diff.c: use utf8_strwidth() to count display width

When unicode filenames (encoded in UTF-8) are used, the visible width
on the screen is not the same as strlen().

For example, `git log --stat` may produce an output like this:

[snip the header]

 Arger.txt  | 1 +
 Ärger.txt | 1 +
 2 files changed, 2 insertions(+)

A side note: the original report was about cyrillic filenames.
After some investigations it turned out that
a) This is not a problem with "ambiguous characters" in unicode
b) The same problem exists for all unicode code points (so we
  can use Latin based Umlauts for demonstrations below)

The 'Ä' takes the same space on the screen as the 'A'.
But needs one more byte in memory, so the the `git log --stat` output
for "Arger.txt" (!) gets mis-aligned:
The maximum length is derived from "Ärger.txt", 10 bytes in memory,
9 positions on the screen. That is why "Arger.txt" gets one extra ' '
for aligment, it needs 9 bytes in memory.
If there was a file "Ö", it would be correctly aligned by chance,
but "Öhö" would not.

The solution is of course, to use utf8_strwidth() instead of strlen()
when dealing with the width on screen.

And then there is another problem, code like this:
strbuf_addf(&out, "%-*s", len, name);
(or using the underlying snprintf() function) does not align the
buffer to a minimum of len measured in screen-width, but uses the
memory count.

One could be tempted to wish that snprintf() was UTF-8 aware.
That doesn't seem to be the case anywhere (tested on Linux and Mac),
probably snprintf() uses the "bytes in memory"/strlen() approach to be
compatible with older versions and this will never change.

The basic idea is to change code in diff.c like this
strbuf_addf(&out, "%-*s", len, name);

into something like this:
int padding = len - utf8_strwidth(name);
if (padding < 0)
	padding = 0;
strbuf_addf(&out, " %s%*s", name, padding, "");

The real change is slighty bigger, as it, as well, integrates two calls
of strbuf_addf() into one.

Tests:
Two things need to be tested:
 - The calculation of the maximum width
 - The calculation of padding

The name "textfile" is changed into "tëxtfilë", both have a width of 8.
If strlen() was used, to get the maximum width, the shorter "binfile" would
have been mis-aligned:
 binfile    | [snip]
 tëxtfilë | [snip]

If only "binfile" would be renamed into "binfilë":
 binfilë | [snip]
 textfile | [snip]

In order to verify that the width is calculated correctly everywhere,
"binfile" is renamed into "binfilë", giving 1 bytes more in strlen()
"tëxtfile" is renamed into "tëxtfilë", 2 byte more in strlen().

The updated t4012-diff-binary.sh checks the correct aligment:
 binfilë  | [snip]
 tëxtfilë | [snip]

Reported-by: Alexander Meshcheryakov <alexander.s.m@gmail.com>
Helped-by: Johannes Schindelin <Johannes.Schindelin@gmx.de>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/diff.c b/diff.c
index ef7159968b68c43c361a4cacc4558e14fe82fd4f..2751cae1315a17a4de692a7a6f8a55a0ffb032f1 100644 (file)
--- a/diff.c
+++ b/diff.c
@@ -2622,7 +2622,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                        continue;
                }
                fill_print_name(file);
-               len = strlen(file->print_name);
+               len = utf8_strwidth(file->print_name);
                if (max_len < len)
                        max_len = len;
 
@@ -2736,7 +2736,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                char *name = file->print_name;
                uintmax_t added = file->added;
                uintmax_t deleted = file->deleted;
-               int name_len;
+               int name_len, padding;
 
                if (!file->is_interesting && (added + deleted == 0))
                        continue;
@@ -2745,7 +2745,7 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                 * "scale" the filename
                 */
                len = name_width;
-               name_len = strlen(name);
+               name_len = utf8_strwidth(name);
                if (name_width < name_len) {
                        char *slash;
                        prefix = "...";
@@ -2755,10 +2755,14 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                        if (slash)
                                name = slash;
                }
+               padding = len - utf8_strwidth(name);
+               if (padding < 0)
+                       padding = 0;
 
                if (file->is_binary) {
-                       strbuf_addf(&out, " %s%-*s |", prefix, len, name);
-                       strbuf_addf(&out, " %*s", number_width, "Bin");
+                       strbuf_addf(&out, " %s%s%*s | %*s",
+                                   prefix, name, padding, "",
+                                   number_width, "Bin");
                        if (!added && !deleted) {
                                strbuf_addch(&out, '\n');
                                emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
@@ -2778,8 +2782,9 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                        continue;
                }
                else if (file->is_unmerged) {
-                       strbuf_addf(&out, " %s%-*s |", prefix, len, name);
-                       strbuf_addstr(&out, " Unmerged\n");
+                       strbuf_addf(&out, " %s%s%*s | %*s",
+                                   prefix, name, padding, "",
+                                   number_width, "Unmerged");
                        emit_diff_symbol(options, DIFF_SYMBOL_STATS_LINE,
                                         out.buf, out.len, 0);
                        strbuf_reset(&out);
@@ -2805,10 +2810,10 @@ static void show_stats(struct diffstat_t *data, struct diff_options *options)
                                add = total - del;
                        }
                }
-               strbuf_addf(&out, " %s%-*s |", prefix, len, name);
-               strbuf_addf(&out, " %*"PRIuMAX"%s",
-                       number_width, added + deleted,
-                       added + deleted ? " " : "");
+               strbuf_addf(&out, " %s%s%*s | %*"PRIuMAX"%s",
+                           prefix, name, padding, "",
+                           number_width, added + deleted,
+                           added + deleted ? " " : "");
                show_graph(&out, '+', add, add_c, reset);
                show_graph(&out, '-', del, del_c, reset);
                strbuf_addch(&out, '\n');

diff --git a/t/t4012-diff-binary.sh b/t/t4012-diff-binary.sh
index c509143c8141e0c4c2f2696080922f339afd432c..c64d9d2f405e1e43a2247d91ca0a1a35af7fbad4 100755 (executable)
--- a/t/t4012-diff-binary.sh
+++ b/t/t4012-diff-binary.sh
@@ -113,20 +113,20 @@ test_expect_success 'diff --no-index with binary creation' '
 '
 
 cat >expect <<EOF
- binfile  |   Bin 0 -> 1026 bytes
- textfile | 10000 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+ binfilë  |   Bin 0 -> 1026 bytes
+ tëxtfilë | 10000 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 EOF
 
 test_expect_success 'diff --stat with binary files and big change count' '
-       printf "\01\00%1024d" 1 >binfile &&
-       git add binfile &&
+       printf "\01\00%1024d" 1 >binfilë &&
+       git add binfilë &&
        i=0 &&
        while test $i -lt 10000; do
                echo $i &&
                i=$(($i + 1)) || return 1
-       done >textfile &&
-       git add textfile &&
-       git diff --cached --stat binfile textfile >output &&
+       done >tëxtfilë &&
+       git add tëxtfilë &&
+       git -c core.quotepath=false diff --cached --stat binfilë tëxtfilë >output &&
        grep " | " output >actual &&
        test_cmp expect actual
 '