510 lines
14 KiB
YAML
510 lines
14 KiB
YAML
# pl.yaml
|
|
# -------
|
|
# Polish language specification.
|
|
|
|
components:
|
|
level:
|
|
null_probability: 0.95
|
|
alphanumeric_probability: 0.04
|
|
standalone_probability: 0.01
|
|
|
|
staircase:
|
|
null_probability: 0.99
|
|
alphanumeric_probability: 0.01
|
|
|
|
entrance:
|
|
null_probability: 0.999
|
|
alphanumeric_probability: 0.001
|
|
|
|
unit:
|
|
null_probability: 0.75
|
|
alphanumeric_probability: 0.25
|
|
|
|
combinations:
|
|
-
|
|
components:
|
|
- house_number
|
|
- unit
|
|
label: house_number
|
|
separators:
|
|
- separator: "/"
|
|
probability: 0.9
|
|
- separator: "-"
|
|
probability: 0.05
|
|
- separator: " - "
|
|
probability: 0.05
|
|
probability: 0.01
|
|
|
|
numbers:
|
|
default: &numer
|
|
canonical: numer
|
|
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:
|
|
dom: &dom
|
|
canonical: dom
|
|
abbreviated: d
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
abbreviated_probability: 0.1
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: left
|
|
alphanumeric:
|
|
default: *numer
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative: *dom
|
|
probability: 0.4
|
|
|
|
alphanumeric_phrase_probability: 0.0001
|
|
|
|
and:
|
|
default: &i
|
|
canonical: i
|
|
abbreviated: "&"
|
|
canonical_probability: 0.2
|
|
abbreviated_probability: 0.75
|
|
sample: true
|
|
sample_probability: 0.05
|
|
|
|
cross_streets:
|
|
and: *i
|
|
at: &w
|
|
canonical: w
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
corner_of: &rogu
|
|
canonical: rogu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
at_the_corner_of: &na_rogu
|
|
canonical: na rogu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
intersection:
|
|
default: *i
|
|
probability: 0.7
|
|
alternatives:
|
|
- alternative: *w
|
|
probability: 0.1
|
|
- alternative: *rogu
|
|
probability: 0.1
|
|
- alternative: *na_rogu
|
|
probability: 0.1
|
|
|
|
between:
|
|
canonical: pomiędzy
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
parentheses_probability: 0.5
|
|
|
|
levels:
|
|
floor: &pietro
|
|
canonical: piętro
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: left
|
|
direction_probability: 0.9
|
|
digits:
|
|
ascii_probability: 0.7
|
|
roman_numeral_probability: 0.3
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.3
|
|
roman_numeral_probability: 0.7
|
|
ordinal_suffix_probability: 0.6
|
|
numeric_probability: 0.4
|
|
ordinal_probability: 0.6
|
|
parter: &parter
|
|
canonical: parter
|
|
sample: true
|
|
canonical_probability: 0.9
|
|
sample_probability: 0.1
|
|
suterena: &suterena
|
|
canonical: suterena
|
|
# e.g. suterena 1
|
|
numeric:
|
|
direction: left
|
|
direction_probability: 0.8
|
|
# e.g. s1
|
|
numeric_affix:
|
|
affix: s
|
|
direction: left
|
|
# e.g. 1. suterena
|
|
ordinal:
|
|
direction: right
|
|
digits:
|
|
ascii_probability: 0.7
|
|
roman_numeral_probability: 0.3
|
|
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
|
|
aliases:
|
|
"<-1":
|
|
default: *suterena
|
|
"-1":
|
|
default: *suterena
|
|
"0":
|
|
default: *parter
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *pietro
|
|
probability: 0.1
|
|
|
|
numbering_starts_at: 0
|
|
|
|
alphanumeric:
|
|
default: *pietro
|
|
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: w pobliżu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.7
|
|
alternatives:
|
|
- alternative:
|
|
canonical: blisko
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
- alternative:
|
|
canonical: koło
|
|
sample: true
|
|
canonical_probability: 0.7
|
|
sample_probability: 0.3
|
|
probability: 0.05
|
|
- alternative:
|
|
canonical: niedaleko
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.05
|
|
- alternative:
|
|
canonical: obok
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.05
|
|
- alternative:
|
|
canonical: przy
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.05
|
|
nearby:
|
|
default:
|
|
canonical: w pobliżu
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.6
|
|
alternatives:
|
|
- alternative:
|
|
canonical: w pobliżu tutaj
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.2
|
|
- alternative:
|
|
canonical: wokół tutaj
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
- alternative:
|
|
canonical: blisko
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
probability: 0.1
|
|
near_me:
|
|
default:
|
|
canonical: w pobliżu mnie
