Merge branch 'lt/pretty-expand-tabs'

When "git log" shows the log message indented by 4-spaces, the
remainder of a line after a HT does not align in the way the author
originally intended.  The command now expands tabs by default in
such a case, and allows the users to override it with a new option,
'--no-expand-tabs'.

* lt/pretty-expand-tabs:
  pretty: test --expand-tabs
  pretty: allow tweaking tabwidth in --expand-tabs
  pretty: enable --expand-tabs by default for selected pretty formats
  pretty: expand tabs in indented logs to make things line up properly

9 files changed, 220 insertions, 10 deletions

diff --git a/Documentation/pretty-options.txt b/Documentation/pretty-options.txt
index 54b88b6dca..6c67182728 100644
--- a/Documentation/pretty-options.txt
+++ b/Documentation/pretty-options.txt
@@ -42,6 +42,20 @@ people using 80-column terminals.
 	verbatim; this means that invalid sequences in the original
 	commit may be copied to the output.
 
+--expand-tabs=<n>::
+--expand-tabs::
+--no-expand-tabs::
+	Perform a tab expansion (replace each tab with enough spaces
+	to fill to the next display column that is multiple of '<n>')
+	in the log message before showing it in the output.
+	`--expand-tabs` is a short-hand for `--expand-tabs=8`, and
+	`--no-expand-tabs` is a short-hand for `--expand-tabs=0`,
+	which disables tab expansion.
++
+By default, tabs are expanded in pretty formats that indent the log
+message by 4 spaces (i.e.  'medium', which is the default, 'full',
+and 'fuller').
+
 ifndef::git-rev-list[]
 --notes[=<treeish>]::
 	Show the notes (see linkgit:git-notes[1]) that annotate the
diff --git a/builtin/log.c b/builtin/log.c
index 9430b80e5e..dff3fbbb43 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -1290,6 +1290,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix)
 	git_config(git_format_config, NULL);
 	init_revisions(&rev, prefix);
 	rev.commit_format = CMIT_FMT_EMAIL;
+	rev.expand_tabs_in_log_default = 0;
 	rev.verbose_header = 1;
 	rev.diff = 1;
 	rev.max_parents = 1;
diff --git a/commit.h b/commit.h
index 5d58be0017..b06db4d5d9 100644
--- a/commit.h
+++ b/commit.h
@@ -147,6 +147,7 @@ struct pretty_print_context {
 	int preserve_subject;
 	struct date_mode date_mode;
 	unsigned date_mode_explicit:1;
+	int expand_tabs_in_log;
 	int need_8bit_cte;
 	char *notes_message;
 	struct reflog_walk_info *reflog_info;
diff --git a/log-tree.c b/log-tree.c
index 60f983934d..78a5381d0e 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -683,6 +683,7 @@ void show_log(struct rev_info *opt)
 	ctx.fmt = opt->commit_format;
 	ctx.mailmap = opt->mailmap;
 	ctx.color = opt->diffopt.use_color;
+	ctx.expand_tabs_in_log = opt->expand_tabs_in_log;
 	ctx.output_encoding = get_log_output_encoding();
 	if (opt->from_ident.mail_begin && opt->from_ident.name_begin)
 		ctx.from_ident = &opt->from_ident;
diff --git a/pretty.c b/pretty.c
index 92b2870a7e..87c44971a1 100644
--- a/pretty.c
+++ b/pretty.c
@@ -16,6 +16,7 @@ static struct cmt_fmt_map {
 	const char *name;
 	enum cmit_fmt format;
 	int is_tformat;
+	int expand_tabs_in_log;
 	int is_alias;
 	const char *user_format;
 } *commit_formats;
@@ -87,13 +88,13 @@ static int git_pretty_formats_config(const char *var, const char *value, void *c
 static void setup_commit_formats(void)
 {
 	struct cmt_fmt_map builtin_formats[] = {
-		{ "raw",	CMIT_FMT_RAW,		0 },
-		{ "medium",	CMIT_FMT_MEDIUM,	0 },
-		{ "short",	CMIT_FMT_SHORT,		0 },
-		{ "email",	CMIT_FMT_EMAIL,		0 },
-		{ "fuller",	CMIT_FMT_FULLER,	0 },
-		{ "full",	CMIT_FMT_FULL,		0 },
-		{ "oneline",	CMIT_FMT_ONELINE,	1 }
+		{ "raw",	CMIT_FMT_RAW,		0,	0 },
+		{ "medium",	CMIT_FMT_MEDIUM,	0,	8 },
+		{ "short",	CMIT_FMT_SHORT,		0,	0 },
+		{ "email",	CMIT_FMT_EMAIL,		0,	0 },
+		{ "fuller",	CMIT_FMT_FULLER,	0,	8 },
+		{ "full",	CMIT_FMT_FULL,		0,	8 },
+		{ "oneline",	CMIT_FMT_ONELINE,	1,	0 }
 	};
 	commit_formats_len = ARRAY_SIZE(builtin_formats);
 	builtin_formats_len = commit_formats_len;
@@ -172,6 +173,7 @@ void get_commit_format(const char *arg, struct rev_info *rev)
 
