Dev docu update

DESCRIPTION

@@ -25,6 +25,8 @@ Imports:
     utils,
     tools,
     tidyr,
+    glue,
+    methods,
     R.utils,
     rlang,
     docxtractr,

NAMESPACE

@@ -1,6 +1,5 @@
 # Generated by roxygen2: do not edit by hand
 
-export()
 export(DTAColumnSpec)
 export(DTAColumnSpecCollection)
 export(DTAContainer)
@@ -19,6 +18,7 @@ export(container)
 export(convert_yaml_to_json)
 export(export_column_value_table)
 export(export_specs_table)
+export(get_arrow_schema_type)
 export(get_column_ids)
 export(get_metadata)
 export(get_rules)
@@ -29,6 +29,7 @@ export(matches_filename)
 export(new_DTAContainer)
 export(number_of_files)
 export(read_file)
+export(rule_check_condition)
 export(rule_check_range)
 export(rule_check_unique)
 export(specs_from_list)
@@ -42,7 +43,6 @@ export(write_table_to_file)
 import(S7)
 importFrom(R.utils,gzip)
 importFrom(arrow,arrow_table)
-importFrom(arrow,read_csv_arrow)
 importFrom(arrow,read_delim_arrow)
 importFrom(cli,cli_abort)
 importFrom(cli,cli_alert_danger)
@@ -77,13 +77,16 @@ importFrom(flextable,padding)
 importFrom(flextable,save_as_docx)
 importFrom(flextable,valign)
 importFrom(flextable,width)
+importFrom(glue,glue)
 importFrom(jsonlite,fromJSON)
 importFrom(jsonlite,toJSON)
 importFrom(jsonlite,write_json)
 importFrom(jsonvalidate,json_schema)
 importFrom(magrittr,"%>%")
+importFrom(methods,is)
 importFrom(purrr,map)
 importFrom(purrr,set_names)
+importFrom(stats,setNames)
 importFrom(tidyr,separate_wider_delim)
 importFrom(tools,md5sum)
 importFrom(utils,setTxtProgressBar)

R/00_helpers.R

@@ -4,7 +4,7 @@ class_DTAColumnSpecCollection <- S7::new_class(
   "DTAColumnSpecCollection"
 )
 class_DTAContainer <- S7::new_class("DTAContainer")
-class_DTAMetadata <- S7::new_class("DTAMetadata")
+class_DTAMetadata <- S7::new_class("DTAMetaData")
 class_character_or_null <- class_character | class_null
 class_numeric_or_null <- class_numeric | class_null
 class_character_or_numeric_or_null <- class_character |

R/DTA-class.R

@@ -52,6 +52,7 @@ DTA <- new_class(
 #'   get_metadata(DTA)
 #' }
 #' @name get_metadata
+#' @rdname get_metadata-DTA
 #' @export
 if (!exists("get_metadata", mode = "function")) {
   get_metadata <- new_generic("get_metadata", "x")

R/DTAColumnSpec-class.R

@@ -68,18 +68,20 @@ DTAColumnSpec <- new_class(
 #' @description
 #' Returns the corresponding Arrow schema type for a given DTAColumnSpec
 #' object based on its `type` property.
+#' @importFrom glue glue
 #' @param x A DTAColumnSpec object.
 #' @return A character string representing the Arrow schema type.
 #' @examples
 #' col <- DTAColumnSpec(id = "AGE", type = "Char")
 #' get_arrow_schema_type(col)
+#' @export
 get_arrow_schema_type <- function(x) {
-  if (!inherits(x, "DTAColumnSpec")) {
+  if (!inherits(x, "DTAtools::DTAColumnSpec")) {
     stop("Input must be a DTAColumnSpec object.")
   }
   type <- x@type
   if (is.null(type)) {
-    stop(str_glue("Type is not set for {x$id}."))
+    stop(glue::glue("Type is not set for {x$id}."))
   }
   switch(
     type,

R/DTAColumnSpecCollection-class.R

@@ -64,9 +64,12 @@ DTAColumnSpecCollection <- new_class(
 #' \dontrun{
 #' names <- get_column_ids(collection)
 #' }
-#' @name get_column_ids-DTAColumnSpecCollection
+#' @name get_column_ids
+#' @rdname get_column_ids-DTAColumnSpecCollection
 #' @export
-get_column_ids <- new_generic("get_column_ids", "x")
+if (!exists("get_column_ids", mode = "function")) {
+  get_column_ids <- new_generic("get_column_ids", "x")
+}
 method(get_column_ids, DTAColumnSpecCollection) <- function(x) {
   return(names(x@columns))
 }

R/DTAContainer-class.R

@@ -315,29 +315,20 @@ write_table_to_file <- function(
 #' \dontrun{
 #' get_metadata(DTAContainer)
 #' }
-#' @name metadata-DTAContainer
+#' @name get_metadata
+#' @rdname get_metadata-DTAContainer
+#' @export
 if (!exists("get_metadata", mode = "function")) {
   get_metadata <- new_generic("get_metadata", "x")
 }
-#' @export
 method(get_metadata, DTAContainer) <- function(x) {
   return(x@specs@metadata)
 }
 
