Files
libpostal/resources/boundaries/names/global.yaml

121 lines
4.1 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

names:
keys:
default: name
probability: 0.75
alternatives:
- alternative: short_name # e.g. NYC
probability: 0.12
- alternative: alt_name # e.g. New York (instead of New York City)
probability: 0.12
- alternative: official_name # e.g. United Kingdom of Great Britain and Northern Ireland
probability: 0.01
components:
country:
keys:
default: name
probability: 0.87
alternatives:
- alternative: ISO3166-1:alpha2
probability: 0.02
- alternative: ISO3166-1:alpha3
probability: 0.01
- alternative: short_name
probability: 0.04
- alternative: alt_name
probability: 0.04
- alternative: int_name
probability: 0.01
- alternative: official_name # e.g. United Kingdom of Great Britain and Northern Ireland
probability: 0.01
regex_replacements:
- country: fr
pattern: "(?:lyon|paris|marseilles?) ([\\d]+(?:e|er|ème|eme) arrondissement)"
replace_with_group: 1
replace_probability: 0.5
prefixes:
language:
ru:
city:
default:
prefix: г.
probability: 0.35
alternatives:
- alternative:
prefix: г
probability: 0.1
- alternative:
prefix: город
probability: 0.05
# This section overrides place names
exceptions:
# Boroughs of New York City
- id: 2552485 # New York County (don't use Manhattan)
type: relation
default: name # New York County
probability: 1.0
- id: 369518 # Kings County (don't use Brooklyn)
type: relation
default: name # Kings County
probability: 1.0
- id: 369519 # Queens County (don't use Queens)
type: relation
default: name # Queens County
probability: 1.0
- id: 2552450 # Bronx County (don't use The Bronx)
type: relation
default: name # Bronx County
probability: 1.0
- id: 962876 # Richmond County (don't use Staten Island)
type: relation
default: name # Richmond County
probability: 1.0
- id: 6577227 # Kingston Parish (always use Kingston)
type: relation
default: name # Kingston
probability: 1.0
- id: 30674098 # Sao Paulo
type: node
default: name
probability: 0.9
alternatives:
- alternative: alt_name
probability: 0.09
- alternative: official_name
probability: 0.01
- id: 298285 # Sao Paulo (relation)
type: relation
default: name
probability: 0.9
alternatives:
- alternative: alt_name
probability: 0.09
- alternative: official_name
probability: 0.01
- id: 556706 # New Zealand
type: relation
default: name:en
probability: 0.77
alternatives:
- alternative: name
probability: 0.1
- alternative: ISO3166-1:alpha2
probability: 0.02
- alternative: ISO3166-1:alpha3
probability: 0.01
- alternative: short_name
probability: 0.04
- alternative: alt_name
probability: 0.04
- alternative: int_name
probability: 0.01
- alternative: official_name
probability: 0.01
- id: 2383266 # Melbourne (city center)
type: relation
default: alt_name # Melbourne
probability: 1.0