Files
libpostal/resources/parser/data_sets/openaddresses.yaml
2016-08-24 14:47:07 -04:00

398 lines
14 KiB
YAML

global:
cldr_country_probability: 0.5
localized_name_probability: 0.7
iso_alpha_2_code_probability: 0.2
iso_alpha_3_code_probability: 0.1
abbreviate_street_probability: 0.3
separate_street_probability: 0.2
abbreviate_unit_probability: 0.3
separate_unit_probability: 0.2
fields: &default_fields
- field_name: NUMBER
component: house_number
- field_name: STREET
component: road
- field_name: UNIT
component: unit
- field_name: CITY
component: city
- field_name: POSTCODE
component: postcode
fields_no_postcode: &fields_no_postcode
- field_name: NUMBER
component: house_number
- field_name: STREET
component: road
- field_name: UNIT
component: unit
- field_name: CITY
component: city
fields_with_unit: &fields_with_unit
- field_name: NUMBER
component: house_number
- field_name: STREET
component: road
- field_name: UNIT
component: unit
- field_name: CITY
component: city
- field_name: POSTCODE
component: postcode
fields_with_state_and_unit: &fields_with_state_and_unit
- field_name: NUMBER
component: house_number
- field_name: STREET
component: road
- field_name: UNIT
component: unit
- field_name: CITY
component: city
- field_name: REGION
component: state
- field_name: POSTCODE
component: postcode
# Turned off by default to avoid performance penalty for reverse geocoding
add_osm_boundaries: false
add_osm_neighborhoods: false
# Units have strong restrictions, have to be a number or hyphenated number
non_numeric_units: false
# This is fine for many countries
numeric_postcodes_only: true
countries:
au:
fields: *fields_with_state_and_unit
files:
- filename: countrywide.csv
non_numeric_units: true
nz:
files:
- filename: countrywide.csv
- filename: city_of_palmerston_north.csv
be:
files:
- filename: flanders.csv
language: nl
subdirs:
wa:
files:
- filename: brussels-fr.csv
language: fr
- filename: brussels-nl.csv
language: nl
us:
cldr_country_probability: 0.05
subdirs:
ca:
add:
state: CA
files:
- filename: alameda.csv
- filename: amador.csv
- filename: berkeley.csv
- filename: butte.csv
- filename: city_of_anaheim.csv
- filename: city_of_bakersfield.csv
- filename: city_of_carson.csv
- filename: city_of_cupertino.csv
- filename: city_of_hayward.csv
- filename: city_of_mountain_view.csv
- filename: city_of_orange.csv
- filename: city_of_san_jose.csv
- filename: contra_costa.csv
- filename: el_dorado.csv
- filename: fresno.csv
- filename: glenn.csv
- filename: humboldt.csv
- filename: kern.csv
- filename: kings.csv
- filename: lake.csv
- filename: lassen.csv
- filename: los_angeles.csv
- filename: madera.csv
- filename: marin.csv
- filename: merced.csv
- filename: mono.csv
- filename: monterey.csv
- filename: napa.csv
- filename: nevada.csv
- filename: orange.csv
- filename: palo_alto.csv
- filename: placer.csv
- filename: riverside.csv
- filename: sacramento.csv
- filename: san_bernardino.csv
- filename: san_diego.csv
- filename: san_francisco.csv
- filename: san_joaquin.csv
- filename: san_luis_obispo.csv
- filename: san_mateo.csv
- filename: santa_barbara.csv
- filename: santa_clara.csv
- filename: santa_cruz.csv
- filename: shasta.csv
- filename: solano.csv
- filename: sonoma.csv
- filename: stanislaus.csv
- filename: trinity.csv
- filename: tuolumne.csv
- filename: ventura.csv
- filename: yolo.csv
- filename: yuba.csv
ct:
add:
state: CT
files:
- filename: statewide.csv
- filename: city_of_hartford.csv
add_osm_boundaries: true
add_osm_neighborhoods: true
- filename: city_of_manchester.csv
add_osm_boundaries: true
- filename: city_of_waterbury.csv
add_osm_boundaries: true
- filename: city_of_watertown.csv
add_osm_boundaries: true
- filename: town_of_avon.csv
add_osm_boundaries: true
- filename: town_of_avon.csv
add_osm_boundaries: true
- filename: town_of_easton_monroe.csv
- filename: town_of_fairfield.csv
add_osm_boundaries: true
- filename: town_of_groton.csv
add_osm_boundaries: true
de:
add:
state: DE
files:
- filename: kent.csv
- filename: new_castle.csv
ga:
add:
