diff --git a/app/models.py b/app/models.py index 5c579d8..5c6aa98 100644 --- a/app/models.py +++ b/app/models.py @@ -325,7 +325,7 @@ TZ Tanzania UA Ukraine | Україна | Ukraina UG Uganda UM United States Minor Outlying Islands -US United States | United States of America | USA | U.S.A. | US | U.S. +US United States | United States of America | USA | U.S.A. | US | U.S. | Americas UY Uruguay UZ Uzbekistan VA Vatican City | Holy See @@ -368,7 +368,8 @@ _REGIONS = ("europe", "emea", "eu", "european union", "eea") #: state or a Canadian province in the same part of the line beats one of #: these ("London, Ontario" is Canada); a country name does not lose to it. _CITIES: dict[str, str] = { - **dict.fromkeys(("vienna", "wien", "graz", "linz", "salzburg", "innsbruck"), "AT"), + **dict.fromkeys(("vienna", "wien", "graz", "linz", "salzburg", "innsbruck", "villach"), + "AT"), **dict.fromkeys(("brussels", "bruxelles", "antwerp", "ghent", "bruges", "brugge", "liege", "luik"), "BE"), **dict.fromkeys(("sofia",), "BG"), @@ -389,7 +390,10 @@ _CITIES: dict[str, str] = { "mannheim", "gottingen", "riederich", "rosenheim", "rostock", "bremen", "bochum", "augsburg", "potsdam", "munster", "deggendorf", "luneburg", "kassel", "braunschweig", "wurzburg", "remscheid", "osnabruck", - "oldenburg", "emmendingen", "wuppertal", "wiesbaden", "tubingen", "mainz", "lubeck"), "DE"), + "oldenburg", "emmendingen", "wuppertal", "wiesbaden", "tubingen", "mainz", "lubeck", + "bayreuth", "bad homburg", "homburg", "ettlingen", "bremerhaven", + "breidenbach", "bielefeld", "saarbrucken", "hildesheim", "moers", "kiel", + "ulm", "regensburg", "freiburg", "obersulm"), "DE"), **dict.fromkeys(("athens", "thessaloniki"), "GR"), **dict.fromkeys(("budapest",), "HU"), **dict.fromkeys(("dublin", "cork", "galway", "limerick"), "IE"), diff --git a/app/places.py b/app/places.py index 0a3e37d..f29e67e 100644 --- a/app/places.py +++ b/app/places.py @@ -134,6 +134,7 @@ _ALIAS_GROUPS: tuple[tuple[str, ...], ...] = ( ("Tübingen", "Tuebingen", "Tubingen"), ("Lübeck", "Luebeck", "Lubeck"), ("Münster", "Muenster", "Munster"), + ("Saarbrücken", "Saarbruecken", "Saarbrucken"), # Austria ("Vienna", "Wien", "Vienne"), ("Salzburg",), @@ -734,7 +735,8 @@ def seed() -> tuple[list[Seed], list[tuple[tuple[str, str], tuple[str, str]]]]: Region and Skåne, which lie in two countries). Europe is a continent over the countries of `_EUROPE`, and is also what - `EU`, `EMEA` and `European Union` name. Every country of `_COUNTRY_NAMES` + `EU`, `EMEA` and `European Union` name. Asia Pacific (`APAC`) is a continent over + nothing. Every country of `_COUNTRY_NAMES` by its names; the US states and Canadian provinces as regions; the regions of `REGIONS`; the towns of the alias groups, of the regions and of `_CITIES`, one place per group (`Copenhagen`, `København`, @@ -754,6 +756,9 @@ def seed() -> tuple[list[Seed], list[tuple[tuple[str, str], tuple[str, str]]]]: seeds[(kind, key)] = Seed(kind, key, name, parent, folds) add(*europe, "Europe", None, (fold(name) for name in ("Europe", *_REGIONS))) + # Asia Pacific holds no country: a role placed there alone keeps the + # host's country, and one beside a country is that country. + add("continent", "asia-pacific", "Asia Pacific", None, ("asia pacific", "apac")) for code, names in _COUNTRY_LABELS.items(): add("country", code, names[0], europe if code in _EUROPE else None, _COUNTRY_FOLDS[code]) for country, code, name in _subdivisions(): diff --git a/app/prep/hosts/hibob.py