[PATCH 0/5] allow non-trailers and multiple-line trailers

[PATCH 0/5] allow non-trailers and multiple-line trailers

[Jonathan Tan]

In [1], Junio explained a possible redesign of trailer support in
interpret-trailers and cherry-pick, something along these lines:

 1. Support non-trailers and multi-line trailers in interpret-trailers
 2. Create a helper function so that the new interpretation can be used
    elsewhere (e.g. in sequencer)
 3. Modify "Signed-off-by" and "(cherry picked by" to use the helper
    function

My current plans for step 1 and step 2 require relatively significant
refactoring in trailer.c, so I thought that I should send out a patch
set covering only step 1 first for discussion, before continuing with my
work on top of this patch set.

Support for steps 2 and 3, including my original use case of being
looser in the definition of a trailer when invoking "cherry-pick -x"
(and thus suppressing the insertion of a newline) will come in a
subsequent patch set.

[1] Message ID <xmqqwphouivf.fsf@gitster.mtv.corp.google.com>

Jonathan Tan (5):
  trailer: use singly-linked list, not doubly
  trailer: streamline trailer item create and add
  trailer: make args have their own struct
  trailer: allow non-trailers in trailer block
  trailer: support values folded to multiple lines

 Documentation/git-interpret-trailers.txt |  10 +-
 t/t7513-interpret-trailers.sh            | 174 +++++++++
 trailer.c                                | 638 +++++++++++++++----------------
 3 files changed, 480 insertions(+), 342 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

[PATCH 1/5] trailer: use singly-linked list, not doubly

[Jonathan Tan]

Use singly-linked lists (instead of doubly-linked lists) in trailer to
keep track of arguments (whether implicit from configuration or explicit
from the command line) and trailer items.

This change significantly reduces the code length and simplifies the code.
There are now fewer pointers to be manipulated, but most trailer
manipulations now require seeking from beginning to end, so there might
be a slight net decrease in performance; however the number of trailers
is usually small (10 to 15 at the most) so this should not cause a big
impact.
---
 trailer.c | 357 ++++++++++++++++++++++----------------------------------------
 1 file changed, 125 insertions(+), 232 deletions(-)

diff --git a/trailer.c b/trailer.c
index c6ea9ac..bf3d7d0 100644
--- a/trailer.c
+++ b/trailer.c
@@ -25,7 +25,6 @@ struct conf_info {
 static struct conf_info default_conf_info;
 
 struct trailer_item {
-	struct trailer_item *previous;
 	struct trailer_item *next;
 	const char *token;
 	const char *value;
@@ -56,7 +55,8 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(struct trailer_item *a, struct trailer_item *b)
+static int same_token(const struct trailer_item *a,
+		      const struct trailer_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -65,12 +65,14 @@ static int same_token(struct trailer_item *a, struct trailer_item *b)
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(struct trailer_item *a, struct trailer_item *b)
+static int same_value(const struct trailer_item *a,
+		      const struct trailer_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(struct trailer_item *a, struct trailer_item *b)
+static int same_trailer(const struct trailer_item *a,
+			const struct trailer_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -129,92 +131,6 @@ static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
 	}
 }
 
-static void update_last(struct trailer_item **last)
-{
-	if (*last)
-		while ((*last)->next != NULL)
-			*last = (*last)->next;
-}
-
-static void update_first(struct trailer_item **first)
-{
-	if (*first)
-		while ((*first)->previous != NULL)
-			*first = (*first)->previous;
-}
-
-static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok,
-				  struct trailer_item **first,
-				  struct trailer_item **last)
-{
-	if (after_or_end(arg_tok->conf.where)) {
-		arg_tok->next = on_tok->next;
-		on_tok->next = arg_tok;
-		arg_tok->previous = on_tok;
-		if (arg_tok->next)
-			arg_tok->next->previous = arg_tok;
-		update_last(last);
-	} else {
-		arg_tok->previous = on_tok->previous;
-		on_tok->previous = arg_tok;
-		arg_tok->next = on_tok;
-		if (arg_tok->previous)
-			arg_tok->previous->next = arg_tok;
-		update_first(first);
-	}
-}
-
-static int check_if_different(struct trailer_item *in_tok,
-			      struct trailer_item *arg_tok,
-			      int check_all)
-{
-	enum action_where where = arg_tok->conf.where;
-	do {
-		if (!in_tok)
-			return 1;
-		if (same_trailer(in_tok, arg_tok))
-			return 0;
-		/*
-		 * if we want to add a trailer after another one,
-		 * we have to check those before this one
-		 */
-		in_tok = after_or_end(where) ? in_tok->previous : in_tok->next;
-	} while (check_all);
-	return 1;
-}
-
-static void remove_from_list(struct trailer_item *item,
-			     struct trailer_item **first,
-			     struct trailer_item **last)
-{
-	struct trailer_item *next = item->next;
-	struct trailer_item *previous = item->previous;
-
-	if (next) {
-		item->next->previous = previous;
-		item->next = NULL;
-	} else if (last)
-		*last = previous;
-
-	if (previous) {
-		item->previous->next = next;
-		item->previous = NULL;
-	} else if (first)
-		*first = next;
-}
-
-static struct trailer_item *remove_first(struct trailer_item **first)
-{
-	struct trailer_item *item = *first;
-	*first = item->next;
-	if (item->next) {
-		item->next->previous = NULL;
-		item->next = NULL;
-	}
-	return item;
-}
-
 static const char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
@@ -263,122 +179,116 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 	}
 }
 
-static void apply_arg_if_exists(struct trailer_item *in_tok,
-				struct trailer_item *arg_tok,
-				struct trailer_item *on_tok,
-				struct trailer_item **in_tok_first,
-				struct trailer_item **in_tok_last)
+static void apply_existing_arg(struct trailer_item **found_next,
+			       struct trailer_item *arg_tok,
+			       struct trailer_item **position_to_add,
+			       const struct trailer_item *in_tok_head,
+			       const struct trailer_item *neighbor)
 {
-	switch (arg_tok->conf.if_exists) {
-	case EXISTS_DO_NOTHING:
+	if (arg_tok->conf.if_exists == EXISTS_DO_NOTHING) {
 		free_trailer_item(arg_tok);
-		break;
-	case EXISTS_REPLACE:
-		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		remove_from_list(in_tok, in_tok_first, in_tok_last);
-		free_trailer_item(in_tok);
-		break;
-	case EXISTS_ADD:
-		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		break;
-	case EXISTS_ADD_IF_DIFFERENT:
-		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(in_tok, arg_tok, 1))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		else
-			free_trailer_item(arg_tok);
-		break;
-	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
-		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(on_tok, arg_tok, 0))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		else
+		return;
+	}
+
+	apply_item_command(*found_next, arg_tok);
+
+	if (arg_tok->conf.if_exists == EXISTS_ADD_IF_DIFFERENT_NEIGHBOR) {
+		if (neighbor && same_trailer(neighbor, arg_tok)) {
 			free_trailer_item(arg_tok);
-		break;
+			return;
+		}
+	} else if (arg_tok->conf.if_exists == EXISTS_ADD_IF_DIFFERENT) {
+		const struct trailer_item *in_tok;
+		for (in_tok = in_tok_head; in_tok; in_tok = in_tok->next) {
+			if (same_trailer(in_tok, arg_tok)) {
+				free_trailer_item(arg_tok);
+				return;
+			}
+		}
+	}
+
+	arg_tok->next = *position_to_add;
+	*position_to_add = arg_tok;
+
+	if (arg_tok->conf.if_exists == EXISTS_REPLACE) {
+		struct trailer_item *new_next = (*found_next)->next;
+		free_trailer_item(*found_next);
+		*found_next = new_next;
 	}
 }
 
-static void apply_arg_if_missing(struct trailer_item **in_tok_first,
-				 struct trailer_item **in_tok_last,
-				 struct trailer_item *arg_tok)
+static void apply_missing_arg(struct trailer_item *arg_tok,
+			      struct trailer_item **position_to_add)
 {
-	struct trailer_item **in_tok;
-	enum action_where where;
-
-	switch (arg_tok->conf.if_missing) {
-	case MISSING_DO_NOTHING:
+	if (arg_tok->conf.if_missing == MISSING_DO_NOTHING) {
 		free_trailer_item(arg_tok);
-		break;
-	case MISSING_ADD:
-		where = arg_tok->conf.where;
-		in_tok = after_or_end(where) ? in_tok_last : in_tok_first;
-		apply_item_command(NULL, arg_tok);
-		if (*in_tok) {
-			add_arg_to_input_list(*in_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		} else {
-			*in_tok_first = arg_tok;
-			*in_tok_last = arg_tok;
-		}
-		break;
+		return;
 	}
+
+	apply_item_command(NULL, arg_tok);
+
+	arg_tok->next = *position_to_add;
+	*position_to_add = arg_tok;
 }
 
-static int find_same_and_apply_arg(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item *arg_tok)
+static void apply_arg(struct trailer_item **in_tok_head,
+		      struct trailer_item *arg_tok)
 {
-	struct trailer_item *in_tok;
-	struct trailer_item *on_tok;
-	struct trailer_item *following_tok;
-
+	struct trailer_item **next, **found_next = NULL, *last = NULL;
 	enum action_where where = arg_tok->conf.where;
-	int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE);
 	int backwards = after_or_end(where);
-	struct trailer_item *start_tok = backwards ? *in_tok_last : *in_tok_first;
 
-	for (in_tok = start_tok; in_tok; in_tok = following_tok) {
-		following_tok = backwards ? in_tok->previous : in_tok->next;
-		if (!same_token(in_tok, arg_tok))
-			continue;
-		on_tok = middle ? in_tok : start_tok;
-		apply_arg_if_exists(in_tok, arg_tok, on_tok,
-				    in_tok_first, in_tok_last);
-		return 1;
+	for (next = in_tok_head; *next; next = &(*next)->next) {
+		last = *next;
+		if ((!found_next || backwards) &&
+		    same_token(*next, arg_tok))
+			found_next = next;
+	}
+
+	if (found_next) {
+		struct trailer_item **position_to_add, *neighbor;
+		switch (where) {
+		case WHERE_START:
+			position_to_add = in_tok_head;
+			neighbor = *in_tok_head;
+			break;
+		case WHERE_BEFORE:
+			position_to_add = found_next;
+			neighbor = *found_next;
+			break;
+		case WHERE_AFTER:
+			position_to_add = &(*found_next)->next;
+			neighbor = *found_next;
+			break;
+		default:
+			position_to_add = next;
+			neighbor = last;
+			break;
+		}
+		apply_existing_arg(found_next, arg_tok, position_to_add,
+				   *in_tok_head, neighbor);
+	} else {
+		struct trailer_item **position_to_add;
+		switch (where) {
+		case WHERE_START:
+		case WHERE_BEFORE:
+			position_to_add = in_tok_head;
+			break;
+		default:
+			position_to_add = next;
+			break;
+		}
+		apply_missing_arg(arg_tok, position_to_add);
 	}
-	return 0;
 }
 
-static void process_trailers_lists(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item **arg_tok_first)
+static void process_trailers_lists(struct trailer_item **in_tok_head,
+				   struct trailer_item *arg_tok_head)
 {
-	struct trailer_item *arg_tok;
-	struct trailer_item *next_arg;
-
-	if (!*arg_tok_first)
-		return;
-
-	for (arg_tok = *arg_tok_first; arg_tok; arg_tok = next_arg) {
-		int applied = 0;
-
-		next_arg = arg_tok->next;
-		remove_from_list(arg_tok, arg_tok_first, NULL);
-
-		applied = find_same_and_apply_arg(in_tok_first,
-						  in_tok_last,
-						  arg_tok);
-
-		if (!applied)
-			apply_arg_if_missing(in_tok_first,
-					     in_tok_last,
-					     arg_tok);
+	struct trailer_item *arg_tok, *next;
+	for (arg_tok = arg_tok_head; arg_tok; arg_tok = next) {
+		next = arg_tok->next;
+		apply_arg(in_tok_head, arg_tok);
 	}
 }
 
@@ -438,29 +348,19 @@ static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
 
 static struct trailer_item *get_conf_item(const char *name)
 {
+	struct trailer_item **next = &first_conf_item;
 	struct trailer_item *item;
-	struct trailer_item *previous;
 
 	/* Look up item with same name */
-	for (previous = NULL, item = first_conf_item;
-	     item;
-	     previous = item, item = item->next) {
-		if (!strcasecmp(item->conf.name, name))
-			return item;
-	}
+	for (next = &first_conf_item; *next; next = &(*next)->next)
+		if (!strcasecmp((*next)->conf.name, name))
+			return *next;
 
 	/* Item does not already exists, create it */
 	item = xcalloc(sizeof(struct trailer_item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
-
-	if (!previous)
-		first_conf_item = item;
-	else {
-		previous->next = item;
-		item->previous = previous;
-	}
-
+	*next = item;
 	return item;
 }
 
@@ -652,26 +552,19 @@ static struct trailer_item *create_trailer_item(const char *string)
 				strbuf_detach(&val, NULL));
 }
 
-static void add_trailer_item(struct trailer_item **first,
-			     struct trailer_item **last,
+static void add_trailer_item(struct trailer_item ***tail,
 			     struct trailer_item *new)
 {
 	if (!new)
 		return;
-	if (!*last) {
-		*first = new;
-		*last = new;
-	} else {
-		(*last)->next = new;
-		new->previous = *last;
-		*last = new;
-	}
+	**tail = new;
+	*tail = &new->next;
 }
 
 static struct trailer_item *process_command_line_args(struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_first = NULL;
-	struct trailer_item *arg_tok_last = NULL;
+	struct trailer_item *arg_tok_head = NULL;
+	struct trailer_item **arg_tok_tail = &arg_tok_head;
 	struct string_list_item *tr;
 	struct trailer_item *item;
 
@@ -679,17 +572,17 @@ static struct trailer_item *process_command_line_args(struct string_list *traile
 	for (item = first_conf_item; item; item = item->next) {
 		if (item->conf.command) {
 			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+			add_trailer_item(&arg_tok_tail, new);
 		}
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+		add_trailer_item(&arg_tok_tail, new);
 	}
 
-	return arg_tok_first;
+	return arg_tok_head;
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -805,8 +698,7 @@ static void print_lines(FILE *outfile, struct strbuf **lines, int start, int end
 
 static int process_input_file(FILE *outfile,
 			      struct strbuf **lines,
-			      struct trailer_item **in_tok_first,
-			      struct trailer_item **in_tok_last)
+			      struct trailer_item ***in_tok_tail)
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
@@ -829,18 +721,19 @@ static int process_input_file(FILE *outfile,
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char) {
 			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_first, in_tok_last, new);
+			add_trailer_item(in_tok_tail, new);
 		}
 	}
 
 	return trailer_end;
 }
 
-static void free_all(struct trailer_item **first)
+static void free_all(struct trailer_item *head)
 {
-	while (*first) {
-		struct trailer_item *item = remove_first(first);
-		free_trailer_item(item);
+	while (head) {
+		struct trailer_item *next = head->next;
+		free_trailer_item(head);
+		head = next;
 	}
 }
 
@@ -877,9 +770,9 @@ static FILE *create_in_place_tempfile(const char *file)
 
 void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers)
 {
-	struct trailer_item *in_tok_first = NULL;
-	struct trailer_item *in_tok_last = NULL;
-	struct trailer_item *arg_tok_first;
+	struct trailer_item *in_tok_head = NULL;
+	struct trailer_item **in_tok_tail = &in_tok_head;
+	struct trailer_item *arg_tok_head;
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
@@ -894,15 +787,15 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 		outfile = create_in_place_tempfile(file);
 
 	/* Print the lines before the trailers */
-	trailer_end = process_input_file(outfile, lines, &in_tok_first, &in_tok_last);
+	trailer_end = process_input_file(outfile, lines, &in_tok_tail);
 
-	arg_tok_first = process_command_line_args(trailers);
+	arg_tok_head = process_command_line_args(trailers);
 
-	process_trailers_lists(&in_tok_first, &in_tok_last, &arg_tok_first);
+	process_trailers_lists(&in_tok_head, arg_tok_head);
 
-	print_all(outfile, in_tok_first, trim_empty);
+	print_all(outfile, in_tok_head, trim_empty);
 
-	free_all(&in_tok_first);
+	free_all(in_tok_head);
 
 	/* Print the lines after the trailers as is */
 	print_lines(outfile, lines, trailer_end, INT_MAX);
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH 1/5] trailer: use singly-linked list, not doubly

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> Use singly-linked lists (instead of doubly-linked lists) in trailer to
> keep track of arguments (whether implicit from configuration or explicit
> from the command line) and trailer items.
>
> This change significantly reduces the code length and simplifies the code.
> There are now fewer pointers to be manipulated, but most trailer
> manipulations now require seeking from beginning to end, so there might
> be a slight net decrease in performance; however the number of trailers
> is usually small (10 to 15 at the most) so this should not cause a big
> impact.

It is overall a very good change, but can you split this into two
independent patches?  s/struct trailer_item/const &/ sprinkled all
over the place is more or less unrelated change and it is very
distracting to see the primary change of the way lists are handled.

Re: [PATCH 1/5] trailer: use singly-linked list, not doubly

[Christian Couder]

On Wed, Oct 12, 2016 at 3:23 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> Use singly-linked lists (instead of doubly-linked lists) in trailer to
> keep track of arguments (whether implicit from configuration or explicit
> from the command line) and trailer items.
>
> This change significantly reduces the code length and simplifies the code.

It's true that the code can be simplified a lot by using a
singly-linked list, but if we already had and used some generic
functions or macros to handle doubly-linked list, I doubt there would
be a significant simplification (as the generic code could not be
deleted in this case).

> There are now fewer pointers to be manipulated, but most trailer
> manipulations now require seeking from beginning to end, so there might
> be a slight net decrease in performance; however the number of trailers
> is usually small (10 to 15 at the most) so this should not cause a big
> impact.

By default we append new trailers at the end of the trailer list, so a
singly-linked list is theoretically not well suited at all for
handling trailer lists.

You say that at most there is a small number of trailers, and that may
be true indeed for the Linux kernel and most projects these days, but
I am not sure it is a good assumption to make in general.

For example if some projects use or start using "CC:  *" trailers and
tools to automatically append such trailers (perhaps using 'git
interpret-trailers' for that purpose by the way) based on people who
touched the same code, then it could very well be a common thing to
have 20 or more trailers on patches/commits for these projects.

There could also be automated testing tools that add their own
"Tested-by: *" trailers, and projects that require many people to add
their "Reviewed-by: *" trailers to each patch/commit. And in general
with millions of users, it is not very safe to make assumptions that
they will all be "reasonable" in the way they use a feature.

Another thing is that when Git started, I doubt many people would have
thought that there would often be more than just one or two
"Signed-off-by: *" trailer, and now 10 or 15 doesn't seem unthinkable.
In fact 'git interpret-trailers' has been made precisely because there
are more and more trailers, so there is more and more a need for a
tool to properly add and manage them.

We recently had a discussion on the list to increase the default
abbreviation length because it was not foreseen at the beginning of
Git that people would need a larger number of characters as projects
grow.

So even for the Linux kernel, I am not sure that it is safe to assume
that the number of trailers will not grow much over the years,
especially if we work on the tool that can make it easy to easily and
automatically add them.

Thanks,
Christian.

Re: [PATCH 1/5] trailer: use singly-linked list, not doubly

[Jeff King]

On Wed, Oct 12, 2016 at 05:38:14PM +0200, Christian Couder wrote:

> On Wed, Oct 12, 2016 at 3:23 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> > Use singly-linked lists (instead of doubly-linked lists) in trailer to
> > keep track of arguments (whether implicit from configuration or explicit
> > from the command line) and trailer items.
> >
> > This change significantly reduces the code length and simplifies the code.
> 
> It's true that the code can be simplified a lot by using a
> singly-linked list, but if we already had and used some generic
> functions or macros to handle doubly-linked list, I doubt there would
> be a significant simplification (as the generic code could not be
> deleted in this case).

We didn't have such generic macros when you wrote the trailer code
originally, but we do now, in list.h (they come from the kernel's
doubly-linked list implementation). I used them recently in a series and
found them pretty pleasant and complete.

Maybe it's worth trying the conversion here to see if it simplifies the
code.

> > There are now fewer pointers to be manipulated, but most trailer
> > manipulations now require seeking from beginning to end, so there might
> > be a slight net decrease in performance; however the number of trailers
> > is usually small (10 to 15 at the most) so this should not cause a big
> > impact.
> 
> By default we append new trailers at the end of the trailer list, so a
> singly-linked list is theoretically not well suited at all for
> handling trailer lists.
> 
> You say that at most there is a small number of trailers, and that may
> be true indeed for the Linux kernel and most projects these days, but
> I am not sure it is a good assumption to make in general.

I agree. As somebody who has fixed quite a number of accidentally
quadratic cases in the number of refs, width of the commit graph, etc,
over the years, these things have a way of creeping up or finding
pathological cases.

You _can_ append to a singly linked list in O(1) if you keep a tail
pointer, but I think using list.h would be even nicer.

-Peff

[PATCH 2/5] trailer: streamline trailer item create and add

[Jonathan Tan]

Currently, creation and addition (to a list) of trailer items are spread
across multiple functions. Streamline this by only having 2 functions:
one to parse the user-supplied string, and one to add the parsed
information to a list.
---
 trailer.c | 135 +++++++++++++++++++++++++++++---------------------------------
 1 file changed, 62 insertions(+), 73 deletions(-)

diff --git a/trailer.c b/trailer.c
index bf3d7d0..e8b1bfb 100644
--- a/trailer.c
+++ b/trailer.c
@@ -335,7 +335,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
 	return 0;
 }
 
-static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
+static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 {
 	*dst = *src;
 	if (src->name)
@@ -467,10 +467,30 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *trailer)
+static const char *token_from_item(struct trailer_item *item, char *tok)
+{
+	if (item->conf.key)
+		return item->conf.key;
+	if (tok)
+		return tok;
+	return item->conf.name;
+}
+
+static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+{
+	if (!strncasecmp(tok, item->conf.name, tok_len))
+		return 1;
+	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
+}
+
+static int parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
+	struct trailer_item *item;
+	int tok_len;
+
 	strbuf_addstr(&seps, separators);
 	strbuf_addch(&seps, '=');
 	len = strcspn(trailer, seps.buf);
@@ -490,73 +510,31 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *tra
 		strbuf_addstr(tok, trailer);
 		strbuf_trim(tok);
 	}
-	return 0;
-}
-
-static const char *token_from_item(struct trailer_item *item, char *tok)
-{
-	if (item->conf.key)
-		return item->conf.key;
-	if (tok)
-		return tok;
-	return item->conf.name;
-}
-
-static struct trailer_item *new_trailer_item(struct trailer_item *conf_item,
-					     char *tok, char *val)
-{
-	struct trailer_item *new = xcalloc(sizeof(*new), 1);
-	new->value = val ? val : xstrdup("");
-
-	if (conf_item) {
-		duplicate_conf(&new->conf, &conf_item->conf);
-		new->token = xstrdup(token_from_item(conf_item, tok));
-		free(tok);
-	} else {
-		duplicate_conf(&new->conf, &default_conf_info);
-		new->token = tok;
-	}
-
-	return new;
-}
-
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
-{
-	if (!strncasecmp(tok, item->conf.name, tok_len))
-		return 1;
-	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
-}
-
-static struct trailer_item *create_trailer_item(const char *string)
-{
-	struct strbuf tok = STRBUF_INIT;
-	struct strbuf val = STRBUF_INIT;
-	struct trailer_item *item;
-	int tok_len;
-
-	if (parse_trailer(&tok, &val, string))
-		return NULL;
-
-	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
+	tok_len = token_len_without_separator(tok->buf, tok->len);
+	*conf = &default_conf_info;
 	for (item = first_conf_item; item; item = item->next) {
-		if (token_matches_item(tok.buf, item, tok_len))
-			return new_trailer_item(item,
-						strbuf_detach(&tok, NULL),
-						strbuf_detach(&val, NULL));
+		if (token_matches_item(tok->buf, item, tok_len)) {
+			char *tok_buf = strbuf_detach(tok, NULL);
+			*conf = &item->conf;
+			strbuf_addstr(tok, token_from_item(item, tok_buf));
+			free(tok_buf);
+			break;
+		}
 	}
 
-	return new_trailer_item(NULL,
-				strbuf_detach(&tok, NULL),
-				strbuf_detach(&val, NULL));
+	return 0;
 }
 
-static void add_trailer_item(struct trailer_item ***tail,
-			     struct trailer_item *new)
+static void add_trailer_item(struct trailer_item ***tail, char *tok, char *val,
+			     const struct conf_info *conf)
 {
-	if (!new)
-		return;
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
+
 	**tail = new;
 	*tail = &new->next;
 }
@@ -567,19 +545,25 @@ static struct trailer_item *process_command_line_args(struct string_list *traile
 	struct trailer_item **arg_tok_tail = &arg_tok_head;
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Add a trailer item for each configured trailer with a command */
-	for (item = first_conf_item; item; item = item->next) {
-		if (item->conf.command) {
-			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_tail, new);
-		}
-	}
+	for (item = first_conf_item; item; item = item->next)
+		if (item->conf.command)
+			add_trailer_item(&arg_tok_tail,
+					 xstrdup(token_from_item(item, NULL)),
+					 xstrdup(""),
+					 &item->conf);
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_tail, new);
+		if (!parse_trailer(&tok, &val, &conf, tr->string))
+			add_trailer_item(&arg_tok_tail,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return arg_tok_head;
@@ -702,6 +686,9 @@ static int process_input_file(FILE *outfile,
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -719,10 +706,12 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char) {
-			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_tail, new);
-		}
+		if (lines[i]->buf[0] != comment_line_char &&
+		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+			add_trailer_item(in_tok_tail,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH 3/5] trailer: make args have their own struct

[Jonathan Tan]

Improve type safety by making arguments (whether from configuration or
from the command line) have their own "struct arg_item" type, separate
from the "struct trailer_item" type used to represent the trailers in
the buffer being manipulated.

Also take the opportunity to refine the "struct trailer_item" definition
by removing the conf (which is used only by arguments) and by removing
const on the string fields, since those fields are owned by the struct.

This change also prepares "struct trailer_item" to be further
differentiated from "struct arg_item" in future patches.
---
 trailer.c | 161 ++++++++++++++++++++++++++++++++++++++------------------------
 1 file changed, 99 insertions(+), 62 deletions(-)

diff --git a/trailer.c b/trailer.c
index e8b1bfb..167b2fd 100644
--- a/trailer.c
+++ b/trailer.c
@@ -26,12 +26,18 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct trailer_item *next;
-	const char *token;
-	const char *value;
+	char *token;
+	char *value;
+};
+
+struct arg_item {
+	struct arg_item *next;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
-static struct trailer_item *first_conf_item;
+static struct arg_item *first_conf_item;
 
 static char *separators = ":";
 
@@ -55,8 +61,7 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(const struct trailer_item *a,
-		      const struct trailer_item *b)
+static int same_token(const struct trailer_item *a, const struct arg_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -65,14 +70,12 @@ static int same_token(const struct trailer_item *a,
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(const struct trailer_item *a,
-		      const struct trailer_item *b)
+static int same_value(const struct trailer_item *a, const struct arg_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(const struct trailer_item *a,
-			const struct trailer_item *b)
+static int same_trailer(const struct trailer_item *a, const struct arg_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -94,11 +97,18 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 
 static void free_trailer_item(struct trailer_item *item)
 {
+	free(item->token);
+	free(item->value);
+	free(item);
+}
+
+static void free_arg_item(struct arg_item *item)
+{
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
-	free((char *)item->token);
-	free((char *)item->value);
+	free(item->token);
+	free(item->value);
 	free(item);
 }
 
@@ -131,13 +141,13 @@ static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
 	}
 }
 
-static const char *apply_command(const char *command, const char *arg)
+static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *argv[] = {NULL, NULL};
-	const char *result;
+	char *result;
 
 	strbuf_addstr(&cmd, command);
 	if (arg)
@@ -162,7 +172,7 @@ static const char *apply_command(const char *command, const char *arg)
 	return result;
 }
 
-static void apply_item_command(struct trailer_item *in_tok, struct trailer_item *arg_tok)
+static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg_tok)
 {
 	if (arg_tok->conf.command) {
 		const char *arg;
@@ -179,60 +189,77 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 	}
 }
 
+static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
+{
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = arg_tok->token;
+	new->value = arg_tok->value;
+	arg_tok->token = arg_tok->value = NULL;
+	free_arg_item(arg_tok);
+	return new;
+}
+
 static void apply_existing_arg(struct trailer_item **found_next,
-			       struct trailer_item *arg_tok,
+			       struct arg_item *arg_tok,
 			       struct trailer_item **position_to_add,
 			       const struct trailer_item *in_tok_head,
 			       const struct trailer_item *neighbor)
 {
-	if (arg_tok->conf.if_exists == EXISTS_DO_NOTHING) {
-		free_trailer_item(arg_tok);
+	enum action_if_exists if_exists = arg_tok->conf.if_exists;
+	struct trailer_item *to_add;
+
+	if (if_exists == EXISTS_DO_NOTHING) {
+		free_arg_item(arg_tok);
 		return;
 	}
 
 	apply_item_command(*found_next, arg_tok);
 
-	if (arg_tok->conf.if_exists == EXISTS_ADD_IF_DIFFERENT_NEIGHBOR) {
+	if (if_exists == EXISTS_ADD_IF_DIFFERENT_NEIGHBOR) {
 		if (neighbor && same_trailer(neighbor, arg_tok)) {
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 			return;
 		}
-	} else if (arg_tok->conf.if_exists == EXISTS_ADD_IF_DIFFERENT) {
+	} else if (if_exists == EXISTS_ADD_IF_DIFFERENT) {
 		const struct trailer_item *in_tok;
 		for (in_tok = in_tok_head; in_tok; in_tok = in_tok->next) {
 			if (same_trailer(in_tok, arg_tok)) {
-				free_trailer_item(arg_tok);
+				free_arg_item(arg_tok);
 				return;
 			}
 		}
 	}
 
-	arg_tok->next = *position_to_add;
-	*position_to_add = arg_tok;
+	to_add = trailer_from_arg(arg_tok);
+	to_add->next = *position_to_add;
+	*position_to_add = to_add;
 
-	if (arg_tok->conf.if_exists == EXISTS_REPLACE) {
+	if (if_exists == EXISTS_REPLACE) {
 		struct trailer_item *new_next = (*found_next)->next;
 		free_trailer_item(*found_next);
 		*found_next = new_next;
 	}
 }
 
-static void apply_missing_arg(struct trailer_item *arg_tok,
+static void apply_missing_arg(struct arg_item *arg_tok,
 			      struct trailer_item **position_to_add)
 {
+	struct trailer_item *to_add;
+
 	if (arg_tok->conf.if_missing == MISSING_DO_NOTHING) {
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		return;
 	}
 
 	apply_item_command(NULL, arg_tok);
 
-	arg_tok->next = *position_to_add;
-	*position_to_add = arg_tok;
+	to_add = trailer_from_arg(arg_tok);
+	to_add->next = *position_to_add;
+	*position_to_add = to_add;
 }
 
 static void apply_arg(struct trailer_item **in_tok_head,
-		      struct trailer_item *arg_tok)
+		      struct arg_item *arg_tok)
 {
 	struct trailer_item **next, **found_next = NULL, *last = NULL;
 	enum action_where where = arg_tok->conf.where;
@@ -283,9 +310,9 @@ static void apply_arg(struct trailer_item **in_tok_head,
 }
 
 static void process_trailers_lists(struct trailer_item **in_tok_head,
-				   struct trailer_item *arg_tok_head)
+				   struct arg_item *arg_tok_head)
 {
-	struct trailer_item *arg_tok, *next;
+	struct arg_item *arg_tok, *next;
 	for (arg_tok = arg_tok_head; arg_tok; arg_tok = next) {
 		next = arg_tok->next;
 		apply_arg(in_tok_head, arg_tok);
@@ -346,10 +373,10 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 		dst->command = xstrdup(src->command);
 }
 
-static struct trailer_item *get_conf_item(const char *name)
+static struct arg_item *get_conf_item(const char *name)
 {
-	struct trailer_item **next = &first_conf_item;
-	struct trailer_item *item;
+	struct arg_item **next = &first_conf_item;
+	struct arg_item *item;
 
 	/* Look up item with same name */
 	for (next = &first_conf_item; *next; next = &(*next)->next)
@@ -357,7 +384,7 @@ static struct trailer_item *get_conf_item(const char *name)
 			return *next;
 
 	/* Item does not already exists, create it */
-	item = xcalloc(sizeof(struct trailer_item), 1);
+	item = xcalloc(sizeof(*item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 	*next = item;
@@ -409,7 +436,7 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v
 static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 {
 	const char *trailer_item, *variable_name;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct conf_info *conf;
 	char *name = NULL;
 	enum trailer_info_type type;
@@ -467,7 +494,7 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static const char *token_from_item(struct trailer_item *item, char *tok)
+static const char *token_from_item(struct arg_item *item, char *tok)
 {
 	if (item->conf.key)
 		return item->conf.key;
@@ -476,7 +503,7 @@ static const char *token_from_item(struct trailer_item *item, char *tok)
 	return item->conf.name;
 }
 
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+static int token_matches_item(const char *tok, struct arg_item *item, int tok_len)
 {
 	if (!strncasecmp(tok, item->conf.name, tok_len))
 		return 1;
@@ -488,7 +515,7 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
-	struct trailer_item *item;
+	struct arg_item *item;
 	int tok_len;
 
 	strbuf_addstr(&seps, separators);
@@ -513,11 +540,13 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 
 	/* Lookup if the token matches something in the config */
 	tok_len = token_len_without_separator(tok->buf, tok->len);
-	*conf = &default_conf_info;
+	if (conf)
+		*conf = &default_conf_info;
 	for (item = first_conf_item; item; item = item->next) {
 		if (token_matches_item(tok->buf, item, tok_len)) {
 			char *tok_buf = strbuf_detach(tok, NULL);
-			*conf = &item->conf;
+			if (conf)
+				*conf = &item->conf;
 			strbuf_addstr(tok, token_from_item(item, tok_buf));
 			free(tok_buf);
 			break;
@@ -527,43 +556,53 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct trailer_item ***tail, char *tok, char *val,
-			     const struct conf_info *conf)
+static void add_trailer_item(struct trailer_item ***tail, char *tok, char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
+
+	**tail = new;
+	*tail = &new->next;
+}
+
+static void add_arg_item(struct arg_item ***tail, char *tok, char *val,
+			 const struct conf_info *conf)
+{
+	struct arg_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
 	duplicate_conf(&new->conf, conf);
 
 	**tail = new;
 	*tail = &new->next;
 }
 
-static struct trailer_item *process_command_line_args(struct string_list *trailers)
+static struct arg_item *process_command_line_args(struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_head = NULL;
-	struct trailer_item **arg_tok_tail = &arg_tok_head;
+	struct arg_item *arg_tok_head = NULL;
+	struct arg_item **arg_tok_tail = &arg_tok_head;
 	struct string_list_item *tr;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
 	const struct conf_info *conf;
 
-	/* Add a trailer item for each configured trailer with a command */
+	/* Add an arg item for each configured trailer with a command */
 	for (item = first_conf_item; item; item = item->next)
 		if (item->conf.command)
-			add_trailer_item(&arg_tok_tail,
-					 xstrdup(token_from_item(item, NULL)),
-					 xstrdup(""),
-					 &item->conf);
+			add_arg_item(&arg_tok_tail,
+				     xstrdup(token_from_item(item, NULL)),
+				     xstrdup(""),
+				     &item->conf);
 
-	/* Add a trailer item for each trailer on the command line */
+	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		if (!parse_trailer(&tok, &val, &conf, tr->string))
-			add_trailer_item(&arg_tok_tail,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+			add_arg_item(&arg_tok_tail,
+				     strbuf_detach(&tok, NULL),
+				     strbuf_detach(&val, NULL),
+				     conf);
 	}
 
 	return arg_tok_head;
@@ -688,7 +727,6 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
-	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -707,11 +745,10 @@ static int process_input_file(FILE *outfile,
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
 			add_trailer_item(in_tok_tail,
 					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+					 strbuf_detach(&val, NULL));
 	}
 
 	return trailer_end;
@@ -761,7 +798,7 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 {
 	struct trailer_item *in_tok_head = NULL;
 	struct trailer_item **in_tok_tail = &in_tok_head;
-	struct trailer_item *arg_tok_head;
+	struct arg_item *arg_tok_head;
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
-- 
2.8.0.rc3.226.g39d4020

[PATCH 4/5] trailer: allow non-trailers in trailer block

[Jonathan Tan]

Currently, interpret-trailers requires all lines of a trailer block to
be trailers (or comments) - if not it would not identify that block as a
trailer block, and thus create its own trailer block, inserting a blank
line.  For example:

  echo -e "\na: b\nnot trailer" |
  git interpret-trailers --trailer "c: d"

would result in:

  a: b
  not trailer

  c: d

Relax the definition of a trailer block to only require 1 trailer, so
that trailers can be directly added to such blocks, resulting in:

  a: b
  not trailer
  c: d

This allows arbitrary lines to be included in trailer blocks, like those
in [1], and still allow interpret-trailers to be used.

This change also makes comments in the trailer block be treated as any
other non-trailer line, preserving them in the output of
interpret-trailers.

[1]
https://kernel.googlesource.com/pub/scm/linux/kernel/git/stable/linux-stable/+/e7d316a02f683864a12389f8808570e37fb90aa3
---

There are some possible inaccuracies in the master branch's
find_trailer_start (in particular, handling of lines that *start* with a
separator, which should not be considered a trailer line) - this patch
preserves the existing behavior.

 Documentation/git-interpret-trailers.txt |  3 +-
 t/t7513-interpret-trailers.sh            | 35 +++++++++++++++
 trailer.c                                | 77 ++++++++++++++++++++++----------
 3 files changed, 90 insertions(+), 25 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 93d1db6..c480da6 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -48,7 +48,8 @@ with only spaces at the end of the commit message part, one blank line
 will be added before the new trailer.
 
 Existing trailers are extracted from the input message by looking for
-a group of one or more lines that contain a colon (by default), where
+a group of one or more lines in which at least one line contains a 
+colon (by default), where
 the group is preceded by one or more empty (or whitespace-only) lines.
 The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index aee785c..7f5cd2a 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -126,6 +126,37 @@ test_expect_success 'with multiline title in the message' '
 	test_cmp expected actual
 '
 
+test_expect_success 'with non-trailer lines mixed with trailer lines' '
+	cat >patch <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines only' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
@@ -257,6 +288,8 @@ test_expect_success 'with message that has comments' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
@@ -286,6 +319,8 @@ test_expect_success 'with message that has an old style conflict block' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
diff --git a/trailer.c b/trailer.c
index 167b2fd..97e96a9 100644
--- a/trailer.c
+++ b/trailer.c
@@ -26,6 +26,10 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct trailer_item *next;
+	/*
+	 * If this is not a trailer line, the line is stored in value
+	 * (excluding the terminating newline) and token is NULL.
+	 */
 	char *token;
 	char *value;
 };
@@ -63,9 +67,14 @@ static size_t token_len_without_separator(const char *token, size_t len)
 
 static int same_token(const struct trailer_item *a, const struct arg_item *b)
 {
-	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
-	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
-	size_t min_len = (a_len > b_len) ? b_len : a_len;
+	size_t a_len, b_len, min_len;
+
+	if (!a->token)
+		return 0;
+
+	a_len = token_len_without_separator(a->token, strlen(a->token));
+	b_len = token_len_without_separator(b->token, strlen(b->token));
+	min_len = (a_len > b_len) ? b_len : a_len;
 
 	return !strncasecmp(a->token, b->token, min_len);
 }
@@ -123,7 +132,14 @@ static char last_non_space_char(const char *s)
 
 static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 {
-	char c = last_non_space_char(tok);
+	char c;
+
+	if (!tok) {
+		fprintf(outfile, "%s\n", val);
+		return;
+	}
+
+	c = last_non_space_char(tok);
 	if (!c)
 		return;
 	if (strchr(separators, c))
@@ -510,8 +526,16 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
 	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
 }
 
+/*
+ * Parse the given trailer into token and value parts.
+ *
+ * If the given trailer does not have a separator (and thus cannot be separated
+ * into token and value parts), it is treated as a token (if parse_as_arg) or
+ * as a non-trailer line (if not parse_as_arg).
+ */
 static int parse_trailer(struct strbuf *tok, struct strbuf *val,
-			 const struct conf_info **conf, const char *trailer)
+			 const struct conf_info **conf, const char *trailer,
+			 int parse_as_arg)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
@@ -523,11 +547,18 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	len = strcspn(trailer, seps.buf);
 	strbuf_release(&seps);
 	if (len == 0) {
-		int l = strlen(trailer);
+		int l;
+		if (!parse_as_arg)
+			return -1;
+
+		l = strlen(trailer);
 		while (l > 0 && isspace(trailer[l - 1]))
 			l--;
 		return error(_("empty trailer token in trailer '%.*s'"), l, trailer);
 	}
+	if (!parse_as_arg && len == strlen(trailer))
+		return -1;
+
 	if (len < strlen(trailer)) {
 		strbuf_add(tok, trailer, len);
 		strbuf_trim(tok);
@@ -598,7 +629,7 @@ static struct arg_item *process_command_line_args(struct string_list *trailers)
 
 	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		if (!parse_trailer(&tok, &val, &conf, tr->string))
+		if (!parse_trailer(&tok, &val, &conf, tr->string, 1))
 			add_arg_item(&arg_tok_tail,
 				     strbuf_detach(&tok, NULL),
 				     strbuf_detach(&val, NULL),
@@ -652,7 +683,7 @@ static int find_patch_start(struct strbuf **lines, int count)
  */
 static int find_trailer_start(struct strbuf **lines, int count)
 {
-	int start, end_of_title, only_spaces = 1;
+	int start, end_of_title, only_spaces = 1, trailer_found = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -668,22 +699,17 @@ static int find_trailer_start(struct strbuf **lines, int count)
 	 * for a line with only spaces before lines with one separator.
 	 */
 	for (start = count - 1; start >= end_of_title; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
-			return start + 1;
+			return trailer_found ? start + 1 : count;
 		}
-		if (strcspn(lines[start]->buf, separators) < lines[start]->len) {
-			if (only_spaces)
-				only_spaces = 0;
-			continue;
-		}
-		return count;
+		only_spaces = 0;
+		if (strcspn(lines[start]->buf, separators) < lines[start]->len)
+			trailer_found = 1;
 	}
 
-	return only_spaces ? count : 0;
+	return count;
 }
 
 /* Get the index of the end of the trailers */
@@ -704,11 +730,8 @@ static int find_trailer_end(struct strbuf **lines, int patch_start)
 
 static int has_blank_line_before(struct strbuf **lines, int start)
 {
-	for (;start >= 0; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
+	if (start >= 0)
 		return contains_only_spaces(lines[start]->buf);
-	}
 	return 0;
 }
 
@@ -744,11 +767,17 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
+		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
 			add_trailer_item(in_tok_tail,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		else {
+			strbuf_addbuf(&val, lines[i]);
+			strbuf_strip_suffix(&val, "\n");
+			add_trailer_item(in_tok_tail,
+					 NULL,
+					 strbuf_detach(&val, NULL));
+		}
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH 5/5] trailer: support values folded to multiple lines

[Jonathan Tan]

Currently, interpret-trailers requires that a trailer be only on 1 line.
For example:

  a: first line
     second line

would be interpreted as one trailer line followed by one non-trailer line.

Make interpret-trailers support RFC 822-style folding, treating those
lines as one logical trailer.
---
 Documentation/git-interpret-trailers.txt |   7 +-
 t/t7513-interpret-trailers.sh            | 139 +++++++++++++++++++++++++++++++
 trailer.c                                |  40 ++++++---
 3 files changed, 170 insertions(+), 16 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index c480da6..cfec636 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -57,11 +57,12 @@ minus signs start the patch part of the message.
 
 When reading trailers, there can be whitespaces before and after the
 token, the separator and the value. There can also be whitespaces
-inside the token and the value.
+inside the token and the value. The value may be split over multiple lines with
+each subsequent line starting with whitespace, like the "folding" in RFC 822.
 
 Note that 'trailers' do not follow and are not intended to follow many
-rules for RFC 822 headers. For example they do not follow the line
-folding rules, the encoding rules and probably many other rules.
+rules for RFC 822 headers. For example they do not follow
+the encoding rules and probably many other rules.
 
 OPTIONS
 -------
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 7f5cd2a..195cdd3 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -157,6 +157,145 @@ test_expect_success 'with non-trailer lines only' '
 	test_cmp expected actual
 '
 
+test_expect_success 'multiline field treated as atomic for placement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		name: value
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for replacement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		another: trailer
+		name: value
+	EOF
+	test_config trailer.name.ifexists replace &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for difference check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.ifexists addIfDifferent &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line *DIFFERENT*
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line
+		Qsecond line *DIFFERENT*
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for neighbor check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	test_config trailer.name.ifexists addIfDifferentNeighbor &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line *DIFFERENT*
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		name: first line
+		Qsecond line *DIFFERENT*
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index 97e96a9..907baa0 100644
--- a/trailer.c
+++ b/trailer.c
@@ -31,7 +31,7 @@ struct trailer_item {
 	 * (excluding the terminating newline) and token is NULL.
 	 */
 	char *token;
-	char *value;
+	struct strbuf value;
 };
 
 struct arg_item {
@@ -81,7 +81,7 @@ static int same_token(const struct trailer_item *a, const struct arg_item *b)
 
 static int same_value(const struct trailer_item *a, const struct arg_item *b)
 {
-	return !strcasecmp(a->value, b->value);
+	return !strcasecmp(a->value.buf, b->value);
 }
 
 static int same_trailer(const struct trailer_item *a, const struct arg_item *b)
@@ -107,7 +107,7 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 static void free_trailer_item(struct trailer_item *item)
 {
 	free(item->token);
-	free(item->value);
+	strbuf_release(&item->value);
 	free(item);
 }
 
@@ -152,8 +152,8 @@ static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
 {
 	struct trailer_item *item;
 	for (item = first; item; item = item->next) {
-		if (!trim_empty || strlen(item->value) > 0)
-			print_tok_val(outfile, item->token, item->value);
+		if (!trim_empty || item->value.len > 0)
+			print_tok_val(outfile, item->token, item->value.buf);
 	}
 }
 
@@ -195,8 +195,8 @@ static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg
 		if (arg_tok->value && arg_tok->value[0]) {
 			arg = arg_tok->value;
 		} else {
-			if (in_tok && in_tok->value)
-				arg = xstrdup(in_tok->value);
+			if (in_tok)
+				arg = xstrdup(in_tok->value.buf);
 			else
 				arg = xstrdup("");
 		}
@@ -209,7 +209,9 @@ static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = arg_tok->token;
-	new->value = arg_tok->value;
+	strbuf_init(&new->value, 0);
+	strbuf_attach(&new->value, arg_tok->value, strlen(arg_tok->value),
+		      strlen(arg_tok->value));
 	arg_tok->token = arg_tok->value = NULL;
 	free_arg_item(arg_tok);
 	return new;
@@ -587,14 +589,17 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct trailer_item ***tail, char *tok, char *val)
+static struct trailer_item *add_trailer_item(struct trailer_item ***tail, char *tok,
+					     char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
-	new->value = val;
+	strbuf_init(&new->value, 0);
+	strbuf_attach(&new->value, val, strlen(val), strlen(val));
 
 	**tail = new;
 	*tail = &new->next;
+	return new;
 }
 
 static void add_arg_item(struct arg_item ***tail, char *tok, char *val,
@@ -750,6 +755,7 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
+	struct trailer_item *last = NULL;
 
 	/* Get the line count */
 	while (lines[count])
@@ -767,16 +773,24 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
+		if (last && isspace(lines[i]->buf[0])) {
+			/* continuation line of the last trailer item */
+			strbuf_addch(&last->value, '\n');
+			strbuf_addbuf(&last->value, lines[i]);
+			strbuf_strip_suffix(&last->value, "\n");
+			continue;
+		}
 		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
-			add_trailer_item(in_tok_tail,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL));
+			last = add_trailer_item(in_tok_tail,
+						strbuf_detach(&tok, NULL),
+						strbuf_detach(&val, NULL));
 		else {
 			strbuf_addbuf(&val, lines[i]);
 			strbuf_strip_suffix(&val, "\n");
 			add_trailer_item(in_tok_tail,
 					 NULL,
 					 strbuf_detach(&val, NULL));
+			last = NULL;
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH 5/5] trailer: support values folded to multiple lines

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> Currently, interpret-trailers requires that a trailer be only on 1 line.
> For example:
>
>   a: first line
>      second line
>
> would be interpreted as one trailer line followed by one non-trailer line.
>
> Make interpret-trailers support RFC 822-style folding, treating those
> lines as one logical trailer.

Let's see how the code handles one minor detail when we see 822
folding, namely, "what happens to the leading whitespace that signals
the beginning of the second and subsequent lines?".

> diff --git a/trailer.c b/trailer.c
> index 97e96a9..907baa0 100644
> --- a/trailer.c
> +++ b/trailer.c
> @@ -31,7 +31,7 @@ struct trailer_item {
>  	 * (excluding the terminating newline) and token is NULL.
>  	 */
>  	char *token;
> -	char *value;
> +	struct strbuf value;
>  };

Is the length of value very frequently used once the list of trailer
lines are fully parsed?  If not, I'd rather not to have "struct
strbuf" in a long-living structure like this one and instead prefer
keeping it a simple and stupid "char *value".

Yes, I know the existing code in trailers overuses strbuf when there
is no need, primarily because it uses the lazy "split into an array
of strbufs" function.  We shouldn't make it worse.

> @@ -767,16 +773,24 @@ static int process_input_file(FILE *outfile,
>  
>  	/* Parse trailer lines */
>  	for (i = trailer_start; i < trailer_end; i++) {
> +		if (last && isspace(lines[i]->buf[0])) {

It is convenient if "value" is a strbuf to do this,

> +			/* continuation line of the last trailer item */
> +			strbuf_addch(&last->value, '\n');
> +			strbuf_addbuf(&last->value, lines[i]);
> +			strbuf_strip_suffix(&last->value, "\n");

but it is easy to introduce a temporary strbuf in this scope and use
it only to create the final value and detach it to last->value, i.e.

		if (last && isspace(*lines[i]->buf)) {
			struct strbuf buf = STRBUF_INIT;
			strbuf_addf(&buf, "%s\n%s", last->value, lines[i]->buf);
			strbuf_strip_suffix(&buf, "\n");
			free(last->value);
			last->value = strbuf_detach(&buf, NULL);

By the way, I now see that the code handles the "minor detail" to
keep the leading whitespace, which is good.

Thanks.

[PATCH v2 0/6] allow non-trailers and multiple-line trailers

[Jonathan Tan]

Thanks, Peff, for the pointer to list.h. Using list.h does simplify the
code by a similar amount to switching it to a singly-linked list, so I
have done that (replacing my earlier "trailer: use singly-linked list,
not doubly" patch). Another advantage is that I no longer need to change
the algorithm, making for a smaller patch.

(There are some quirks resulting from list.h implementing a circular
list, like needing to pass "head" as a sentinel when iterating from the
middle of the list, but those are minor, and my original singly-linked
list implementation had quirks too anyway like needing to pass a pointer
to the next pointer.)

Updates:
 (-> 1/6)
 - Added separate patch for const correctness changes
 (1/5 -> 2/6)
 - Dropped singly-linked list patch, instead replacing existing
   doubly-linked list implementation with list.h
 (5/5 -> 6/6)
 - Used "char *" instead of "struct strbuf"
 - Modified test slightly to test whitespace at beginning of line

Jonathan Tan (6):
  trailer: improve const correctness
  trailer: use list.h for doubly-linked list
  trailer: streamline trailer item create and add
  trailer: make args have their own struct
  trailer: allow non-trailers in trailer block
  trailer: support values folded to multiple lines

 Documentation/git-interpret-trailers.txt |  10 +-
 t/t7513-interpret-trailers.sh            | 174 ++++++++++
 trailer.c                                | 538 +++++++++++++++----------------
 3 files changed, 444 insertions(+), 278 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 1/6] trailer: improve const correctness

[Jonathan Tan]

Change "const char *" to "char *" in struct trailer_item and in the
return value of apply_command (since those strings are owned strings).

Change "struct conf_info *" to "const struct conf_info *" (since that
struct is not modified).
---
 trailer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/trailer.c b/trailer.c
index c6ea9ac..1f191b2 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,8 +27,8 @@ static struct conf_info default_conf_info;
 struct trailer_item {
 	struct trailer_item *previous;
 	struct trailer_item *next;
-	const char *token;
-	const char *value;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -95,8 +95,8 @@ static void free_trailer_item(struct trailer_item *item)
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
-	free((char *)item->token);
-	free((char *)item->value);
+	free(item->token);
+	free(item->value);
 	free(item);
 }
 
@@ -215,13 +215,13 @@ static struct trailer_item *remove_first(struct trailer_item **first)
 	return item;
 }
 
-static const char *apply_command(const char *command, const char *arg)
+static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *argv[] = {NULL, NULL};
-	const char *result;
+	char *result;
 
 	strbuf_addstr(&cmd, command);
 	if (arg)
@@ -425,7 +425,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
 	return 0;
 }
 
-static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
+static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 {
 	*dst = *src;
 	if (src->name)
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 2/6] trailer: use list.h for doubly-linked list

[Jonathan Tan]

Replace the existing handwritten implementation of a doubly-linked list
in trailer.c with the functions and macros from list.h. This
significantly simplifies the code.
---
 trailer.c | 258 ++++++++++++++++++++++----------------------------------------
 1 file changed, 91 insertions(+), 167 deletions(-)

diff --git a/trailer.c b/trailer.c
index 1f191b2..0afa240 100644
--- a/trailer.c
+++ b/trailer.c
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "tempfile.h"
 #include "trailer.h"
+#include "list.h"
 /*
  * Copyright (c) 2013, 2014 Christian Couder <chriscool@tuxfamily.org>
  */
@@ -25,19 +26,24 @@ struct conf_info {
 static struct conf_info default_conf_info;
 
 struct trailer_item {
-	struct trailer_item *previous;
-	struct trailer_item *next;
+	struct list_head list;
 	char *token;
 	char *value;
 	struct conf_info conf;
 };
 
-static struct trailer_item *first_conf_item;
+LIST_HEAD(conf_head);
 
 static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+/* Iterate over the elements of the list. */
+#define list_for_each_dir(pos, head, is_reverse) \
+	for (pos = is_reverse ? (head)->prev : (head)->next; \
+		pos != (head); \
+		pos = is_reverse ? pos->prev : pos->next)
+
 static int after_or_end(enum action_where where)
 {
 	return (where == WHERE_AFTER) || (where == WHERE_END);
@@ -120,101 +126,49 @@ static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 		fprintf(outfile, "%s%c %s\n", tok, separators[0], val);
 }
 
-static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
+static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	for (item = first; item; item = item->next) {
+	list_for_each(pos, head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!trim_empty || strlen(item->value) > 0)
 			print_tok_val(outfile, item->token, item->value);
 	}
 }
 
-static void update_last(struct trailer_item **last)
-{
-	if (*last)
-		while ((*last)->next != NULL)
-			*last = (*last)->next;
-}
-
-static void update_first(struct trailer_item **first)
-{
-	if (*first)
-		while ((*first)->previous != NULL)
-			*first = (*first)->previous;
-}
-
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok,
-				  struct trailer_item **first,
-				  struct trailer_item **last)
-{
-	if (after_or_end(arg_tok->conf.where)) {
-		arg_tok->next = on_tok->next;
-		on_tok->next = arg_tok;
-		arg_tok->previous = on_tok;
-		if (arg_tok->next)
-			arg_tok->next->previous = arg_tok;
-		update_last(last);
-	} else {
-		arg_tok->previous = on_tok->previous;
-		on_tok->previous = arg_tok;
-		arg_tok->next = on_tok;
-		if (arg_tok->previous)
-			arg_tok->previous->next = arg_tok;
-		update_first(first);
-	}
+				  struct trailer_item *arg_tok)
+{
+	if (after_or_end(arg_tok->conf.where))
+		list_add(&arg_tok->list, &on_tok->list);
+	else
+		list_add_tail(&arg_tok->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
 			      struct trailer_item *arg_tok,
-			      int check_all)
+			      int check_all,
+			      struct list_head *head)
 {
 	enum action_where where = arg_tok->conf.where;
+	struct list_head *next_head;
 	do {
-		if (!in_tok)
-			return 1;
 		if (same_trailer(in_tok, arg_tok))
 			return 0;
 		/*
 		 * if we want to add a trailer after another one,
 		 * we have to check those before this one
 		 */
-		in_tok = after_or_end(where) ? in_tok->previous : in_tok->next;
+		next_head = after_or_end(where) ? in_tok->list.prev
+						: in_tok->list.next;
+		if (next_head == head)
+			break;
+		in_tok = list_entry(next_head, struct trailer_item, list);
 	} while (check_all);
 	return 1;
 }
 
-static void remove_from_list(struct trailer_item *item,
-			     struct trailer_item **first,
-			     struct trailer_item **last)
-{
-	struct trailer_item *next = item->next;
-	struct trailer_item *previous = item->previous;
-
-	if (next) {
-		item->next->previous = previous;
-		item->next = NULL;
-	} else if (last)
-		*last = previous;
-
-	if (previous) {
-		item->previous->next = next;
-		item->previous = NULL;
-	} else if (first)
-		*first = next;
-}
-
-static struct trailer_item *remove_first(struct trailer_item **first)
-{
-	struct trailer_item *item = *first;
-	*first = item->next;
-	if (item->next) {
-		item->next->previous = NULL;
-		item->next = NULL;
-	}
-	return item;
-}
-
 static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
@@ -266,8 +220,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 static void apply_arg_if_exists(struct trailer_item *in_tok,
 				struct trailer_item *arg_tok,
 				struct trailer_item *on_tok,
-				struct trailer_item **in_tok_first,
-				struct trailer_item **in_tok_last)
+				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
@@ -275,40 +228,34 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		remove_from_list(in_tok, in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
+		list_del(&in_tok->list);
 		free_trailer_item(in_tok);
 		break;
 	case EXISTS_ADD:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(in_tok, arg_tok, 1))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(in_tok, arg_tok, 1, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(on_tok, arg_tok, 0))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(on_tok, arg_tok, 0, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	}
 }
 
-static void apply_arg_if_missing(struct trailer_item **in_tok_first,
-				 struct trailer_item **in_tok_last,
+static void apply_arg_if_missing(struct list_head *head,
 				 struct trailer_item *arg_tok)
 {
-	struct trailer_item **in_tok;
 	enum action_where where;
 
 	switch (arg_tok->conf.if_missing) {
@@ -317,68 +264,60 @@ static void apply_arg_if_missing(struct trailer_item **in_tok_first,
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
-		in_tok = after_or_end(where) ? in_tok_last : in_tok_first;
 		apply_item_command(NULL, arg_tok);
-		if (*in_tok) {
-			add_arg_to_input_list(*in_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		} else {
-			*in_tok_first = arg_tok;
-			*in_tok_last = arg_tok;
-		}
-		break;
+		if (after_or_end(where))
+			list_add_tail(&arg_tok->list, head);
+		else
+			list_add(&arg_tok->list, head);
 	}
 }
 
-static int find_same_and_apply_arg(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
+static int find_same_and_apply_arg(struct list_head *head,
 				   struct trailer_item *arg_tok)
 {
+	struct list_head *pos;
 	struct trailer_item *in_tok;
 	struct trailer_item *on_tok;
-	struct trailer_item *following_tok;
 
 	enum action_where where = arg_tok->conf.where;
 	int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE);
 	int backwards = after_or_end(where);
-	struct trailer_item *start_tok = backwards ? *in_tok_last : *in_tok_first;
+	struct trailer_item *start_tok;
 
-	for (in_tok = start_tok; in_tok; in_tok = following_tok) {
-		following_tok = backwards ? in_tok->previous : in_tok->next;
+	if (list_empty(head))
+		return 0;
+
+	start_tok = list_entry(backwards ? head->prev : head->next,
+			       struct trailer_item,
+			       list);
+
+	list_for_each_dir(pos, head, backwards) {
+		in_tok = list_entry(pos, struct trailer_item, list);
 		if (!same_token(in_tok, arg_tok))
 			continue;
 		on_tok = middle ? in_tok : start_tok;
-		apply_arg_if_exists(in_tok, arg_tok, on_tok,
-				    in_tok_first, in_tok_last);
+		apply_arg_if_exists(in_tok, arg_tok, on_tok, head);
 		return 1;
 	}
 	return 0;
 }
 
-static void process_trailers_lists(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item **arg_tok_first)
+static void process_trailers_lists(struct list_head *head,
+				   struct list_head *arg_head)
 {
+	struct list_head *pos, *p;
 	struct trailer_item *arg_tok;
-	struct trailer_item *next_arg;
-
-	if (!*arg_tok_first)
-		return;
 
-	for (arg_tok = *arg_tok_first; arg_tok; arg_tok = next_arg) {
+	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
+		arg_tok = list_entry(pos, struct trailer_item, list);
 
-		next_arg = arg_tok->next;
-		remove_from_list(arg_tok, arg_tok_first, NULL);
+		list_del(pos);
 
-		applied = find_same_and_apply_arg(in_tok_first,
-						  in_tok_last,
-						  arg_tok);
+		applied = find_same_and_apply_arg(head, arg_tok);
 
 		if (!applied)
-			apply_arg_if_missing(in_tok_first,
-					     in_tok_last,
-					     arg_tok);
+			apply_arg_if_missing(head, arg_tok);
 	}
 }
 
@@ -438,13 +377,12 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 
 static struct trailer_item *get_conf_item(const char *name)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	struct trailer_item *previous;
 
 	/* Look up item with same name */
-	for (previous = NULL, item = first_conf_item;
-	     item;
-	     previous = item, item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
@@ -454,12 +392,7 @@ static struct trailer_item *get_conf_item(const char *name)
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
-	if (!previous)
-		first_conf_item = item;
-	else {
-		previous->next = item;
-		item->previous = previous;
-	}
+	list_add_tail(&item->list, &conf_head);
 
 	return item;
 }
@@ -633,6 +566,7 @@ static struct trailer_item *create_trailer_item(const char *string)
 	struct strbuf val = STRBUF_INIT;
 	struct trailer_item *item;
 	int tok_len;
+	struct list_head *pos;
 
 	if (parse_trailer(&tok, &val, string))
 		return NULL;
@@ -640,7 +574,8 @@ static struct trailer_item *create_trailer_item(const char *string)
 	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (token_matches_item(tok.buf, item, tok_len))
 			return new_trailer_item(item,
 						strbuf_detach(&tok, NULL),
@@ -652,44 +587,34 @@ static struct trailer_item *create_trailer_item(const char *string)
 				strbuf_detach(&val, NULL));
 }
 
-static void add_trailer_item(struct trailer_item **first,
-			     struct trailer_item **last,
-			     struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, struct trailer_item *new)
 {
 	if (!new)
 		return;
-	if (!*last) {
-		*first = new;
-		*last = new;
-	} else {
-		(*last)->next = new;
-		new->previous = *last;
-		*last = new;
-	}
+	list_add_tail(&new->list, head);
 }
 
-static struct trailer_item *process_command_line_args(struct string_list *trailers)
+static void process_command_line_args(struct list_head *arg_head, 
+				      struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_first = NULL;
-	struct trailer_item *arg_tok_last = NULL;
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (item->conf.command) {
 			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+			add_trailer_item(arg_head, new);
 		}
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+		add_trailer_item(arg_head, new);
 	}
-
-	return arg_tok_first;
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -805,8 +730,7 @@ static void print_lines(FILE *outfile, struct strbuf **lines, int start, int end
 
 static int process_input_file(FILE *outfile,
 			      struct strbuf **lines,
-			      struct trailer_item **in_tok_first,
-			      struct trailer_item **in_tok_last)
+			      struct list_head *head)
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
@@ -829,18 +753,19 @@ static int process_input_file(FILE *outfile,
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char) {
 			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_first, in_tok_last, new);
+			add_trailer_item(head, new);
 		}
 	}
 
 	return trailer_end;
 }
 
-static void free_all(struct trailer_item **first)
+static void free_all(struct list_head *head)
 {
-	while (*first) {
-		struct trailer_item *item = remove_first(first);
-		free_trailer_item(item);
+	struct list_head *pos, *p;
+	list_for_each_safe(pos, p, head) {
+		list_del(pos);
+		free_trailer_item(list_entry(pos, struct trailer_item, list));
 	}
 }
 
@@ -877,9 +802,8 @@ static FILE *create_in_place_tempfile(const char *file)
 
 void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers)
 {
-	struct trailer_item *in_tok_first = NULL;
-	struct trailer_item *in_tok_last = NULL;
-	struct trailer_item *arg_tok_first;
+	LIST_HEAD(head);
+	LIST_HEAD(arg_head);
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
@@ -894,15 +818,15 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 		outfile = create_in_place_tempfile(file);
 
 	/* Print the lines before the trailers */
-	trailer_end = process_input_file(outfile, lines, &in_tok_first, &in_tok_last);
+	trailer_end = process_input_file(outfile, lines, &head);
 
-	arg_tok_first = process_command_line_args(trailers);
+	process_command_line_args(&arg_head, trailers);
 
-	process_trailers_lists(&in_tok_first, &in_tok_last, &arg_tok_first);
+	process_trailers_lists(&head, &arg_head);
 
-	print_all(outfile, in_tok_first, trim_empty);
+	print_all(outfile, &head, trim_empty);
 
-	free_all(&in_tok_first);
+	free_all(&head);
 
 	/* Print the lines after the trailers as is */
 	print_lines(outfile, lines, trailer_end, INT_MAX);
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v2 2/6] trailer: use list.h for doubly-linked list

[Jakub Narębski]

W dniu 13.10.2016 o 01:40, Jonathan Tan pisze:
> Replace the existing handwritten implementation of a doubly-linked list
> in trailer.c with the functions and macros from list.h. This
> significantly simplifies the code.
> ---
>  trailer.c | 258 ++++++++++++++++++++++----------------------------------------
>  1 file changed, 91 insertions(+), 167 deletions(-)

Very nice gains!

BTW. could you sign (Signed-off-by) your patches? TIA.

Best,
-- 
Jakub Narębski

Re: [PATCH v2 2/6] trailer: use list.h for doubly-linked list

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> Replace the existing handwritten implementation of a doubly-linked list
> in trailer.c with the functions and macros from list.h. This
> significantly simplifies the code.
> ---

The handcrafted one in trailer.c somehow did not use the common
practice of using a doubly-linked cycle as a doubly-linked list with
a designated fake element as the pointers to the first and to the
last elements of the list (instead it used NULL as the "this is the
end in this direction" convention just like a common singly-linked
list), and this update removes the need for special cases handling
the elements at the beginning and at the end that comes from that
choice by switching to list.h macros.  update_last/update_first can
go, two parameters that were passed to point at the variables for
the beginning and the end can go, the special cases for the initial
condition in add_trailer_item() can go, all thanks to this change.

Very nice.

>  trailer.c | 258 ++++++++++++++++++++++----------------------------------------
>  1 file changed, 91 insertions(+), 167 deletions(-)

[PATCH v2 3/6] trailer: streamline trailer item create and add

[Jonathan Tan]

Currently, creation and addition (to a list) of trailer items are spread
across multiple functions. Streamline this by only having 2 functions:
one to parse the user-supplied string, and one to add the parsed
information to a list.
---
 trailer.c | 130 +++++++++++++++++++++++++++++---------------------------------
 1 file changed, 60 insertions(+), 70 deletions(-)

diff --git a/trailer.c b/trailer.c
index 0afa240..54cc930 100644
--- a/trailer.c
+++ b/trailer.c
@@ -500,10 +500,31 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *trailer)
+static const char *token_from_item(struct trailer_item *item, char *tok)
+{
+	if (item->conf.key)
+		return item->conf.key;
+	if (tok)
+		return tok;
+	return item->conf.name;
+}
+
+static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+{
+	if (!strncasecmp(tok, item->conf.name, tok_len))
+		return 1;
+	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
+}
+
+static int parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
+	struct trailer_item *item;
+	int tok_len;
+	struct list_head *pos;
+
 	strbuf_addstr(&seps, separators);
 	strbuf_addch(&seps, '=');
 	len = strcspn(trailer, seps.buf);
@@ -523,74 +544,31 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *tra
 		strbuf_addstr(tok, trailer);
 		strbuf_trim(tok);
 	}
-	return 0;
-}
-
-static const char *token_from_item(struct trailer_item *item, char *tok)
-{
-	if (item->conf.key)
-		return item->conf.key;
-	if (tok)
-		return tok;
-	return item->conf.name;
-}
-
-static struct trailer_item *new_trailer_item(struct trailer_item *conf_item,
-					     char *tok, char *val)
-{
-	struct trailer_item *new = xcalloc(sizeof(*new), 1);
-	new->value = val ? val : xstrdup("");
-
-	if (conf_item) {
-		duplicate_conf(&new->conf, &conf_item->conf);
-		new->token = xstrdup(token_from_item(conf_item, tok));
-		free(tok);
-	} else {
-		duplicate_conf(&new->conf, &default_conf_info);
-		new->token = tok;
-	}
-
-	return new;
-}
-
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
-{
-	if (!strncasecmp(tok, item->conf.name, tok_len))
-		return 1;
-	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
-}
-
-static struct trailer_item *create_trailer_item(const char *string)
-{
-	struct strbuf tok = STRBUF_INIT;
-	struct strbuf val = STRBUF_INIT;
-	struct trailer_item *item;
-	int tok_len;
-	struct list_head *pos;
-
-	if (parse_trailer(&tok, &val, string))
-		return NULL;
-
-	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
+	tok_len = token_len_without_separator(tok->buf, tok->len);
+	*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (token_matches_item(tok.buf, item, tok_len))
-			return new_trailer_item(item,
-						strbuf_detach(&tok, NULL),
-						strbuf_detach(&val, NULL));
+		if (token_matches_item(tok->buf, item, tok_len)) {
+			char *tok_buf = strbuf_detach(tok, NULL);
+			*conf = &item->conf;
+			strbuf_addstr(tok, token_from_item(item, tok_buf));
+			free(tok_buf);
+			break;
+		}
 	}
 
-	return new_trailer_item(NULL,
-				strbuf_detach(&tok, NULL),
-				strbuf_detach(&val, NULL));
+	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, char *tok, char *val,
+			     const struct conf_info *conf)
 {
-	if (!new)
-		return;
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
@@ -599,21 +577,28 @@ static void process_command_line_args(struct list_head *arg_head,
 {
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (item->conf.command) {
-			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(arg_head, new);
-		}
+		if (item->conf.command)
+			add_trailer_item(arg_head,
+					 xstrdup(token_from_item(item, NULL)),
+					 xstrdup(""),
+					 &item->conf);
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(arg_head, new);
+		if (!parse_trailer(&tok, &val, &conf, tr->string))
+			add_trailer_item(arg_head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 }
 
@@ -734,6 +719,9 @@ static int process_input_file(FILE *outfile,
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -751,10 +739,12 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char) {
-			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(head, new);
-		}
+		if (lines[i]->buf[0] != comment_line_char &&
+		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+			add_trailer_item(head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 4/6] trailer: make args have their own struct

[Jonathan Tan]

Improve type safety by making arguments (whether from configuration or
from the command line) have their own "struct arg_item" type, separate
from the "struct trailer_item" type used to represent the trailers in
the buffer being manipulated.

This change also prepares "struct trailer_item" to be further
differentiated from "struct arg_item" in future patches.
---
 trailer.c | 135 +++++++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 85 insertions(+), 50 deletions(-)

diff --git a/trailer.c b/trailer.c
index 54cc930..a9ed3f8 100644
--- a/trailer.c
+++ b/trailer.c
@@ -29,6 +29,12 @@ struct trailer_item {
 	struct list_head list;
 	char *token;
 	char *value;
+};
+
+struct arg_item {
+	struct list_head list;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -62,7 +68,7 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(struct trailer_item *a, struct trailer_item *b)
+static int same_token(struct trailer_item *a, struct arg_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -71,12 +77,12 @@ static int same_token(struct trailer_item *a, struct trailer_item *b)
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(struct trailer_item *a, struct trailer_item *b)
+static int same_value(struct trailer_item *a, struct arg_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(struct trailer_item *a, struct trailer_item *b)
+static int same_trailer(struct trailer_item *a, struct arg_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -98,6 +104,13 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 
 static void free_trailer_item(struct trailer_item *item)
 {
+	free(item->token);
+	free(item->value);
+	free(item);
+}
+
+static void free_arg_item(struct arg_item *item)
+{
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
@@ -137,17 +150,29 @@ static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 	}
 }
 
+static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
+{
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = arg_tok->token;
+	new->value = arg_tok->value;
+	arg_tok->token = arg_tok->value = NULL;
+	free_arg_item(arg_tok);
+	return new;
+}
+
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok)
+				  struct arg_item *arg_tok)
 {
-	if (after_or_end(arg_tok->conf.where))
-		list_add(&arg_tok->list, &on_tok->list);
+	int aoe = after_or_end(arg_tok->conf.where);
+	struct trailer_item *to_add = trailer_from_arg(arg_tok);
+	if (aoe)
+		list_add(&to_add->list, &on_tok->list);
 	else
-		list_add_tail(&arg_tok->list, &on_tok->list);
+		list_add_tail(&to_add->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
-			      struct trailer_item *arg_tok,
+			      struct arg_item *arg_tok,
 			      int check_all,
 			      struct list_head *head)
 {
@@ -200,7 +225,7 @@ static char *apply_command(const char *command, const char *arg)
 	return result;
 }
 
-static void apply_item_command(struct trailer_item *in_tok, struct trailer_item *arg_tok)
+static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg_tok)
 {
 	if (arg_tok->conf.command) {
 		const char *arg;
@@ -218,13 +243,13 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 }
 
 static void apply_arg_if_exists(struct trailer_item *in_tok,
-				struct trailer_item *arg_tok,
+				struct arg_item *arg_tok,
 				struct trailer_item *on_tok,
 				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
@@ -241,39 +266,41 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		if (check_if_different(in_tok, arg_tok, 1, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
 		if (check_if_different(on_tok, arg_tok, 0, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	}
 }
 
 static void apply_arg_if_missing(struct list_head *head,
-				 struct trailer_item *arg_tok)
+				 struct arg_item *arg_tok)
 {
 	enum action_where where;
+	struct trailer_item *to_add;
 
 	switch (arg_tok->conf.if_missing) {
 	case MISSING_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
 		apply_item_command(NULL, arg_tok);
+		to_add = trailer_from_arg(arg_tok);
 		if (after_or_end(where))
-			list_add_tail(&arg_tok->list, head);
+			list_add_tail(&to_add->list, head);
 		else
-			list_add(&arg_tok->list, head);
+			list_add(&to_add->list, head);
 	}
 }
 
 static int find_same_and_apply_arg(struct list_head *head,
-				   struct trailer_item *arg_tok)
+				   struct arg_item *arg_tok)
 {
 	struct list_head *pos;
 	struct trailer_item *in_tok;
@@ -306,11 +333,11 @@ static void process_trailers_lists(struct list_head *head,
 				   struct list_head *arg_head)
 {
 	struct list_head *pos, *p;
-	struct trailer_item *arg_tok;
+	struct arg_item *arg_tok;
 
 	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
-		arg_tok = list_entry(pos, struct trailer_item, list);
+		arg_tok = list_entry(pos, struct arg_item, list);
 
 		list_del(pos);
 
@@ -375,20 +402,20 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 		dst->command = xstrdup(src->command);
 }
 
-static struct trailer_item *get_conf_item(const char *name)
+static struct arg_item *get_conf_item(const char *name)
 {
 	struct list_head *pos;
-	struct trailer_item *item;
+	struct arg_item *item;
 
 	/* Look up item with same name */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
 
 	/* Item does not already exists, create it */
-	item = xcalloc(sizeof(struct trailer_item), 1);
+	item = xcalloc(sizeof(*item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
@@ -442,7 +469,7 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v
 static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 {
 	const char *trailer_item, *variable_name;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct conf_info *conf;
 	char *name = NULL;
 	enum trailer_info_type type;
@@ -500,7 +527,7 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static const char *token_from_item(struct trailer_item *item, char *tok)
+static const char *token_from_item(struct arg_item *item, char *tok)
 {
 	if (item->conf.key)
 		return item->conf.key;
@@ -509,7 +536,7 @@ static const char *token_from_item(struct trailer_item *item, char *tok)
 	return item->conf.name;
 }
 
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+static int token_matches_item(const char *tok, struct arg_item *item, int tok_len)
 {
 	if (!strncasecmp(tok, item->conf.name, tok_len))
 		return 1;
@@ -521,7 +548,7 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
-	struct trailer_item *item;
+	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
@@ -547,12 +574,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 
 	/* Lookup if the token matches something in the config */
 	tok_len = token_len_without_separator(tok->buf, tok->len);
-	*conf = &default_conf_info;
+	if (conf)
+		*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (token_matches_item(tok->buf, item, tok_len)) {
 			char *tok_buf = strbuf_detach(tok, NULL);
-			*conf = &item->conf;
+			if (conf)
+				*conf = &item->conf;
 			strbuf_addstr(tok, token_from_item(item, tok_buf));
 			free(tok_buf);
 			break;
@@ -562,43 +591,51 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val,
-			     const struct conf_info *conf)
+static void add_trailer_item(struct list_head *head, char *tok, char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
-	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
+static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
+			 const struct conf_info *conf)
+{
+	struct arg_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
+	list_add_tail(&new->list, arg_head);
+}
+
 static void process_command_line_args(struct list_head *arg_head, 
 				      struct string_list *trailers)
 {
 	struct string_list_item *tr;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
 	const struct conf_info *conf;
 	struct list_head *pos;
 
-	/* Add a trailer item for each configured trailer with a command */
+	/* Add an arg item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (item->conf.command)
-			add_trailer_item(arg_head,
-					 xstrdup(token_from_item(item, NULL)),
-					 xstrdup(""),
-					 &item->conf);
+			add_arg_item(arg_head,
+				     xstrdup(token_from_item(item, NULL)),
+				     xstrdup(""),
+				     &item->conf);
 	}
 
-	/* Add a trailer item for each trailer on the command line */
+	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		if (!parse_trailer(&tok, &val, &conf, tr->string))
-			add_trailer_item(arg_head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+			add_arg_item(arg_head,
+				     strbuf_detach(&tok, NULL),
+				     strbuf_detach(&val, NULL),
+				     conf);
 	}
 }
 
@@ -721,7 +758,6 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
-	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -740,11 +776,10 @@ static int process_input_file(FILE *outfile,
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+					 strbuf_detach(&val, NULL));
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 5/6] trailer: allow non-trailers in trailer block

[Jonathan Tan]

Currently, interpret-trailers requires all lines of a trailer block to
be trailers (or comments) - if not it would not identify that block as a
trailer block, and thus create its own trailer block, inserting a blank
line.  For example:

  echo -e "\na: b\nnot trailer" |
  git interpret-trailers --trailer "c: d"

would result in:

  a: b
  not trailer

  c: d

Relax the definition of a trailer block to only require 1 trailer, so
that trailers can be directly added to such blocks, resulting in:

  a: b
  not trailer
  c: d

This allows arbitrary lines to be included in trailer blocks, like those
in [1], and still allow interpret-trailers to be used.

This change also makes comments in the trailer block be treated as any
other non-trailer line, preserving them in the output of
interpret-trailers.

[1]
https://kernel.googlesource.com/pub/scm/linux/kernel/git/stable/linux-stable/+/e7d316a02f683864a12389f8808570e37fb90aa3
---
 Documentation/git-interpret-trailers.txt |  3 +-
 t/t7513-interpret-trailers.sh            | 35 +++++++++++++++
 trailer.c                                | 77 ++++++++++++++++++++++----------
 3 files changed, 90 insertions(+), 25 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 93d1db6..c480da6 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -48,7 +48,8 @@ with only spaces at the end of the commit message part, one blank line
 will be added before the new trailer.
 
 Existing trailers are extracted from the input message by looking for
-a group of one or more lines that contain a colon (by default), where
+a group of one or more lines in which at least one line contains a 
+colon (by default), where
 the group is preceded by one or more empty (or whitespace-only) lines.
 The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index aee785c..7f5cd2a 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -126,6 +126,37 @@ test_expect_success 'with multiline title in the message' '
 	test_cmp expected actual
 '
 
+test_expect_success 'with non-trailer lines mixed with trailer lines' '
+	cat >patch <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines only' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
@@ -257,6 +288,8 @@ test_expect_success 'with message that has comments' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
@@ -286,6 +319,8 @@ test_expect_success 'with message that has an old style conflict block' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
diff --git a/trailer.c b/trailer.c
index a9ed3f8..d6dfc7a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,6 +27,10 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct list_head list;
+	/*
+	 * If this is not a trailer line, the line is stored in value
+	 * (excluding the terminating newline) and token is NULL.
+	 */
 	char *token;
 	char *value;
 };
@@ -70,9 +74,14 @@ static size_t token_len_without_separator(const char *token, size_t len)
 
 static int same_token(struct trailer_item *a, struct arg_item *b)
 {
-	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
-	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
-	size_t min_len = (a_len > b_len) ? b_len : a_len;
+	size_t a_len, b_len, min_len;
+
+	if (!a->token)
+		return 0;
+
+	a_len = token_len_without_separator(a->token, strlen(a->token));
+	b_len = token_len_without_separator(b->token, strlen(b->token));
+	min_len = (a_len > b_len) ? b_len : a_len;
 
 	return !strncasecmp(a->token, b->token, min_len);
 }
@@ -130,7 +139,14 @@ static char last_non_space_char(const char *s)
 
 static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 {
-	char c = last_non_space_char(tok);
+	char c;
+
+	if (!tok) {
+		fprintf(outfile, "%s\n", val);
+		return;
+	}
+
+	c = last_non_space_char(tok);
 	if (!c)
 		return;
 	if (strchr(separators, c))
@@ -543,8 +559,16 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
 	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
 }
 
+/*
+ * Parse the given trailer into token and value parts.
+ *
+ * If the given trailer does not have a separator (and thus cannot be separated
+ * into token and value parts), it is treated as a token (if parse_as_arg) or
+ * as a non-trailer line (if not parse_as_arg).
+ */
 static int parse_trailer(struct strbuf *tok, struct strbuf *val,
-			 const struct conf_info **conf, const char *trailer)
+			 const struct conf_info **conf, const char *trailer,
+			 int parse_as_arg)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
@@ -557,11 +581,18 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	len = strcspn(trailer, seps.buf);
 	strbuf_release(&seps);
 	if (len == 0) {
-		int l = strlen(trailer);
+		int l;
+		if (!parse_as_arg)
+			return -1;
+
+		l = strlen(trailer);
 		while (l > 0 && isspace(trailer[l - 1]))
 			l--;
 		return error(_("empty trailer token in trailer '%.*s'"), l, trailer);
 	}
+	if (!parse_as_arg && len == strlen(trailer))
+		return -1;
+
 	if (len < strlen(trailer)) {
 		strbuf_add(tok, trailer, len);
 		strbuf_trim(tok);
@@ -631,7 +662,7 @@ static void process_command_line_args(struct list_head *arg_head,
 
 	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		if (!parse_trailer(&tok, &val, &conf, tr->string))
+		if (!parse_trailer(&tok, &val, &conf, tr->string, 1))
 			add_arg_item(arg_head,
 				     strbuf_detach(&tok, NULL),
 				     strbuf_detach(&val, NULL),
@@ -683,7 +714,7 @@ static int find_patch_start(struct strbuf **lines, int count)
  */
 static int find_trailer_start(struct strbuf **lines, int count)
 {
-	int start, end_of_title, only_spaces = 1;
+	int start, end_of_title, only_spaces = 1, trailer_found = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -699,22 +730,17 @@ static int find_trailer_start(struct strbuf **lines, int count)
 	 * for a line with only spaces before lines with one separator.
 	 */
 	for (start = count - 1; start >= end_of_title; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
-			return start + 1;
+			return trailer_found ? start + 1 : count;
 		}
-		if (strcspn(lines[start]->buf, separators) < lines[start]->len) {
-			if (only_spaces)
-				only_spaces = 0;
-			continue;
-		}
-		return count;
+		only_spaces = 0;
+		if (strcspn(lines[start]->buf, separators) < lines[start]->len)
+			trailer_found = 1;
 	}
 
-	return only_spaces ? count : 0;
+	return count;
 }
 
 /* Get the index of the end of the trailers */
@@ -735,11 +761,8 @@ static int find_trailer_end(struct strbuf **lines, int patch_start)
 
 static int has_blank_line_before(struct strbuf **lines, int start)
 {
-	for (;start >= 0; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
+	if (start >= 0)
 		return contains_only_spaces(lines[start]->buf);
-	}
 	return 0;
 }
 
@@ -775,11 +798,17 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
+		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		else {
+			strbuf_addbuf(&val, lines[i]);
+			strbuf_strip_suffix(&val, "\n");
+			add_trailer_item(head,
+					 NULL,
+					 strbuf_detach(&val, NULL));
+		}
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v2 6/6] trailer: support values folded to multiple lines

[Jonathan Tan]

Currently, interpret-trailers requires that a trailer be only on 1 line.
For example:

  a: first line
     second line

would be interpreted as one trailer line followed by one non-trailer line.

Make interpret-trailers support RFC 822-style folding, treating those
lines as one logical trailer.
---
 Documentation/git-interpret-trailers.txt |   7 +-
 t/t7513-interpret-trailers.sh            | 139 +++++++++++++++++++++++++++++++
 trailer.c                                |  22 +++--
 3 files changed, 160 insertions(+), 8 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index c480da6..cfec636 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -57,11 +57,12 @@ minus signs start the patch part of the message.
 
 When reading trailers, there can be whitespaces before and after the
 token, the separator and the value. There can also be whitespaces
-inside the token and the value.
+inside the token and the value. The value may be split over multiple lines with
+each subsequent line starting with whitespace, like the "folding" in RFC 822.
 
 Note that 'trailers' do not follow and are not intended to follow many
-rules for RFC 822 headers. For example they do not follow the line
-folding rules, the encoding rules and probably many other rules.
+rules for RFC 822 headers. For example they do not follow
+the encoding rules and probably many other rules.
 
 OPTIONS
 -------
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 7f5cd2a..31db699 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -157,6 +157,145 @@ test_expect_success 'with non-trailer lines only' '
 	test_cmp expected actual
 '
 
+test_expect_success 'multiline field treated as atomic for placement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		name: value
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for replacement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		another: trailer
+		name: value
+	EOF
+	test_config trailer.name.ifexists replace &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for difference check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.ifexists addIfDifferent &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line
+		QQQQQsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for neighbor check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	test_config trailer.name.ifexists addIfDifferentNeighbor &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		name: first line
+		QQQQQsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index d6dfc7a..ef276e6 100644
--- a/trailer.c
+++ b/trailer.c
@@ -248,7 +248,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg
 		if (arg_tok->value && arg_tok->value[0]) {
 			arg = arg_tok->value;
 		} else {
-			if (in_tok && in_tok->value)
+			if (in_tok)
 				arg = xstrdup(in_tok->value);
 			else
 				arg = xstrdup("");
@@ -622,12 +622,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val)
+static struct trailer_item *add_trailer_item(struct list_head *head, char *tok,
+					     char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
 	list_add_tail(&new->list, head);
+	return new;
 }
 
 static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
@@ -781,6 +783,7 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
+	struct trailer_item *last = NULL;
 
 	/* Get the line count */
 	while (lines[count])
@@ -798,16 +801,25 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
+		if (last && isspace(lines[i]->buf[0])) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addf(&sb, "%s\n%s", last->value, lines[i]->buf);
+			strbuf_strip_suffix(&sb, "\n");
+			free(last->value);
+			last->value = strbuf_detach(&sb, NULL);
+			continue;
+		}
 		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
-			add_trailer_item(head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL));
+			last = add_trailer_item(head,
+						strbuf_detach(&tok, NULL),
+						strbuf_detach(&val, NULL));
 		else {
 			strbuf_addbuf(&val, lines[i]);
 			strbuf_strip_suffix(&val, "\n");
 			add_trailer_item(head,
 					 NULL,
 					 strbuf_detach(&val, NULL));
+			last = NULL;
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

[PATCH v3 0/6] allow non-trailers and multiple-line trailers

[Jonathan Tan]

Ah, I knew I forgot something. These are exactly the same as v2, except
that these are signed off.

Jonathan Tan (6):
  trailer: improve const correctness
  trailer: use list.h for doubly-linked list
  trailer: streamline trailer item create and add
  trailer: make args have their own struct
  trailer: allow non-trailers in trailer block
  trailer: support values folded to multiple lines

 Documentation/git-interpret-trailers.txt |  10 +-
 t/t7513-interpret-trailers.sh            | 174 ++++++++++
 trailer.c                                | 538 +++++++++++++++----------------
 3 files changed, 444 insertions(+), 278 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

[PATCH v3 1/6] trailer: improve const correctness

[Jonathan Tan]

Change "const char *" to "char *" in struct trailer_item and in the
return value of apply_command (since those strings are owned strings).

Change "struct conf_info *" to "const struct conf_info *" (since that
struct is not modified).

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/trailer.c b/trailer.c
index c6ea9ac..1f191b2 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,8 +27,8 @@ static struct conf_info default_conf_info;
 struct trailer_item {
 	struct trailer_item *previous;
 	struct trailer_item *next;
-	const char *token;
-	const char *value;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -95,8 +95,8 @@ static void free_trailer_item(struct trailer_item *item)
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
-	free((char *)item->token);
-	free((char *)item->value);
+	free(item->token);
+	free(item->value);
 	free(item);
 }
 
@@ -215,13 +215,13 @@ static struct trailer_item *remove_first(struct trailer_item **first)
 	return item;
 }
 
-static const char *apply_command(const char *command, const char *arg)
+static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *argv[] = {NULL, NULL};
-	const char *result;
+	char *result;
 
 	strbuf_addstr(&cmd, command);
 	if (arg)
@@ -425,7 +425,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
 	return 0;
 }
 
-static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
+static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 {
 	*dst = *src;
 	if (src->name)
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v3 1/6] trailer: improve const correctness

[Stefan Beller]

On Fri, Oct 14, 2016 at 10:37 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> Change "const char *" to "char *" in struct trailer_item and in the
> return value of apply_command (since those strings are owned strings).
>
> Change "struct conf_info *" to "const struct conf_info *" (since that
> struct is not modified).
>
> Signed-off-by: Jonathan Tan <jonathantanmy@google.com>

Reviewed-by Stefan Beller <sbeller@google.com>

> ---
>  trailer.c | 14 +++++++-------
>  1 file changed, 7 insertions(+), 7 deletions(-)
>
> diff --git a/trailer.c b/trailer.c
> index c6ea9ac..1f191b2 100644
> --- a/trailer.c
> +++ b/trailer.c
> @@ -27,8 +27,8 @@ static struct conf_info default_conf_info;
>  struct trailer_item {
>         struct trailer_item *previous;
>         struct trailer_item *next;
> -       const char *token;
> -       const char *value;
> +       char *token;
> +       char *value;
>         struct conf_info conf;
>  };
>
> @@ -95,8 +95,8 @@ static void free_trailer_item(struct trailer_item *item)
>         free(item->conf.name);
>         free(item->conf.key);
>         free(item->conf.command);
> -       free((char *)item->token);
> -       free((char *)item->value);
> +       free(item->token);
> +       free(item->value);
>         free(item);
>  }
>
> @@ -215,13 +215,13 @@ static struct trailer_item *remove_first(struct trailer_item **first)
>         return item;
>  }
>
> -static const char *apply_command(const char *command, const char *arg)
> +static char *apply_command(const char *command, const char *arg)
>  {
>         struct strbuf cmd = STRBUF_INIT;
>         struct strbuf buf = STRBUF_INIT;
>         struct child_process cp = CHILD_PROCESS_INIT;
>         const char *argv[] = {NULL, NULL};
> -       const char *result;
> +       char *result;
>
>         strbuf_addstr(&cmd, command);
>         if (arg)
> @@ -425,7 +425,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
>         return 0;
>  }
>
> -static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
> +static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
>  {
>         *dst = *src;
>         if (src->name)
> --
> 2.8.0.rc3.226.g39d4020
>

[PATCH v3 2/6] trailer: use list.h for doubly-linked list

[Jonathan Tan]

Replace the existing handwritten implementation of a doubly-linked list
in trailer.c with the functions and macros from list.h. This
significantly simplifies the code.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 258 ++++++++++++++++++++++----------------------------------------
 1 file changed, 91 insertions(+), 167 deletions(-)

diff --git a/trailer.c b/trailer.c
index 1f191b2..0afa240 100644
--- a/trailer.c
+++ b/trailer.c
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "tempfile.h"
 #include "trailer.h"
+#include "list.h"
 /*
  * Copyright (c) 2013, 2014 Christian Couder <chriscool@tuxfamily.org>
  */
@@ -25,19 +26,24 @@ struct conf_info {
 static struct conf_info default_conf_info;
 
 struct trailer_item {
-	struct trailer_item *previous;
-	struct trailer_item *next;
+	struct list_head list;
 	char *token;
 	char *value;
 	struct conf_info conf;
 };
 
-static struct trailer_item *first_conf_item;
+LIST_HEAD(conf_head);
 
 static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+/* Iterate over the elements of the list. */
+#define list_for_each_dir(pos, head, is_reverse) \
+	for (pos = is_reverse ? (head)->prev : (head)->next; \
+		pos != (head); \
+		pos = is_reverse ? pos->prev : pos->next)
+
 static int after_or_end(enum action_where where)
 {
 	return (where == WHERE_AFTER) || (where == WHERE_END);
@@ -120,101 +126,49 @@ static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 		fprintf(outfile, "%s%c %s\n", tok, separators[0], val);
 }
 
-static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
+static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	for (item = first; item; item = item->next) {
+	list_for_each(pos, head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!trim_empty || strlen(item->value) > 0)
 			print_tok_val(outfile, item->token, item->value);
 	}
 }
 
