[thirdparty/git.git] / range-diff.c

#include "cache.h"
#include "range-diff.h"
#include "string-list.h"
#include "run-command.h"
#include "strvec.h"
#include "hashmap.h"
#include "xdiff-interface.h"
#include "linear-assignment.h"
#include "diffcore.h"
#include "commit.h"
#include "pretty.h"
#include "userdiff.h"
#include "apply.h"

struct patch_util {
	/* For the search for an exact match */
	struct hashmap_entry e;
	const char *diff, *patch;

	int i, shown;
	int diffsize;
	size_t diff_offset;
	/* the index of the matching item in the other branch, or -1 */
	int matching;
	struct object_id oid;
};

static size_t find_end_of_line(char *buffer, unsigned long size)
{
	char *eol = memchr(buffer, '\n', size);

	if (!eol)
		return size;

	*eol = '\0';
	return eol + 1 - buffer;
}

/*
 * Reads the patches into a string list, with the `util` field being populated
 * as struct object_id (will need to be free()d).
 */
static int read_patches(const char *range, struct string_list *list,
			const struct strvec *other_arg)
{
	struct child_process cp = CHILD_PROCESS_INIT;
	struct strbuf buf = STRBUF_INIT, contents = STRBUF_INIT;
	struct patch_util *util = NULL;
	int in_header = 1;
	char *line, *current_filename = NULL;
	int offset, len;
	size_t size;

	strvec_pushl(&cp.args, "log", "--no-color", "-p", "--no-merges",
		     "--reverse", "--date-order", "--decorate=no",
		     "--no-prefix",
		     /*
		      * Choose indicators that are not used anywhere
		      * else in diffs, but still look reasonable
		      * (e.g. will not be confusing when debugging)
		      */
		     "--output-indicator-new=>",
		     "--output-indicator-old=<",
		     "--output-indicator-context=#",
		     "--no-abbrev-commit",
		     "--pretty=medium",
		     "--notes",
		     NULL);
	if (other_arg)
		strvec_pushv(&cp.args, other_arg->v);
	strvec_push(&cp.args, range);
	cp.out = -1;
	cp.no_stdin = 1;
	cp.git_cmd = 1;

	if (start_command(&cp))
		return error_errno(_("could not start `log`"));
	if (strbuf_read(&contents, cp.out, 0) < 0) {
		error_errno(_("could not read `log` output"));
		finish_command(&cp);
		return -1;
	}

	line = contents.buf;
	size = contents.len;
	for (offset = 0; size > 0; offset += len, size -= len, line += len) {
		const char *p;

		len = find_end_of_line(line, size);
		line[len - 1] = '\0';
		if (skip_prefix(line, "commit ", &p)) {
			if (util) {
				string_list_append(list, buf.buf)->util = util;
				strbuf_reset(&buf);
			}
			util = xcalloc(sizeof(*util), 1);
			if (get_oid(p, &util->oid)) {
				error(_("could not parse commit '%s'"), p);
				free(util);
				free(current_filename);
				string_list_clear(list, 1);
				strbuf_release(&buf);
				strbuf_release(&contents);
				finish_command(&cp);
				return -1;
			}
			util->matching = -1;
			in_header = 1;
			continue;
		}

		if (!util) {
			error(_("could not parse first line of `log` output: "
				"did not start with 'commit ': '%s'"),
			      line);
			free(current_filename);
			string_list_clear(list, 1);
			strbuf_release(&buf);
			strbuf_release(&contents);
			finish_command(&cp);
			return -1;
		}

		if (starts_with(line, "diff --git")) {
			struct patch patch = { 0 };
			struct strbuf root = STRBUF_INIT;
			int linenr = 0;
			int orig_len;

			in_header = 0;
			strbuf_addch(&buf, '\n');
			if (!util->diff_offset)
				util->diff_offset = buf.len;
			line[len - 1] = '\n';
			orig_len = len;
			len = parse_git_diff_header(&root, &linenr, 0, line,
						    len, size, &patch);
			if (len < 0)
				die(_("could not parse git header '%.*s'"),
				    orig_len, line);
			strbuf_addstr(&buf, " ## ");
			if (patch.is_new > 0)
				strbuf_addf(&buf, "%s (new)", patch.new_name);
			else if (patch.is_delete > 0)
				strbuf_addf(&buf, "%s (deleted)", patch.old_name);
			else if (patch.is_rename)
				strbuf_addf(&buf, "%s => %s", patch.old_name, patch.new_name);
			else
				strbuf_addstr(&buf, patch.new_name);

			free(current_filename);
			if (patch.is_delete > 0)
				current_filename = xstrdup(patch.old_name);
			else
				current_filename = xstrdup(patch.new_name);

			if (patch.new_mode && patch.old_mode &&
			    patch.old_mode != patch.new_mode)
				strbuf_addf(&buf, " (mode change %06o => %06o)",
					    patch.old_mode, patch.new_mode);

