_data[[j]]))
-      if (all(is.na(col_data))) {
-        error_log <- append(error_log, paste0("  ", "---> {.file ", data_file, "} {.field ", dttm_col_names[j], "} (failed to parse)"))
+      #if entire column is NA:
+      if (all(is.na(col_data)) & all(is.na(char_data[[j]]))) {
+        error_log <- append(error_log,
+                            paste0("  ",
+                                   "---> {.file ",
+                                   data_file,
+                                   "} {.field ",
+                                   dttm_col_names[j],
+                                   "} contains no data. Remove this column or use defined missing value codes to indicate data are missing." ))
+      } else if (all(is.na(col_data))) {
+        #if entire column failed to parse:
+        error_log <- append(error_log,
+                            paste0("  ", "---> {.file ", data_file,
+                                   "} {.field ", dttm_col_names[j],
+                                   "} (failed to parse)"))
+        #if part of the column failed to parse:
       } else if (sum(is.na(col_data)) > orig_na_count) {
-        error_log <- append(error_log, paste0("  ---> {.file ", data_file, "} {.field ", dttm_col_names[j], "} (partially failed to parse)"))
+        error_log <- append(error_log,
+                            paste0("  ---> {.file ", data_file, "} {.field ",
+                                   dttm_col_names[j],
+                                   "} (partially failed to parse)"))
       }
     }
   }

README.md

@@ -1,11 +1,14 @@
 <!-- badges: start -->
-[![R-CMD-check](https://github.com/nationalparkservice/DPchecker/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/nationalparkservice/DPchecker/actions/workflows/R-CMD-check.yaml)
+[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
+[![CodeFactor](https://www.codefactor.io/repository/github/roblbaker/dpchecker/badge)](https://www.codefactor.io/repository/github/roblbaker/dpchecker)
 <!-- badges: end -->
 
+<!-- CMD-check badge...for once it's working...[![R-CMD-check](https://github.com/nationalparkservice/DPchecker/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/nationalparkservice/DPchecker/actions/workflows/R-CMD-check.yaml) -->
+
 
 # DPchecker
 
-#### v0.3.2
+#### v0.3.3
 
 DPchecker (Data Package checker) is a package with a series of functions for NPS data package authors and reviewers to check for internal consistency among data/meta data and with the data package standards.