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

#include "cache.h"
#include "range-diff.h"
#include "string-list.h"
#include "run-command.h"
#include "argv-array.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)
{
	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;

	argv_array_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", range,
			NULL);
	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);
				string_list_clear(list, 1);
				strbuf_release(&buf);
				strbuf_release(&contents);
				finish_command(&cp);
				return -1;
			}
			util->matching = -1;
			in_header = 1;
			continue;
		}

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

			in_header = 0;
			strbuf_addch(&buf, '\n');
			if (!util->diff_offset)
				util->diff_offset = buf.len;
			line[len - 1] = '\n';
			len = parse_git_diff_header(&root, &linenr, 0, line,
						    len, size, &patch);
			if (len < 0)
				die(_("could not parse git header '%.*s'"), (int)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;
	int i;

	hashmap_init(&map, (hashmap_cmp_fn)patch_util_cmp, NULL, 0);

	/* 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_free(&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,
		    struct diff_options *diffopt)
{
	int res = 0;

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

	if (read_patches(range1, &branch1))
		res = error(_("could not parse log for '%s'"), range1);
	if (!res && read_patches(range2, &branch2))
		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"
	5	#include "argv-array.h"
	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	*/
	43	static int read_patches(const char range, struct string_list list)
	44	{
	45	struct child_process cp = CHILD_PROCESS_INIT;
44b67cb6	46	struct strbuf buf = STRBUF_INIT, contents = STRBUF_INIT;
d9c66f0b JS	47	struct patch_util *util = NULL;
d9c66f0b JS	48	int in_header = 1;
444e0969	49	char line, current_filename = NULL;
44b67cb6 TG	50	int offset, len;
44b67cb6 TG	51	size_t size;
d9c66f0b JS	52
	53	argv_array_pushl(&cp.args, "log", "--no-color", "-p", "--no-merges",
	54	"--reverse", "--date-order", "--decorate=no",
937b76ed	55	"--no-prefix",
8d5ccb59 SB	56	/*
	57	* Choose indicators that are not used anywhere
	58	* else in diffs, but still look reasonable
	59	* (e.g. will not be confusing when debugging)
	60	*/
	61	"--output-indicator-new=>",
	62	"--output-indicator-old=<",
	63	"--output-indicator-context=#",
d9c66f0b JS	64	"--no-abbrev-commit", range,
	65	NULL);
	66	cp.out = -1;
	67	cp.no_stdin = 1;
	68	cp.git_cmd = 1;
	69
	70	if (start_command(&cp))
	71	return error_errno(_("could not start `log`"));
44b67cb6	72	if (strbuf_read(&contents, cp.out, 0) < 0) {
d9c66f0b JS	73	error_errno(_("could not read `log` output"));
	74	finish_command(&cp);
	75	return -1;
	76	}
	77
44b67cb6 TG	78	line = contents.buf;
	79	size = contents.len;
	80	for (offset = 0; size > 0; offset += len, size -= len, line += len) {
d9c66f0b JS	81	const char *p;
d9c66f0b JS	82
44b67cb6 TG	83	len = find_end_of_line(line, size);
	84	line[len - 1] = '\0';
	85	if (skip_prefix(line, "commit ", &p)) {
