Link the obvious towns of the Unmapped list: 460 unlinked place texts down to 50

About 190 German towns (mostly 1KOMMA5°'s) and the German states, French,
Italian, Dutch, Asian and other towns, the ISO3 codes and German or French
country names boards write. Towns keep their marks through spelling groups.
The tests that used Paderborn, Jena and Überlingen as unknown towns use
Bopfingen, Lauchheim and Ellwangen instead. Left: names that are no place,
ambiguous ones (Halifax, Richmond, Victoria, Durham, Warwick) and bare codes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
WolfandClaude Opus 5.5 committed 2026-09-30 13:34:27 +02:00
1 parent 19401cfc7a
commit 3e3060ba50
6 files changed
+188 -85

No files matched your search

+125 -61
View File
@@ -135,7 +135,7 @@ CC Cocos Islands | Cocos (Keeling) Islands
CD Democratic Republic of the Congo | DR Congo | DRC | Congo-Kinshasa CD Democratic Republic of the Congo | DR Congo | DRC | Congo-Kinshasa
CF Central African Republic CF Central African Republic
CG Republic of the Congo | Congo-Brazzaville CG Republic of the Congo | Congo-Brazzaville
CH Switzerland | Schweiz | Suisse | Svizzera | Svizra CH Switzerland | Schweiz | Suisse | Svizzera | Svizra | CHE
CI Côte d'Ivoire | Ivory Coast CI Côte d'Ivoire | Ivory Coast
CK Cook Islands CK Cook Islands
CL Chile CL Chile
@@ -151,7 +151,7 @@ CY Cyprus | Κύπρος | Kypros | Kibris
CZ Czechia | Czech Republic | Česko | Česká republika CZ Czechia | Czech Republic | Česko | Česká republika
DE Germany | Deutschland | DEU | Deutschlandweit DE Germany | Deutschland | DEU | Deutschlandweit
DJ Djibouti DJ Djibouti
DK Denmark | Danmark DK Denmark | Danmark | Dänemark
DM Dominica DM Dominica
DO Dominican Republic DO Dominican Republic
DZ Algeria DZ Algeria
@@ -160,16 +160,16 @@ EE Estonia | Eesti
EG Egypt EG Egypt
EH Western Sahara EH Western Sahara
ER Eritrea ER Eritrea
ES Spain | España | Espanya ES Spain | España | Espanya | ESP | Spanien | Espagne
ET Ethiopia ET Ethiopia
FI Finland | Suomi FI Finland | Suomi
FJ Fiji FJ Fiji
FK Falkland Islands FK Falkland Islands
FM Micronesia FM Micronesia
FO Faroe Islands | Føroyar | Færøerne FO Faroe Islands | Føroyar | Færøerne
FR France FR France | FRA
GA Gabon GA Gabon
GB United Kingdom | UK | U.K. | Great Britain | Britain | England | Scotland | Wales | Northern Ireland GB United Kingdom | UK | U.K. | Great Britain | Britain | England | Scotland | Wales | Northern Ireland | GBR
GD Grenada GD Grenada
GE Georgia | Sakartvelo GE Georgia | Sakartvelo
GF French Guiana GF French Guiana
@@ -187,7 +187,7 @@ GT Guatemala
GU Guam GU Guam
GW Guinea-Bissau GW Guinea-Bissau
GY Guyana GY Guyana
HK Hong Kong HK Hong Kong | 香港
HM Heard Island and McDonald Islands HM Heard Island and McDonald Islands
HN Honduras HN Honduras
HR Croatia | Hrvatska HR Croatia | Hrvatska
@@ -206,7 +206,7 @@ IT Italy | Italia
JE Jersey JE Jersey
JM Jamaica JM Jamaica
JO Jordan JO Jordan
JP Japan JP Japan | JPN
KE Kenya KE Kenya
KG Kyrgyzstan KG Kyrgyzstan
KH Cambodia KH Cambodia
@@ -249,8 +249,8 @@ MT Malta
MU Mauritius MU Mauritius
MV Maldives MV Maldives
MW Malawi MW Malawi
MX Mexico | México MX Mexico | México | MEX
MY Malaysia MY Malaysia | MYS
MZ Mozambique MZ Mozambique
NA Namibia NA Namibia
NC New Caledonia NC New Caledonia
@@ -258,7 +258,7 @@ NE Niger
NF Norfolk Island NF Norfolk Island
NG Nigeria NG Nigeria
NI Nicaragua NI Nicaragua
NL Netherlands | The Netherlands | Nederland | Holland NL Netherlands | The Netherlands | Nederland | Holland | NLD | Niederlande
NO Norway | Norge | Noreg NO Norway | Norge | Noreg
NP Nepal NP Nepal
NR Nauru NR Nauru
@@ -285,11 +285,11 @@ RO Romania | România
RS Serbia | Srbija | Србија RS Serbia | Srbija | Србија
RU Russia | Russian Federation | Россия | Rossiya RU Russia | Russian Federation | Россия | Rossiya
RW Rwanda RW Rwanda
SA Saudi Arabia | KSA SA Saudi Arabia | KSA | SAU
SB Solomon Islands SB Solomon Islands
SC Seychelles SC Seychelles
SD Sudan SD Sudan
SE Sweden | Sverige SE Sweden | Sverige | Suède
SG Singapore SG Singapore
SH Saint Helena SH Saint Helena
SI Slovenia | Slovenija SI Slovenia | Slovenija
@@ -310,7 +310,7 @@ TC Turks and Caicos Islands
TD Chad TD Chad
TF French Southern Territories TF French Southern Territories
TG Togo TG Togo
TH Thailand TH Thailand | THA
TJ Tajikistan TJ Tajikistan
TK Tokelau TK Tokelau
TL Timor-Leste | East Timor TL Timor-Leste | East Timor
@@ -368,8 +368,8 @@ _REGIONS = ("europe", "emea", "eu", "european union", "eea")
#: state or a Canadian province in the same part of the line beats one of #: 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. #: these ("London, Ontario" is Canada); a country name does not lose to it.
