From ccbd94dabdb0a70bd6876437c0e161ef9dfb546f Mon Sep 17 00:00:00 2001
From: Yann MAHE <yann@datadoghq.com>
Date: Wed, 24 Aug 2016 15:12:32 -0400
Subject: [PATCH] =?UTF-8?q?[dogstatsd]=20support=20unicode=20tags=20?=
 =?UTF-8?q?=F0=9F=94=A3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using unicode with DogStatsD tags causes `UnicodeDecodeError`
exceptions.

Do not raise on unicode tags. Fix #132.
---
 datadog/dogstatsd/base.py           | 13 ++++++++-----
 datadog/util/compat.py              |  4 ++++
 tests/unit/dogstatsd/test_statsd.py |  4 ++--
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/datadog/dogstatsd/base.py b/datadog/dogstatsd/base.py
index 25d509c49..6205cdaa4 100644
--- a/datadog/dogstatsd/base.py
+++ b/datadog/dogstatsd/base.py
@@ -2,20 +2,23 @@
 """
 DogStatsd is a Python client for DogStatsd, a Statsd fork for Datadog.
 """
-
-import logging
-import os
+# stdlib
+from functools import wraps
 from random import random
 from time import time
+import logging
+import os
 import socket
 import struct
-from functools import wraps
 
 try:
     from itertools import imap
 except ImportError:
     imap = map
 
+# datadog
+from datadog.util.compat import text
+
 
 log = logging.getLogger('dogstatsd')
 
@@ -289,7 +292,7 @@ def _report(self, metric, metric_type, value, tags, sample_rate):
         if tags:
             payload.extend(["|#", ",".join(tags)])
 
-        encoded = "".join(imap(str, payload))
+        encoded = "".join(imap(text, payload))
 
         # Send it
         self._send(encoded)
diff --git a/datadog/util/compat.py b/datadog/util/compat.py
index aa4cb2840..003908cd9 100644
--- a/datadog/util/compat.py
+++ b/datadog/util/compat.py
@@ -24,6 +24,8 @@ def iteritems(d):
     def iternext(iter):
         return next(iter)
 
+    text = str
+
 else:
     get_input = raw_input
     import ConfigParser as configparser
@@ -36,6 +38,8 @@ def iteritems(d):
     def iternext(iter):
         return iter.next()
 
+    text = unicode
+
 
 try:
     from UserDict import IterableUserDict
diff --git a/tests/unit/dogstatsd/test_statsd.py b/tests/unit/dogstatsd/test_statsd.py
index 13992ca65..112da7a4b 100644
--- a/tests/unit/dogstatsd/test_statsd.py
+++ b/tests/unit/dogstatsd/test_statsd.py
@@ -103,8 +103,8 @@ def test_tagged_gauge(self):
         t.assert_equal('gt:123.4|g|#country:china,age:45,blue', self.recv())
 
     def test_tagged_counter(self):
-        self.statsd.increment('ct', tags=['country:canada', 'red'])
-        t.assert_equal('ct:1|c|#country:canada,red', self.recv())
+        self.statsd.increment('ct', tags=[u'country:españa', 'red'])
+        t.assert_equal(u'ct:1|c|#country:españa,red', self.recv())
 
     def test_tagged_histogram(self):
         self.statsd.histogram('h', 1, tags=['red'])