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

[openaddresses] fixing house numbers with multiple consecutive hyphens

Browse Source
This commit is contained in:
Al
2016-12-06 22:50:14 -05:00
parent ae527ef5b1
commit 3ff472c8cf
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/geodata/openaddresses/formatter.py
View File

@@ -54,6 +54,8 @@ class OpenAddressesFormatter(object):
AddressFormatter.HOUSE_NUMBER: [ AddressFormatter.HOUSE_NUMBER: [
# Most of the house numbers in Montreal start with "#" # Most of the house numbers in Montreal start with "#"
(re.compile('^#', re.UNICODE), six.u('')), (re.compile('^#', re.UNICODE), six.u('')),
# Some house numbers have multiple hyphens
(re.compile('[\-]{2,}'), six.u('-')),
# Some house number ranges are split up like "12 -14" # Some house number ranges are split up like "12 -14"
(re.compile('[\s]*\-[\s]*'), six.u('-')), (re.compile('[\s]*\-[\s]*'), six.u('-')),
] ]