d9c66f0b JS	86	if (util) {
	87	string_list_append(list, buf.buf)->util = util;
	88	strbuf_reset(&buf);
	89	}
	90	util = xcalloc(sizeof(*util), 1);
	91	if (get_oid(p, &util->oid)) {
	92	error(_("could not parse commit '%s'"), p);
	93	free(util);
	94	string_list_clear(list, 1);
	95	strbuf_release(&buf);
44b67cb6	96	strbuf_release(&contents);
d9c66f0b JS	97	finish_command(&cp);
	98	return -1;
	99	}
	100	util->matching = -1;
	101	in_header = 1;
	102	continue;
	103	}
	104
44b67cb6	105	if (starts_with(line, "diff --git")) {
b66885a3 TG	106	struct patch patch = { 0 };
	107	struct strbuf root = STRBUF_INIT;
	108	int linenr = 0;
	109
d9c66f0b JS	110	in_header = 0;
	111	strbuf_addch(&buf, '\n');
	112	if (!util->diff_offset)
	113	util->diff_offset = buf.len;
b66885a3	114	line[len - 1] = '\n';
937b76ed	115	len = parse_git_diff_header(&root, &linenr, 0, line,
b66885a3 TG	116	len, size, &patch);
	117	if (len < 0)
	118	die(_("could not parse git header '%.*s'"), (int)len, line);
	119	strbuf_addstr(&buf, " ## ");
	120	if (patch.is_new > 0)
	121	strbuf_addf(&buf, "%s (new)", patch.new_name);
	122	else if (patch.is_delete > 0)
	123	strbuf_addf(&buf, "%s (deleted)", patch.old_name);
	124	else if (patch.is_rename)
	125	strbuf_addf(&buf, "%s => %s", patch.old_name, patch.new_name);
	126	else
	127	strbuf_addstr(&buf, patch.new_name);
	128
444e0969 TG	129	free(current_filename);
	130	if (patch.is_delete > 0)
	131	current_filename = xstrdup(patch.old_name);
	132	else
	133	current_filename = xstrdup(patch.new_name);
	134
b66885a3 TG	135	if (patch.new_mode && patch.old_mode &&
	136	patch.old_mode != patch.new_mode)
	137	strbuf_addf(&buf, " (mode change %06o => %06o)",
	138	patch.old_mode, patch.new_mode);
	139
	140	strbuf_addstr(&buf, " ##");
d9c66f0b	141	} else if (in_header) {
44b67cb6	142	if (starts_with(line, "Author: ")) {
499352c2	143	strbuf_addstr(&buf, " ## Metadata ##\n");
44b67cb6	144	strbuf_addstr(&buf, line);
d9c66f0b	145	strbuf_addstr(&buf, "\n\n");
499352c2	146	strbuf_addstr(&buf, " ## Commit message ##\n");
9f726e1b DL	147	} else if (starts_with(line, "Notes") &&
	148	line[strlen(line) - 1] == ':') {
	149	strbuf_addstr(&buf, "\n\n");
	150	/* strip the trailing colon */
	151	strbuf_addf(&buf, " ## %.*s ##\n",
	152	(int)(strlen(line) - 1), line);
44b67cb6 TG	153	} else if (starts_with(line, " ")) {
	154	p = line + len - 2;
	155	while (isspace(*p) && p >= line)
	156	p--;
	157	strbuf_add(&buf, line, p - line + 1);
d9c66f0b JS	158	strbuf_addch(&buf, '\n');
	159	}
	160	continue;
e1db2630 TG	161	} else if (skip_prefix(line, "@@ ", &p)) {
e1db2630 TG	162	p = strstr(p, "@@");
444e0969 TG	163	strbuf_addstr(&buf, "@@");
	164	if (current_filename && p[2])
	165	strbuf_addf(&buf, " %s:", current_filename);
	166	if (p)
	167	strbuf_addstr(&buf, p + 2);
b66885a3	168	} else if (!line[0])
d9c66f0b JS	169	/*
	170	* A completely blank (not ' \n', which is context)
	171	* line is not valid in a diff. We skip it
	172	* silently, because this neatly handles the blank
	173	* separator line between commits in git-log
	174	* output.
