pathauditor: check for codepoints ignored on OS X

mercurial/pathutil.py

@@ -1,8 +1,12 b''
 import os, errno, stat
 
+import encoding
 import util
 from i18n import _
 
+def _lowerclean(s):
+    return encoding.hfsignoreclean(s.lower())
+
 class pathauditor(object):
     '''ensure that a filesystem path contains no banned components.
     the following properties of a path are checked:
@@ -39,11 +43,11 b' class pathauditor(object):'
             raise util.Abort(_("path ends in directory separator: %s") % path)
         parts = util.splitpath(path)
         if (os.path.splitdrive(path)[0]
-            or parts[0].lower() in ('.hg', '.hg.', '')
+            or _lowerclean(parts[0]) in ('.hg', '.hg.', '')
             or os.pardir in parts):
             raise util.Abort(_("path contains illegal component: %s") % path)
-        if '.hg' in path.lower():
-            lparts = [p.lower() for p in parts]
+        if '.hg' in _lowerclean(path):
+            lparts = [_lowerclean(p.lower()) for p in parts]
             for p in '.hg', '.hg.':
                 if p in lparts[1:]:
                     pos = lparts.index(p)

tests/test-commit.t

@@ -457,4 +457,21 b' commit copy'
        0         0       6  .....       0 26d3ca0dfd18 000000000000 000000000000 (re)
        1         6       7  .....       1 d267bddd54f7 26d3ca0dfd18 000000000000 (re)
 
+verify pathauditor blocks evil filepaths
+  $ cat > evil-commit.py <<EOF
+  > from mercurial import ui, hg, context, node
+  > notrc = u".h\u200cg".encode('utf-8') + '/hgrc'
+  > u = ui.ui()
+  > r = hg.repository(u, '.')
+  > def filectxfn(repo, memctx, path):
+  >     return context.memfilectx(repo, path, '[hooks]\nupdate = echo owned')
+  > c = context.memctx(r, [r['tip'].node(), node.nullid],
+  >                    'evil', [notrc], filectxfn, 0)
+  > r.commitctx(c)
+  > EOF
+  $ $PYTHON evil-commit.py
+  $ hg co --clean tip
+  abort: path contains illegal component: .h\xe2\x80\x8cg/hgrc (esc)
+  [255]
+
   $ cd ..