[PATCH (GITK) v2 1/4] gitk: Port new encoding logic from git-gui.

[Alexander Gavrilov <angavrilov@gmail.com>]

Recently handling of file encodings in GIT-GUI has
been greatly enhanced. It now follows these rules:

- File encoding defaults to the system encoding.
- It can be overridden by setting the gui.encoding option.
- Finally, the 'encoding' attribute is checked on
  per-file basis; it has the last word.

This patch inserts copies of git-gui functions necessary
for supporting this into gitk. The following patch will
connect them to the rest of the code.

Note: Since git-check-attr does not provide support for
reading attributes from trees, attribute lookup is done
using files from the working directory.

It also extends the range of supported encoding
names, to match changes in git-gui.

Signed-off-by: Alexander Gavrilov <angavrilov@gmail.com>
Tested-by: Johannes Sixt <johannes.sixt@telecom.at>
---
 gitk |   50 +++++++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/gitk b/gitk
index 546627f..b210f79 100755
--- a/gitk
+++ b/gitk
@@ -9726,7 +9726,7 @@ set encoding_aliases {
     { ISO-8859-16 iso-ir-226 ISO_8859-16:2001 ISO_8859-16 latin10 l10 }
     { GBK CP936 MS936 windows-936 }
     { JIS_Encoding csJISEncoding }
-    { Shift_JIS MS_Kanji csShiftJIS }
+    { Shift_JIS MS_Kanji csShiftJIS ShiftJIS Shift-JIS }
     { Extended_UNIX_Code_Packed_Format_for_Japanese csEUCPkdFmtJapanese
       EUC-JP }
     { Extended_UNIX_Code_Fixed_Width_for_Japanese csEUCFixWidJapanese }
@@ -9768,7 +9768,7 @@ proc tcl_encoding {enc} {
     set i [lsearch -exact $lcnames $enc]
     if {$i < 0} {
 	# look for "isonnn" instead of "iso-nnn" or "iso_nnn"
-	if {[regsub {^iso[-_]} $enc iso encx]} {
+	if {[regsub {^(iso|cp|ibm|jis)[-_]} $enc {\1} encx]} {
 	    set i [lsearch -exact $lcnames $encx]
 	}
     }
@@ -9780,7 +9780,7 @@ proc tcl_encoding {enc} {
 	    foreach e $ll {
 		set i [lsearch -exact $lcnames $e]
 		if {$i < 0} {
-		    if {[regsub {^iso[-_]} $e iso ex]} {
+		    if {[regsub {^(iso|cp|ibm|jis)[-_]} $e {\1} ex]} {
 			set i [lsearch -exact $lcnames $ex]
 		    }
 		}
@@ -9795,6 +9795,45 @@ proc tcl_encoding {enc} {
     return {}
 }
 
+proc gitattr {path attr default} {
+	if {[catch {set r [exec 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 get_path_encoding {path} {
+	global gui_encoding
+	set tcl_enc [tcl_encoding $gui_encoding]
+	if {$tcl_enc eq {}} {
+		set tcl_enc [encoding system]
+	}
+	if {$path ne {}} {
+		set enc2 [tcl_encoding [gitattr $path encoding $tcl_enc]]
+		if {$enc2 ne {}} {
+			set tcl_enc $enc2
+		}
+	}
+	return $tcl_enc
+}
+
+proc get_cached_encoding {path} {
+	global path_encoding_cache
+	if {[info exists path_encoding_cache($path)]} {
+		return $path_encoding_cache($path)
+	} else {
+		set enc [get_path_encoding $path]
+		set path_encoding_cache($path) $enc
+		return $enc
+	}
+}
+
 # First check that Tcl/Tk is recent enough
 if {[catch {package require Tk 8.4} err]} {
     show_error {} . [mc "Sorry, gitk cannot run with this version of Tcl/Tk.\n\
@@ -9817,6 +9856,11 @@ if {$tclencoding == {}} {
     puts stderr "Warning: encoding $gitencoding is not supported by Tcl/Tk"
 }
 
+set gui_encoding [encoding system]
+catch {
+	set gui_encoding [exec git config --get gui.encoding]
+}
+
 set mainfont {Helvetica 9}
 set textfont {Courier 9}
 set uifont {Helvetica 9 bold}
-- 
1.6.0.20.g6148bc