git-gui: Use gitattribute "encoding" for file content display

Most folks using git-gui on internationalized files have complained
that it doesn't recognize UTF-8 correctly.  In the past we have just
ignored the problem and showed the file contents as binary/US-ASCII,
which is wrong no matter how you look at it.

This really should be a per-file attribute, managed by .gitattributes,
so we now pull the "encoding" attribute data for the given path from
the .gitattributes (if available) and use that, falling back to UTF-8
if the attributes are unavailable, git-check-attr is broken, or an
encoding for this path not specified.

We apply the encoding anytime we show file content, which currently
is limited to only the diff viewer and the blame viewer.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>

4 files changed, 26 insertions, 4 deletions

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 000000000..f96112d47
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,3 @@
+*           encoding=US-ASCII
+git-gui.sh  encoding=UTF-8
+/po/*.po    encoding=UTF-8
diff --git a/git-gui.sh b/git-gui.sh
index cb0fcac99..4a762355d 100755
--- a/git-gui.sh
+++ b/git-gui.sh
@@ -521,6 +521,19 @@ proc kill_file_process {fd} {
 	}
 }
 
+proc gitattr {path attr default} {
+	if {[catch {set r [git check-attr $attr -- $path]}]} {
+		set r unspecified
+	} else {
+		set r [join [lrange [split $r :] 2 end] :]
+		regsub {^ } $r {} r
+	}
+	if {$r eq {unspecified}} {
+		return $default
+	}
+	return $r
+}
+
 proc sq {value} {
 	regsub -all ' $value "'\\''" value
 	return "'$value'"
diff --git a/lib/blame.tcl b/lib/blame.tcl
index 0d635cd3a..9464a599d 100644
--- a/lib/blame.tcl
+++ b/lib/blame.tcl
@@ -399,7 +399,10 @@ method _load {jump} {
 	} else {
 		set fd [git_read cat-file blob "$commit:$path"]
 	}
-	fconfigure $fd -blocking 0 -translation lf -encoding binary
+	fconfigure $fd \
+		-blocking 0 \
+		-translation lf \
+		-encoding [tcl_encoding [gitattr $path encoding UTF-8]]
 	fileevent $fd readable [cb _read_file $fd $jump]
 	set current_fd $fd
 }
diff --git a/lib/diff.tcl b/lib/diff.tcl
index a30c80a93..b0ecfbcb5 100644
--- a/lib/diff.tcl
+++ b/lib/diff.tcl
@@ -164,8 +164,11 @@ proc show_other_diff {path w m scroll_pos} {
 					set sz [string length $content]
 				}
 				file {
+					set enc [gitattr $path encoding UTF-8]
 					set fd [open $path r]
-					fconfigure $fd -eofchar {}
+					fconfigure $fd \
+						-eofchar {} \
+						-encoding [tcl_encoding $enc]
 					set content [read $fd $max_sz]
 					close $fd
 					set sz [file size $path]
@@ -279,8 +282,8 @@ proc start_show_diff {scroll_pos {add_opts {}}} {
 	set ::current_diff_inheader 1
 	fconfigure $fd \
 		-blocking 0 \
-		-encoding binary \
-		-translation binary
+		-encoding [tcl_encoding [gitattr $path encoding UTF-8]] \
+		-translation lf
 	fileevent $fd readable [list read_diff $fd $scroll_pos]
 }