_CITIES: dict[str, str] = { _CITIES: dict[str, str] = {
**dict.fromkeys(("vienna", "wien", "graz", "linz", "salzburg", "innsbruck", "villach"), **dict.fromkeys(("vienna", "wien", "graz", "linz", "salzburg", "innsbruck", "villach",
"AT"), "klagenfurt"), "AT"),
**dict.fromkeys(("brussels", "bruxelles", "antwerp", "ghent", "bruges", "brugge", "liege", **dict.fromkeys(("brussels", "bruxelles", "antwerp", "ghent", "bruges", "brugge", "liege",
"luik"), "BE"), "luik"), "BE"),
**dict.fromkeys(("sofia",), "BG"), **dict.fromkeys(("sofia",), "BG"),
@@ -378,73 +378,129 @@ _CITIES: dict[str, str] = {
**dict.fromkeys(("prague", "praha", "brno"), "CZ"), **dict.fromkeys(("prague", "praha", "brno"), "CZ"),
**dict.fromkeys(("copenhagen", "kobenhavn", "aarhus", "arhus", "odense", "aalborg", **dict.fromkeys(("copenhagen", "kobenhavn", "aarhus", "arhus", "odense", "aalborg",
"region hovedstaden", "frederiksberg", "lyngby", "kgs lyngby", "region hovedstaden", "frederiksberg", "lyngby", "kgs lyngby",
"kongens lyngby", "ballerup", "hellerup", "bagsvaerd", "horsholm", "kongens lyngby", "ballerup", "hellerup", "bagsvaerd", "horsholm", "brondby",
"brondby", "glostrup", "soborg", "malov", "birkerod"), "DK"), "glostrup", "soborg", "malov", "birkerod", "hornbaek"), "DK"),
**dict.fromkeys(("tallinn", "tartu"), "EE"), **dict.fromkeys(("tallinn", "tartu"), "EE"),
**dict.fromkeys(("helsinki", "espoo", "tampere", "vantaa"), "FI"), **dict.fromkeys(("helsinki", "espoo", "tampere", "vantaa"), "FI"),
**dict.fromkeys(("paris", "lyon", "marseille", "toulouse", "nantes", "bordeaux", **dict.fromkeys(("paris", "lyon", "marseille", "toulouse", "nantes", "bordeaux", "lille",
"lille", "rennes", "amiens"), "FR"), "rennes", "amiens", "rouen", "aix en provence", "grenoble", "annecy", "metz",
"strasbourg", "antibes", "avignon", "bourg en bresse", "brest", "caen",
"chambery", "colmar", "montpellier", "nancy", "nice", "nimes",
"saint etienne", "saint nazaire", "saint ouen l aumone", "valence", "angers",
"bayonne", "beauvais", "boulogne sur mer", "challans", "cholet",
"clermont ferrand", "dunkerque", "la roche sur yon", "la rochelle",
"lamballe", "lannion", "laval", "le havre", "le mans", "lens",
"les sables d olonne", "limoges", "lorient", "loudeac", "morlaix", "mulhouse",
"orleans", "orvault", "paimpol", "pornic", "quimper", "reims", "reze",
"saint brieuc", "saint herblain", "saint malo", "tours", "troyes", "vannes",
"vertou"), "FR"),
**dict.fromkeys(("berlin", "munich", "munchen", "hamburg", "frankfurt", "cologne", "koln", **dict.fromkeys(("berlin", "munich", "munchen", "hamburg", "frankfurt", "cologne", "koln",
"stuttgart", "dusseldorf", "leipzig", "dresden", "hannover", "nuremberg", "stuttgart", "dusseldorf", "leipzig", "dresden", "hannover", "nuremberg",
"nurnberg", "karlsruhe", "heidelberg", "bonn", "essen", "dortmund", "nurnberg", "karlsruhe", "heidelberg", "bonn", "essen", "dortmund",
"mannheim", "gottingen", "riederich", "rosenheim", "rostock", "bremen", "mannheim", "gottingen", "riederich", "rosenheim", "rostock", "bremen",
"bochum", "augsburg", "potsdam", "munster", "deggendorf", "luneburg", "bochum", "augsburg", "potsdam", "munster", "deggendorf", "luneburg",
"kassel", "braunschweig", "wurzburg", "remscheid", "osnabruck", "kassel", "braunschweig", "wurzburg", "remscheid", "osnabruck", "oldenburg",
"oldenburg", "emmendingen", "wuppertal", "wiesbaden", "tubingen", "mainz", "lubeck", "emmendingen", "wuppertal", "wiesbaden", "tubingen", "mainz", "lubeck",
"bayreuth", "bad homburg", "homburg", "ettlingen", "bremerhaven", "bayreuth", "bad homburg", "homburg", "ettlingen", "bremerhaven",
"breidenbach", "bielefeld", "saarbrucken", "hildesheim", "moers", "kiel", "breidenbach", "bielefeld", "saarbrucken", "hildesheim", "moers", "kiel",
"ulm", "regensburg", "freiburg", "obersulm", "seevetal", "ulm", "regensburg", "freiburg", "obersulm", "seevetal", "neukirchen vluyn",
"neukirchen vluyn"), "DE"), "flensburg", "ingolstadt", "kempten", "konstanz", "magdeburg", "weimar",
"chemnitz", "erfurt", "freiberg", "gustrow", "kaiserslautern", "mohnesee",
"neubrandenburg", "neumarkt", "neumunster", "paderborn", "pforzheim",
"aachen", "amberg", "annaberg buchholz", "backnang", "bad kissingen",
"bad liebenzell", "baden baden", "bamberg", "besigheim",
"bietigheim bissingen", "bocholt", "brackenheim", "bretten", "bruchsal",
"cloppenburg", "cottbus", "crailsheim", "dachau", "darmstadt",
