git-commit-vandalism/rerere.c

#include "cache.h"
#include "lockfile.h"
#include "string-list.h"
#include "rerere.h"
#include "xdiff-interface.h"
#include "dir.h"
#include "resolve-undo.h"
#include "ll-merge.h"
#include "attr.h"
#include "pathspec.h"

#define RESOLVED 0
#define PUNTED 1
#define THREE_STAGED 2
void *RERERE_RESOLVED = &RERERE_RESOLVED;

/* if rerere_enabled == -1, fall back to detection of .git/rr-cache */
static int rerere_enabled = -1;

/* automatically update cleanly resolved paths to the index */
static int rerere_autoupdate;

const char *rerere_path(const char *hex, const char *file)
{
	return git_path("rr-cache/%s/%s", hex, file);
}

static int has_rerere_resolution(const char *hex)
{
	struct stat st;
	return !stat(rerere_path(hex, "postimage"), &st);
}

static void read_rr(struct string_list *rr)
{
	unsigned char sha1[20];
	char buf[PATH_MAX];
	FILE *in = fopen(git_path_merge_rr(), "r");
	if (!in)
		return;
	while (fread(buf, 40, 1, in) == 1) {
		int i;
		char *name;
		if (get_sha1_hex(buf, sha1))
			die("corrupt MERGE_RR");
		buf[40] = '\0';
		name = xstrdup(buf);
		if (fgetc(in) != '\t')
			die("corrupt MERGE_RR");
		for (i = 0; i < sizeof(buf); i++) {
			int c = fgetc(in);
			if (c < 0)
				die("corrupt MERGE_RR");
			buf[i] = c;
			if (c == 0)
				 break;
		}
		if (i == sizeof(buf))
			die("filename too long");
		string_list_insert(rr, buf)->util = name;
	}
	fclose(in);
}

static struct lock_file write_lock;

static int write_rr(struct string_list *rr, int out_fd)
{
	int i;
	for (i = 0; i < rr->nr; i++) {
		const char *path;
		int length;
		if (!rr->items[i].util)
			continue;
		path = rr->items[i].string;
		length = strlen(path) + 1;
		if (write_in_full(out_fd, rr->items[i].util, 40) != 40 ||
		    write_str_in_full(out_fd, "\t") != 1 ||
		    write_in_full(out_fd, path, length) != length)
			die("unable to write rerere record");
	}
	if (commit_lock_file(&write_lock) != 0)
		die("unable to write rerere record");
	return 0;
}

static void ferr_write(const void *p, size_t count, FILE *fp, int *err)
{
	if (!count || *err)
		return;
	if (fwrite(p, count, 1, fp) != 1)
		*err = errno;
}

static inline void ferr_puts(const char *s, FILE *fp, int *err)
{
	ferr_write(s, strlen(s), fp, err);
}

struct rerere_io {
	int (*getline)(struct strbuf *, struct rerere_io *);
	FILE *output;
	int wrerror;
	/* some more stuff */
};

static void rerere_io_putstr(const char *str, struct rerere_io *io)
{
	if (io->output)
		ferr_puts(str, io->output, &io->wrerror);
}

static void rerere_io_putconflict(int ch, int size, struct rerere_io *io)
{
	char buf[64];

	while (size) {
		if (size < sizeof(buf) - 2) {
			memset(buf, ch, size);
			buf[size] = '\n';
			buf[size + 1] = '\0';
			size = 0;
		} else {
			int sz = sizeof(buf) - 1;
			if (size <= sz)
				sz -= (sz - size) + 1;
			memset(buf, ch, sz);
			buf[sz] = '\0';
			size -= sz;
		}
		rerere_io_putstr(buf, io);
	}
}

static void rerere_io_putmem(const char *mem, size_t sz, struct rerere_io *io)
{
	if (io->output)
		ferr_write(mem, sz, io->output, &io->wrerror);
}

struct rerere_io_file {
	struct rerere_io io;
	FILE *input;
};

static int rerere_file_getline(struct strbuf *sb, struct rerere_io *io_)
{
	struct rerere_io_file *io = (struct rerere_io_file *)io_;
	return strbuf_getwholeline(sb, io->input, '\n');
}

static int is_cmarker(char *buf, int marker_char, int marker_size, int want_sp)
{
	while (marker_size--)
		if (*buf++ != marker_char)
			return 0;
	if (want_sp && *buf != ' ')
		return 0;
	return isspace(*buf);
}