-static void update_last(struct trailer_item **last)
-{
-	if (*last)
-		while ((*last)->next != NULL)
-			*last = (*last)->next;
-}
-
-static void update_first(struct trailer_item **first)
-{
-	if (*first)
-		while ((*first)->previous != NULL)
-			*first = (*first)->previous;
-}
-
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok,
-				  struct trailer_item **first,
-				  struct trailer_item **last)
-{
-	if (after_or_end(arg_tok->conf.where)) {
-		arg_tok->next = on_tok->next;
-		on_tok->next = arg_tok;
-		arg_tok->previous = on_tok;
-		if (arg_tok->next)
-			arg_tok->next->previous = arg_tok;
-		update_last(last);
-	} else {
-		arg_tok->previous = on_tok->previous;
-		on_tok->previous = arg_tok;
-		arg_tok->next = on_tok;
-		if (arg_tok->previous)
-			arg_tok->previous->next = arg_tok;
-		update_first(first);
-	}
+				  struct trailer_item *arg_tok)
+{
+	if (after_or_end(arg_tok->conf.where))
+		list_add(&arg_tok->list, &on_tok->list);
+	else
+		list_add_tail(&arg_tok->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
 			      struct trailer_item *arg_tok,
-			      int check_all)
+			      int check_all,
+			      struct list_head *head)
 {
 	enum action_where where = arg_tok->conf.where;
+	struct list_head *next_head;
 	do {
-		if (!in_tok)
-			return 1;
 		if (same_trailer(in_tok, arg_tok))
 			return 0;
 		/*
 		 * if we want to add a trailer after another one,
 		 * we have to check those before this one
 		 */
-		in_tok = after_or_end(where) ? in_tok->previous : in_tok->next;
+		next_head = after_or_end(where) ? in_tok->list.prev
+						: in_tok->list.next;
+		if (next_head == head)
+			break;
+		in_tok = list_entry(next_head, struct trailer_item, list);
 	} while (check_all);
 	return 1;
 }
 
-static void remove_from_list(struct trailer_item *item,
-			     struct trailer_item **first,
-			     struct trailer_item **last)
-{
-	struct trailer_item *next = item->next;
-	struct trailer_item *previous = item->previous;
-
-	if (next) {
-		item->next->previous = previous;
-		item->next = NULL;
-	} else if (last)
-		*last = previous;
-
-	if (previous) {
-		item->previous->next = next;
-		item->previous = NULL;
-	} else if (first)
-		*first = next;
-}
-
-static struct trailer_item *remove_first(struct trailer_item **first)
-{
-	struct trailer_item *item = *first;
-	*first = item->next;
-	if (item->next) {
-		item->next->previous = NULL;
-		item->next = NULL;
-	}
-	return item;
-}
-
 static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
@@ -266,8 +220,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 static void apply_arg_if_exists(struct trailer_item *in_tok,
 				struct trailer_item *arg_tok,
 				struct trailer_item *on_tok,
-				struct trailer_item **in_tok_first,
-				struct trailer_item **in_tok_last)
+				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
@@ -275,40 +228,34 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		remove_from_list(in_tok, in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
+		list_del(&in_tok->list);
 		free_trailer_item(in_tok);
 		break;
 	case EXISTS_ADD:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(in_tok, arg_tok, 1))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(in_tok, arg_tok, 1, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(on_tok, arg_tok, 0))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(on_tok, arg_tok, 0, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	}
 }
 
-static void apply_arg_if_missing(struct trailer_item **in_tok_first,
-				 struct trailer_item **in_tok_last,
+static void apply_arg_if_missing(struct list_head *head,
 				 struct trailer_item *arg_tok)
 {
-	struct trailer_item **in_tok;
 	enum action_where where;
 
 	switch (arg_tok->conf.if_missing) {
@@ -317,68 +264,60 @@ static void apply_arg_if_missing(struct trailer_item **in_tok_first,
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
-		in_tok = after_or_end(where) ? in_tok_last : in_tok_first;
 		apply_item_command(NULL, arg_tok);
-		if (*in_tok) {
-			add_arg_to_input_list(*in_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		} else {
-			*in_tok_first = arg_tok;
-			*in_tok_last = arg_tok;
-		}
-		break;
+		if (after_or_end(where))
+			list_add_tail(&arg_tok->list, head);
+		else
+			list_add(&arg_tok->list, head);
 	}
 }
 
-static int find_same_and_apply_arg(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
+static int find_same_and_apply_arg(struct list_head *head,
 				   struct trailer_item *arg_tok)
 {
+	struct list_head *pos;
 	struct trailer_item *in_tok;
 	struct trailer_item *on_tok;
-	struct trailer_item *following_tok;
 
 	enum action_where where = arg_tok->conf.where;
 	int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE);
 	int backwards = after_or_end(where);
-	struct trailer_item *start_tok = backwards ? *in_tok_last : *in_tok_first;
+	struct trailer_item *start_tok;
 
-	for (in_tok = start_tok; in_tok; in_tok = following_tok) {
-		following_tok = backwards ? in_tok->previous : in_tok->next;
+	if (list_empty(head))
+		return 0;
+
+	start_tok = list_entry(backwards ? head->prev : head->next,
+			       struct trailer_item,
+			       list);
+
+	list_for_each_dir(pos, head, backwards) {
+		in_tok = list_entry(pos, struct trailer_item, list);
 		if (!same_token(in_tok, arg_tok))
 			continue;
 		on_tok = middle ? in_tok : start_tok;
-		apply_arg_if_exists(in_tok, arg_tok, on_tok,
-				    in_tok_first, in_tok_last);
+		apply_arg_if_exists(in_tok, arg_tok, on_tok, head);
 		return 1;
 	}
 	return 0;
 }
 
-static void process_trailers_lists(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item **arg_tok_first)
+static void process_trailers_lists(struct list_head *head,
+				   struct list_head *arg_head)
 {
+	struct list_head *pos, *p;
 	struct trailer_item *arg_tok;
-	struct trailer_item *next_arg;
-
-	if (!*arg_tok_first)
-		return;
 
-	for (arg_tok = *arg_tok_first; arg_tok; arg_tok = next_arg) {
+	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
+		arg_tok = list_entry(pos, struct trailer_item, list);
 
-		next_arg = arg_tok->next;
-		remove_from_list(arg_tok, arg_tok_first, NULL);
+		list_del(pos);
 
-		applied = find_same_and_apply_arg(in_tok_first,
-						  in_tok_last,
-						  arg_tok);
+		applied = find_same_and_apply_arg(head, arg_tok);
 
 		if (!applied)
-			apply_arg_if_missing(in_tok_first,
-					     in_tok_last,
-					     arg_tok);
+			apply_arg_if_missing(head, arg_tok);
 	}
 }
 
@@ -438,13 +377,12 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 
 static struct trailer_item *get_conf_item(const char *name)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	struct trailer_item *previous;
 
 	/* Look up item with same name */
-	for (previous = NULL, item = first_conf_item;
-	     item;
-	     previous = item, item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
@@ -454,12 +392,7 @@ static struct trailer_item *get_conf_item(const char *name)
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
-	if (!previous)
-		first_conf_item = item;
-	else {
-		previous->next = item;
-		item->previous = previous;
-	}
+	list_add_tail(&item->list, &conf_head);
 
 	return item;
 }
@@ -633,6 +566,7 @@ static struct trailer_item *create_trailer_item(const char *string)
 	struct strbuf val = STRBUF_INIT;
 	struct trailer_item *item;
 	int tok_len;
+	struct list_head *pos;
 
 	if (parse_trailer(&tok, &val, string))
 		return NULL;
@@ -640,7 +574,8 @@ static struct trailer_item *create_trailer_item(const char *string)
 	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (token_matches_item(tok.buf, item, tok_len))
 			return new_trailer_item(item,
 						strbuf_detach(&tok, NULL),
@@ -652,44 +587,34 @@ static struct trailer_item *create_trailer_item(const char *string)
 				strbuf_detach(&val, NULL));
 }
 
-static void add_trailer_item(struct trailer_item **first,
-			     struct trailer_item **last,
-			     struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, struct trailer_item *new)
 {
 	if (!new)
 		return;
-	if (!*last) {
-		*first = new;
-		*last = new;
-	} else {
-		(*last)->next = new;
-		new->previous = *last;
-		*last = new;
-	}
+	list_add_tail(&new->list, head);
 }
 
-static struct trailer_item *process_command_line_args(struct string_list *trailers)
+static void process_command_line_args(struct list_head *arg_head, 
+				      struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_first = NULL;
-	struct trailer_item *arg_tok_last = NULL;
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (item->conf.command) {
 			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+			add_trailer_item(arg_head, new);
 		}
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+		add_trailer_item(arg_head, new);
 	}
-
-	return arg_tok_first;
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -805,8 +730,7 @@ static void print_lines(FILE *outfile, struct strbuf **lines, int start, int end
 
 static int process_input_file(FILE *outfile,
 			      struct strbuf **lines,
-			      struct trailer_item **in_tok_first,
-			      struct trailer_item **in_tok_last)
+			      struct list_head *head)
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
@@ -829,18 +753,19 @@ static int process_input_file(FILE *outfile,
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char) {
 			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_first, in_tok_last, new);
+			add_trailer_item(head, new);
 		}
 	}
 
 	return trailer_end;
 }
 
-static void free_all(struct trailer_item **first)
+static void free_all(struct list_head *head)
 {
-	while (*first) {
-		struct trailer_item *item = remove_first(first);
-		free_trailer_item(item);
+	struct list_head *pos, *p;
+	list_for_each_safe(pos, p, head) {
+		list_del(pos);
+		free_trailer_item(list_entry(pos, struct trailer_item, list));
 	}
 }
 
@@ -877,9 +802,8 @@ static FILE *create_in_place_tempfile(const char *file)
 
 void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers)
 {
-	struct trailer_item *in_tok_first = NULL;
-	struct trailer_item *in_tok_last = NULL;
-	struct trailer_item *arg_tok_first;
+	LIST_HEAD(head);
+	LIST_HEAD(arg_head);
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
@@ -894,15 +818,15 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 		outfile = create_in_place_tempfile(file);
 
 	/* Print the lines before the trailers */
-	trailer_end = process_input_file(outfile, lines, &in_tok_first, &in_tok_last);
+	trailer_end = process_input_file(outfile, lines, &head);
 
-	arg_tok_first = process_command_line_args(trailers);
+	process_command_line_args(&arg_head, trailers);
 
-	process_trailers_lists(&in_tok_first, &in_tok_last, &arg_tok_first);
+	process_trailers_lists(&head, &arg_head);
 
-	print_all(outfile, in_tok_first, trim_empty);
+	print_all(outfile, &head, trim_empty);
 
-	free_all(&in_tok_first);
+	free_all(&head);
 
 	/* Print the lines after the trailers as is */
 	print_lines(outfile, lines, trailer_end, INT_MAX);
-- 
2.8.0.rc3.226.g39d4020

[PATCH v3 3/6] trailer: streamline trailer item create and add

[Jonathan Tan]

Currently, creation and addition (to a list) of trailer items are spread
across multiple functions. Streamline this by only having 2 functions:
one to parse the user-supplied string, and one to add the parsed
information to a list.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 130 +++++++++++++++++++++++++++++---------------------------------
 1 file changed, 60 insertions(+), 70 deletions(-)

diff --git a/trailer.c b/trailer.c
index 0afa240..54cc930 100644
--- a/trailer.c
+++ b/trailer.c
@@ -500,10 +500,31 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *trailer)
+static const char *token_from_item(struct trailer_item *item, char *tok)
+{
+	if (item->conf.key)
+		return item->conf.key;
+	if (tok)
+		return tok;
+	return item->conf.name;
+}
+
+static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+{
+	if (!strncasecmp(tok, item->conf.name, tok_len))
+		return 1;
+	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
+}
+
+static int parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
+	struct trailer_item *item;
+	int tok_len;
+	struct list_head *pos;
+
 	strbuf_addstr(&seps, separators);
 	strbuf_addch(&seps, '=');
 	len = strcspn(trailer, seps.buf);
@@ -523,74 +544,31 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *tra
 		strbuf_addstr(tok, trailer);
 		strbuf_trim(tok);
 	}
-	return 0;
-}
-
-static const char *token_from_item(struct trailer_item *item, char *tok)
-{
-	if (item->conf.key)
-		return item->conf.key;
-	if (tok)
-		return tok;
-	return item->conf.name;
-}
-
-static struct trailer_item *new_trailer_item(struct trailer_item *conf_item,
-					     char *tok, char *val)
-{
-	struct trailer_item *new = xcalloc(sizeof(*new), 1);
-	new->value = val ? val : xstrdup("");
-
-	if (conf_item) {
-		duplicate_conf(&new->conf, &conf_item->conf);
-		new->token = xstrdup(token_from_item(conf_item, tok));
-		free(tok);
-	} else {
-		duplicate_conf(&new->conf, &default_conf_info);
-		new->token = tok;
-	}
-
-	return new;
-}
-
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
-{
-	if (!strncasecmp(tok, item->conf.name, tok_len))
-		return 1;
-	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
-}
-
-static struct trailer_item *create_trailer_item(const char *string)
-{
-	struct strbuf tok = STRBUF_INIT;
-	struct strbuf val = STRBUF_INIT;
-	struct trailer_item *item;
-	int tok_len;
-	struct list_head *pos;
-
-	if (parse_trailer(&tok, &val, string))
-		return NULL;
-
-	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
+	tok_len = token_len_without_separator(tok->buf, tok->len);
+	*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (token_matches_item(tok.buf, item, tok_len))
-			return new_trailer_item(item,
-						strbuf_detach(&tok, NULL),
-						strbuf_detach(&val, NULL));
+		if (token_matches_item(tok->buf, item, tok_len)) {
+			char *tok_buf = strbuf_detach(tok, NULL);
+			*conf = &item->conf;
+			strbuf_addstr(tok, token_from_item(item, tok_buf));
+			free(tok_buf);
+			break;
+		}
 	}
 
-	return new_trailer_item(NULL,
-				strbuf_detach(&tok, NULL),
-				strbuf_detach(&val, NULL));
+	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, char *tok, char *val,
+			     const struct conf_info *conf)
 {
-	if (!new)
-		return;
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
@@ -599,21 +577,28 @@ static void process_command_line_args(struct list_head *arg_head,
 {
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (item->conf.command) {
-			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(arg_head, new);
-		}
+		if (item->conf.command)
+			add_trailer_item(arg_head,
+					 xstrdup(token_from_item(item, NULL)),
+					 xstrdup(""),
+					 &item->conf);
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(arg_head, new);
+		if (!parse_trailer(&tok, &val, &conf, tr->string))
+			add_trailer_item(arg_head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 }
 
@@ -734,6 +719,9 @@ static int process_input_file(FILE *outfile,
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -751,10 +739,12 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char) {
-			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(head, new);
-		}
+		if (lines[i]->buf[0] != comment_line_char &&
+		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+			add_trailer_item(head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v3 3/6] trailer: streamline trailer item create and add

[Stefan Beller]

On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> Currently, creation and addition (to a list) of trailer items are spread
> across multiple functions. Streamline this by only having 2 functions:
> one to parse the user-supplied string, and one to add the parsed
> information to a list.
>
> Signed-off-by: Jonathan Tan <jonathantanmy@google.com>

Reviewed-by: Stefan Beller <sbeller@google.com>

[PATCH v3 4/6] trailer: make args have their own struct

[Jonathan Tan]

Improve type safety by making arguments (whether from configuration or
from the command line) have their own "struct arg_item" type, separate
from the "struct trailer_item" type used to represent the trailers in
the buffer being manipulated.

This change also prepares "struct trailer_item" to be further
differentiated from "struct arg_item" in future patches.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 135 +++++++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 85 insertions(+), 50 deletions(-)

diff --git a/trailer.c b/trailer.c
index 54cc930..a9ed3f8 100644
--- a/trailer.c
+++ b/trailer.c
@@ -29,6 +29,12 @@ struct trailer_item {
 	struct list_head list;
 	char *token;
 	char *value;
+};
+
+struct arg_item {
+	struct list_head list;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -62,7 +68,7 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(struct trailer_item *a, struct trailer_item *b)
+static int same_token(struct trailer_item *a, struct arg_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -71,12 +77,12 @@ static int same_token(struct trailer_item *a, struct trailer_item *b)
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(struct trailer_item *a, struct trailer_item *b)
+static int same_value(struct trailer_item *a, struct arg_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(struct trailer_item *a, struct trailer_item *b)
+static int same_trailer(struct trailer_item *a, struct arg_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -98,6 +104,13 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 
 static void free_trailer_item(struct trailer_item *item)
 {
+	free(item->token);
+	free(item->value);
+	free(item);
+}
+
+static void free_arg_item(struct arg_item *item)
+{
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
@@ -137,17 +150,29 @@ static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 	}
 }
 
+static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
+{
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = arg_tok->token;
+	new->value = arg_tok->value;
+	arg_tok->token = arg_tok->value = NULL;
+	free_arg_item(arg_tok);
+	return new;
+}
+
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok)
+				  struct arg_item *arg_tok)
 {
-	if (after_or_end(arg_tok->conf.where))
-		list_add(&arg_tok->list, &on_tok->list);
+	int aoe = after_or_end(arg_tok->conf.where);
+	struct trailer_item *to_add = trailer_from_arg(arg_tok);
+	if (aoe)
+		list_add(&to_add->list, &on_tok->list);
 	else
-		list_add_tail(&arg_tok->list, &on_tok->list);
+		list_add_tail(&to_add->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
-			      struct trailer_item *arg_tok,
+			      struct arg_item *arg_tok,
 			      int check_all,
 			      struct list_head *head)
 {
@@ -200,7 +225,7 @@ static char *apply_command(const char *command, const char *arg)
 	return result;
 }
 
-static void apply_item_command(struct trailer_item *in_tok, struct trailer_item *arg_tok)
+static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg_tok)
 {
 	if (arg_tok->conf.command) {
 		const char *arg;
@@ -218,13 +243,13 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 }
 
 static void apply_arg_if_exists(struct trailer_item *in_tok,
-				struct trailer_item *arg_tok,
+				struct arg_item *arg_tok,
 				struct trailer_item *on_tok,
 				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
@@ -241,39 +266,41 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		if (check_if_different(in_tok, arg_tok, 1, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
 		if (check_if_different(on_tok, arg_tok, 0, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	}
 }
 
 static void apply_arg_if_missing(struct list_head *head,
-				 struct trailer_item *arg_tok)
+				 struct arg_item *arg_tok)
 {
 	enum action_where where;
+	struct trailer_item *to_add;
 
 	switch (arg_tok->conf.if_missing) {
 	case MISSING_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
 		apply_item_command(NULL, arg_tok);
+		to_add = trailer_from_arg(arg_tok);
 		if (after_or_end(where))
-			list_add_tail(&arg_tok->list, head);
+			list_add_tail(&to_add->list, head);
 		else
-			list_add(&arg_tok->list, head);
+			list_add(&to_add->list, head);
 	}
 }
 
 static int find_same_and_apply_arg(struct list_head *head,
-				   struct trailer_item *arg_tok)
+				   struct arg_item *arg_tok)
 {
 	struct list_head *pos;
 	struct trailer_item *in_tok;
@@ -306,11 +333,11 @@ static void process_trailers_lists(struct list_head *head,
 				   struct list_head *arg_head)
 {
 	struct list_head *pos, *p;
-	struct trailer_item *arg_tok;
+	struct arg_item *arg_tok;
 
 	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
-		arg_tok = list_entry(pos, struct trailer_item, list);
+		arg_tok = list_entry(pos, struct arg_item, list);
 
 		list_del(pos);
 
@@ -375,20 +402,20 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 		dst->command = xstrdup(src->command);
 }
 
-static struct trailer_item *get_conf_item(const char *name)
+static struct arg_item *get_conf_item(const char *name)
 {
 	struct list_head *pos;
-	struct trailer_item *item;
+	struct arg_item *item;
 
 	/* Look up item with same name */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
 
 	/* Item does not already exists, create it */
-	item = xcalloc(sizeof(struct trailer_item), 1);
+	item = xcalloc(sizeof(*item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
@@ -442,7 +469,7 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v
 static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 {
 	const char *trailer_item, *variable_name;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct conf_info *conf;
 	char *name = NULL;
 	enum trailer_info_type type;
@@ -500,7 +527,7 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static const char *token_from_item(struct trailer_item *item, char *tok)
+static const char *token_from_item(struct arg_item *item, char *tok)
 {
 	if (item->conf.key)
 		return item->conf.key;
@@ -509,7 +536,7 @@ static const char *token_from_item(struct trailer_item *item, char *tok)
 	return item->conf.name;
 }
 
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+static int token_matches_item(const char *tok, struct arg_item *item, int tok_len)
 {
 	if (!strncasecmp(tok, item->conf.name, tok_len))
 		return 1;
@@ -521,7 +548,7 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
-	struct trailer_item *item;
+	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
@@ -547,12 +574,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 
 	/* Lookup if the token matches something in the config */
 	tok_len = token_len_without_separator(tok->buf, tok->len);
-	*conf = &default_conf_info;
+	if (conf)
+		*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (token_matches_item(tok->buf, item, tok_len)) {
 			char *tok_buf = strbuf_detach(tok, NULL);
-			*conf = &item->conf;
+			if (conf)
+				*conf = &item->conf;
 			strbuf_addstr(tok, token_from_item(item, tok_buf));
 			free(tok_buf);
 			break;
@@ -562,43 +591,51 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val,
-			     const struct conf_info *conf)
+static void add_trailer_item(struct list_head *head, char *tok, char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
-	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
+static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
+			 const struct conf_info *conf)
+{
+	struct arg_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
+	list_add_tail(&new->list, arg_head);
+}
+
 static void process_command_line_args(struct list_head *arg_head, 
 				      struct string_list *trailers)
 {
 	struct string_list_item *tr;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
 	const struct conf_info *conf;
 	struct list_head *pos;
 
-	/* Add a trailer item for each configured trailer with a command */
+	/* Add an arg item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (item->conf.command)
-			add_trailer_item(arg_head,
-					 xstrdup(token_from_item(item, NULL)),
-					 xstrdup(""),
-					 &item->conf);
+			add_arg_item(arg_head,
+				     xstrdup(token_from_item(item, NULL)),
+				     xstrdup(""),
+				     &item->conf);
 	}
 
-	/* Add a trailer item for each trailer on the command line */
+	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		if (!parse_trailer(&tok, &val, &conf, tr->string))
-			add_trailer_item(arg_head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+			add_arg_item(arg_head,
+				     strbuf_detach(&tok, NULL),
+				     strbuf_detach(&val, NULL),
+				     conf);
 	}
 }
 
@@ -721,7 +758,6 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
-	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -740,11 +776,10 @@ static int process_input_file(FILE *outfile,
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+					 strbuf_detach(&val, NULL));
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v3 4/6] trailer: make args have their own struct

[Stefan Beller]

On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> Improve type safety by making arguments (whether from configuration or
> from the command line) have their own "struct arg_item" type, separate
> from the "struct trailer_item" type used to represent the trailers in
> the buffer being manipulated.
>
> This change also prepares "struct trailer_item" to be further
> differentiated from "struct arg_item" in future patches.
>
> Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
> ---
>  trailer.c | 135 +++++++++++++++++++++++++++++++++++++++-----------------------
>  1 file changed, 85 insertions(+), 50 deletions(-)
>
> diff --git a/trailer.c b/trailer.c
> index 54cc930..a9ed3f8 100644
> --- a/trailer.c
> +++ b/trailer.c
> @@ -29,6 +29,12 @@ struct trailer_item {
>         struct list_head list;
>         char *token;
>         char *value;
> +};
> +
> +struct arg_item {
> +       struct list_head list;
> +       char *token;
> +       char *value;
>         struct conf_info conf;
>  };

(Unrelated side note:) When first seeing this diff, I assumed the diff
heuristic is going wild, because it doesn't add a full struct.
But on a second closer look, I realize this is the only correct diff,
because we do not account for moved lines from one struct to the
other.


>  static void add_arg_to_input_list(struct trailer_item *on_tok,
> -                                 struct trailer_item *arg_tok)
> +                                 struct arg_item *arg_tok)
>  {
> -       if (after_or_end(arg_tok->conf.where))
> -               list_add(&arg_tok->list, &on_tok->list);
> +       int aoe = after_or_end(arg_tok->conf.where);
> +       struct trailer_item *to_add = trailer_from_arg(arg_tok);
> +       if (aoe)

The use of an extra variable here is more readable than my
imagined version of inlining to_add into the list_add calls
just to save aoe.

Looks good to me.

Stefan

Re: [PATCH v3 4/6] trailer: make args have their own struct

[Junio C Hamano]

Stefan Beller <sbeller@google.com> writes:

>> @@ -29,6 +29,12 @@ struct trailer_item {
>>         struct list_head list;
>>         char *token;
>>         char *value;
>> +};
>> +
>> +struct arg_item {
>> +       struct list_head list;
>> +       char *token;
>> +       char *value;
>>         struct conf_info conf;
>>  };
>
> (Unrelated side note:) When first seeing this diff, I assumed the diff
> heuristic is going wild, because it doesn't add a full struct.
> But on a second closer look, I realize this is the only correct diff,
> because we do not account for moved lines from one struct to the
> other.

It probably is not "the only" correct diff, as you actually could
shift it the other way by one to three lines.  I am not sure which
one among four possible diff is the easiest to grok, though.  Both
the above (picking the highest possible position) and the below (the
other extreme) are probably easier to read than anything in between.

 struct trailer_item {
+	struct list_head list;
+	char *token;
+	char *value;
+};
+
+struct arg_item {
 	struct list_head list;
 	char *token;
 	char *value;
 	struct conf_info conf;
 };
 

[PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Jonathan Tan]

Currently, interpret-trailers requires all lines of a trailer block to
be trailers (or comments) - if not it would not identify that block as a
trailer block, and thus create its own trailer block, inserting a blank
line.  For example:

  echo -e "\na: b\nnot trailer" |
  git interpret-trailers --trailer "c: d"

would result in:

  a: b
  not trailer

  c: d

Relax the definition of a trailer block to only require 1 trailer, so
that trailers can be directly added to such blocks, resulting in:

  a: b
  not trailer
  c: d

This allows arbitrary lines to be included in trailer blocks, like those
in [1], and still allow interpret-trailers to be used.

This change also makes comments in the trailer block be treated as any
other non-trailer line, preserving them in the output of
interpret-trailers.

[1]
https://kernel.googlesource.com/pub/scm/linux/kernel/git/stable/linux-stable/+/e7d316a02f683864a12389f8808570e37fb90aa3

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |  3 +-
 t/t7513-interpret-trailers.sh            | 35 +++++++++++++++
 trailer.c                                | 77 ++++++++++++++++++++++----------
 3 files changed, 90 insertions(+), 25 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 93d1db6..c480da6 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -48,7 +48,8 @@ with only spaces at the end of the commit message part, one blank line
 will be added before the new trailer.
 
 Existing trailers are extracted from the input message by looking for
-a group of one or more lines that contain a colon (by default), where
+a group of one or more lines in which at least one line contains a 
+colon (by default), where
 the group is preceded by one or more empty (or whitespace-only) lines.
 The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index aee785c..7f5cd2a 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -126,6 +126,37 @@ test_expect_success 'with multiline title in the message' '
 	test_cmp expected actual
 '
 
+test_expect_success 'with non-trailer lines mixed with trailer lines' '
+	cat >patch <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this: is a trailer
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines only' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
@@ -257,6 +288,8 @@ test_expect_success 'with message that has comments' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
@@ -286,6 +319,8 @@ test_expect_success 'with message that has an old style conflict block' '
 	cat >>expected <<-\EOF &&
 		# comment
 
+		# other comment
+		# yet another comment
 		Reviewed-by: Johan
 		Cc: Peff
 		# last comment
diff --git a/trailer.c b/trailer.c
index a9ed3f8..d6dfc7a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,6 +27,10 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct list_head list;
+	/*
+	 * If this is not a trailer line, the line is stored in value
+	 * (excluding the terminating newline) and token is NULL.
+	 */
 	char *token;
 	char *value;
 };
@@ -70,9 +74,14 @@ static size_t token_len_without_separator(const char *token, size_t len)
 
 static int same_token(struct trailer_item *a, struct arg_item *b)
 {
-	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
-	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
-	size_t min_len = (a_len > b_len) ? b_len : a_len;
+	size_t a_len, b_len, min_len;
+
+	if (!a->token)
+		return 0;
+
+	a_len = token_len_without_separator(a->token, strlen(a->token));
+	b_len = token_len_without_separator(b->token, strlen(b->token));
+	min_len = (a_len > b_len) ? b_len : a_len;
 
 	return !strncasecmp(a->token, b->token, min_len);
 }
@@ -130,7 +139,14 @@ static char last_non_space_char(const char *s)
 
 static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 {
-	char c = last_non_space_char(tok);
+	char c;
+
+	if (!tok) {
+		fprintf(outfile, "%s\n", val);
+		return;
+	}
+
+	c = last_non_space_char(tok);
 	if (!c)
 		return;
 	if (strchr(separators, c))
@@ -543,8 +559,16 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
 	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
 }
 
+/*
+ * Parse the given trailer into token and value parts.
+ *
+ * If the given trailer does not have a separator (and thus cannot be separated
+ * into token and value parts), it is treated as a token (if parse_as_arg) or
+ * as a non-trailer line (if not parse_as_arg).
+ */
 static int parse_trailer(struct strbuf *tok, struct strbuf *val,
-			 const struct conf_info **conf, const char *trailer)
+			 const struct conf_info **conf, const char *trailer,
+			 int parse_as_arg)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
@@ -557,11 +581,18 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	len = strcspn(trailer, seps.buf);
 	strbuf_release(&seps);
 	if (len == 0) {
-		int l = strlen(trailer);
+		int l;
+		if (!parse_as_arg)
+			return -1;
+
+		l = strlen(trailer);
 		while (l > 0 && isspace(trailer[l - 1]))
 			l--;
 		return error(_("empty trailer token in trailer '%.*s'"), l, trailer);
 	}
+	if (!parse_as_arg && len == strlen(trailer))
+		return -1;
+
 	if (len < strlen(trailer)) {
 		strbuf_add(tok, trailer, len);
 		strbuf_trim(tok);
@@ -631,7 +662,7 @@ static void process_command_line_args(struct list_head *arg_head,
 
 	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		if (!parse_trailer(&tok, &val, &conf, tr->string))
+		if (!parse_trailer(&tok, &val, &conf, tr->string, 1))
 			add_arg_item(arg_head,
 				     strbuf_detach(&tok, NULL),
 				     strbuf_detach(&val, NULL),
@@ -683,7 +714,7 @@ static int find_patch_start(struct strbuf **lines, int count)
  */
 static int find_trailer_start(struct strbuf **lines, int count)
 {
-	int start, end_of_title, only_spaces = 1;
+	int start, end_of_title, only_spaces = 1, trailer_found = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -699,22 +730,17 @@ static int find_trailer_start(struct strbuf **lines, int count)
 	 * for a line with only spaces before lines with one separator.
 	 */
 	for (start = count - 1; start >= end_of_title; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
-			return start + 1;
+			return trailer_found ? start + 1 : count;
 		}
-		if (strcspn(lines[start]->buf, separators) < lines[start]->len) {
-			if (only_spaces)
-				only_spaces = 0;
-			continue;
-		}
-		return count;
+		only_spaces = 0;
+		if (strcspn(lines[start]->buf, separators) < lines[start]->len)
+			trailer_found = 1;
 	}
 
-	return only_spaces ? count : 0;
+	return count;
 }
 
 /* Get the index of the end of the trailers */
@@ -735,11 +761,8 @@ static int find_trailer_end(struct strbuf **lines, int patch_start)
 
 static int has_blank_line_before(struct strbuf **lines, int start)
 {
-	for (;start >= 0; start--) {
-		if (lines[start]->buf[0] == comment_line_char)
-			continue;
+	if (start >= 0)
 		return contains_only_spaces(lines[start]->buf);
-	}
 	return 0;
 }
 
@@ -775,11 +798,17 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
+		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		else {
+			strbuf_addbuf(&val, lines[i]);
+			strbuf_strip_suffix(&val, "\n");
+			add_trailer_item(head,
+					 NULL,
+					 strbuf_detach(&val, NULL));
+		}
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Stefan Beller]

On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
>
>  Existing trailers are extracted from the input message by looking for
> -a group of one or more lines that contain a colon (by default), where
> +a group of one or more lines in which at least one line contains a
> +colon (by default), where

Please see commit
578e6021c0819d7be1179e05e7ce0e6fdb2a01b7
for an example where I think this is overly broad.

