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

[addresses] adding the ability to hyphenate the generated unit/floor numbers, either for ranges or simple hyphenated numbers, including hyphenated variants of the letter + number or number + letter forms. Implementing for English but something similar can be done in the other configs.

Browse Source
This commit is contained in:
Al
2017-03-27 01:48:25 -04:00
parent 56f00250c2
commit 217de3a8a2
6 changed files with 74 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/geodata/addresses/staircases.py
View File

@@ -29,6 +29,10 @@ class Staircase(NumberedComponent):
if num_type == cls.NUMERIC:
number = weighted_choice(cls.staircase_range, cls.staircase_range_cdf)
return safe_decode(number)
elif num_type == cls.HYPHENATED_NUMBER:
number = weighted_choice(cls.staircase_range, cls.staircase_range_cdf)
number2 = number + weighted_choice(cls.staircase_range, cls.staircase_range_cdf)
return u'{}-{}'.format(number, number2)
else:
alphabet = address_config.get_property('alphabet', language, country=country, default=latin_alphabet)
alphabet_probability = address_config.get_property('alphabet_probability', language, country=country, default=None)
@@ -41,7 +45,13 @@ class Staircase(NumberedComponent):
number = weighted_choice(cls.staircase_range, cls.staircase_range_cdf)
whitespace_probability = float(num_type_props.get('whitespace_probability', 0.0))
whitespace_phrase = six.u(' ') if whitespace_probability and random.random() < whitespace_probability else six.u('')
hyphen_probability = float(num_type_props.get('hyphen_probability', 0.0))
whitespace_phrase = u''
r = random.random()
if r < whitespace_probability:
whitespace_phrase = u' '
elif r < (whitespace_probability + hyphen_probability):
whitespace_phrase = u'-'
if num_type == cls.ALPHA_PLUS_NUMERIC:
return six.u('{}{}{}').format(letter, whitespace_phrase, number)