static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_size)
{
	git_SHA_CTX ctx;
	int hunk_no = 0;
	enum {
		RR_CONTEXT = 0, RR_SIDE_1, RR_SIDE_2, RR_ORIGINAL
	} hunk = RR_CONTEXT;
	struct strbuf one = STRBUF_INIT, two = STRBUF_INIT;
	struct strbuf buf = STRBUF_INIT;

	if (sha1)
		git_SHA1_Init(&ctx);

	while (!io->getline(&buf, io)) {
		if (is_cmarker(buf.buf, '<', marker_size, 1)) {
			if (hunk != RR_CONTEXT)
				goto bad;
			hunk = RR_SIDE_1;
		} else if (is_cmarker(buf.buf, '|', marker_size, 0)) {
			if (hunk != RR_SIDE_1)
				goto bad;
			hunk = RR_ORIGINAL;
		} else if (is_cmarker(buf.buf, '=', marker_size, 0)) {
			if (hunk != RR_SIDE_1 && hunk != RR_ORIGINAL)
				goto bad;
			hunk = RR_SIDE_2;
		} else if (is_cmarker(buf.buf, '>', marker_size, 1)) {
			if (hunk != RR_SIDE_2)
				goto bad;
			if (strbuf_cmp(&one, &two) > 0)
				strbuf_swap(&one, &two);
			hunk_no++;
			hunk = RR_CONTEXT;
			rerere_io_putconflict('<', marker_size, io);
			rerere_io_putmem(one.buf, one.len, io);
			rerere_io_putconflict('=', marker_size, io);
			rerere_io_putmem(two.buf, two.len, io);
			rerere_io_putconflict('>', marker_size, io);
			if (sha1) {
				git_SHA1_Update(&ctx, one.buf ? one.buf : "",
					    one.len + 1);
				git_SHA1_Update(&ctx, two.buf ? two.buf : "",
					    two.len + 1);
			}
			strbuf_reset(&one);
			strbuf_reset(&two);
		} else if (hunk == RR_SIDE_1)
			strbuf_addbuf(&one, &buf);
		else if (hunk == RR_ORIGINAL)
			; /* discard */
		else if (hunk == RR_SIDE_2)
			strbuf_addbuf(&two, &buf);
		else
			rerere_io_putstr(buf.buf, io);
		continue;
	bad:
		hunk = 99; /* force error exit */
		break;
	}
	strbuf_release(&one);
	strbuf_release(&two);
	strbuf_release(&buf);

	if (sha1)
		git_SHA1_Final(sha1, &ctx);
	if (hunk != RR_CONTEXT)
		return -1;
	return hunk_no;
}

static int handle_file(const char *path, unsigned char *sha1, const char *output)
{
	int hunk_no = 0;
	struct rerere_io_file io;
	int marker_size = ll_merge_marker_size(path);

	memset(&io, 0, sizeof(io));
	io.io.getline = rerere_file_getline;
	io.input = fopen(path, "r");
	io.io.wrerror = 0;
	if (!io.input)
		return error("Could not open %s", path);

	if (output) {
		io.io.output = fopen(output, "w");
		if (!io.io.output) {
			fclose(io.input);
			return error("Could not write %s", output);
		}
	}

	hunk_no = handle_path(sha1, (struct rerere_io *)&io, marker_size);

	fclose(io.input);
	if (io.io.wrerror)
		error("There were errors while writing %s (%s)",
		      path, strerror(io.io.wrerror));
	if (io.io.output && fclose(io.io.output))
		io.io.wrerror = error("Failed to flush %s: %s",
				      path, strerror(errno));

	if (hunk_no < 0) {
		if (output)
			unlink_or_warn(output);
		return error("Could not parse conflict hunks in %s", path);
	}
	if (io.io.wrerror)
		return -1;
	return hunk_no;
}

struct rerere_io_mem {
	struct rerere_io io;
	struct strbuf input;
};

static int rerere_mem_getline(struct strbuf *sb, struct rerere_io *io_)
{
	struct rerere_io_mem *io = (struct rerere_io_mem *)io_;
	char *ep;
	size_t len;

	strbuf_release(sb);
	if (!io->input.len)
		return -1;
	ep = memchr(io->input.buf, '\n', io->input.len);
	if (!ep)
		ep = io->input.buf + io->input.len;
	else if (*ep == '\n')
		ep++;
	len = ep - io->input.buf;
	strbuf_add(sb, io->input.buf, len);
	strbuf_remove(&io->input, 0, len);
	return 0;
}

static int handle_cache(const char *path, unsigned char *sha1, const char *output)
{
	mmfile_t mmfile[3] = {{NULL}};
	mmbuffer_t result = {NULL, 0};
	const struct cache_entry *ce;
	int pos, len, i, hunk_no;
	struct rerere_io_mem io;
	int marker_size = ll_merge_marker_size(path);