Another made up example, that I'd want to feed
in commit -s eventually:

--8<--
demonstrate colons in Java

First paragraph is not interesting.

Also if using another Language such as Java, where I point out
Class::function() to be problematic
--8<--

This would lack the white space between the last paragraph and
the Sign off ?

So for this patch I am mostly concerned about false positives hidden
in actual text.

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Junio C Hamano]

Stefan Beller <sbeller@google.com> writes:

> On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
>>
>>  Existing trailers are extracted from the input message by looking for
>> -a group of one or more lines that contain a colon (by default), where
>> +a group of one or more lines in which at least one line contains a
>> +colon (by default), where
>
> Please see commit
> 578e6021c0819d7be1179e05e7ce0e6fdb2a01b7
> for an example where I think this is overly broad.

Hmph.  That's a merge.

    Merge branch 'rs/c-auto-resets-attributes'

    When "%C(auto)" appears at the very beginning of the pretty format
    string, it did not need to issue the reset sequence, but it did.

    * rs/c-auto-resets-attributes:
      pretty: avoid adding reset for %C(auto) if output is empty

And neither of the two colon containing line remotely resembles how
a typical RFC-822 header is formatted.  So that may serve as a hint
to how we can tighten it without introducing false negative.

> Another made up example, that I'd want to feed
> in commit -s eventually:
>
> --8<--
> demonstrate colons in Java
>
> First paragraph is not interesting.
>
> Also if using another Language such as Java, where I point out
> Class::function() to be problematic
> --8<--
>
> This would lack the white space between the last paragraph and
> the Sign off ?
>
> So for this patch I am mostly concerned about false positives hidden
> in actual text.

Yes.  

These are exactly why I mentioned "if certian number or percentage"
in my earlier suggestion.

I think in practice, "A paragraph with at least one Signed-off-by:
line, and has no more than 3/4 of the (logical) lines that do not
resemble how a typical RFC-822 header is formatted" or something
along that line would give us a reasonable safety.  

Your Java example will fail the criteria in two ways, so we'd be
safe ;-)

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Jonathan Tan]

On 10/17/2016 06:42 PM, Junio C Hamano wrote:
> Stefan Beller <sbeller@google.com> writes:
>
>> On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
>>>
>>>  Existing trailers are extracted from the input message by looking for
>>> -a group of one or more lines that contain a colon (by default), where
>>> +a group of one or more lines in which at least one line contains a
>>> +colon (by default), where
>>
>> Please see commit
>> 578e6021c0819d7be1179e05e7ce0e6fdb2a01b7
>> for an example where I think this is overly broad.
>
> Hmph.  That's a merge.
>
>     Merge branch 'rs/c-auto-resets-attributes'
>
>     When "%C(auto)" appears at the very beginning of the pretty format
>     string, it did not need to issue the reset sequence, but it did.
>
>     * rs/c-auto-resets-attributes:
>       pretty: avoid adding reset for %C(auto) if output is empty
>
> And neither of the two colon containing line remotely resembles how
> a typical RFC-822 header is formatted.  So that may serve as a hint
> to how we can tighten it without introducing false negative.

The only "offending" character is the space (according to RFC 822), but 
that sounds like a good rule to have.

>> Another made up example, that I'd want to feed
>> in commit -s eventually:
>>
>> --8<--
>> demonstrate colons in Java
>>
>> First paragraph is not interesting.
>>
>> Also if using another Language such as Java, where I point out
>> Class::function() to be problematic
>> --8<--
>>
>> This would lack the white space between the last paragraph and
>> the Sign off ?
>>
>> So for this patch I am mostly concerned about false positives hidden
>> in actual text.
>
> Yes.
>
> These are exactly why I mentioned "if certian number or percentage"
> in my earlier suggestion.
>
> I think in practice, "A paragraph with at least one Signed-off-by:
> line, and has no more than 3/4 of the (logical) lines that do not
> resemble how a typical RFC-822 header is formatted" or something
> along that line would give us a reasonable safety.

I think that "Signed-off-by:" is not guaranteed to be present. Defining 
a trailer line as "a line starting with a token, then optional 
whitespace, then separator", maybe the following rule:
- at least one trailer line generated by Git ("(cherry picked by" or 
"Signed-off-by") or configured in the "trailer" section in gitconfig
OR
- at least 3/4 logical trailer lines (I'm wondering if this should be 
100% trailer lines)

?

> Your Java example will fail the criteria in two ways, so we'd be
> safe ;-)

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

>>     * rs/c-auto-resets-attributes:
>>       pretty: avoid adding reset for %C(auto) if output is empty
>>
>> And neither of the two colon containing line remotely resembles how
>> a typical RFC-822 header is formatted.  So that may serve as a hint
>> to how we can tighten it without introducing false negative.
>
> The only "offending" character is the space (according to RFC 822),
> but that sounds like a good rule to have.

I suspect that we should be willing to deviate from the letter of
RFC to reject misidentification.  I saw things like

	Thanks to: Jonathan Tan <jt@host.xz>
	Signed-off-by: A U Thor <au@th.or>

in the wild (notice the SP between Thanks and to), for example.
Rejecting leading whitespace as a line that does *not* start the
header (hence its colon does not count) may be a good compromise.

> I think that "Signed-off-by:" is not guaranteed to be
> present.

But do we really care about that case where there is no S-o-b:?  I
personally do not think so.

> Defining a trailer line as "a line starting with a token,
> then optional whitespace, then separator", maybe the following rule:
> - at least one trailer line generated by Git ("(cherry picked by" or
> "Signed-off-by") or configured in the "trailer" section in gitconfig
> OR
> - at least 3/4 logical trailer lines (I'm wondering if this should be
> 100% trailer lines)

I'd strongly suggest turning that OR to AND.  We will not safely be
able to write a commit log message that describes how S-o-b lines
are handled in its last paragraph otherwise.

I do not care too deeply about 3/4, but I meant to allow 75% cruft
but no more than that, and the fact that the threashold is set at
way more than 50% is important.  IOW, if you have

	Ordinary log message here...

	S-o-b: A U Thor <au@th.or>
	[a short description that is typically a single liner
        in the real world use pattern we saw in the world, but
	could overflow to become multi line cruft]
	S-o-b: R E Layer <re@lay.er>

"last paragraph" is 5 lines long, among which 60% are cruft that is
below the 75% threshold, and "am -s" can still add the S-o-b of the
committer at the end of that existing last paragraph.  Making it too
strict would raise the false negative ratio.

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Jonathan Tan]

On 10/18/2016 09:36 AM, Junio C Hamano wrote:
> Jonathan Tan <jonathantanmy@google.com> writes:
>
>>>     * rs/c-auto-resets-attributes:
>>>       pretty: avoid adding reset for %C(auto) if output is empty
>>>
>>> And neither of the two colon containing line remotely resembles how
>>> a typical RFC-822 header is formatted.  So that may serve as a hint
>>> to how we can tighten it without introducing false negative.
>>
>> The only "offending" character is the space (according to RFC 822),
>> but that sounds like a good rule to have.
>
> I suspect that we should be willing to deviate from the letter of
> RFC to reject misidentification.  I saw things like
>
> 	Thanks to: Jonathan Tan <jt@host.xz>
> 	Signed-off-by: A U Thor <au@th.or>
>
> in the wild (notice the SP between Thanks and to), for example.
> Rejecting leading whitespace as a line that does *not* start the
> header (hence its colon does not count) may be a good compromise.

Good point.

>> I think that "Signed-off-by:" is not guaranteed to be
>> present.
>
> But do we really care about that case where there is no S-o-b:?  I
> personally do not think so.

I think we should - the use case I had in mind when I started this is 
the Android Git repository, which does not use Signed-off-by. For 
example, I quoted this commit in an earlier e-mail [1]:

https://android.googlesource.com/platform/frameworks/base/+/4c5281862f750cbc9d7355a07ef1a5545b9b3523

which has the footer:

   Bug: http://b/30562229
   Test: readelf --dyn-sym app_process32 and check that bsd_signal is 
exported
         readelf --dyn-sym app_process64 and check that bsd_signal is 
not exported
   Change-Id: Iec584070b42bc7fa43b114c0f884aff2db5a6858

>> Defining a trailer line as "a line starting with a token,
>> then optional whitespace, then separator", maybe the following rule:
>> - at least one trailer line generated by Git ("(cherry picked by" or
>> "Signed-off-by") or configured in the "trailer" section in gitconfig
>> OR
>> - at least 3/4 logical trailer lines (I'm wondering if this should be
>> 100% trailer lines)
>
> I'd strongly suggest turning that OR to AND.  We will not safely be
> able to write a commit log message that describes how S-o-b lines
> are handled in its last paragraph otherwise.
>
> I do not care too deeply about 3/4, but I meant to allow 75% cruft
> but no more than that, and the fact that the threashold is set at
> way more than 50% is important.  IOW, if you have
>
> 	Ordinary log message here...
>
> 	S-o-b: A U Thor <au@th.or>
> 	[a short description that is typically a single liner
>         in the real world use pattern we saw in the world, but
> 	could overflow to become multi line cruft]
> 	S-o-b: R E Layer <re@lay.er>
>
> "last paragraph" is 5 lines long, among which 60% are cruft that is
> below the 75% threshold, and "am -s" can still add the S-o-b of the
> committer at the end of that existing last paragraph.  Making it too
> strict would raise the false negative ratio.

Ah, sorry, I misread your original suggestion.

Would this work then:
- at least one trailer line generated by Git ("(cherry picked by" or
   "Signed-off-by: ") or configured in the "trailer" section in
   git config AND at least 25% logical trailer lines
OR
- 100% logical trailer lines

The first part is your original suggestion except that I think that it 
is more consistent to allow other trailer lines as well (but I do not 
feel too strongly about this). The second part would satisfy the Android 
Git use case above, and also retain existing behavior when 
"Signed-off-by" (for example) is added to an existing footer that does 
not contain "Signed-off-by" yet.

What do you think?

[1] Message ID <29cb0f55-f729-80af-cdca-64e927fa97c0@google.com>

Re: [PATCH v3 5/6] trailer: allow non-trailers in trailer block

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> Would this work then:
> - at least one trailer line generated by Git ("(cherry picked by" or
>   "Signed-off-by: ") or configured in the "trailer" section in
>   git config AND at least 25% logical trailer lines
> OR
> - 100% logical trailer lines

Sure.  

At that point, I doubt that the latter "100% logical trailer" makes
much difference, though, because at least one of them is likely to
be in the former set, or the users can easily make it so by throwing
what they use like "Bug: ", "Test: " and "Change-ID: " in the
"configured in the trailer section" category.  FWIW, I do not think
we mind terribly to tweak the definition of "generated by Git" class
to "commonly used in Git managed projects" to include "Change-ID:"
and friends.

[PATCH v3 6/6] trailer: support values folded to multiple lines

[Jonathan Tan]

Currently, interpret-trailers requires that a trailer be only on 1 line.
For example:

  a: first line
     second line

would be interpreted as one trailer line followed by one non-trailer line.

Make interpret-trailers support RFC 822-style folding, treating those
lines as one logical trailer.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |   7 +-
 t/t7513-interpret-trailers.sh            | 139 +++++++++++++++++++++++++++++++
 trailer.c                                |  22 +++--
 3 files changed, 160 insertions(+), 8 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index c480da6..cfec636 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -57,11 +57,12 @@ minus signs start the patch part of the message.
 
 When reading trailers, there can be whitespaces before and after the
 token, the separator and the value. There can also be whitespaces
-inside the token and the value.
+inside the token and the value. The value may be split over multiple lines with
+each subsequent line starting with whitespace, like the "folding" in RFC 822.
 
 Note that 'trailers' do not follow and are not intended to follow many
-rules for RFC 822 headers. For example they do not follow the line
-folding rules, the encoding rules and probably many other rules.
+rules for RFC 822 headers. For example they do not follow
+the encoding rules and probably many other rules.
 
 OPTIONS
 -------
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 7f5cd2a..31db699 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -157,6 +157,145 @@ test_expect_success 'with non-trailer lines only' '
 	test_cmp expected actual
 '
 
+test_expect_success 'multiline field treated as atomic for placement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		name: value
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for replacement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		another: trailer
+		name: value
+	EOF
+	test_config trailer.name.ifexists replace &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for difference check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.ifexists addIfDifferent &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line
+		QQQQQsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for neighbor check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	test_config trailer.name.ifexists addIfDifferentNeighbor &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		name: first line
+		QQQQQsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index d6dfc7a..ef276e6 100644
--- a/trailer.c
+++ b/trailer.c
@@ -248,7 +248,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg
 		if (arg_tok->value && arg_tok->value[0]) {
 			arg = arg_tok->value;
 		} else {
-			if (in_tok && in_tok->value)
+			if (in_tok)
 				arg = xstrdup(in_tok->value);
 			else
 				arg = xstrdup("");
@@ -622,12 +622,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val)
+static struct trailer_item *add_trailer_item(struct list_head *head, char *tok,
+					     char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
 	list_add_tail(&new->list, head);
+	return new;
 }
 
 static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
@@ -781,6 +783,7 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
+	struct trailer_item *last = NULL;
 
 	/* Get the line count */
 	while (lines[count])
@@ -798,16 +801,25 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
+		if (last && isspace(lines[i]->buf[0])) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addf(&sb, "%s\n%s", last->value, lines[i]->buf);
+			strbuf_strip_suffix(&sb, "\n");
+			free(last->value);
+			last->value = strbuf_detach(&sb, NULL);
+			continue;
+		}
 		if (!parse_trailer(&tok, &val, NULL, lines[i]->buf, 0))
-			add_trailer_item(head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL));
+			last = add_trailer_item(head,
+						strbuf_detach(&tok, NULL),
+						strbuf_detach(&val, NULL));
 		else {
 			strbuf_addbuf(&val, lines[i]);
 			strbuf_strip_suffix(&val, "\n");
 			add_trailer_item(head,
 					 NULL,
 					 strbuf_detach(&val, NULL));
+			last = NULL;
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v3 6/6] trailer: support values folded to multiple lines

[Stefan Beller]

On Fri, Oct 14, 2016 at 10:38 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> Currently, interpret-trailers requires that a trailer be only on 1 line.
> For example:
>
>   a: first line
>      second line
>
> would be interpreted as one trailer line followed by one non-trailer line.
>
> Make interpret-trailers support RFC 822-style folding, treating those
> lines as one logical trailer.
>
> Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
> ---

Looks good,

Thanks,
Stefan

[PATCH v4 0/8] allow non-trailers and multiple-line trailers

[Jonathan Tan]

Main changes are:
 - implemented the previously discussed trailer block recognizing rule
   (recognized trailer + 25% trailers or 100% trailers)
 - forbidding leading whitespace in trailers to avoid false positives

Once the recognized trailer + 25% trailers rule is implemented,
implementing the 100% trailer rule gives us backwards compatibility and
is only a few lines of code, so I included it.

Summary of changes from v3:
 2/6->2/8:
   - squashed Ramsay Jones's "static" patch
 new->5/8:
   - new patch
 5/6->6/8:
   - new trailer block recognizing rule
   - reverted to the existing behavior of ignoring comments, since the
     number of trailers and non-trailers in the trailer block now
     matters more
 new->7/8:
   - new patch
 6/6->8/8:
   - updated trailer block recognizing code, since the continuation
     lines must not be counted if they follow a trailer line

Jonathan Tan (8):
  trailer: improve const correctness
  trailer: use list.h for doubly-linked list
  trailer: streamline trailer item create and add
  trailer: make args have their own struct
  trailer: clarify failure modes in parse_trailer
  trailer: allow non-trailers in trailer block
  trailer: forbid leading whitespace in trailers
  trailer: support values folded to multiple lines

 Documentation/git-interpret-trailers.txt |  14 +-
 t/t7513-interpret-trailers.sh            | 299 +++++++++++++++
 trailer.c                                | 619 +++++++++++++++++--------------
 3 files changed, 651 insertions(+), 281 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 1/8] trailer: improve const correctness

[Jonathan Tan]

Change "const char *" to "char *" in struct trailer_item and in the
return value of apply_command (since those strings are owned strings).

Change "struct conf_info *" to "const struct conf_info *" (since that
struct is not modified).

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/trailer.c b/trailer.c
index c6ea9ac..1f191b2 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,8 +27,8 @@ static struct conf_info default_conf_info;
 struct trailer_item {
 	struct trailer_item *previous;
 	struct trailer_item *next;
-	const char *token;
-	const char *value;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -95,8 +95,8 @@ static void free_trailer_item(struct trailer_item *item)
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
-	free((char *)item->token);
-	free((char *)item->value);
+	free(item->token);
+	free(item->value);
 	free(item);
 }
 
@@ -215,13 +215,13 @@ static struct trailer_item *remove_first(struct trailer_item **first)
 	return item;
 }
 
-static const char *apply_command(const char *command, const char *arg)
+static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *argv[] = {NULL, NULL};
-	const char *result;
+	char *result;
 
 	strbuf_addstr(&cmd, command);
 	if (arg)
@@ -425,7 +425,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
 	return 0;
 }
 
-static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
+static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 {
 	*dst = *src;
 	if (src->name)
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 2/8] trailer: use list.h for doubly-linked list

[Jonathan Tan]

Replace the existing handwritten implementation of a doubly-linked list
in trailer.c with the functions and macros from list.h. This
significantly simplifies the code.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com>
---
 trailer.c | 258 ++++++++++++++++++++++----------------------------------------
 1 file changed, 91 insertions(+), 167 deletions(-)

diff --git a/trailer.c b/trailer.c
index 1f191b2..4e85aae 100644
--- a/trailer.c
+++ b/trailer.c
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "tempfile.h"
 #include "trailer.h"
+#include "list.h"
 /*
  * Copyright (c) 2013, 2014 Christian Couder <chriscool@tuxfamily.org>
  */
@@ -25,19 +26,24 @@ struct conf_info {
 static struct conf_info default_conf_info;
 
 struct trailer_item {
-	struct trailer_item *previous;
-	struct trailer_item *next;
+	struct list_head list;
 	char *token;
 	char *value;
 	struct conf_info conf;
 };
 
-static struct trailer_item *first_conf_item;
+static LIST_HEAD(conf_head);
 
 static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+/* Iterate over the elements of the list. */
+#define list_for_each_dir(pos, head, is_reverse) \
+	for (pos = is_reverse ? (head)->prev : (head)->next; \
+		pos != (head); \
+		pos = is_reverse ? pos->prev : pos->next)
+
 static int after_or_end(enum action_where where)
 {
 	return (where == WHERE_AFTER) || (where == WHERE_END);
@@ -120,101 +126,49 @@ static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 		fprintf(outfile, "%s%c %s\n", tok, separators[0], val);
 }
 
-static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
+static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	for (item = first; item; item = item->next) {
+	list_for_each(pos, head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!trim_empty || strlen(item->value) > 0)
 			print_tok_val(outfile, item->token, item->value);
 	}
 }
 
-static void update_last(struct trailer_item **last)
-{
-	if (*last)
-		while ((*last)->next != NULL)
-			*last = (*last)->next;
-}
-
-static void update_first(struct trailer_item **first)
-{
-	if (*first)
-		while ((*first)->previous != NULL)
-			*first = (*first)->previous;
-}
-
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok,
-				  struct trailer_item **first,
-				  struct trailer_item **last)
-{
-	if (after_or_end(arg_tok->conf.where)) {
-		arg_tok->next = on_tok->next;
-		on_tok->next = arg_tok;
-		arg_tok->previous = on_tok;
-		if (arg_tok->next)
-			arg_tok->next->previous = arg_tok;
-		update_last(last);
-	} else {
-		arg_tok->previous = on_tok->previous;
-		on_tok->previous = arg_tok;
-		arg_tok->next = on_tok;
-		if (arg_tok->previous)
-			arg_tok->previous->next = arg_tok;
-		update_first(first);
-	}
+				  struct trailer_item *arg_tok)
+{
+	if (after_or_end(arg_tok->conf.where))
+		list_add(&arg_tok->list, &on_tok->list);
+	else
+		list_add_tail(&arg_tok->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
 			      struct trailer_item *arg_tok,
-			      int check_all)
+			      int check_all,
+			      struct list_head *head)
 {
 	enum action_where where = arg_tok->conf.where;
+	struct list_head *next_head;
 	do {
-		if (!in_tok)
-			return 1;
 		if (same_trailer(in_tok, arg_tok))
 			return 0;
 		/*
 		 * if we want to add a trailer after another one,
 		 * we have to check those before this one
 		 */
-		in_tok = after_or_end(where) ? in_tok->previous : in_tok->next;
+		next_head = after_or_end(where) ? in_tok->list.prev
+						: in_tok->list.next;
+		if (next_head == head)
+			break;
+		in_tok = list_entry(next_head, struct trailer_item, list);
 	} while (check_all);
 	return 1;
 }
 
-static void remove_from_list(struct trailer_item *item,
-			     struct trailer_item **first,
-			     struct trailer_item **last)
-{
-	struct trailer_item *next = item->next;
-	struct trailer_item *previous = item->previous;
-
-	if (next) {
-		item->next->previous = previous;
-		item->next = NULL;
-	} else if (last)
-		*last = previous;
-
-	if (previous) {
-		item->previous->next = next;
-		item->previous = NULL;
-	} else if (first)
-		*first = next;
-}
-
-static struct trailer_item *remove_first(struct trailer_item **first)
-{
-	struct trailer_item *item = *first;
-	*first = item->next;
-	if (item->next) {
-		item->next->previous = NULL;
-		item->next = NULL;
-	}
-	return item;
-}
-
 static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
@@ -266,8 +220,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 static void apply_arg_if_exists(struct trailer_item *in_tok,
 				struct trailer_item *arg_tok,
 				struct trailer_item *on_tok,
-				struct trailer_item **in_tok_first,
-				struct trailer_item **in_tok_last)
+				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
@@ -275,40 +228,34 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		remove_from_list(in_tok, in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
+		list_del(&in_tok->list);
 		free_trailer_item(in_tok);
 		break;
 	case EXISTS_ADD:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(in_tok, arg_tok, 1))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(in_tok, arg_tok, 1, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(on_tok, arg_tok, 0))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(on_tok, arg_tok, 0, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	}
 }
 
-static void apply_arg_if_missing(struct trailer_item **in_tok_first,
-				 struct trailer_item **in_tok_last,
+static void apply_arg_if_missing(struct list_head *head,
 				 struct trailer_item *arg_tok)
 {
-	struct trailer_item **in_tok;
 	enum action_where where;
 
 	switch (arg_tok->conf.if_missing) {
@@ -317,68 +264,60 @@ static void apply_arg_if_missing(struct trailer_item **in_tok_first,
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
-		in_tok = after_or_end(where) ? in_tok_last : in_tok_first;
 		apply_item_command(NULL, arg_tok);
-		if (*in_tok) {
-			add_arg_to_input_list(*in_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		} else {
-			*in_tok_first = arg_tok;
-			*in_tok_last = arg_tok;
-		}
-		break;
+		if (after_or_end(where))
+			list_add_tail(&arg_tok->list, head);
+		else
+			list_add(&arg_tok->list, head);
 	}
 }
 
-static int find_same_and_apply_arg(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
+static int find_same_and_apply_arg(struct list_head *head,
 				   struct trailer_item *arg_tok)
 {
+	struct list_head *pos;
 	struct trailer_item *in_tok;
 	struct trailer_item *on_tok;
-	struct trailer_item *following_tok;
 
 	enum action_where where = arg_tok->conf.where;
 	int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE);
 	int backwards = after_or_end(where);
-	struct trailer_item *start_tok = backwards ? *in_tok_last : *in_tok_first;
+	struct trailer_item *start_tok;
 
-	for (in_tok = start_tok; in_tok; in_tok = following_tok) {
-		following_tok = backwards ? in_tok->previous : in_tok->next;
+	if (list_empty(head))
+		return 0;
+
+	start_tok = list_entry(backwards ? head->prev : head->next,
+			       struct trailer_item,
+			       list);
+
+	list_for_each_dir(pos, head, backwards) {
+		in_tok = list_entry(pos, struct trailer_item, list);
 		if (!same_token(in_tok, arg_tok))
 			continue;
 		on_tok = middle ? in_tok : start_tok;
-		apply_arg_if_exists(in_tok, arg_tok, on_tok,
-				    in_tok_first, in_tok_last);
+		apply_arg_if_exists(in_tok, arg_tok, on_tok, head);
 		return 1;
 	}
 	return 0;
 }
 
-static void process_trailers_lists(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item **arg_tok_first)
+static void process_trailers_lists(struct list_head *head,
+				   struct list_head *arg_head)
 {
+	struct list_head *pos, *p;
 	struct trailer_item *arg_tok;
-	struct trailer_item *next_arg;
-
-	if (!*arg_tok_first)
-		return;
 
-	for (arg_tok = *arg_tok_first; arg_tok; arg_tok = next_arg) {
+	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
+		arg_tok = list_entry(pos, struct trailer_item, list);
 
-		next_arg = arg_tok->next;
-		remove_from_list(arg_tok, arg_tok_first, NULL);
+		list_del(pos);
 
-		applied = find_same_and_apply_arg(in_tok_first,
-						  in_tok_last,
-						  arg_tok);
+		applied = find_same_and_apply_arg(head, arg_tok);
 
 		if (!applied)
-			apply_arg_if_missing(in_tok_first,
-					     in_tok_last,
-					     arg_tok);
+			apply_arg_if_missing(head, arg_tok);
 	}
 }
 
@@ -438,13 +377,12 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 
 static struct trailer_item *get_conf_item(const char *name)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	struct trailer_item *previous;
 
 	/* Look up item with same name */
-	for (previous = NULL, item = first_conf_item;
-	     item;
-	     previous = item, item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
@@ -454,12 +392,7 @@ static struct trailer_item *get_conf_item(const char *name)
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
-	if (!previous)
-		first_conf_item = item;
-	else {
-		previous->next = item;
-		item->previous = previous;
-	}
+	list_add_tail(&item->list, &conf_head);
 
 	return item;
 }
@@ -633,6 +566,7 @@ static struct trailer_item *create_trailer_item(const char *string)
 	struct strbuf val = STRBUF_INIT;
 	struct trailer_item *item;
 	int tok_len;
+	struct list_head *pos;
 
 	if (parse_trailer(&tok, &val, string))
 		return NULL;
@@ -640,7 +574,8 @@ static struct trailer_item *create_trailer_item(const char *string)
 	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (token_matches_item(tok.buf, item, tok_len))
 			return new_trailer_item(item,
 						strbuf_detach(&tok, NULL),
@@ -652,44 +587,34 @@ static struct trailer_item *create_trailer_item(const char *string)
 				strbuf_detach(&val, NULL));
 }
 
-static void add_trailer_item(struct trailer_item **first,
-			     struct trailer_item **last,
-			     struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, struct trailer_item *new)
 {
 	if (!new)
 		return;
-	if (!*last) {
-		*first = new;
-		*last = new;
-	} else {
-		(*last)->next = new;
-		new->previous = *last;
-		*last = new;
-	}
+	list_add_tail(&new->list, head);
 }
 
-static struct trailer_item *process_command_line_args(struct string_list *trailers)
+static void process_command_line_args(struct list_head *arg_head, 
+				      struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_first = NULL;
-	struct trailer_item *arg_tok_last = NULL;
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (item->conf.command) {
 			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+			add_trailer_item(arg_head, new);
 		}
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+		add_trailer_item(arg_head, new);
 	}
-
-	return arg_tok_first;
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -805,8 +730,7 @@ static void print_lines(FILE *outfile, struct strbuf **lines, int start, int end
 
 static int process_input_file(FILE *outfile,
 			      struct strbuf **lines,
-			      struct trailer_item **in_tok_first,
-			      struct trailer_item **in_tok_last)
+			      struct list_head *head)
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
@@ -829,18 +753,19 @@ static int process_input_file(FILE *outfile,
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char) {
 			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_first, in_tok_last, new);
+			add_trailer_item(head, new);
 		}
 	}
 
 	return trailer_end;
 }
 
-static void free_all(struct trailer_item **first)
+static void free_all(struct list_head *head)
 {
-	while (*first) {
-		struct trailer_item *item = remove_first(first);
-		free_trailer_item(item);
+	struct list_head *pos, *p;
+	list_for_each_safe(pos, p, head) {
+		list_del(pos);
+		free_trailer_item(list_entry(pos, struct trailer_item, list));
 	}
 }
 
@@ -877,9 +802,8 @@ static FILE *create_in_place_tempfile(const char *file)
 
 void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers)
 {
-	struct trailer_item *in_tok_first = NULL;
-	struct trailer_item *in_tok_last = NULL;
-	struct trailer_item *arg_tok_first;
+	LIST_HEAD(head);
+	LIST_HEAD(arg_head);
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
@@ -894,15 +818,15 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 		outfile = create_in_place_tempfile(file);
 
 	/* Print the lines before the trailers */
-	trailer_end = process_input_file(outfile, lines, &in_tok_first, &in_tok_last);
+	trailer_end = process_input_file(outfile, lines, &head);
 
-	arg_tok_first = process_command_line_args(trailers);
+	process_command_line_args(&arg_head, trailers);
 
-	process_trailers_lists(&in_tok_first, &in_tok_last, &arg_tok_first);
+	process_trailers_lists(&head, &arg_head);
 
-	print_all(outfile, in_tok_first, trim_empty);
+	print_all(outfile, &head, trim_empty);
 
-	free_all(&in_tok_first);
+	free_all(&head);
 
 	/* Print the lines after the trailers as is */
 	print_lines(outfile, lines, trailer_end, INT_MAX);
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 3/8] trailer: streamline trailer item create and add

[Jonathan Tan]

Currently, creation and addition (to a list) of trailer items are spread
across multiple functions. Streamline this by only having 2 functions:
one to parse the user-supplied string, and one to add the parsed
information to a list.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 130 +++++++++++++++++++++++++++++---------------------------------
 1 file changed, 60 insertions(+), 70 deletions(-)

diff --git a/trailer.c b/trailer.c
index 4e85aae..ae3972a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -500,10 +500,31 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *trailer)
+static const char *token_from_item(struct trailer_item *item, char *tok)
+{
+	if (item->conf.key)
+		return item->conf.key;
+	if (tok)
+		return tok;
+	return item->conf.name;
+}
+
+static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+{
+	if (!strncasecmp(tok, item->conf.name, tok_len))
+		return 1;
+	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
+}
+
+static int parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
+	struct trailer_item *item;
+	int tok_len;
+	struct list_head *pos;
+
 	strbuf_addstr(&seps, separators);
 	strbuf_addch(&seps, '=');
 	len = strcspn(trailer, seps.buf);
@@ -523,74 +544,31 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *tra
 		strbuf_addstr(tok, trailer);
 		strbuf_trim(tok);
 	}
-	return 0;
-}
-
-static const char *token_from_item(struct trailer_item *item, char *tok)
-{
-	if (item->conf.key)
-		return item->conf.key;
-	if (tok)
-		return tok;
-	return item->conf.name;
-}
-
-static struct trailer_item *new_trailer_item(struct trailer_item *conf_item,
-					     char *tok, char *val)
-{
-	struct trailer_item *new = xcalloc(sizeof(*new), 1);
-	new->value = val ? val : xstrdup("");
-
-	if (conf_item) {
-		duplicate_conf(&new->conf, &conf_item->conf);
-		new->token = xstrdup(token_from_item(conf_item, tok));
-		free(tok);
-	} else {
-		duplicate_conf(&new->conf, &default_conf_info);
-		new->token = tok;
-	}
-
-	return new;
-}
-
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
-{
-	if (!strncasecmp(tok, item->conf.name, tok_len))
-		return 1;
-	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
-}
-
-static struct trailer_item *create_trailer_item(const char *string)
-{
-	struct strbuf tok = STRBUF_INIT;
-	struct strbuf val = STRBUF_INIT;
-	struct trailer_item *item;
-	int tok_len;
-	struct list_head *pos;
-
-	if (parse_trailer(&tok, &val, string))
-		return NULL;
-
-	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
+	tok_len = token_len_without_separator(tok->buf, tok->len);
+	*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (token_matches_item(tok.buf, item, tok_len))
-			return new_trailer_item(item,
-						strbuf_detach(&tok, NULL),
-						strbuf_detach(&val, NULL));
+		if (token_matches_item(tok->buf, item, tok_len)) {
+			char *tok_buf = strbuf_detach(tok, NULL);
+			*conf = &item->conf;
+			strbuf_addstr(tok, token_from_item(item, tok_buf));
+			free(tok_buf);
+			break;
+		}
 	}
 
-	return new_trailer_item(NULL,
-				strbuf_detach(&tok, NULL),
-				strbuf_detach(&val, NULL));
+	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, char *tok, char *val,
+			     const struct conf_info *conf)
 {
-	if (!new)
-		return;
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
@@ -599,21 +577,28 @@ static void process_command_line_args(struct list_head *arg_head,
 {
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (item->conf.command) {
-			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(arg_head, new);
-		}
+		if (item->conf.command)
+			add_trailer_item(arg_head,
+					 xstrdup(token_from_item(item, NULL)),
+					 xstrdup(""),
+					 &item->conf);
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(arg_head, new);
+		if (!parse_trailer(&tok, &val, &conf, tr->string))
+			add_trailer_item(arg_head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 }
 
@@ -734,6 +719,9 @@ static int process_input_file(FILE *outfile,
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -751,10 +739,12 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char) {
-			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(head, new);
-		}
+		if (lines[i]->buf[0] != comment_line_char &&
+		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+			add_trailer_item(head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 4/8] trailer: make args have their own struct

[Jonathan Tan]

Improve type safety by making arguments (whether from configuration or
from the command line) have their own "struct arg_item" type, separate
from the "struct trailer_item" type used to represent the trailers in
the buffer being manipulated.