"donaueschingen", "donauworth", "ebersberg", "eppingen", "erding", "erlangen",
"ettenheim", "feuchtwangen", "filderstadt", "florsheim", "flohrsheim",
"freising", "friedrichshafen", "fulda", "furth", "geislingen", "gera",
"germering", "goppingen", "gundelsheim", "gunzburg", "hagenow", "halle saale",
"heidenheim", "heilbronn", "herrsching", "herzogenaurach", "holzkirchen",
"holzminden", "hoxter", "idar oberstein", "jena", "kaisheim", "kierspe",
"kirchheim", "kitzingen", "koblenz", "kolbermoor", "konigsbrunn", "kunzelsau",
"landau", "landsberg", "landshut", "lauf an der pegnitz", "lindern", "lingen",
"lorrach", "ludwigsburg", "ludwigshafen", "malchow", "marburg", "meissen",
"memmingen", "meppen", "metzingen", "monchengladbach", "moosburg", "mosbach",
"muhldorf", "mulheim", "murnau", "neuburg an der donau", "neustadt",
"nordlingen", "northeim", "oberhausen", "offenburg", "ohringen", "passau",
"peine", "petershausen", "pfaffenhofen", "pfullendorf", "plau am see",
"prien am chiemsee", "rastatt", "reutlingen", "riesa", "robel", "roth",
"rothenburg ob der tauber", "rottweil", "salzgitter", "sankt georgen",
"schorndorf", "schwabisch gmund", "schwabisch hall", "schweinfurt",
"starnberg", "stockach", "tegernsee", "templin", "trier", "tuttlingen",
"uberlingen", "uedem", "vaihingen", "villingen schwenningen",
"waren an der muritz", "wasserburg", "weilheim", "wernigerode", "wismar",
"wittenberg", "wittstock", "wolfenbuttel", "wolfratshausen", "wolfsburg",
"zwickau", "euskirchen", "tangstedt", "erkrath", "sigmaringen", "grimmen",
"ribnitz damgarten", "stralsund", "warstein", "ansbach", "balingen", "coburg",
"duisburg", "grossostheim", "merzig", "saarlouis", "schwerin", "singen",
"troisdorf", "bad bevensen", "dannenberg", "luchow", "nagold", "salzwedel",
"uelzen", "boblingen", "giessen", "hagen", "hechingen", "leverkusen",
"solingen", "wetzlar"), "DE"),
**dict.fromkeys(("athens", "thessaloniki"), "GR"), **dict.fromkeys(("athens", "thessaloniki"), "GR"),
**dict.fromkeys(("budapest",), "HU"), **dict.fromkeys(("budapest", "cegled"), "HU"),
**dict.fromkeys(("dublin", "cork", "galway", "limerick"), "IE"), **dict.fromkeys(("dublin", "cork", "galway", "limerick"), "IE"),
**dict.fromkeys(("milan", "milano", "rome", "roma", "turin", "torino", "bologna", **dict.fromkeys(("milan", "milano", "rome", "roma", "turin", "torino", "bologna", "florence",
"florence", "verona", "cagliari", "ascoli piceno", "ancarano", "naples", "verona", "cagliari", "ascoli piceno", "ancarano", "naples", "napoli",
"napoli", "venice", "venezia", "genoa", "genova", "bolzano"), "IT"), "venice", "venezia", "genoa", "genova", "bolzano", "padua", "padova",
"brindisi", "matera", "pistoia", "taranto", "asti", "campobasso", "cassino",
"chieti", "civitavecchia", "cosenza", "crema", "fiumicino", "frosinone",
"grosseto", "guidonia montecelio", "l aquila", "ladispoli", "lamezia terme",
"latina", "livorno", "lucca", "massa carrara", "pescara", "pisa", "ravenna",
"rimini", "sanremo", "teramo", "terni", "trieste", "vibo valentia", "forli",
"cesena", "emilia romagna", "tuscany", "lazio"), "IT"),
**dict.fromkeys(("riga",), "LV"), **dict.fromkeys(("riga",), "LV"),
**dict.fromkeys(("vilnius", "kaunas"), "LT"), **dict.fromkeys(("vilnius", "kaunas"), "LT"),
**dict.fromkeys(("luxembourg", "luxemburg"), "LU"), **dict.fromkeys(("luxembourg", "luxemburg"), "LU"),
**dict.fromkeys(("valletta",), "MT"), **dict.fromkeys(("valletta",), "MT"),
**dict.fromkeys(("amsterdam", "rotterdam", "utrecht", "the hague", "den haag", "eindhoven", **dict.fromkeys(("amsterdam", "rotterdam", "utrecht", "the hague", "den haag", "eindhoven",
"delft"), "NL"), "delft", "amersfoort", "deventer", "maastricht", "bleiswijk", "almere",
**dict.fromkeys(("warsaw", "warszawa", "krakow", "wroclaw", "gdansk", "poznan", "lodz"), "enschede"), "NL"),
"PL"), **dict.fromkeys(("warsaw", "warszawa", "krakow", "wroclaw", "gdansk", "poznan", "lodz",
"biskupiec", "sochaczew", "teresin"), "PL"),
**dict.fromkeys(("lisbon", "lisboa", "porto", "braga"), "PT"), **dict.fromkeys(("lisbon", "lisboa", "porto", "braga"), "PT"),
**dict.fromkeys(("bucharest", "bucuresti", "cluj", "cluj napoca", "iasi", "timisoara"), "RO"), **dict.fromkeys(("bucharest", "bucuresti", "cluj", "cluj napoca", "iasi", "timisoara",
"brasov"), "RO"),