	/*
	 * Reproduce the conflicted merge in-core
	 */
	len = strlen(path);
	pos = cache_name_pos(path, len);
	if (0 <= pos)
		return -1;
	pos = -pos - 1;

	for (i = 0; i < 3; i++) {
		enum object_type type;
		unsigned long size;
		int j;

		if (active_nr <= pos)
			break;
		ce = active_cache[pos++];
		if (ce_namelen(ce) != len || memcmp(ce->name, path, len))
			continue;
		j = ce_stage(ce) - 1;
		mmfile[j].ptr = read_sha1_file(ce->sha1, &type, &size);
		mmfile[j].size = size;
	}
	for (i = 0; i < 3; i++) {
		if (!mmfile[i].ptr && !mmfile[i].size)
			mmfile[i].ptr = xstrdup("");
	}
	/*
	 * NEEDSWORK: handle conflicts from merges with
	 * merge.renormalize set, too
	 */
	ll_merge(&result, path, &mmfile[0], NULL,
		 &mmfile[1], "ours",
		 &mmfile[2], "theirs", NULL);
	for (i = 0; i < 3; i++)
		free(mmfile[i].ptr);

	memset(&io, 0, sizeof(io));
	io.io.getline = rerere_mem_getline;
	if (output)
		io.io.output = fopen(output, "w");
	else
		io.io.output = NULL;
	strbuf_init(&io.input, 0);
	strbuf_attach(&io.input, result.ptr, result.size, result.size);

	hunk_no = handle_path(sha1, (struct rerere_io *)&io, marker_size);
	strbuf_release(&io.input);
	if (io.io.output)
		fclose(io.io.output);
	return hunk_no;
}

static int check_one_conflict(int i, int *type)
{
	const struct cache_entry *e = active_cache[i];

	if (!ce_stage(e)) {
		*type = RESOLVED;
		return i + 1;
	}

	*type = PUNTED;
	if (ce_stage(e) == 1) {
		if (active_nr <= ++i)
			return i + 1;
	}

	/* Only handle regular files with both stages #2 and #3 */
	if (i + 1 < active_nr) {
		const struct cache_entry *e2 = active_cache[i];
		const struct cache_entry *e3 = active_cache[i + 1];
		if (ce_stage(e2) == 2 &&
		    ce_stage(e3) == 3 &&
		    ce_same_name(e, e3) &&
		    S_ISREG(e2->ce_mode) &&
		    S_ISREG(e3->ce_mode))
			*type = THREE_STAGED;
	}

	/* Skip the entries with the same name */
	while (i < active_nr && ce_same_name(e, active_cache[i]))
		i++;
	return i;
}

static int find_conflict(struct string_list *conflict)
{
	int i;
	if (read_cache() < 0)
		return error("Could not read index");

	for (i = 0; i < active_nr;) {
		int conflict_type;
		const struct cache_entry *e = active_cache[i];
		i = check_one_conflict(i, &conflict_type);
		if (conflict_type == THREE_STAGED)
			string_list_insert(conflict, (const char *)e->name);
	}
	return 0;
}

int rerere_remaining(struct string_list *merge_rr)
{
	int i;
	if (read_cache() < 0)
		return error("Could not read index");

	for (i = 0; i < active_nr;) {
		int conflict_type;
		const struct cache_entry *e = active_cache[i];
		i = check_one_conflict(i, &conflict_type);
		if (conflict_type == PUNTED)
			string_list_insert(merge_rr, (const char *)e->name);
		else if (conflict_type == RESOLVED) {
			struct string_list_item *it;
			it = string_list_lookup(merge_rr, (const char *)e->name);
			if (it != NULL) {
				free(it->util);
				it->util = RERERE_RESOLVED;
			}
		}
	}
	return 0;
}

static int merge(const char *name, const char *path)
{
	int ret;
	mmfile_t cur = {NULL, 0}, base = {NULL, 0}, other = {NULL, 0};
	mmbuffer_t result = {NULL, 0};

	if (handle_file(path, NULL, rerere_path(name, "thisimage")) < 0)
		return 1;