This change also prepares "struct trailer_item" to be further
differentiated from "struct arg_item" in future patches.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 135 +++++++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 85 insertions(+), 50 deletions(-)

diff --git a/trailer.c b/trailer.c
index ae3972a..99018f8 100644
--- a/trailer.c
+++ b/trailer.c
@@ -29,6 +29,12 @@ struct trailer_item {
 	struct list_head list;
 	char *token;
 	char *value;
+};
+
+struct arg_item {
+	struct list_head list;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -62,7 +68,7 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(struct trailer_item *a, struct trailer_item *b)
+static int same_token(struct trailer_item *a, struct arg_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -71,12 +77,12 @@ static int same_token(struct trailer_item *a, struct trailer_item *b)
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(struct trailer_item *a, struct trailer_item *b)
+static int same_value(struct trailer_item *a, struct arg_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(struct trailer_item *a, struct trailer_item *b)
+static int same_trailer(struct trailer_item *a, struct arg_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -98,6 +104,13 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 
 static void free_trailer_item(struct trailer_item *item)
 {
+	free(item->token);
+	free(item->value);
+	free(item);
+}
+
+static void free_arg_item(struct arg_item *item)
+{
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
@@ -137,17 +150,29 @@ static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 	}
 }
 
+static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
+{
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = arg_tok->token;
+	new->value = arg_tok->value;
+	arg_tok->token = arg_tok->value = NULL;
+	free_arg_item(arg_tok);
+	return new;
+}
+
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok)
+				  struct arg_item *arg_tok)
 {
-	if (after_or_end(arg_tok->conf.where))
-		list_add(&arg_tok->list, &on_tok->list);
+	int aoe = after_or_end(arg_tok->conf.where);
+	struct trailer_item *to_add = trailer_from_arg(arg_tok);
+	if (aoe)
+		list_add(&to_add->list, &on_tok->list);
 	else
-		list_add_tail(&arg_tok->list, &on_tok->list);
+		list_add_tail(&to_add->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
-			      struct trailer_item *arg_tok,
+			      struct arg_item *arg_tok,
 			      int check_all,
 			      struct list_head *head)
 {
@@ -200,7 +225,7 @@ static char *apply_command(const char *command, const char *arg)
 	return result;
 }
 
-static void apply_item_command(struct trailer_item *in_tok, struct trailer_item *arg_tok)
+static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg_tok)
 {
 	if (arg_tok->conf.command) {
 		const char *arg;
@@ -218,13 +243,13 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 }
 
 static void apply_arg_if_exists(struct trailer_item *in_tok,
-				struct trailer_item *arg_tok,
+				struct arg_item *arg_tok,
 				struct trailer_item *on_tok,
 				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
@@ -241,39 +266,41 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		if (check_if_different(in_tok, arg_tok, 1, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
 		if (check_if_different(on_tok, arg_tok, 0, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	}
 }
 
 static void apply_arg_if_missing(struct list_head *head,
-				 struct trailer_item *arg_tok)
+				 struct arg_item *arg_tok)
 {
 	enum action_where where;
+	struct trailer_item *to_add;
 
 	switch (arg_tok->conf.if_missing) {
 	case MISSING_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
 		apply_item_command(NULL, arg_tok);
+		to_add = trailer_from_arg(arg_tok);
 		if (after_or_end(where))
-			list_add_tail(&arg_tok->list, head);
+			list_add_tail(&to_add->list, head);
 		else
-			list_add(&arg_tok->list, head);
+			list_add(&to_add->list, head);
 	}
 }
 
 static int find_same_and_apply_arg(struct list_head *head,
-				   struct trailer_item *arg_tok)
+				   struct arg_item *arg_tok)
 {
 	struct list_head *pos;
 	struct trailer_item *in_tok;
@@ -306,11 +333,11 @@ static void process_trailers_lists(struct list_head *head,
 				   struct list_head *arg_head)
 {
 	struct list_head *pos, *p;
-	struct trailer_item *arg_tok;
+	struct arg_item *arg_tok;
 
 	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
-		arg_tok = list_entry(pos, struct trailer_item, list);
+		arg_tok = list_entry(pos, struct arg_item, list);
 
 		list_del(pos);
 
@@ -375,20 +402,20 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 		dst->command = xstrdup(src->command);
 }
 
-static struct trailer_item *get_conf_item(const char *name)
+static struct arg_item *get_conf_item(const char *name)
 {
 	struct list_head *pos;
-	struct trailer_item *item;
+	struct arg_item *item;
 
 	/* Look up item with same name */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
 
 	/* Item does not already exists, create it */
-	item = xcalloc(sizeof(struct trailer_item), 1);
+	item = xcalloc(sizeof(*item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
@@ -442,7 +469,7 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v
 static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 {
 	const char *trailer_item, *variable_name;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct conf_info *conf;
 	char *name = NULL;
 	enum trailer_info_type type;
@@ -500,7 +527,7 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static const char *token_from_item(struct trailer_item *item, char *tok)
+static const char *token_from_item(struct arg_item *item, char *tok)
 {
 	if (item->conf.key)
 		return item->conf.key;
@@ -509,7 +536,7 @@ static const char *token_from_item(struct trailer_item *item, char *tok)
 	return item->conf.name;
 }
 
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+static int token_matches_item(const char *tok, struct arg_item *item, int tok_len)
 {
 	if (!strncasecmp(tok, item->conf.name, tok_len))
 		return 1;
@@ -521,7 +548,7 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
-	struct trailer_item *item;
+	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
@@ -547,12 +574,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 
 	/* Lookup if the token matches something in the config */
 	tok_len = token_len_without_separator(tok->buf, tok->len);
-	*conf = &default_conf_info;
+	if (conf)
+		*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (token_matches_item(tok->buf, item, tok_len)) {
 			char *tok_buf = strbuf_detach(tok, NULL);
-			*conf = &item->conf;
+			if (conf)
+				*conf = &item->conf;
 			strbuf_addstr(tok, token_from_item(item, tok_buf));
 			free(tok_buf);
 			break;
@@ -562,43 +591,51 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val,
-			     const struct conf_info *conf)
+static void add_trailer_item(struct list_head *head, char *tok, char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
-	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
+static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
+			 const struct conf_info *conf)
+{
+	struct arg_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
+	list_add_tail(&new->list, arg_head);
+}
+
 static void process_command_line_args(struct list_head *arg_head, 
 				      struct string_list *trailers)
 {
 	struct string_list_item *tr;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
 	const struct conf_info *conf;
 	struct list_head *pos;
 
-	/* Add a trailer item for each configured trailer with a command */
+	/* Add an arg item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (item->conf.command)
-			add_trailer_item(arg_head,
-					 xstrdup(token_from_item(item, NULL)),
-					 xstrdup(""),
-					 &item->conf);
+			add_arg_item(arg_head,
+				     xstrdup(token_from_item(item, NULL)),
+				     xstrdup(""),
+				     &item->conf);
 	}
 
-	/* Add a trailer item for each trailer on the command line */
+	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		if (!parse_trailer(&tok, &val, &conf, tr->string))
-			add_trailer_item(arg_head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+			add_arg_item(arg_head,
+				     strbuf_detach(&tok, NULL),
+				     strbuf_detach(&val, NULL),
+				     conf);
 	}
 }
 
@@ -721,7 +758,6 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
-	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -740,11 +776,10 @@ static int process_input_file(FILE *outfile,
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+					 strbuf_detach(&val, NULL));
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Jonathan Tan]

The parse_trailer function has a few modes of operation, all depending
on whether the separator is present in its input, and if yes, the
separator's position. Some of these modes are failure modes, and these
failure modes are handled differently depending on whether the trailer
line was sourced from a file or from a command-line argument.

Extract a function to find the separator, allowing the invokers of
parse_trailer to determine how to handle the failure modes instead of
making parse_trailer do it.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 70 +++++++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 48 insertions(+), 22 deletions(-)

diff --git a/trailer.c b/trailer.c
index 99018f8..137a3fb 100644
--- a/trailer.c
+++ b/trailer.c
@@ -543,29 +543,40 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
 	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val,
-			 const struct conf_info **conf, const char *trailer)
+/*
+ * Return the location of the first separator or '=' in line, or -1 if either a
+ * newline or the null terminator is reached first.
+ */
+static int find_separator(const char *line)
+{
+	const char *c;
+	for (c = line; ; c++) {
+		if (!*c || *c == '\n')
+			return -1;
+		if (*c == '=' || strchr(separators, *c))
+			return c - line;
+	}
+}
+
+/*
+ * Obtain the token, value, and conf from the given trailer.
+ *
+ * separator_pos must not be 0, since the token cannot be an empty string.
+ *
+ * If separator_pos is -1, interpret the whole trailer as a token.
+ */
+static void parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer,
+			 int separator_pos)
 {
-	size_t len;
-	struct strbuf seps = STRBUF_INIT;
 	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
-	strbuf_addstr(&seps, separators);
-	strbuf_addch(&seps, '=');
-	len = strcspn(trailer, seps.buf);
-	strbuf_release(&seps);
-	if (len == 0) {
-		int l = strlen(trailer);
-		while (l > 0 && isspace(trailer[l - 1]))
-			l--;
-		return error(_("empty trailer token in trailer '%.*s'"), l, trailer);
-	}
-	if (len < strlen(trailer)) {
-		strbuf_add(tok, trailer, len);
+	if (separator_pos != -1) {
+		strbuf_add(tok, trailer, separator_pos);
 		strbuf_trim(tok);
-		strbuf_addstr(val, trailer + len + 1);
+		strbuf_addstr(val, trailer + separator_pos + 1);
 		strbuf_trim(val);
 	} else {
 		strbuf_addstr(tok, trailer);
@@ -587,8 +598,6 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 			break;
 		}
 	}
-
-	return 0;
 }
 
 static void add_trailer_item(struct list_head *head, char *tok, char *val)
@@ -631,11 +640,22 @@ static void process_command_line_args(struct list_head *arg_head,
 
 	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		if (!parse_trailer(&tok, &val, &conf, tr->string))
+		int separator_pos = find_separator(tr->string);
+		if (separator_pos == 0) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addstr(&sb, tr->string);
+			strbuf_trim(&sb);
+			error(_("empty trailer token in trailer '%.*s'"),
+			      (int) sb.len, sb.buf);
+			strbuf_release(&sb);
+		} else {
+			parse_trailer(&tok, &val, &conf, tr->string,
+				      separator_pos);
 			add_arg_item(arg_head,
 				     strbuf_detach(&tok, NULL),
 				     strbuf_detach(&val, NULL),
 				     conf);
+		}
 	}
 }
 
@@ -775,11 +795,17 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
+		int separator_pos;
+		if (lines[i]->buf[0] == comment_line_char)
+			continue;
+		separator_pos = find_separator(lines[i]->buf);
+		if (separator_pos >= 1) {
+			parse_trailer(&tok, &val, NULL, lines[i]->buf,
+				      separator_pos);
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		}
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Stefan Beller]

On Thu, Oct 20, 2016 at 2:39 PM, Jonathan Tan <jonathantanmy@google.com> wrote:
> The parse_trailer function has a few modes of operation, all depending
> on whether the separator is present in its input, and if yes, the
> separator's position. Some of these modes are failure modes, and these
> failure modes are handled differently depending on whether the trailer
> line was sourced from a file or from a command-line argument.
>
> Extract a function to find the separator, allowing the invokers of
> parse_trailer to determine how to handle the failure modes instead of
> making parse_trailer do it.
>
> Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
> ---
>  trailer.c | 70 +++++++++++++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 48 insertions(+), 22 deletions(-)
>
> diff --git a/trailer.c b/trailer.c
> index 99018f8..137a3fb 100644
> --- a/trailer.c
> +++ b/trailer.c
> @@ -543,29 +543,40 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
>         return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
>  }
>
> -static int parse_trailer(struct strbuf *tok, struct strbuf *val,
> -                        const struct conf_info **conf, const char *trailer)
> +/*
> + * Return the location of the first separator or '=' in line, or -1 if either a
> + * newline or the null terminator is reached first.
> + */
> +static int find_separator(const char *line)
> +{
> +       const char *c;
> +       for (c = line; ; c++) {
> +               if (!*c || *c == '\n')
> +                       return -1;
> +               if (*c == '=' || strchr(separators, *c))
> +                       return c - line;
> +       }

I was about to suggest this function can be simplified and maybe
even inlined by the use of strspn or strcspn, but I think manual
processing of the string is fine, too, as it would not really be shorter.

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Junio C Hamano]

Stefan Beller <sbeller@google.com> writes:

>> +static int find_separator(const char *line)
>> +{
>> +       const char *c;
>> +       for (c = line; ; c++) {
>> +               if (!*c || *c == '\n')
>> +                       return -1;
>> +               if (*c == '=' || strchr(separators, *c))
>> +                       return c - line;
>> +       }
>
> I was about to suggest this function can be simplified and maybe
> even inlined by the use of strspn or strcspn, but I think manual
> processing of the string is fine, too, as it would not really be shorter.

Hmm, I fear that iterating over a line one-byte-at-a-time and
running strchr(separators, *c) on it for each byte has a performance
implication over running a single call to strcspn(line, separators).

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Jonathan Tan]

On 10/20/2016 03:14 PM, Junio C Hamano wrote:
> Stefan Beller <sbeller@google.com> writes:
>
>>> +static int find_separator(const char *line)
>>> +{
>>> +       const char *c;
>>> +       for (c = line; ; c++) {
>>> +               if (!*c || *c == '\n')
>>> +                       return -1;
>>> +               if (*c == '=' || strchr(separators, *c))
>>> +                       return c - line;
>>> +       }
>>
>> I was about to suggest this function can be simplified and maybe
>> even inlined by the use of strspn or strcspn, but I think manual
>> processing of the string is fine, too, as it would not really be shorter.
>
> Hmm, I fear that iterating over a line one-byte-at-a-time and
> running strchr(separators, *c) on it for each byte has a performance
> implication over running a single call to strcspn(line, separators).

If we do that, there is also the necessity of creating a string that 
combines the separators and '=' (I guess '\n' is not necessary now, 
since all the lines are null terminated). I'm OK either way.

(We could cache that string, although I would think that if we did that, 
we might as well write the loop manually, like in this patch.)

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> If we do that, there is also the necessity of creating a string that
> combines the separators and '=' (I guess '\n' is not necessary now,
> since all the lines are null terminated). I'm OK either way.
>
> (We could cache that string, although I would think that if we did
> that, we might as well write the loop manually, like in this patch.)

I wonder if there is a legit reason to look for '=' in the first
place.  "Signed-off-by= Jonathan Tan <jt@my.home>" does not look
like a valid trailer line to me.

Isn't that a remnant of lazy coding in the original that tried to
share a single parser for contents and command line options or
something?

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Jonathan Tan]

On 10/20/2016 03:45 PM, Junio C Hamano wrote:
> Jonathan Tan <jonathantanmy@google.com> writes:
>
>> If we do that, there is also the necessity of creating a string that
>> combines the separators and '=' (I guess '\n' is not necessary now,
>> since all the lines are null terminated). I'm OK either way.
>>
>> (We could cache that string, although I would think that if we did
>> that, we might as well write the loop manually, like in this patch.)
>
> I wonder if there is a legit reason to look for '=' in the first
> place.  "Signed-off-by= Jonathan Tan <jt@my.home>" does not look
> like a valid trailer line to me.
>
> Isn't that a remnant of lazy coding in the original that tried to
> share a single parser for contents and command line options or
> something?

That is true - I think we can take the allowed separators as an argument 
(meaning that we can have different behavior for file parsing and 
command line parsing), and since we already have that string, we can use 
strcspn. I'll try this out in the next reroll.

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Junio C Hamano]

Jonathan Tan <jonathantanmy@google.com> writes:

> That is true - I think we can take the allowed separators as an
> argument (meaning that we can have different behavior for file parsing
> and command line parsing), and since we already have that string, we
> can use strcspn. I'll try this out in the next reroll.

Sounds good.  Thanks.


The following is a tangent that I think this topic should ignore,
but we may want to revisit it sometime later.

I think the design of the "separator" mechanism is one of the things
we botched in the current system.  If I recall correctly, this was
introduced to allow people write "Bug# 538" in the trailer section
and get it recognised as a valid trailer.

When I say that this was a botched design, I do not mean to say that
we should have instead forced projects to adopt "Bug: 538" format.
The design is botched because the users' wish to allow "Bug# 538" or
"Bug #538" by setting separators to ":#" from the built-in ":" does
not mean that they would want "Signed-off-by# me <my@addre.ss>" to
be accepted.

If I were guiding a topic that introduce this feature from scratch
today, I would probably suggest a pattern based approach, e.g.  a
built-in "[-A-Za-z0-9]+:" [*1*] may be the default prefix that is
used to recognize the beginning of a trailer, and a user or a
project that wants "Bug #538" would be allowed to add an additional
pattern, e.g. "Bug *#", that recognises a custom trailer line that
is used by the project.


[Footnote]

*1* Or more lenient "[A-Za-z0-9][- A-Za-z0-9]*:".

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Christian Couder]

On Fri, Oct 21, 2016 at 2:18 AM, Junio C Hamano <gitster@pobox.com> wrote:
> Jonathan Tan <jonathantanmy@google.com> writes:
>
>> That is true - I think we can take the allowed separators as an
>> argument (meaning that we can have different behavior for file parsing
>> and command line parsing), and since we already have that string, we
>> can use strcspn. I'll try this out in the next reroll.
>
> Sounds good.  Thanks.
>
>
> The following is a tangent that I think this topic should ignore,
> but we may want to revisit it sometime later.
>
> I think the design of the "separator" mechanism is one of the things
> we botched in the current system.  If I recall correctly, this was
> introduced to allow people write "Bug# 538" in the trailer section
> and get it recognised as a valid trailer.
>
> When I say that this was a botched design, I do not mean to say that
> we should have instead forced projects to adopt "Bug: 538" format.
> The design is botched because the users' wish to allow "Bug# 538" or
> "Bug #538" by setting separators to ":#" from the built-in ":" does
> not mean that they would want "Signed-off-by# me <my@addre.ss>" to
> be accepted.
>
> If I were guiding a topic that introduce this feature from scratch
> today, I would probably suggest a pattern based approach, e.g.  a
> built-in "[-A-Za-z0-9]+:" [*1*] may be the default prefix that is
> used to recognize the beginning of a trailer, and a user or a
> project that wants "Bug #538" would be allowed to add an additional
> pattern, e.g. "Bug *#", that recognises a custom trailer line that
> is used by the project.

When we designed the separator mechanism, we had the following discussions:

https://public-inbox.org/git/xmqqa9a1d6xn.fsf@gitster.dls.corp.google.com/
https://public-inbox.org/git/xmqqmwcuzyqx.fsf@gitster.dls.corp.google.com/

They made me think that you were against too much flexibility, so I
removed functionality that allowed to put separators into the ".key"
config options, and now you are saying that we botched the thing and
that you would like more flexibility of this kind back.

Anyway I think it is still possible to add back such kind of
functionality in a backward compatible way for example by adding
".extendedKey" config options.

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Junio C Hamano]

Christian Couder <christian.couder@gmail.com> writes:

> On Fri, Oct 21, 2016 at 2:18 AM, Junio C Hamano <gitster@pobox.com> wrote:
>>
>> If I were guiding a topic that introduce this feature from scratch
>> today, I would probably suggest a pattern based approach, e.g.  a
>> built-in "[-A-Za-z0-9]+:" [*1*] may be the default prefix that is
>> used to recognize the beginning of a trailer, and a user or a
>> project that wants "Bug #538" would be allowed to add an additional
>> pattern, e.g. "Bug *#", that recognises a custom trailer line that
>> is used by the project.
>
> When we designed the separator mechanism, we had the following discussions:
>
> https://public-inbox.org/git/xmqqa9a1d6xn.fsf@gitster.dls.corp.google.com/
> https://public-inbox.org/git/xmqqmwcuzyqx.fsf@gitster.dls.corp.google.com/
>
> They made me think that you were against too much flexibility, so I
> removed functionality that allowed to put separators into the ".key"
> config options, and now you are saying that we botched the thing and
> that you would like more flexibility of this kind back.

Correct.  Pay attention to the fact that I said _we_ botched.

If an initial design made by a topic author is crappy, that may be
author's botch.  Once a topic goes through a review cycle by getting
reviewed, rerolled, re-reviewed, ... to the point that those
involved accept the result, and we later realize that it was not
good, the botch no longer is author's alone.  If it is shipped as
part of a release, then it is not just the authors and the reviewers
but everybody.  We collectively stopped at a place that was not
ideal and share the blame ;-).

> Anyway I think it is still possible to add back such kind of
> functionality in a backward compatible way for example by adding
> ".extendedKey" config options.

Yup, or with trailer.keyPattern that is multi-values, or with any
number of alternatives.

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Christian Couder]

On Fri, Oct 21, 2016 at 12:45 AM, Junio C Hamano <gitster@pobox.com> wrote:
> Jonathan Tan <jonathantanmy@google.com> writes:
>
>> If we do that, there is also the necessity of creating a string that
>> combines the separators and '=' (I guess '\n' is not necessary now,
>> since all the lines are null terminated). I'm OK either way.
>>
>> (We could cache that string, although I would think that if we did
>> that, we might as well write the loop manually, like in this patch.)
>
> I wonder if there is a legit reason to look for '=' in the first
> place.  "Signed-off-by= Jonathan Tan <jt@my.home>" does not look
> like a valid trailer line to me.
>
> Isn't that a remnant of lazy coding in the original that tried to
> share a single parser for contents and command line options or
> something?

I think the relevant discussion was this one:

https://public-inbox.org/git/20140915.080429.1739849931027469667.chriscool@tuxfamily.org/

Re: [PATCH v4 5/8] trailer: clarify failure modes in parse_trailer

[Jonathan Tan]

On 10/20/2016 03:40 PM, Jonathan Tan wrote:
> On 10/20/2016 03:14 PM, Junio C Hamano wrote:
>> Stefan Beller <sbeller@google.com> writes:
>>
>>>> +static int find_separator(const char *line)
>>>> +{
>>>> +       const char *c;
>>>> +       for (c = line; ; c++) {
>>>> +               if (!*c || *c == '\n')
>>>> +                       return -1;
>>>> +               if (*c == '=' || strchr(separators, *c))
>>>> +                       return c - line;
>>>> +       }
>>>
>>> I was about to suggest this function can be simplified and maybe
>>> even inlined by the use of strspn or strcspn, but I think manual
>>> processing of the string is fine, too, as it would not really be
>>> shorter.
>>
>> Hmm, I fear that iterating over a line one-byte-at-a-time and
>> running strchr(separators, *c) on it for each byte has a performance
>> implication over running a single call to strcspn(line, separators).
>
> If we do that, there is also the necessity of creating a string that
> combines the separators and '=' (I guess '\n' is not necessary now,
> since all the lines are null terminated). I'm OK either way.
>
> (We could cache that string, although I would think that if we did that,
> we might as well write the loop manually, like in this patch.)

Actually I guess we could generate the separators_and_equal string 
whenever we obtain new separators from the config. I'll do this in the 
next reroll.

[PATCH v4 6/8] trailer: allow non-trailers in trailer block

[Jonathan Tan]

Currently, interpret-trailers requires all lines of a trailer block to
be trailers (or comments) - if not it would not identify that block as a
trailer block, and thus create its own trailer block, inserting a blank
line.  For example:

  echo -e "\nSigned-off-by: x\nnot trailer" |
  git interpret-trailers --trailer "c: d"

would result in:

  Signed-off-by: x
  not trailer

  c: d

Relax the definition of a trailer block to require that the trailers (i)
are all trailers, or (ii) contain at least one Git-generated trailer and
consists of at least 25% trailers.

  Signed-off-by: x
  not trailer
  c: d

(i) is the existing functionality. (ii) allows arbitrary lines to be
included in trailer blocks, like those in [1], and still allow
interpret-trailers to be used.

[1]
https://kernel.googlesource.com/pub/scm/linux/kernel/git/stable/linux-stable/+/e7d316a02f683864a12389f8808570e37fb90aa3

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |   5 +-
 t/t7513-interpret-trailers.sh            | 115 +++++++++++++++++++++++++++++++
 trailer.c                                |  89 ++++++++++++++++++++----
 3 files changed, 194 insertions(+), 15 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 93d1db6..cf4c5ea 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -48,8 +48,9 @@ with only spaces at the end of the commit message part, one blank line
 will be added before the new trailer.
 
 Existing trailers are extracted from the input message by looking for
-a group of one or more lines that contain a colon (by default), where
-the group is preceded by one or more empty (or whitespace-only) lines.
+a group of one or more lines that (i) are all trailers, or (ii) contains at
+least one Git-generated trailer and consists of at least 25% trailers.
+The group must be preceded by one or more empty (or whitespace-only) lines.
 The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
 minus signs start the patch part of the message.
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index aee785c..003e90f 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -126,6 +126,121 @@ test_expect_success 'with multiline title in the message' '
 	test_cmp expected actual
 '
 
+test_expect_success 'with non-trailer lines mixed with Signed-off-by' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		Signed-off-by: a <a@example.com>
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		Signed-off-by: a <a@example.com>
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with cherry picked from' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		(cherry picked from commit x)
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		(cherry picked from commit x)
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with a configured trailer' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		My-trailer: x
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		My-trailer: x
+		this is not a trailer
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with a non-configured trailer' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		I-am-not-configured: x
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		I-am-not-configured: x
+		this is not a trailer
+
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with all non-configured trailers' '
+	cat >patch <<-\EOF &&
+
+		I-am-not-configured: x
+		I-am-also-not-configured: x
+	EOF
+	cat >expected <<-\EOF &&
+
+		I-am-not-configured: x
+		I-am-also-not-configured: x
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines only' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index 137a3fb..da15b79 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,6 +27,10 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct list_head list;
+	/*
+	 * If this is not a trailer line, the line is stored in value
+	 * (excluding the terminating newline) and token is NULL.
+	 */
 	char *token;
 	char *value;
 };
@@ -44,6 +48,12 @@ static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+static const char *git_generated_prefixes[] = {
+	"Signed-off-by: ",
+	"(cherry picked from commit ",
+	NULL
+};
+
 /* Iterate over the elements of the list. */
 #define list_for_each_dir(pos, head, is_reverse) \
 	for (pos = is_reverse ? (head)->prev : (head)->next; \
@@ -70,9 +80,14 @@ static size_t token_len_without_separator(const char *token, size_t len)
 
 static int same_token(struct trailer_item *a, struct arg_item *b)
 {
-	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
-	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
-	size_t min_len = (a_len > b_len) ? b_len : a_len;
+	size_t a_len, b_len, min_len;
+
+	if (!a->token)
+		return 0;
+
+	a_len = token_len_without_separator(a->token, strlen(a->token));
+	b_len = token_len_without_separator(b->token, strlen(b->token));
+	min_len = (a_len > b_len) ? b_len : a_len;
 
 	return !strncasecmp(a->token, b->token, min_len);
 }
@@ -130,7 +145,14 @@ static char last_non_space_char(const char *s)
 
 static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 {
-	char c = last_non_space_char(tok);
+	char c;
+
+	if (!tok) {
+		fprintf(outfile, "%s\n", val);
+		return;
+	}
+
+	c = last_non_space_char(tok);
 	if (!c)
 		return;
 	if (strchr(separators, c))
@@ -704,6 +726,7 @@ static int find_patch_start(struct strbuf **lines, int count)
 static int find_trailer_start(struct strbuf **lines, int count)
 {
 	int start, end_of_title, only_spaces = 1;
+	int recognized_prefix = 0, trailer_lines = 0, non_trailer_lines = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -715,26 +738,60 @@ static int find_trailer_start(struct strbuf **lines, int count)
 	end_of_title = start;
 
 	/*
-	 * Get the start of the trailers by looking starting from the end
-	 * for a line with only spaces before lines with one separator.
+	 * Get the start of the trailers by looking starting from the end for a
+	 * blank line before a set of non-blank lines that (i) are all
+	 * trailers, or (ii) contains at least one Git-generated trailer and
+	 * consists of at least 25% trailers.
 	 */
 	for (start = count - 1; start >= end_of_title; start--) {
+		const char **p;
+		int separator_pos;
+
 		if (lines[start]->buf[0] == comment_line_char)
 			continue;
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
-			return start + 1;
+			if (recognized_prefix &&
+			    trailer_lines * 3 >= non_trailer_lines)
+				return start + 1;
+			if (trailer_lines && !non_trailer_lines)
+				return start + 1;
+			return count;
 		}
-		if (strcspn(lines[start]->buf, separators) < lines[start]->len) {
-			if (only_spaces)
-				only_spaces = 0;
-			continue;
+		only_spaces = 0;
+
+		for (p = git_generated_prefixes; *p; p++) {
+			if (starts_with(lines[start]->buf, *p)) {
+				trailer_lines++;
+				recognized_prefix = 1;
+				goto continue_outer_loop;
+			}
 		}
-		return count;
+
+		separator_pos = find_separator(lines[start]->buf);
+		if (separator_pos >= 1) {
+			struct list_head *pos;
+
+			trailer_lines++;
+			if (recognized_prefix)
+				continue;
+			list_for_each(pos, &conf_head) {
+				struct arg_item *item;
+				item = list_entry(pos, struct arg_item, list);
+				if (token_matches_item(lines[start]->buf, item,
+						       separator_pos)) {
+					recognized_prefix = 1;
+					break;
+				}
+			}
+		} else
+			non_trailer_lines++;
+continue_outer_loop:
+		;
 	}
 
-	return only_spaces ? count : 0;
+	return count;
 }
 
 /* Get the index of the end of the trailers */
@@ -805,6 +862,12 @@ static int process_input_file(FILE *outfile,
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		} else {
+			strbuf_addbuf(&val, lines[i]);
+			strbuf_strip_suffix(&val, "\n");
+			add_trailer_item(head,
+					 NULL,
+					 strbuf_detach(&val, NULL));
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 7/8] trailer: forbid leading whitespace in trailers

[Jonathan Tan]

Currently, interpret-trailers allows leading whitespace in trailer
lines. This leads to false positives, especially for quoted lines or
bullet lists.