			strbuf_addstr(&buf, " ##");
		} else if (in_header) {
			if (starts_with(line, "Author: ")) {
				strbuf_addstr(&buf, " ## Metadata ##\n");
				strbuf_addstr(&buf, line);
				strbuf_addstr(&buf, "\n\n");
				strbuf_addstr(&buf, " ## Commit message ##\n");
			} else if (starts_with(line, "Notes") &&
				   line[strlen(line) - 1] == ':') {
				strbuf_addstr(&buf, "\n\n");
				/* strip the trailing colon */
				strbuf_addf(&buf, " ## %.*s ##\n",
					    (int)(strlen(line) - 1), line);
			} else if (starts_with(line, "    ")) {
				p = line + len - 2;
				while (isspace(*p) && p >= line)
					p--;
				strbuf_add(&buf, line, p - line + 1);
				strbuf_addch(&buf, '\n');
			}
			continue;
		} else if (skip_prefix(line, "@@ ", &p)) {
			p = strstr(p, "@@");
			strbuf_addstr(&buf, "@@");
			if (current_filename && p[2])
				strbuf_addf(&buf, " %s:", current_filename);
			if (p)
				strbuf_addstr(&buf, p + 2);
		} else if (!line[0])
			/*
			 * A completely blank (not ' \n', which is context)
			 * line is not valid in a diff.  We skip it
			 * silently, because this neatly handles the blank
			 * separator line between commits in git-log
			 * output.
			 */
			continue;
		else if (line[0] == '>') {
			strbuf_addch(&buf, '+');
			strbuf_addstr(&buf, line + 1);
		} else if (line[0] == '<') {
			strbuf_addch(&buf, '-');
			strbuf_addstr(&buf, line + 1);
		} else if (line[0] == '#') {
			strbuf_addch(&buf, ' ');
			strbuf_addstr(&buf, line + 1);
		} else {
			strbuf_addch(&buf, ' ');
			strbuf_addstr(&buf, line);
		}

		strbuf_addch(&buf, '\n');
		util->diffsize++;
	}
	strbuf_release(&contents);

	if (util)
		string_list_append(list, buf.buf)->util = util;
	strbuf_release(&buf);
	free(current_filename);

	if (finish_command(&cp))
		return -1;

	return 0;
}

static int patch_util_cmp(const void *dummy, const struct patch_util *a,
			  const struct patch_util *b, const char *keydata)
{
	return strcmp(a->diff, keydata ? keydata : b->diff);
}

static void find_exact_matches(struct string_list *a, struct string_list *b)
{
	struct hashmap map = HASHMAP_INIT((hashmap_cmp_fn)patch_util_cmp, NULL);
	int i;

	/* First, add the patches of a to a hash map */
	for (i = 0; i < a->nr; i++) {
		struct patch_util *util = a->items[i].util;

		util->i = i;
		util->patch = a->items[i].string;
		util->diff = util->patch + util->diff_offset;
		hashmap_entry_init(&util->e, strhash(util->diff));
		hashmap_add(&map, &util->e);
	}

	/* Now try to find exact matches in b */
	for (i = 0; i < b->nr; i++) {
		struct patch_util *util = b->items[i].util, *other;

		util->i = i;
		util->patch = b->items[i].string;
		util->diff = util->patch + util->diff_offset;
		hashmap_entry_init(&util->e, strhash(util->diff));
		other = hashmap_remove_entry(&map, util, e, NULL);
		if (other) {
			if (other->matching >= 0)
				BUG("already assigned!");

			other->matching = i;
			util->matching = other->i;
		}
	}

	hashmap_clear(&map);
}

static void diffsize_consume(void *data, char *line, unsigned long len)
{
	(*(int *)data)++;
}

static void diffsize_hunk(void *data, long ob, long on, long nb, long nn,
			  const char *funcline, long funclen)
{
	diffsize_consume(data, NULL, 0);
}

static int diffsize(const char *a, const char *b)
{
	xpparam_t pp = { 0 };
	xdemitconf_t cfg = { 0 };
	mmfile_t mf1, mf2;
	int count = 0;

	mf1.ptr = (char *)a;
	mf1.size = strlen(a);
	mf2.ptr = (char *)b;
	mf2.size = strlen(b);

	cfg.ctxlen = 3;
	if (!xdi_diff_outf(&mf1, &mf2,
			   diffsize_hunk, diffsize_consume, &count,
			   &pp, &cfg))
		return count;

	error(_("failed to generate diff"));
	return COST_MAX;
}

static void get_correspondences(struct string_list *a, struct string_list *b,
				int creation_factor)
{
	int n = a->nr + b->nr;
	int *cost, c, *a2b, *b2a;
	int i, j;

	ALLOC_ARRAY(cost, st_mult(n, n));
	ALLOC_ARRAY(a2b, n);
	ALLOC_ARRAY(b2a, n);

	for (i = 0; i < a->nr; i++) {
		struct patch_util *a_util = a->items[i].util;

		for (j = 0; j < b->nr; j++) {
			struct patch_util *b_util = b->items[j].util;

			if (a_util->matching == j)
				c = 0;
			else if (a_util->matching < 0 && b_util->matching < 0)
				c = diffsize(a_util->diff, b_util->diff);
			else
				c = COST_MAX;
			cost[i + n * j] = c;
		}

		c = a_util->matching < 0 ?
			a_util->diffsize * creation_factor / 100 : COST_MAX;
		for (j = b->nr; j < n; j++)
			cost[i + n * j] = c;
	}

	for (j = 0; j < b->nr; j++) {
		struct patch_util *util = b->items[j].util;

		c = util->matching < 0 ?
			util->diffsize * creation_factor / 100 : COST_MAX;
		for (i = a->nr; i < n; i++)
			cost[i + n * j] = c;
	}

	for (i = a->nr; i < n; i++)
		for (j = b->nr; j < n; j++)
			cost[i + n * j] = 0;

	compute_assignment(n, n, cost, a2b, b2a);

