.gitignore

@@ -1,3 +1,4 @@
 .claude
 *.out
 __pycache__/
+data-import/cache/

DATA-LICENSES.md

@@ -2,9 +2,16 @@
 
 Every shipped dataset, its source, its licence and the attribution it asks for. A
 `data-import/` script rebuilds each sourced table; a curated one is hand-written.
+The scripts run through `docker compose run --rm data-import data-import/<name>.py`
+and cache their downloads under `data-import/cache/`; `geo-se.py` needs a
+Trafikverket API key, free at [data.trafikverket.se](https://data.trafikverket.se/),
+in `TRAFIKVERKET_API_KEY` or a `--key-file`.
 
 | Table | Source | Licence | Attribution | Rebuild |
 |-------|--------|---------|-------------|---------|
+| `geo/SE/locality.tsv`, `postal-code.tsv` | [GeoNames](https://www.geonames.org/) postal codes for SE; populations from SCB tätorter 2023 | [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); CC0 1.0 | "Postal codes from GeoNames, www.geonames.org" | `data-import/geo-se.py` |
+| `geo/SE/region.tsv`, `municipality.tsv` | [SCB](https://www.scb.se/) län and kommun codes 2026 and population 2024 | [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/) | none required | `data-import/geo-se.py` |
+| `geo/SE/street.tsv` | [Trafikverket NVDB](https://www.trafikverket.se/) Gatunamn, through the open API | CC0 1.0 | none required | `data-import/geo-se.py` |
 | `misc/country.tsv` | [datasets/country-codes](https://github.com/datasets/country-codes) | [PDDL 1.0](https://opendatacommons.org/licenses/pddl/1-0/) | none required | `data-import/country.py` |
 | `misc/currency.tsv` | [datasets/currency-codes](https://github.com/datasets/currency-codes); symbols from [Unicode CLDR](https://github.com/unicode-org/cldr) `en.xml` and `root.xml` | PDDL 1.0; [Unicode License v3](https://www.unicode.org/license.txt) | CLDR: "Copyright © 1991-2025 Unicode, Inc. Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the United States and other countries." | `data-import/currency.py` |
 | `misc/httpstatus.tsv` | curated (IANA HTTP status codes are facts) | — | — | — |