**dict.fromkeys(("belgrade", "beograd"), "RS"), **dict.fromkeys(("belgrade", "beograd"), "RS"),
**dict.fromkeys(("bratislava",), "SK"), **dict.fromkeys(("bratislava",), "SK"),
**dict.fromkeys(("ljubljana",), "SI"), **dict.fromkeys(("ljubljana",), "SI"),
**dict.fromkeys(("madrid", "barcelona", "valencia", "seville", "malaga", "bilbao", **dict.fromkeys(("madrid", "barcelona", "valencia", "seville", "malaga", "bilbao", "granada",
"granada", "santiago de compostela"), "ES"), "santiago de compostela", "pontevedra", "tarragona"), "ES"),
**dict.fromkeys(("stockholm", "gothenburg", "goteborg", "malmo", "uppsala", "vasteras", **dict.fromkeys(("stockholm", "gothenburg", "goteborg", "malmo", "uppsala", "vasteras",
"linkoping", "orebro", "norrkoping", "jonkoping"), "SE"), "linkoping", "orebro", "norrkoping", "jonkoping", "almhult", "halmstad",
"solna"), "SE"),
**dict.fromkeys(("reykjavik",), "IS"), **dict.fromkeys(("reykjavik",), "IS"),
**dict.fromkeys(("oslo", "bergen", "trondheim"), "NO"), **dict.fromkeys(("oslo", "bergen", "trondheim"), "NO"),
**dict.fromkeys(("london", "manchester", "edinburgh", "glasgow", "bristol", "cambridge uk", **dict.fromkeys(("london", "manchester", "edinburgh", "glasgow", "bristol", "cambridge uk",
"oxford", "leeds", "birmingham uk", "belfast", "leicester", "cardiff", "oxford", "leeds", "birmingham uk", "belfast", "leicester", "cardiff",
"guildford", "truro", "swansea", "blackpool", "coventry", "brighton", "guildford", "truro", "swansea", "blackpool", "coventry", "brighton",
"weybridge", "surrey", "sussex", "east anglia", "carlisle", "hinckley", "weybridge", "surrey", "sussex", "east anglia", "carlisle", "hinckley",
"slough", "southampton", "swindon", "liverpool", "redhill", "slough", "southampton", "swindon", "liverpool", "redhill", "milton keynes",
"milton keynes"), "GB"), "birmingham", "cambridge", "fermanagh", "tyrone"), "GB"),
**dict.fromkeys(("zurich", "geneva", "geneve", "basel", "lausanne", "bern", "zug", **dict.fromkeys(("zurich", "geneva", "geneve", "basel", "lausanne", "bern", "zug",
"sankt gallen", "st gallen", "lucerne", "luzern"), "CH"), "sankt gallen", "st gallen", "lucerne", "luzern", "landquart"), "CH"),
**dict.fromkeys(("kyiv", "kiev"), "UA"), **dict.fromkeys(("kyiv", "kiev"), "UA"),
**dict.fromkeys(("istanbul", "ankara"), "TR"), **dict.fromkeys(("istanbul", "ankara"), "TR"),
**dict.fromkeys(("tirana",), "AL"), **dict.fromkeys(("tirana",), "AL"),
**dict.fromkeys(("yerevan",), "AM"), **dict.fromkeys(("yerevan",), "AM"),
**dict.fromkeys(("tbilisi",), "GE"), **dict.fromkeys(("tbilisi",), "GE"),
**dict.fromkeys(("new york", "new york city", "nyc", "san francisco", "sf", "seattle", **dict.fromkeys(("new york", "new york city", "nyc", "san francisco", "sf", "seattle",
"boston", "chicago", "austin", "los angeles", "palo alto", "boston", "chicago", "austin", "los angeles", "palo alto", "mountain view",
"mountain view", "san mateo", "foster city", "sunnyvale", "san jose", "san mateo", "foster city", "sunnyvale", "san jose", "menlo park",
"menlo park", "redwood city", "costa mesa", "denver", "atlanta", "redwood city", "costa mesa", "denver", "atlanta", "washington dc",
"washington dc", "washington d c", "miami", "dallas", "houston", "washington d c", "miami", "dallas", "houston", "phoenix", "tempe",
"phoenix", "tempe", "portland", "salt lake city", "pittsburgh", "portland", "salt lake city", "pittsburgh", "philadelphia", "detroit",
"philadelphia", "detroit", "san diego", "raleigh", "nashville", "san diego", "raleigh", "nashville", "minneapolis", "cambridge ma",
"minneapolis", "cambridge ma", "bay area", "arlington"), "US"), "bay area", "arlington", "leominster", "andover", "el segundo", "columbus",
**dict.fromkeys(("toronto", "vancouver", "montreal", "ottawa", "calgary", "waterloo"), "tysons corner", "tysons", "lowell", "mclean", "morrisville", "southlake",
"CA"), "st louis", "aventura", "brooklyn", "charlotte", "corte madera",
"morgan hill", "newport beach", "las vegas", "san antonio", "tampa",
"indianapolis", "honolulu", "memphis", "glenview", "shakopee", "lexington",
"wilmington", "murrieta"), "US"),
**dict.fromkeys(("toronto", "vancouver", "montreal", "ottawa", "calgary", "waterloo",
"edmonton", "winnipeg"), "CA"),