	for (i = 0; i < a->nr; i++)
		if (a2b[i] >= 0 && a2b[i] < b->nr) {
			struct patch_util *a_util = a->items[i].util;
			struct patch_util *b_util = b->items[a2b[i]].util;

			a_util->matching = a2b[i];
			b_util->matching = i;
		}

	free(cost);
	free(a2b);
	free(b2a);
}

static void output_pair_header(struct diff_options *diffopt,
			       int patch_no_width,
			       struct strbuf *buf,
			       struct strbuf *dashes,
			       struct patch_util *a_util,
			       struct patch_util *b_util)
{
	struct object_id *oid = a_util ? &a_util->oid : &b_util->oid;
	struct commit *commit;
	char status;
	const char *color_reset = diff_get_color_opt(diffopt, DIFF_RESET);
	const char *color_old = diff_get_color_opt(diffopt, DIFF_FILE_OLD);
	const char *color_new = diff_get_color_opt(diffopt, DIFF_FILE_NEW);
	const char *color_commit = diff_get_color_opt(diffopt, DIFF_COMMIT);
	const char *color;

	if (!dashes->len)
		strbuf_addchars(dashes, '-',
				strlen(find_unique_abbrev(oid,
							  DEFAULT_ABBREV)));

	if (!b_util) {
		color = color_old;
		status = '<';
	} else if (!a_util) {
		color = color_new;
		status = '>';
	} else if (strcmp(a_util->patch, b_util->patch)) {
		color = color_commit;
		status = '!';
	} else {
		color = color_commit;
		status = '=';
	}

	strbuf_reset(buf);
	strbuf_addstr(buf, status == '!' ? color_old : color);
	if (!a_util)
		strbuf_addf(buf, "%*s:  %s ", patch_no_width, "-", dashes->buf);
	else
		strbuf_addf(buf, "%*d:  %s ", patch_no_width, a_util->i + 1,
			    find_unique_abbrev(&a_util->oid, DEFAULT_ABBREV));

	if (status == '!')
		strbuf_addf(buf, "%s%s", color_reset, color);
	strbuf_addch(buf, status);
	if (status == '!')
		strbuf_addf(buf, "%s%s", color_reset, color_new);

	if (!b_util)
		strbuf_addf(buf, " %*s:  %s", patch_no_width, "-", dashes->buf);
	else
		strbuf_addf(buf, " %*d:  %s", patch_no_width, b_util->i + 1,
			    find_unique_abbrev(&b_util->oid, DEFAULT_ABBREV));

	commit = lookup_commit_reference(the_repository, oid);
	if (commit) {
		if (status == '!')
			strbuf_addf(buf, "%s%s", color_reset, color);

		strbuf_addch(buf, ' ');
		pp_commit_easy(CMIT_FMT_ONELINE, commit, buf);
	}
	strbuf_addf(buf, "%s\n", color_reset);

	fwrite(buf->buf, buf->len, 1, diffopt->file);
}

static struct userdiff_driver section_headers = {
	.funcname = { "^ ## (.*) ##$\n"
		      "^.?@@ (.*)$", REG_EXTENDED }
};

static struct diff_filespec *get_filespec(const char *name, const char *p)
{
	struct diff_filespec *spec = alloc_filespec(name);

	fill_filespec(spec, &null_oid, 0, 0100644);
	spec->data = (char *)p;
	spec->size = strlen(p);
	spec->should_munmap = 0;
	spec->is_stdin = 1;
	spec->driver = &section_headers;

	return spec;
}

static void patch_diff(const char *a, const char *b,
		       struct diff_options *diffopt)
{
	diff_queue(&diff_queued_diff,
		   get_filespec("a", a), get_filespec("b", b));

	diffcore_std(diffopt);
	diff_flush(diffopt);
}

static void output(struct string_list *a, struct string_list *b,
		   struct diff_options *diffopt)
{
	struct strbuf buf = STRBUF_INIT, dashes = STRBUF_INIT;
	int patch_no_width = decimal_width(1 + (a->nr > b->nr ? a->nr : b->nr));
	int i = 0, j = 0;

	/*
	 * We assume the user is really more interested in the second argument
	 * ("newer" version). To that end, we print the output in the order of
	 * the RHS (the `b` parameter). To put the LHS (the `a` parameter)
	 * commits that are no longer in the RHS into a good place, we place
	 * them once we have shown all of their predecessors in the LHS.
	 */

	while (i < a->nr || j < b->nr) {
		struct patch_util *a_util, *b_util;
		a_util = i < a->nr ? a->items[i].util : NULL;
		b_util = j < b->nr ? b->items[j].util : NULL;

		/* Skip all the already-shown commits from the LHS. */
		while (i < a->nr && a_util->shown)
			a_util = ++i < a->nr ? a->items[i].util : NULL;

		/* Show unmatched LHS commit whose predecessors were shown. */
		if (i < a->nr && a_util->matching < 0) {
			output_pair_header(diffopt, patch_no_width,
					   &buf, &dashes, a_util, NULL);
			i++;
			continue;
		}

		/* Show unmatched RHS commits. */
		while (j < b->nr && b_util->matching < 0) {
			output_pair_header(diffopt, patch_no_width,
					   &buf, &dashes, NULL, b_util);
			b_util = ++j < b->nr ? b->items[j].util : NULL;
		}

