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

[osm] giving parse_osm_number_range a parameter for max range and setting it to 1000 for postal codes e.g. for major cities that may have several hundred postal codes

Browse Source
This commit is contained in:
Al
2016-08-15 10:34:24 -04:00
parent 637baad629
commit 29fc198aba
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
scripts/geodata/osm/extract.py
View File

@@ -149,7 +149,7 @@ letter_range_regex = re.compile(r'([^\W\d_]){}([^\W\d_])'.format(non_breaking_da
number_split_regex = re.compile('[,;]')
def parse_osm_number_range(value, parse_letter_range=True):
def parse_osm_number_range(value, parse_letter_range=True, max_range=100):
value = normalize_string(value, string_options=NORMALIZE_STRING_LATIN_ASCII | NORMALIZE_STRING_DECOMPOSE)
numbers = []
values = number_split_regex.split(value)
@@ -169,8 +169,8 @@ def parse_osm_number_range(value, parse_letter_range=True):
end_num = int(end_num)
if end_num > start_num:
if end_num - start_num > 100:
end_num = start_num + 100
if end_num - start_num > max_range:
end_num = start_num + max_range
for i in xrange(start_num, end_num + 1):
numbers.append(safe_decode(i).zfill(zfill))
@@ -188,8 +188,8 @@ def parse_osm_number_range(value, parse_letter_range=True):
start_num = ord(start_num)
end_num = ord(end_num)
if end_num > start_num:
if end_num - start_num > 100:
end_num = start_num + 100
if end_num - start_num > max_range:
end_num = start_num + max_range
for i in xrange(start_num, end_num + 1):
numbers.append(six.unichr(i))
else:

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

@@ -452,7 +452,7 @@ class OSMAddressFormatter(object):
valid_postcode = True
if not valid_postcode:
postal_codes = parse_osm_number_range(postal_code, parse_letter_range=False)
postal_codes = parse_osm_number_range(postal_code, parse_letter_range=False, max_range=1000)
return postal_code