diff hgext/convert/cvsps.py @ 33388:0823f0983eaa

convert: transcode CVS log messages by specified encoding (issue5597)

Converting from CVS to Mercurial assumes that CVS log messages in "cvs
rlog" output are encoded in UTF-8 (or basic Latin-1). But cvs itself
is usually unaware of encoding of log messages, in practice.

Therefore, if there are commits, of which log message is encoded in
other than UTF-8, log message of corresponded revisions in the
converted repository will be broken.

To avoid such broken log messages, this patch transcodes CVS log
messages by encoding specified via "convert.cvsps.logencoding"
configuration.

This patch accepts multiple encoding for convenience, because
"multiple encoding mixed in a repository" easily occurs. For example,
UTF-8 (recent POSIX), cp932 (Windows), and EUC-JP (legacy POSIX) are
well known encoding for Japanese.

--- a/hgext/convert/cvsps.py	Mon Jul 10 23:09:52 2017 +0900
+++ b/hgext/convert/cvsps.py	Tue Jul 11 02:10:04 2017 +0900
@@ -12,6 +12,7 @@
 from mercurial.i18n import _
 from mercurial import (
     encoding,
+    error,
     hook,
     pycompat,
     util,
@@ -491,6 +492,35 @@
 
     ui.status(_('%d log entries\n') % len(log))
 
+    encodings = ui.configlist('convert', 'cvsps.logencoding')
+    if encodings:
+        def revstr(r):
+            # this is needed, because logentry.revision is a tuple of "int"
+            # (e.g. (1, 2) for "1.2")
+            return '.'.join(pycompat.maplist(pycompat.bytestr, r))
+
+        for entry in log:
+            comment = entry.comment
+            for e in encodings:
+                try:
+                    entry.comment = comment.decode(e).encode('utf-8')
+                    if ui.debugflag:
+                        ui.debug("transcoding by %s: %s of %s\n" %
+                                 (e, revstr(entry.revision), entry.file))
+                    break
+                except UnicodeDecodeError:
+                    pass # try next encoding
+                except LookupError as inst: # unknown encoding, maybe
+                    raise error.Abort(inst,
+                                      hint=_('check convert.cvsps.logencoding'
+                                             ' configuration'))
+            else:
+                raise error.Abort(_("no encoding can transcode"
+                                    " CVS log message for %s of %s")
+                                  % (revstr(entry.revision), entry.file),
+                                  hint=_('check convert.cvsps.logencoding'
+                                         ' configuration'))
+
     hook.hook(ui, None, "cvslog", True, log=log)
 
     return log