b/app/prep/hosts/hibob.py index 7f24d35..c0a4951 100644 --- a/app/prep/hosts/hibob.py +++ b/app/prep/hosts/hibob.py @@ -1,13 +1,14 @@ """HiBob's words, mapped to the app's.""" #: `employmentType`, the company's own name for it. "Permanent" says nothing -#: about hours and stays unmapped. +#: about hours and maps to none. EMPLOYMENT: dict[str, str] = { "regular full time": "full_time", "full time": "full_time", "full-time": "full_time", "regular part time": "part_time", "part time": "part_time", "part-time": "part_time", "contract": "contract", "contractor": "contract", "temporary": "temporary", "fixed term": "temporary", - "intern": "internship", "internship": "internship", "freelance": "freelance"} + "intern": "internship", "internship": "internship", "freelance": "freelance", + "permanent": ""} #: `workspaceTypeId`. REMOTE: dict[str, str] = {"remote": "remote", "hybrid": "hybrid", "on_site": "onsite", "onsite": "onsite"} diff --git a/app/prep/hosts/jobylon.py b/app/prep/hosts/jobylon.py index d10518d..944527b 100644 --- a/app/prep/hosts/jobylon.py +++ b/app/prep/hosts/jobylon.py @@ -2,20 +2,21 @@ #: The embed's `experience`. Only the coarse levels are mapped; "Experienced" #: sits between "Mid level" and the managerial levels and says too little to -#: place, so it stays unmapped. +#: place, so it maps to none. SENIORITY: dict[str, str] = { "student": "intern", "internship": "intern", "trainee": "intern", "entry level": "junior", "entry-level": "junior", "junior": "junior", "graduate": "junior", "mid level": "mid", "mid-level": "mid", "mid": "mid", "senior": "senior", "lead": "lead", "manager": "manager", "director": "director", - "executive": "exec", "not applicable": ""} + "executive": "exec", "not applicable": "", "experienced": ""} #: The embed's `employment_type`. EMPLOYMENT: dict[str, str] = { "full-time": "full_time", "full time": "full_time", "part-time": "part_time", "part time": "part_time", "contract": "contract", "consultant": "contract", "temporary": "temporary", "internship": "internship", "intern": "internship", - "freelance": "freelance", "summer job": "temporary", "seasonal": "temporary"} + "freelance": "freelance", "summer job": "temporary", "seasonal": "temporary", + "not applicable": ""} #: `workspace`. REMOTE: dict[str, str] = {"remote": "remote", "hybrid": "hybrid", "on-site": "onsite", "onsite": "onsite"} diff --git a/app/prep/hosts/lever.py b/app/prep/hosts/lever.py index 1195002..a2c93fa 100644 --- a/app/prep/hosts/lever.py +++ b/app/prep/hosts/lever.py @@ -1,9 +1,27 @@ """Lever's words, mapped to the app's.""" -#: `categories.commitment`. A commitment is free text on Lever ("Permanent" is -#: seen too and says nothing about hours). +#: `categories.commitment`. A commitment is free text on Lever. "Permanent", +#: a country's employee ("GE Employee") or "All work types" say nothing about +#: hours and map to none; a working student is an internship, as on Personio. EMPLOYMENT: dict[str, str] = { "full-time": "full_time", "full time": "full_time", "fulltime": "full_time", "part-time": "part_time", "part time": "part_time", "parttime": "part_time", "intern": "internship", "internship": "internship", "contract": "contract", - "contractor": "contract", "temporary": "temporary", "freelance": "freelance"} + "contractor": "contract", "temporary": "temporary", "freelance": "freelance", + "employee / full-time": "full_time", "full-time permanent": "full_time", + "full-time (long term)": "full_time", "employee, full time": "full_time", + "employee, full