Merge branch 'jc/int'

* jc/int:
  More tests in t3901.
  Consistent message encoding while reusing log from an existing commit.
  t3901: test "format-patch | am" pipe with i18n
  Use log output encoding in --pretty=email headers.

6 files changed, 333 insertions, 33 deletions

diff --git a/commit.c b/commit.c
index 496d37a..9b2b842 100644
--- a/commit.c
+++ b/commit.c
@@ -464,20 +464,29 @@ static int get_one_line(const char *msg, unsigned long len)
 	return ret;
 }
 
+/* High bit set, or ISO-2022-INT */
+static int non_ascii(int ch)
+{
+	ch = (ch & 0xff);
+	return ((ch & 0x80) || (ch == 0x1b));
+}
+
 static int is_rfc2047_special(char ch)
 {
-	return ((ch & 0x80) || (ch == '=') || (ch == '?') || (ch == '_'));
+	return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
 }
 
-static int add_rfc2047(char *buf, const char *line, int len)
+static int add_rfc2047(char *buf, const char *line, int len,
+		       const char *encoding)
 {
 	char *bp = buf;
 	int i, needquote;
-	static const char q_utf8[] = "=?utf-8?q?";
+	char q_encoding[128];
+	const char *q_encoding_fmt = "=?%s?q?";
 
 	for (i = needquote = 0; !needquote && i < len; i++) {
-		unsigned ch = line[i];
-		if (ch & 0x80)
+		int ch = line[i];
+		if (non_ascii(ch))
 			needquote++;
 		if ((i + 1 < len) &&
 		    (ch == '=' && line[i+1] == '?'))
@@ -486,8 +495,11 @@ static int add_rfc2047(char *buf, const char *line, int len)
 	if (!needquote)
 		return sprintf(buf, "%.*s", len, line);
 
-	memcpy(bp, q_utf8, sizeof(q_utf8)-1);
-	bp += sizeof(q_utf8)-1;
+	i = snprintf(q_encoding, sizeof(q_encoding), q_encoding_fmt, encoding);
+	if (sizeof(q_encoding) < i)
+		die("Insanely long encoding name %s", encoding);
+	memcpy(bp, q_encoding, i);
+	bp += i;
 	for (i = 0; i < len; i++) {
 		unsigned ch = line[i] & 0xFF;
 		if (is_rfc2047_special(ch)) {
@@ -505,7 +517,8 @@ static int add_rfc2047(char *buf, const char *line, int len)
 }
 
 static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf,
-			 const char *line, int relative_date)
+			 const char *line, int relative_date,
+			 const char *encoding)
 {
 	char *date;
 	int namelen;
@@ -533,7 +546,8 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf,
 		filler = "";
 		strcpy(buf, "From: ");
 		ret = strlen(buf);
-		ret += add_rfc2047(buf + ret, line, display_name_length);
+		ret += add_rfc2047(buf + ret, line, display_name_length,
+				   encoding);
 		memcpy(buf + ret, name_tail, namelen - display_name_length);
 		ret += namelen - display_name_length;
 		buf[ret++] = '\n';
@@ -668,21 +682,18 @@ static char *replace_encoding_header(char *buf, char *encoding)
 	return buf;
 }
 
-static char *logmsg_reencode(const struct commit *commit)
+static char *logmsg_reencode(const struct commit *commit,
+			     char *output_encoding)
 {
 	char *encoding;
 	char *out;
-	char *output_encoding = (git_log_output_encoding
-				 ? git_log_output_encoding
-				 : git_commit_encoding);
+	char *utf8 = "utf-8";
 
-	if (!output_encoding)
-		output_encoding = "utf-8";
-	else if (!*output_encoding)
+	if (!*output_encoding)
 		return NULL;
 	encoding = get_header(commit, "encoding");
 	if (!encoding)
-		return NULL;
+		encoding = utf8;
 	if (!strcmp(encoding, output_encoding))
 		out = strdup(commit->buffer);
 	else
@@ -691,7 +702,8 @@ static char *logmsg_reencode(const struct commit *commit)
 	if (out)
 		out = replace_encoding_header(out, output_encoding);
 
-	free(encoding);
+	if (encoding != utf8)
+		free(encoding);
 	if (!out)
 		return NULL;
 	return out;
@@ -711,8 +723,15 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 	int parents_shown = 0;
 	const char *msg = commit->buffer;
 	int plain_non_ascii = 0;
-	char *reencoded = logmsg_reencode(commit);
+	char *reencoded;
+	char *encoding;
 
+	encoding = (git_log_output_encoding
+		    ? git_log_output_encoding
+		    : git_commit_encoding);
+	if (!encoding)
+		encoding = "utf-8";
+	reencoded = logmsg_reencode(commit, encoding);
 	if (reencoded)
 		msg = reencoded;
 