	if (read_mmfile(&cur, rerere_path(name, "thisimage")) ||
			read_mmfile(&base, rerere_path(name, "preimage")) ||
			read_mmfile(&other, rerere_path(name, "postimage"))) {
		ret = 1;
		goto out;
	}
	ret = ll_merge(&result, path, &base, NULL, &cur, "", &other, "", NULL);
	if (!ret) {
		FILE *f;

		if (utime(rerere_path(name, "postimage"), NULL) < 0)
			warning("failed utime() on %s: %s",
					rerere_path(name, "postimage"),
					strerror(errno));
		f = fopen(path, "w");
		if (!f)
			return error("Could not open %s: %s", path,
				     strerror(errno));
		if (fwrite(result.ptr, result.size, 1, f) != 1)
			error("Could not write %s: %s", path, strerror(errno));
		if (fclose(f))
			return error("Writing %s failed: %s", path,
				     strerror(errno));
	}

out:
	free(cur.ptr);
	free(base.ptr);
	free(other.ptr);
	free(result.ptr);

	return ret;
}

static struct lock_file index_lock;

static void update_paths(struct string_list *update)
{
	int i;

	hold_locked_index(&index_lock, 1);

	for (i = 0; i < update->nr; i++) {
		struct string_list_item *item = &update->items[i];
		if (add_file_to_cache(item->string, 0))
			exit(128);
	}

	if (active_cache_changed) {
		if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
			die("Unable to write new index file");
	} else
		rollback_lock_file(&index_lock);
}

static int do_plain_rerere(struct string_list *rr, int fd)
{
	struct string_list conflict = STRING_LIST_INIT_DUP;
	struct string_list update = STRING_LIST_INIT_DUP;
	int i;

	find_conflict(&conflict);

	/*
	 * MERGE_RR records paths with conflicts immediately after merge
	 * failed.  Some of the conflicted paths might have been hand resolved
	 * in the working tree since then, but the initial run would catch all
	 * and register their preimages.
	 */

	for (i = 0; i < conflict.nr; i++) {
		const char *path = conflict.items[i].string;
		if (!string_list_has_string(rr, path)) {
			unsigned char sha1[20];
			char *hex;
			int ret;
			ret = handle_file(path, sha1, NULL);
			if (ret < 1)
				continue;
			hex = xstrdup(sha1_to_hex(sha1));
			string_list_insert(rr, path)->util = hex;
			if (mkdir_in_gitdir(git_path("rr-cache/%s", hex)))
				continue;
			handle_file(path, NULL, rerere_path(hex, "preimage"));
			fprintf(stderr, "Recorded preimage for '%s'\n", path);
		}
	}

	/*
	 * Now some of the paths that had conflicts earlier might have been
	 * hand resolved.  Others may be similar to a conflict already that
	 * was resolved before.
	 */

	for (i = 0; i < rr->nr; i++) {
		int ret;
		const char *path = rr->items[i].string;
		const char *name = (const char *)rr->items[i].util;

		if (has_rerere_resolution(name)) {
			if (!merge(name, path)) {
				const char *msg;
				if (rerere_autoupdate) {
					string_list_insert(&update, path);
					msg = "Staged '%s' using previous resolution.\n";
				} else
					msg = "Resolved '%s' using previous resolution.\n";
				fprintf(stderr, msg, path);
				goto mark_resolved;
			}
		}

		/* Let's see if we have resolved it. */
		ret = handle_file(path, NULL, NULL);
		if (ret)
			continue;

		fprintf(stderr, "Recorded resolution for '%s'.\n", path);
		copy_file(rerere_path(name, "postimage"), path, 0666);
	mark_resolved:
		rr->items[i].util = NULL;
	}

	if (update.nr)
		update_paths(&update);

	return write_rr(rr, fd);
}

static void git_rerere_config(void)
{
	git_config_get_bool("rerere.enabled", &rerere_enabled);
	git_config_get_bool("rerere.autoupdate", &rerere_autoupdate);
	git_config(git_default_config, NULL);
}

static GIT_PATH_FUNC(git_path_rr_cache, "rr-cache")

static int is_rerere_enabled(void)
{
	int rr_cache_exists;

	if (!rerere_enabled)
		return 0;

	rr_cache_exists = is_directory(git_path_rr_cache());
	if (rerere_enabled < 0)
		return rr_cache_exists;

	if (!rr_cache_exists && mkdir_in_gitdir(git_path_rr_cache()))
		die("Could not create directory %s", git_path_rr_cache());
	return 1;
}

int setup_rerere(struct string_list *merge_rr, int flags)
{
	int fd;

	git_rerere_config();
	if (!is_rerere_enabled())
		return -1;

