# HG changeset patch
# User Manuel Jacob <me@manueljacob.de>
# Date 2020-06-16 12:00:20
# Node ID 75b59d221aa322cfd4b8ce55c41e9841654e0fb2
# Parent  de7bdb0e2a95edda3bf609e203f77e5385f765fd

py3: pass native string to urlreq.url2pathname()

Of course, I’m not happy with the warning, but it’s better than crashing.
Solving the problem properly is hard, and non-UTF-8 percent-encoded bytes in
file URLs seem rare enough to block solving that all file URLs (even if not
SVN-specific) will cause a crash.

diff --git a/hgext/convert/subversion.py b/hgext/convert/subversion.py
--- a/hgext/convert/subversion.py
+++ b/hgext/convert/subversion.py
@@ -321,7 +321,26 @@ def issvnurl(ui, url):
                 and path[2:6].lower() == b'%3a/'
             ):
                 path = path[:2] + b':/' + path[6:]
-            path = urlreq.url2pathname(path)
+            # pycompat.fsdecode() / pycompat.fsencode() are used so that bytes
+            # in the URL roundtrip correctly on Unix. urlreq.url2pathname() on
+            # py3 will decode percent-encoded bytes using the utf-8 encoding
+            # and the "replace" error handler. This means that it will not
+            # preserve non-UTF-8 bytes (https://bugs.python.org/issue40983).
+            # url.open() uses the reverse function (urlreq.pathname2url()) and
+            # has a similar problem
+            # (https://bz.mercurial-scm.org/show_bug.cgi?id=6357). It makes
+            # sense to solve both problems together and handle all file URLs
+            # consistently. For now, we warn.
+            unicodepath = urlreq.url2pathname(pycompat.fsdecode(path))
+            if pycompat.ispy3 and u'\N{REPLACEMENT CHARACTER}' in unicodepath:
+                ui.warn(
+                    _(
+                        b'on Python 3, we currently do not support non-UTF-8 '
+                        b'percent-encoded bytes in file URLs for Subversion '
+                        b'repositories\n'
+                    )
+                )
+            path = pycompat.fsencode(unicodepath)
     except ValueError:
         proto = b'file'
         path = os.path.abspath(url)
diff --git a/tests/test-convert-svn-encoding.t b/tests/test-convert-svn-encoding.t
--- a/tests/test-convert-svn-encoding.t
+++ b/tests/test-convert-svn-encoding.t
@@ -152,3 +152,23 @@ Check tags are in UTF-8
   f7e66f98380ed1e53a797c5c7a7a2616a7ab377d branch\xc3\xa9 (esc)
 
   $ cd ..
+
+#if py3
+For now, on Python 3, we abort when encountering non-UTF-8 percent-encoded
+bytes in a filename.
+
+  $ hg convert file:///%ff test
+  initializing destination test repository
+  on Python 3, we currently do not support non-UTF-8 percent-encoded bytes in file URLs for Subversion repositories
+  file:///%ff does not look like a CVS checkout
+  $TESTTMP/file:/%ff does not look like a Git repository
+  file:///%ff does not look like a Subversion repository
+  file:///%ff is not a local Mercurial repository
+  file:///%ff does not look like a darcs repository
+  file:///%ff does not look like a monotone repository
+  file:///%ff does not look like a GNU Arch repository
+  file:///%ff does not look like a Bazaar repository
+  file:///%ff does not look like a P4 repository
+  abort: file:///%ff: missing or unsupported repository
+  [255]
+#endif