Files
jobboard/plugins/readers/_countries.py
T
WolfandClaude Opus 5.5 3462a4abe7 Read big boards within the agents' reach: countries and remote from the enabled agents, Europe for favourites, filtered at the source by six hosts
app/jobs/reach.py derives each board's reach once per pull and the pull hands it to the runner through the batch payload. SmartRecruiters, Eightfold and SuccessFactors filter one country a request, Phenom a list, Workday and Oracle by host ids from facets. Remote beside countries is a series of its own, since two facets intersect.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-30 09:55:18 +02:00

94 lines
5.7 KiB
Python

"""Country codes and the English names hosts write, for the readers that
filter by a country's name (Eightfold, Phenom) or name a host id by it
(Workday, Oracle), and for SuccessFactors, which writes a place's country as
its code.
`NAMES` is ISO 3166-1 alpha-2 to the English short name. `code_of` reads a
name back, with the spellings hosts use that are not the short name
("United States of America", "Korea, Republic of", "Czech Republic").
"""
from __future__ import annotations
import unicodedata
#: ISO 3166-1 alpha-2 to the English name, which is what `country_of` reads:
#: a bare "DE" or "SE" in a location line is taken for Delaware or nothing.
NAMES: dict[str, str] = dict(entry.strip().split(" ", 1) for entry in """
AD Andorra | AE United Arab Emirates | AF Afghanistan | AG Antigua and Barbuda | AI
Anguilla | AL Albania | AM Armenia | AO Angola | AR Argentina | AS American Samoa | AT
Austria | AU Australia | AW Aruba | AX Åland Islands | AZ Azerbaijan | BA Bosnia and
Herzegovina | BB Barbados | BD Bangladesh | BE Belgium | BF Burkina Faso | BG Bulgaria
| BH Bahrain | BI Burundi | BJ Benin | BM Bermuda | BN Brunei | BO Bolivia | BQ
Caribbean Netherlands | BR Brazil | BS Bahamas | BT Bhutan | BW Botswana | BY Belarus
| BZ Belize | CA Canada | CD Democratic Republic of the Congo | CF Central African
Republic | CG Republic of the Congo | CH Switzerland | CI Côte d'Ivoire | CK Cook
Islands | CL Chile | CM Cameroon | CN China | CO Colombia | CR Costa Rica | CU Cuba |
CV Cabo Verde | CW Curaçao | CY Cyprus | CZ Czechia | DE Germany | DJ Djibouti | DK
Denmark | DM Dominica | DO Dominican Republic | DZ Algeria | EC Ecuador | EE Estonia |
EG Egypt | ER Eritrea | ES Spain | ET Ethiopia | FI Finland | FJ Fiji | FK Falkland
Islands | FM Micronesia | FO Faroe Islands | FR France | GA Gabon | GB United Kingdom
| GD Grenada | GE Georgia | GF French Guiana | GG Guernsey | GH Ghana | GI Gibraltar |
GL Greenland | GM Gambia | GN Guinea | GP Guadeloupe | GQ Equatorial Guinea | GR
Greece | GT Guatemala | GU Guam | GW Guinea-Bissau | GY Guyana | HK Hong Kong | HN
Honduras | HR Croatia | HT Haiti | HU Hungary | ID Indonesia | IE Ireland | IL Israel
| IM Isle of Man | IN India | IQ Iraq | IR Iran | IS Iceland | IT Italy | JE Jersey |
JM Jamaica | JO Jordan | JP Japan | KE Kenya | KG Kyrgyzstan | KH Cambodia | KI
Kiribati | KM Comoros | KN Saint Kitts and Nevis | KP North Korea | KR South Korea |
KW Kuwait | KY Cayman Islands | KZ Kazakhstan | LA Laos | LB Lebanon | LC Saint Lucia