		/* Show matching LHS/RHS pair. */
		if (j < b->nr) {
			a_util = a->items[b_util->matching].util;
			output_pair_header(diffopt, patch_no_width,
					   &buf, &dashes, a_util, b_util);
			if (!(diffopt->output_format & DIFF_FORMAT_NO_OUTPUT))
				patch_diff(a->items[b_util->matching].string,
					   b->items[j].string, diffopt);
			a_util->shown = 1;
			j++;
		}
	}
	strbuf_release(&buf);
	strbuf_release(&dashes);
}

static struct strbuf *output_prefix_cb(struct diff_options *opt, void *data)
{
	return data;
}

int show_range_diff(const char *range1, const char *range2,
		    int creation_factor, int dual_color,
		    const struct diff_options *diffopt,
		    const struct strvec *other_arg)
{
	int res = 0;

	struct string_list branch1 = STRING_LIST_INIT_DUP;
	struct string_list branch2 = STRING_LIST_INIT_DUP;

	if (read_patches(range1, &branch1, other_arg))
		res = error(_("could not parse log for '%s'"), range1);
	if (!res && read_patches(range2, &branch2, other_arg))
		res = error(_("could not parse log for '%s'"), range2);

	if (!res) {
		struct diff_options opts;
		struct strbuf indent = STRBUF_INIT;

		if (diffopt)
			memcpy(&opts, diffopt, sizeof(opts));
		else
			diff_setup(&opts);

		if (!opts.output_format)
			opts.output_format = DIFF_FORMAT_PATCH;
		opts.flags.suppress_diff_headers = 1;
		opts.flags.dual_color_diffed_diffs = dual_color;
		opts.flags.suppress_hunk_header_line_count = 1;
		opts.output_prefix = output_prefix_cb;
		strbuf_addstr(&indent, "    ");
		opts.output_prefix_data = &indent;
		diff_setup_done(&opts);

		find_exact_matches(&branch1, &branch2);
		get_correspondences(&branch1, &branch2, creation_factor);
		output(&branch1, &branch2, &opts);

		strbuf_release(&indent);
	}

	string_list_clear(&branch1, 1);
	string_list_clear(&branch2, 1);

	return res;
}
Commit	Line	Data
d9c66f0b JS	1	#include "cache.h"
	2	#include "range-diff.h"
	3	#include "string-list.h"
	4	#include "run-command.h"
dbbcd44f	5	#include "strvec.h"
d9c66f0b JS	6	#include "hashmap.h"
	7	#include "xdiff-interface.h"
	8	#include "linear-assignment.h"
c8c5e43a	9	#include "diffcore.h"
eb0be38c JS	10	#include "commit.h"
eb0be38c JS	11	#include "pretty.h"
4eba1fe6	12	#include "userdiff.h"
b66885a3	13	#include "apply.h"
d9c66f0b JS	14
	15	struct patch_util {
	16	/* For the search for an exact match */
	17	struct hashmap_entry e;
	18	const char diff, patch;
	19
9dc46e02	20	int i, shown;
d9c66f0b JS	21	int diffsize;
	22	size_t diff_offset;
	23	/* the index of the matching item in the other branch, or -1 */
	24	int matching;
	25	struct object_id oid;
	26	};
	27
44b67cb6 TG	28	static size_t find_end_of_line(char *buffer, unsigned long size)
	29	{
	30	char *eol = memchr(buffer, '\n', size);
	31
	32	if (!eol)
	33	return size;
	34
	35	*eol = '\0';
	36	return eol + 1 - buffer;
	37	}
	38
d9c66f0b JS	39	/*
	40	* Reads the patches into a string list, with the `util` field being populated
	41	* as struct object_id (will need to be free()d).
	42	*/
bd361918	43	static int read_patches(const char range, struct string_list list,
c972bf4c	44	const struct strvec *other_arg)
d9c66f0b JS	45	{
d9c66f0b JS	46	struct child_process cp = CHILD_PROCESS_INIT;
44b67cb6	47	struct strbuf buf = STRBUF_INIT, contents = STRBUF_INIT;
d9c66f0b JS	48	struct patch_util *util = NULL;
d9c66f0b JS	49	int in_header = 1;
444e0969	50	char line, current_filename = NULL;
44b67cb6 TG	51	int offset, len;
44b67cb6 TG	52	size_t size;
d9c66f0b	53
c972bf4c	54	strvec_pushl(&cp.args, "log", "--no-color", "-p", "--no-merges",
f6d8942b JK	55	"--reverse", "--date-order", "--decorate=no",
	56	"--no-prefix",
	57	/*
	58	* Choose indicators that are not used anywhere
	59	* else in diffs, but still look reasonable
	60	* (e.g. will not be confusing when debugging)
	61	*/
	62	"--output-indicator-new=>",
	63	"--output-indicator-old=<",
	64	"--output-indicator-context=#",
	65	"--no-abbrev-commit",
	66	"--pretty=medium",
	67	"--notes",
	68	NULL);
bd361918	69	if (other_arg)
d70a9eb6	70	strvec_pushv(&cp.args, other_arg->v);
c972bf4c	71	strvec_push(&cp.args, range);
d9c66f0b JS	72	cp.out = -1;
	73	cp.no_stdin = 1;
	74	cp.git_cmd = 1;
	75
	76	if (start_command(&cp))
	77	return error_errno(_("could not start `log`"));
44b67cb6	78	if (strbuf_read(&contents, cp.out, 0) < 0) {
d9c66f0b JS	79	error_errno(_("could not read `log` output"));
	80	finish_command(&cp);
	81	return -1;
	82	}
	83
44b67cb6 TG	84	line = contents.buf;
	85	size = contents.len;
	86	for (offset = 0; size > 0; offset += len, size -= len, line += len) {
d9c66f0b JS	87	const char *p;
d9c66f0b JS	88
44b67cb6 TG	89	len = find_end_of_line(line, size);
	90	line[len - 1] = '\0';
	91	if (skip_prefix(line, "commit ", &p)) {
d9c66f0b JS	92	if (util) {
	93	string_list_append(list, buf.buf)->util = util;
	94	strbuf_reset(&buf);
	95	}
	96	util = xcalloc(sizeof(*util), 1);
	97	if (get_oid(p, &util->oid)) {
	98	error(_("could not parse commit '%s'"), p);
	99	free(util);
8c29b497	100	free(current_filename);
d9c66f0b JS	101	string_list_clear(list, 1);
d9c66f0b JS	102	strbuf_release(&buf);
44b67cb6	103	strbuf_release(&contents);
d9c66f0b JS	104	finish_command(&cp);
	105	return -1;
	106	}
	107	util->matching = -1;
	108	in_header = 1;
	109	continue;
	110	}
	111
8cf51561 VD	112	if (!util) {
	113	error(_("could not parse first line of `log` output: "
	114	"did not start with 'commit ': '%s'"),
	115	line);
8c29b497	116	free(current_filename);
8cf51561 VD	117	string_list_clear(list, 1);
	118	strbuf_release(&buf);
	119	strbuf_release(&contents);
	120	finish_command(&cp);
	121	return -1;
	122	}
	123
44b67cb6	124	if (starts_with(line, "diff --git")) {
b66885a3 TG	125	struct patch patch = { 0 };
	126	struct strbuf root = STRBUF_INIT;
	127	int linenr = 0;
8d1675eb	128	int orig_len;
b66885a3	129
d9c66f0b JS	130	in_header = 0;
	131	strbuf_addch(&buf, '\n');
	132	if (!util->diff_offset)
	133	util->diff_offset = buf.len;
b66885a3	134	line[len - 1] = '\n';
8d1675eb	135	orig_len = len;
937b76ed	136	len = parse_git_diff_header(&root, &linenr, 0, line,
b66885a3 TG	137	len, size, &patch);
b66885a3 TG	138	if (len < 0)
8d1675eb VD	139	die(_("could not parse git header '%.*s'"),
8d1675eb VD	140	orig_len, line);
b66885a3 TG	141	strbuf_addstr(&buf, " ## ");
	142	if (patch.is_new > 0)
	143	strbuf_addf(&buf, "%s (new)", patch.new_name);
	144	else if (patch.is_delete > 0)
	145	strbuf_addf(&buf, "%s (deleted)", patch.old_name);
	146	else if (patch.is_rename)
	147	strbuf_addf(&buf, "%s => %s", patch.old_name, patch.new_name);
	148	else
	149	strbuf_addstr(&buf, patch.new_name);
	150
444e0969 TG	151	free(current_filename);
	152	if (patch.is_delete > 0)
	153	current_filename = xstrdup(patch.old_name);
	154	else
	155	current_filename = xstrdup(patch.new_name);
	156
b66885a3 TG	157	if (patch.new_mode && patch.old_mode &&
	158	patch.old_mode != patch.new_mode)
	159	strbuf_addf(&buf, " (mode change %06o => %06o)",
	160	patch.old_mode, patch.new_mode);
	161
	162	strbuf_addstr(&buf, " ##");
d9c66f0b	163	} else if (in_header) {
44b67cb6	164	if (starts_with(line, "Author: ")) {
499352c2	165	strbuf_addstr(&buf, " ## Metadata ##\n");
44b67cb6	166	strbuf_addstr(&buf, line);
d9c66f0b	167	strbuf_addstr(&buf, "\n\n");
499352c2	168	strbuf_addstr(&buf, " ## Commit message ##\n");
9f726e1b DL	169	} else if (starts_with(line, "Notes") &&
	170	line[strlen(line) - 1] == ':') {
	171	strbuf_addstr(&buf, "\n\n");
	172	/* strip the trailing colon */
	173	strbuf_addf(&buf, " ## %.*s ##\n",
	174	(int)(strlen(line) - 1), line);
44b67cb6 TG	175	} else if (starts_with(line, " ")) {
	176	p = line + len - 2;
	177	while (isspace(*p) && p >= line)
	178	p--;
	179	strbuf_add(&buf, line, p - line + 1);
d9c66f0b JS	180	strbuf_addch(&buf, '\n');
	181	}
	182	continue;
e1db2630 TG	183	} else if (skip_prefix(line, "@@ ", &p)) {
e1db2630 TG	184	p = strstr(p, "@@");
444e0969 TG	185	strbuf_addstr(&buf, "@@");
	186	if (current_filename && p[2])
	187	strbuf_addf(&buf, " %s:", current_filename);
	188	if (p)
	189	strbuf_addstr(&buf, p + 2);
b66885a3	190	} else if (!line[0])
d9c66f0b JS	191	/*
	192	* A completely blank (not ' \n', which is context)
	193	* line is not valid in a diff. We skip it
	194	* silently, because this neatly handles the blank
	195	* separator line between commits in git-log
	196	* output.
d9c66f0b JS	197	*/
d9c66f0b JS	198	continue;
44b67cb6	199	else if (line[0] == '>') {
8d5ccb59	200	strbuf_addch(&buf, '+');
44b67cb6 TG	201	strbuf_addstr(&buf, line + 1);
44b67cb6 TG	202	} else if (line[0] == '<') {
8d5ccb59	203	strbuf_addch(&buf, '-');
44b67cb6 TG	204	strbuf_addstr(&buf, line + 1);
44b67cb6 TG	205	} else if (line[0] == '#') {
8d5ccb59	206	strbuf_addch(&buf, ' ');
44b67cb6	207	strbuf_addstr(&buf, line + 1);
8d5ccb59	208	} else {
2543a641	209	strbuf_addch(&buf, ' ');
44b67cb6	210	strbuf_addstr(&buf, line);
8d5ccb59	211	}
d9c66f0b JS	212
	213	strbuf_addch(&buf, '\n');
	214	util->diffsize++;
	215	}
44b67cb6	216	strbuf_release(&contents);
d9c66f0b JS	217
	218	if (util)
	219	string_list_append(list, buf.buf)->util = util;
	220	strbuf_release(&buf);
444e0969	221	free(current_filename);
d9c66f0b JS	222
	223	if (finish_command(&cp))
	224	return -1;
	225
	226	return 0;
	227	}
	228
	229	static int patch_util_cmp(const void dummy, const struct patch_util a,
1ca69225	230	const struct patch_util b, const char keydata)
d9c66f0b JS	231	{
	232	return strcmp(a->diff, keydata ? keydata : b->diff);
	233	}
	234
	235	static void find_exact_matches(struct string_list a, struct string_list b)
	236	{
b19315d8	237	struct hashmap map = HASHMAP_INIT((hashmap_cmp_fn)patch_util_cmp, NULL);
d9c66f0b JS	238	int i;
d9c66f0b JS	239
d9c66f0b JS	240	/* First, add the patches of a to a hash map */
	241	for (i = 0; i < a->nr; i++) {
	242	struct patch_util *util = a->items[i].util;
	243
	244	util->i = i;
	245	util->patch = a->items[i].string;
	246	util->diff = util->patch + util->diff_offset;
d22245a2	247	hashmap_entry_init(&util->e, strhash(util->diff));
b94e5c1d	248	hashmap_add(&map, &util->e);
d9c66f0b JS	249	}
	250
	251	/* Now try to find exact matches in b */
	252	for (i = 0; i < b->nr; i++) {
	253	struct patch_util util = b->items[i].util, other;
	254
	255	util->i = i;
	256	util->patch = b->items[i].string;
	257	util->diff = util->patch + util->diff_offset;
d22245a2	258	hashmap_entry_init(&util->e, strhash(util->diff));
404ab78e	259	other = hashmap_remove_entry(&map, util, e, NULL);
d9c66f0b JS	260	if (other) {
	261	if (other->matching >= 0)
	262	BUG("already assigned!");
	263
	264	other->matching = i;
	265	util->matching = other->i;
	266	}
	267	}
	268
6da1a258	269	hashmap_clear(&map);
d9c66f0b JS	270	}
	271
	272	static void diffsize_consume(void data, char line, unsigned long len)
	273	{
	274	((int )data)++;
	275	}
	276
d2eb8093 JK	277	static void diffsize_hunk(void *data, long ob, long on, long nb, long nn,
	278	const char *funcline, long funclen)
	279	{
	280	diffsize_consume(data, NULL, 0);
	281	}
	282
d9c66f0b JS	283	static int diffsize(const char a, const char b)
	284	{
	285	xpparam_t pp = { 0 };
	286	xdemitconf_t cfg = { 0 };
	287	mmfile_t mf1, mf2;
	288	int count = 0;
	289
	290	mf1.ptr = (char *)a;
	291	mf1.size = strlen(a);
	292	mf2.ptr = (char *)b;
	293	mf2.size = strlen(b);
	294
	295	cfg.ctxlen = 3;
d2eb8093 JK	296	if (!xdi_diff_outf(&mf1, &mf2,
	297	diffsize_hunk, diffsize_consume, &count,
	298	&pp, &cfg))
d9c66f0b JS	299	return count;
	300
	301	error(_("failed to generate diff"));
	302	return COST_MAX;
	303	}
	304
	305	static void get_correspondences(struct string_list a, struct string_list b,
	306	int creation_factor)
	307	{
	308	int n = a->nr + b->nr;
	309	int cost, c, a2b, *b2a;
	310	int i, j;
	311
	312	ALLOC_ARRAY(cost, st_mult(n, n));
	313	ALLOC_ARRAY(a2b, n);
	314	ALLOC_ARRAY(b2a, n);
	315
	316	for (i = 0; i < a->nr; i++) {
	317	struct patch_util *a_util = a->items[i].util;
	318
	319	for (j = 0; j < b->nr; j++) {
	320	struct patch_util *b_util = b->items[j].util;
	321
	322	if (a_util->matching == j)
	323	c = 0;
	324	else if (a_util->matching < 0 && b_util->matching < 0)
	325	c = diffsize(a_util->diff, b_util->diff);
	326	else
	327	c = COST_MAX;
	328	cost[i + n * j] = c;
	329	}
	330
	331	c = a_util->matching < 0 ?
	332	a_util->diffsize * creation_factor / 100 : COST_MAX;
	333	for (j = b->nr; j < n; j++)
	334	cost[i + n * j] = c;
	335	}
	336
	337	for (j = 0; j < b->nr; j++) {
	338	struct patch_util *util = b->items[j].util;
	339
	340	c = util->matching < 0 ?
	341	util->diffsize * creation_factor / 100 : COST_MAX;
	342	for (i = a->nr; i < n; i++)
	343	cost[i + n * j] = c;
	344	}
	345
	346	for (i = a->nr; i < n; i++)
	347	for (j = b->nr; j < n; j++)
	348	cost[i + n * j] = 0;
	349
	350	compute_assignment(n, n, cost, a2b, b2a);
	351
	352	for (i = 0; i < a->nr; i++)
	353	if (a2b[i] >= 0 && a2b[i] < b->nr) {
	354	struct patch_util *a_util = a->items[i].util;
	355	struct patch_util *b_util = b->items[a2b[i]].util;
	356
	357	a_util->matching = a2b[i];
	358	b_util->matching = i;
	359	}
	360
	361	free(cost);
	362	free(a2b);
363	free(b2a);
364	}
365
faa1df86	366	static void output_pair_header(struct diff_options *diffopt,
d1f87a2d	367	int patch_no_width,
faa1df86	368	struct strbuf *buf,
eb0be38c JS	369	struct strbuf *dashes,
	370	struct patch_util *a_util,
	371	struct patch_util *b_util)
d9c66f0b	372	{
eb0be38c JS	373	struct object_id *oid = a_util ? &a_util->oid : &b_util->oid;
eb0be38c JS	374	struct commit *commit;
faa1df86 JS	375	char status;
	376	const char *color_reset = diff_get_color_opt(diffopt, DIFF_RESET);
	377	const char *color_old = diff_get_color_opt(diffopt, DIFF_FILE_OLD);
	378	const char *color_new = diff_get_color_opt(diffopt, DIFF_FILE_NEW);
	379	const char *color_commit = diff_get_color_opt(diffopt, DIFF_COMMIT);
	380	const char *color;
eb0be38c JS	381
	382	if (!dashes->len)
	383	strbuf_addchars(dashes, '-',
	384	strlen(find_unique_abbrev(oid,
	385	DEFAULT_ABBREV)));
	386
faa1df86 JS	387	if (!b_util) {
	388	color = color_old;
	389	status = '<';
	390	} else if (!a_util) {
	391	color = color_new;
	392	status = '>';
	393	} else if (strcmp(a_util->patch, b_util->patch)) {
	394	color = color_commit;
	395	status = '!';
	396	} else {
	397	color = color_commit;
	398	status = '=';
	399	}
	400
eb0be38c	401	strbuf_reset(buf);
faa1df86	402	strbuf_addstr(buf, status == '!' ? color_old : color);
eb0be38c	403	if (!a_util)
d1f87a2d	404	strbuf_addf(buf, "%*s: %s ", patch_no_width, "-", dashes->buf);
eb0be38c	405	else
d1f87a2d	406	strbuf_addf(buf, "%*d: %s ", patch_no_width, a_util->i + 1,
eb0be38c JS	407	find_unique_abbrev(&a_util->oid, DEFAULT_ABBREV));
eb0be38c JS	408
faa1df86 JS	409	if (status == '!')
	410	strbuf_addf(buf, "%s%s", color_reset, color);
	411	strbuf_addch(buf, status);
	412	if (status == '!')
	413	strbuf_addf(buf, "%s%s", color_reset, color_new);
eb0be38c JS	414
eb0be38c JS	415	if (!b_util)
d1f87a2d	416	strbuf_addf(buf, " %*s: %s", patch_no_width, "-", dashes->buf);
eb0be38c	417	else
d1f87a2d	418	strbuf_addf(buf, " %*d: %s", patch_no_width, b_util->i + 1,
eb0be38c JS	419	find_unique_abbrev(&b_util->oid, DEFAULT_ABBREV));
	420
	421	commit = lookup_commit_reference(the_repository, oid);
	422	if (commit) {
faa1df86 JS	423	if (status == '!')
	424	strbuf_addf(buf, "%s%s", color_reset, color);
	425
eb0be38c JS	426	strbuf_addch(buf, ' ');
	427	pp_commit_easy(CMIT_FMT_ONELINE, commit, buf);
	428	}
faa1df86	429	strbuf_addf(buf, "%s\n", color_reset);
eb0be38c	430
87f1b2d4	431	fwrite(buf->buf, buf->len, 1, diffopt->file);
d9c66f0b JS	432	}
d9c66f0b JS	433
499352c2 TG	434	static struct userdiff_driver section_headers = {
	435	.funcname = { "^ ## (.*) ##$\n"
	436	"^.?@@ (.*)$", REG_EXTENDED }
4eba1fe6 JS	437	};
4eba1fe6 JS	438
