From cfa57c96a3a3a6e0f0961b5fb8bada71621e3ab6 Mon Sep 17 00:00:00 2001 From: Al Date: Sun, 4 Oct 2015 02:02:59 -0400 Subject: [PATCH] [fix] untagged formatted addresses --- scripts/geodata/osm/osm_address_training_data.py | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/scripts/geodata/osm/osm_address_training_data.py b/scripts/geodata/osm/osm_address_training_data.py index 793e6cb1..124c35f8 100644 --- a/scripts/geodata/osm/osm_address_training_data.py +++ b/scripts/geodata/osm/osm_address_training_data.py @@ -578,17 +578,16 @@ def build_address_format_training_data(language_rtree, infile, out_dir, tag_comp formatted_addresses.append(formatted_address) for formatted_address in formatted_addresses: - if formatted_address is not None: + if formatted_address and formatted_address.strip(): formatted_address = tsv_string(formatted_address) if not formatted_address or not formatted_address.strip(): continue row = (language, country, formatted_address) writer.writerow(row) - else: - if formatted_address is not None: - formatted_address = tsv_string(formatted_address) - writer.writerow([formatted_address]) + elif formatted_address and formatted_address.strip(): + formatted_address = tsv_string(formatted_address) + writer.writerow([formatted_address]) i += 1 if i % 1000 == 0 and i > 0: