# HG changeset patch
# User Gregory Szorc <gregory.szorc@gmail.com>
# Date 2017-03-13 19:16:47
# Node ID fb1f70331ee663f29db0501d8dada622175becd5
# Parent  1ed169c5e235b66aaa7dba8cbb5e3df5c2ca808f

pycompat: custom implementation of urllib.parse.quote()

urllib.parse.quote() accepts either str or bytes and returns str.

There exists a urllib.parse.quote_from_bytes() which only accepts
bytes. We should probably use that to retain strong typing and
avoid surprises.

In addition, since nearly all strings in Mercurial are bytes, we
probably don't want quote() returning unicode.

So, this patch implements a custom quote() that only accepts bytes
and returns bytes. The quoted URL should only contain URL safe
characters which is a strict subset of ASCII. So
`.encode('ascii', 'strict')` should be safe.

diff --git a/mercurial/pycompat.py b/mercurial/pycompat.py
--- a/mercurial/pycompat.py
+++ b/mercurial/pycompat.py
@@ -269,7 +269,6 @@ if not ispy3:
 else:
     import urllib.parse
     urlreq._registeraliases(urllib.parse, (
-        "quote",
         "splitattr",
         "splitpasswd",
         "splitport",
@@ -313,3 +312,12 @@ else:
         "SimpleHTTPRequestHandler",
         "CGIHTTPRequestHandler",
     ))
+
+    # urllib.parse.quote() accepts both str and bytes, decodes bytes
+    # (if necessary), and returns str. This is wonky. We provide a custom
+    # implementation that only accepts bytes and emits bytes.
+    def quote(s, safe=r'/'):
+        s = urllib.parse.quote_from_bytes(s, safe=safe)
+        return s.encode('ascii', 'strict')
+
+    urlreq.quote = quote