729 lines
20 KiB
YAML
729 lines
20 KiB
YAML
# de.yaml
|
|
# -------
|
|
# Note: this will only apply to the German language code, which encompasses Germany,
|
|
# Austria, Switzerland (but not Swiss-German, which has its own language code),
|
|
# Lichtenstein, Luxembourg (Luxembourgish has its own language code), and part of Belgium.
|
|
|
|
|
|
components:
|
|
level:
|
|
null_probability: 0.85
|
|
alphanumeric_probability: 0.1
|
|
standalone_probability: 0.05
|
|
|
|
staircase:
|
|
null_probability: 0.99
|
|
alphanumeric_probability: 0.01
|
|
|
|
entrance:
|
|
null_probability: 0.999
|
|
alphanumeric_probability: 0.001
|
|
|
|
unit:
|
|
null_probability: 0.9
|
|
alphanumeric_probability: 0.1
|
|
|
|
combinations:
|
|
# e.g. 2/34, more common way to specify a unit number in German
|
|
# if unit exists in the first place
|
|
-
|
|
components:
|
|
- house_number
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: /
|
|
probability: 0.8
|
|
- separator: "-"
|
|
probability: 0.1
|
|
- separator: " - "
|
|
probability: 0.1
|
|
probability: 0.05
|
|
|
|
|
|
numbers:
|
|
default: &nummer
|
|
canonical: nummer
|
|
abbreviated: nr
|
|
sample: true
|
|
# Probabilities
|
|
canonical_probability: 0.3
|
|
abbreviated_probability: 0.5
|
|
sample_probability: 0.2
|
|
sample_exclude:
|
|
- "#"
|
|
numeric:
|
|
direction: left
|
|
numeric_affix:
|
|
affix: "#"
|
|
direction: left
|
|
|
|
numeric_probability: 0.4
|
|
numeric_affix_probability: 0.6
|
|
|
|
|
|
house_numbers:
|
|
gebaude: &gebaude
|
|
canonical: gebäude
|
|
abbreviated: geb
|
|
sample: true
|
|
canonical_probability: 0.5
|
|
abbreviated_probability: 0.5
|
|
sample_probability: 0.05
|
|
numeric:
|
|
direction: left
|
|
alphanumeric:
|
|
default: *nummer
|
|
probability: 0.95
|
|
alternatives:
|
|
- alternative: *gebaude
|
|
probability: 0.05
|
|
|
|
alphanumeric_phrase_probability: 0.05
|
|
|
|
conscription_numbers:
|
|
alphanumeric:
|
|
default:
|
|
canonical: konskriptionsnummer
|
|
abbreviated: konskr. nr
|
|
canonical_probability: 0.15
|
|
abbreviated_probability: 0.65
|
|
sample: true
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
and:
|
|
default: &und
|
|
canonical: und
|
|
abbreviated: "&"
|
|
canonical_probability: 0.2
|
|
abbreviated_probability: 0.75
|
|
sample: true
|
|
sample_probability: 0.05
|
|
|
|
cross_streets:
|
|
and: *und
|
|
corner_of: &ecke_von
|
|
canonical: ecke von
|
|
at_the_corner_of: &an_der_ecke_von
|
|
canonical: an der ecke von
|
|
intersection:
|
|
default: *und
|
|
probability: 0.7
|
|
alternatives:
|
|
- alternative: *ecke_von
|
|
probability: 0.15
|
|
- alternative: *an_der_ecke_von
|
|
probability: 0.15
|
|
|
|
between:
|
|
canonical: zwischen
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
parentheses_probability: 0.5
|
|
|
|
levels:
|
|
floor: &obergeschoss
|
|
canonical: obergeschoss
|
|
abbreviated: og
|
|
sample: true
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.1
|
|
canonical_probability: 0.5
|
|
abbreviated_probability: 0.4
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: og
|
|
direction: right
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.8
|
|
spellout_probability: 0.2
|
|
numeric_probability: 0.3
|
|
numeric_affix_probability: 0.5
|
|
ordinal_probability: 0.2
|
|
etage: &etage
|
|
canonical: etage
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: right
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.8
|
|
spellout_probability: 0.2
|
|
numeric_probability: 0.4
|
|
ordinal_probability: 0.6
|
|
stock: &stock
|
|
canonical: stock
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: right
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.8
|
|
spellout_probability: 0.2
|
|
numeric_probability: 0.1
|
|
ordinal_probability: 0.9
|
|
erdgeschoss: &erdgeschoss
|
|
canonical: erdgeschoss
|
|
abbreviated: eg
|
|
sample: true
|
|
canonical_probability: 0.3
|
|
abbreviated_probability: 0.6
|
|
sample_probability: 0.1
|
|
untergeschoss: &untergeschoss
|
|
canonical: untergeschoss
|
|
abbreviated: ug
|
|
sample: true
|
|
canonical_probability: 0.4
|
|
abbreviated_probability: 0.5
|
|
sample_probability: 0.1
|
|
# e.g. Basement 1
|
|
numeric:
|
|
direction: left
|
|
# e.g. 1ug
|
|
numeric_affix:
|
|
affix: ug
|
|
direction: left
|
|
# e.g. 1. UG
|
|
ordinal:
|
|
direction: right
|
|
standalone_probability: 0.985
|
|
number_abs_value: true
|
|
number_min_abs_value: 1
|
|
numeric_probability: 0.005
|
|
numeric_affix_probability: 0.005
|
|
ordinal_probability: 0.005
|
|
unterste_etage: &unterste_etage
|
|
canonical: unterste etage
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
oberste_etage: &oberste_etage
|
|
canonical: oberste etage
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
|
|
aliases:
|
|
"<-1":
|
|
default: *untergeschoss
|
|
"-1":
|
|
default: *untergeschoss
|
|
"0":
|
|
default: *erdgeschoss
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *unterste_etage
|
|
probability: 0.1
|
|
"top":
|
|
default: *obergeschoss
|
|
probability: 0.75
|
|
alternatives:
|
|
- alternative: *stock
|
|
probability: 0.1
|
|
- alternative: *etage
|
|
probability: 0.05
|
|
- alternative: *oberste_etage
|
|
probability: 0.1
|
|
|
|
numbering_starts_at: 0
|
|
|
|
alphanumeric:
|
|
default: *obergeschoss
|
|
probability: 0.85
|
|
alternatives:
|
|
- alternative: *stock
|
|
probability: 0.1
|
|
- alternative: *etage
|
|
probability: 0.05
|
|
numeric_probability: 0.99 # With this probability, pick an integer
|
|
alpha_probability: 0.0098 # With this probability, pick a letter e.g. A
|
|
numeric_plus_alpha_probability: 0.0001 # e.g. 2A
|
|
alpha_plus_numeric_probability: 0.0001 # e.g. A2
|
|
|
|
categories:
|
|
near:
|
|
default:
|
|
canonical: nähe
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.5
|
|
alternatives:
|
|
- alternative:
|
|
canonical: bei
|
|
probability: 0.3
|
|
- alternative:
|
|
canonical: nah
|
|
probability: 0.15
|
|
- alternative:
|
|
canonical: nahe an
|
|
probability: 0.05
|
|
nearby:
|
|
default:
|
|
canonical: hier in der nähe
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.4
|
|
alternatives:
|
|
- alternative:
|
|
canonical: in der nähe
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.3
|
|
- alternative:
|
|
canonical: in der nähe hier
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
- alternative:
|
|
canonical: in der nähe von
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
- alternative:
|
|
canonical: nahe gelegen
|
|
probability: 0.05
|
|
- alternative:
|
|
canonical: hier in der gegend
|
|
probability: 0.05
|
|
|
|
near_me:
|
|
default:
|
|
canonical: in meiner nähe
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative:
|
|
canonical: in der nähe zu mir
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
# Don't worry about agreement
|
|
in:
|
|
default:
|
|
canonical: in
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative:
|
|
canonical: im
|
|
probability: 0.2
|
|
- alternative:
|
|
canonical: um
|
|
probability: 0.2
|
|
|
|
|
|
# Probabilities of each phrase
|
|
near_probability: 0.35
|
|
nearby_probability: 0.2
|
|
near_me_probability: 0.1
|
|
in_probability: 0.35
|
|
|
|
|
|
directions:
|
|
right: &rechts
|
|
canonical: rechts
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: r
|
|
direction: right
|
|
whitespace_probability: 0.1