d9c66f0b JS	175	*/
d9c66f0b JS	176	continue;
44b67cb6	177	else if (line[0] == '>') {
8d5ccb59	178	strbuf_addch(&buf, '+');
44b67cb6 TG	179	strbuf_addstr(&buf, line + 1);
44b67cb6 TG	180	} else if (line[0] == '<') {
8d5ccb59	181	strbuf_addch(&buf, '-');
44b67cb6 TG	182	strbuf_addstr(&buf, line + 1);
44b67cb6 TG	183	} else if (line[0] == '#') {
8d5ccb59	184	strbuf_addch(&buf, ' ');
44b67cb6	185	strbuf_addstr(&buf, line + 1);
8d5ccb59	186	} else {
2543a641	187	strbuf_addch(&buf, ' ');
44b67cb6	188	strbuf_addstr(&buf, line);
8d5ccb59	189	}
d9c66f0b JS	190
	191	strbuf_addch(&buf, '\n');
	192	util->diffsize++;
	193	}
44b67cb6	194	strbuf_release(&contents);
d9c66f0b JS	195
	196	if (util)
	197	string_list_append(list, buf.buf)->util = util;
	198	strbuf_release(&buf);
444e0969	199	free(current_filename);
d9c66f0b JS	200
	201	if (finish_command(&cp))
	202	return -1;
	203
	204	return 0;
	205	}
	206
	207	static int patch_util_cmp(const void dummy, const struct patch_util a,
1ca69225	208	const struct patch_util b, const char keydata)
d9c66f0b JS	209	{
	210	return strcmp(a->diff, keydata ? keydata : b->diff);
	211	}
	212
	213	static void find_exact_matches(struct string_list a, struct string_list b)
	214	{
	215	struct hashmap map;
	216	int i;
	217
	218	hashmap_init(&map, (hashmap_cmp_fn)patch_util_cmp, NULL, 0);
	219
	220	/* First, add the patches of a to a hash map */
	221	for (i = 0; i < a->nr; i++) {
	222	struct patch_util *util = a->items[i].util;
	223
	224	util->i = i;
	225	util->patch = a->items[i].string;
	226	util->diff = util->patch + util->diff_offset;
d22245a2	227	hashmap_entry_init(&util->e, strhash(util->diff));
b94e5c1d	228	hashmap_add(&map, &util->e);
d9c66f0b JS	229	}
	230
	231	/* Now try to find exact matches in b */
	232	for (i = 0; i < b->nr; i++) {
	233	struct patch_util util = b->items[i].util, other;
	234
	235	util->i = i;
	236	util->patch = b->items[i].string;
	237	util->diff = util->patch + util->diff_offset;
d22245a2	238	hashmap_entry_init(&util->e, strhash(util->diff));
404ab78e	239	other = hashmap_remove_entry(&map, util, e, NULL);
d9c66f0b JS	240	if (other) {
	241	if (other->matching >= 0)
	242	BUG("already assigned!");
	243
	244	other->matching = i;
	245	util->matching = other->i;
	246	}
	247	}
	248
c8e424c9	249	hashmap_free(&map);
d9c66f0b JS	250	}
	251
	252	static void diffsize_consume(void data, char line, unsigned long len)
	253	{
	254	((int )data)++;
	255	}
	256
d2eb8093 JK	257	static void diffsize_hunk(void *data, long ob, long on, long nb, long nn,
	258	const char *funcline, long funclen)
	259	{
	260	diffsize_consume(data, NULL, 0);
	261	}
	262
d9c66f0b JS	263	static int diffsize(const char a, const char b)
	264	{
	265	xpparam_t pp = { 0 };
	266	xdemitconf_t cfg = { 0 };
	267	mmfile_t mf1, mf2;
	268	int count = 0;
	269
	270	mf1.ptr = (char *)a;
	271	mf1.size = strlen(a);
	272	mf2.ptr = (char *)b;
	273	mf2.size = strlen(b);
	274
	275	cfg.ctxlen = 3;
d2eb8093 JK	276	if (!xdi_diff_outf(&mf1, &mf2,
	277	diffsize_hunk, diffsize_consume, &count,
	278	&pp, &cfg))
d9c66f0b JS	279	return count;
	280
	281	error(_("failed to generate diff"));
	282	return COST_MAX;
	283	}
	284
	285	static void get_correspondences(struct string_list a, struct string_list b,
	286	int creation_factor)
	287	{
	288	int n = a->nr + b->nr;
	289	int cost, c, a2b, *b2a;
	290	int i, j;
	291
	292	ALLOC_ARRAY(cost, st_mult(n, n));
	293	ALLOC_ARRAY(a2b, n);
	294	ALLOC_ARRAY(b2a, n);
	295
	296	for (i = 0; i < a->nr; i++) {
	297	struct patch_util *a_util = a->items[i].util;
	298
	299	for (j = 0; j < b->nr; j++) {
	300	struct patch_util *b_util = b->items[j].util;
	301
	302	if (a_util->matching == j)
	303	c = 0;
	304	else if (a_util->matching < 0 && b_util->matching < 0)
	305	c = diffsize(a_util->diff, b_util->diff);
	306	else
	307	c = COST_MAX;
	308	cost[i + n * j] = c;
	309	}
	310
	311	c = a_util->matching < 0 ?
	312	a_util->diffsize * creation_factor / 100 : COST_MAX;
	313	for (j = b->nr; j < n; j++)
	314	cost[i + n * j] = c;
	315	}
	316
	317	for (j = 0; j < b->nr; j++) {
	318	struct patch_util *util = b->items[j].util;
	319
	320	c = util->matching < 0 ?
	321	util->diffsize * creation_factor / 100 : COST_MAX;
	322	for (i = a->nr; i < n; i++)
	323	cost[i + n * j] = c;
	324	}
	325
	326	for (i = a->nr; i < n; i++)
	327	for (j = b->nr; j < n; j++)
	328	cost[i + n * j] = 0;
	329
	330	compute_assignment(n, n, cost, a2b, b2a);
	331
	332	for (i = 0; i < a->nr; i++)
	333	if (a2b[i] >= 0 && a2b[i] < b->nr) {
	334	struct patch_util *a_util = a->items[i].util;
	335	struct patch_util *b_util = b->items[a2b[i]].util;
	336
	337	a_util->matching = a2b[i];
	338	b_util->matching = i;
	339	}
	340
	341	free(cost);
	342	free(a2b);
343	free(b2a);
344	}
345
faa1df86	346	static void output_pair_header(struct diff_options *diffopt,
d1f87a2d	347	int patch_no_width,
faa1df86	348	struct strbuf *buf,
eb0be38c JS	349	struct strbuf *dashes,
	350	struct patch_util *a_util,
	351	struct patch_util *b_util)
d9c66f0b	352	{
eb0be38c JS	353	struct object_id *oid = a_util ? &a_util->oid : &b_util->oid;
eb0be38c JS	354	struct commit *commit;
faa1df86 JS	355	char status;
	356	const char *color_reset = diff_get_color_opt(diffopt, DIFF_RESET);
	357	const char *color_old = diff_get_color_opt(diffopt, DIFF_FILE_OLD);
	358	const char *color_new = diff_get_color_opt(diffopt, DIFF_FILE_NEW);
	359	const char *color_commit = diff_get_color_opt(diffopt, DIFF_COMMIT);
	360	const char *color;
eb0be38c JS	361
	362	if (!dashes->len)
	363	strbuf_addchars(dashes, '-',
	364	strlen(find_unique_abbrev(oid,
	365	DEFAULT_ABBREV)));
	366
faa1df86 JS	367	if (!b_util) {
	368	color = color_old;
	369	status = '<';
	370	} else if (!a_util) {
	371	color = color_new;
	372	status = '>';
	373	} else if (strcmp(a_util->patch, b_util->patch)) {
	374	color = color_commit;
	375	status = '!';
	376	} else {
	377	color = color_commit;
	378	status = '=';
	379	}
	380
eb0be38c	381	strbuf_reset(buf);
faa1df86	382	strbuf_addstr(buf, status == '!' ? color_old : color);
eb0be38c	383	if (!a_util)
d1f87a2d	384	strbuf_addf(buf, "%*s: %s ", patch_no_width, "-", dashes->buf);
eb0be38c	385	else
d1f87a2d	386	strbuf_addf(buf, "%*d: %s ", patch_no_width, a_util->i + 1,
eb0be38c JS	387	find_unique_abbrev(&a_util->oid, DEFAULT_ABBREV));
eb0be38c JS	388
faa1df86 JS	389	if (status == '!')
	390	strbuf_addf(buf, "%s%s", color_reset, color);
	391	strbuf_addch(buf, status);
	392	if (status == '!')
	393	strbuf_addf(buf, "%s%s", color_reset, color_new);
eb0be38c JS	394
eb0be38c JS	395	if (!b_util)
d1f87a2d	396	strbuf_addf(buf, " %*s: %s", patch_no_width, "-", dashes->buf);
eb0be38c	397	else
d1f87a2d	398	strbuf_addf(buf, " %*d: %s", patch_no_width, b_util->i + 1,
eb0be38c JS	399	find_unique_abbrev(&b_util->oid, DEFAULT_ABBREV));
	400
	401	commit = lookup_commit_reference(the_repository, oid);
	402	if (commit) {
faa1df86 JS	403	if (status == '!')
	404	strbuf_addf(buf, "%s%s", color_reset, color);
	405
eb0be38c JS	406	strbuf_addch(buf, ' ');
	407	pp_commit_easy(CMIT_FMT_ONELINE, commit, buf);
	408	}
faa1df86	409	strbuf_addf(buf, "%s\n", color_reset);
eb0be38c	410
87f1b2d4	411	fwrite(buf->buf, buf->len, 1, diffopt->file);
d9c66f0b JS	412	}
d9c66f0b JS	413
499352c2 TG	414	static struct userdiff_driver section_headers = {
	415	.funcname = { "^ ## (.*) ##$\n"
	416	"^.?@@ (.*)$", REG_EXTENDED }
4eba1fe6 JS	417	};
4eba1fe6 JS	418
c8c5e43a JS	419	static struct diff_filespec get_filespec(const char name, const char *p)
	420	{
	421	struct diff_filespec *spec = alloc_filespec(name);
	422
0e573e8f	423	fill_filespec(spec, &null_oid, 0, 0100644);
c8c5e43a JS	424	spec->data = (char *)p;
	425	spec->size = strlen(p);
	426	spec->should_munmap = 0;
	427	spec->is_stdin = 1;
499352c2	428	spec->driver = &section_headers;
c8c5e43a JS	429
	430	return spec;
	431	}
	432
	433	static void patch_diff(const char a, const char b,
1ca69225	434	struct diff_options *diffopt)
c8c5e43a JS	435	{
	436	diff_queue(&diff_queued_diff,
	437	get_filespec("a", a), get_filespec("b", b));
	438
	439	diffcore_std(diffopt);
	440	diff_flush(diffopt);
	441	}
	442
	443	static void output(struct string_list a, struct string_list b,
	444	struct diff_options *diffopt)
d9c66f0b	445	{
eb0be38c	446	struct strbuf buf = STRBUF_INIT, dashes = STRBUF_INIT;
d1f87a2d	447	int patch_no_width = decimal_width(1 + (a->nr > b->nr ? a->nr : b->nr));
9dc46e02 JS	448	int i = 0, j = 0;
	449
	450	/*
	451	* We assume the user is really more interested in the second argument
	452	* ("newer" version). To that end, we print the output in the order of
	453	* the RHS (the `b` parameter). To put the LHS (the `a` parameter)
	454	* commits that are no longer in the RHS into a good place, we place
	455	* them once we have shown all of their predecessors in the LHS.
	456	*/
	457
	458	while (i < a->nr \|\| j < b->nr) {
	459	struct patch_util a_util, b_util;
	460	a_util = i < a->nr ? a->items[i].util : NULL;
	461	b_util = j < b->nr ? b->items[j].util : NULL;
	462
	463	/* Skip all the already-shown commits from the LHS. */
	464	while (i < a->nr && a_util->shown)
	465	a_util = ++i < a->nr ? a->items[i].util : NULL;
	466
	467	/* Show unmatched LHS commit whose predecessors were shown. */
	468	if (i < a->nr && a_util->matching < 0) {
d1f87a2d	469	output_pair_header(diffopt, patch_no_width,
faa1df86	470	&buf, &dashes, a_util, NULL);
9dc46e02 JS	471	i++;
	472	continue;
	473	}
d9c66f0b	474
9dc46e02 JS	475	/* Show unmatched RHS commits. */
9dc46e02 JS	476	while (j < b->nr && b_util->matching < 0) {
d1f87a2d	477	output_pair_header(diffopt, patch_no_width,
faa1df86	478	&buf, &dashes, NULL, b_util);
9dc46e02	479	b_util = ++j < b->nr ? b->items[j].util : NULL;
d9c66f0b	480	}
d9c66f0b	481
9dc46e02 JS	482	/* Show matching LHS/RHS pair. */
	483	if (j < b->nr) {
	484	a_util = a->items[b_util->matching].util;
d1f87a2d	485	output_pair_header(diffopt, patch_no_width,
faa1df86	486	&buf, &dashes, a_util, b_util);
c8c5e43a JS	487	if (!(diffopt->output_format & DIFF_FORMAT_NO_OUTPUT))
	488	patch_diff(a->items[b_util->matching].string,
	489	b->items[j].string, diffopt);
9dc46e02 JS	490	a_util->shown = 1;
	491	j++;
	492	}
d9c66f0b	493	}
eb0be38c JS	494	strbuf_release(&buf);
eb0be38c JS	495	strbuf_release(&dashes);
d9c66f0b JS	496	}
d9c66f0b JS	497
73a834e9 ES	498	static struct strbuf output_prefix_cb(struct diff_options opt, void *data)
	499	{
	500	return data;
	501	}
	502
d9c66f0b	503	int show_range_diff(const char range1, const char range2,
73a834e9 ES	504	int creation_factor, int dual_color,
73a834e9 ES	505	struct diff_options *diffopt)
d9c66f0b JS	506	{
	507	int res = 0;
	508
	509	struct string_list branch1 = STRING_LIST_INIT_DUP;
	510	struct string_list branch2 = STRING_LIST_INIT_DUP;
	511
	512	if (read_patches(range1, &branch1))
	513	res = error(_("could not parse log for '%s'"), range1);
	514	if (!res && read_patches(range2, &branch2))
	515	res = error(_("could not parse log for '%s'"), range2);
	516
	517	if (!res) {
73a834e9 ES	518	struct diff_options opts;
	519	struct strbuf indent = STRBUF_INIT;
	520
d8981c3f JH	521	if (diffopt)
	522	memcpy(&opts, diffopt, sizeof(opts));
	523	else
	524	diff_setup(&opts);
	525
a48e12ef ÆAB	526	if (!opts.output_format)
a48e12ef ÆAB	527	opts.output_format = DIFF_FORMAT_PATCH;
73a834e9 ES	528	opts.flags.suppress_diff_headers = 1;
73a834e9 ES	529	opts.flags.dual_color_diffed_diffs = dual_color;
430be36e	530	opts.flags.suppress_hunk_header_line_count = 1;
73a834e9 ES	531	opts.output_prefix = output_prefix_cb;
	532	strbuf_addstr(&indent, " ");
	533	opts.output_prefix_data = &indent;
	534	diff_setup_done(&opts);
	535
d9c66f0b JS	536	find_exact_matches(&branch1, &branch2);
d9c66f0b JS	537	get_correspondences(&branch1, &branch2, creation_factor);
73a834e9 ES	538	output(&branch1, &branch2, &opts);
	539
	540	strbuf_release(&indent);
d9c66f0b JS	541	}
	542
	543	string_list_clear(&branch1, 1);
	544	string_list_clear(&branch2, 1);
	545
	546	return res;
	547	}