@@ -738,7 +757,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 				    i + 1 < len && msg[i+1] == '\n')
 					in_body = 1;
 			}
-			else if (ch & 0x80) {
+			else if (non_ascii(ch)) {
 				plain_non_ascii = 1;
 				break;
 			}
@@ -797,13 +816,15 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 				offset += add_user_info("Author", fmt,
 							buf + offset,
 							line + 7,
-							relative_date);
+							relative_date,
+							encoding);
 			if (!memcmp(line, "committer ", 10) &&
 			    (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER))
 				offset += add_user_info("Commit", fmt,
 							buf + offset,
 							line + 10,
-							relative_date);
+							relative_date,
+							encoding);
 			continue;
 		}
 
@@ -826,7 +847,8 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 			int slen = strlen(subject);
 			memcpy(buf + offset, subject, slen);
 			offset += slen;
-			offset += add_rfc2047(buf + offset, line, linelen);
+			offset += add_rfc2047(buf + offset, line, linelen,
+					      encoding);
 		}
 		else {
 			memset(buf + offset, ' ', indent);
@@ -837,11 +859,17 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 		if (fmt == CMIT_FMT_ONELINE)
 			break;
 		if (subject && plain_non_ascii) {
-			static const char header[] =
-				"Content-Type: text/plain; charset=UTF-8\n"
+			int sz;
+			char header[512];
+			const char *header_fmt =
+				"Content-Type: text/plain; charset=%s\n"
 				"Content-Transfer-Encoding: 8bit\n";
-			memcpy(buf + offset, header, sizeof(header)-1);
-			offset += sizeof(header)-1;
+			sz = snprintf(header, sizeof(header), header_fmt,
+				      encoding);
+			if (sizeof(header) < sz)
+				die("Encoding name %s too long", encoding);
+			memcpy(buf + offset, header, sz);
+			offset += sz;
 		}
 		if (after_subject) {
 			int slen = strlen(after_subject);
diff --git a/git-commit.sh b/git-commit.sh
index 9fdf234..e23918c 100755
--- a/git-commit.sh
+++ b/git-commit.sh
@@ -429,7 +429,9 @@ then
 	fi
 elif test "$use_commit" != ""
 then
-	git-cat-file commit "$use_commit" | sed -e '1,/^$/d'
+	encoding=$(git repo-config i18n.commitencoding || echo UTF-8)
+	git show -s --pretty=raw --encoding="$encoding" "$use_commit" |
+	sed -e '1,/^$/d' -e 's/^    //'
 elif test -f "$GIT_DIR/MERGE_MSG"
 then
 	cat "$GIT_DIR/MERGE_MSG"
@@ -491,7 +493,8 @@ then
 		q
 	}
 	'
-	set_author_env=`git-cat-file commit "$use_commit" |
+	encoding=$(git repo-config i18n.commitencoding || echo UTF-8)
+	set_author_env=`git show -s --pretty=raw --encoding="$encoding" "$use_commit" |
 	LANG=C LC_ALL=C sed -ne "$pick_author_script"`
 	eval "$set_author_env"
 	export GIT_AUTHOR_NAME
diff --git a/git-revert.sh b/git-revert.sh
index 224e654..71cbcbc 100755
--- a/git-revert.sh
+++ b/git-revert.sh
@@ -81,6 +81,8 @@ prev=$(git-rev-parse --verify "$commit^1" 2>/dev/null) ||
 git-rev-parse --verify "$commit^2" >/dev/null 2>&1 &&
 	die "Cannot run $me a multi-parent commit."
 
+encoding=$(git repo-config i18n.commitencoding || echo UTF-8)
+
 # "commit" is an existing commit.  We would want to apply
 # the difference it introduces since its first parent "prev"
 # on top of the current HEAD if we are cherry-pick.  Or the
@@ -88,10 +90,11 @@ git-rev-parse --verify "$commit^2" >/dev/null 2>&1 &&
 
 case "$me" in
 revert)
-	git-rev-list --pretty=oneline --max-count=1 $commit |
+	git show -s --pretty=oneline --encoding="$encoding" $commit |
 	sed -e '
 		s/^[^ ]* /Revert "/
-		s/$/"/'
+		s/$/"/
+	'
 	echo
 	echo "This reverts commit $commit."
 	test "$rev" = "$commit" ||
@@ -120,14 +123,17 @@ cherry-pick)
 
 		q
 	}'
-	set_author_env=`git-cat-file commit "$commit" |
+
+	logmsg=`git show -s --pretty=raw --encoding="$encoding" "$commit"`
+	set_author_env=`echo "$logmsg" |
 	LANG=C LC_ALL=C sed -ne "$pick_author_script"`
 	eval "$set_author_env"
 	export GIT_AUTHOR_NAME
 	export GIT_AUTHOR_EMAIL
 	export GIT_AUTHOR_DATE
 
