Merge branch 'js/rerere'

* js/rerere:
  Make git-rerere a builtin
  Add a test for git-rerere
  move read_mmfile() into xdiff-interface

8 files changed, 585 insertions, 19 deletions

diff --git a/Makefile b/Makefile
index d56970c56..8827dee59 100644
--- a/Makefile
+++ b/Makefile
@@ -171,7 +171,6 @@ SCRIPT_SH = \
 
 SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
-	git-rerere.perl \
 	git-cvsserver.perl \
 	git-svnimport.perl git-cvsexportcommit.perl \
 	git-send-email.perl git-svn.perl
@@ -288,6 +287,7 @@ BUILTIN_OBJS = \
 	builtin-push.o \
 	builtin-read-tree.o \
 	builtin-repo-config.o \
+	builtin-rerere.o \
 	builtin-rev-list.o \
 	builtin-rev-parse.o \
 	builtin-rm.o \
diff --git a/builtin-merge-file.c b/builtin-merge-file.c
index 6c4c3a351..913577390 100644
--- a/builtin-merge-file.c
+++ b/builtin-merge-file.c
@@ -1,26 +1,10 @@
 #include "cache.h"
 #include "xdiff/xdiff.h"
+#include "xdiff-interface.h"
 
 static const char merge_file_usage[] =
 "git merge-file [-p | --stdout] [-q | --quiet] [-L name1 [-L orig [-L name2]]] file1 orig_file file2";
 
-static int read_file(mmfile_t *ptr, const char *filename)
-{
-	struct stat st;
-	FILE *f;
-
-	if (stat(filename, &st))
-		return error("Could not stat %s", filename);
-	if ((f = fopen(filename, "rb")) == NULL)
-		return error("Could not open %s", filename);
-	ptr->ptr = xmalloc(st.st_size);
-	if (fread(ptr->ptr, st.st_size, 1, f) != 1)
-		return error("Could not read %s", filename);
-	fclose(f);
-	ptr->size = st.st_size;
-	return 0;
-}
-
 int cmd_merge_file(int argc, char **argv, char **envp)
 {
 	char *names[3];
@@ -53,7 +37,7 @@ int cmd_merge_file(int argc, char **argv, char **envp)
 		names[i] = argv[i + 1];
 
 	for (i = 0; i < 3; i++)
-		if (read_file(mmfs + i, argv[i + 1]))
+		if (read_mmfile(mmfs + i, argv[i + 1]))
 			return -1;
 
 	ret = xdl_merge(mmfs + 1, mmfs + 0, names[0], mmfs + 2, names[2],
diff --git a/builtin-rerere.c b/builtin-rerere.c
new file mode 100644
index 000000000..d064bd8bf
--- /dev/null
+++ b/builtin-rerere.c
@@ -0,0 +1,406 @@
+#include "cache.h"
+#include "path-list.h"
+#include "xdiff/xdiff.h"
+#include "xdiff-interface.h"
+
+#include <time.h>
+
+static const char git_rerere_usage[] =
+"git-rerere [clear | status | diff | gc]";
+
+/* these values are days */
+static int cutoff_noresolve = 15;
+static int cutoff_resolve = 60;
+
+static char *merge_rr_path;
+
+static const char *rr_path(const char *name, const char *file)
+{
+	return git_path("rr-cache/%s/%s", name, file);
+}
+
+static void read_rr(struct path_list *rr)
+{
+	unsigned char sha1[20];
+	char buf[PATH_MAX];
+	FILE *in = fopen(merge_rr_path, "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) && (buf[i] = fgetc(in)); i++)
+			; /* do nothing */
+		if (i == sizeof(buf))
+			die("filename too long");
+		path_list_insert(buf, rr)->util = xstrdup(name);
+	}
+	fclose(in);
+}
+
+static struct lock_file write_lock;
+
+static int write_rr(struct path_list *rr, int out_fd)
+{
+	int i;
+	for (i = 0; i < rr->nr; i++) {
+		const char *path = rr->items[i].path;
+		write(out_fd, rr->items[i].util, 40);
+		write(out_fd, "\t", 1);
+		write(out_fd, path, strlen(path) + 1);
+	}
+	close(out_fd);
+	return commit_lock_file(&write_lock);
+}
+
+struct buffer {
