[addresses] adding new config for postal codes around the world. Allows appending the ISO alpha-2 country code to the beginning of the postcode as in e.g. SI-1000 (only used if the postcode begins with a digit). This system was used for postal codes in continental Europe as a recommendation from the CEPT. Now 7 member states still use it, so in those countries add the country-code with higher probability. The config also contains the license plate codes for countries where e.g. L-1234 might be used instead of LU-1234. Allows configuring in which countries postcodes should be validated using Google's per-country validation regexes (and the ability to override with a custom regex), and in which countries other admin component names should be stripped.

scripts/geodata/postal_codes/validation.py

@@ -0,0 +1,33 @@
+import re
+from geodata.i18n.google import google_i18n
+from geodata.postal_codes.config import postal_codes_config
+
+
+class PostcodeRegexes(object):
+    def __init__(self):
+        self.responses = {}
+        self.postcode_regexes = {}
+
+    def get(self, country_code):
+        ret = self.postcode_regexes.get(country_code.lower())
+        if ret is None:
+
+            override_regex = postal_codes_config.get_property('override_regex', country=country_code)
+            if override_regex:
+                ret = re.compile(override_regex, re.I)
+                self.postcode_regexes[country_code.lower()] = ret
+                return ret
+
+            response = google_i18n.get(country_code)
+            if response:
+                postcode_expression = response.get('zip')
+                if not postcode_expression:
+                    self.postcode_regexes[country_code.lower()] = None
+                    return None
+                ret = re.compile(postcode_expression, re.I)
+                self.postcode_regexes[country_code.lower()] = ret
+
+        return ret
+
+
+postcode_regexes = PostcodeRegexes()