state: GA
# By default every county in Georgia needs OSM boundary info unless specified
add_osm_boundaries: true
# Note: files that are left out are deliberate, a lot of merged fields, decal numbers, etc.
files:
- filename: appling.csv
- filename: bacon.csv
- filename: berrien.csv
- filename: bibb.csv
- filename: bleckley.csv
- filename: brooks.csv
- filename: burke.csv
- filename: calhoun.csv
- filename: candler.csv
- filename: carroll.csv
- filename: charlton.csv
- filename: chatham.csv
fields: *fields_with_state_and_unit
- filename: city_of_johns_creek.csv
add_osm_boundaries: false
fields: *fields_with_state_and_unit
- filename: coffee.csv
- filename: colquitt.csv
- filename: dooly.csv
- filename: dougherty.csv
- filename: echols.csv
- filename: evans.csv
- filename: fulton.csv
add_osm_boundaries: false
fields: *fields_with_state_and_unit
- filename: gordon.csv
- filename: harris.csv
- filename: heard.csv
- filename: harris.csv
- filename: houston.csv
- filename: irwin.csv
- filename: jefferson.csv
- filename: johnson.csv
- filename: jones.csv
- filename: lanier.csv
- filename: laurens.csv
- filename: long.csv
- filename: mcintosh.csv
- filename: miller.csv
- filename: mitchell.csv
- filename: muscogee.csv
- filename: pierce.csv
- filename: quitman.csv
- filename: randolph.csv
- filename: stewart.csv
- filename: sumter.csv
- filename: tattnall.csv
- filename: thomas.csv
- filename: tift.csv
- filename: toombs.csv
- filename: troup.csv
- filename: turner.csv
- filename: twiggs.csv
- filename: wheeler.csv
- filename: wilkinson.csv
ma:
add:
state: MA
files:
- filename: statewide.csv
- filename: city_of_boston.csv
add_osm_boundaries: true
add_osm_neighborhoods: true
- filename: city_of_cambridge.csv
add_osm_boundaries: true
add_osm_neighborhoods: true
- filename: town_of_newton.csv
md:
add:
state: MD
files:
- filename: statewide.csv
me:
add:
state: ME
files:
- filename: statewide.csv
nh:
add:
state: NH
files:
- filename: statewide.csv
nj:
add:
state: NJ
files:
- filename: statewide.csv
add_osm_boundaries: true
ny:
add:
state: NY
files:
- filename: statewide.csv
fields: *fields_no_postcode
- filename: broome.csv
- filename: city_of_new_york.csv
add_osm_boundaries: true
add_osm_neighborhoods: true
- filename: city_of_rochester.csv
- filename: erie.csv
fields: *fields_no_postcode
pa:
add:
state: PA
files:
- filename: adams.csv
fields: *fields_with_unit
non_numeric_units: true
- filename: allegheny.csv
- filename: armstrong.csv
- filename: bedford.csv
- filename: berks.csv
- filename: butler.csv
- filename: cameron.csv
add_osm_boundaries: true
- filename: centre.csv
add_osm_boundaries: true
- filename: chester.csv
fields: *fields_with_unit
add_osm_boundaries: true
non_numeric_units: true
- filename: clearfield.csv
add_osm_boundaries: true
- filename: clinton.csv
- filename: crawford.csv
- filename: erie.csv
- filename: forest.csv
- filename: franklin.csv
- filename: fulton.csv
add_osm_boundaries: true
- filename: juniata.csv
- filename: lancaster.csv
- filename: lawrence.csv
add_osm_boundaries: true
- filename: lehigh.csv
- filename: lycoming.csv
- filename: mckean.csv
- filename: mercer.csv
- filename: monroe.csv
- filename: northampton.csv
add_osm_boundaries: true
- filename: northumberland.csv
- filename: perry.csv
- filename: philadelphia.csv
add_osm_boundaries: true
add_osm_neighborhoods: true
- filename: pike.csv
- filename: potter.csv
- filename: snyder.csv
- filename: somerset.csv
- filename: sullivan.csv
- filename: tioga.csv
- filename: union.csv
- filename: venango.csv
- filename: wayne.csv
ri:
add:
state: RI
files:
- filename: statewide.csv
sc:
add:
state: SC
files:
- filename: aiken.csv
- filename: anderson.csv
- filename: beaufort.csv
add_osm_boundaries: true
- filename: calhoun.csv
- filename: charleston.csv
- filename: city_of_charleston.csv
add_osm_neighborhoods: true
- filename: colleton.csv
- filename: darlington.csv
- filename: dorchester.csv
- filename: florence.csv
- filename: georgetown.csv
add_osm_boundaries: true
- filename: greenville.csv
- filename: greenwood.csv
add_osm_boundaries: true
- filename: hilton_head_island.csv
add_osm_boundaries: true
- filename: horry.csv
- filename: laurens.csv
- filename: saluda.csv
add_osm_boundaries: true
- filename: sumter.csv
- filename: york.csv
vt:
add:
state: VT
files:
- filename: statewide.csv