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
|
|
# Don't worry about agreement
|
|
in:
|
|
default:
|
|
canonical: w
|
|
probability: 0.7
|
|
alternatives:
|
|
- alternative:
|
|
canonical: we
|
|
probability: 0.3
|
|
|
|
# Probabilities of each phrase
|
|
near_probability: 0.35
|
|
nearby_probability: 0.2
|
|
near_me_probability: 0.1
|
|
in_probability: 0.35
|
|
|
|
|
|
directions:
|
|
right: &prawo
|
|
canonical: prawo
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
left: &lewo
|
|
canonical: lewo
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: right
|
|
alternatives:
|
|
- alternative: *prawo
|
|
probability: 0.5
|
|
- alternative: *lewo
|
|
probability: 0.5
|
|
|
|
cardinal_directions:
|
|
east: &wschod
|
|
canonical: wschód
|
|
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
|
|
|
|
west: &zachod
|
|
canonical: zachód
|
|
abbreviated: z
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: z
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
north: &polnoc
|
|
canonical: północ
|
|
abbreviated: pn
|
|
canonical_probability: 0.95
|
|
abbreviated_probability: 0.05
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: pn
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
south: &poludnie
|
|
canonical: południe
|
|
abbreviated: pd
|
|
sample: true
|
|
canonical_probability: 0.75
|
|
abbreviated_probability: 0.1
|
|
sample_probability: 0.15
|
|
numeric:
|
|
direction: right
|
|
numeric_affix:
|
|
affix: pd
|
|
direction: right
|
|
numeric_probability: 0.5
|
|
numeric_affix_probability: 0.5
|
|
|
|
alternatives:
|
|
- alternative: *polnoc
|
|
probability: 0.25
|
|
- alternative: *wschod
|
|
probability: 0.25
|
|
- alternative: *poludnie
|
|
probability: 0.25
|
|
- alternative: *zachod
|
|
probability: 0.25
|
|
|
|
|
|
entrances:
|
|
wejscie: &wejscie
|
|
canonical: wejście
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
# Wejście 1, Wejście A, etc.
|
|
alphanumeric: &entrance_alphanumeric
|
|
default: *wejscie
|
|
numeric_probability: 0.1 # e.g. Wejście 1
|
|
alpha_probability: 0.85 # e.g. Wejście 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:
|
|
schody: &schody
|
|
canonical: schody
|
|
sample: true
|
|
canonical_probability: 0.8
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
|
|
alphanumeric: &staircase_alphanumeric
|
|
default: *schody
|
|
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: *polnoc
|
|
- alternative: *poludnie
|
|
- alternative: *wschod
|
|
- alternative: *zachod
|
|
|
|
|
|
po_boxes:
|
|
skrytka_pocztowa: &skrytka_pocztowa
|
|
canonical: skrytka pocztowa
|
|
abbreviated: skr poczt
|
|
sample: true
|
|
canonical_probability: 0.3
|
|
abbreviated_probability: 0.5
|
|
sample_probability: 0.2
|
|
numeric:
|
|
direction: left
|
|
add_number_phrase: true
|
|
add_number_phrase_probability: 0.2 # Skr Poczt 1234
|
|
alphanumeric:
|
|
default: *skrytka_pocztowa
|
|
numeric_probability: 0.9 # Skr Poczt 123
|
|
alpha_probability: 0.05 # Skr Poczt A
|
|
numeric_plus_alpha_probability: 0.04 # Skr Poczt 123G
|
|
alpha_plus_numeric_probability: 0.01 # Skr Poczt 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:
|
|
mieszkanie: &mieszkanie
|
|
canonical: mieszkanie
|
|
abbreviated: m
|
|
sample: true
|
|
canonical_probability: 0.05
|
|
abbreviated_probability: 0.9
|
|
sample_probability: 0.05
|
|
numeric:
|
|
direction: left
|
|
pokoj: &pokoj
|
|
canonical: pokój
|
|
abbreviated: pok
|
|
sample: true
|
|
canonical_probability: 0.4
|
|
abbreviated_probability: 0.5
|
|
sample_probability: 0.1
|
|
numeric:
|
|
direction: left
|
|
|
|
alphanumeric: &unit_alphanumeric
|
|
default: *mieszkanie
|
|
probability: 0.9
|
|
alternatives:
|
|
- alternative: *pokoj
|
|
probability: 0.1
|
|
numeric_probability: 0.9 # e.g. m. 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. m. A
|
|
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
|
|
# If there are 10 floors, create unit numbers like #301 or #1032
|
|
use_floor_probability: 0.01
|
|
|
|
zones:
|
|
commercial: &commercial_unit_types
|
|
default: *pokoj
|
|
numeric_probability: 0.95 # e.g. pokój 1
|
|
numeric_plus_alpha_probability: 0.01 # e.g. pokój 1A
|
|
alpha_plus_numeric_probability: 0.01 # e.g. pokój A1
|
|
alpha_probability: 0.03 # e.g. pokój A
|
|
alpha_plus_numeric:
|
|
whitespace_probability: 0.1
|
|
numeric_plus_alpha:
|
|
whitespace_probability: 0.1
|
|
university: *commercial_unit_types
|