From d08e8d8dd3ef8289aef7ac82ae18cfa08cef1fb9 Mon Sep 17 00:00:00 2001 From: Al Date: Fri, 16 Dec 2016 06:57:05 -0500 Subject: [PATCH] [openaddresses] adding a value map for Italian province abbreviations in the countrywide file (they're commonly used in addresses and this may be a better place to handle that since the province names are given). Updating OpenAddresses config to use new dictionary field maps. --- resources/parser/data_sets/openaddresses.yaml | 208 +++++++++++++----- 1 file changed, 148 insertions(+), 60 deletions(-) diff --git a/resources/parser/data_sets/openaddresses.yaml b/resources/parser/data_sets/openaddresses.yaml index 33d07463..22fed75b 100644 --- a/resources/parser/data_sets/openaddresses.yaml +++ b/resources/parser/data_sets/openaddresses.yaml @@ -21,64 +21,43 @@ global: - "http://s3.amazonaws.com/data.openaddresses.io/runs/127209/za/ec/nelson_mandela_bay.zip" 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 + NUMBER: + component: house_number + STREET: + component: road + UNIT: + component: unit + CITY: + component: city + 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 + NUMBER: + component: house_number + STREET: + component: road + UNIT: + component: unit + CITY: + component: city fields_with_state: &fields_with_state - - field_name: NUMBER - component: house_number - - field_name: STREET - component: road - - field_name: CITY - component: city - - field_name: REGION - component: state - - field_name: POSTCODE - component: postcode + <<: *default_fields + REGION: + component: state 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 + <<: *default_fields + UNIT: + component: unit 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 + <<: *default_fields + REGION: + component: state + UNIT: + component: unit # Turned off by default to avoid performance penalty for reverse geocoding @@ -730,6 +709,122 @@ countries: it: files: - filename: countrywide.csv + fields: + <<: *default_fields + DISTRICT: + component: state_district + value_map: + "AGRIGENTO": AG + "ALESSANDRIA": AL + "ANCONA": AN + "AOSTA": AO + "AREZZO": AR + "ASCOLI PICENO": AP + "ASTI": AT + "AVELLINO": AV + "BARI": BA + "BARLETTA-ANDRIA-TRANI": BT + "BELLUNO": BL + "BENEVENTO": BN + "BERGAMO": BG + "BIELLA": BI + "BOLOGNA": BO + "BOLZANO/BOZEN": BZ + "BRESCIA": BS + "BRINDISI": BR + "CAGLIARI": CA + "CALTANISSETTA": CL + "CAMPOBASSO": CB + "CARBONIA-IGLESIAS": CI + "CASERTA": CE + "CATANIA": CT + "CATANZARO": CZ + "CHIETI": CH + "COMO": CO + "COSENZA": CS + "CREMONA": CR + "CROTONE": KR + "CUNEO": CN + "ENNA": EN + "FERMO": FM + "FERRARA": FE + "FIRENZE": FI + "FOGGIA": FG + "FORLI'-CESENA": FC + "FROSINONE": FR + "GENOVA": GE + "GORIZIA": GO + "GROSSETO": GR + "IMPERIA": IM + "ISERNIA": IS + "LA SPEZIA": SP + "L'AQUILA": AQ + "LATINA": LT + "LECCE": LE + "LECCO": LC + "LIVORNO": LI + "LODI": LO + "LUCCA": LU + "MACERATA": MC + "MANTOVA": MN + "MASSA-CARRARA": MS + "MATERA": MT + "MEDIO CAMPIDANO": VS + "MESSINA": ME + "MILANO": MI + "MODENA": MO + "MONZA E DELLA BRIANZA": MB + "NAPOLI": NA + "NOVARA": NO + "NUORO": NU + "OGLIASTRA": OG + "OLBIA-TEMPIO": OT + "ORISTANO": OR + "PADOVA": PD + "PALERMO": PA + "PARMA": PR + "PAVIA": PV + "PERUGIA": PG + "PESARO E URBINO": PU + "PESCARA": PE + "PIACENZA": PC + "PISA": PI + "PISTOIA": PT + "PORDENONE": PN + "POTENZA": PZ + "PRATO": PO + "RAGUSA": RG + "RAVENNA": RA + "REGGIO DI CALABRIA": RC + "REGGIO NELL'EMILIA": RE + "RIETI": RI + "RIMINI": RN + "ROMA": RM + "ROVIGO": RO + "SALERNO": SA + "SASSARI": SS + "SAVONA": SV + "SIENA": SI + "SIRACUSA": SR + "SONDRIO": SO + "TARANTO": TA + "TERAMO": TE + "TERNI": TR + "TORINO": TO + "TRAPANI": TP + "TRENTO": TN + "TREVISO": TV + "TRIESTE": TS + "UDINE": UD + "VARESE": VA + "VENEZIA": VE + "VERBANO-CUSIO-OSSOLA": VB + "VERCELLI": VC + "VERONA": VR + "VIBO VALENTIA": VV + "VICENZA": VI + "VITERBO": VT + subdirs: # Trentino-Alto Adige/Südtirol 32: @@ -839,16 +934,9 @@ countries: files: - filename: statewide.csv fields: - - field_name: NUMBER - component: house_number - - field_name: STREET - component: road - - field_name: UNIT - component: unit - - field_name: CITY - component: city_district - - field_name: POSTCODE - component: postcode + <<: *default_fields + CITY: + component: city_district add_osm_boundaries: true durango: