From 0c792a2cc37205cc8e8d677308ff5e82c15a0a30 Mon Sep 17 00:00:00 2001 From: Al Date: Sat, 26 Sep 2015 03:21:26 -0400 Subject: [PATCH] [osm/formatting] Changing the way the formatter elimiates inter-component separators, changing repo back to OpenCageData after pull request merge --- scripts/geodata/address_formatting/formatter.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/scripts/geodata/address_formatting/formatter.py b/scripts/geodata/address_formatting/formatter.py index 1c2d9759..825cf0cc 100644 --- a/scripts/geodata/address_formatting/formatter.py +++ b/scripts/geodata/address_formatting/formatter.py @@ -9,7 +9,7 @@ from postal.text.tokenize import tokenize, tokenize_raw, token_types from collections import OrderedDict from itertools import ifilter -FORMATTER_GIT_REPO = 'https://github.com/openvenues/address-formatting' +FORMATTER_GIT_REPO = 'https://github.com/OpenCageData/address-formatting' class AddressFormatter(object): @@ -182,12 +182,17 @@ class AddressFormatter(object): else: i = j = 0 tokens = value.split() + + separator_tag = self.separator_tag + for i, t in enumerate(tokens): - if '/' in t: + t, c = t.split('/') + if c != separator_tag: break for j, t in enumerate(reversed(tokens)): - if '/' in t: + t, c = t.split('/') + if c != separator_tag: break if j == 0: