[3/5,GSOC] ref-filter: reuse final buffer

Commit Message

ZheNing Hu Aug. 17, 2021, 7:14 a.m. UTC

From: ZheNing Hu <[e-mail]>

In format_ref_array_item(), we add the object data
to ref_formatting_state, and copy the data from
ref_formatting_state to final_buf at the end. There
are huge copies of data.

Because final_buf will be cleared before every time
we call format_ref_array_item(). So we actually add
content to an empty strbuf. We can add the object's
data directly to this final_buffer instead of adding
objects' data to state.stack->output first, then
copy to final_buf.

Add a can_reuse_final_buffer flag to struct ref_format
and create can_reuse_final_buffer() to check if we are
use %(align), %(end), %(if), %(then), %(else). If not,
we can reuse the buf of finnal_buf.

Reuse the buffer address of final_buf in
format_ref_array_item(), we directly add the data to the
final buffer, return the content to final_buf at the end.

This will bring performance improvements.

Mentored-by: Christian Couder <[e-mail]>
Mentored-by: Hariom Verma <[e-mail]>
Signed-off-by: ZheNing Hu <[e-mail]>
---
 ref-filter.c | 39 ++++++++++++++++++++++++++++++++++-----
 ref-filter.h |  3 ++-
 2 files changed, 36 insertions(+), 6 deletions(-)

Patch

diff --git a/ref-filter.c b/ref-filter.c
index 76a31fb79b1..7106d4c1c4c 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -1023,6 +1023,19 @@  static int need_parse_buffer(enum atom_type atom_type) {
 	}
 }
 
+static int can_reuse_final_buffer(enum atom_type atom_type) {
+	switch (atom_type) {
+	case ATOM_ALIGN:
+	case ATOM_END:
+	case ATOM_IF:
+	case ATOM_THEN:
+	case ATOM_ELSE:
+		return 0;
+	default:
+		return 1;
+	}
+}
+
 /*
  * Make sure the format string is well formed, and parse out
  * the used atoms.
@@ -1054,6 +1067,7 @@  int verify_ref_format(struct ref_format *format)
 			format->can_skip_parse_buffer = 0;
 		if (reject_atom(used_atom[at].atom_type))
 			die(_("this command reject atom %%(%.*s)"), (int)(ep - sp - 2), sp + 2);
+		format->can_reuse_final_buffer = can_reuse_final_buffer(used_atom[at].atom_type);
 
 		if ((format->quote_style == QUOTE_PYTHON ||
 		     format->quote_style == QUOTE_SHELL ||
@@ -2627,7 +2641,14 @@  int format_ref_array_item(struct ref_array_item *info,
 	struct ref_formatting_state state = REF_FORMATTING_STATE_INIT;
 
 	state.quote_style = format->quote_style;
-	push_stack_element(&state.stack);
+	if (format->can_reuse_final_buffer) {
+		struct ref_formatting_stack *s = xmalloc(sizeof(struct ref_formatting_stack));
+		s->output = *final_buf;
+		s->prev = state.stack;
+		state.stack = s;
+	} else {
+		push_stack_element(&state.stack);
+	}
 	info->can_skip_parse_buffer = format->can_skip_parse_buffer;
 
 	cp = format->format;
@@ -2641,7 +2662,8 @@  int format_ref_array_item(struct ref_array_item *info,
 			append_literal(cp, e->beg - 2, &state);
 		if (get_ref_atom_value(info, e->at, &atomv, error_buf) ||
 		    atomv->handler(atomv, &state, error_buf)) {
-			pop_stack_element(&state.stack);
+			if (!format->can_reuse_final_buffer)
+				pop_stack_element(&state.stack);
 			return -1;
 		}
 		cp = e->end + 1;
@@ -2656,16 +2678,23 @@  int format_ref_array_item(struct ref_array_item *info,
 		struct atom_value resetv = ATOM_VALUE_INIT;
 		resetv.s = GIT_COLOR_RESET;
 		if (append_atom(&resetv, &state, error_buf)) {
-			pop_stack_element(&state.stack);
+			if (!format->can_reuse_final_buffer)
+				pop_stack_element(&state.stack);
 			return -1;
 		}
 	}
 	if (state.stack->prev) {
+		assert(!format->can_reuse_final_buffer);
 		pop_stack_element(&state.stack);
 		return strbuf_addf_ret(error_buf, -1, _("format: %%(end) atom missing"));
 	}
-	strbuf_addbuf(final_buf, &state.stack->output);
-	pop_stack_element(&state.stack);
+	if(format->can_reuse_final_buffer) {
+		*final_buf = state.stack->output;
+		free(state.stack);
+	} else {
+		strbuf_addbuf(final_buf, &state.stack->output);
+		pop_stack_element(&state.stack);
+	}
 	return 0;
 }
 
diff --git a/ref-filter.h b/ref-filter.h
index df54836a643..a62a14a2e43 100644
--- a/ref-filter.h
+++ b/ref-filter.h
@@ -92,10 +92,11 @@  struct ref_format {
 	int can_skip_parse_buffer;
 	/* Internal state to ref-filter */
 	int need_color_reset_at_eol;
+	int can_reuse_final_buffer;
 	struct list_head parsed_atom_head;
 };
 
-#define REF_FORMAT_INIT { .use_color = -1, .can_skip_parse_buffer = 1 }
+#define REF_FORMAT_INIT { .use_color = -1, .can_skip_parse_buffer = 1, .can_reuse_final_buffer = 1 }
 
 /*  Macros for checking --merged and --no-merged options */
 #define _OPT_MERGED_NO_MERGED(option, filter, h) \