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

[fix] blank values containing punctuation in formatting

Browse Source
This commit is contained in:
Al
2015-09-26 21:49:28 -04:00
parent dac0440be8
commit 5b829cd5a7
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
scripts/geodata/address_formatting/formatter.py
View File

@@ -167,16 +167,20 @@ class AddressFormatter(object):
def strip_component(self, value, tagged=False): def strip_component(self, value, tagged=False):
if not tagged: if not tagged:
start = end = 0 start = end = 0
tokens = tokenize_raw(value) tokens = tokenize_raw(value.strip())
for token_start, token_length, token_type in tokens: for token_start, token_length, token_type in tokens:
start = token_start start = token_start
if token_type < token_types.PERIOD.value: if token_type < token_types.PERIOD.value:
break break
else:
start = token_start + token_length
for token_start, token_length, token_type in reversed(tokens): for token_start, token_length, token_type in reversed(tokens):
end = token_start + token_length end = token_start + token_length
if token_type < token_types.PERIOD.value: if token_type < token_types.PERIOD.value:
break break
else:
end = token_start
return value[start:end] return value[start:end]
else: else: