Files
libpostal/resources/parser/data_sets/openaddresses.yaml

844 lines
33 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
add_osm_neighborhoods: true
subdirs:
al:
add:
state: AL
files:
- filename: baldwin.csv
add_osm_boundaries: true
- filename: calhoun.csv
add_osm_boundaries: true
- filename: city_of_huntsville.csv
- filename: montgomery.csv
- filename: shelby.csv
add_osm_boundaries: true
- filename: st_clair.csv
add_osm_boundaries: true
- filename: tuscaloosa.csv
ca:
add:
state: CA
files:
- filename: alameda.csv
- filename: amador.csv
- filename: berkeley.csv
- filename: butte.csv
- filename: city_of_anaheim.csv
add_osm_boundaries: true
- filename: city_of_bakersfield.csv
- filename: city_of_carson.csv
- filename: city_of_cupertino.csv
- filename: city_of_hayward.csv
add_osm_boundaries: true
- filename: city_of_mountain_view.csv
- filename: city_of_orange.csv
- filename: city_of_san_jose.csv
add_osm_boundaries: true
- filename: city_of_temecula.csv
- filename: contra_costa.csv
add_osm_boundaries: true
- filename: el_dorado.csv
add_osm_boundaries: true
- filename: fresno.csv
add_osm_boundaries: true
- filename: glenn.csv
add_osm_boundaries: true
- filename: humboldt.csv
- filename: kings.csv
add_osm_boundaries: true
- filename: lake.csv
add_osm_boundaries: true
- filename: lassen.csv
add_osm_boundaries: true
- filename: los_angeles.csv
- filename: madera.csv
add_osm_boundaries: true
- filename: mono.csv
- filename: monterey.csv
- filename: napa.csv
add_osm_boundaries: true
- filename: nevada.csv
- filename: palo_alto.csv
add_osm_boundaries: true
- filename: placer.csv
add_osm_boundaries: true
- filename: riverside.csv
- filename: sacramento.csv
add_osm_boundaries: true
- filename: san_bernardino.csv
- filename: san_diego.csv
- filename: san_francisco.csv
add_osm_boundaries: true
- filename: san_joaquin.csv
add_osm_boundaries: true
- filename: san_luis_obispo.csv
- filename: san_mateo.csv
add_osm_boundaries: true
- filename: santa_barbara.csv
- filename: santa_clara.csv
- filename: santa_cruz.csv
- filename: shasta.csv
- filename: solano.csv
- filename: sonoma.csv
- filename: stanislaus.csv
add_osm_boundaries: true
- filename: trinity.csv
- filename: tuolumne.csv
add_osm_boundaries: true
- filename: ventura.csv
- filename: yolo.csv
add_osm_boundaries: true
- filename: yuba.csv
ct:
add:
state: CT
files:
- filename: statewide.csv
- filename: city_of_hartford.csv
add_osm_boundaries: 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
dc:
add:
state: DC
files:
- filename: statewide.csv
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
il:
add:
state: IL
files:
- filename: alexander.csv
add_osm_boundaries: true
- filename: boone.csv
- filename: champaign.csv
- filename: city_of_aurora.csv
- filename: city_of_chicago.csv
- filename: city_of_east_peoria.csv
add_osm_boundaries: true
- filename: city_of_naperville.csv
- filename: city_of_schaumburg.csv
- filename: city_of_west_peoria.csv
- filename: coles.csv
add_osm_boundaries: true
- filename: cook.csv
- filename: cumberland.csv
add_osm_boundaries: true
- filename: douglas.csv
add_osm_boundaries: true
- filename: dupage.csv
- filename: effingham.csv
add_osm_boundaries: true
- filename: jersey.csv
add_osm_boundaries: true
- filename: kane.csv
- filename: kankakee.csv
add_osm_boundaries: true
- filename: kendall.csv
- filename: knox.csv
add_osm_boundaries: true
- filename: lake.csv
add_osm_boundaries: true
- filename: lawrence.csv
add_osm_boundaries: true
- filename: logan.csv
add_osm_boundaries: true
- filename: macon.csv
- filename: macoupin.csv
add_osm_boundaries: true
- filename: marshall.csv
add_osm_boundaries: true
- filename: massac.csv
add_osm_boundaries: true
- filename: mchenry.csv
add_osm_boundaries: true
- filename: menard.csv
add_osm_boundaries: true
- filename: morgan.csv
- filename: moultrie.csv
- filename: piatt.csv
- filename: putnam.csv
add_osm_boundaries: true
- filename: randolph.csv
add_osm_boundaries: true
- filename: schuyler.csv
add_osm_boundaries: true
- filename: shelby.csv
- filename: st_clair.csv
- filename: stephenson.csv
add_osm_boundaries: true
- filename: tazewell.csv
add_osm_boundaries: true
- filename: vermilion.csv
add_osm_boundaries: true
- filename: whiteside.csv
add_osm_boundaries: true
- filename: williamson.csv
add_osm_boundaries: true
- filename: winnebago.csv
- filename: woodford.csv