data-import/geo-se.py

@@ -0,0 +1,264 @@
+#!/usr/bin/env python3
+"""Rebuild data/geo/SE/*.tsv from SCB (CC0), GeoNames (CC BY 4.0) and Trafikverket NVDB (CC0).
+
+    TRAFIKVERKET_API_KEY=… data-import/geo-se.py [--key-file FILE] [--cache DIR] [--streets-per-locality N] [--out DIR]
+
+A locality is a GeoNames postort, placed in the municipality it names, else of its
+tätort, else of most of its codes, and weighted by its tätort's population, else its
+municipality's, else 200. Box codes are dropped by the digit after the postort's own
+prefix. Each NVDB street segment goes to the nearest postal code centroid; a locality
+keeps the N names with most segments.
+"""
+import argparse
+import collections
+import csv
+import io
+import json
+import math
+import os
+import re
+import sys
+import urllib.request
+import xml.etree.ElementTree as ET
+import zipfile
+from pathlib import Path
+
+CODES = "https://www.scb.se/contentassets/7a89e48960f741e08918e489ea36354a/kommunlankod-2026.xlsx"
+POPULATION = "https://api.scb.se/OV0104/v1/doris/sv/ssd/START/BE/BE0101/BE0101A/BefolkningNy"
+POPULATION_QUERY = {
+    "query": [
+        {"code": "Region", "selection": {"filter": "all", "values": ["*"]}},
+        {"code": "ContentsCode", "selection": {"filter": "item", "values": ["BE0101N1"]}},
+        {"code": "Tid", "selection": {"filter": "top", "values": ["1"]}},
+    ],
+    "response": {"format": "json"},
+}
+TATORTER = "https://geodata.scb.se/geoserver/stat/wfs?service=WFS&version=2.0.0&request=GetFeature&typeNames=stat:Tatorter_2023&outputFormat=csv&propertyName=tatort,kommun,bef"
+POSTAL_CODES = "https://download.geonames.org/export/zip/SE.zip"
+NVDB = "https://api.trafikinfo.trafikverket.se/v2/data.json"
+NVDB_PAGE = 50000
+OUT = Path(__file__).resolve().parent.parent / "data" / "geo" / "SE"
+CACHE = Path(__file__).resolve().parent / "cache"
+TIMEZONE = "Europe/Stockholm"
+ONE_POSITION = {"Stockholm", "Göteborg", "Malmö"}
+UNMATCHED_POPULATION = 200
+XLSX_NS = {"m": "http://schemas.openxmlformats.org/spreadsheetml/2006/main"}
+
+
+def fetch(url, cache, name, data=None, headers=None):
+    path = cache / name
+    if not path.exists():
+        req = urllib.request.Request(url, data=data, headers=headers or {})
+        with urllib.request.urlopen(req, timeout=300) as r:
+            path.write_bytes(r.read())
+    return path.read_bytes()
+
+
+def xlsx_rows(data):
+    z = zipfile.ZipFile(io.BytesIO(data))
+    strings = ["".join(t.text or "" for t in si.iter("{%s}t" % XLSX_NS["m"])) for si in ET.fromstring(z.read("xl/sharedStrings.xml")).findall("m:si", XLSX_NS)]
+    sheet = ET.fromstring(z.read("xl/worksheets/sheet1.xml"))
+    for row in sheet.findall(".//m:row", XLSX_NS):
+        cells = []
+        for c in row.findall("m:c", XLSX_NS):
+            v = c.find("m:v", XLSX_NS)
+            cells.append("" if v is None else strings[int(v.text)] if c.get("t") == "s" else v.text)
+        yield cells
+
+
+def scb_codes(cache):
+    regions, municipalities = {}, {}
+    for cells in xlsx_rows(fetch(CODES, cache, "kommunlankod.xlsx")):
+        if len(cells) < 2 or not re.fullmatch(r"\d{2}|\d{4}", cells[0]):
+            continue
+        (regions if len(cells[0]) == 2 else municipalities)[cells[0]] = cells[1].strip()
+    return regions, municipalities
+
+
+def scb_population(cache):
+    body = json.dumps(POPULATION_QUERY).encode()
+    data = fetch(POPULATION, cache, "befolkning.json", data=body, headers={"Content-Type": "application/json"})
+    return {row["key"][0]: row["values"][0] for row in json.loads(data.decode("utf-8-sig"))["data"]}
+
+
+def scb_tatorter(cache):
+    text = fetch(TATORTER, cache, "tatorter.csv").decode("utf-8")
+    by_name = collections.defaultdict(list)
+    for r in csv.DictReader(io.StringIO(text)):
+        by_name[r["tatort"]].append((r["kommun"], int(r["bef"])))
+    return by_name
+
+
+def geonames(cache):
+    z = zipfile.ZipFile(io.BytesIO(fetch(POSTAL_CODES, cache, "SE.zip")))
+    rows = []
+    for line in z.read("SE.txt").decode("utf-8").splitlines():
+        f = line.split("\t")
+        lat, lon = (float(f[9]), float(f[10])) if f[9] and f[10] else (None, None)
+        rows.append({"code": f[1], "locality": f[2], "municipality": f[6], "lat": lat, "lon": lon})
+    return rows
+
+
+def nvdb_segments(cache, key):
+    path = cache / "nvdb-gatunamn.tsv"
+    if not path.exists():
+        with open(path, "w", encoding="utf-8") as out:
+            change = "0"
+            while True:
+                query = (
+                    f'<REQUEST><LOGIN authenticationkey="{key}"/>'
+                    f'<QUERY objecttype="Gatunamn" namespace="vägdata.nvdb_dk_o" schemaversion="1.0" limit="{NVDB_PAGE}" changeid="{change}">'
+                    "<FILTER><EQ name=\"Deleted\" value=\"false\"/></FILTER>"
+                    "<INCLUDE>Namn</INCLUDE><INCLUDE>Geometry.WKT-WGS84-3D</INCLUDE></QUERY></REQUEST>"
+                )
+                req = urllib.request.Request(NVDB, data=query.encode(), headers={"Content-Type": "text/xml"})
+                with urllib.request.urlopen(req, timeout=600) as r:
+                    result = json.load(r)["RESPONSE"]["RESULT"][0]
+                rows = result.get("Gatunamn", [])
+                for row in rows:
+                    m = re.match(r"LINESTRING Z \(([-\d.]+) ([-\d.]+) ", row.get("Geometry", {}).get("WKT-WGS84-3D", ""))
+                    name = " ".join(row.get("Namn", "").split())
+                    if m and name:
+                        out.write(f"{name}\t{m.group(1)}\t{m.group(2)}\n")
+                change = result["INFO"]["LASTCHANGEID"]
+                if len(rows) < NVDB_PAGE:
+                    break
+    for line in path.read_text(encoding="utf-8").splitlines():
+        name, lon, lat = line.split("\t")
+        yield name, float(lat), float(lon)
+
+
+class Nearest:
+    """Nearest point by an equirectangular distance, over a degree grid."""
+
+    def __init__(self, points, cell=0.05):
+        self.cell = cell
+        self.grid = collections.defaultdict(list)
+        for lat, lon, value in points:
+            self.grid[(int(lat // cell), int(lon // cell))].append((lat, lon, value))
+
+    def find(self, lat, lon):
+        ci, cj = int(lat // self.cell), int(lon // self.cell)
+        best, best_d = None, math.inf
+        ring = 0
+        while ring < 400:
+            for i in range(ci - ring, ci + ring + 1):
+                for j in range(cj - ring, cj + ring + 1):
+                    if max(abs(i - ci), abs(j - cj)) != ring:
+                        continue
+                    for plat, plon, value in self.grid.get((i, j), ()):
+                        d = (plat - lat) ** 2 + ((plon - lon) * math.cos(math.radians(lat))) ** 2
+                        if d < best_d:
+                            best, best_d = value, d
+            if best is not None and math.sqrt(best_d) < ring * self.cell * math.cos(math.radians(lat)):
+                return best
+            ring += 1
+        return best
+
+
+def street_delivery(name, codes):
+    """The codes delivered to a street: the digit after the postort's own prefix says box, company or reply."""
+    if name in ONE_POSITION:
+        return [c for c in codes if c[1] != "0"]
+    largest = collections.Counter(c[:3] for c in codes).most_common(1)[0][1]
+    length = 3 if largest * 2 >= len(codes) else 2
+    return [c for c in codes if c[length] not in "018"]
+
+
+def municipality_of(name, rows, tatorter, municipalities):
+    named = [code for code, n in municipalities.items() if n == name]
+    if named:
+        return named[0], "kommun"
+    voted = collections.Counter(r["municipality"] for r in rows if r["municipality"] in municipalities)
+    matches = tatorter.get(name, [])
+    if matches:
+        in_vote = [m for m in matches if voted and m[0] == voted.most_common(1)[0][0]]
+        return max(in_vote or matches, key=lambda m: m[1])[0], "tatort"
+    if voted:
+        return voted.most_common(1)[0][0], "codes"
+    return None, "unplaced"
+
+
+def population_of(name, municipality, tatorter, municipalities, population):
+    matches = [m for m in tatorter.get(name, []) if m[0] == municipality]
+    if matches:
+        return str(max(m[1] for m in matches))
+    return population[municipality] if municipalities[municipality] == name else str(UNMATCHED_POPULATION)
+
+
+def well_cased(name):