**dict.fromkeys(("buenos aires",), "AR"), **dict.fromkeys(("buenos aires",), "AR"),
**dict.fromkeys(("sao paulo", "rio de janeiro", "sao jose dos campos"), "BR"), **dict.fromkeys(("sao paulo", "rio de janeiro", "sao jose dos campos", "curitiba"), "BR"),
**dict.fromkeys(("santiago", "santiago de chile"), "CL"), **dict.fromkeys(("santiago", "santiago de chile"), "CL"),
**dict.fromkeys(("bogota",), "CO"), **dict.fromkeys(("bogota",), "CO"),
**dict.fromkeys(("lima", "miraflores"), "PE"), **dict.fromkeys(("lima", "miraflores"), "PE"),
@@ -453,7 +509,7 @@ _CITIES: dict[str, str] = {
**dict.fromkeys(("santo domingo",), "DO"), **dict.fromkeys(("santo domingo",), "DO"),
**dict.fromkeys(("san salvador",), "SV"), **dict.fromkeys(("san salvador",), "SV"),
**dict.fromkeys(("panama city",), "PA"), **dict.fromkeys(("panama city",), "PA"),
**dict.fromkeys(("mexico city", "ciudad de mexico", "guadalajara"), "MX"), **dict.fromkeys(("mexico city", "ciudad de mexico", "guadalajara", "cdmx"), "MX"),
**dict.fromkeys(("dubai", "abu dhabi"), "AE"), **dict.fromkeys(("dubai", "abu dhabi"), "AE"),
**dict.fromkeys(("riyadh",), "SA"), **dict.fromkeys(("riyadh",), "SA"),
**dict.fromkeys(("doha",), "QA"), **dict.fromkeys(("doha",), "QA"),
@@ -463,23 +519,31 @@ _CITIES: dict[str, str] = {
**dict.fromkeys(("cairo", "maadi"), "EG"), **dict.fromkeys(("cairo", "maadi"), "EG"),
**dict.fromkeys(("casablanca",), "MA"), **dict.fromkeys(("casablanca",), "MA"),
**dict.fromkeys(("dakar",), "SN"), **dict.fromkeys(("dakar",), "SN"),
**dict.fromkeys(("tel aviv", "tel aviv yafo", "jerusalem", "haifa"), "IL"), **dict.fromkeys(("tel aviv", "tel aviv yafo", "jerusalem", "haifa", "netanya"), "IL"),
**dict.fromkeys(("almaty",), "KZ"), **dict.fromkeys(("almaty",), "KZ"),
**dict.fromkeys(("karachi", "lahore", "islamabad"), "PK"), **dict.fromkeys(("karachi", "lahore", "islamabad"), "PK"),
**dict.fromkeys(("dhaka",), "BD"), **dict.fromkeys(("dhaka",), "BD"),
**dict.fromkeys(("bengaluru", "bangalore", "hyderabad", "pune", "mumbai", "chennai", **dict.fromkeys(("bengaluru", "bangalore", "hyderabad", "pune", "mumbai", "chennai", "gurgaon",
"gurgaon", "gurugram", "noida", "new delhi", "delhi"), "IN"), "gurugram", "noida", "new delhi", "delhi", "ahmedabad"), "IN"),
**dict.fromkeys(("kuala lumpur", "bangsar south"), "MY"), **dict.fromkeys(("kuala lumpur", "bangsar south", "melaka", "malacca", "kulim", "penang",
"ipoh"), "MY"),
**dict.fromkeys(("singapore",), "SG"), **dict.fromkeys(("singapore",), "SG"),
**dict.fromkeys(("manila", "taguig"), "PH"), **dict.fromkeys(("manila", "taguig", "cavite", "general trias", "muntinlupa"), "PH"),
**dict.fromkeys(("bangkok",), "TH"), **dict.fromkeys(("bangkok", "samut prakan", "samut prakarn"), "TH"),
**dict.fromkeys(("phnom penh",), "KH"), **dict.fromkeys(("phnom penh",), "KH"),
**dict.fromkeys(("taipei",), "TW"), **dict.fromkeys(("taipei", "hsinchu", "kaohsiung", "tainan"), "TW"),
**dict.fromkeys(("tokyo", "osaka"), "JP"), **dict.fromkeys(("tokyo", "osaka", "nagoya"), "JP"),
**dict.fromkeys(("shanghai", "beijing", "shenzhen", "chengdu", "guangzhou"), "CN"), **dict.fromkeys(("shanghai", "beijing", "shenzhen", "chengdu", "guangzhou", "wuxi", "xi an",
**dict.fromkeys(("seoul",), "KR"), "qingdao", "chongqing", "nanjing", "tianjin", "wuhan", "xiamen"), "CN"),
**dict.fromkeys(("sydney", "melbourne", "brisbane", "perth", "new south wales", **dict.fromkeys(("seoul", "seongnam", "busan", "daegu", "daejeon", "gwangju"), "KR"),
"queensland"), "AU"), **dict.fromkeys(("sydney", "melbourne", "brisbane", "perth", "new south wales", "queensland",
"canberra"), "AU"),
**dict.fromkeys(("jakarta", "batam"), "ID"),
**dict.fromkeys(("hanoi", "ho chi minh"), "VN"),
**dict.fromkeys(("tunis",), "TN"),
**dict.fromkeys(("ebene",), "MU"),
**dict.fromkeys(("cape town", "johannesburg"), "ZA"),
**dict.fromkeys(("auckland",), "NZ"),
} }
#: US states and Canadian provinces, by name and by the code boards write #: US states and Canadian provinces, by name and by the code boards write
@@ -592,7 +656,7 @@ def country_of(place: str) -> str:
A state code that is also a country's ("DE", "CO", "MA"), and "Georgia", A state code that is also a country's ("DE", "CO", "MA"), and "Georgia",
count as the state only when the line names a place in the US too: count as the state only when the line names a place in the US too:
"Berlin, DE" is DE, "Bogota, CO" is CO, "Paderborn, DE" is '' rather "Berlin, DE" is DE, "Bogota, CO" is CO, "Ellwangen, DE" is '' rather
than Delaware. A country code in parentheses, "Leicester (GB)", is read than Delaware. A country code in parentheses, "Leicester (GB)", is read
only when no name matched.""" only when no name matched."""
