Merge pull request #139 from varju/url-encode-query-string

URL encode non-alpha querystring parameters

awscurl/awscurl.py

@@ -16,6 +16,7 @@
 import configargparse
 import requests
 from requests.structures import CaseInsensitiveDict
+from urllib.parse import quote
 
 
 from .utils import sha256_hash, sha256_hash_for_binary_data, sign
@@ -315,11 +316,24 @@ def __normalize_query_string(query):
                        for s in query.split('&')
                        if len(s) > 0)
 
-    normalized = '&'.join('%s=%s' % (p[0], p[1] if len(p) > 1 else '')
+    normalized = '&'.join('%s=%s' % (aws_url_encode(p[0]), aws_url_encode(p[1]) if len(p) > 1 else '')
                           for p in sorted(parameter_pairs))
     return normalized
 
 
+def aws_url_encode(text):
+    """
+    URI-encode each parameter name and value according to the following rules:
+    - Do not URI-encode any of the unreserved characters that RFC 3986 defines: A-Z, a-z, 0-9, hyphen (-),
+      underscore (_), period (.), and tilde (~).
+    - Percent-encode all other characters with %XY, where X and Y are hexadecimal characters (0-9 and uppercase A-F).
+      For example, the space character must be encoded as %20 (not using '+', as some encoding schemes do) and
+      extended UTF-8 characters must be in the form %XY%ZA%BC.
+    - Double-encode any equals (=) characters in parameter values.
+    """
+    return quote(text, safe='~=').replace('=', '==')
+
+
 def __now():
     return datetime.datetime.utcnow()
 

tests/stages_test.py

@@ -45,6 +45,33 @@ def test_task_1_create_a_canonical_request(self):
                          "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855")
         self.assertEqual(signed_headers, "host;x-amz-date")
 
+    def test_task_1_create_a_canonical_request_url_encode_querystring(self):
+        """
+        Test that canonical requests correctly sort and url encode querystring parameters.
+        """
+        canonical_request, payload_hash, signed_headers = task_1_create_a_canonical_request(
+            query="arg1=true&arg3=c,b,a&arg2=false&noEncoding=ABC-abc_1.23~tilde/slash",
+            headers="{'Content-Type': 'application/json', 'Accept': 'application/xml'}",
+            port=None,
+            host="my-gateway-id.execute-api.us-east-1.amazonaws.com",
+            amzdate="20190921T022008Z",
+            method="GET",
+            data="",
+            security_token=None,
+            data_binary=False,
+            canonical_uri="/stage/my-path")
+        self.assertEqual(canonical_request, "GET\n"
+                         "/stage/my-path\n"
+                         "arg1=true&arg2=false&arg3=c%2Cb%2Ca&noEncoding=ABC-abc_1.23~tilde%2Fslash\n"
+                         "host:my-gateway-id.execute-api.us-east-1.amazonaws.com\n"
+                         "x-amz-date:20190921T022008Z\n"
+                         "\n"
+                         "host;x-amz-date\n"
+                         "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855")
+        self.assertEqual(payload_hash,
+                         "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855")
+        self.assertEqual(signed_headers, "host;x-amz-date")
+
     def test_task_2_create_the_string_to_sign(self):
         """
         Test the next function that is creating a string in exactly the same way as AWS is on the

tests/unit_test.py

@@ -2,14 +2,13 @@
 # -*- coding: UTF-8 -*-
 
 import datetime
-import logging
 import sys
 
 from unittest import TestCase
 
 from mock import patch
 
-from awscurl.awscurl import make_request
+from awscurl.awscurl import aws_url_encode, make_request
 
 from requests.exceptions import SSLError
 from requests import Response
@@ -318,3 +317,13 @@ def test_make_request(self, mocked_resp):
         self.assertFalse(expected in str(r.text.encode('utf-8')))
 
     pass
+
+class TestAwsUrlEncode(TestCase):
+  def test_aws_url_encode(self):
+    self.assertEqual(aws_url_encode(""), "")
+    self.assertEqual(aws_url_encode("AZaz09-_.~"), "AZaz09-_.~")
+    self.assertEqual(aws_url_encode(" /:@[`{"), "%20%2F%3A%40%5B%60%7B")
+    self.assertEqual(aws_url_encode("a=,=b"), "a==%2C==b")
+    self.assertEqual(aws_url_encode("\u0394-\u30a1"), "%CE%94-%E3%82%A1")
+
+  pass