From e560e533087d315b0f5d24d578333dc84aa6c5a6 Mon Sep 17 00:00:00 2001 From: Al Date: Tue, 24 Nov 2015 22:27:57 -0500 Subject: [PATCH] [fix] formatter --- scripts/geodata/osm/osm_address_training_data.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/scripts/geodata/osm/osm_address_training_data.py b/scripts/geodata/osm/osm_address_training_data.py index 96f337e7..d67707e3 100644 --- a/scripts/geodata/osm/osm_address_training_data.py +++ b/scripts/geodata/osm/osm_address_training_data.py @@ -685,7 +685,7 @@ def build_address_format_training_data_limited(language_rtree, infile, out_dir): i = 0 # Simple whitespace splitter is all that's necessary - formatter = AddressFormatter(splitter=' ') + formatter = AddressFormatter(splitter=u' ') f = open(os.path.join(out_dir, ADDRESS_FORMAT_DATA_LANGUAGE_FILENAME), 'w') writer = csv.writer(f, 'tsv_no_quote') @@ -714,6 +714,9 @@ def build_address_format_training_data_limited(language_rtree, infile, out_dir): if not name_language: continue + if have_country: + value['addr:country'] = u'' + single_language = len(name_language) == 1 for lang, val in name_language.iteritems():