add additional expression of FoR-classification

Author: chreman

server/preprocessing/other-scripts/subject_cleaning.R

@@ -125,10 +125,12 @@ drop_not_elsewhere_classified <- function(keywords) {
 }
 
 drop_for <- function(keywords) {
-  # ANZSRC Fields of Research, three serialisations:
-  #   "01 Mathematical Sciences (for)", "38 Economics (for-2020)", "FoR 03 (Chemical Sciences)".
+  # ANZSRC Fields of Research, serialisations seen in the data:
+  #   "01 Mathematical Sciences (for)", "38 Economics (for-2020)", "FoR 03 (Chemical Sciences)",
+  #   "anzsrc-for: 3402 Inorganic Chemistry".
   # The FoR-prefix form requires a letter after "(" so a stray "... (89.8%)" is not matched.
-  keywords[!grepl("\\(for(-2020)?\\)\\s*$|^FoR [0-9]+ \\([A-Za-z]", keywords, ignore.case = TRUE)]
+  keywords[!grepl("\\(for(-2020)?\\)\\s*$|^FoR [0-9]+ \\([A-Za-z]|^anzsrc-for ?: ?[0-9]+",
+                  keywords, ignore.case = TRUE)]
 }
 
 drop_hrcs <- function(keywords) {

server/preprocessing/other-scripts/test/test_subject_cleaning.R

@@ -71,10 +71,13 @@ test_that("rcdc keywords are dropped", {
 test_that("'not elsewhere classified' keywords are dropped", {
   drops_to_cooperation("Biological Sciences not elsewhere classified")
 })
-test_that("FoR keywords are dropped (all three serialisations)", {
+test_that("FoR keywords are dropped (all serialisations)", {
   drops_to_cooperation("01 Mathematical Sciences (for)")
   drops_to_cooperation("38 Economics (for-2020)")
   drops_to_cooperation("FoR 03 (Chemical Sciences)")
+  drops_to_cooperation("anzsrc-for: 3402 Inorganic Chemistry")
+  drops_to_cooperation("anzsrc-for: 34 Chemical Sciences")
+  drops_to_cooperation("anzsrc-for: 03 Chemical Sciences")
 })
 test_that("hrcs keywords are dropped", {
   drops_to_cooperation("2.1 Biological and endogenous factors (hrcs-rac)")