Forbid leading whitespace in trailers.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |  2 +-
 t/t7513-interpret-trailers.sh            | 15 +++++++++++++++
 trailer.c                                |  2 +-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index cf4c5ea..4966b5b 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -55,7 +55,7 @@ The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
 minus signs start the patch part of the message.
 
-When reading trailers, there can be whitespaces before and after the
+When reading trailers, there can be whitespaces after the
 token, the separator and the value. There can also be whitespaces
 inside the token and the value.
 
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 003e90f..3d94b3a 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -241,6 +241,21 @@ test_expect_success 'with non-trailer lines only' '
 	test_cmp expected actual
 '
 
+test_expect_success 'line with leading whitespace is not trailer' '
+	q_to_tab >patch <<-\EOF &&
+
+		Qtoken: value
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		Qtoken: value
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index da15b79..3ef5576 100644
--- a/trailer.c
+++ b/trailer.c
@@ -770,7 +770,7 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		}
 
 		separator_pos = find_separator(lines[start]->buf);
-		if (separator_pos >= 1) {
+		if (separator_pos >= 1 && !isspace(lines[start]->buf[0])) {
 			struct list_head *pos;
 
 			trailer_lines++;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v4 8/8] trailer: support values folded to multiple lines

[Jonathan Tan]

Currently, interpret-trailers requires that a trailer be only on 1 line.
For example:

a: first line
   second line

would be interpreted as one trailer line followed by one non-trailer line.

Make interpret-trailers support RFC 822-style folding, treating those
lines as one logical trailer.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |   7 +-
 t/t7513-interpret-trailers.sh            | 169 +++++++++++++++++++++++++++++++
 trailer.c                                |  43 ++++++--
 3 files changed, 210 insertions(+), 9 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 4966b5b..e99bda6 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -57,11 +57,12 @@ minus signs start the patch part of the message.
 
 When reading trailers, there can be whitespaces after the
 token, the separator and the value. There can also be whitespaces
-inside the token and the value.
+inside the token and the value. The value may be split over multiple lines with
+each subsequent line starting with whitespace, like the "folding" in RFC 822.
 
 Note that 'trailers' do not follow and are not intended to follow many
-rules for RFC 822 headers. For example they do not follow the line
-folding rules, the encoding rules and probably many other rules.
+rules for RFC 822 headers. For example they do not follow
+the encoding rules and probably many other rules.
 
 OPTIONS
 -------
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 3d94b3a..4dd1d7c 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -256,6 +256,175 @@ test_expect_success 'line with leading whitespace is not trailer' '
 	test_cmp expected actual
 '
 
+test_expect_success 'multiline field treated as one trailer for 25% check' '
+	q_to_tab >patch <<-\EOF &&
+
+		Signed-off-by: a <a@example.com>
+		name: value on
+		Qmultiple lines
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		Signed-off-by: a <a@example.com>
+		name: value on
+		Qmultiple lines
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		name: value
+	EOF
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for placement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		name: value
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for replacement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		another: trailer
+		name: value
+	EOF
+	test_config trailer.name.ifexists replace &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for difference check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.ifexists addIfDifferent &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line
+		QQQQQsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for neighbor check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	test_config trailer.name.ifexists addIfDifferentNeighbor &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		name: first line
+		QQQQQsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index 3ef5576..306c387 100644
--- a/trailer.c
+++ b/trailer.c
@@ -622,12 +622,14 @@ static void parse_trailer(struct strbuf *tok, struct strbuf *val,
 	}
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val)
+static struct trailer_item *add_trailer_item(struct list_head *head, char *tok,
+					     char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
 	list_add_tail(&new->list, head);
+	return new;
 }
 
 static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
@@ -727,6 +729,14 @@ static int find_trailer_start(struct strbuf **lines, int count)
 {
 	int start, end_of_title, only_spaces = 1;
 	int recognized_prefix = 0, trailer_lines = 0, non_trailer_lines = 0;
+	/*
+	 * Number of possible continuation lines encountered. This will be
+	 * reset to 0 if we encounter a trailer (since those lines are to be
+	 * considered continuations of that trailer), and added to
+	 * non_trailer_lines if we encounter a non-trailer (since those lines
+	 * are to be considered non-trailers).
+	 */
+	int possible_continuation_lines = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -747,11 +757,15 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		const char **p;
 		int separator_pos;
 
-		if (lines[start]->buf[0] == comment_line_char)
+		if (lines[start]->buf[0] == comment_line_char) {
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
 			continue;
+		}
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
+			non_trailer_lines += possible_continuation_lines;
 			if (recognized_prefix &&
 			    trailer_lines * 3 >= non_trailer_lines)
 				return start + 1;
@@ -764,6 +778,7 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		for (p = git_generated_prefixes; *p; p++) {
 			if (starts_with(lines[start]->buf, *p)) {
 				trailer_lines++;
+				possible_continuation_lines = 0;
 				recognized_prefix = 1;
 				goto continue_outer_loop;
 			}
@@ -774,6 +789,7 @@ static int find_trailer_start(struct strbuf **lines, int count)
 			struct list_head *pos;
 
 			trailer_lines++;
+			possible_continuation_lines = 0;
 			if (recognized_prefix)
 				continue;
 			list_for_each(pos, &conf_head) {
@@ -785,8 +801,13 @@ static int find_trailer_start(struct strbuf **lines, int count)
 					break;
 				}
 			}
-		} else
+		} else if (isspace(lines[start]->buf[0]))
+			possible_continuation_lines++;
+		else {
 			non_trailer_lines++;
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
+		}
 continue_outer_loop:
 		;
 	}
@@ -835,6 +856,7 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
+	struct trailer_item *last = NULL;
 
 	/* Get the line count */
 	while (lines[count])
@@ -855,19 +877,28 @@ static int process_input_file(FILE *outfile,
 		int separator_pos;
 		if (lines[i]->buf[0] == comment_line_char)
 			continue;
+		if (last && isspace(lines[i]->buf[0])) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addf(&sb, "%s\n%s", last->value, lines[i]->buf);
+			strbuf_strip_suffix(&sb, "\n");
+			free(last->value);
+			last->value = strbuf_detach(&sb, NULL);
+			continue;
+		}
 		separator_pos = find_separator(lines[i]->buf);
 		if (separator_pos >= 1) {
 			parse_trailer(&tok, &val, NULL, lines[i]->buf,
 				      separator_pos);
-			add_trailer_item(head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL));
+			last = add_trailer_item(head,
+						strbuf_detach(&tok, NULL),
+						strbuf_detach(&val, NULL));
 		} else {
 			strbuf_addbuf(&val, lines[i]);
 			strbuf_strip_suffix(&val, "\n");
 			add_trailer_item(head,
 					 NULL,
 					 strbuf_detach(&val, NULL));
+			last = NULL;
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 0/8] allow non-trailers and multiple-line trailers

[Jonathan Tan]

I've updated patch 5/8 to use strcspn and to pass in the list of
separators, meaning that we no longer accept '=' in file input (and also
updated its commit message accordingly).

We also discussed inlining find_separator, but after looking at the
code, I think that it is more convenient if find_separator returns -1
when there is no separator, because of the 3 times it is used (as
of 8/8), it is checked twice with '>= 1' (since both "no separator" and
"string begins with separator" are handled in the same way - treating
them as a non-trailer line). So I have left it as its own function.

No other updates.

Jonathan Tan (8):
  trailer: improve const correctness
  trailer: use list.h for doubly-linked list
  trailer: streamline trailer item create and add
  trailer: make args have their own struct
  trailer: clarify failure modes in parse_trailer
  trailer: allow non-trailers in trailer block
  trailer: forbid leading whitespace in trailers
  trailer: support values folded to multiple lines

 Documentation/git-interpret-trailers.txt |  14 +-
 t/t7513-interpret-trailers.sh            | 299 +++++++++++++++
 trailer.c                                | 620 +++++++++++++++++--------------
 3 files changed, 654 insertions(+), 279 deletions(-)

-- 
2.8.0.rc3.226.g39d4020

Re: [PATCH v5 0/8] allow non-trailers and multiple-line trailers

[Junio C Hamano]

On Fri, Oct 21, 2016 at 10:54 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
> I've updated patch 5/8 to use strcspn and to pass in the list of
> separators, meaning that we no longer accept '=' in file input (and also
> updated its commit message accordingly).

Thanks for a pleasant read. Queued.

Hopefully this is ready for 'next' now.

Re: [PATCH v5 0/8] allow non-trailers and multiple-line trailers

[Stefan Beller]

On Fri, Oct 21, 2016 at 4:59 PM, Junio C Hamano <gitster@pobox.com> wrote:
> On Fri, Oct 21, 2016 at 10:54 AM, Jonathan Tan <jonathantanmy@google.com> wrote:
>> I've updated patch 5/8 to use strcspn and to pass in the list of
>> separators, meaning that we no longer accept '=' in file input (and also
>> updated its commit message accordingly).
>
> Thanks for a pleasant read. Queued.
>
> Hopefully this is ready for 'next' now.

I also just read through and was about to say the same.

[PATCH v5 1/8] trailer: improve const correctness

[Jonathan Tan]

Change "const char *" to "char *" in struct trailer_item and in the
return value of apply_command (since those strings are owned strings).

Change "struct conf_info *" to "const struct conf_info *" (since that
struct is not modified).

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/trailer.c b/trailer.c
index c6ea9ac..1f191b2 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,8 +27,8 @@ static struct conf_info default_conf_info;
 struct trailer_item {
 	struct trailer_item *previous;
 	struct trailer_item *next;
-	const char *token;
-	const char *value;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -95,8 +95,8 @@ static void free_trailer_item(struct trailer_item *item)
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
-	free((char *)item->token);
-	free((char *)item->value);
+	free(item->token);
+	free(item->value);
 	free(item);
 }
 
@@ -215,13 +215,13 @@ static struct trailer_item *remove_first(struct trailer_item **first)
 	return item;
 }
 
-static const char *apply_command(const char *command, const char *arg)
+static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
 	struct child_process cp = CHILD_PROCESS_INIT;
 	const char *argv[] = {NULL, NULL};
-	const char *result;
+	char *result;
 
 	strbuf_addstr(&cmd, command);
 	if (arg)
@@ -425,7 +425,7 @@ static int set_if_missing(struct conf_info *item, const char *value)
 	return 0;
 }
 
-static void duplicate_conf(struct conf_info *dst, struct conf_info *src)
+static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 {
 	*dst = *src;
 	if (src->name)
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 2/8] trailer: use list.h for doubly-linked list

[Jonathan Tan]

Replace the existing handwritten implementation of a doubly-linked list
in trailer.c with the functions and macros from list.h. This
significantly simplifies the code.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Ramsay Jones <ramsay@ramsayjones.plus.com>
---
 trailer.c | 258 ++++++++++++++++++++++----------------------------------------
 1 file changed, 91 insertions(+), 167 deletions(-)

diff --git a/trailer.c b/trailer.c
index 1f191b2..4e85aae 100644
--- a/trailer.c
+++ b/trailer.c
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "tempfile.h"
 #include "trailer.h"
+#include "list.h"
 /*
  * Copyright (c) 2013, 2014 Christian Couder <chriscool@tuxfamily.org>
  */
@@ -25,19 +26,24 @@ struct conf_info {
 static struct conf_info default_conf_info;
 
 struct trailer_item {
-	struct trailer_item *previous;
-	struct trailer_item *next;
+	struct list_head list;
 	char *token;
 	char *value;
 	struct conf_info conf;
 };
 
-static struct trailer_item *first_conf_item;
+static LIST_HEAD(conf_head);
 
 static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+/* Iterate over the elements of the list. */
+#define list_for_each_dir(pos, head, is_reverse) \
+	for (pos = is_reverse ? (head)->prev : (head)->next; \
+		pos != (head); \
+		pos = is_reverse ? pos->prev : pos->next)
+
 static int after_or_end(enum action_where where)
 {
 	return (where == WHERE_AFTER) || (where == WHERE_END);
@@ -120,101 +126,49 @@ static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 		fprintf(outfile, "%s%c %s\n", tok, separators[0], val);
 }
 
-static void print_all(FILE *outfile, struct trailer_item *first, int trim_empty)
+static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	for (item = first; item; item = item->next) {
+	list_for_each(pos, head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!trim_empty || strlen(item->value) > 0)
 			print_tok_val(outfile, item->token, item->value);
 	}
 }
 
-static void update_last(struct trailer_item **last)
-{
-	if (*last)
-		while ((*last)->next != NULL)
-			*last = (*last)->next;
-}
-
-static void update_first(struct trailer_item **first)
-{
-	if (*first)
-		while ((*first)->previous != NULL)
-			*first = (*first)->previous;
-}
-
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok,
-				  struct trailer_item **first,
-				  struct trailer_item **last)
-{
-	if (after_or_end(arg_tok->conf.where)) {
-		arg_tok->next = on_tok->next;
-		on_tok->next = arg_tok;
-		arg_tok->previous = on_tok;
-		if (arg_tok->next)
-			arg_tok->next->previous = arg_tok;
-		update_last(last);
-	} else {
-		arg_tok->previous = on_tok->previous;
-		on_tok->previous = arg_tok;
-		arg_tok->next = on_tok;
-		if (arg_tok->previous)
-			arg_tok->previous->next = arg_tok;
-		update_first(first);
-	}
+				  struct trailer_item *arg_tok)
+{
+	if (after_or_end(arg_tok->conf.where))
+		list_add(&arg_tok->list, &on_tok->list);
+	else
+		list_add_tail(&arg_tok->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
 			      struct trailer_item *arg_tok,
-			      int check_all)
+			      int check_all,
+			      struct list_head *head)
 {
 	enum action_where where = arg_tok->conf.where;
+	struct list_head *next_head;
 	do {
-		if (!in_tok)
-			return 1;
 		if (same_trailer(in_tok, arg_tok))
 			return 0;
 		/*
 		 * if we want to add a trailer after another one,
 		 * we have to check those before this one
 		 */
-		in_tok = after_or_end(where) ? in_tok->previous : in_tok->next;
+		next_head = after_or_end(where) ? in_tok->list.prev
+						: in_tok->list.next;
+		if (next_head == head)
+			break;
+		in_tok = list_entry(next_head, struct trailer_item, list);
 	} while (check_all);
 	return 1;
 }
 
-static void remove_from_list(struct trailer_item *item,
-			     struct trailer_item **first,
-			     struct trailer_item **last)
-{
-	struct trailer_item *next = item->next;
-	struct trailer_item *previous = item->previous;
-
-	if (next) {
-		item->next->previous = previous;
-		item->next = NULL;
-	} else if (last)
-		*last = previous;
-
-	if (previous) {
-		item->previous->next = next;
-		item->previous = NULL;
-	} else if (first)
-		*first = next;
-}
-
-static struct trailer_item *remove_first(struct trailer_item **first)
-{
-	struct trailer_item *item = *first;
-	*first = item->next;
-	if (item->next) {
-		item->next->previous = NULL;
-		item->next = NULL;
-	}
-	return item;
-}
-
 static char *apply_command(const char *command, const char *arg)
 {
 	struct strbuf cmd = STRBUF_INIT;
@@ -266,8 +220,7 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 static void apply_arg_if_exists(struct trailer_item *in_tok,
 				struct trailer_item *arg_tok,
 				struct trailer_item *on_tok,
-				struct trailer_item **in_tok_first,
-				struct trailer_item **in_tok_last)
+				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
@@ -275,40 +228,34 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
-		remove_from_list(in_tok, in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
+		list_del(&in_tok->list);
 		free_trailer_item(in_tok);
 		break;
 	case EXISTS_ADD:
 		apply_item_command(in_tok, arg_tok);
-		add_arg_to_input_list(on_tok, arg_tok,
-				      in_tok_first, in_tok_last);
+		add_arg_to_input_list(on_tok, arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(in_tok, arg_tok, 1))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(in_tok, arg_tok, 1, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
-		if (check_if_different(on_tok, arg_tok, 0))
-			add_arg_to_input_list(on_tok, arg_tok,
-					      in_tok_first, in_tok_last);
+		if (check_if_different(on_tok, arg_tok, 0, head))
+			add_arg_to_input_list(on_tok, arg_tok);
 		else
 			free_trailer_item(arg_tok);
 		break;
 	}
 }
 
-static void apply_arg_if_missing(struct trailer_item **in_tok_first,
-				 struct trailer_item **in_tok_last,
+static void apply_arg_if_missing(struct list_head *head,
 				 struct trailer_item *arg_tok)
 {
-	struct trailer_item **in_tok;
 	enum action_where where;
 
 	switch (arg_tok->conf.if_missing) {
@@ -317,68 +264,60 @@ static void apply_arg_if_missing(struct trailer_item **in_tok_first,
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
-		in_tok = after_or_end(where) ? in_tok_last : in_tok_first;
 		apply_item_command(NULL, arg_tok);
-		if (*in_tok) {
-			add_arg_to_input_list(*in_tok, arg_tok,
-					      in_tok_first, in_tok_last);
-		} else {
-			*in_tok_first = arg_tok;
-			*in_tok_last = arg_tok;
-		}
-		break;
+		if (after_or_end(where))
+			list_add_tail(&arg_tok->list, head);
+		else
+			list_add(&arg_tok->list, head);
 	}
 }
 
-static int find_same_and_apply_arg(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
+static int find_same_and_apply_arg(struct list_head *head,
 				   struct trailer_item *arg_tok)
 {
+	struct list_head *pos;
 	struct trailer_item *in_tok;
 	struct trailer_item *on_tok;
-	struct trailer_item *following_tok;
 
 	enum action_where where = arg_tok->conf.where;
 	int middle = (where == WHERE_AFTER) || (where == WHERE_BEFORE);
 	int backwards = after_or_end(where);
-	struct trailer_item *start_tok = backwards ? *in_tok_last : *in_tok_first;
+	struct trailer_item *start_tok;
 
-	for (in_tok = start_tok; in_tok; in_tok = following_tok) {
-		following_tok = backwards ? in_tok->previous : in_tok->next;
+	if (list_empty(head))
+		return 0;
+
+	start_tok = list_entry(backwards ? head->prev : head->next,
+			       struct trailer_item,
+			       list);
+
+	list_for_each_dir(pos, head, backwards) {
+		in_tok = list_entry(pos, struct trailer_item, list);
 		if (!same_token(in_tok, arg_tok))
 			continue;
 		on_tok = middle ? in_tok : start_tok;
-		apply_arg_if_exists(in_tok, arg_tok, on_tok,
-				    in_tok_first, in_tok_last);
+		apply_arg_if_exists(in_tok, arg_tok, on_tok, head);
 		return 1;
 	}
 	return 0;
 }
 
-static void process_trailers_lists(struct trailer_item **in_tok_first,
-				   struct trailer_item **in_tok_last,
-				   struct trailer_item **arg_tok_first)
+static void process_trailers_lists(struct list_head *head,
+				   struct list_head *arg_head)
 {
+	struct list_head *pos, *p;
 	struct trailer_item *arg_tok;
-	struct trailer_item *next_arg;
-
-	if (!*arg_tok_first)
-		return;
 
-	for (arg_tok = *arg_tok_first; arg_tok; arg_tok = next_arg) {
+	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
+		arg_tok = list_entry(pos, struct trailer_item, list);
 
-		next_arg = arg_tok->next;
-		remove_from_list(arg_tok, arg_tok_first, NULL);
+		list_del(pos);
 
-		applied = find_same_and_apply_arg(in_tok_first,
-						  in_tok_last,
-						  arg_tok);
+		applied = find_same_and_apply_arg(head, arg_tok);
 
 		if (!applied)
-			apply_arg_if_missing(in_tok_first,
-					     in_tok_last,
-					     arg_tok);
+			apply_arg_if_missing(head, arg_tok);
 	}
 }
 
@@ -438,13 +377,12 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 
 static struct trailer_item *get_conf_item(const char *name)
 {
+	struct list_head *pos;
 	struct trailer_item *item;
-	struct trailer_item *previous;
 
 	/* Look up item with same name */
-	for (previous = NULL, item = first_conf_item;
-	     item;
-	     previous = item, item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
@@ -454,12 +392,7 @@ static struct trailer_item *get_conf_item(const char *name)
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
-	if (!previous)
-		first_conf_item = item;
-	else {
-		previous->next = item;
-		item->previous = previous;
-	}
+	list_add_tail(&item->list, &conf_head);
 
 	return item;
 }
@@ -633,6 +566,7 @@ static struct trailer_item *create_trailer_item(const char *string)
 	struct strbuf val = STRBUF_INIT;
 	struct trailer_item *item;
 	int tok_len;
+	struct list_head *pos;
 
 	if (parse_trailer(&tok, &val, string))
 		return NULL;
@@ -640,7 +574,8 @@ static struct trailer_item *create_trailer_item(const char *string)
 	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (token_matches_item(tok.buf, item, tok_len))
 			return new_trailer_item(item,
 						strbuf_detach(&tok, NULL),
@@ -652,44 +587,34 @@ static struct trailer_item *create_trailer_item(const char *string)
 				strbuf_detach(&val, NULL));
 }
 
-static void add_trailer_item(struct trailer_item **first,
-			     struct trailer_item **last,
-			     struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, struct trailer_item *new)
 {
 	if (!new)
 		return;
-	if (!*last) {
-		*first = new;
-		*last = new;
-	} else {
-		(*last)->next = new;
-		new->previous = *last;
-		*last = new;
-	}
+	list_add_tail(&new->list, head);
 }
 
-static struct trailer_item *process_command_line_args(struct string_list *trailers)
+static void process_command_line_args(struct list_head *arg_head, 
+				      struct string_list *trailers)
 {
-	struct trailer_item *arg_tok_first = NULL;
-	struct trailer_item *arg_tok_last = NULL;
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
-	for (item = first_conf_item; item; item = item->next) {
+	list_for_each(pos, &conf_head) {
+		item = list_entry(pos, struct trailer_item, list);
 		if (item->conf.command) {
 			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+			add_trailer_item(arg_head, new);
 		}
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(&arg_tok_first, &arg_tok_last, new);
+		add_trailer_item(arg_head, new);
 	}
-
-	return arg_tok_first;
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -805,8 +730,7 @@ static void print_lines(FILE *outfile, struct strbuf **lines, int start, int end
 
 static int process_input_file(FILE *outfile,
 			      struct strbuf **lines,
-			      struct trailer_item **in_tok_first,
-			      struct trailer_item **in_tok_last)
+			      struct list_head *head)
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
@@ -829,18 +753,19 @@ static int process_input_file(FILE *outfile,
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char) {
 			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(in_tok_first, in_tok_last, new);
+			add_trailer_item(head, new);
 		}
 	}
 
 	return trailer_end;
 }
 
-static void free_all(struct trailer_item **first)
+static void free_all(struct list_head *head)
 {
-	while (*first) {
-		struct trailer_item *item = remove_first(first);
-		free_trailer_item(item);
+	struct list_head *pos, *p;
+	list_for_each_safe(pos, p, head) {
+		list_del(pos);
+		free_trailer_item(list_entry(pos, struct trailer_item, list));
 	}
 }
 
@@ -877,9 +802,8 @@ static FILE *create_in_place_tempfile(const char *file)
 
 void process_trailers(const char *file, int in_place, int trim_empty, struct string_list *trailers)
 {
-	struct trailer_item *in_tok_first = NULL;
-	struct trailer_item *in_tok_last = NULL;
-	struct trailer_item *arg_tok_first;
+	LIST_HEAD(head);
+	LIST_HEAD(arg_head);
 	struct strbuf **lines;
 	int trailer_end;
 	FILE *outfile = stdout;
@@ -894,15 +818,15 @@ void process_trailers(const char *file, int in_place, int trim_empty, struct str
 		outfile = create_in_place_tempfile(file);
 
 	/* Print the lines before the trailers */
-	trailer_end = process_input_file(outfile, lines, &in_tok_first, &in_tok_last);
+	trailer_end = process_input_file(outfile, lines, &head);
 
-	arg_tok_first = process_command_line_args(trailers);
+	process_command_line_args(&arg_head, trailers);
 
-	process_trailers_lists(&in_tok_first, &in_tok_last, &arg_tok_first);
+	process_trailers_lists(&head, &arg_head);
 
-	print_all(outfile, in_tok_first, trim_empty);
+	print_all(outfile, &head, trim_empty);
 
-	free_all(&in_tok_first);
+	free_all(&head);
 
 	/* Print the lines after the trailers as is */
 	print_lines(outfile, lines, trailer_end, INT_MAX);
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 3/8] trailer: streamline trailer item create and add

[Jonathan Tan]

Currently, creation and addition (to a list) of trailer items are spread
across multiple functions. Streamline this by only having 2 functions:
one to parse the user-supplied string, and one to add the parsed
information to a list.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 130 +++++++++++++++++++++++++++++---------------------------------
 1 file changed, 60 insertions(+), 70 deletions(-)

diff --git a/trailer.c b/trailer.c
index 4e85aae..ae3972a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -500,10 +500,31 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *trailer)
+static const char *token_from_item(struct trailer_item *item, char *tok)
+{
+	if (item->conf.key)
+		return item->conf.key;
+	if (tok)
+		return tok;
+	return item->conf.name;
+}
+
+static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+{
+	if (!strncasecmp(tok, item->conf.name, tok_len))
+		return 1;
+	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
+}
+
+static int parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer)
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
+	struct trailer_item *item;
+	int tok_len;
+	struct list_head *pos;
+
 	strbuf_addstr(&seps, separators);
 	strbuf_addch(&seps, '=');
 	len = strcspn(trailer, seps.buf);
@@ -523,74 +544,31 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val, const char *tra
 		strbuf_addstr(tok, trailer);
 		strbuf_trim(tok);
 	}
-	return 0;
-}
-
-static const char *token_from_item(struct trailer_item *item, char *tok)
-{
-	if (item->conf.key)
-		return item->conf.key;
-	if (tok)
-		return tok;
-	return item->conf.name;
-}
-
-static struct trailer_item *new_trailer_item(struct trailer_item *conf_item,
-					     char *tok, char *val)
-{
-	struct trailer_item *new = xcalloc(sizeof(*new), 1);
-	new->value = val ? val : xstrdup("");
-
-	if (conf_item) {
-		duplicate_conf(&new->conf, &conf_item->conf);
-		new->token = xstrdup(token_from_item(conf_item, tok));
-		free(tok);
-	} else {
-		duplicate_conf(&new->conf, &default_conf_info);
-		new->token = tok;
-	}
-
-	return new;
-}
-
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
-{
-	if (!strncasecmp(tok, item->conf.name, tok_len))
-		return 1;
-	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
-}
-
-static struct trailer_item *create_trailer_item(const char *string)
-{
-	struct strbuf tok = STRBUF_INIT;
-	struct strbuf val = STRBUF_INIT;
-	struct trailer_item *item;
-	int tok_len;
-	struct list_head *pos;
-
-	if (parse_trailer(&tok, &val, string))
-		return NULL;
-
-	tok_len = token_len_without_separator(tok.buf, tok.len);
 
 	/* Lookup if the token matches something in the config */
+	tok_len = token_len_without_separator(tok->buf, tok->len);
+	*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (token_matches_item(tok.buf, item, tok_len))
-			return new_trailer_item(item,
-						strbuf_detach(&tok, NULL),
-						strbuf_detach(&val, NULL));
+		if (token_matches_item(tok->buf, item, tok_len)) {
+			char *tok_buf = strbuf_detach(tok, NULL);
+			*conf = &item->conf;
+			strbuf_addstr(tok, token_from_item(item, tok_buf));
+			free(tok_buf);
+			break;
+		}
 	}
 
-	return new_trailer_item(NULL,
-				strbuf_detach(&tok, NULL),
-				strbuf_detach(&val, NULL));
+	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, struct trailer_item *new)
+static void add_trailer_item(struct list_head *head, char *tok, char *val,
+			     const struct conf_info *conf)
 {
-	if (!new)
-		return;
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
@@ -599,21 +577,28 @@ static void process_command_line_args(struct list_head *arg_head,
 {
 	struct string_list_item *tr;
 	struct trailer_item *item;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 	struct list_head *pos;
 
 	/* Add a trailer item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct trailer_item, list);
-		if (item->conf.command) {
-			struct trailer_item *new = new_trailer_item(item, NULL, NULL);
-			add_trailer_item(arg_head, new);
-		}
+		if (item->conf.command)
+			add_trailer_item(arg_head,
+					 xstrdup(token_from_item(item, NULL)),
+					 xstrdup(""),
+					 &item->conf);
 	}
 
 	/* Add a trailer item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		struct trailer_item *new = create_trailer_item(tr->string);
-		add_trailer_item(arg_head, new);
+		if (!parse_trailer(&tok, &val, &conf, tr->string))
+			add_trailer_item(arg_head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 }
 
@@ -734,6 +719,9 @@ static int process_input_file(FILE *outfile,
 {
 	int count = 0;
 	int patch_start, trailer_start, trailer_end, i;
+	struct strbuf tok = STRBUF_INIT;
+	struct strbuf val = STRBUF_INIT;
+	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -751,10 +739,12 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char) {
-			struct trailer_item *new = create_trailer_item(lines[i]->buf);
-			add_trailer_item(head, new);
-		}
+		if (lines[i]->buf[0] != comment_line_char &&
+		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+			add_trailer_item(head,
+					 strbuf_detach(&tok, NULL),
+					 strbuf_detach(&val, NULL),
+					 conf);
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 4/8] trailer: make args have their own struct

[Jonathan Tan]

Improve type safety by making arguments (whether from configuration or
from the command line) have their own "struct arg_item" type, separate
from the "struct trailer_item" type used to represent the trailers in
the buffer being manipulated.