+	char *ptr;
+	int nr, alloc;
+};
+
+static void append_line(struct buffer *buffer, const char *line)
+{
+	int len = strlen(line);
+
+	if (buffer->nr + len > buffer->alloc) {
+		buffer->alloc = alloc_nr(buffer->nr + len);
+		buffer->ptr = xrealloc(buffer->ptr, buffer->alloc);
+	}
+	memcpy(buffer->ptr + buffer->nr, line, len);
+	buffer->nr += len;
+}
+
+static int handle_file(const char *path,
+	 unsigned char *sha1, const char *output)
+{
+	SHA_CTX ctx;
+	char buf[1024];
+	int hunk = 0, hunk_no = 0;
+	struct buffer minus = { NULL, 0, 0 }, plus = { NULL, 0, 0 };
+	struct buffer *one = &minus, *two = &plus;
+	FILE *f = fopen(path, "r");
+	FILE *out;
+
+	if (!f)
+		return error("Could not open %s", path);
+
+	if (output) {
+		out = fopen(output, "w");
+		if (!out) {
+			fclose(f);
+			return error("Could not write %s", output);
+		}
+	} else
+		out = NULL;
+
+	if (sha1)
+		SHA1_Init(&ctx);
+
+	while (fgets(buf, sizeof(buf), f)) {
+		if (!strncmp("<<<<<<< ", buf, 8))
+			hunk = 1;
+		else if (!strncmp("=======", buf, 7))
+			hunk = 2;
+		else if (!strncmp(">>>>>>> ", buf, 8)) {
+			hunk_no++;
+			hunk = 0;
+			if (memcmp(one->ptr, two->ptr, one->nr < two->nr ?
+						one->nr : two->nr) > 0) {
+				struct buffer *swap = one;
+				one = two;
+				two = swap;
+			}
+			if (out) {
+				fputs("<<<<<<<\n", out);
+				fwrite(one->ptr, one->nr, 1, out);
+				fputs("=======\n", out);
+				fwrite(two->ptr, two->nr, 1, out);
+				fputs(">>>>>>>\n", out);
+			}
+			if (sha1) {
+				SHA1_Update(&ctx, one->ptr, one->nr);
+				SHA1_Update(&ctx, "\0", 1);
+				SHA1_Update(&ctx, two->ptr, two->nr);
+				SHA1_Update(&ctx, "\0", 1);
+			}
+		} else if (hunk == 1)
+			append_line(one, buf);
+		else if (hunk == 2)
+			append_line(two, buf);
+		else if (out)
+			fputs(buf, out);
+	}
+
+	fclose(f);
+	if (out)
+		fclose(out);
+	if (sha1)
+		SHA1_Final(sha1, &ctx);
+	return hunk_no;
+}
+
+static int find_conflict(struct path_list *conflict)
+{
+	int i;
+	if (read_cache() < 0)
+		return error("Could not read index");
+	for (i = 0; i + 2 < active_nr; i++) {
+		struct cache_entry *e1 = active_cache[i];
+		struct cache_entry *e2 = active_cache[i + 1];
+		struct cache_entry *e3 = active_cache[i + 2];
+		if (ce_stage(e1) == 1 && ce_stage(e2) == 2 &&
+				ce_stage(e3) == 3 && ce_same_name(e1, e2) &&
+				ce_same_name(e1, e3)) {
+			path_list_insert((const char *)e1->name, conflict);
+			i += 3;
+		}
+	}
+	return 0;
+}
+
+static int merge(const char *name, const char *path)
+{
+	int ret;
+	mmfile_t cur, base, other;
+	mmbuffer_t result = {NULL, 0};
+	xpparam_t xpp = {XDF_NEED_MINIMAL};
+
+	if (handle_file(path, NULL, rr_path(name, "thisimage")) < 0)
+		return 1;
+
+	if (read_mmfile(&cur, rr_path(name, "thisimage")) ||
+			read_mmfile(&base, rr_path(name, "preimage")) ||
+			read_mmfile(&other, rr_path(name, "postimage")))
+		return 1;
+	ret = xdl_merge(&base, &cur, "", &other, "",
+			&xpp, XDL_MERGE_ZEALOUS, &result);
+	if (!ret) {
+		FILE *f = fopen(path, "w");
+		if (!f)
+			return error("Could not write to %s", path);
+		fwrite(result.ptr, result.size, 1, f);
+		fclose(f);
+	}
+
+	free(cur.ptr);
+	free(base.ptr);
+	free(other.ptr);
+	free(result.ptr);
+
+	return ret;
+}
+
+static void unlink_rr_item(const char *name)
