gitk: Enhance file encoding support
This allows the encoding to be specified for file contents and used when displaying files and diffs in the bottom-left pane. When displaying diffs, the encoding for each diff hunk is that for the file that the diff hunk is from, so it can change through the course of the diff. The encoding for file contents is determined as follows: - 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. Note: Since git-check-attr does not provide support for reading attributes from trees, attribute lookup is done using files from the working directory. This also extends the range of supported encoding names, adding ShiftJIS and Shift-JIS as aliases for Shift_JIS, and allowing cp-*, cp_*, ibm-*, ibm_*, jis-* and jis_* as aliases for cp*, ibm* and jis* respectively. This also fixes some bugs in handling of non-ASCII filenames. Core git apparently supports only locale-encoded filenames, so processing is done using the system encoding. Signed-off-by: Alexander Gavrilov <angavrilov@gmail.com> Tested-by: Johannes Sixt <johannes.sixt@telecom.at> Signed-off-by: Paul Mackerras <paulus@samba.org>
Alexander Gavrilov committed
Oct 13, 2008 at 12:12 UTC
09c7029dfa58748268a6306bfe764456a65a22bf
1 file changed
+63
-11
gitk
+63
-11
@@ -6229,7 +6229,7 @@ proc gettree {id} {
6229
set treepending $id
6230
set treefilelist($id) {}
6231
set treeidlist($id) {}
6232
- fconfigure $gtf -blocking 0
6232
+ fconfigure $gtf -blocking 0 -encoding binary
6233
filerun $gtf [list gettreeline $gtf $id]
6234
}
6235
} else {
@@ -6251,11 +6251,12 @@ proc gettreeline {gtf id} {
6251
set line [string range $line 0 [expr {$i-1}]]
6252
if {$diffids ne $nullid2 && [lindex $line 1] ne "blob"} continue
6253
set sha1 [lindex $line 2]
6254
- if {[string index $fname 0] eq "\""} {
6255
- set fname [lindex $fname 0]
6256
- }
6254
lappend treeidlist($id) $sha1
6255
}
6256
+ if {[string index $fname 0] eq "\""} {
6257
+ set fname [lindex $fname 0]
6258
+ }
6259
+ set fname [encoding convertfrom $fname]
6260
lappend treefilelist($id) $fname
6261
}
6262
if {![eof $gtf]} {
@@ -6296,7 +6297,7 @@ proc showfile {f} {
6297
return
6298
}
6299
}
6299
- fconfigure $bf -blocking 0
6300
+ fconfigure $bf -blocking 0 -encoding [get_path_encoding $f]
6301
filerun $bf [list getblobline $bf $diffids]
6302
$ctext config -state normal
6303
clear_ctext $commentend
@@ -6334,6 +6335,7 @@ proc mergediff {id} {
6335
global diffids
6336
global parents
6337
global diffcontext
6338
+ global diffencoding
6339
global limitdiffs vfilelimit curview
6340
6341
set diffmergeid $id
@@ -6347,9 +6349,10 @@ proc mergediff {id} {
6349
error_popup "[mc "Error getting merge diffs:"] $err"
6350
return
6351
}
6350
- fconfigure $mdf -blocking 0
6352
+ fconfigure $mdf -blocking 0 -encoding binary
6353
set mdifffd($id) $mdf
6354
set np [llength $parents($curview,$id)]
6355
+ set diffencoding [get_path_encoding {}]
6356
settabs $np
6357
filerun $mdf [list getmergediffline $mdf $id $np]
6358
}
@@ -6357,6 +6360,7 @@ proc mergediff {id} {
6360
proc getmergediffline {mdf id np} {
6361
global diffmergeid ctext cflist mergemax
6362
