enum rfc2047_type {
RFC2047_SUBJECT,
- RFC2047_ADDRESS,
+ RFC2047_ADDRESS
};
static int is_rfc2047_special(char ch, enum rfc2047_type type)
return strbuf_detach(&tmp, NULL);
}
-char *logmsg_reencode(const struct commit *commit,
- char **commit_encoding,
- const char *output_encoding)
+const char *logmsg_reencode(const struct commit *commit,
+ char **commit_encoding,
+ const char *output_encoding)
{
static const char *utf8 = "UTF-8";
const char *use_encoding;
char *encoding;
- char *msg = commit->buffer;
+ const char *msg = get_commit_buffer(commit, NULL);
char *out;
- if (!msg) {
- enum object_type type;
- unsigned long size;
-
- msg = read_sha1_file(commit->object.sha1, &type, &size);
- if (!msg)
- die("Cannot read commit object %s",
- sha1_to_hex(commit->object.sha1));
- if (type != OBJ_COMMIT)
- die("Expected commit for '%s', got %s",
- sha1_to_hex(commit->object.sha1), typename(type));
- }
-
if (!output_encoding || !*output_encoding) {
if (commit_encoding)
*commit_encoding =
* Otherwise, we still want to munge the encoding header in the
* result, which will be done by modifying the buffer. If we
* are using a fresh copy, we can reuse it. But if we are using
- * the cached copy from commit->buffer, we need to duplicate it
- * to avoid munging commit->buffer.
+ * the cached copy from get_commit_buffer, we need to duplicate it
+ * to avoid munging the cached copy.
*/
- out = msg;
- if (out == commit->buffer)
- out = xstrdup(out);
+ if (msg == get_cached_commit_buffer(commit, NULL))
+ out = xstrdup(msg);
+ else
+ out = (char *)msg;
}
else {
/*
* copy, we can free it.
*/
out = reencode_string(msg, output_encoding, use_encoding);
- if (out && msg != commit->buffer)
- free(msg);
+ if (out)
+ unuse_commit_buffer(commit, msg);
}
/*
return out ? out : msg;
}
-void logmsg_free(char *msg, const struct commit *commit)
-{
- if (msg != commit->buffer)
- free(msg);
-}
-
static int mailmap_name(const char **email, size_t *email_len,
const char **name, size_t *name_len)
{
struct signature_check signature_check;
enum flush_type flush_type;
enum trunc_type truncate;
- char *message;
+ const char *message;
char *commit_encoding;
size_t width, indent1, indent2;
int auto_color;
if (c->signature_check.key)
strbuf_addstr(sb, c->signature_check.key);
break;
+ default:
+ return 0;
}
return 2;
}
context.commit = commit;
context.pretty_ctx = pretty_ctx;
context.wrap_start = sb->len;
+ /*
+ * convert a commit message to UTF-8 first
+ * as far as 'format_commit_item' assumes it in UTF-8
+ */
context.message = logmsg_reencode(commit,
&context.commit_encoding,
- output_enc);
+ utf8);
strbuf_expand(sb, format, format_commit_item, &context);
rewrap_message_tail(sb, &context, 0, 0, 0);
+ /* then convert a commit message to an actual output encoding */
if (output_enc) {
if (same_encoding(utf8, output_enc))
output_enc = NULL;
}
free(context.commit_encoding);
- logmsg_free(context.message, commit);
+ unuse_commit_buffer(commit, context.message);
free(context.signature_check.gpg_output);
free(context.signature_check.signer);
}
unsigned long beginning_of_body;
int indent = 4;
const char *msg;
- char *reencoded;
+ const char *reencoded;
const char *encoding;
int need_8bit_cte = pp->need_8bit_cte;
if (pp->fmt == CMIT_FMT_EMAIL && sb->len <= beginning_of_body)
strbuf_addch(sb, '\n');
- logmsg_free(reencoded, commit);
+ unuse_commit_buffer(commit, reencoded);
}
void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit,
. "$TEST_DIRECTORY"/lib-terminal.sh
test_tick
+# Tested non-UTF-8 encoding
+test_encoding="ISO8859-1"
+
# String "added" in German
# (translated with Google Translate),
# encoded in UTF-8, used as a commit log message below.
-added=$(printf "added (hinzugef\303\274gt) foo")
-added_iso88591=$(echo "$added" | iconv -f utf-8 -t iso8859-1)
+added_utf8_part=$(printf "\303\274")
+added_utf8_part_iso88591=$(echo "$added_utf8_part" | iconv -f utf-8 -t $test_encoding)
+added=$(printf "added (hinzugef${added_utf8_part}gt) foo")
+added_iso88591=$(echo "$added" | iconv -f utf-8 -t $test_encoding)
# same but "changed"
-changed=$(printf "changed (ge\303\244ndert) foo")
-changed_iso88591=$(echo "$changed" | iconv -f utf-8 -t iso8859-1)
+changed_utf8_part=$(printf "\303\244")
+changed_utf8_part_iso88591=$(echo "$changed_utf8_part" | iconv -f utf-8 -t $test_encoding)
+changed=$(printf "changed (ge${changed_utf8_part}ndert) foo")
+changed_iso88591=$(echo "$changed" | iconv -f utf-8 -t $test_encoding)
+
+# Count of char to truncate
+# Number is chosen so, that non-ACSII characters
+# (see $added_utf8_part and $changed_utf8_part)
+# fall into truncated parts of appropriate words both from left and right
+truncate_count=20
test_expect_success 'setup' '
: >foo &&
git add foo &&
- git config i18n.commitEncoding iso8859-1 &&
+ git config i18n.commitEncoding $test_encoding &&
git commit -m "$added_iso88591" &&
head1=$(git rev-parse --verify HEAD) &&
head1_short=$(git rev-parse --verify --short $head1) &&
test_format encoding %e <<EOF
commit $head2
-iso8859-1
+$test_encoding
commit $head1
-iso8859-1
+$test_encoding
EOF
test_format subject %s <<EOF
$added
EOF
+test_format subject-truncated "%<($truncate_count,trunc)%s" <<EOF
+commit $head2
+changed (ge${changed_utf8_part}ndert)..
