add qualifier_group column for both primary and supplementary qualifiers

 - used to identify related terms

Author: brownag

R/data-documentation.R

@@ -99,12 +99,12 @@
 #' World Reference Base for Soil Resources (4th Edition, 2022)
 #'
 #' A _list_ containing three _data.frame_ elements `"rsg"`, `"pq"`, and `"sq"` providing information on the 'Representative Soil Groups', 'Principal Qualifiers,' and 'Supplementary Qualifiers,' respectively.
-#' 
+#'
 #' @details
-#' 
-#' Each element has the column `"code"` which is a number (1-32) referring to the position in the Reference Soil Groups, and the column `"reference_soil_group"` which is the corresponding group name. 
-#'  - The _data.frame_ `"rsg"` has column `"criteria"`, describing the logical criteria for each Reference Soil Group. 
-#'  - The _data.frame_ `"pq"` has qualifier names in column `"principal_qualifier"` and `"sq"` has column `"supplementary_qualifier"`. The `"pq"` and `"sq"` qualifier names may be single qualifiers, or several related qualifiers separated with a forward slash `" / "`
+#'
+#' Each element has the column `"code"` which is a number (1-32) referring to the position in the Reference Soil Groups, and the column `"reference_soil_group"` which is the corresponding group name.
+#'  - The _data.frame_ `"rsg"` has column `"criteria"`, describing the logical criteria for each Reference Soil Group.
+#'  - The _data.frame_ `"pq"` has qualifier names in column `"principal_qualifier"` and `"sq"` has column `"supplementary_qualifier"`. The `"pq"` and `"sq"` qualifier name columns (`primary_qualifier` and `supplementary_qualifier`) contain individual qualifier terms. Related qualifiers can be identified using `qualifier_group` column which is derived from qualifier names separated with a forward slash `" / "`
 #'
 #' @references
 #'
@@ -114,4 +114,4 @@
 #'
 #' @keywords datasets
 #'
-"wrb_4th_2022"
+"wrb_4th_2022"

data-raw/wrb_4th_2022.R

@@ -2,7 +2,7 @@
 library(pdftools)
 
 ## SETUP
-## 
+##
 # dir.create("misc/WRB2022")
 # download.file("https://wrb.isric.org/files/WRB_fourth_edition_2022-12-18.pdf",
 #               destfile = "misc/WRB2022/WRB_fourth_edition_2022-12-18.pdf")
@@ -18,7 +18,7 @@ library(pdftools)
 ## nope
 # x <- pdf_data("misc/WRB2022/WRB_fourth_edition_2022-12-18.pdf")
 # y <- do.call('rbind', x)
-# 
+#
 
 x <- readLines("misc/WRB2022/WRB_RSG.txt")
 x <- gsub("\u003c", "<", gsub("\u003E", ">", gsub("\u2264", "<=", gsub("\u2265", ">=", x))))
@@ -59,7 +59,12 @@ z <- lapply(xx, function(y) {
 names(z) <- z.names
 
 wrb_pq <- do.call('rbind', lapply(seq(z), function(i) {
-  data.frame(code = i, reference_soil_group = z.names[i], principal_qualifiers = z[[z.names[i]]])
+  pq <- lapply(strsplit(z[[z.names[i]]], "/"), trimws)
+  pg <- lapply(seq(pq), function(j) rep(z[[z.names[i]]][j], length(pq[[j]])))
+  data.frame(code = i,
+             reference_soil_group = z.names[i],
+             qualifier_group = unlist(pg),
+             principal_qualifiers = unlist(pq))
 }))
 rownames(wrb_pq) <- NULL
 # View(wrb_pq)
@@ -79,7 +84,12 @@ z <- lapply(xx, function(y) {
 names(z) <- z.names
 
 wrb_sq <- do.call('rbind', lapply(seq(z), function(i) {
-  data.frame(code = i, reference_soil_group = z.names[i], supplementary_qualifiers = z[[z.names[i]]])
+  sq <- lapply(strsplit(z[[z.names[i]]], "/"), trimws)
+  sg <- lapply(seq(sq), function(j) rep(z[[z.names[i]]][j], length(sq[[j]])))
+  data.frame(code = i,
+             reference_soil_group = z.names[i],
+             qualifier_group = unlist(pg),
+             supplementary_qualifiers = unlist(pq))
 }))
 rownames(wrb_sq) <- NULL
 # View(wrb_sq)