Unicode file name support (gitk and git-gui)

Assumes file names in git tree objects are UTF-8 encoded.

On most unix systems, the system encoding (and thus the TCL system
encoding) will be UTF-8, so file names will be displayed correctly.

On Windows, it is impossible to set the system encoding to UTF-8. Changing
the TCL system encoding (via 'encoding system ...', e.g. in the startup
code) is explicitly discouraged by the TCL docs.

Change gitk and git-gui functions dealing with file names to always convert
from and to UTF-8.

Signed-off-by: Karsten Blees <[email protected]>

Author: kblees

git-gui/git-gui.sh

@@ -552,6 +552,9 @@ proc git {args} {
 
 	_trace_exec [concat $opt $cmdp $args]
 	set result [eval exec $opt $cmdp $args]
+	if {[encoding system] != "utf-8"} {
+		set result [encoding convertfrom utf-8 [encoding convertto $result]]
+	}
 	if {$::_trace} {
 		puts stderr "< $result"
 	}
@@ -1107,7 +1110,7 @@ git-version proc _parse_config {arr_name args} {
 				[list git_read config] \
 				$args \
 				[list --null --list]]
-			fconfigure $fd_rc -translation binary
+			fconfigure $fd_rc -translation binary -encoding utf-8
 			set buf [read $fd_rc]
 			close $fd_rc
 		}
@@ -1685,7 +1688,7 @@ proc read_diff_index {fd after} {
 		set i [split [string range $buf_rdi $c [expr {$z1 - 2}]] { }]
 		set p [string range $buf_rdi $z1 [expr {$z2 - 1}]]
 		merge_state \
-			[encoding convertfrom $p] \
+			[encoding convertfrom utf-8 $p] \
 			[lindex $i 4]? \
 			[list [lindex $i 0] [lindex $i 2]] \
 			[list]
@@ -1718,7 +1721,7 @@ proc read_diff_files {fd after} {
 		set i [split [string range $buf_rdf $c [expr {$z1 - 2}]] { }]
 		set p [string range $buf_rdf $z1 [expr {$z2 - 1}]]
 		merge_state \
-			[encoding convertfrom $p] \
+			[encoding convertfrom utf-8 $p] \
 			?[lindex $i 4] \
 			[list] \
 			[list [lindex $i 0] [lindex $i 2]]
@@ -1741,7 +1744,7 @@ proc read_ls_others {fd after} {
 	set pck [split $buf_rlo "\0"]
 	set buf_rlo [lindex $pck end]
 	foreach p [lrange $pck 0 end-1] {
-		set p [encoding convertfrom $p]
+		set p [encoding convertfrom utf-8 $p]
 		if {[string index $p end] eq {/}} {
 			set p [string range $p 0 end-1]
 		}

git-gui/lib/browser.tcl

@@ -197,7 +197,7 @@ method _ls {tree_id {name {}}} {
 	$w conf -state disabled
 
 	set fd [git_read ls-tree -z $tree_id]
-	fconfigure $fd -blocking 0 -translation binary -encoding binary
+	fconfigure $fd -blocking 0 -translation binary -encoding utf-8
 	fileevent $fd readable [cb _read $fd]
 }
 

git-gui/lib/index.tcl

@@ -115,7 +115,7 @@ proc write_update_indexinfo {fd pathList totalCnt batch after} {
 		set info [lindex $s 2]
 		if {$info eq {}} continue
 
-		puts -nonewline $fd "$info\t[encoding convertto $path]\0"
+		puts -nonewline $fd "$info\t[encoding convertto utf-8 $path]\0"
 		display_file $path $new
 	}
 
@@ -186,7 +186,7 @@ proc write_update_index {fd pathList totalCnt batch after} {
 		?M {set new M_}
 		?? {continue}
 		}
-		puts -nonewline $fd "[encoding convertto $path]\0"
+		puts -nonewline $fd "[encoding convertto utf-8 $path]\0"
 		display_file $path $new
 	}
 
@@ -247,7 +247,7 @@ proc write_checkout_index {fd pathList totalCnt batch after} {
 		?M -
 		?T -
 		?D {
-			puts -nonewline $fd "[encoding convertto $path]\0"
+			puts -nonewline $fd "[encoding convertto utf-8 $path]\0"
 			display_file $path ?_
 		}
 		}

gitk-git/gitk

@@ -7629,7 +7629,7 @@ proc gettreeline {gtf id} {
 	if {[string index $fname 0] eq "\""} {
 	    set fname [lindex $fname 0]
 	}
-	set fname [encoding convertfrom $fname]
+	set fname [encoding convertfrom utf-8 $fname]
 	lappend treefilelist($id) $fname
     }
     if {![eof $gtf]} {
@@ -7891,7 +7891,7 @@ proc gettreediffline {gdtf ids} {
 	    if {[string index $file 0] eq "\""} {
 		set file [lindex $file 0]
 	    }
-	    set file [encoding convertfrom $file]
+	    set file [encoding convertfrom utf-8 $file]
 	    if {$file ne [lindex $treediff end]} {
 		lappend treediff $file
 		lappend sublist $file
@@ -8036,7 +8036,7 @@ proc makediffhdr {fname ids} {
     global ctext curdiffstart treediffs diffencoding
     global ctext_file_names jump_to_here targetline diffline
 
-    set fname [encoding convertfrom $fname]
+    set fname [encoding convertfrom utf-8 $fname]
     set diffencoding [get_path_encoding $fname]
     set i [lsearch -exact $treediffs($ids) $fname]
     if {$i >= 0} {
@@ -8093,7 +8093,7 @@ proc parseblobdiffline {ids line} {
 
     if {![string compare -length 5 "diff " $line]} {
 	if {![regexp {^diff (--cc|--git) } $line m type]} {
-	    set line [encoding convertfrom $line]
+	    set line [encoding convertfrom utf-8 $line]
 	    $ctext insert end "$line\n" hunksep
 	    continue
 	}
@@ -8140,7 +8140,7 @@ proc parseblobdiffline {ids line} {
 	makediffhdr $fname $ids
 
     } elseif {![string compare -length 16 "* Unmerged path " $line]} {
-	set fname [encoding convertfrom [string range $line 16 end]]
+	set fname [encoding convertfrom utf-8 [string range $line 16 end]]
 	$ctext insert end "\n"
 	set curdiffstart [$ctext index "end - 1c"]
 	lappend ctext_file_names $fname
@@ -8195,7 +8195,7 @@ proc parseblobdiffline {ids line} {
 	    if {[string index $fname 0] eq "\""} {
 		set fname [lindex $fname 0]
 	    }
-	    set fname [encoding convertfrom $fname]
+	    set fname [encoding convertfrom utf-8 $fname]
 	    set i [lsearch -exact $treediffs($ids) $fname]
 	    if {$i >= 0} {
 		setinlist difffilestart $i $curdiffstart
@@ -8214,6 +8214,7 @@ proc parseblobdiffline {ids line} {
 	    set diffinhdr 0
 	    return
 	}
+	set line [encoding convertfrom utf-8 $line]
 	$ctext insert end "$line\n" filesep
 
     } else {
@@ -12047,7 +12048,7 @@ proc cache_gitattr {attr pathlist} {
 	    foreach row [split $rlist "\n"] {
 		if {[regexp "(.*): $attr: (.*)" $row m path value]} {
 		    if {[string index $path 0] eq "\""} {
-			set path [encoding convertfrom [lindex $path 0]]
+			set path [encoding convertfrom utf-8 [lindex $path 0]]
 		    }
 		    set path_attr_cache($attr,$path) $value
 		}