global difffilestart mdifffd
6363
+ global diffencoding
6364
6365
$ctext conf -state normal
6366
set nr 0
@@ -6368,18 +6372,22 @@ proc getmergediffline {mdf id np} {
6372
}
6373
if {[regexp {^diff --cc (.*)} $line match fname]} {
6374
# start of a new file
6375
+ set fname [encoding convertfrom $fname]
6376
$ctext insert end "\n"
6377
set here [$ctext index "end - 1c"]
6378
lappend difffilestart $here
6379
add_flist [list $fname]
6380
+ set diffencoding [get_path_encoding $fname]
6381
set l [expr {(78 - [string length $fname]) / 2}]
6382
set pad [string range "----------------------------------------" 1 $l]
6383
$ctext insert end "$pad $fname $pad\n" filesep
6384
} elseif {[regexp {^@@} $line]} {
6385
+ set line [encoding convertfrom $diffencoding $line]
6386
$ctext insert end "$line\n" hunksep
6387
} elseif {[regexp {^[0-9a-f]{40}$} $line] || [regexp {^index} $line]} {
6388
# do nothing
6389
} else {
6390
+ set line [encoding convertfrom $diffencoding $line]
6391
# parse the prefix - one ' ', '-' or '+' for each parent
6392
set spaces {}
6393
set minuses {}
@@ -6514,7 +6522,7 @@ proc gettreediffs {ids} {
6522
6523
set treepending $ids
6524
set treediff {}
6517
- fconfigure $gdtf -blocking 0
6525
+ fconfigure $gdtf -blocking 0 -encoding binary
6526
filerun $gdtf [list gettreediffline $gdtf $ids]
6527
}
6528
@@ -6530,6 +6538,7 @@ proc gettreediffline {gdtf ids} {
6538
if {[string index $file 0] eq "\""} {
6539
set file [lindex $file 0]
6540
}
6541
+ set file [encoding convertfrom $file]
6542
lappend treediff $file
6543
}
6544
}
@@ -6587,6 +6596,7 @@ proc getblobdiffs {ids} {
6596
global diffcontext
6597
global ignorespace
6598
global limitdiffs vfilelimit curview
6599
+ global diffencoding
6600
6601
set cmd [diffcmd $ids "-p -C --no-commit-id -U$diffcontext"]
6602
if {$ignorespace} {
@@ -6600,7 +6610,8 @@ proc getblobdiffs {ids} {
6610
return
6611
}
6612
set diffinhdr 0
6603
- fconfigure $bdf -blocking 0
6613
+ set diffencoding [get_path_encoding {}]
6614
+ fconfigure $bdf -blocking 0 -encoding binary
6615
set blobdifffd($ids) $bdf
6616
filerun $bdf [list getblobdiffline $bdf $diffids]
6617
}
@@ -6634,6 +6645,7 @@ proc getblobdiffline {bdf ids} {
6645
global diffids blobdifffd ctext curdiffstart
6646
global diffnexthead diffnextnote difffilestart
6647
global diffinhdr treediffs
6648
+ global diffencoding
6649
6650
set nr 0
6651
$ctext conf -state normal
@@ -6671,10 +6683,13 @@ proc getblobdiffline {bdf ids} {
6683
} else {
6684
set fname [string range $line 2 [expr {$i - 1}]]
6685
}
6686
+ set fname [encoding convertfrom $fname]
6687
+ set diffencoding [get_path_encoding $fname]
6688
makediffhdr $fname $ids
6689
6690
} elseif {[regexp {^@@ -([0-9]+)(,[0-9]+)? \+([0-9]+)(,[0-9]+)? @@(.*)} \
6691
$line match f1l f1c f2l f2c rest]} {
6692
+ set line [encoding convertfrom $diffencoding $line]
6693
$ctext insert end "$line\n" hunksep
6694
set diffinhdr 0
6695
@@ -6684,6 +6699,7 @@ proc getblobdiffline {bdf ids} {
6699
if {[string index $fname 0] eq "\""} {
6700
set fname [lindex $fname 0]
6701
}
6702
+ set fname [encoding convertfrom $fname]
6703
set i [lsearch -exact $treediffs($ids) $fname]