 	rev->commit_format = commit_format->format;
 	rev->use_terminator = commit_format->is_tformat;
+	rev->expand_tabs_in_log_default = commit_format->expand_tabs_in_log;
 	if (commit_format->format == CMIT_FMT_USERFORMAT) {
 		save_user_format(rev, commit_format->user_format,
 				 commit_format->is_tformat);
@@ -1629,6 +1631,72 @@ void pp_title_line(struct pretty_print_context *pp,
 	strbuf_release(&title);
 }
 
+static int pp_utf8_width(const char *start, const char *end)
+{
+	int width = 0;
+	size_t remain = end - start;
+
+	while (remain) {
+		int n = utf8_width(&start, &remain);
+		if (n < 0 || !start)
+			return -1;
+		width += n;
+	}
+	return width;
+}
+
+static void strbuf_add_tabexpand(struct strbuf *sb, int tabwidth,
+				 const char *line, int linelen)
+{
+	const char *tab;
+
+	while ((tab = memchr(line, '\t', linelen)) != NULL) {
+		int width = pp_utf8_width(line, tab);
+
+		/*
+		 * If it wasn't well-formed utf8, or it
+		 * had characters with badly defined
+		 * width (control characters etc), just
+		 * give up on trying to align things.
+		 */
+		if (width < 0)
+			break;
+
+		/* Output the data .. */
+		strbuf_add(sb, line, tab - line);
+
+		/* .. and the de-tabified tab */
+		strbuf_addchars(sb, ' ', tabwidth - (width % tabwidth));
+
+		/* Skip over the printed part .. */
+		linelen -= tab + 1 - line;
+		line = tab + 1;
+	}
+
+	/*
+	 * Print out everything after the last tab without
+	 * worrying about width - there's nothing more to
+	 * align.
+	 */
+	strbuf_add(sb, line, linelen);
+}
+
+/*
+ * pp_handle_indent() prints out the intendation, and
+ * the whole line (without the final newline), after
+ * de-tabifying.
+ */
+static void pp_handle_indent(struct pretty_print_context *pp,
+			     struct strbuf *sb, int indent,
+			     const char *line, int linelen)
+{
+	strbuf_addchars(sb, ' ', indent);
+	if (pp->expand_tabs_in_log)
+		strbuf_add_tabexpand(sb, pp->expand_tabs_in_log, line, linelen);
+	else
+		strbuf_add(sb, line, linelen);
+}
+
 void pp_remainder(struct pretty_print_context *pp,
 		  const char **msg_p,
 		  struct strbuf *sb,
@@ -1653,8 +1721,12 @@ void pp_remainder(struct pretty_print_context *pp,
 
 		strbuf_grow(sb, linelen + indent + 20);
 		if (indent)
-			strbuf_addchars(sb, ' ', indent);
-		strbuf_add(sb, line, linelen);
+			pp_handle_indent(pp, sb, indent, line, linelen);
+		else if (pp->expand_tabs_in_log)
+			strbuf_add_tabexpand(sb, pp->expand_tabs_in_log,
+					     line, linelen);
+		else
+			strbuf_add(sb, line, linelen);
 		strbuf_addch(sb, '\n');
 	}
 }
diff --git a/revision.c b/revision.c
index 8b2dfe3160..b683476b9c 100644
--- a/revision.c
+++ b/revision.c
@@ -1356,8 +1356,10 @@ void init_revisions(struct rev_info *revs, const char *prefix)
 	revs->skip_count = -1;
 	revs->max_count = -1;
 	revs->max_parents = -1;
+	revs->expand_tabs_in_log = -1;
 
 	revs->commit_format = CMIT_FMT_DEFAULT;
+	revs->expand_tabs_in_log_default = 8;
 
 	init_grep_defaults();
 	grep_init(&revs->grep_filter, prefix);
@@ -1854,6 +1856,15 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 		revs->verbose_header = 1;
 		revs->pretty_given = 1;
 		get_commit_format(arg+9, revs);
+	} else if (!strcmp(arg, "--expand-tabs")) {
+		revs->expand_tabs_in_log = 8;
+	} else if (!strcmp(arg, "--no-expand-tabs")) {
+		revs->expand_tabs_in_log = 0;
+	} else if (skip_prefix(arg, "--expand-tabs=", &arg)) {
+		int val;
+		if (strtol_i(arg, 10, &val) < 0 || val < 0)
+			die("'%s': not a non-negative integer", arg);
+		revs->expand_tabs_in_log = val;
 	} else if (!strcmp(arg, "--show-notes") || !strcmp(arg, "--notes")) {
 		revs->show_notes = 1;
 		revs->show_notes_given = 1;
@@ -2327,6 +2338,9 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 	if (revs->first_parent_only && revs->bisect)
 		die(_("--first-parent is incompatible with --bisect"));
 