| LI Liechtenstein | LK Sri Lanka | LR Liberia | LS Lesotho | LT Lithuania | LU
Luxembourg | LV Latvia | LY Libya | MA Morocco | MC Monaco | MD Moldova | ME
Montenegro | MG Madagascar | MH Marshall Islands | MK North Macedonia | ML Mali | MM
Myanmar | MN Mongolia | MO Macao | MP Northern Mariana Islands | MQ Martinique | MR
Mauritania | MS Montserrat | MT Malta | MU Mauritius | MV Maldives | MW Malawi | MX
Mexico | MY Malaysia | MZ Mozambique | NA Namibia | NC New Caledonia | NE Niger | NG
Nigeria | NI Nicaragua | NL Netherlands | NO Norway | NP Nepal | NR Nauru | NU Niue |
NZ New Zealand | OM Oman | PA Panama | PE Peru | PF French Polynesia | PG Papua New
Guinea | PH Philippines | PK Pakistan | PL Poland | PR Puerto Rico | PS Palestine | PT
Portugal | PW Palau | PY Paraguay | QA Qatar | RE Réunion | RO Romania | RS Serbia |
RU Russia | RW Rwanda | SA Saudi Arabia | SB Solomon Islands | SC Seychelles | SD
Sudan | SE Sweden | SG Singapore | SI Slovenia | SK Slovakia | SL Sierra Leone | SM
San Marino | SN Senegal | SO Somalia | SR Suriname | SS South Sudan | ST São Tomé and
Príncipe | SV El Salvador | SY Syria | SZ Eswatini | TC Turks and Caicos Islands | TD
Chad | TG Togo | TH Thailand | TJ Tajikistan | TL Timor-Leste | TM Turkmenistan | TN
Tunisia | TO Tonga | TR Turkey | TT Trinidad and Tobago | TV Tuvalu | TW Taiwan | TZ
Tanzania | UA Ukraine | UG Uganda | US United States | UY Uruguay | UZ Uzbekistan | VA
Vatican City | VC Saint Vincent and the Grenadines | VE Venezuela | VG British Virgin
Islands | VI U.S. Virgin Islands | VN Vietnam | VU Vanuatu | WS Samoa | XK Kosovo | YE
Yemen | ZA South Africa | ZM Zambia | ZW Zimbabwe
""".replace("\n", " ").split(" | "))
#: Other names hosts give a country: Workday's "United States of America" and
#: "Korea, Republic of", older and local spellings.
_OTHER = {
"united states of america": "US", "usa": "US", "u.s.a.": "US", "u.s.": "US",
"united kingdom of great britain and northern ireland": "GB", "great britain": "GB",
"uk": "GB", "england": "GB", "korea, republic of": "KR", "republic of korea": "KR",
"korea": "KR", "czech republic": "CZ", "turkiye": "TR", "viet nam": "VN",
"russian federation": "RU", "hong kong sar": "HK", "hong kong sar, china": "HK",
"taiwan, province of china": "TW", "macau": "MO", "the netherlands": "NL",
"holland": "NL", "slovak republic": "SK", "republic of ireland": "IE",
"ivory coast": "CI", "cote d'ivoire": "CI", "north macedonia, republic of": "MK",
"macedonia": "MK", "iran, islamic republic of": "IR", "moldova, republic of": "MD",
"tanzania, united republic of": "TZ", "united arab emirates (uae)": "AE", "uae": "AE",
}
def _fold(name: str) -> str:
decomposed = unicodedata.normalize("NFKD", name.strip().casefold())
return " ".join("".join(c for c in decomposed if not unicodedata.combining(c)).split())
_BY_NAME: dict[str, str] = {_fold(name): code for code, name in NAMES.items()} | _OTHER
def code_of(name: str) -> str:
"""The ISO code of a country written by name, '' for a name not known.
Case and accents do not matter."""
return _BY_NAME.get(_fold(name or ""), "")
def name_of(code: str) -> str:
"""The English name of an ISO code, '' for a code not known."""
return NAMES.get((code or "").strip().upper(), "")