	if (flags & (RERERE_AUTOUPDATE|RERERE_NOAUTOUPDATE))
		rerere_autoupdate = !!(flags & RERERE_AUTOUPDATE);
	fd = hold_lock_file_for_update(&write_lock, git_path_merge_rr(),
				       LOCK_DIE_ON_ERROR);
	read_rr(merge_rr);
	return fd;
}

int rerere(int flags)
{
	struct string_list merge_rr = STRING_LIST_INIT_DUP;
	int fd;

	fd = setup_rerere(&merge_rr, flags);
	if (fd < 0)
		return 0;
	return do_plain_rerere(&merge_rr, fd);
}

static int rerere_forget_one_path(const char *path, struct string_list *rr)
{
	const char *filename;
	char *hex;
	unsigned char sha1[20];
	int ret;

	ret = handle_cache(path, sha1, NULL);
	if (ret < 1)
		return error("Could not parse conflict hunks in '%s'", path);
	hex = xstrdup(sha1_to_hex(sha1));
	filename = rerere_path(hex, "postimage");
	if (unlink(filename))
		return (errno == ENOENT
			? error("no remembered resolution for %s", path)
			: error("cannot unlink %s: %s", filename, strerror(errno)));

	handle_cache(path, sha1, rerere_path(hex, "preimage"));
	fprintf(stderr, "Updated preimage for '%s'\n", path);


	string_list_insert(rr, path)->util = hex;
	fprintf(stderr, "Forgot resolution for %s\n", path);
	return 0;
}

int rerere_forget(struct pathspec *pathspec)
{
	int i, fd;
	struct string_list conflict = STRING_LIST_INIT_DUP;
	struct string_list merge_rr = STRING_LIST_INIT_DUP;

	if (read_cache() < 0)
		return error("Could not read index");

	fd = setup_rerere(&merge_rr, RERERE_NOAUTOUPDATE);
	if (fd < 0)
		return 0;

	unmerge_cache(pathspec);
	find_conflict(&conflict);
	for (i = 0; i < conflict.nr; i++) {
		struct string_list_item *it = &conflict.items[i];
		if (!match_pathspec(pathspec, it->string,
				    strlen(it->string), 0, NULL, 0))
			continue;
		rerere_forget_one_path(it->string, &merge_rr);
	}
	return write_rr(&merge_rr, fd);
}

static time_t rerere_created_at(const char *name)
{
	struct stat st;
	return stat(rerere_path(name, "preimage"), &st) ? (time_t) 0 : st.st_mtime;
}

static time_t rerere_last_used_at(const char *name)
{
	struct stat st;
	return stat(rerere_path(name, "postimage"), &st) ? (time_t) 0 : st.st_mtime;
}

static void unlink_rr_item(const char *name)
{
	unlink(rerere_path(name, "thisimage"));
	unlink(rerere_path(name, "preimage"));
	unlink(rerere_path(name, "postimage"));
	rmdir(git_path("rr-cache/%s", name));
}

void rerere_gc(struct string_list *rr)
{
	struct string_list to_remove = STRING_LIST_INIT_DUP;
	DIR *dir;
	struct dirent *e;
	int i, cutoff;
	time_t now = time(NULL), then;
	int cutoff_noresolve = 15;
	int cutoff_resolve = 60;

	git_config_get_int("gc.rerereresolved", &cutoff_resolve);
	git_config_get_int("gc.rerereunresolved", &cutoff_noresolve);
	git_config(git_default_config, NULL);
	dir = opendir(git_path("rr-cache"));
	if (!dir)
		die_errno("unable to open rr-cache directory");
	while ((e = readdir(dir))) {
		if (is_dot_or_dotdot(e->d_name))
			continue;

		then = rerere_last_used_at(e->d_name);
		if (then) {
			cutoff = cutoff_resolve;
		} else {
			then = rerere_created_at(e->d_name);
			if (!then)
				continue;
			cutoff = cutoff_noresolve;
		}
		if (then < now - cutoff * 86400)
			string_list_append(&to_remove, e->d_name);
	}
	closedir(dir);
	for (i = 0; i < to_remove.nr; i++)
		unlink_rr_item(to_remove.items[i].string);
	string_list_clear(&to_remove, 0);
}

void rerere_clear(struct string_list *merge_rr)
{
	int i;

	for (i = 0; i < merge_rr->nr; i++) {
		const char *name = (const char *)merge_rr->items[i].util;
		if (!has_rerere_resolution(name))
			unlink_rr_item(name);
	}
	unlink_or_warn(git_path_merge_rr());
}