# HG changeset patch
# User Manuel Jacob <me@manueljacob.de>
# Date 1593485752 -7200
# Node ID 697212a830fbac295d7270684bf232f87584cbdd
# Parent  bd0f122f3f51939b2adc7d6f9d8611692b1ebdce
convert: bail out in Subversion source if encountering non-ASCII HTTP(S) URL

Before this patch, in the tested case, urllib raised `httplib.InvalidURL: URL
can't contain control characters. '/\xff/!svn/ver/0/.svn' (found at least
'\xff')`, which resulted in that the URL was never recognized as a Subversion
repository.

This patch adds a check that bails out if the URL contains non-ASCII characters.
The warning is not overly user-friendly, but giving the user something to type
into a search engine is definitively better than not explaining why the
repository was not recognized.

We could support non-ASCII chracters by quoting them before passing them to
urllib. However, we would want to be compatible with what the `svn` command
does, which converts the URL from the locale encoding to UTF-8, percent-encodes
it and sends it to the server. If the locale encoding is not UTF-8, the
behavior is IMHO not very intuitive, as the `svn` command may send different
(percent-encoded) octets than what was passed on the console. Instead of
copying this behavior, we better leave it forbidden.

diff -r bd0f122f3f51 -r 697212a830fb hgext/convert/subversion.py
--- a/hgext/convert/subversion.py	Mon Jun 29 02:05:12 2020 +0200
+++ b/hgext/convert/subversion.py	Tue Jun 30 04:55:52 2020 +0200
@@ -347,6 +347,15 @@
         path = os.path.abspath(url)
     if proto == b'file':
         path = util.pconvert(path)
+    elif proto in (b'http', 'https'):
+        if not encoding.isasciistr(path):
+            ui.warn(
+                _(
+                    b"Subversion sources don't support non-ASCII characters in "
+                    b"HTTP(S) URLs. Please percent-encode them.\n"
+                )
+            )
+            return False
     check = protomap.get(proto, lambda *args: False)
     while b'/' in path:
         if check(ui, path, proto):
diff -r bd0f122f3f51 -r 697212a830fb tests/test-convert-svn-encoding.t
--- a/tests/test-convert-svn-encoding.t	Mon Jun 29 02:05:12 2020 +0200
+++ b/tests/test-convert-svn-encoding.t	Tue Jun 30 04:55:52 2020 +0200
@@ -153,6 +153,16 @@
 
   $ cd ..
 
+Subversion sources don't support non-ASCII characters in HTTP(S) URLs.
+
+  $ XFF=$($PYTHON -c 'from mercurial.utils.procutil import stdout; stdout.write(b"\xff")')
+  $ hg convert --source-type=svn http://localhost:$HGPORT/$XFF test
+  initializing destination test repository
+  Subversion sources don't support non-ASCII characters in HTTP(S) URLs. Please percent-encode them.
+  http://localhost:$HGPORT/\xff does not look like a Subversion repository (esc)
+  abort: http://localhost:$HGPORT/\xff: missing or unsupported repository (esc)
+  [255]
+
 #if py3
 For now, on Python 3, we abort when encountering non-UTF-8 percent-encoded
 bytes in a filename.