tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[osm] abbreviate toponyms (qualifiers) with some probability so we get those versions in the model's phrase dictionaries

Browse Source
This commit is contained in:
Al
2016-08-22 20:29:29 -04:00
parent d281e71d2c
commit 8b57a7acf2
3 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/geodata/address_expansions/gazetteers.py
View File

@@ -142,7 +142,6 @@ NAME_DICTIONARIES = (GIVEN_NAME_DICTIONARY,
SURNAME_DICTIONARY,)
NAME_ABBREVIATION_DICTIONARIES = STREET_TYPES_DICTIONARIES + ('academic_degrees',
'building_types',
'company_types',
@@ -152,6 +151,8 @@ NAME_ABBREVIATION_DICTIONARIES = STREET_TYPES_DICTIONARIES + ('academic_degrees'
'toponyms',
)
QUALIFIERS_DICTIONARY = 'qualifiers'
HOUSE_NUMBER_DICTIONARIES = ('house_number', 'no_number')
POSTCODE_DICTIONARIES = ('postcode',)
@@ -184,6 +185,7 @@ def create_gazetteer(*dictionaries):
street_types_gazetteer = create_gazetteer(*STREET_TYPES_DICTIONARIES)
qualifiers_gazetteer = create_gazetteer(QUALIFIERS_DICTIONARY)
names_gazetteer = create_gazetteer(*NAME_ABBREVIATION_DICTIONARIES)
chains_gazetteer = create_gazetteer(CHAIN_DICTIONARY)
unit_types_gazetteer = create_gazetteer(*UNIT_ABBREVIATION_DICTIONARIES)