+	if (revs->expand_tabs_in_log < 0)
+		revs->expand_tabs_in_log = revs->expand_tabs_in_log_default;
+
 	return left;
 }
 
diff --git a/revision.h b/revision.h
index dca0d38171..9fac1a607d 100644
--- a/revision.h
+++ b/revision.h
@@ -148,6 +148,8 @@ struct rev_info {
 			linear:1;
 
 	struct date_mode date_mode;
+	int		expand_tabs_in_log; /* unset if negative */
+	int		expand_tabs_in_log_default;
 
 	unsigned int	abbrev;
 	enum cmit_fmt	commit_format;
diff --git a/t/t4201-shortlog.sh b/t/t4201-shortlog.sh
index f5e63670fa..a9773658f0 100755
--- a/t/t4201-shortlog.sh
+++ b/t/t4201-shortlog.sh
@@ -115,7 +115,7 @@ EOF
 '
 
 test_expect_success !MINGW 'shortlog from non-git directory' '
-	git log HEAD >log &&
+	git log --no-expand-tabs HEAD >log &&
 	GIT_DIR=non-existing git shortlog -w <log >out &&
 	test_cmp expect out
 '
diff --git a/t/t4213-log-tabexpand.sh b/t/t4213-log-tabexpand.sh
new file mode 100755
index 0000000000..e01a8f6ac9
--- /dev/null
+++ b/t/t4213-log-tabexpand.sh
@@ -0,0 +1,105 @@
+#!/bin/sh
+
+test_description='log/show --expand-tabs'
+
+. ./test-lib.sh
+
+HT="	"
+title='tab indent at the beginning of the title line'
+body='tab indent on a line in the body'
+
+# usage: count_expand $indent $numSP $numHT @format_args
+count_expand ()
+{
+	expect=
+	count=$(( $1 + $2 )) ;# expected spaces
+	while test $count -gt 0
+	do
+		expect="$expect "
+		count=$(( $count - 1 ))
+	done
+	shift 2
+	count=$1 ;# expected tabs
+	while test $count -gt 0
+	do
+		expect="$expect$HT"
+		count=$(( $count - 1 ))
+	done
+	shift
+
+	# The remainder of the command line is "git show -s" options
+	case " $* " in
+	*' --pretty=short '*)
+		line=$title ;;
+	*)
+		line=$body ;;
+	esac
+
+	# Prefix the output with the command line arguments, and
+	# replace SP with a dot both in the expecte and actual output
+	# so that test_cmp would show the differene together with the
+	# breakage in a way easier to consume by the debugging user.
+	{
+		echo "git show -s $*"
+		echo "$expect$line"
+	} | sed -e 's/ /./g' >expect
+
+	{
+		echo "git show -s $*"
+		git show -s "$@" |
+		sed -n -e "/$line\$/p"
+	} | sed -e 's/ /./g' >actual
+
+	test_cmp expect actual
+}
+
+test_expand ()
+{
+	fmt=$1
+	case "$fmt" in
+	*=raw | *=short | *=email)
+		default="0 1" ;;
+	*)
+		default="8 0" ;;
+	esac
+	case "$fmt" in
+	*=email)
+		in=0 ;;
+	*)
+		in=4 ;;
+	esac
+	test_expect_success "expand/no-expand${fmt:+ for $fmt}" '
+		count_expand $in $default $fmt &&
+		count_expand $in 8 0 $fmt --expand-tabs &&
+		count_expand $in 8 0 --expand-tabs $fmt &&
+		count_expand $in 8 0 $fmt --expand-tabs=8 &&
+		count_expand $in 8 0 --expand-tabs=8 $fmt &&
+		count_expand $in 0 1 $fmt --no-expand-tabs &&
+		count_expand $in 0 1 --no-expand-tabs $fmt &&
+		count_expand $in 0 1 $fmt --expand-tabs=0 &&
+		count_expand $in 0 1 --expand-tabs=0 $fmt &&
+		count_expand $in 4 0 $fmt --expand-tabs=4 &&
+		count_expand $in 4 0 --expand-tabs=4 $fmt
+	'
+}
+
+test_expect_success 'setup' '
+	test_tick &&
+	sed -e "s/Q/$HT/g" <<-EOF >msg &&
+	Q$title
+
+	Q$body
+	EOF
+	git commit --allow-empty -F msg
+'
+
+test_expand ""
+test_expand --pretty
+test_expand --pretty=short
+test_expand --pretty=medium
+test_expand --pretty=full
+test_expand --pretty=fuller
+test_expand --pretty=raw
+test_expand --pretty=email
+
+test_done