gitk: Fix commit encoding support

This commit fixes two problems with commit encodings:

1) git-log actually uses i18n.logoutputencoding to generate
its output, and falls back to i18n.commitencoding only
when that option is not set.  Thus, gitk should use its
value to read the results, if available.

2) The readcommit function did not process encodings at all.
This led to randomly appearing misconverted commits if
the commit encoding differed from the current locale.

Now commit messages should be displayed correctly, except
when logoutputencoding is set to an encoding that cannot
represent charecters in the message.  For example, it is
impossible to convert Japanese characters from Shift-JIS
to CP-1251 (although the reverse conversion works).

The reason for using git log to read the commit and then getting
Tcl to convert its output is that is essentially what happens in
the normal path through getcommitlines, hence there is less chance
for unintended differences in how commits are processed in
getcommitlines and do_readcommit.

Signed-off-by: Alexander Gavrilov <angavrilov@gmail.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>

diff --git a/gitk b/gitk
index e6aafe8a687ee501a86666a00b2ccd9d5a014114..3864d3826de6ea24fb807cc2346d74d84c39db42 100755 (executable)
--- a/gitk
+++ b/gitk
@@ -1555,9 +1555,27 @@ proc chewcommits {} {
     return 0
 }
 
     return 0
 }
 

+proc do_readcommit {id} {
+    global tclencoding
+
+    # Invoke git-log to handle automatic encoding conversion
+    set fd [open [concat | git log --no-color --pretty=raw -1 $id] r]
+    # Read the results using i18n.logoutputencoding
+    fconfigure $fd -translation lf -eofchar {}
+    if {$tclencoding != {}} {
+       fconfigure $fd -encoding $tclencoding
+    }
+    set contents [read $fd]
+    close $fd
+    # Remove the heading line
+    regsub {^commit [0-9a-f]+\n} $contents {} contents
+
+    return $contents
+}
+

 proc readcommit {id} {
 proc readcommit {id} {

-    if {[catch {set contents [exec git cat-file commit $id]}]} return
-    parsecommit $id $contents 0
+    if {[catch {set contents [do_readcommit $id]}]} return
+    parsecommit $id $contents 1

 }
 
 proc parsecommit {id contents listed} {
 }
 
 proc parsecommit {id contents listed} {


@@ -10558,6 +10576,9 @@ set gitencoding {}
 catch {
     set gitencoding [exec git config --get i18n.commitencoding]
 }
 catch {
     set gitencoding [exec git config --get i18n.commitencoding]
 }

+catch {
+    set gitencoding [exec git config --get i18n.logoutputencoding]
+}

 if {$gitencoding == ""} {
     set gitencoding "utf-8"
 }
 if {$gitencoding == ""} {
     set gitencoding "utf-8"
 }