convert/darcs: handle non-ASCII metadata in darcs changelog (issue2354)
Given a commit author or message with non-ASCII characters in a darcs
repo, convert would raise a UnicodeEncodeError when adding changesets
to the hg changelog.
This happened because etree returns back unicode objects for any text
it can't encode into ASCII. convert was passing these objects to
changelog.add(), which would then attempt encoding.fromlocal() on
them.
This patch ensures converter_source.recode() is called on each piece
of commit data returned by etree.
(Also note that darcs is currently encoding agnostic and will print
out whatever is in a patch's metadata byte-for-byte, even in the XML
changelog.)
--- a/hgext/convert/darcs.py Sat Sep 11 00:39:34 2010 +0200
+++ b/hgext/convert/darcs.py Fri Sep 10 09:30:50 2010 -0500
@@ -83,6 +83,8 @@
shutil.rmtree(self.tmppath, ignore_errors=True)
def xml(self, cmd, **kwargs):
+ # NOTE: darcs is currently encoding agnostic and will print
+ # patch metadata byte-for-byte, even in the XML changelog.
etree = ElementTree()
fp = self._run(cmd, **kwargs)
etree.parse(fp)
@@ -107,8 +109,12 @@
elt = self.changes[rev]
date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y')
desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
- return commit(author=elt.get('author'), date=util.datestr(date),
- desc=desc.strip(), parents=self.parents[rev])
+ # etree can return unicode objects for name, comment, and author,
+ # so recode() is used to ensure str objects are emitted.
+ return commit(author=self.recode(elt.get('author')),
+ date=util.datestr(date),
+ desc=self.recode(desc).strip(),
+ parents=self.parents[rev])
def pull(self, rev):
output, status = self.run('pull', self.path, all=True,
--- a/tests/test-convert-darcs Sat Sep 11 00:39:34 2010 +0200
+++ b/tests/test-convert-darcs Fri Sep 10 09:30:50 2010 -0500
@@ -56,13 +56,18 @@
rm dir/d2
darcs mv dir dir2
darcs record -a -l -m p3
-cd ..
+
+echo % test utf-8 commit message and author
+echo g > g
+# darcs is encoding agnostic, so it takes whatever bytes it's given
+darcs record -a -l -m 'p4: desc ñ' -A 'author ñ'
glog()
{
- hg glog --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
+ HGENCODING=utf-8 hg glog --template '{rev} "{desc|firstline}" ({author}) files: {files}\n' "$@"
}
+cd ..
hg convert darcs-repo darcs-repo-hg
# The converter does not currently handle patch conflicts very well.
# When they occur, it reverts *all* changes and moves forward,
--- a/tests/test-convert-darcs.out Sat Sep 11 00:39:34 2010 +0200
+++ b/tests/test-convert-darcs.out Fri Sep 10 09:30:50 2010 -0500
@@ -12,26 +12,32 @@
Finished recording patch 'p2'
% test file and directory move
Finished recording patch 'p3'
+% test utf-8 commit message and author
+Finished recording patch 'p4: desc ñ'
initializing destination darcs-repo-hg repository
scanning source...
sorting...
converting...
-4 p0
-3 p1.2
-2 p1.1
-1 p2
-0 p3
-o 4 "p3" files: dir/d dir/d2 dir2/d f ff
+5 p0
+4 p1.2
+3 p1.1
+2 p2
+1 p3
+0 p4: desc ?
+o 5 "p4: desc ñ" (author ñ) files: g
|
-o 3 "p2" files: a dir/d dir/d2 f
+o 4 "p3" (test@example.org) files: dir/d dir/d2 dir2/d f ff
|
-o 2 "p1.1" files:
+o 3 "p2" (test@example.org) files: a dir/d dir/d2 f
|
-o 1 "p1.2" files: a b
+o 2 "p1.1" (test@example.org) files:
|
-o 0 "p0" files: a
+o 1 "p1.2" (test@example.org) files: a b
+|
+o 0 "p0" (test@example.org) files: a
7225b30cdf38257d5cc7780772c051b6f33e6d6b 644 a
1e88685f5ddec574a34c70af492f95b6debc8741 644 b
37406831adc447ec2385014019599dfec953c806 644 dir2/d
b783a337463792a5c7d548ad85a7d3253c16ba8c 644 ff
+0973eb1b2ecc4de7fafe7447ce1b7462108b4848 644 g