-#' @title Get Rules
-#' @description
-#' Method to get Rules from DTAContainer.
-#' @param x An object of class DTAContainer
-#' @return A list with rules information
-#' @examples
-#' \dontrun{
-#' get_rules(DTAContainer)
-#' }
-#' @name get_rules-DTAContainer
+#' @export
 if (!exists("get_rules", mode = "function")) {
   get_rules <- new_generic("get_rules", "x")
 }
-#' @export
 method(get_rules, DTAContainer) <- function(x) {
   return(x@specs@rules)
 }
@@ -353,7 +344,8 @@ method(get_rules, DTAContainer) <- function(x) {
 #' column_format <- number_of_files(dtafileinfo)
 #' }
 # Define the generic only if it doesn't already exist
-#' @name get_max_number_of_files-DTAContainer
+#' @name get_max_number_of_files
+#' @rdname get_max_number_of_files-DTAContainer
 if (!exists("get_max_number_of_files", mode = "function")) {
   get_max_number_of_files <- new_generic("get_max_number_of_files", "x")
 }

R/evaluateSchemaRules.R

@@ -64,10 +64,10 @@ rule_check_unique <- function(rule, df) {
       id = rule@id,
       valid = FALSE,
       message = sprintf(
-        "Rule '%s' violated: %d duplicate values found in column %s",
+        "Rule '%s' violated: %d duplicate row found when selecting column(s): %s",
         rule@id,
         sum(duplicated_rows, na.rm = TRUE),
-        col
+        paste(cols, collapse = ", ")
       )
     )
   } else {
@@ -236,6 +236,7 @@ apply_schema_rules <- function(rules, df) {
 #'   Aborts with a CLI error if any rule fails.
 #' @param DTAColumnSpecCollection A `DTAColumnSpecCollection` with rules defined.
 #' @param table A data.frame to validate.
+#' @importFrom stats setNames
 #' @return (Invisibly) the list of rule results from `applySchemaRules()`.
 #' @export
 validate_rules <- function(DTAColumnSpecCollection, table) {
@@ -257,6 +258,7 @@ validate_rules <- function(DTAColumnSpecCollection, table) {
 }
 
 #' @keywords internal
+#' @importFrom methods is
 check_rule_class <- function(x) {
   if (methods::is(x, "DTAtools::DTARule")) {
     invisible(TRUE)

README.md

@@ -63,7 +63,7 @@ Specification contain definitions of:
 
 - **columns:** defines column names, format specification and optionally patterns or selection for values in the column. More details in section [YAML Column Format](#yaml-column-format).
 - **rules:** defines rules for columns, e.g. if column A is empty, then columns B must contain a value. More details in section [YAML Schema Rule Specification](#yaml-schema-rule-specification).
-- **metadata:** DTA meta data about version, author etc. More details in section [YAML Metadata].
+- **metadata:** DTA meta data about version, author etc. More details in section [YAML Metadata](#yaml-metadata).
 
 First, you import the specifications from a YAML file.
 
@@ -105,19 +105,19 @@ writeTableToFile(
 
 If you want to export the specifications stored in the YAML as a table to Word file you can use this function:
 
-``` r
+```r
 export_specs_table(specs, "dta_spec_table.docx")
 ```
 
 ### Export Column Values Table
 
 Exporting all defined potential values in a column to a word table.
 
-``` r
+```r
 export_column_value_table(specs, "column_value_table.docx", id = "VISIT")
 ```
 
-## YAML Column Format {#yaml-column-format}
+## YAML Column Format
 
 Columns specifications can contain
 
@@ -158,7 +158,7 @@ columns:
       - "other"
 ```
 
-## YAML Schema Rule Specification {#yaml-schema-rule-specification}
+## YAML Schema Rule Specification
 
 The `DTAtools` package supports schema-based validation of tabular data using declarative rules defined in YAML. These rules are evaluated after column-level validation and allow for complex inter-column logic enforcement.
 
@@ -332,13 +332,13 @@ metadata:
 
 ### Validation Functions
 
--   `validate_table()`: Validates a data frame against a spec specs
+- `validate_table()`: Validates a data frame against a spec specs
 
 ### Export Functions
 
--   `write_table_to_file()`: Write validated tables to disk with optional compression and metadata
--   `export_specs_table()`: Export full spec documentation to Word
--   `export_column_value_table()`: Export allowed values of a column to Word
+- `write_table_to_file()`: Write validated tables to disk with optional compression and metadata
+- `export_specs_table()`: Export full spec documentation to Word
+- `export_column_value_table()`: Export allowed values of a column to Word
 
 #### Rules Engine
 

inst/extdata/params_spec.yaml

@@ -7,13 +7,14 @@ columns:
     label: Study Identifier
     type: Char
     nullable: false
+    length: 10
     values:
       - 1234-5678
-    pattern: ^[0-9]{4}-[0-9]{4}$
     description: Unique study ID
   - id: VISIT
     label: Visit
     type: Char
+    length: 12
     nullable: false
     values:
       - V01
@@ -38,6 +39,7 @@ columns:
   - id: INCLUDE
     label: Include in analysis
     type: Char
+    length: 1
     nullable: true
     values:
       - "Y"

tests/testthat/test-DTAColumnSpecCollection.R

@@ -77,7 +77,7 @@ test_that("specs_from_list constructs valid object", {
   )
 
   # check metadata method
-  expect_equal(metadata(collection), list())
+  expect_equal(get_metadata(collection), list())
 
   # Test specs_to_list
 

tests/testthat/test-DTAContainer.R

@@ -19,5 +19,5 @@ test_that("DTAContainer object is created and tables are accessible", {
   expect_equal(get_data(data_obj, "test")$STUDYID[1], "1234")
 
   # check metadata method
-  expect_equal(metadata(data_obj), list())
+  expect_equal(get_metadata(data_obj), list())
 })