-	git-cat-file commit $commit | sed -e '1,/^$/d'
+	echo "$logmsg" |
+	sed -e '1,/^$/d' -e 's/^    //'
 	case "$replay" in
 	'')
 		echo "(cherry picked from commit $commit)"
diff --git a/t/t3901-8859-1.txt b/t/t3901-8859-1.txt
new file mode 100755
index 0000000..38c21a6
--- /dev/null
+++ b/t/t3901-8859-1.txt
@@ -0,0 +1,4 @@
+: to be sourced in t3901 -- this is latin-1
+GIT_AUTHOR_NAME="Αιν σϊ" &&
+GIT_COMMITTER_NAME=$GIT_AUTHOR_NAME &&
+export GIT_AUTHOR_NAME GIT_COMMITTER_NAME
diff --git a/t/t3901-i18n-patch.sh b/t/t3901-i18n-patch.sh
new file mode 100755
index 0000000..eda0e2d
--- /dev/null
+++ b/t/t3901-i18n-patch.sh
@@ -0,0 +1,255 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Junio C Hamano
+#
+
+test_description='i18n settings and format-patch | am pipe'
+
+. ./test-lib.sh
+
+check_encoding () {
+	# Make sure characters are not corrupted
+	cnt="$1" header="$2" i=1 j=0 bad=0
+	while test "$i" -le $cnt
+	do
+		git format-patch --encoding=UTF-8 --stdout HEAD~$i..HEAD~$j |
+		grep "^From: =?UTF-8?q?=C3=81=C3=A9=C3=AD_=C3=B3=C3=BA?=" &&
+		git-cat-file commit HEAD~$j |
+		case "$header" in
+		8859)
+			grep "^encoding ISO-8859-1" ;;
+		*)
+			! grep "^encoding ISO-8859-1" ;;
+		esac || {
+			bad=1
+			break
+		}
+		j=$i
+		i=$(($i+1))
+	done
+	(exit $bad)
+}
+
+test_expect_success setup '
+	git-repo-config i18n.commitencoding UTF-8 &&
+
+	# use UTF-8 in author and committer name to match the
+	# i18n.commitencoding settings
+	. ../t3901-utf8.txt &&
+
+	test_tick &&
+	echo "$GIT_AUTHOR_NAME" >mine &&
+	git add mine &&
+	git commit -s -m "Initial commit" &&
+
+	test_tick &&
+	echo Hello world >mine &&
+	git add mine &&
+	git commit -s -m "Second on main" &&
+
+	# the first commit on the side branch is UTF-8
+	test_tick &&
+	git checkout -b side master^ &&
+	echo Another file >yours &&
+	git add yours &&
+	git commit -s -m "Second on side" &&
+
+	# the second one on the side branch is ISO-8859-1
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	# use author and committer name in ISO-8859-1 to match it.
+	. ../t3901-8859-1.txt &&
+	test_tick &&
+	echo Yet another >theirs &&
+	git add theirs &&
+	git commit -s -m "Third on side" &&
+
+	# Back to default
+	git-repo-config i18n.commitencoding UTF-8
+'
+
+test_expect_success 'format-patch output (ISO-8859-1)' '
+	git-repo-config i18n.logoutputencoding ISO-8859-1 &&
+
+	git format-patch --stdout master..HEAD^ >out-l1 &&
+	git format-patch --stdout HEAD^ >out-l2 &&
+	grep "^Content-Type: text/plain; charset=ISO-8859-1" out-l1 &&
+	grep "^From: =?ISO-8859-1?q?=C1=E9=ED_=F3=FA?=" out-l1 &&
+	grep "^Content-Type: text/plain; charset=ISO-8859-1" out-l2 &&
+	grep "^From: =?ISO-8859-1?q?=C1=E9=ED_=F3=FA?=" out-l2
+'
+
+test_expect_success 'format-patch output (UTF-8)' '
+	git repo-config i18n.logoutputencoding UTF-8 &&
+
+	git format-patch --stdout master..HEAD^ >out-u1 &&
+	git format-patch --stdout HEAD^ >out-u2 &&
+	grep "^Content-Type: text/plain; charset=UTF-8" out-u1 &&
+	grep "^From: =?UTF-8?q?=C3=81=C3=A9=C3=AD_=C3=B3=C3=BA?=" out-u1 &&
+	grep "^Content-Type: text/plain; charset=UTF-8" out-u2 &&
+	grep "^From: =?UTF-8?q?=C3=81=C3=A9=C3=AD_=C3=B3=C3=BA?=" out-u2
+'
+
+test_expect_success 'rebase (U/U)' '
+	# We want the result of rebase in UTF-8
+	git-repo-config i18n.commitencoding UTF-8 &&
+
+	# The test is about logoutputencoding not affecting the
+	# final outcome -- it is used internally to generate the
+	# patch and the log.
+
+	git repo-config i18n.logoutputencoding UTF-8 &&
+
+	# The result will be committed by GIT_COMMITTER_NAME --
+	# we want UTF-8 encoded name.
+	. ../t3901-utf8.txt &&
+	git checkout -b test &&
+	git-rebase master &&
+
+	check_encoding 2
