[addresses] Adding digit spellout and the list form of field combinations to existing configs

This commit is contained in:
Al
2016-07-04 13:46:19 -04:00
parent 64f167f045
commit af11db1488
20 changed files with 353 additions and 124 deletions

View File

@@ -25,35 +25,7 @@ components:
combinations:
# For unit types like 2/34 (more common in Canada and Australia)
house_number_unit:
components:
- house_number
- unit
label: house_number
separators:
- separator: "-"
probability: 0.9
- separator: " - "
probability: 0.05
- separator: /
probability: 0.05
probability: 0.005
house_number_floor:
components:
- house_number
- unit
label: house_number
separators:
- separator: "-"
probability: 0.9
- separator: " - "
probability: 0.05
- separator: /
probability: 0.05
probability: 0.005
house_number_staircase_unit:
-
components:
- house_number
- staircase
@@ -67,6 +39,33 @@ components:
- separator: /
probability: 0.05
probability: 0.005
# For unit types like 2/34 (more common in Canada and Australia)
-
components:
- house_number
- unit
label: house_number
separators:
- separator: "-"
probability: 0.9
- separator: " - "
probability: 0.05
- separator: /
probability: 0.05
probability: 0.005
-
components:
- house_number
- level
label: house_number
separators:
- separator: "-"
probability: 0.9
- separator: " - "
probability: 0.05
- separator: /
probability: 0.05
probability: 0.005
numbers:
@@ -134,6 +133,9 @@ levels:
standalone_probability: 0.2 # Let e.g. 5º be the entire floor string
# If ordinal is selected, chance of e.g. just using 2o without Andar
null_phrase_probability: 0.6
digits:
ascii_probability: 0.8
spellout_probability: 0.2
numeric_probability: 0.2
ordinal_probability: 0.8
nivel: &nivel
@@ -151,6 +153,9 @@ levels:
direction_probability: 0.95
standalone_probability: 0.2
null_phrase_probability: 0.6
digits:
ascii_probability: 0.8
spellout_probability: 0.2
numeric_probability: 0.2
ordinal_probability: 0.8
@@ -176,6 +181,9 @@ levels:
standalone_probability: 0.2 # Let e.g. 5º be the entire floor string
# If ordinal is selected, chance of e.g. just using 2o without Piso
null_phrase_probability: 0.6
digits:
ascii_probability: 0.8
spellout_probability: 0.2
numeric_probability: 0.2
numeric_affix_probability: 0.05
ordinal_probability: 0.75
@@ -204,8 +212,7 @@ levels:
terreo: &terreo
canonical: terréo
sample: true
canonical_probability: 0.3
abbreviated_probability: 0.4
canonical_probability: 0.7
sample_probability: 0.3
baixos: &baixos
canonical: baixos
@@ -241,6 +248,9 @@ levels:
canonical: sub cave
abbreviated: scv
sample: true
canonical_probability: 0.4
abbreviated_probability: 0.3
sample_probability: 0.3
# e.g. sub cave 1
numeric:
direction: left
@@ -750,6 +760,10 @@ units:
canonical: casa
numeric:
direction: left
moradia: &moradia
canonical: moradia
numeric:
direction: left
room: &sala
canonical: sala
numeric:
@@ -769,10 +783,12 @@ units:
alternatives:
- alternative: *sala
probability: 0.1
- alternative: *casa
probability: 0.05
- alternative: *porta
probability: 0.05
- alternative: *casa
probability: 0.04
- alternative: *moradia
probability: 0.01
# Separate random probability for adding directions like 2o Izq, 2 Dcha, etc.
add_direction: true
@@ -796,7 +812,9 @@ units:
- alternative: *sala
probability: 0.1
- alternative: *casa
probability: 0.03
probability: 0.02
- alternative: *moradia
probability: 0.01
- alternative: *porta
probability: 0.05
- alternative: *letra
@@ -903,7 +921,7 @@ countries:
levels:
numbering_starts_at: 1
aliases:
"0":
"0": &ground_floor_brasil
default: *andar_terreo
probability: 0.4
alternatives:
@@ -920,7 +938,7 @@ countries:
probability: 0.05
- alternative: *piso
probability: 0.01
"1": *ground_floor_brasil
postcodes:
alphanumeric:
@@ -929,8 +947,8 @@ countries:
abbreviated: cep
sample: true
canonical_probability: 0.001
abbreviated_probability: 0.995
sample_probability: 0.004
abbreviated_probability: 0.949
sample_probability: 0.05
numeric:
# Postcodes in Brazil are sometimes prefixed by CEP
@@ -945,7 +963,7 @@ countries:
numeric_affix_probability: 0.12
strict_numeric: true
po_boxes:
po_boxes: &po_boxes_caixa_postal
alphanumeric:
default:
canonical: caixa postal
@@ -982,3 +1000,55 @@ countries:
probability: 0.05
- alternative: *letra
probability: 0.05
# Angola
ao:
postcodes: &postcodes_codigo_postal
alphanumeric:
default:
canonical: código postal
abbreviated: cp
sample: true
canonical_probability: 0.001
abbreviated_probability: 0.949
sample_probability: 0.05
numeric:
direction: left
numeric_affix:
affix: cp
direction: left
# null_probability means the chance of doing nothing e.g. just the postal code
null_probability: 0.7
numeric_probability: 0.18
numeric_affix_probability: 0.12
strict_numeric: true
po_boxes: *po_boxes_caixa_postal
# Mozambique
mz:
postcodes: *postcodes_codigo_postal
po_boxes: *po_boxes_caixa_postal
# Cape Verde
cv:
po_boxes: *po_boxes_caixa_postal
# East Timor
tl:
po_boxes: *po_boxes_caixa_postal
# São Tome and Principe
st:
po_boxes: *po_boxes_caixa_postal
# Guinea-Bissau
gw:
po_boxes: *po_boxes_caixa_postal
# Macau
mo:
po_boxes: *po_boxes_caixa_postal