+    return all(part[:1].isupper() and (len(part) == 1 or not part.isupper()) for part in re.split(r"[ -]", name))
+
+
+def write(path, columns, rows):
+    lines = ["\t".join(columns)]
+    for row in rows:
+        cells = [str(row[c]) for c in columns]
+        assert not any(re.search(r"[\t\n{}]", c) for c in cells), row
+        lines.append("\t".join(cells))
+    path.write_text("\n".join(lines) + "\n", encoding="utf-8")
+    print(f"{path}: {len(rows)} rows", file=sys.stderr)
+
+
+def main():
+    p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    p.add_argument("--cache", default=str(CACHE))
+    p.add_argument("--key-file", help="file holding the Trafikverket API key; TRAFIKVERKET_API_KEY otherwise")
+    p.add_argument("--out", default=str(OUT))
+    p.add_argument("--streets-per-locality", type=int, default=10)
+    a = p.parse_args()
+    key = Path(a.key_file).read_text().strip() if a.key_file else os.environ.get("TRAFIKVERKET_API_KEY")
+    if not key:
+        sys.exit("set TRAFIKVERKET_API_KEY or pass --key-file")
+    cache, out = Path(a.cache), Path(a.out)
+    cache.mkdir(parents=True, exist_ok=True)
+    out.mkdir(parents=True, exist_ok=True)
+
+    regions, municipalities = scb_codes(cache)
+    population = scb_population(cache)
+    tatorter = scb_tatorter(cache)
+    codes = geonames(cache)
+
+    by_locality = collections.defaultdict(list)
+    for r in codes:
+        by_locality[r["locality"]].append(r)
+    localities, how = {}, collections.Counter()
+    for name, rows in by_locality.items():
+        municipality, method = municipality_of(name, rows, tatorter, municipalities)
+        how[method] += 1
+        kept = street_delivery(name, [r["code"].replace(" ", "") for r in rows])
+        with_point = [r for r in rows if r["lat"] is not None]
+        if municipality is None or not kept or not with_point or not well_cased(name):
+            continue
+        lat = sum(r["lat"] for r in with_point) / len(with_point)
+        lon = sum(r["lon"] for r in with_point) / len(with_point)
+        localities[name] = {"name": name, "municipality": municipality, "population": population_of(name, municipality, tatorter, municipalities, population), "lat": f"{lat:.4f}", "lon": f"{lon:.4f}", "codes": kept}
+    print(f"municipality by {dict(how)}; {len(by_locality) - len(localities)} postorter dropped", file=sys.stderr)
+
+    centroids = [(r["lat"], r["lon"], r["locality"]) for r in codes if r["lat"] is not None and r["locality"] in localities]
+    nearest_locality = Nearest(centroids)
+    segments = collections.Counter()
+    for name, lat, lon in nvdb_segments(cache, key):
+        segments[(nearest_locality.find(lat, lon), name)] += 1
+    streets_of = collections.defaultdict(list)
+    for (locality, name), n in segments.items():
+        streets_of[locality].append((n, name))
+    streets = []
+    for locality in sorted(streets_of):
+        for n, name in sorted(streets_of[locality], key=lambda s: (-s[0], s[1]))[: a.streets_per_locality]:
+            streets.append({"name": name, "locality": locality, "segments": n})
+    for name in [l for l in localities if l not in streets_of]:
+        del localities[name]
+
+    empty = sorted(m for m in municipalities if not any(l["municipality"] == m for l in localities.values()))
+    if empty:
+        sys.exit(f"municipalities without a locality: {empty}")
+    write(out / "region.tsv", ["code", "name", "population", "timezone"], [{"code": c, "name": n, "population": population[c], "timezone": TIMEZONE} for c, n in sorted(regions.items())])
+    write(out / "municipality.tsv", ["code", "name", "region", "population"], [{"code": c, "name": n, "region": c[:2], "population": population[c]} for c, n in sorted(municipalities.items())])
+    write(out / "locality.tsv", ["name", "municipality", "population", "lat", "lon"], [l for _, l in sorted(localities.items())])
+    write(out / "postal-code.tsv", ["code", "locality"], sorted(({"code": f"{c[:3]} {c[3:]}", "locality": l["name"]} for l in localities.values() for c in l["codes"]), key=lambda r: r["code"]))
+    write(out / "street.tsv", ["name", "locality", "segments"], streets)
+
+
+if __name__ == "__main__":
+    main()