+{
+	unlink(rr_path(name, "thisimage"));
+	unlink(rr_path(name, "preimage"));
+	unlink(rr_path(name, "postimage"));
+	rmdir(git_path("rr-cache/%s", name));
+}
+
+static void garbage_collect(struct path_list *rr)
+{
+	struct path_list to_remove = { NULL, 0, 0, 1 };
+	char buf[1024];
+	DIR *dir;
+	struct dirent *e;
+	int len, i, cutoff;
+	time_t now = time(NULL), then;
+
+	strlcpy(buf, git_path("rr-cache"), sizeof(buf));
+	len = strlen(buf);
+	dir = opendir(buf);
+	strcpy(buf + len++, "/");
+	while ((e = readdir(dir))) {
+		const char *name = e->d_name;
+		struct stat st;
+		if (name[0] == '.' && (name[1] == '\0' ||
+					(name[1] == '.' && name[2] == '\0')))
+			continue;
+		i = snprintf(buf + len, sizeof(buf) - len, "%s", name);
+		strlcpy(buf + len + i, "/preimage", sizeof(buf) - len - i);
+		if (stat(buf, &st))
+			continue;
+		then = st.st_mtime;
+		strlcpy(buf + len + i, "/postimage", sizeof(buf) - len - i);
+		cutoff = stat(buf, &st) ? cutoff_noresolve : cutoff_resolve;
+		if (then < now - cutoff * 86400) {
+			buf[len + i] = '\0';
+			path_list_insert(xstrdup(name), &to_remove);
+		}
+	}
+	for (i = 0; i < to_remove.nr; i++)
+		unlink_rr_item(to_remove.items[i].path);
+	path_list_clear(&to_remove, 0);
+}
+
+static int outf(void *dummy, mmbuffer_t *ptr, int nbuf)
+{
+	int i;
+	for (i = 0; i < nbuf; i++)
+		write(1, ptr[i].ptr, ptr[i].size);
+	return 0;
+}
+
+static int diff_two(const char *file1, const char *label1,
+		const char *file2, const char *label2)
+{
+	xpparam_t xpp;
+	xdemitconf_t xecfg;
+	xdemitcb_t ecb;
+	mmfile_t minus, plus;
+
+	if (read_mmfile(&minus, file1) || read_mmfile(&plus, file2))
+		return 1;
+
+	printf("--- a/%s\n+++ b/%s\n", label1, label2);
+	fflush(stdout);
+	xpp.flags = XDF_NEED_MINIMAL;
+	xecfg.ctxlen = 3;
+	xecfg.flags = 0;
+	ecb.outf = outf;
+	xdl_diff(&minus, &plus, &xpp, &xecfg, &ecb);
+
+	free(minus.ptr);
+	free(plus.ptr);
+	return 0;
+}
+
+static int copy_file(const char *src, const char *dest)
+{
+	FILE *in, *out;
+	char buffer[32768];
+	int count;
+
+	if (!(in = fopen(src, "r")))
+		return error("Could not open %s", src);
+	if (!(out = fopen(dest, "w")))
+		return error("Could not open %s", dest);
+	while ((count = fread(buffer, 1, sizeof(buffer), in)))
+		fwrite(buffer, 1, count, out);
+	fclose(in);
+	fclose(out);
+	return 0;
+}
+
+static int do_plain_rerere(struct path_list *rr, int fd)
+{
+	struct path_list conflict = { NULL, 0, 0, 1 };
+	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].path;
+		if (!path_list_has_path(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));
+			path_list_insert(path, rr)->util = hex;
+			if (mkdir(git_path("rr-cache/%s", hex), 0755))
+				continue;;
+			handle_file(path, NULL, rr_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++) {
+		struct stat st;
+		int ret;
+		const char *path = rr->items[i].path;
+		const char *name = (const char *)rr->items[i].util;
+
+		if (!stat(rr_path(name, "preimage"), &st) &&
+				!stat(rr_path(name, "postimage"), &st)) {
+			if (!merge(name, path)) {
+				fprintf(stderr, "Resolved '%s' using "
+						"previous resolution.\n", path);
+				goto tail_optimization;
+			}
+		}
+
+		/* 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(path, rr_path(name, "postimage"));
