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

[fix] top language

Browse Source
This commit is contained in:
Al
2015-09-03 20:09:46 -04:00
parent 44bf94a158
commit b15d2d70aa
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/geodata/osm/osm_address_training_data.py
View File

@@ -624,12 +624,17 @@ def build_toponym_training_data(language_rtree, infile, out_dir):
name_language = defaultdict(list) name_language = defaultdict(list)
official = official_languages[country]
num_langs = len(candidate_languages) num_langs = len(candidate_languages)
default_langs = set([l for l, default in official_languages[country].iteritems() if default]) default_langs = set([l for l, default in official.iteritems() if default])
num_defaults = len(default_langs) num_defaults = len(default_langs)
top_lang = official_languages[country].iterkeys().next() top_lang = None
if top_lang not in WELL_REPRESENTED_LANGUAGES and len(default_langs) > 1: if len(official) > 0:
top_lang = official.iterkeys().next()
if top_lang is not None and top_lang not in WELL_REPRESENTED_LANGUAGES and len(default_langs) > 1:
default_langs -= WELL_REPRESENTED_LANGUAGES default_langs -= WELL_REPRESENTED_LANGUAGES
elif len(default_langs & WELL_REPRESENTED_LANGUAGES) > 1: elif len(default_langs & WELL_REPRESENTED_LANGUAGES) > 1:
continue continue