This change also prepares "struct trailer_item" to be further
differentiated from "struct arg_item" in future patches.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 135 +++++++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 85 insertions(+), 50 deletions(-)

diff --git a/trailer.c b/trailer.c
index ae3972a..99018f8 100644
--- a/trailer.c
+++ b/trailer.c
@@ -29,6 +29,12 @@ struct trailer_item {
 	struct list_head list;
 	char *token;
 	char *value;
+};
+
+struct arg_item {
+	struct list_head list;
+	char *token;
+	char *value;
 	struct conf_info conf;
 };
 
@@ -62,7 +68,7 @@ static size_t token_len_without_separator(const char *token, size_t len)
 	return len;
 }
 
-static int same_token(struct trailer_item *a, struct trailer_item *b)
+static int same_token(struct trailer_item *a, struct arg_item *b)
 {
 	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
 	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
@@ -71,12 +77,12 @@ static int same_token(struct trailer_item *a, struct trailer_item *b)
 	return !strncasecmp(a->token, b->token, min_len);
 }
 
-static int same_value(struct trailer_item *a, struct trailer_item *b)
+static int same_value(struct trailer_item *a, struct arg_item *b)
 {
 	return !strcasecmp(a->value, b->value);
 }
 
-static int same_trailer(struct trailer_item *a, struct trailer_item *b)
+static int same_trailer(struct trailer_item *a, struct arg_item *b)
 {
 	return same_token(a, b) && same_value(a, b);
 }
@@ -98,6 +104,13 @@ static inline void strbuf_replace(struct strbuf *sb, const char *a, const char *
 
 static void free_trailer_item(struct trailer_item *item)
 {
+	free(item->token);
+	free(item->value);
+	free(item);
+}
+
+static void free_arg_item(struct arg_item *item)
+{
 	free(item->conf.name);
 	free(item->conf.key);
 	free(item->conf.command);
@@ -137,17 +150,29 @@ static void print_all(FILE *outfile, struct list_head *head, int trim_empty)
 	}
 }
 
+static struct trailer_item *trailer_from_arg(struct arg_item *arg_tok)
+{
+	struct trailer_item *new = xcalloc(sizeof(*new), 1);
+	new->token = arg_tok->token;
+	new->value = arg_tok->value;
+	arg_tok->token = arg_tok->value = NULL;
+	free_arg_item(arg_tok);
+	return new;
+}
+
 static void add_arg_to_input_list(struct trailer_item *on_tok,
-				  struct trailer_item *arg_tok)
+				  struct arg_item *arg_tok)
 {
-	if (after_or_end(arg_tok->conf.where))
-		list_add(&arg_tok->list, &on_tok->list);
+	int aoe = after_or_end(arg_tok->conf.where);
+	struct trailer_item *to_add = trailer_from_arg(arg_tok);
+	if (aoe)
+		list_add(&to_add->list, &on_tok->list);
 	else
-		list_add_tail(&arg_tok->list, &on_tok->list);
+		list_add_tail(&to_add->list, &on_tok->list);
 }
 
 static int check_if_different(struct trailer_item *in_tok,
-			      struct trailer_item *arg_tok,
+			      struct arg_item *arg_tok,
 			      int check_all,
 			      struct list_head *head)
 {
@@ -200,7 +225,7 @@ static char *apply_command(const char *command, const char *arg)
 	return result;
 }
 
-static void apply_item_command(struct trailer_item *in_tok, struct trailer_item *arg_tok)
+static void apply_item_command(struct trailer_item *in_tok, struct arg_item *arg_tok)
 {
 	if (arg_tok->conf.command) {
 		const char *arg;
@@ -218,13 +243,13 @@ static void apply_item_command(struct trailer_item *in_tok, struct trailer_item
 }
 
 static void apply_arg_if_exists(struct trailer_item *in_tok,
-				struct trailer_item *arg_tok,
+				struct arg_item *arg_tok,
 				struct trailer_item *on_tok,
 				struct list_head *head)
 {
 	switch (arg_tok->conf.if_exists) {
 	case EXISTS_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case EXISTS_REPLACE:
 		apply_item_command(in_tok, arg_tok);
@@ -241,39 +266,41 @@ static void apply_arg_if_exists(struct trailer_item *in_tok,
 		if (check_if_different(in_tok, arg_tok, 1, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	case EXISTS_ADD_IF_DIFFERENT_NEIGHBOR:
 		apply_item_command(in_tok, arg_tok);
 		if (check_if_different(on_tok, arg_tok, 0, head))
 			add_arg_to_input_list(on_tok, arg_tok);
 		else
-			free_trailer_item(arg_tok);
+			free_arg_item(arg_tok);
 		break;
 	}
 }
 
 static void apply_arg_if_missing(struct list_head *head,
-				 struct trailer_item *arg_tok)
+				 struct arg_item *arg_tok)
 {
 	enum action_where where;
+	struct trailer_item *to_add;
 
 	switch (arg_tok->conf.if_missing) {
 	case MISSING_DO_NOTHING:
-		free_trailer_item(arg_tok);
+		free_arg_item(arg_tok);
 		break;
 	case MISSING_ADD:
 		where = arg_tok->conf.where;
 		apply_item_command(NULL, arg_tok);
+		to_add = trailer_from_arg(arg_tok);
 		if (after_or_end(where))
-			list_add_tail(&arg_tok->list, head);
+			list_add_tail(&to_add->list, head);
 		else
-			list_add(&arg_tok->list, head);
+			list_add(&to_add->list, head);
 	}
 }
 
 static int find_same_and_apply_arg(struct list_head *head,
-				   struct trailer_item *arg_tok)
+				   struct arg_item *arg_tok)
 {
 	struct list_head *pos;
 	struct trailer_item *in_tok;
@@ -306,11 +333,11 @@ static void process_trailers_lists(struct list_head *head,
 				   struct list_head *arg_head)
 {
 	struct list_head *pos, *p;
-	struct trailer_item *arg_tok;
+	struct arg_item *arg_tok;
 
 	list_for_each_safe(pos, p, arg_head) {
 		int applied = 0;
-		arg_tok = list_entry(pos, struct trailer_item, list);
+		arg_tok = list_entry(pos, struct arg_item, list);
 
 		list_del(pos);
 
@@ -375,20 +402,20 @@ static void duplicate_conf(struct conf_info *dst, const struct conf_info *src)
 		dst->command = xstrdup(src->command);
 }
 
-static struct trailer_item *get_conf_item(const char *name)
+static struct arg_item *get_conf_item(const char *name)
 {
 	struct list_head *pos;
-	struct trailer_item *item;
+	struct arg_item *item;
 
 	/* Look up item with same name */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (!strcasecmp(item->conf.name, name))
 			return item;
 	}
 
 	/* Item does not already exists, create it */
-	item = xcalloc(sizeof(struct trailer_item), 1);
+	item = xcalloc(sizeof(*item), 1);
 	duplicate_conf(&item->conf, &default_conf_info);
 	item->conf.name = xstrdup(name);
 
@@ -442,7 +469,7 @@ static int git_trailer_default_config(const char *conf_key, const char *value, v
 static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 {
 	const char *trailer_item, *variable_name;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct conf_info *conf;
 	char *name = NULL;
 	enum trailer_info_type type;
@@ -500,7 +527,7 @@ static int git_trailer_config(const char *conf_key, const char *value, void *cb)
 	return 0;
 }
 
-static const char *token_from_item(struct trailer_item *item, char *tok)
+static const char *token_from_item(struct arg_item *item, char *tok)
 {
 	if (item->conf.key)
 		return item->conf.key;
@@ -509,7 +536,7 @@ static const char *token_from_item(struct trailer_item *item, char *tok)
 	return item->conf.name;
 }
 
-static int token_matches_item(const char *tok, struct trailer_item *item, int tok_len)
+static int token_matches_item(const char *tok, struct arg_item *item, int tok_len)
 {
 	if (!strncasecmp(tok, item->conf.name, tok_len))
 		return 1;
@@ -521,7 +548,7 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 {
 	size_t len;
 	struct strbuf seps = STRBUF_INIT;
-	struct trailer_item *item;
+	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
@@ -547,12 +574,14 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 
 	/* Lookup if the token matches something in the config */
 	tok_len = token_len_without_separator(tok->buf, tok->len);
-	*conf = &default_conf_info;
+	if (conf)
+		*conf = &default_conf_info;
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (token_matches_item(tok->buf, item, tok_len)) {
 			char *tok_buf = strbuf_detach(tok, NULL);
-			*conf = &item->conf;
+			if (conf)
+				*conf = &item->conf;
 			strbuf_addstr(tok, token_from_item(item, tok_buf));
 			free(tok_buf);
 			break;
@@ -562,43 +591,51 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 	return 0;
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val,
-			     const struct conf_info *conf)
+static void add_trailer_item(struct list_head *head, char *tok, char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
-	duplicate_conf(&new->conf, conf);
 	list_add_tail(&new->list, head);
 }
 
+static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
+			 const struct conf_info *conf)
+{
+	struct arg_item *new = xcalloc(sizeof(*new), 1);
+	new->token = tok;
+	new->value = val;
+	duplicate_conf(&new->conf, conf);
+	list_add_tail(&new->list, arg_head);
+}
+
 static void process_command_line_args(struct list_head *arg_head, 
 				      struct string_list *trailers)
 {
 	struct string_list_item *tr;
-	struct trailer_item *item;
+	struct arg_item *item;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
 	const struct conf_info *conf;
 	struct list_head *pos;
 
-	/* Add a trailer item for each configured trailer with a command */
+	/* Add an arg item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
-		item = list_entry(pos, struct trailer_item, list);
+		item = list_entry(pos, struct arg_item, list);
 		if (item->conf.command)
-			add_trailer_item(arg_head,
-					 xstrdup(token_from_item(item, NULL)),
-					 xstrdup(""),
-					 &item->conf);
+			add_arg_item(arg_head,
+				     xstrdup(token_from_item(item, NULL)),
+				     xstrdup(""),
+				     &item->conf);
 	}
 
-	/* Add a trailer item for each trailer on the command line */
+	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
 		if (!parse_trailer(&tok, &val, &conf, tr->string))
-			add_trailer_item(arg_head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+			add_arg_item(arg_head,
+				     strbuf_detach(&tok, NULL),
+				     strbuf_detach(&val, NULL),
+				     conf);
 	}
 }
 
@@ -721,7 +758,6 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
-	const struct conf_info *conf;
 
 	/* Get the line count */
 	while (lines[count])
@@ -740,11 +776,10 @@ static int process_input_file(FILE *outfile,
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
 		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, &conf, lines[i]->buf))
+		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL),
-					 conf);
+					 strbuf_detach(&val, NULL));
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 5/8] trailer: clarify failure modes in parse_trailer

[Jonathan Tan]

The parse_trailer function has a few modes of operation, all depending
on whether the separator is present in its input, and if yes, the
separator's position. Some of these modes are failure modes, and these
failure modes are handled differently depending on whether the trailer
line was sourced from a file or from a command-line argument.

Extract a function to find the separator, allowing the invokers of
parse_trailer to determine how to handle the failure modes instead of
making parse_trailer do it. In this function, also take in the list of
separators, so that we can distinguish between command line arguments
(which allow '=' as separator) and file input (which does not allow '='
as separator).

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 trailer.c | 75 ++++++++++++++++++++++++++++++++++++++++++++-------------------
 1 file changed, 53 insertions(+), 22 deletions(-)

diff --git a/trailer.c b/trailer.c
index 99018f8..aff858b 100644
--- a/trailer.c
+++ b/trailer.c
@@ -543,29 +543,37 @@ static int token_matches_item(const char *tok, struct arg_item *item, int tok_le
 	return item->conf.key ? !strncasecmp(tok, item->conf.key, tok_len) : 0;
 }
 
-static int parse_trailer(struct strbuf *tok, struct strbuf *val,
-			 const struct conf_info **conf, const char *trailer)
+/*
+ * Return the location of the first separator in line, or -1 if there is no
+ * separator.
+ */
+static int find_separator(const char *line, const char *separators)
+{
+	int loc = strcspn(line, separators);
+	if (!line[loc])
+		return -1;
+	return loc;
+}
+
+/*
+ * Obtain the token, value, and conf from the given trailer.
+ *
+ * separator_pos must not be 0, since the token cannot be an empty string.
+ *
+ * If separator_pos is -1, interpret the whole trailer as a token.
+ */
+static void parse_trailer(struct strbuf *tok, struct strbuf *val,
+			 const struct conf_info **conf, const char *trailer,
+			 int separator_pos)
 {
-	size_t len;
-	struct strbuf seps = STRBUF_INIT;
 	struct arg_item *item;
 	int tok_len;
 	struct list_head *pos;
 
-	strbuf_addstr(&seps, separators);
-	strbuf_addch(&seps, '=');
-	len = strcspn(trailer, seps.buf);
-	strbuf_release(&seps);
-	if (len == 0) {
-		int l = strlen(trailer);
-		while (l > 0 && isspace(trailer[l - 1]))
-			l--;
-		return error(_("empty trailer token in trailer '%.*s'"), l, trailer);
-	}
-	if (len < strlen(trailer)) {
-		strbuf_add(tok, trailer, len);
+	if (separator_pos != -1) {
+		strbuf_add(tok, trailer, separator_pos);
 		strbuf_trim(tok);
-		strbuf_addstr(val, trailer + len + 1);
+		strbuf_addstr(val, trailer + separator_pos + 1);
 		strbuf_trim(val);
 	} else {
 		strbuf_addstr(tok, trailer);
@@ -587,8 +595,6 @@ static int parse_trailer(struct strbuf *tok, struct strbuf *val,
 			break;
 		}
 	}
-
-	return 0;
 }
 
 static void add_trailer_item(struct list_head *head, char *tok, char *val)
@@ -619,6 +625,12 @@ static void process_command_line_args(struct list_head *arg_head,
 	const struct conf_info *conf;
 	struct list_head *pos;
 
+	/*
+	 * In command-line arguments, '=' is accepted (in addition to the
+	 * separators that are defined).
+	 */
+	char *cl_separators = xstrfmt("=%s", separators);
+
 	/* Add an arg item for each configured trailer with a command */
 	list_for_each(pos, &conf_head) {
 		item = list_entry(pos, struct arg_item, list);
@@ -631,12 +643,25 @@ static void process_command_line_args(struct list_head *arg_head,
 
 	/* Add an arg item for each trailer on the command line */
 	for_each_string_list_item(tr, trailers) {
-		if (!parse_trailer(&tok, &val, &conf, tr->string))
+		int separator_pos = find_separator(tr->string, cl_separators);
+		if (separator_pos == 0) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addstr(&sb, tr->string);
+			strbuf_trim(&sb);
+			error(_("empty trailer token in trailer '%.*s'"),
+			      (int) sb.len, sb.buf);
+			strbuf_release(&sb);
+		} else {
+			parse_trailer(&tok, &val, &conf, tr->string,
+				      separator_pos);
 			add_arg_item(arg_head,
 				     strbuf_detach(&tok, NULL),
 				     strbuf_detach(&val, NULL),
 				     conf);
+		}
 	}
+
+	free(cl_separators);
 }
 
 static struct strbuf **read_input_file(const char *file)
@@ -775,11 +800,17 @@ static int process_input_file(FILE *outfile,
 
 	/* Parse trailer lines */
 	for (i = trailer_start; i < trailer_end; i++) {
-		if (lines[i]->buf[0] != comment_line_char &&
-		    !parse_trailer(&tok, &val, NULL, lines[i]->buf))
+		int separator_pos;
+		if (lines[i]->buf[0] == comment_line_char)
+			continue;
+		separator_pos = find_separator(lines[i]->buf, separators);
+		if (separator_pos >= 1) {
+			parse_trailer(&tok, &val, NULL, lines[i]->buf,
+				      separator_pos);
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		}
 	}
 
 	return trailer_end;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 6/8] trailer: allow non-trailers in trailer block

[Jonathan Tan]

Currently, interpret-trailers requires all lines of a trailer block to
be trailers (or comments) - if not it would not identify that block as a
trailer block, and thus create its own trailer block, inserting a blank
line.  For example:

  echo -e "\nSigned-off-by: x\nnot trailer" |
  git interpret-trailers --trailer "c: d"

would result in:

  Signed-off-by: x
  not trailer

  c: d

Relax the definition of a trailer block to require that the trailers (i)
are all trailers, or (ii) contain at least one Git-generated trailer and
consists of at least 25% trailers.

  Signed-off-by: x
  not trailer
  c: d

(i) is the existing functionality. (ii) allows arbitrary lines to be
included in trailer blocks, like those in [1], and still allow
interpret-trailers to be used.

[1]
https://kernel.googlesource.com/pub/scm/linux/kernel/git/stable/linux-stable/+/e7d316a02f683864a12389f8808570e37fb90aa3

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |   5 +-
 t/t7513-interpret-trailers.sh            | 115 +++++++++++++++++++++++++++++++
 trailer.c                                |  89 ++++++++++++++++++++----
 3 files changed, 194 insertions(+), 15 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 93d1db6..cf4c5ea 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -48,8 +48,9 @@ with only spaces at the end of the commit message part, one blank line
 will be added before the new trailer.
 
 Existing trailers are extracted from the input message by looking for
-a group of one or more lines that contain a colon (by default), where
-the group is preceded by one or more empty (or whitespace-only) lines.
+a group of one or more lines that (i) are all trailers, or (ii) contains at
+least one Git-generated trailer and consists of at least 25% trailers.
+The group must be preceded by one or more empty (or whitespace-only) lines.
 The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
 minus signs start the patch part of the message.
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index aee785c..003e90f 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -126,6 +126,121 @@ test_expect_success 'with multiline title in the message' '
 	test_cmp expected actual
 '
 
+test_expect_success 'with non-trailer lines mixed with Signed-off-by' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		Signed-off-by: a <a@example.com>
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		Signed-off-by: a <a@example.com>
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with cherry picked from' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		(cherry picked from commit x)
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		(cherry picked from commit x)
+		this is not a trailer
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with a configured trailer' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		My-trailer: x
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		My-trailer: x
+		this is not a trailer
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines mixed with a non-configured trailer' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		I-am-not-configured: x
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+		this is not a trailer
+		I-am-not-configured: x
+		this is not a trailer
+
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with all non-configured trailers' '
+	cat >patch <<-\EOF &&
+
+		I-am-not-configured: x
+		I-am-also-not-configured: x
+	EOF
+	cat >expected <<-\EOF &&
+
+		I-am-not-configured: x
+		I-am-also-not-configured: x
+		token: value
+	EOF
+	test_config trailer.my.key "My-trailer: " &&
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'with non-trailer lines only' '
+	cat >patch <<-\EOF &&
+
+		this is not a trailer
+	EOF
+	cat >expected <<-\EOF &&
+
+		this is not a trailer
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index aff858b..199f86a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -27,6 +27,10 @@ static struct conf_info default_conf_info;
 
 struct trailer_item {
 	struct list_head list;
+	/*
+	 * If this is not a trailer line, the line is stored in value
+	 * (excluding the terminating newline) and token is NULL.
+	 */
 	char *token;
 	char *value;
 };
@@ -44,6 +48,12 @@ static char *separators = ":";
 
 #define TRAILER_ARG_STRING "$ARG"
 
+static const char *git_generated_prefixes[] = {
+	"Signed-off-by: ",
+	"(cherry picked from commit ",
+	NULL
+};
+
 /* Iterate over the elements of the list. */
 #define list_for_each_dir(pos, head, is_reverse) \
 	for (pos = is_reverse ? (head)->prev : (head)->next; \
@@ -70,9 +80,14 @@ static size_t token_len_without_separator(const char *token, size_t len)
 
 static int same_token(struct trailer_item *a, struct arg_item *b)
 {
-	size_t a_len = token_len_without_separator(a->token, strlen(a->token));
-	size_t b_len = token_len_without_separator(b->token, strlen(b->token));
-	size_t min_len = (a_len > b_len) ? b_len : a_len;
+	size_t a_len, b_len, min_len;
+
+	if (!a->token)
+		return 0;
+
+	a_len = token_len_without_separator(a->token, strlen(a->token));
+	b_len = token_len_without_separator(b->token, strlen(b->token));
+	min_len = (a_len > b_len) ? b_len : a_len;
 
 	return !strncasecmp(a->token, b->token, min_len);
 }
@@ -130,7 +145,14 @@ static char last_non_space_char(const char *s)
 
 static void print_tok_val(FILE *outfile, const char *tok, const char *val)
 {
-	char c = last_non_space_char(tok);
+	char c;
+
+	if (!tok) {
+		fprintf(outfile, "%s\n", val);
+		return;
+	}
+
+	c = last_non_space_char(tok);
 	if (!c)
 		return;
 	if (strchr(separators, c))
@@ -709,6 +731,7 @@ static int find_patch_start(struct strbuf **lines, int count)
 static int find_trailer_start(struct strbuf **lines, int count)
 {
 	int start, end_of_title, only_spaces = 1;
+	int recognized_prefix = 0, trailer_lines = 0, non_trailer_lines = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -720,26 +743,60 @@ static int find_trailer_start(struct strbuf **lines, int count)
 	end_of_title = start;
 
 	/*
-	 * Get the start of the trailers by looking starting from the end
-	 * for a line with only spaces before lines with one separator.
+	 * Get the start of the trailers by looking starting from the end for a
+	 * blank line before a set of non-blank lines that (i) are all
+	 * trailers, or (ii) contains at least one Git-generated trailer and
+	 * consists of at least 25% trailers.
 	 */
 	for (start = count - 1; start >= end_of_title; start--) {
+		const char **p;
+		int separator_pos;
+
 		if (lines[start]->buf[0] == comment_line_char)
 			continue;
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
-			return start + 1;
+			if (recognized_prefix &&
+			    trailer_lines * 3 >= non_trailer_lines)
+				return start + 1;
+			if (trailer_lines && !non_trailer_lines)
+				return start + 1;
+			return count;
 		}
-		if (strcspn(lines[start]->buf, separators) < lines[start]->len) {
-			if (only_spaces)
-				only_spaces = 0;
-			continue;
+		only_spaces = 0;
+
+		for (p = git_generated_prefixes; *p; p++) {
+			if (starts_with(lines[start]->buf, *p)) {
+				trailer_lines++;
+				recognized_prefix = 1;
+				goto continue_outer_loop;
+			}
 		}
-		return count;
+
+		separator_pos = find_separator(lines[start]->buf);
+		if (separator_pos >= 1) {
+			struct list_head *pos;
+
+			trailer_lines++;
+			if (recognized_prefix)
+				continue;
+			list_for_each(pos, &conf_head) {
+				struct arg_item *item;
+				item = list_entry(pos, struct arg_item, list);
+				if (token_matches_item(lines[start]->buf, item,
+						       separator_pos)) {
+					recognized_prefix = 1;
+					break;
+				}
+			}
+		} else
+			non_trailer_lines++;
+continue_outer_loop:
+		;
 	}
 
-	return only_spaces ? count : 0;
+	return count;
 }
 
 /* Get the index of the end of the trailers */
@@ -810,6 +867,12 @@ static int process_input_file(FILE *outfile,
 			add_trailer_item(head,
 					 strbuf_detach(&tok, NULL),
 					 strbuf_detach(&val, NULL));
+		} else {
+			strbuf_addbuf(&val, lines[i]);
+			strbuf_strip_suffix(&val, "\n");
+			add_trailer_item(head,
+					 NULL,
+					 strbuf_detach(&val, NULL));
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 7/8] trailer: forbid leading whitespace in trailers

[Jonathan Tan]

Currently, interpret-trailers allows leading whitespace in trailer
lines. This leads to false positives, especially for quoted lines or
bullet lists.

Forbid leading whitespace in trailers.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |  2 +-
 t/t7513-interpret-trailers.sh            | 15 +++++++++++++++
 trailer.c                                |  2 +-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index cf4c5ea..4966b5b 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -55,7 +55,7 @@ The group must either be at the end of the message or be the last
 non-whitespace lines before a line that starts with '---'. Such three
 minus signs start the patch part of the message.
 
-When reading trailers, there can be whitespaces before and after the
+When reading trailers, there can be whitespaces after the
 token, the separator and the value. There can also be whitespaces
 inside the token and the value.
 
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 003e90f..3d94b3a 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -241,6 +241,21 @@ test_expect_success 'with non-trailer lines only' '
 	test_cmp expected actual
 '
 
+test_expect_success 'line with leading whitespace is not trailer' '
+	q_to_tab >patch <<-\EOF &&
+
+		Qtoken: value
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		Qtoken: value
+
+		token: value
+	EOF
+	git interpret-trailers --trailer "token: value" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index 199f86a..d978437 100644
--- a/trailer.c
+++ b/trailer.c
@@ -775,7 +775,7 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		}
 
 		separator_pos = find_separator(lines[start]->buf);
-		if (separator_pos >= 1) {
+		if (separator_pos >= 1 && !isspace(lines[start]->buf[0])) {
 			struct list_head *pos;
 
 			trailer_lines++;
-- 
2.8.0.rc3.226.g39d4020

[PATCH v5 8/8] trailer: support values folded to multiple lines

[Jonathan Tan]

Currently, interpret-trailers requires that a trailer be only on 1 line.
For example:

a: first line
   second line

would be interpreted as one trailer line followed by one non-trailer line.

Make interpret-trailers support RFC 822-style folding, treating those
lines as one logical trailer.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
---
 Documentation/git-interpret-trailers.txt |   7 +-
 t/t7513-interpret-trailers.sh            | 169 +++++++++++++++++++++++++++++++
 trailer.c                                |  45 ++++++--
 3 files changed, 211 insertions(+), 10 deletions(-)

diff --git a/Documentation/git-interpret-trailers.txt b/Documentation/git-interpret-trailers.txt
index 4966b5b..e99bda6 100644
--- a/Documentation/git-interpret-trailers.txt
+++ b/Documentation/git-interpret-trailers.txt
@@ -57,11 +57,12 @@ minus signs start the patch part of the message.
 
 When reading trailers, there can be whitespaces after the
 token, the separator and the value. There can also be whitespaces
-inside the token and the value.
+inside the token and the value. The value may be split over multiple lines with
+each subsequent line starting with whitespace, like the "folding" in RFC 822.
 
 Note that 'trailers' do not follow and are not intended to follow many
-rules for RFC 822 headers. For example they do not follow the line
-folding rules, the encoding rules and probably many other rules.
+rules for RFC 822 headers. For example they do not follow
+the encoding rules and probably many other rules.
 
 OPTIONS
 -------
diff --git a/t/t7513-interpret-trailers.sh b/t/t7513-interpret-trailers.sh
index 3d94b3a..4dd1d7c 100755
--- a/t/t7513-interpret-trailers.sh
+++ b/t/t7513-interpret-trailers.sh
@@ -256,6 +256,175 @@ test_expect_success 'line with leading whitespace is not trailer' '
 	test_cmp expected actual
 '
 
+test_expect_success 'multiline field treated as one trailer for 25% check' '
+	q_to_tab >patch <<-\EOF &&
+
+		Signed-off-by: a <a@example.com>
+		name: value on
+		Qmultiple lines
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		Signed-off-by: a <a@example.com>
+		name: value on
+		Qmultiple lines
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		this is not a trailer
+		name: value
+	EOF
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for placement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		name: value
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for replacement' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: value on
+		Qmultiple lines
+		another: trailer
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		another: trailer
+		name: value
+	EOF
+	test_config trailer.name.ifexists replace &&
+	git interpret-trailers --trailer "name: value" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for difference check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.ifexists addIfDifferent &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line
+		QQQQQsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+		name: first line *DIFFERENT*
+		Qsecond line
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'multiline field treated as atomic for neighbor check' '
+	q_to_tab >patch <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	test_config trailer.name.where after &&
+	test_config trailer.name.ifexists addIfDifferentNeighbor &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		Qsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual &&
+
+	q_to_tab >trailer <<-\EOF &&
+		name: first line
+		QQQQQsecond line
+	EOF
+	q_to_tab >expected <<-\EOF &&
+
+		another: trailer
+		name: first line
+		Qsecond line
+		name: first line
+		QQQQQsecond line
+		another: trailer
+	EOF
+	git interpret-trailers --trailer "$(cat trailer)" patch >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'with config setup' '
 	git config trailer.ack.key "Acked-by: " &&
 	cat >expected <<-\EOF &&
diff --git a/trailer.c b/trailer.c
index d978437..65866d0 100644
--- a/trailer.c
+++ b/trailer.c
@@ -619,12 +619,14 @@ static void parse_trailer(struct strbuf *tok, struct strbuf *val,
 	}
 }
 
-static void add_trailer_item(struct list_head *head, char *tok, char *val)
+static struct trailer_item *add_trailer_item(struct list_head *head, char *tok,
+					     char *val)
 {
 	struct trailer_item *new = xcalloc(sizeof(*new), 1);
 	new->token = tok;
 	new->value = val;
 	list_add_tail(&new->list, head);
+	return new;
 }
 
 static void add_arg_item(struct list_head *arg_head, char *tok, char *val,
@@ -732,6 +734,14 @@ static int find_trailer_start(struct strbuf **lines, int count)
 {
 	int start, end_of_title, only_spaces = 1;
 	int recognized_prefix = 0, trailer_lines = 0, non_trailer_lines = 0;
+	/*
+	 * Number of possible continuation lines encountered. This will be
+	 * reset to 0 if we encounter a trailer (since those lines are to be
+	 * considered continuations of that trailer), and added to
+	 * non_trailer_lines if we encounter a non-trailer (since those lines
+	 * are to be considered non-trailers).
+	 */
+	int possible_continuation_lines = 0;
 
 	/* The first paragraph is the title and cannot be trailers */
 	for (start = 0; start < count; start++) {
@@ -752,11 +762,15 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		const char **p;
 		int separator_pos;
 
-		if (lines[start]->buf[0] == comment_line_char)
+		if (lines[start]->buf[0] == comment_line_char) {
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
 			continue;
+		}
 		if (contains_only_spaces(lines[start]->buf)) {
 			if (only_spaces)
 				continue;
+			non_trailer_lines += possible_continuation_lines;
 			if (recognized_prefix &&
 			    trailer_lines * 3 >= non_trailer_lines)
 				return start + 1;
@@ -769,16 +783,18 @@ static int find_trailer_start(struct strbuf **lines, int count)
 		for (p = git_generated_prefixes; *p; p++) {
 			if (starts_with(lines[start]->buf, *p)) {
 				trailer_lines++;
+				possible_continuation_lines = 0;
 				recognized_prefix = 1;
 				goto continue_outer_loop;
 			}
 		}
 
-		separator_pos = find_separator(lines[start]->buf);
+		separator_pos = find_separator(lines[start]->buf, separators);
 		if (separator_pos >= 1 && !isspace(lines[start]->buf[0])) {
 			struct list_head *pos;
 
 			trailer_lines++;
+			possible_continuation_lines = 0;
 			if (recognized_prefix)
 				continue;
 			list_for_each(pos, &conf_head) {
@@ -790,8 +806,13 @@ static int find_trailer_start(struct strbuf **lines, int count)
 					break;
 				}
 			}
-		} else
+		} else if (isspace(lines[start]->buf[0]))
+			possible_continuation_lines++;
+		else {
 			non_trailer_lines++;
+			non_trailer_lines += possible_continuation_lines;
+			possible_continuation_lines = 0;
+		}
 continue_outer_loop:
 		;
 	}
@@ -840,6 +861,7 @@ static int process_input_file(FILE *outfile,
 	int patch_start, trailer_start, trailer_end, i;
 	struct strbuf tok = STRBUF_INIT;
 	struct strbuf val = STRBUF_INIT;
+	struct trailer_item *last = NULL;
 
 	/* Get the line count */
 	while (lines[count])
@@ -860,19 +882,28 @@ static int process_input_file(FILE *outfile,
 		int separator_pos;
 		if (lines[i]->buf[0] == comment_line_char)
 			continue;
+		if (last && isspace(lines[i]->buf[0])) {
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addf(&sb, "%s\n%s", last->value, lines[i]->buf);
+			strbuf_strip_suffix(&sb, "\n");
+			free(last->value);
+			last->value = strbuf_detach(&sb, NULL);
+			continue;
+		}
 		separator_pos = find_separator(lines[i]->buf, separators);
 		if (separator_pos >= 1) {
 			parse_trailer(&tok, &val, NULL, lines[i]->buf,
 				      separator_pos);
-			add_trailer_item(head,
-					 strbuf_detach(&tok, NULL),
-					 strbuf_detach(&val, NULL));
+			last = add_trailer_item(head,
+						strbuf_detach(&tok, NULL),
+						strbuf_detach(&val, NULL));
 		} else {
 			strbuf_addbuf(&val, lines[i]);
 			strbuf_strip_suffix(&val, "\n");
 			add_trailer_item(head,
 					 NULL,
 					 strbuf_detach(&val, NULL));
+			last = NULL;
 		}
 	}
 
-- 
2.8.0.rc3.226.g39d4020