time (100%)": "full_time", "eor / full-time": "full_time", + "full-time, remote": "full_time", + "fixed term contract": "temporary", "fixed-term": "temporary", "fixed-terms": "temporary", + "ftc": "temporary", "temporary contract": "temporary", "short term": "temporary", + "freelancer": "freelance", "full time contractor": "contract", + "early careers internship contract": "internship", "fr intern": "internship", + "fr apprentice": "internship", "working student": "internship", + "permanent": "", "permanent employment": "", "employee - permanent": "", + "permanent contract": "", "uk permanent employee": "", "ge employee": "", + "es employee": "", "fr executive/cadre": "", + "employee, full or part time flexible (100-80%)": "", "all work types": "", + "general opportunity application": "", "hourly": "", "remote": ""} + +#: `workplaceType`. +REMOTE: dict[str, str] = {"unspecified": ""} diff --git a/app/prep/hosts/personio.py b/app/prep/hosts/personio.py index 62bb864..0eb5cdb 100644 --- a/app/prep/hosts/personio.py +++ b/app/prep/hosts/personio.py @@ -8,4 +8,5 @@ SENIORITY = {"entry-level": "junior", "student": "intern", "executive": "exec", #: (which says nothing about the hours), its `schedule`. EMPLOYMENT = {"temporary": "temporary", "freelance": "contract", "intern": "internship", "working_student": "internship", "trainee": "internship", - "permanent": "", "full-time": "full_time", "part-time": "part_time"} + "permanent": "", "full-time": "full_time", "part-time": "part_time", + "full-or-part-time": ""} diff --git a/app/prep/hosts/recruitee.py b/app/prep/hosts/recruitee.py index 0410f4b..6383cb5 100644 --- a/app/prep/hosts/recruitee.py +++ b/app/prep/hosts/recruitee.py @@ -2,8 +2,9 @@ #: `experience_code`. `experienced` names no level and is known, so it maps #: to none. -SENIORITY = {"student_school": "intern", "entry_level": "junior", "mid_level": "mid", - "experienced": ""} +SENIORITY = {"student_school": "intern", "student_college": "intern", "entry_level": "junior", + "mid_level": "mid", "experienced": "", "manager": "manager", + "senior_manager": "senior_manager", "executive": "exec"} #: The words of `employment_type_code` (`fulltime_permanent`), which is #: lowercased and split at "_" and "-"; the first entry found among its words diff --git a/app/prep/hosts/smartrecruiters.py b/app/prep/hosts/smartrecruiters.py index 0306623..45798b6 100644 --- a/app/prep/hosts/smartrecruiters.py +++ b/app/prep/hosts/smartrecruiters.py @@ -8,4 +8,5 @@ SENIORITY = {"internship": "intern", "entry_level": "junior", "director": "direc #: `typeOfEmployment.id`. EMPLOYMENT = {"permanent": "", "intern": "internship", "temporary": "temporary", - "contract": "contract", "part_time": "part_time", "full_time": "full_time"} + "contract": "contract", "part_time": "part_time", "full_time": "full_time", + "part-time": "part_time"} diff --git a/tests/test_gazetteer.py b/tests/test_gazetteer.py index 856eb7d..9b7f6da 100644 --- a/tests/test_gazetteer.py +++ b/tests/test_gazetteer.py @@ -50,7 +50,7 @@ def names(text: str) -> list[str]: def test_the_seed_holds_the_dictionaries_in_code() -> None: seeds, includes = seed() kinds = Counter(s.kind for s in seeds) - assert kinds["continent"] == 1 + assert {s.key for s in seeds if s.kind == "continent"} == {"europe", "asia-pacific"} assert kinds["country"] == sum(1 for line in _COUNTRY_NAMES.split("\n") if line) keys = {(s.kind, s.key) for s in seeds} assert {("region", key) for key in places.REGIONS} <= keys