larvit/fejkdata
3
0
Fork 0
Code Pull Requests Actions Activity

Rename misc.country to misc.territory, name each one's sovereign state, and state the four data rules that settle it

Browse Source
This commit is contained in:
Lilleman auf Larv
2026-09-18 23:02:45 +02:00
parent e9d8603611
commit b0db82f2f1
8 changed files with 336 additions and 276 deletions
Download Patch File Download Diff File Expand all files Collapse all files
data-import/territory.py
+19 -6
View File
@@ -1,21 +1,23 @@
#!/usr/bin/env python3
"""Rebuild data/misc/country.tsv from datasets/country-codes (PDDL).
"""Rebuild data/misc/territory.tsv from datasets/country-codes (PDDL).
data-import/country.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
data-import/territory.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
"""
import argparse
import csv
import io
import re
import sys
from pathlib import Path
import source
import tsv
SOURCE = "https://raw.githubusercontent.com/datasets/country-codes/main/data/country-codes.csv"
OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "country.tsv"
OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "territory.tsv"
CACHE = Path(__file__).resolve().parent / "cache"
COLUMNS = ["alpha2", "alpha3", "calling-code", "capital", "currency", "flag", "languages", "name", "numeric", "tld"]
COLUMNS = ["alpha2", "alpha3", "calling-code", "capital", "country", "currency", "flag", "languages", "name", "numeric", "tld"]
SOVEREIGN = re.compile(r"^(?:Part of|Territor(?:y|ies) of|Crown dependency of|Commonwealth of|Associated with) ([A-Z]{2})$")
# Gaps in the source, keyed by alpha2.
FIXUPS = {"TR": {"currency": "TRY"}}
@@ -33,6 +35,12 @@ def languages(field):
return ",".join(p for p in field.split(",") if p)
def country(alpha2, independent):
"""The sovereign state the register records; a territory it records none for stands alone."""
m = SOVEREIGN.match(independent)
return m.group(1) if m else alpha2
def rows(text):
for r in csv.DictReader(io.StringIO(text)):
alpha2 = r["ISO3166-1-Alpha-2"]
@@ -41,6 +49,7 @@ def rows(text):
"alpha3": r["ISO3166-1-Alpha-3"],
"calling-code": calling_code(r["Dial"]),
"capital": r["Capital"],
"country": country(alpha2, r["is_independent"]),
"currency": r["ISO4217-currency_alphabetic_code"].split(",")[0],
"flag": flag(alpha2),
"languages": languages(r["Languages"]),
@@ -59,8 +68,12 @@ def main():
p.add_argument("--source", default=SOURCE)
p.add_argument("--out", default=str(OUT))
a = p.parse_args()
table = rows(source.fetch(a.source, a.cache, "country-codes.csv").decode("utf-8"))
tsv.write(a.out, COLUMNS, sorted(table, key=lambda r: r["alpha2"]))
table = sorted(rows(source.fetch(a.source, a.cache, "country-codes.csv").decode("utf-8")), key=lambda r: r["alpha2"])
shipped = {r["alpha2"] for r in table}
for r in table:
if r["country"] not in shipped:
sys.exit(f"{r['alpha2']}: country {r['country']} is no shipped territory; a sovereign the set drops leaves its territories unreadable")
tsv.write(a.out, COLUMNS, table)
if __name__ == "__main__":