diff hgext/convert/subversion.py @ 45022:e3b19004087a stable

convert: correctly convert paths to UTF-8 for Subversion

The previous code using encoding.tolocal() only worked by chance in these
situations:

* The string is ASCII: The fast path was triggered and the string was returned
  unmodified.
* The local encoding is UTF-8: The source and target encoding is the same.
* The string is not valid UTF-8 and the native encoding is ISO-8859-1: If the
  string doesn’t decode using UTF-8, ISO-8859-1 is tried as a fallback. During
  `hg convert`, the local encoding is always UTF-8. The irony is that in this
  case, encoding.tolocal() behaves like what someone would expect the reverse
  function, encoding.fromlocal(), to do.

When the locale encoding is ISO-8859-15, trying to convert a SVN repo `/tmp/a€`
failed before like this:

file:///tmp/a%C2%A4 does not look like a Subversion repository to libsvn version 1.14.0

The correct URL is `file:///tmp/a%E2%82%AC`.

Unlike previously (with the ISO-8859-1 fallback), decoding the path using the
locale encoding can fail. In this case, we have to bail out, as Subversion
won’t be able to do anything useful with the path.

--- a/hgext/convert/subversion.py	Tue Jun 30 05:04:36 2020 +0200
+++ b/hgext/convert/subversion.py	Mon Jun 29 15:03:36 2020 +0200
@@ -3,6 +3,8 @@
 # Copyright(C) 2007 Daniel Holth et al
 from __future__ import absolute_import
 
+import codecs
+import locale
 import os
 import re
 import xml.dom.minidom
@@ -63,6 +65,38 @@
     svn = None
 
 
+# In Subversion, paths are Unicode (encoded as UTF-8), which Subversion
+# converts from / to native strings when interfacing with the OS. When passing
+# paths to Subversion, we have to recode them such that it roundstrips with
+# what Subversion is doing.
+
+fsencoding = None
+
+
+def init_fsencoding():
+    global fsencoding, fsencoding_is_utf8
+    if fsencoding is not None:
+        return
+    if pycompat.iswindows:
+        # On Windows, filenames are Unicode, but we store them using the MBCS
+        # encoding.
+        fsencoding = 'mbcs'
+    else:
+        # This is the encoding used to convert UTF-8 back to natively-encoded
+        # strings in Subversion 1.14.0 or earlier with APR 1.7.0 or earlier.
+        with util.with_lc_ctype():
+            fsencoding = locale.nl_langinfo(locale.CODESET) or 'ISO-8859-1'
+    fsencoding = codecs.lookup(fsencoding).name
+    fsencoding_is_utf8 = fsencoding == codecs.lookup('utf-8').name
+
+
+def fs2svn(s):
+    if fsencoding_is_utf8:
+        return s
+    else:
+        return s.decode(fsencoding).encode('utf-8')
+
+
 class SvnPathNotFound(Exception):
     pass
 
@@ -117,7 +151,7 @@
             path = b'/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
-        path = encoding.tolocal(path)
+        path = fs2svn(path)
         path = b'file://%s' % quote(path)
     return svn.core.svn_path_canonicalize(path)
 
@@ -347,6 +381,17 @@
     except ValueError:
         proto = b'file'
         path = os.path.abspath(url)
+        try:
+            path.decode(fsencoding)
+        except UnicodeDecodeError:
+            ui.warn(
+                _(
+                    b'Subversion requires that paths can be converted to '
+                    b'Unicode using the current locale encoding (%s)\n'
+                )
+                % pycompat.sysbytes(fsencoding)
+            )
+            return False
     if proto == b'file':
         path = util.pconvert(path)
     elif proto in (b'http', 'https'):
@@ -384,6 +429,7 @@
     def __init__(self, ui, repotype, url, revs=None):
         super(svn_source, self).__init__(ui, repotype, url, revs=revs)
 
+        init_fsencoding()
         if not (
             url.startswith(b'svn://')
             or url.startswith(b'svn+ssh://')