+tail_optimization:
+		if (i < rr->nr - 1) {
+			memmove(rr->items + i,
+					rr->items + i + 1,
+					rr->nr - i - 1);
+		}
+		rr->nr--;
+		i--;
+	}
+
+	return write_rr(rr, fd);
+}
+
+int cmd_rerere(int argc, const char **argv, const char *prefix)
+{
+	struct path_list merge_rr = { NULL, 0, 0, 1 };
+	int i, fd = -1;
+	struct stat st;
+
+	if (stat(git_path("rr-cache"), &st) || !S_ISDIR(st.st_mode))
+		return 0;
+
+	merge_rr_path = xstrdup(git_path("rr-cache/MERGE_RR"));
+	fd = hold_lock_file_for_update(&write_lock, merge_rr_path, 1);
+	read_rr(&merge_rr);
+
+	if (argc < 2)
+		return do_plain_rerere(&merge_rr, fd);
+	else if (!strcmp(argv[1], "clear")) {
+		for (i = 0; i < merge_rr.nr; i++) {
+			const char *name = (const char *)merge_rr.items[i].util;
+			if (!stat(git_path("rr-cache/%s", name), &st) &&
+					S_ISDIR(st.st_mode) &&
+					stat(rr_path(name, "postimage"), &st))
+				unlink_rr_item(name);
+		}
+		unlink(merge_rr_path);
+	} else if (!strcmp(argv[1], "gc"))
+		garbage_collect(&merge_rr);
+	else if (!strcmp(argv[1], "status"))
+		for (i = 0; i < merge_rr.nr; i++)
+			printf("%s\n", merge_rr.items[i].path);
+	else if (!strcmp(argv[1], "diff"))
+		for (i = 0; i < merge_rr.nr; i++) {
+			const char *path = merge_rr.items[i].path;
+			const char *name = (const char *)merge_rr.items[i].util;
+			diff_two(rr_path(name, "preimage"), path, path, path);
+		}
+	else
+		usage(git_rerere_usage);
+
+	path_list_clear(&merge_rr, 1);
+	return 0;
+}
+
diff --git a/builtin.h b/builtin.h
index 08519e7c8..8ffd8b265 100644
--- a/builtin.h
+++ b/builtin.h
@@ -52,6 +52,7 @@ extern int cmd_prune_packed(int argc, const char **argv, const char *prefix);
 extern int cmd_push(int argc, const char **argv, const char *prefix);
 extern int cmd_read_tree(int argc, const char **argv, const char *prefix);
 extern int cmd_repo_config(int argc, const char **argv, const char *prefix);
+extern int cmd_rerere(int argc, const char **argv, const char *prefix);
 extern int cmd_rev_list(int argc, const char **argv, const char *prefix);
 extern int cmd_rev_parse(int argc, const char **argv, const char *prefix);
 extern int cmd_rm(int argc, const char **argv, const char *prefix);
diff --git a/git.c b/git.c
index 7bb61d837..e732a098f 100644
--- a/git.c
+++ b/git.c
@@ -247,6 +247,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "push", cmd_push, RUN_SETUP },
 		{ "read-tree", cmd_read_tree, RUN_SETUP },
 		{ "repo-config", cmd_repo_config },
+		{ "rerere", cmd_rerere, RUN_SETUP },
 		{ "rev-list", cmd_rev_list, RUN_SETUP },
 		{ "rev-parse", cmd_rev_parse, RUN_SETUP },
 		{ "rm", cmd_rm, RUN_SETUP },
diff --git a/t/t4200-rerere.sh b/t/t4200-rerere.sh
new file mode 100755
index 000000000..5ee5b2309
--- /dev/null
+++ b/t/t4200-rerere.sh
@@ -0,0 +1,154 @@
+#!/bin/sh
+#
+# Copyright (c) 2006 Johannes E. Schindelin
+#
+
+test_description='git-rerere
+'
+
+. ./test-lib.sh
+
+cat > a1 << EOF
+Whether 'tis nobler in the mind to suffer
+The slings and arrows of outrageous fortune,
+Or to take arms against a sea of troubles,
+And by opposing end them? To die: to sleep;
+No more; and by a sleep to say we end
+The heart-ache and the thousand natural shocks
+That flesh is heir to, 'tis a consummation
+Devoutly to be wish'd.