data/geo/SE/address.json

@@ -0,0 +1,14 @@
+{
+  "format": "{street} {number}\n{postal-code} {locality}",
+  "street": "{.street.name}",
+  "number": [
+    "{int(1,9)}",
+    "{int(10,99)}",
+    { "format": "{int(100,999)}", "weight": 0.2 },
+    { "format": "{int(1,9)}{upper(1)}", "weight": 0.2 },
+    { "format": "{int(10,99)}{upper(1)}", "weight": 0.1 },
+    { "format": "{int(100,999)}{upper(1)}", "weight": 0.05 }
+  ],
+  "postal-code": "{.postal-code.code}",
+  "locality": "{.locality.name}"
+}

data/geo/SE/locality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "locality.tsv", "key": "name", "parent": "municipality", "weight": "population" }

data/geo/SE/municipality.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "municipality.tsv", "key": "code", "name": "name", "parent": "region", "weight": "population" }

data/geo/SE/municipality.tsv

@@ -0,0 +1,291 @@
+code	name	region	population
+0114	Upplands Väsby	01	50323
+0115	Vallentuna	01	35119
+0117	Österåker	01	49787
+0120	Värmdö	01	46635
+0123	Järfälla	01	88950
+0125	Ekerö	01	28910
+0126	Huddinge	01	114304
+0127	Botkyrka	01	95905
+0128	Salem	01	17507
+0136	Haninge	01	100895
+0138	Tyresö	01	49179
+0139	Upplands-Bro	01	32868
+0140	Nykvarn	01	12342
+0160	Täby	01	77744
+0162	Danderyd	01	32425
+0163	Sollentuna	01	77624
+0180	Stockholm	01	995574
+0181	Södertälje	01	102911
+0182	Nacka	01	112112
+0183	Sundbyberg	01	56274
+0184	Solna	01	85789
+0186	Lidingö	01	48377
+0187	Vaxholm	01	11822
+0188	Norrtälje	01	66585
+0191	Sigtuna	01	52767
+0192	Nynäshamn	01	30579
+0305	Håbo	03	22973
+0319	Älvkarleby	03	9552
+0330	Knivsta	03	21193
+0331	Heby	03	14345
+0360	Tierp	03	21104
+0380	Uppsala	03	248016
+0381	Enköping	03	48591
+0382	Östhammar	03	22138
+0428	Vingåker	04	8750
+0461	Gnesta	04	11458
+0480	Nyköping	04	58344
+0481	Oxelösund	04	12031
+0482	Flen	04	15362
+0483	Katrineholm	04	34154
+0484	Eskilstuna	04	107203
+0486	Strängnäs	04	39313
+0488	Trosa	04	14927
+0509	Ödeshög	05	5237
+0512	Ydre	05	3626
+0513	Kinda	05	9957
+0560	Boxholm	05	5517
+0561	Åtvidaberg	05	11467
+0562	Finspång	05	21623
+0563	Valdemarsvik	05	7525
+0580	Linköping	05	168035
+0581	Norrköping	05	144980
+0582	Söderköping	05	14789
+0583	Motala	05	43505
+0584	Vadstena	05	7490
+0586	Mjölby	05	28695
+0604	Aneby	06	6797
+0617	Gnosjö	06	9131
+0642	Mullsjö	06	7594
+0643	Habo	06	13456
+0662	Gislaved	06	28936
+0665	Vaggeryd	06	14825
+0680	Jönköping	06	147654
+0682	Nässjö	06	31587
+0683	Värnamo	06	34542
+0684	Sävsjö	06	11563
+0685	Vetlanda	06	27528
+0686	Eksjö	06	17792
+0687	Tranås	06	18604
+0760	Uppvidinge	07	9061
+0761	Lessebo	07	8289
+0763	Tingsryd	07	11966
+0764	Alvesta	07	19830
+0765	Älmhult	07	17653
+0767	Markaryd	07	9938
+0780	Växjö	07	98334
+0781	Ljungby	07	28280
+0821	Högsby	08	5321
+0834	Torsås	08	6984
+0840	Mörbylånga	08	16224
+0860	Hultsfred	08	13673
+0861	Mönsterås	08	13069
+0862	Emmaboda	08	9006
+0880	Kalmar	08	72704
+0881	Nybro	08	19951
+0882	Oskarshamn	08	26923
+0883	Västervik	08	36447
+0884	Vimmerby	08	15384
+0885	Borgholm	08	10666
+0980	Gotland	09	60971
+1060	Olofström	10	13000
+1080	Karlskrona	10	66301
+1081	Ronneby	10	28741
+1082	Karlshamn	10	31751
+1083	Sölvesborg	10	17430
+1214	Svalöv	12	14543
+1230	Staffanstorp	12	27303
+1231	Burlöv	12	20101
+1233	Vellinge	12	37816
+1256	Östra Göinge	12	13978
+1257	Örkelljunga	12	10277
+1260	Bjuv	12	15985
+1261	Kävlinge	12	32477
+1262	Lomma	12	24715
+1263	Svedala	12	23581
+1264	Skurup	12	17099
+1265	Sjöbo	12	19337
+1266	Hörby	12	15562
+1267	Höör	12	17518
+1270	Tomelilla	12	13639
+1272	Bromölla	12	12470
+1273	Osby	12	12947
+1275	Perstorp	12	7235
+1276	Klippan	12	17714
+1277	Åstorp	12	16449
+1278	Båstad	12	16026
+1280	Malmö	12	365644
+1281	Lund	12	131590
+1282	Landskrona	12	47309
+1283	Helsingborg	12	152091
+1284	Höganäs	12	28430
+1285	Eslöv	12	34922
+1286	Ystad	12	32106
+1287	Trelleborg	12	47269