add_osm_boundaries: true
in:
add:
state: IN
files:
- filename: adams.csv
- filename: allen.csv
add_osm_boundaries: true
- filename: bartholomew.csv
- filename: benton.csv
- filename: cass.csv
- filename: city-of-hobart.csv
- filename: clark.csv
- filename: elkhart.csv
- filename: floyd.csv
- filename: grant.csv
- filename: hamilton.csv
add_osm_boundaries: true
- filename: hendricks.csv
add_osm_boundaries: true
- filename: jay.csv
- filename: laporte.csv
- filename: lawrence.csv
add_osm_boundaries: true
- filename: madison.csv
add_osm_boundaries: true
- filename: marion_county.csv
- filename: martin.csv
- filename: miami.csv
add_osm_boundaries: true
- filename: monroe.csv
add_osm_boundaries: true
- filename: morgan.csv
add_osm_boundaries: true
- filename: orange.csv
- filename: owen.csv
- filename: porter.csv
- filename: st_joseph.csv
add_osm_boundaries: true
- filename: white.csv
add_osm_boundaries: true
ky:
add:
state: KY
files:
- filename: boone.csv
add_osm_boundaries: true
- filename: city_of_paducah.csv
add_osm_boundaries: true
- filename: clark.csv
add_osm_boundaries: true
- filename: hardin.csv
add_osm_boundaries: true
- filename: jefferson.csv
- filename: lexington-fayette.csv
add_osm_boundaries: true
- filename: mccracken.csv
add_osm_boundaries: true
- filename: oldham.csv
add_osm_boundaries: true
la:
add:
state: LA
files:
- filename: ascension.csv
- filename: assumption.csv
add_osm_boundaries: true
- filename: beauregard.csv
add_osm_boundaries: true
- filename: bienville.csv
- filename: city_of_bossier.csv
add_osm_boundaries: true
- filename: city_of_denham_springs.csv
add_osm_boundaries: true
- filename: city_of_new_iberia.csv
add_osm_boundaries: true
- filename: city_of_new_orleans.csv
add_osm_boundaries: true
- filename: claiborne.csv
add_osm_boundaries: true
- filename: concordia.csv
- filename: desoto.csv
- filename: east_baton_rouge_parish.csv
- filename: iberia.csv
add_osm_boundaries: true
- filename: jefferson_parish.csv
add_osm_boundaries: true
- filename: lafayette.csv
- filename: natchitoches.csv
add_osm_boundaries: true
- filename: orleans_parish.csv
add_osm_boundaries: true
- filename: pointe_coupee.csv
- filename: red_river_parish.csv
- filename: st_charles_parish.csv
- filename: st_james.csv
- filename: st_john_the_baptist_parish.csv
- filename: st_martin.csv
add_osm_boundaries: true
- filename: terrebonne.csv
- filename: washington.csv
add_osm_boundaries: true
- filename: webster.csv
- filename: west_feliciana.csv
ma:
add:
state: MA
files:
- filename: statewide.csv
- filename: city_of_boston.csv
add_osm_boundaries: true
- filename: city_of_cambridge.csv
add_osm_boundaries: true
- filename: town_of_newton.csv
md:
add:
state: MD
files:
- filename: statewide.csv
me:
add:
state: ME
files:
- filename: statewide.csv
ms:
add:
state: MS
files:
- filename: city_of_biloxi.csv
add_osm_boundaries: true
- filename: city_of_diamondhead.csv
add_osm_boundaries: true
- filename: city_of_diberville.csv
- filename: city_of_ocean_springs.csv
- filename: city_of_pelahatchie.csv
- filename: city_of_vicksburg.csv
add_osm_boundaries: true
- filename: desoto.csv
- filename: hancock.csv
add_osm_boundaries: true
- filename: harrison.csv
add_osm_boundaries: true
- filename: hinds.csv
add_osm_boundaries: true
- filename: pontotoc.csv
add_osm_boundaries: true
- filename: simpson.csv
nc:
add:
state: NC
files:
- filename: alamance.csv
add_osm_boundaries: true
- filename: alleghany.csv
add_osm_boundaries: true
- filename: anson.csv
- filename: avery.csv
add_osm_boundaries: true
- filename: buncombe.csv
add_osm_boundaries: true
- filename: burke.csv
- filename: cabarrus.csv
- filename: camden.csv
- filename: cary.csv
add_osm_boundaries: true
- filename: caswell.csv
add_osm_boundaries: true
- filename: chatham.csv
- filename: city_of_carolina_beach.csv
add_osm_boundaries: true
- filename: city_of_elizabeth_city.csv
- filename: city_of_king.csv
- filename: city_of_salisbury.csv
- filename: cleveland.csv
add_osm_boundaries: true
- filename: columbus.csv
add_osm_boundaries: true
- filename: craven.csv
add_osm_boundaries: true
- filename: davie.csv
add_osm_boundaries: true
- filename: franklin.csv
- filename: granville.csv
- filename: guilford.csv
add_osm_boundaries: true
- filename: harnett.csv
- filename: haywood.csv
- filename: henderson.csv
add_osm_boundaries: true