segments = [(text, _hits(_place_fold(text))) for text in _SEGMENT.split(place or "")] segments = [(text, _hits(_place_fold(text))) for text in _SEGMENT.split(place or "")]
+43 -5
View File
@@ -179,6 +179,27 @@ _ALIAS_GROUPS: tuple[tuple[str, ...], ...] = (
("Timișoara", "Timisoara"), ("Timișoara", "Timisoara"),
("Marseille", "Marseilles"), ("Marseille", "Marseilles"),
("Bolzano", "Bozen"), ("Bolzano", "Bozen"),
("Padua", "Padova"),
("Forlì",),
("L'Aquila",),
("Massa-Carrara", "Massa Carrara"),
# France, with the marks and hyphens a fold drops
("Aix-en-Provence",), ("Bourg-en-Bresse",), ("Boulogne-sur-Mer",), ("Chambéry",),
("Clermont-Ferrand",), ("La Roche-sur-Yon",), ("Les Sables-d'Olonne",), ("Loudéac",),
("Nîmes",), ("Orléans",), ("Rezé",), ("Saint-Brieuc",), ("Saint-Étienne",),
("Saint-Herblain",), ("Saint-Malo",), ("Saint-Nazaire",), ("Saint-Ouen-l'Aumône",),
# Germany, likewise
("Annaberg-Buchholz",), ("Baden-Baden",), ("Bietigheim-Bissingen",), ("Böblingen",),
("Donauwörth",), ("Flörsheim", "Flohrsheim"), ("Fürth",), ("Gießen", "Giessen"),
("Göppingen",), ("Großostheim",), ("Günzburg",), ("Güstrow",), ("Halle (Saale)",),
("Höxter",), ("Idar-Oberstein",), ("Königsbrunn",), ("Künzelsau",), ("Lörrach",),
("Lüchow",), ("Meißen", "Meissen"), ("Möhnesee",), ("Mönchengladbach",), ("Mühldorf",),
("Mülheim",), ("Neumünster",), ("Nördlingen",), ("Öhringen",), ("Ribnitz-Damgarten",),
("Röbel",), ("Schwäbisch Gmünd",), ("Schwäbisch Hall",), ("Überlingen",),
("Villingen-Schwenningen",), ("Waren an der Müritz",), ("Wolfenbüttel",),
# Elsewhere
("Cegléd",), ("Brașov", "Brasov"), ("Älmhult",), ("Hornbæk",), ("Melaka", "Malacca"),
("Samut Prakan", "Samut Prakarn"), ("Xi'an",), ("Ho Chi Minh City", "Ho Chi Minh"),
) )
@@ -305,13 +326,30 @@ _ORESUND = Region(
_split("Øresund, Öresund, Oresund, Oresund Region, Øresundsregionen, Öresundsregionen"), _split("Øresund, Öresund, Oresund, Oresund Region, Øresundsregionen, Öresundsregionen"),
(), includes=("hovedstaden", "skane")) (), includes=("hovedstaden", "skane"))
# Germany's by the names boards write for a remote role's area, towns not # Germany's states and the areas boards write for a remote role's area, by
# listed: a town in Germany is found through the country. # name, towns not listed: a town in Germany is found through the country.
_GERMANY = tuple(Region(key, label, _split(names), (), "DE") for key, label, names in ( _GERMANY = tuple(Region(key, label, _split(names), (), "DE") for key, label, names in (
("niedersachsen", "Niedersachsen", "Niedersachsen, Lower Saxony"), ("niedersachsen", "Niedersachsen", "Niedersachsen, Lower Saxony"),
("norddeutschland", "Norddeutschland", "Norddeutschland, Northern Germany"), ("norddeutschland", "Norddeutschland", "Norddeutschland, Northern Germany"),
("ostdeutschland", "Ostdeutschland", "Ostdeutschland, Eastern Germany"), ("ostdeutschland", "Ostdeutschland", "Ostdeutschland, Eastern Germany"),
("suddeutschland", "Süddeutschland", "Süddeutschland, Southern Germany"))) ("suddeutschland", "Süddeutschland", "Süddeutschland, Southern Germany"),
("baden-wurttemberg", "Baden-Württemberg", "Baden-Württemberg"),
("bayern", "Bayern", "Bayern, Bavaria"),
("brandenburg", "Brandenburg", "Brandenburg"),
("hessen", "Hessen", "Hessen, Hesse"),
("mecklenburg-vorpommern", "Mecklenburg-Vorpommern",
"Mecklenburg-Vorpommern, Mecklenburg-Western Pomerania"),
("nordrhein-westfalen", "Nordrhein-Westfalen", "Nordrhein-Westfalen, North Rhine-Westphalia, NRW"),
("rheinland-pfalz", "Rheinland-Pfalz", "Rheinland-Pfalz, Rhineland-Palatinate"),
("saarland", "Saarland", "Saarland"),
("sachsen", "Sachsen", "Sachsen, Saxony"),
("sachsen-anhalt", "Sachsen-Anhalt", "Sachsen-Anhalt, Saxony-Anhalt"),
("schleswig-holstein", "Schleswig-Holstein", "Schleswig-Holstein"),
("thuringen", "Thüringen", "Thüringen, Thuringia"),
("bodensee", "Bodensee", "Bodensee, Lake Constance"),
("harz", "Harz", "Harz"),
("rugen", "Rügen", "Rügen"),
("uckermark", "Uckermark", "Uckermark")))
REGIONS: dict[str, Region] = { REGIONS: dict[str, Region] = {
r.key: r for r in (_SKANE, _HOVEDSTADEN, _ZEALAND, _ORESUND, _JUTLAND, _FUNEN, *_GERMANY)} r.key: r for r in (_SKANE, _HOVEDSTADEN, _ZEALAND, _ORESUND, _JUTLAND, _FUNEN, *_GERMANY)}
@@ -694,7 +732,7 @@ KINDS: tuple[str, ...] = ("continent", "country", "region", "city")
#: Entries of `_CITIES` that name a region rather than a town. #: Entries of `_CITIES` that name a region rather than a town.