+1290	Kristianstad	12	86379
+1291	Simrishamn	12	18890
+1292	Ängelholm	12	45110
+1293	Hässleholm	12	52114
+1315	Hylte	13	10196
+1380	Halmstad	13	106084
+1381	Laholm	13	26595
+1382	Falkenberg	13	47337
+1383	Varberg	13	69070
+1384	Kungsbacka	13	85792
+1401	Härryda	14	40003
+1402	Partille	14	41060
+1407	Öckerö	14	12771
+1415	Stenungsund	14	27851
+1419	Tjörn	14	16092
+1421	Orust	14	15352
+1427	Sotenäs	14	9104
+1430	Munkedal	14	10354
+1435	Tanum	14	12773
+1438	Dals-Ed	14	4606
+1439	Färgelanda	14	6376
+1440	Ale	14	32576
+1441	Lerum	14	43570
+1442	Vårgårda	14	12474
+1443	Bollebygd	14	9802
+1444	Grästorp	14	5555
+1445	Essunga	14	5560
+1446	Karlsborg	14	7023
+1447	Gullspång	14	5031
+1452	Tranemo	14	11839
+1460	Bengtsfors	14	9076
+1461	Mellerud	14	9052
+1462	Lilla Edet	14	14442
+1463	Mark	14	35155
+1465	Svenljunga	14	10747
+1466	Herrljunga	14	9497
+1470	Vara	14	16088
+1471	Götene	14	13286
+1472	Tibro	14	11338
+1473	Töreboda	14	9043
+1480	Göteborg	14	608993
+1481	Mölndal	14	71420
+1482	Kungälv	14	50313
+1484	Lysekil	14	13907
+1485	Uddevalla	14	57010
+1486	Strömstad	14	13482
+1487	Vänersborg	14	40041
+1488	Trollhättan	14	59003
+1489	Alingsås	14	42722
+1490	Borås	14	114872
+1491	Ulricehamn	14	24985
+1492	Åmål	14	11906
+1493	Mariestad	14	24583
+1494	Lidköping	14	40425
+1495	Skara	14	18707
+1496	Skövde	14	57995
+1497	Hjo	14	9350
+1498	Tidaholm	14	12805
+1499	Falköping	14	32806
+1715	Kil	17	12061
+1730	Eda	17	8412
+1737	Torsby	17	11321
+1760	Storfors	17	3788
+1761	Hammarö	17	16992
+1762	Munkfors	17	3625
+1763	Forshaga	17	11520
+1764	Grums	17	9004
+1765	Årjäng	17	9825
+1766	Sunne	17	13356
+1780	Karlstad	17	98084
+1781	Kristinehamn	17	23756
+1782	Filipstad	17	9776
+1783	Hagfors	17	11418
+1784	Arvika	17	25547
+1785	Säffle	17	14899
+1814	Lekeberg	18	8606
+1860	Laxå	18	5423
+1861	Hallsberg	18	16120
+1862	Degerfors	18	9278
+1863	Hällefors	18	6321
+1864	Ljusnarsberg	18	4369
+1880	Örebro	18	160140
+1881	Kumla	18	22681
+1882	Askersund	18	11477
+1883	Karlskoga	18	30180
+1884	Nora	18	10639
+1885	Lindesberg	18	23141
+1904	Skinnskatteberg	19	4256
+1907	Surahammar	19	9845
+1960	Kungsör	19	8694
+1961	Hallstahammar	19	16653
+1962	Norberg	19	5452
+1980	Västerås	19	160634
+1981	Sala	19	22843
+1982	Fagersta	19	13072
+1983	Köping	19	25729
+1984	Arboga	19	13980
+2021	Vansbro	20	6752
+2023	Malung-Sälen	20	10254
+2026	Gagnef	20	10384
+2029	Leksand	20	16137
+2031	Rättvik	20	10998
+2034	Orsa	20	6851
+2039	Älvdalen	20	6882
+2061	Smedjebacken	20	10823
+2062	Mora	20	20540
+2080	Falun	20	59945
+2081	Borlänge	20	51425
+2082	Säter	20	11223
+2083	Hedemora	20	15281
+2084	Avesta	20	22417
+2085	Ludvika	20	26634
+2101	Ockelbo	21	5715
+2104	Hofors	21	9281
+2121	Ovanåker	21	11341
+2132	Nordanstig	21	9262
+2161	Ljusdal	21	18445
+2180	Gävle	21	103838
+2181	Sandviken	21	38360
+2182	Söderhamn	21	24545
+2183	Bollnäs	21	26243
+2184	Hudiksvall	21	37528
+2260	Ånge	22	9044
+2262	Timrå	22	17521
+2280	Härnösand	22	24515
+2281	Sundsvall	22	99048
+2282	Kramfors	22	17491
+2283	Sollefteå	22	18396
+2284	Örnsköldsvik	22	55443
+2303	Ragunda	23	5146
+2305	Bräcke	23	6035
+2309	Krokom	23	15680
+2313	Strömsund	23	11023
+2321	Åre	23	12693
+2326	Berg	23	7108
+2361	Härjedalen	23	10175
+2380	Östersund	23	64979
+2401	Nordmaling	24	6942
+2403	Bjurholm	24	2359
+2404	Vindeln	24	5417
+2409	Robertsfors	24	6690
+2417	Norsjö	24	3968
+2418	Malå	24	2962
+2421	Storuman	24	5577
+2422	Sorsele	24	2357
+2425	Dorotea	24	2294
+2460	Vännäs	24	9132
+2462	Vilhelmina	24	6229
+2463	Åsele	24	2694
+2480	Umeå	24	134249
+2481	Lycksele	24	12118
+2482	Skellefteå	24	78150
+2505	Arvidsjaur	25	6089
+2506	Arjeplog	25	2599
+2510	Jokkmokk	25	4701
+2513	Överkalix	25	3201
+2514	Kalix	25	15391
+2518	Övertorneå	25	4057
+2521	Pajala	25	5857
+2523	Gällivare	25	17233
+2560	Älvsbyn	25	7774
+2580	Luleå	25	79645
+2581	Piteå	25	42447
+2582	Boden	25	28049
+2583	Haparanda	25	9151
+2584	Kiruna	25	22426

