fix: make build script functional within codespaces

.devcontainer/devcontainer.json

@@ -13,6 +13,10 @@
     }
   },
 
+  "features": {
+    "ghcr.io/devcontainers/features/python:1": {}
+  },
+
   "onCreateCommand": "echo \"//npm.pkg.github.com/:_authToken=$GITHUB_TOKEN\" > ~/.npmrc",
   "postCreateCommand": "npm ci",
   "postAttachCommand": "echo \"//npm.pkg.github.com/:_authToken=$GITHUB_TOKEN\" > ~/.npmrc"

.github/workflows/test.yml

@@ -16,6 +16,7 @@ jobs:
     - run: npm ci
       env:
         NODE_AUTH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    - run: make
     - run: npm test
     - name: Report coverage
       uses: codecov/codecov-action@v4

Makefile

@@ -2,6 +2,6 @@ TARGET = iso3166.min.js
 $(TARGET): parse.py data.csv codes.csv functions.js
 	python parse.py
 	echo ";(function () {" > $(TARGET)
-	./node_modules/.bin/uglifyjs -c -m --lint data.js functions.js >> $(TARGET)
+	./node_modules/.bin/uglifyjs -c -m -- data.js functions.js >> $(TARGET)
 	echo "})();" >> $(TARGET)
 	rm data.js

package.json

@@ -13,7 +13,7 @@
     "benchmark": "^2.1.4",
     "tape": "*",
     "tinybench": "^2.9.0",
-    "uglifyjs": "^2.4.10",
+    "uglify-js": "^3.19.3",
     "underscore": "^1.8.3"
   }
 }

parse.py

@@ -1,15 +1,18 @@
 import csv
 import json
 import re
+from functools import reduce
 
 
 def unicode_csv_reader(utf8_data, **kwargs):
     csv_reader = csv.reader(utf8_data, dialect=csv.excel, **kwargs)
     for row in csv_reader:
-        yield [unicode(cell, "utf-8") for cell in row]
+        # No need to decode from utf-8, as strings are Unicode in Python 3.
+        yield [cell for cell in row]
+
 
 # countries and their subdivisions.
-with open("data.csv", "r") as csv_file:
+with open("data.csv", "r", encoding="utf-8") as csv_file:
     countries = {}
     for row in unicode_csv_reader(csv_file):
         country_name = row[0]
@@ -23,32 +26,33 @@ def unicode_csv_reader(utf8_data, **kwargs):
             "name": subdivision_name.strip(),
             "type": type.strip()
         }
+
     subdivisions = reduce(
-        lambda a, b: a + len(countries[b].keys()), countries, 0
+        lambda a, b: a + len(list(countries[b]["sub"].keys())), countries, 0
     )
 
-    print "Countries: %d, Subdivisions: %d" % (
-        len(countries.keys()), subdivisions
-    )
+    print("Countries: %d, Subdivisions: %d" % (
+        len(countries), subdivisions
+    ))
 
-    with open("data.js", "w") as json_file:
-        print "Dumping subdivisions to data.js"
+    with open("data.js", "w", encoding="utf-8") as json_file:
+        print("Dumping subdivisions to data.js")
         json_file.write("var data = ")
-        json.dump(countries, json_file)
+        json.dump(countries, json_file, ensure_ascii=False)
         json_file.write(";")
 
 # alpha-3 to alpha-2 country code conversions
-with open("codes.csv", "r") as csv_file:
+with open("codes.csv", "r", encoding="utf-8") as csv_file:
     codes = {}
     for row in unicode_csv_reader(csv_file):
         alpha2 = row[0]
         alpha3 = row[1]
         codes[alpha3] = alpha2
 
-    print "Country codes: %d" % len(codes.keys())
+    print("Country codes: %d" % len(codes))
 
-    with open("data.js", "a") as json_file:
-        print "Dumping codes to data.js"
+    with open("data.js", "a", encoding="utf-8") as json_file:
+        print("Dumping codes to data.js")
         json_file.write("var codes = ")
-        json.dump(codes, json_file)
+        json.dump(codes, json_file, ensure_ascii=False)
         json_file.write(";")