6704
if {$i >= 0} {
6705
setinlist difffilestart $i $curdiffstart
@@ -6694,6 +6710,8 @@ proc getblobdiffline {bdf ids} {
6710
if {[string index $fname 0] eq "\""} {
6711
set fname [lindex $fname 0]
6712
}
6713
+ set fname [encoding convertfrom $fname]
6714
+ set diffencoding [get_path_encoding $fname]
6715
makediffhdr $fname $ids
6716
} elseif {[string compare -length 3 $line "---"] == 0} {
6717
# do nothing
@@ -6705,6 +6723,7 @@ proc getblobdiffline {bdf ids} {
6723
$ctext insert end "$line\n" filesep
6724
6725
} else {
6726
+ set line [encoding convertfrom $diffencoding $line]
6727
set x [string range $line 0 0]
6728
if {$x == "-" || $x == "+"} {
6729
set tag [expr {$x == "+"}]
@@ -9727,7 +9746,7 @@ set encoding_aliases {
9746
{ ISO-8859-16 iso-ir-226 ISO_8859-16:2001 ISO_8859-16 latin10 l10 }
9747
{ GBK CP936 MS936 windows-936 }
9748
{ JIS_Encoding csJISEncoding }
9730
- { Shift_JIS MS_Kanji csShiftJIS }
9749
+ { Shift_JIS MS_Kanji csShiftJIS ShiftJIS Shift-JIS }
9750
{ Extended_UNIX_Code_Packed_Format_for_Japanese csEUCPkdFmtJapanese
9751
EUC-JP }
9752
{ Extended_UNIX_Code_Fixed_Width_for_Japanese csEUCFixWidJapanese }
@@ -9769,7 +9788,7 @@ proc tcl_encoding {enc} {
9788
set i [lsearch -exact $lcnames $enc]
9789
if {$i < 0} {
9790
# look for "isonnn" instead of "iso-nnn" or "iso_nnn"
9772
- if {[regsub {^iso[-_]} $enc iso encx]} {
9791
+ if {[regsub {^(iso|cp|ibm|jis)[-_]} $enc {\1} encx]} {
9792
set i [lsearch -exact $lcnames $encx]
9793
}
9794
}
@@ -9781,7 +9800,7 @@ proc tcl_encoding {enc} {
9800
foreach e $ll {
9801
set i [lsearch -exact $lcnames $e]
9802
if {$i < 0} {
9784
- if {[regsub {^iso[-_]} $e iso ex]} {
9803
+ if {[regsub {^(iso|cp|ibm|jis)[-_]} $e {\1} ex]} {
9804
set i [lsearch -exact $lcnames $ex]
9805
}
9806
}
@@ -9796,6 +9815,34 @@ proc tcl_encoding {enc} {
9815
return {}
9816
}
9817
9818
+proc gitattr {path attr default} {
9819
+ if {[catch {set r [exec git check-attr $attr -- $path]}]} {
9820
+ set r unspecified
9821
+ } else {
9822
+ set r [join [lrange [split $r :] 2 end] :]
9823
+ regsub {^ } $r {} r
9824
+ }
9825
+ if {$r eq {unspecified}} {
9826
+ return $default
9827
+ }
9828
+ return $r
9829
+}
9830
+
9831
+proc get_path_encoding {path} {
9832
+ global gui_encoding
9833
+ set tcl_enc [tcl_encoding $gui_encoding]
9834
+ if {$tcl_enc eq {}} {
9835
+ set tcl_enc [encoding system]
9836
+ }
9837
+ if {$path ne {}} {
9838
+ set enc2 [tcl_encoding [gitattr $path encoding $tcl_enc]]
9839
+ if {$enc2 ne {}} {
9840
+ set tcl_enc $enc2
9841
+ }
9842
+ }
9843
+ return $tcl_enc
9844
+}
9845
+
9846
# First check that Tcl/Tk is recent enough
9847
if {[catch {package require Tk 8.4} err]} {
9848
show_error {} . [mc "Sorry, gitk cannot run with this version of Tcl/Tk.\n\
@@ -9818,6 +9865,11 @@ if {$tclencoding == {}} {
9865
puts stderr "Warning: encoding $gitencoding is not supported by Tcl/Tk"
9866
}
9867
9868
+set gui_encoding [encoding system]
9869
+catch {
9870
+ set gui_encoding [exec git config --get gui.encoding]
9871
+}
9872
+
9873
set mainfont {Helvetica 9}
9874
set textfont {Courier 9}
9875
set uifont {Helvetica 9 bold}