data/geo/SE/postal-code.json

@@ -0,0 +1 @@
+{ "format": "{code}", "rows": "postal-code.tsv", "key": "code", "parent": "locality" }

data/geo/SE/region.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "region.tsv", "key": "code", "name": "name", "weight": "population" }

data/geo/SE/region.tsv

@@ -0,0 +1,22 @@
+code	name	population	timezone
+01	Stockholms län	2473307	Europe/Stockholm
+03	Uppsala län	407912	Europe/Stockholm
+04	Södermanlands län	301542	Europe/Stockholm
+05	Östergötlands län	472446	Europe/Stockholm
+06	Jönköpings län	370009	Europe/Stockholm
+07	Kronobergs län	203351	Europe/Stockholm
+08	Kalmar län	246352	Europe/Stockholm
+09	Gotlands län	60971	Europe/Stockholm
+10	Blekinge län	157223	Europe/Stockholm
+12	Skåne län	1428626	Europe/Stockholm
+13	Hallands län	345074	Europe/Stockholm
+14	Västra Götalands län	1772821	Europe/Stockholm
+17	Värmlands län	283384	Europe/Stockholm
+18	Örebro län	308375	Europe/Stockholm
+19	Västmanlands län	281158	Europe/Stockholm
+20	Dalarnas län	286546	Europe/Stockholm
+21	Gävleborgs län	284558	Europe/Stockholm
+22	Västernorrlands län	241458	Europe/Stockholm
+23	Jämtlands län	132839	Europe/Stockholm
+24	Västerbottens län	281138	Europe/Stockholm
+25	Norrbottens län	248620	Europe/Stockholm