+'
+
+test_expect_success 'rebase (U/L)' '
+	git-repo-config i18n.commitencoding UTF-8 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-utf8.txt &&
+
+	git reset --hard side &&
+	git-rebase master &&
+
+	check_encoding 2
+'
+
+test_expect_success 'rebase (L/L)' '
+	# In this test we want ISO-8859-1 encoded commits as the result
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard side &&
+	git-rebase master &&
+
+	check_encoding 2 8859
+'
+
+test_expect_success 'rebase (L/U)' '
+	# This is pathological -- use UTF-8 as intermediate form
+	# to get ISO-8859-1 results.
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding UTF-8 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard side &&
+	git-rebase master &&
+
+	check_encoding 2 8859
+'
+
+test_expect_success 'cherry-pick(U/U)' '
+	# Both the commitencoding and logoutputencoding is set to UTF-8.
+
+	git-repo-config i18n.commitencoding UTF-8 &&
+	git repo-config i18n.logoutputencoding UTF-8 &&
+	. ../t3901-utf8.txt &&
+
+	git reset --hard master &&
+	git cherry-pick side^ &&
+	git cherry-pick side &&
+	EDITOR=: VISUAL=: git revert HEAD &&
+
+	check_encoding 3
+'
+
+test_expect_success 'cherry-pick(L/L)' '
+	# Both the commitencoding and logoutputencoding is set to ISO-8859-1
+
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard master &&
+	git cherry-pick side^ &&
+	git cherry-pick side &&
+	EDITOR=: VISUAL=: git revert HEAD &&
+
+	check_encoding 3 8859
+'
+
+test_expect_success 'cherry-pick(U/L)' '
+	# Commitencoding is set to UTF-8 but logoutputencoding is ISO-8859-1
+
+	git-repo-config i18n.commitencoding UTF-8 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-utf8.txt &&
+
+	git reset --hard master &&
+	git cherry-pick side^ &&
+	git cherry-pick side &&
+	EDITOR=: VISUAL=: git revert HEAD &&
+
+	check_encoding 3
+'
+
+test_expect_success 'cherry-pick(L/U)' '
+	# Again, the commitencoding is set to ISO-8859-1 but
+	# logoutputencoding is set to UTF-8.
+
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding UTF-8 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard master &&
+	git cherry-pick side^ &&
+	git cherry-pick side &&
+	EDITOR=: VISUAL=: git revert HEAD &&
+
+	check_encoding 3 8859
+'
+
+test_expect_success 'rebase --merge (U/U)' '
+	git-repo-config i18n.commitencoding UTF-8 &&
+	git repo-config i18n.logoutputencoding UTF-8 &&
+	. ../t3901-utf8.txt &&
+
+	git reset --hard side &&
+	git-rebase --merge master &&
+
+	check_encoding 2
+'
+
+test_expect_success 'rebase --merge (U/L)' '
+	git-repo-config i18n.commitencoding UTF-8 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-utf8.txt &&
+
+	git reset --hard side &&
+	git-rebase --merge master &&
+
+	check_encoding 2
+'
+
+test_expect_success 'rebase --merge (L/L)' '
+	# In this test we want ISO-8859-1 encoded commits as the result
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding ISO-8859-1 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard side &&
+	git-rebase --merge master &&
+
+	check_encoding 2 8859
+'
+
+test_expect_success 'rebase --merge (L/U)' '
+	# This is pathological -- use UTF-8 as intermediate form
+	# to get ISO-8859-1 results.
+	git-repo-config i18n.commitencoding ISO-8859-1 &&
+	git repo-config i18n.logoutputencoding UTF-8 &&
+	. ../t3901-8859-1.txt &&
+
+	git reset --hard side &&
+	git-rebase --merge master &&
+
+	check_encoding 2 8859
+'
+
+test_done
diff --git a/t/t3901-utf8.txt b/t/t3901-utf8.txt
new file mode 100755
index 0000000..5f5205c
--- /dev/null
+++ b/t/t3901-utf8.txt
@@ -0,0 +1,4 @@
+: to be sourced in t3901 -- this is utf8
+GIT_AUTHOR_NAME="Áéí óú" &&
+GIT_COMMITTER_NAME=$GIT_AUTHOR_NAME &&
+export GIT_AUTHOR_NAME GIT_COMMITTER_NAME