_CITY_REGIONS = frozenset(("new south wales", "queensland", "surrey", "sussex", "east anglia", _CITY_REGIONS = frozenset(("new south wales", "queensland", "surrey", "sussex", "east anglia",
"bay area")) "bay area", "emilia romagna", "tuscany", "lazio"))
#: Words a place text holds when it names how or where-ever a role is worked #: Words a place text holds when it names how or where-ever a role is worked
#: rather than a place: "Remote", "Multiple Locations", "Home based". A text #: rather than a place: "Remote", "Multiple Locations", "Home based". A text
@@ -922,7 +960,7 @@ class Gazetteer:
def resolve(self, text: str) -> tuple[int, ...]: def resolve(self, text: str) -> tuple[int, ...]:
"""The places one place text names, most specific first from the left: """The places one place text names, most specific first from the left:
`Aarhus N, Region Central Jutland, Denmark` is Aarhus, `Malmö/Lund` `Aarhus N, Region Central Jutland, Denmark` is Aarhus, `Malmö/Lund`
is Malmö and Lund, `Paderborn, Germany` is Germany, `Remote` is none. is Malmö and Lund, `Ellwangen, Germany` is Germany, `Remote` is none.
Every alias the text holds as whole words is a candidate, longest Every alias the text holds as whole words is a candidate, longest
first. A fold that names several places is the one in the country first. A fold that names several places is the one in the country
+10 -10
View File
@@ -83,7 +83,7 @@ def test_copenhagen_is_in_the_capital_region_in_denmark_in_europe() -> None:
("Copenhagen Office", ["Copenhagen"]), ("Copenhagen Office", ["Copenhagen"]),
("Malmö/Lund", ["Malmö", "Lund"]), ("Malmö/Lund", ["Malmö", "Lund"]),
("Aalborg, Copenhagen, Kolding", ["Aalborg", "Copenhagen", "Kolding"]), ("Aalborg, Copenhagen, Kolding", ["Aalborg", "Copenhagen", "Kolding"]),
("Paderborn, Germany", ["Germany"]), ("Bopfingen, Germany", ["Germany"]),
("Skåne län, Sweden", ["Skåne"]), ("Skåne län, Sweden", ["Skåne"]),
("London, Ontario", ["Ontario"]), ("London, Ontario", ["Ontario"]),
("Bergen op Zoom, Netherlands", ["Netherlands"]), ("Bergen op Zoom, Netherlands", ["Netherlands"]),
@@ -117,7 +117,7 @@ def test_a_text_of_how_a_role_is_worked_is_no_place(text: str) -> None:
assert places.placeless(text) assert places.placeless(text)
@pytest.mark.parametrize("text", ["Oberkochen", "Remote, APAC", "Jena"]) @pytest.mark.parametrize("text", ["Oberkochen", "Remote, APAC", "Lauchheim"])
def test_a_text_with_a_name_is_a_place(text: str) -> None: def test_a_text_with_a_name_is_a_place(text: str) -> None:
assert not places.placeless(text) assert not places.placeless(text)
@@ -235,7 +235,7 @@ def uids(store: Store, *tokens: str) -> set[str]:
def several(store: Store) -> dict[str, str]: def several(store: Store) -> dict[str, str]:
lines = {"cph": "Copenhagen; London", "eu": "Berlin, Germany; Paris, France", lines = {"cph": "Copenhagen; London", "eu": "Berlin, Germany; Paris, France",
"malmo": "Malmö", "lund": "Lund, Skåne", "billund": "Billund", "malmo": "Malmö", "lund": "Lund, Skåne", "billund": "Billund",
"zeiss": "Oberkochen; Jena", "remote": "Remote (SE)", "ny": "New York, NY"} "zeiss": "Oberkochen; Lauchheim", "remote": "Remote (SE)", "ny": "New York, NY"}
for key, line in lines.items(): for key, line in lines.items():
upsert(store, posting(key, place=line)) upsert(store, posting(key, place=line))
return {key: posting(key).uid for key in lines} return {key: posting(key).uid for key in lines}
@@ -312,10 +312,10 @@ def test_a_place_gate_matches_over_the_gazetteer(store: Store,
# ------------------------------------------------------------ unresolved texts # ------------------------------------------------------------ unresolved texts
def test_unresolved_texts_are_listed_most_roles_first(store: Store) -> None: def test_unresolved_texts_are_listed_most_roles_first(store: Store) -> None:
for n, line in enumerate(("Oberkochen; Jena", "Oberkochen", "Remote", "Aalen; Berlin")): for n, line in enumerate(("Oberkochen; Lauchheim", "Oberkochen", "Remote", "Aalen; Berlin")):
upsert(store, posting(str(n), place=line)) upsert(store, posting(str(n), place=line))
assert store.unresolved_places() == [("oberkochen", "Oberkochen", 2), ("aalen", "Aalen", 1), assert store.unresolved_places() == [("oberkochen", "Oberkochen", 2), ("aalen", "Aalen", 1),
("jena", "Jena", 1)] ("lauchheim", "Lauchheim", 1)]
assert store.unresolved_places(limit=1) == [("oberkochen", "Oberkochen", 2)] assert store.unresolved_places(limit=1) == [("oberkochen", "Oberkochen", 2)]
@@ -344,12 +344,12 @@ def test_an_alias_links_what_it_names(store: Store) -> None:
def test_a_place_added_by_hand_is_resolved_and_found(store: Store) -> None: def test_a_place_added_by_hand_is_resolved_and_found(store: Store) -> None:
upsert(store, posting("1", place="Oberkochen; Jena")) upsert(store, posting("1", place="Oberkochen; Lauchheim"))
upsert(store, posting("2", place="Paderborn, Germany")) upsert(store, posting("2", place="Bopfingen, Germany"))
oberkochen = store.add_place("Oberkochen", "city", "country:DE") oberkochen = store.add_place("Oberkochen", "city", "country:DE")
store.add_place("Paderborn", "city", "country:DE") store.add_place("Bopfingen", "city", "country:DE")