|
|
numeric_probability: 0.8
|
|
numeric_affix_probability: 0.2
|
|
left: &links
|
|
canonical: links
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: l
|
|
direction: right
|
|
whitespace_probability: 0.1
|
|
numeric_probability: 0.4
|
|
numeric_affix_probability: 0.6
|
|
alternatives:
|
|
- alternative: *rechts
|
|
probability: 0.5
|
|
- alternative: *links
|
|
probability: 0.5
|
|
|
|
|
|
cardinal_directions:
|
|
east: &ost
|
|
canonical: ost
|
|
abbreviated: o
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: o
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
west: &west
|
|
canonical: west
|
|
abbreviated: w
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: w
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
north: &nord
|
|
canonical: nord
|
|
abbreviated: n
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: n
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
south: &sud
|
|
canonical: süd
|
|
abbreviated: s
|
|
sample: true
|
|
canonical_probability: 0.75
|
|
abbreviated_probability: 0.1
|
|
sample_probability: 0.15
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: s
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
alternatives:
|
|
- alternative: *nord
|
|
probability: 0.25
|
|
- alternative: *ost
|
|
probability: 0.25
|
|
- alternative: *sud
|
|
probability: 0.25
|
|
- alternative: *west
|
|
probability: 0.25
|
|
|
|
|
|
entrances:
|
|
eingang: &eingang
|
|
canonical: eingang
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
# Eingang 1, Eingang A, etc.
|
|
alphanumeric: &entrance_alphanumeric
|
|
default: *eingang
|
|
numeric_probability: 0.1 # e.g. Eingang 1
|
|
alpha_probability: 0.85 # e.g. Eingang A
|
|
numeric_plus_alpha_probability: 0.025 # e.g. 1A
|
|
alpha_plus_numeric_probability: 0.025 # e.g. A1
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
staircases:
|
|
stiege: &stiege
|
|
canonical: stiege
|
|
abbreviated: stg
|
|
sample: true
|
|
canonical_probability: 0.7
|
|
abbreviated_probability: 0.2
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: left
|
|
treppe: &treppe
|
|
canonical: treppe
|
|
numeric:
|
|
direction: left
|
|
|
|
alphanumeric: &staircase_alphanumeric
|
|
default: *stiege
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative: *treppe
|
|
probability: 0.4
|
|
numeric_probability: 0.75
|
|
alpha_probability: 0.2
|
|
numeric_plus_alpha_probability: 0.025
|
|
alpha_plus_numeric_probability: 0.025
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
directional:
|
|
direction: left
|
|
direction_probability: 0.85
|
|
modifier:
|
|
alternatives:
|
|
- alternative: *nord
|
|
- alternative: *sud
|
|
- alternative: *ost
|
|
- alternative: *west
|
|
|
|
po_boxes:
|
|
postfach: &postfach
|
|
canonical: postfach
|
|
abbreviated: pf
|
|
sample: true
|
|
canonical_probability: 0.6
|
|
abbreviated_probability: 0.2
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.2 # PF No 1234
|
|
numeric_probability: 1.0
|
|
alphanumeric:
|
|
sample: false
|
|
default: *postfach
|
|
numeric_probability: 0.9 # Apdo 123
|
|
alpha_probability: 0.05 # Apdo A
|
|
numeric_plus_alpha_probability: 0.04 # Apdo 123G
|
|
alpha_plus_numeric_probability: 0.01 # Apdo A123
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
digits:
|
|
- length: 1
|
|
probability: 0.05
|
|
- length: 2
|
|
probability: 0.1
|
|
- length: 3
|
|
probability: 0.2
|
|
- length: 4
|
|
probability: 0.5
|
|
- length: 5
|
|
probability: 0.1
|
|
- length: 6
|
|
probability: 0.05
|
|
|
|
units:
|
|
halle: &halle
|
|
canonical: halle
|
|
numeric:
|
|
direction: left
|
|
wohnung: &wohnung
|
|
canonical: wohnung
|
|
abbreviated: whg
|
|
sample: true
