Answer architecture round 5: the shipped packages are enus, svse, geose, geous and misc, each holding its files at its root under its manifest's namespace, and the errors use the wording a bench of the Audience chose

2026-10-11 12:15:41 +02:00
parent 29a76d5d9a
commit 7b70530a8a
152 changed files with 217 additions and 132 deletions
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/currency.tsv from datasets/currency-codes (PDDL) and CLDR's symbols (Unicode).
+"""Rebuild data/misc/currency.tsv from datasets/currency-codes (PDDL) and CLDR's symbols (Unicode).

    data-import/currency.py [--source URL_OR_FILE] [--symbols URL_OR_FILE ...] [--cache DIR] [--out FILE]

@@ -19,7 +19,7 @@ SYMBOLS = [
    "https://raw.githubusercontent.com/unicode-org/cldr/main/common/main/en.xml",
    "https://raw.githubusercontent.com/unicode-org/cldr/main/common/main/root.xml",
 ]
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "currency.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "currency.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["code", "decimals", "name", "numeric", "symbol"]

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/geo/SE/geo/SE/*.tsv from SCB (CC0), GeoNames (CC BY 4.0) and Trafikverket NVDB (CC0).
+"""Rebuild data/geose/*.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]
 """
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/geo/US/geo/US/*.tsv from the Census Bureau's Gazetteer, population estimates, ZCTA relationships and TIGER/Line files (public domain).
+"""Rebuild data/geous/*.tsv from the Census Bureau's Gazetteer, population estimates, ZCTA relationships and TIGER/Line files (public domain).

    data-import/geo-us.py [--cache DIR] [--min-population N] [--streets-per-locality N] [--out DIR]
 """
@@ -5,14 +5,14 @@ import math
 import sys
 from pathlib import Path

-DATA = Path(__file__).resolve().parent.parent / "data" / "geo"
+DATA = Path(__file__).resolve().parent.parent / "data"
 CACHE = Path(__file__).resolve().parent / "cache"


 def parser(doc, country, **own):
    """A parser for the options every country's import takes, plus the script's own: each keyword names one option, with
    "_" standing for "-"."""
-    options = {"cache": {"default": str(CACHE)}, "out": {"default": str(DATA / country / "geo" / country)}, "streets_per_locality": {"type": int, "default": 10}, **own}
+    options = {"cache": {"default": str(CACHE)}, "out": {"default": str(DATA / ("geo" + country.lower()))}, "streets_per_locality": {"type": int, "default": 10}, **own}
    p = argparse.ArgumentParser(description=doc.splitlines()[0])
    for name in sorted(options):
        p.add_argument("--" + name.replace("_", "-"), **options[name])
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/httpmethod.tsv from the IANA HTTP Method Registry.
+"""Rebuild data/misc/httpmethod.tsv from the IANA HTTP Method Registry.

    data-import/httpmethod.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -18,7 +18,7 @@ import source
 import tsv

 SOURCE = "https://www.iana.org/assignments/http-methods/methods.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "httpmethod.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "httpmethod.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["idempotent", "method", "safe"]
 CORE = re.compile(r"\[RFC9110, Section 9\.3\.|\[RFC5789, Section 2\]")
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/httpstatus.tsv from the IANA HTTP Status Code Registry.
+"""Rebuild data/misc/httpstatus.tsv from the IANA HTTP Status Code Registry.

    data-import/httpstatus.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -14,7 +14,7 @@ import source
 import tsv

 SOURCE = "https://www.iana.org/assignments/http-status-codes/http-status-codes-1.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "httpstatus.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "httpstatus.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["code", "reason"]

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/language.tsv from datasets/language-codes (PDDL), the LoC ISO 639-2 register.
+"""Rebuild data/misc/language.tsv from datasets/language-codes (PDDL), the LoC ISO 639-2 register.

    data-import/language.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -15,7 +15,7 @@ import source
 import tsv

 SOURCE = "https://raw.githubusercontent.com/datasets/language-codes/main/data/language-codes-full.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "language.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "language.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["code", "code3", "name"]

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/loglevel.tsv from RFC 5424 and POSIX <syslog.h>.
+"""Rebuild data/misc/loglevel.tsv from RFC 5424 and POSIX <syslog.h>.

    data-import/loglevel.py [--source URL_OR_FILE] [--posix URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -18,7 +18,7 @@ import tsv

 SOURCE = "https://www.rfc-editor.org/rfc/rfc5424.txt"
 POSIX = "https://pubs.opengroup.org/onlinepubs/9799919799/basedefs/syslog.h.html"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "loglevel.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "loglevel.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["code", "keyword", "severity"]
 TABLE = re.compile(r"Table 1\.\s+Syslog Message Facilities(.*?)Table 2\.\s+Syslog Message Severities", re.S)
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/mimetype.tsv from mime-db (MIT), the IANA media type registry with extensions.
+"""Rebuild data/misc/mimetype.tsv from mime-db (MIT), the IANA media type registry with extensions.

    data-import/mimetype.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -13,7 +13,7 @@ import source
 import tsv

 SOURCE = "https://raw.githubusercontent.com/jshttp/mime-db/master/db.json"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "mimetype.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "mimetype.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["ext", "type"]
 FIXUPS = {"application/mp4": "mp4s", "audio/mpeg": "mp3", "audio/ogg": "ogg", "video/quicktime": "mov"}
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/sv_SE/sv_SE/first-name.tsv and last-name.tsv from SCB's whole-population name counts (CC0, "Källa: SCB").
+"""Rebuild data/svse/first-name.tsv and last-name.tsv from SCB's whole-population name counts (CC0, "Källa: SCB").