c8c5e43a JS	439	static struct diff_filespec get_filespec(const char name, const char *p)
	440	{
	441	struct diff_filespec *spec = alloc_filespec(name);
	442
0e573e8f	443	fill_filespec(spec, &null_oid, 0, 0100644);
c8c5e43a JS	444	spec->data = (char *)p;
	445	spec->size = strlen(p);
	446	spec->should_munmap = 0;
	447	spec->is_stdin = 1;
499352c2	448	spec->driver = &section_headers;
c8c5e43a JS	449
	450	return spec;
	451	}
	452
	453	static void patch_diff(const char a, const char b,
1ca69225	454	struct diff_options *diffopt)
c8c5e43a JS	455	{
	456	diff_queue(&diff_queued_diff,
	457	get_filespec("a", a), get_filespec("b", b));
	458
	459	diffcore_std(diffopt);
	460	diff_flush(diffopt);
	461	}
	462
	463	static void output(struct string_list a, struct string_list b,
	464	struct diff_options *diffopt)
d9c66f0b	465	{
eb0be38c	466	struct strbuf buf = STRBUF_INIT, dashes = STRBUF_INIT;
d1f87a2d	467	int patch_no_width = decimal_width(1 + (a->nr > b->nr ? a->nr : b->nr));
9dc46e02 JS	468	int i = 0, j = 0;
	469
	470	/*
	471	* We assume the user is really more interested in the second argument
	472	* ("newer" version). To that end, we print the output in the order of
	473	* the RHS (the `b` parameter). To put the LHS (the `a` parameter)
	474	* commits that are no longer in the RHS into a good place, we place
	475	* them once we have shown all of their predecessors in the LHS.
	476	*/
	477
	478	while (i < a->nr \|\| j < b->nr) {
	479	struct patch_util a_util, b_util;
	480	a_util = i < a->nr ? a->items[i].util : NULL;
	481	b_util = j < b->nr ? b->items[j].util : NULL;
	482
	483	/* Skip all the already-shown commits from the LHS. */
	484	while (i < a->nr && a_util->shown)
	485	a_util = ++i < a->nr ? a->items[i].util : NULL;
	486
	487	/* Show unmatched LHS commit whose predecessors were shown. */
	488	if (i < a->nr && a_util->matching < 0) {
d1f87a2d	489	output_pair_header(diffopt, patch_no_width,
faa1df86	490	&buf, &dashes, a_util, NULL);
9dc46e02 JS	491	i++;
	492	continue;
	493	}
d9c66f0b	494
9dc46e02 JS	495	/* Show unmatched RHS commits. */
9dc46e02 JS	496	while (j < b->nr && b_util->matching < 0) {
d1f87a2d	497	output_pair_header(diffopt, patch_no_width,
faa1df86	498	&buf, &dashes, NULL, b_util);
9dc46e02	499	b_util = ++j < b->nr ? b->items[j].util : NULL;
d9c66f0b	500	}
d9c66f0b	501
9dc46e02 JS	502	/* Show matching LHS/RHS pair. */
	503	if (j < b->nr) {
	504	a_util = a->items[b_util->matching].util;
d1f87a2d	505	output_pair_header(diffopt, patch_no_width,
faa1df86	506	&buf, &dashes, a_util, b_util);
c8c5e43a JS	507	if (!(diffopt->output_format & DIFF_FORMAT_NO_OUTPUT))
	508	patch_diff(a->items[b_util->matching].string,
	509	b->items[j].string, diffopt);
9dc46e02 JS	510	a_util->shown = 1;
	511	j++;
	512	}
d9c66f0b	513	}
eb0be38c JS	514	strbuf_release(&buf);
eb0be38c JS	515	strbuf_release(&dashes);
d9c66f0b JS	516	}
d9c66f0b JS	517
73a834e9 ES	518	static struct strbuf output_prefix_cb(struct diff_options opt, void *data)
	519	{
	520	return data;
	521	}
	522
d9c66f0b	523	int show_range_diff(const char range1, const char range2,
73a834e9	524	int creation_factor, int dual_color,
f8675343	525	const struct diff_options *diffopt,
c972bf4c	526	const struct strvec *other_arg)
d9c66f0b JS	527	{
	528	int res = 0;
	529
	530	struct string_list branch1 = STRING_LIST_INIT_DUP;
	531	struct string_list branch2 = STRING_LIST_INIT_DUP;
	532
bd361918	533	if (read_patches(range1, &branch1, other_arg))
d9c66f0b	534	res = error(_("could not parse log for '%s'"), range1);
bd361918	535	if (!res && read_patches(range2, &branch2, other_arg))
d9c66f0b JS	536	res = error(_("could not parse log for '%s'"), range2);
	537
	538	if (!res) {
73a834e9 ES	539	struct diff_options opts;
	540	struct strbuf indent = STRBUF_INIT;
	541
d8981c3f JH	542	if (diffopt)
	543	memcpy(&opts, diffopt, sizeof(opts));
	544	else
	545	diff_setup(&opts);
	546
a48e12ef ÆAB	547	if (!opts.output_format)
a48e12ef ÆAB	548	opts.output_format = DIFF_FORMAT_PATCH;
73a834e9 ES	549	opts.flags.suppress_diff_headers = 1;
73a834e9 ES	550	opts.flags.dual_color_diffed_diffs = dual_color;
430be36e	551	opts.flags.suppress_hunk_header_line_count = 1;
73a834e9 ES	552	opts.output_prefix = output_prefix_cb;
	553	strbuf_addstr(&indent, " ");
	554	opts.output_prefix_data = &indent;
	555	diff_setup_done(&opts);
	556
d9c66f0b JS	557	find_exact_matches(&branch1, &branch2);
d9c66f0b JS	558	get_correspondences(&branch1, &branch2, creation_factor);
73a834e9 ES	559	output(&branch1, &branch2, &opts);
	560
	561	strbuf_release(&indent);
d9c66f0b JS	562	}
	563
	564	string_list_clear(&branch1, 1);
	565	string_list_clear(&branch2, 1);
	566
	567	return res;
	568	}