|
|
canonical_probability: 0.6
|
|
abbreviated_probability: 0.1
|
|
sample_probability: 0.3
|
|
plural:
|
|
canonical: wohnungen
|
|
numeric:
|
|
direction: left
|
|
# Wohnung nummer 4
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.2
|
|
haus: &haus
|
|
canonical: haus
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
wohnungsnummer: &wohnungsnummer
|
|
canonical: wohnungsnummer
|
|
sample: true
|
|
canonical_probability: 0.6
|
|
sample_probability: 0.4
|
|
numeric:
|
|
direction: left
|
|
appartement: &appartement
|
|
canonical: appartement
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
buro: &buro
|
|
canonical: büro
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
zimmer: &zimmer
|
|
canonical: zimmer
|
|
sample: true
|
|
canonical_probability: 0.7
|
|
sample_probability: 0.3
|
|
numeric:
|
|
direction: left
|
|
alphanumeric: &unit_alphanumeric
|
|
default: *wohnung
|
|
probability: 0.8
|
|
alternatives:
|
|
- alternative: *wohnungsnummer
|
|
probability: 0.1
|
|
- alternative: *appartement
|
|
probability: 0.05
|
|
- alternative: *haus
|
|
probability: 0.05
|
|
|
|
numeric_probability: 0.9 # e.g. Wohnung 1
|
|
numeric_plus_alpha_probability: 0.03 # e.g. 1A
|
|
alpha_plus_numeric_probability: 0.03 # e.g. A1
|
|
alpha_probability: 0.04 # e.g. Wohnung A
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
# Separate random probability for adding directions like 2R, 2L, etc.
|
|
add_direction: true
|
|
add_direction_probability: 0.1
|
|
|
|
# Add directions for plain numbers
|
|
add_direction_numeric: true
|
|
# Add direction only e.g. Wohnung Rechts
|
|
add_direction_standalone: true
|
|
|
|
# If there are 10 floors, create unit numbers like #301 or #1032
|
|
use_floor_probability: 0.1
|
|
|
|
zone:
|
|
residential: *unit_alphanumeric
|
|
commercial:
|
|
default: *buro
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *zimmer
|
|
probability: 0.1
|
|
university:
|
|
default: *halle
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *zimmer
|
|
probability: 0.1
|
|
|
|
|
|
countries:
|
|
# Austria
|
|
at:
|
|
# Staircase and entrance numbers more common
|
|
components:
|
|
level:
|
|
null_probability: 0.6
|
|
alphanumeric_probability: 0.3
|
|
standalone_probability: 0.1
|
|
staircase:
|
|
null_probability: 0.9
|
|
alphanumeric_probability: 0.1
|
|
|
|
entrance:
|
|
null_probability: 0.99
|
|
alphanumeric_probability: 0.01
|
|
|
|
unit:
|
|
null_probability: 0.4
|
|
alphanumeric_probability: 0.6
|
|
|
|
# Combined apartment numbers are very common
|
|
combinations:
|
|
# e.g. Neubaugasse 55/A/1/5
|
|
-
|
|
components:
|
|
- house_number
|
|
- entrance
|
|
- staircase
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: /
|
|
probability: 0.98
|
|
- separator: "-"
|
|
probability: 0.02
|
|
probability: 0.9
|
|
# e.g. Neubaugasse 55/1/5
|
|
-
|
|
components:
|
|
- house_number
|
|
- staircase
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: /
|
|
probability: 0.98
|
|
- separator: "-"
|
|
probability: 0.02
|
|
probability: 0.8
|
|
# e.g. Neubaugasse 55/5
|
|
-
|
|
components:
|
|
- house_number
|
|
- unit
|
|
label: house_number
|
|
probability: 0.7
|
|
separators:
|
|
- separator: /
|
|
probability: 0.98
|
|
- separator: "-"
|
|
probability: 0.02
|
|
|
|
units:
|
|
top: &top
|
|
canonical: top
|
|
numeric:
|
|
direction: left
|
|
alphanumeric: &austria_units_alphanumeric
|
|
default: *top
|
|
probability: 0.75
|
|
alternatives:
|
|
- alternative: *haus
|
|
probability: 0.15
|
|
- alternative: *wohnung
|
|
probability: 0.05
|
|
- alternative: *wohnungsnummer
|
|
probability: 0.025
|
|
- alternative: *appartement
|
|
probability: 0.025
|