+commit $head1
+added (hinzugef${added_utf8_part}gt..
+EOF
+
test_format body %b <<EOF
commit $head2
commit $head1
)
'
-iconv -f utf-8 -t iso8859-1 > commit-msg <<EOF
+iconv -f utf-8 -t $test_encoding > commit-msg <<EOF
Test printing of complex bodies
This commit message is much longer than the others,
-and it will be encoded in iso8859-1. We should therefore
-include an iso8859 character: ¡bueno!
+and it will be encoded in $test_encoding. We should therefore
+include an ISO8859 character: ¡bueno!
EOF
test_expect_success 'setup complex body' '
- git config i18n.commitencoding iso8859-1 &&
+ git config i18n.commitencoding $test_encoding &&
echo change2 >foo && git commit -a -F commit-msg &&
head3=$(git rev-parse --verify HEAD) &&
head3_short=$(git rev-parse --short $head3)
test_format complex-encoding %e <<EOF
commit $head3
-iso8859-1
+$test_encoding
commit $head2
-iso8859-1
+$test_encoding
commit $head1
-iso8859-1
+$test_encoding
EOF
test_format complex-subject %s <<EOF
$added_iso88591
EOF
+test_format complex-subject-trunc "%<($truncate_count,trunc)%s" <<EOF
+commit $head3
+Test printing of c..
+commit $head2
+changed (ge${changed_utf8_part_iso88591}ndert)..
+commit $head1
+added (hinzugef${added_utf8_part_iso88591}gt..
+EOF
+
+test_format complex-subject-mtrunc "%<($truncate_count,mtrunc)%s" <<EOF
+commit $head3
+Test prin..ex bodies
+commit $head2
+changed (..dert) foo
+commit $head1
+added (hi..f${added_utf8_part_iso88591}gt) foo
+EOF
+
+test_format complex-subject-ltrunc "%<($truncate_count,ltrunc)%s" <<EOF
+commit $head3
+.. of complex bodies
+commit $head2
+..ged (ge${changed_utf8_part_iso88591}ndert) foo
+commit $head1
+.. (hinzugef${added_utf8_part_iso88591}gt) foo
+EOF
+
test_expect_success 'prepare expected messages (for test %b)' '
cat <<-EOF >expected.utf-8 &&
commit $head3
This commit message is much longer than the others,
- and it will be encoded in iso8859-1. We should therefore
- include an iso8859 character: ¡bueno!
+ and it will be encoded in $test_encoding. We should therefore
+ include an ISO8859 character: ¡bueno!
commit $head2
commit $head1
EOF
- iconv -f utf-8 -t iso8859-1 expected.utf-8 >expected.iso8859-1
+ iconv -f utf-8 -t $test_encoding expected.utf-8 >expected.ISO8859-1
'
-test_format complex-body %b <expected.iso8859-1
+test_format complex-body %b <expected.ISO8859-1
# Git uses i18n.commitEncoding if no i18n.logOutputEncoding set
# so unset i18n.commitEncoding to test encoding conversion
$added
EOF
+test_format complex-subject-commitencoding-unset-trunc "%<($truncate_count,trunc)%s" <<EOF
+commit $head3
+Test printing of c..
+commit $head2
+changed (ge${changed_utf8_part}ndert)..
+commit $head1
+added (hinzugef${added_utf8_part}gt..
+EOF
+
+test_format complex-subject-commitencoding-unset-mtrunc "%<($truncate_count,mtrunc)%s" <<EOF
+commit $head3
+Test prin..ex bodies
+commit $head2
+changed (..dert) foo
+commit $head1
+added (hi..f${added_utf8_part}gt) foo
+EOF
+
+test_format complex-subject-commitencoding-unset-ltrunc "%<($truncate_count,ltrunc)%s" <<EOF
+commit $head3
+.. of complex bodies
+commit $head2
+..ged (ge${changed_utf8_part}ndert) foo
+commit $head1
+.. (hinzugef${added_utf8_part}gt) foo
+EOF
+
test_format complex-body-commitencoding-unset %b <expected.utf-8
test_expect_success '%x00 shows NUL' '
test_cmp expect actual
'
+ test_expect_success 'unused %G placeholders are passed through' '
+ echo "%GX %G" >expect &&
+ git log -1 --format="%GX %G" >actual &&
+ test_cmp expect actual
+ '
+
test_done