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

[osm/formatting] Tagging separators as well in tagged output of the address formatter

Browse Source
This commit is contained in:
Al
2015-09-24 01:22:49 -04:00
parent f6c30778bf
commit c85ce0b11d
1 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
scripts/geodata/address_formatting/formatter.py
View File

@@ -38,6 +38,9 @@ class AddressFormatter(object):
splitter = ' | ' splitter = ' | '
separator_tag = 'SEP'
field_separator_tag = 'FSEP'
aliases = OrderedDict([ aliases = OrderedDict([
('name', 'house'), ('name', 'house'),
('addr:housename', 'house'), ('addr:housename', 'house'),
@@ -116,7 +119,9 @@ class AddressFormatter(object):
values = self.whitespace_component_regex.split(output) values = self.whitespace_component_regex.split(output)
output = self.splitter.join([ splitter = self.splitter if not tagged else ' {}/{} '.format(self.splitter.strip(), self.field_separator_tag)
output = splitter.join([
self.strip_component(val, tagged=tagged) self.strip_component(val, tagged=tagged)
for val in values for val in values
]) ])
@@ -153,6 +158,12 @@ class AddressFormatter(object):
text = re.sub(regex, replacement, text) text = re.sub(regex, replacement, text)
return text return text
def tag_template_separators(self, template):
template = re.sub(r'},', '}} ,/{} '.format(self.separator_tag), template)
template = re.sub(r'}-', '}} -/{} '.format(self.separator_tag), template)
template = re.sub(r' - ', ' -/{} '.format(self.separator_tag), template)
return template
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
@@ -203,6 +214,7 @@ class AddressFormatter(object):
self.apply_replacements(template, components) self.apply_replacements(template, components)
if tag_components: if tag_components:
template_text = self.tag_template_separators(template_text)
components = {k: u' '.join([u'{}/{}'.format(t, k.replace(' ', '_')) components = {k: u' '.join([u'{}/{}'.format(t, k.replace(' ', '_'))
for t, c in tokenize(v)]) for t, c in tokenize(v)])
for k, v in components.iteritems()} for k, v in components.iteritems()}