    data-import/names-se.py [--source URL_OR_FILE] [--first N] [--last N] [--cache DIR] [--out DIR]

@@ -14,7 +14,7 @@ import tsv
 import xlsx

 SOURCE = "https://www.scb.se/contentassets/9fe7dbb460994c72b835163dbc491ef9/namn-med-minst-tva-barare-31-december-2022.xlsx"
-OUT = Path(__file__).resolve().parent.parent / "data" / "sv_SE" / "sv_SE"
+OUT = Path(__file__).resolve().parent.parent / "data" / "svse"
 CACHE = Path(__file__).resolve().parent / "cache"
 SHEETS = {"f": "Tilltalsnamn kvinnor", "m": "Tilltalsnamn män"}
 SURNAMES = "Efternamn"
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/en_US/en_US/first-name.tsv and last-name.tsv from SSA baby names and the Census 2010 surnames (public domain).
+"""Rebuild data/enus/first-name.tsv and last-name.tsv from SSA baby names and the Census 2010 surnames (public domain).

    data-import/names-us.py [--names URL_OR_FILE] [--surnames URL_OR_FILE] [--from-year YEAR] [--first N] [--last N] [--cache DIR] [--out DIR]

@@ -20,7 +20,7 @@ import tsv

 NAMES = "https://raw.githubusercontent.com/hackerb9/ssa-baby-names/master/alldata.txt"
 SURNAMES = "https://www2.census.gov/topics/genealogy/2010surnames/names.zip"
-OUT = Path(__file__).resolve().parent.parent / "data" / "en_US" / "en_US"
+OUT = Path(__file__).resolve().parent.parent / "data" / "enus"
 CACHE = Path(__file__).resolve().parent / "cache"
 MC = re.compile(r"^Mc([a-z])")
 PLACEHOLDERS = {"Baby", "Female", "Infant", "Male", "Notnamed", "Unknown", "Unnamed"}
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/port.tsv from the IANA Service Name and Transport Protocol Port Number Registry.
+"""Rebuild data/misc/port.tsv from the IANA Service Name and Transport Protocol Port Number Registry.

    data-import/port.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -17,7 +17,7 @@ import source
 import tsv

 SOURCE = "https://www.iana.org/assignments/service-names-port-numbers/service-names-port-numbers.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "port.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "port.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["number", "service"]
 FLOOR = 4000
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/protocol.tsv from the IANA Protocol Numbers registry.
+"""Rebuild data/misc/protocol.tsv from the IANA Protocol Numbers registry.

    data-import/protocol.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -17,7 +17,7 @@ import source
 import tsv

 SOURCE = "https://www.iana.org/assignments/protocol-numbers/protocol-numbers-1.csv"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "protocol.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "protocol.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["keyword", "name", "number"]
 SKIP = ("Reserved", "deprecated")
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/territory.tsv from datasets/country-codes (PDDL).
+"""Rebuild data/misc/territory.tsv from datasets/country-codes (PDDL).

    data-import/territory.py [--source URL_OR_FILE] [--cache DIR] [--out FILE]
 """
@@ -14,7 +14,7 @@ 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" / "misc" / "territory.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "territory.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 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})$")
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/timezone.tsv from the IANA tzdb tarball (public domain) and GeoNames (CC BY 4.0).
+"""Rebuild data/misc/timezone.tsv from the IANA tzdb tarball (public domain) and GeoNames (CC BY 4.0).

    data-import/timezone.py [--source URL_OR_FILE] [--cities URL_OR_FILE] [--cache DIR] [--out FILE] [--territories FILE]

@@ -22,8 +22,8 @@ import tsv

 SOURCE = "https://data.iana.org/time-zones/tzdata-latest.tar.gz"
 CITIES = "https://download.geonames.org/export/dump/cities15000.zip"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "timezone.tsv"
-TERRITORIES = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "territory.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "timezone.tsv"
+TERRITORIES = Path(__file__).resolve().parent.parent / "data" / "misc" / "territory.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["offset", "territory", "weight", "zone"]
 REGIONS = ["africa", "antarctica", "asia", "australasia", "backward", "etcetera", "europe", "northamerica", "southamerica"]
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/tld.tsv from the IANA Root Zone Database.
+"""Rebuild data/misc/tld.tsv from the IANA Root Zone Database.

    data-import/tld.py [--source URL_OR_FILE] [--zone URL_OR_FILE] [--cache DIR] [--out FILE]

@@ -20,7 +20,7 @@ import tsv

 SOURCE = "https://www.iana.org/domains/root/db"
 ZONE = "https://data.iana.org/TLD/tlds-alpha-by-domain.txt"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "tld.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "tld.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["tld", "type", "unicode"]
 TYPES = ("country-code", "generic", "generic-restricted", "infrastructure", "sponsored")
@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""Rebuild data/misc/misc/useragent.tsv from microlinkhq/top-user-agents (MIT).
+"""Rebuild data/misc/useragent.tsv from microlinkhq/top-user-agents (MIT).

    data-import/useragent.py [--source URL] [--cache DIR] [--out FILE]

@@ -16,7 +16,7 @@ import source
 import tsv

 SOURCE = "https://raw.githubusercontent.com/microlinkhq/top-user-agents/master/src"
-OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "misc" / "useragent.tsv"
+OUT = Path(__file__).resolve().parent.parent / "data" / "misc" / "useragent.tsv"
 CACHE = Path(__file__).resolve().parent / "cache"
 COLUMNS = ["browser", "device", "os", "ua"]
 # First match wins: a Chromium fork this list does not name ships as Chrome.