--- a/mercurial/changelog.py Thu May 19 16:57:14 2011 +0200
+++ b/mercurial/changelog.py Thu May 19 18:10:03 2011 +0200
@@ -205,6 +205,11 @@
def add(self, manifest, files, desc, transaction, p1, p2,
user, date=None, extra=None):
+ # Convert to UTF-8 encoded bytestrings as the very first
+ # thing: calling any method on a localstr object will turn it
+ # into a str object and the cached UTF-8 string is thus lost.
+ user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
+
user = user.strip()
# An empty username or a username with a "\n" will make the
# revision text contain two "\n\n" sequences -> corrupt
@@ -218,8 +223,6 @@
# strip trailing whitespace and leading and trailing empty lines
desc = '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')
- user, desc = encoding.fromlocal(user), encoding.fromlocal(desc)
-
if date:
parseddate = "%d %d" % util.parsedate(date)
else:
--- a/tests/test-context.py Thu May 19 16:57:14 2011 +0200
+++ b/tests/test-context.py Thu May 19 18:10:03 2011 +0200
@@ -1,5 +1,5 @@
import os
-from mercurial import hg, ui
+from mercurial import hg, ui, context, encoding
u = ui.ui()
@@ -17,3 +17,16 @@
repo.commit(text='commit1', date="0 0")
print "workingfilectx.date =", repo[None]['foo'].date()
+
+# test memctx with non-ASCII commit message
+
+def filectxfn(repo, memctx, path):
+ return context.memfilectx("foo", "")
+
+ctx = context.memctx(repo, ['tip', None],
+ encoding.tolocal("Gr\xc3\xbcezi!"),
+ ["foo"], filectxfn)
+ctx.commit()
+for enc in "ASCII", "Latin-1", "UTF-8":
+ encoding.encoding = enc
+ print "%-8s: %s" % (enc, repo["tip"].description())
--- a/tests/test-context.py.out Thu May 19 16:57:14 2011 +0200
+++ b/tests/test-context.py.out Thu May 19 18:10:03 2011 +0200
@@ -1,1 +1,4 @@
workingfilectx.date = (1000, 0)
+ASCII : Gr?ezi!
+Latin-1 : Grüezi!
+UTF-8 : Grüezi!