assert texts(store, posting("1").uid) == [(0, "Oberkochen", "Oberkochen"), (1, "Jena", "")] assert texts(store, posting("1").uid) == [(0, "Oberkochen", "Oberkochen"), (1, "Lauchheim", "")]
assert texts(store, posting("2").uid) == [(0, "Paderborn, Germany", "Paderborn")] assert texts(store, posting("2").uid) == [(0, "Bopfingen, Germany", "Bopfingen")]
assert uids(store, "place:oberkochen") == {posting("1").uid} assert uids(store, "place:oberkochen") == {posting("1").uid}
assert store.gazetteer().country(oberkochen) == "DE" assert store.gazetteer().country(oberkochen) == "DE"
with pytest.raises(ValueError): with pytest.raises(ValueError):
+2 -1
View File
@@ -351,7 +351,8 @@ def test_null_columns_match_nothing_and_do_not_raise() -> None:
def test_every_region_has_names_and_towns() -> None: def test_every_region_has_names_and_towns() -> None:
germany = {"niedersachsen", "norddeutschland", "ostdeutschland", "suddeutschland"} germany = {r.key for r in places._GERMANY}
assert {"niedersachsen", "bayern", "thuringen", "harz"} <= germany
assert set(REGIONS) == {"skane", "hovedstaden", "zealand", "oresund", "jutland", assert set(REGIONS) == {"skane", "hovedstaden", "zealand", "oresund", "jutland",
"funen"} | germany "funen"} | germany
for key, region in REGIONS.items(): for key, region in REGIONS.items():
+7 -7
View File
@@ -275,12 +275,12 @@ def test_a_changed_table_maps_every_open_role_again_without_a_pull(store: Store)
def test_a_town_added_to_the_code_is_linked_at_the_next_prep( def test_a_town_added_to_the_code_is_linked_at_the_next_prep(
store: Store, monkeypatch: pytest.MonkeyPatch) -> None: store: Store, monkeypatch: pytest.MonkeyPatch) -> None:
store.upsert_role(item("1", places=[{"text": "Überlingen", "remote": None}])) store.upsert_role(item("1", places=[{"text": "Ellwangen", "remote": None}]))
prep.run(store, tables=TABLES) prep.run(store, tables=TABLES)
assert [p["text"] for p in store.unlinked_places()] == ["Überlingen"] assert [p["text"] for p in store.unlinked_places()] == ["Ellwangen"]
assert row(store, "1")["country"] == "" assert row(store, "1")["country"] == ""
monkeypatch.setitem(models._CITIES, "uberlingen", "DE") monkeypatch.setitem(models._CITIES, "ellwangen", "DE")
done = prep.run(store, tables=TABLES) done = prep.run(store, tables=TABLES)
assert done.remapped assert done.remapped
assert store.unlinked_places() == [] assert store.unlinked_places() == []
@@ -340,9 +340,9 @@ def test_app_prep_runs_and_lists_the_unmapped_words(
assert json.loads(capsys.readouterr().out)["read"] == 1 assert json.loads(capsys.readouterr().out)["read"] == 1
assert cli.main(["-c", str(path), "prep", "unmapped"]) == 0 assert cli.main(["-c", str(path), "prep", "unmapped"]) == 0
assert capsys.readouterr().out.split() == ["seniority", "acme", "1", "grand", "poobah"] assert capsys.readouterr().out.split() == ["seniority", "acme", "1", "grand", "poobah"]
Store(tmp_path / "roledesk.db").upsert_role(item("2", place="Überlingen")) Store(tmp_path / "roledesk.db").upsert_role(item("2", place="Ellwangen"))
assert cli.main(["-c", str(path), "prep", "unlinked"]) == 0 assert cli.main(["-c", str(path), "prep", "unlinked"]) == 0
assert capsys.readouterr().out.split() == ["1", "Überlingen", "-:1", "Acme"] assert capsys.readouterr().out.split() == ["1", "Ellwangen", "-:1", "Acme"]
assert cli.main(["-c", str(path), "prep", "--remap"]) == 0 assert cli.main(["-c", str(path), "prep", "--remap"]) == 0
assert json.loads(capsys.readouterr().out)["remapped"] is True assert json.loads(capsys.readouterr().out)["remapped"] is True
@@ -371,11 +371,11 @@ def test_the_api_lists_the_unlinked_places(tmp_path: Path) -> None:
app = create_app(Config(server=ServerConfig(host="127.0.0.1", port=0), app = create_app(Config(server=ServerConfig(host="127.0.0.1", port=0),
database=tmp_path / "roledesk.db")) database=tmp_path / "roledesk.db"))
app.state.store.upsert_role(item("1", place="Überlingen", country="DE")) app.state.store.upsert_role(item("1", place="Ellwangen", country="DE"))
prep.run(app.state.store, tables=TABLES) prep.run(app.state.store, tables=TABLES)
with TestClient(app) as client: with TestClient(app) as client:
found = client.get("/api/prep/unlinked").json() found = client.get("/api/prep/unlinked").json()
assert found == [{"fold": "uberlingen", "text": "Überlingen", "roles": 1, assert found == [{"fold": "ellwangen", "text": "Ellwangen", "roles": 1,
"countries": [["DE", 1]], "companies": ["Acme"]}] "countries": [["DE", 1]], "companies": ["Acme"]}]
+1 -1
View File
@@ -60,7 +60,7 @@ def store(tmp_path: Path) -> Store:
("Wrocław", "PL"), # ł and đ do not decompose under NFKD ("Wrocław", "PL"), # ł and đ do not decompose under NFKD
("Łódź, Poland", "PL"), ("Łódź, Poland", "PL"),
("Bogota, CO", "CO"), # a state code that is a country's too ("Bogota, CO", "CO"), # a state code that is a country's too
("Paderborn, DE", ""), # ... is no US state without a US place ("Ellwangen, DE", ""), # ... is no US state without a US place
("Sliema, MT", ""), ("Sliema, MT", ""),
("Casablanca, MA", "MA"), ("Casablanca, MA", "MA"),
("Cambridge, MA", "US"), ("Cambridge, MA", "US"),