- filename: iredell.csv
- filename: lee.csv
- filename: lincoln.csv
add_osm_boundaries: true
- filename: madison.csv
add_osm_boundaries: true
- filename: mecklenburg.csv
- filename: montgomery.csv
add_osm_boundaries: true
- filename: moore.csv
add_osm_boundaries: true
- filename: new_hanover.csv
add_osm_boundaries: true
- filename: onslow.csv
add_osm_boundaries: true
- filename: orange.csv
add_osm_boundaries: true
- filename: rutherford.csv
- filename: stanly.csv
add_osm_boundaries: true
- filename: surry.csv
- filename: town_of_chapel_hill.csv
add_osm_boundaries: true
- filename: union.csv
add_osm_boundaries: true
- filename: wake.csv
- filename: washington.csv
- filename: wayne.csv
- filename: wilson.csv
add_osm_boundaries: true
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:
# Note: uses New York as the city for all 5 boroughs of NYC, which
# is correct and what the OSM data uses as well. We store boroughs
# in the neighborhoods index and label them "city_district" so boroughs
# can still show up in this data set, but if it were listing city=Brooklyn
# and so forth, we'd have to stick add_osm_boundaries on statewide.csv
- filename: statewide.csv
fields: *fields_no_postcode
- filename: broome.csv
- filename: city_of_new_york.csv
add_osm_boundaries: true
- filename: city_of_rochester.csv
- filename: erie.csv
fields: *fields_no_postcode
oh:
add:
state: OH
files:
- filename: adams.csv
- filename: allen.csv
- filename: ashland.csv
- filename: ashtabula.csv
- filename: athens.csv
- filename: auglaize.csv
add_osm_boundaries: true
- filename: brown.csv
- filename: butler.csv
add_osm_boundaries: true
- filename: carroll.csv
- filename: champaign.csv
- filename: city_of_perrysburg.csv
- filename: clark.csv
- filename: clermont.csv
- filename: clinton.csv
- filename: columbiana.csv
- filename: coshocton.csv
- filename: crawford.csv
- filename: cuyahoga.csv
- filename: darke.csv
- filename: defiance.csv
- filename: delaware.csv
add_osm_boundaries: true
- filename: erie.csv
- filename: fairfield.csv
- filename: fayette.csv
- filename: franklin.csv
- filename: fulton.csv
add_osm_boundaries: true
- filename: gallia.csv
- filename: geauga.csv
add_osm_boundaries: true
- filename: greene.csv
- filename: guernsey.csv
- filename: hancock.csv
- filename: hardin.csv
- filename: harrison.csv
- filename: henry.csv
- filename: highland.csv
- filename: hocking.csv
- filename: holmes.csv
- filename: huron.csv
- filename: jackson.csv
- filename: jefferson.csv
- filename: knox.csv
- filename: lake.csv
- filename: lawrence.csv
add_osm_boundaries: true
- filename: licking.csv
- filename: logan.csv
- filename: lorain.csv
- filename: lucas.csv
- filename: madison.csv
- filename: mahoning.csv
- filename: marion.csv
- filename: medina.csv
- filename: meigs.csv
- filename: mercer.csv
- filename: miami.csv
- filename: monroe.csv
- filename: montgomery.csv
- filename: morgan.csv
- filename: morrow.csv
- filename: muskingum.csv
- filename: noble.csv
- filename: ottawa.csv
- filename: paulding.csv
- filename: perry.csv
- filename: pickaway.csv
- filename: pike.csv
- filename: portage.csv
- filename: preble.csv
- filename: putnam.csv
- filename: richland.csv
- filename: ross.csv
- filename: sandusky.csv
- filename: seneca.csv
- filename: shelby.csv
- filename: stark.csv
- filename: summit.csv
add_osm_boundaries: true
- filename: toledo.csv
- filename: trumbull.csv
- filename: tuscarawas.csv
- filename: union.csv
- filename: van_wert.csv
- filename: vinton.csv
- filename: washington.csv
- filename: wayne.csv
- filename: williams.csv
- filename: wood.csv
- filename: wyandot.csv
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
- 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
tn:
add:
state: TN
files:
- filename: blount.csv
- filename: cheatham.csv
add_osm_boundaries: true
- filename: city_of_chattanooga.csv
- filename: city_of_memphis.csv
- filename: city_of_murfreesboro.csv
add_osm_boundaries: true
- filename: city_of_nashville.csv
- filename: city_of_spring_hill.csv
- filename: franklin.csv
- filename: putnam.csv
- filename: sevier.csv
- filename: shelby.csv
- filename: statewide.csv
add_osm_boundaries: true
- filename: williamson.csv
add_osm_boundaries: true
va:
add:
state: VA
files:
- filename: statewide.csv
postcode_strip_non_digit_chars: true
vt:
add:
state: VT
files:
- filename: statewide.csv