data/geo/SE/street.json

@@ -0,0 +1 @@
+{ "format": "{name}", "rows": "street.tsv", "parent": "locality", "weight": "segments" }

data/sv_SE/address.json

@@ -1,21 +1,7 @@
 {
   "format": "{street} {street-number}\n{postal-code} {locality}",
-  "street": [
+  "street": "{/geo.SE.address.street}",
-    {
+  "street-number": "{/geo.SE.address.number}",
-      "format": "{first}{last}",
+  "postal-code": "{/geo.SE.address.postal-code}",
-      "first": ["Ängs", "Bergs", "Björk", "Drottning", "Eke", "Furu", "Hamn", "Köpmans", "Kungs", "Linné", "Norra", "Nybro", "Oden", "Öster", "Park", "Skogs", "Skol", "Slotts", "Söder", "Stations", "Stor", "Strand", "Trädgårds", "Vasa", "Väster"],
+  "locality": "{/geo.SE.address.locality}"
-      "last": ["gatan", "vägen", "stigen", "gränd", "backen", "torget", "allén"]
-    },
-    ["Avenyn", "Birger Jarlsgatan", "Promenaden", "Staby", "Sveavägen", "Vintjärn"]
-  ],
-  "street-number": [
-    "{int(1,9)}",
-    "{int(10,99)}",
-    { "format": "{int(100,999)}", "weight": 0.2 },
-    { "format": "{int(1,9)}{upper(1)}", "weight": 0.2 },
-    { "format": "{int(10,99)}{upper(1)}", "weight": 0.1 },
-    { "format": "{int(100,999)}{upper(1)}", "weight": 0.05 }
-  ],
-  "postal-code": "{int(100,999)} {int(10,99)}",
-  "locality": ["Alingsås", "Alvesta", "Ängelholm", "Arboga", "Arvika", "Avesta", "Boden", "Bollnäs", "Borås", "Borlänge", "Enköping", "Eskilstuna", "Eslöv", "Fagersta", "Falkenberg", "Falköping", "Falun", "Finspång", "Gällivare", "Gävle", "Göteborg", "Halmstad", "Haparanda", "Härnösand", "Hässleholm", "Helsingborg", "Huddinge", "Hudiksvall", "Jönköping", "Kalmar", "Karlshamn", "Karlskoga", "Karlskrona", "Karlstad", "Katrineholm", "Kiruna", "Köping", "Kramfors", "Kristianstad", "Kristinehamn", "Landskrona", "Lidingö", "Lidköping", "Lindesberg", "Linköping", "Ljungby", "Ludvika", "Luleå", "Lund", "Lycksele", "Malmö", "Mariestad", "Mjölby", "Mölndal", "Mora", "Motala", "Nacka", "Nässjö", "Norrköping", "Norrtälje", "Nyköping", "Nynäshamn", "Örebro", "Örnsköldsvik", "Oskarshamn", "Östersund", "Piteå", "Rabbalshede", "Ronneby", "Säffle", "Sandviken", "Sävsjö", "Sigtuna", "Skara", "Skellefteå", "Skövde", "Söderhamn", "Södertälje", "Sollentuna", "Solna", "Sölvesborg", "Stockholm", "Strängnäs", "Sundbyberg", "Sundsvall", "Täby", "Tierp", "Tranås", "Trelleborg", "Trollhättan", "Uddevalla", "Ulricehamn", "Umeå", "Upplands Väsby", "Uppsala", "Vänersborg", "Varberg", "Värnamo", "Västerås", "Västervik", "Växjö", "Vetlanda", "Vimmerby", "Visby", "Ystad"]
 }