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

[fix] exclude country toponyms where the default languages is well represented

Browse Source
This commit is contained in:
Al
2015-09-03 20:56:58 -04:00
parent 20bb191624
commit 8345afbcd0
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
scripts/geodata/osm/osm_address_training_data.py
View File

@@ -624,12 +624,15 @@ def build_toponym_training_data(language_rtree, infile, out_dir):
name_language = defaultdict(list)
all_langs = country_languages[country]
official = official_languages[country]
num_langs = len(candidate_languages)
default_langs = set([l for l, default in official.iteritems() if default])
num_defaults = len(default_langs)
defaults_well_represented = all((d in WELL_REPRESENTED_LANGUAGES for d in defaults))
regional_langs = list(chain(*(p['languages'] for p in language_props if p.get('admin_level', 0) > 0)))
top_lang = None
@@ -666,7 +669,7 @@ def build_toponym_training_data(language_rtree, infile, out_dir):
have_qualified_names = True
name_language[lang].append(v)
if not have_qualified_names and len(regional_langs) <= 1 and num_langs == 1 and 'name' in value:
if not have_qualified_names and len(regional_langs) <= 1 and 'name' in value and (len(all_langs) == 1 or (num_langs == 1 and not defaults_well_represented)):
name_language[candidate_languages[0]['lang']].append(value['name'])
for k, v in name_language.iteritems():