+EOF
+
+git add a1
+git commit -q -a -m initial
+
+git checkout -b first
+cat >> a1 << EOF
+To die, to sleep;
+To sleep: perchance to dream: ay, there's the rub;
+For in that sleep of death what dreams may come
+When we have shuffled off this mortal coil,
+Must give us pause: there's the respect
+That makes calamity of so long life;
+EOF
+git commit -q -a -m first
+
+git checkout -b second master
+git show first:a1 | sed 's/To die, t/To die! T/' > a1
+git commit -q -a -m second
+
+# activate rerere
+mkdir .git/rr-cache
+
+test_expect_failure 'conflicting merge' 'git pull . first'
+
+sha1=4f58849a60b4f969a2848966b6d02893b783e8fb
+rr=.git/rr-cache/$sha1
+test_expect_success 'recorded preimage' "grep ======= $rr/preimage"
+
+test_expect_success 'no postimage or thisimage yet' \
+	"test ! -f $rr/postimage -a ! -f $rr/thisimage"
+
+git show first:a1 > a1
+
+cat > expect << EOF
+--- a/a1
++++ b/a1
+@@ -6,11 +6,7 @@
+ The heart-ache and the thousand natural shocks
+ That flesh is heir to, 'tis a consummation
+ Devoutly to be wish'd.
+-<<<<<<<
+-To die! To sleep;
+-=======
+ To die, to sleep;
+->>>>>>>
+ To sleep: perchance to dream: ay, there's the rub;
+ For in that sleep of death what dreams may come
+ When we have shuffled off this mortal coil,
+EOF
+
+git rerere diff > out
+
+test_expect_success 'rerere diff' 'diff -u expect out'
+
+cat > expect << EOF
+a1
+EOF
+
+git rerere status > out
+
+test_expect_success 'rerere status' 'diff -u expect out'
+
+test_expect_success 'commit succeeds' \
+	"git commit -q -a -m 'prefer first over second'"
+
+test_expect_success 'recorded postimage' "test -f $rr/postimage"
+
+git checkout -b third master
+git show second^:a1 | sed 's/To die: t/To die! T/' > a1
+git commit -q -a -m third
+
+test_expect_failure 'another conflicting merge' 'git pull . first'
+
+git show first:a1 | sed 's/To die: t/To die! T/' > expect
+test_expect_success 'rerere kicked in' "! grep ======= a1"
+
+test_expect_success 'rerere prefers first change' 'diff -u a1 expect'
+
+rm $rr/postimage
+echo "$sha1	a1" | tr '\012' '\0' > .git/rr-cache/MERGE_RR
+
+test_expect_success 'rerere clear' 'git rerere clear'
+
+test_expect_success 'clear removed the directory' "test ! -d $rr"
+
+mkdir $rr
+echo Hello > $rr/preimage
+echo World > $rr/postimage
+
+sha2=4000000000000000000000000000000000000000
+rr2=.git/rr-cache/$sha2
+mkdir $rr2
+echo Hello > $rr2/preimage
+
+case "$(date -d @11111111 +%s 2>/dev/null)" in
+[1-9]*)
+	# it is a recent GNU date. good.
+	now=$(date +%s)
+	almost_15_days_ago=$(($now+60-15*86400))
+	just_over_15_days_ago=$(($now-1-15*86400))
+	almost_60_days_ago=$(($now+60-60*86400))
+	just_over_60_days_ago=$(($now-1-60*86400))
+	predate1="$(date -d "@$almost_60_days_ago" +%c)"
+	predate2="$(date -d "@$almost_15_days_ago" +%c)"
+	postdate1="$(date -d "@$just_over_60_days_ago" +%c)"
+	postdate2="$(date -d "@$just_over_15_days_ago" +%c)"
+	;;
+*)
+	# it is not GNU date. oh, well.
+	predate1="$(date)"
+	predate2="$(date)"
+	postdate1='1 Oct 2006 00:00:00'
+	postdate2='1 Dec 2006 00:00:00'
+esac
+
+touch -m -d "$predate1" $rr/preimage
+touch -m -d "$predate2" $rr2/preimage
+
+test_expect_success 'garbage collection (part1)' 'git rerere gc'
+
+test_expect_success 'young records still live' \
+	"test -f $rr/preimage -a -f $rr2/preimage"
+
+touch -m -d "$postdate1" $rr/preimage
+touch -m -d "$postdate2" $rr2/preimage
+
+test_expect_success 'garbage collection (part2)' 'git rerere gc'
+
+test_expect_success 'old records rest in peace' \
+	"test ! -f $rr/preimage -a ! -f $rr2/preimage"
+
+test_done
+
+
diff --git a/xdiff-interface.c b/xdiff-interface.c
index 08602f522..6c1f99b14 100644
--- a/xdiff-interface.c
+++ b/xdiff-interface.c
@@ -102,3 +102,22 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf)
 	}
 	return 0;
 }
+
+int read_mmfile(mmfile_t *ptr, const char *filename)
+{
+	struct stat st;
+	FILE *f;
+
+	if (stat(filename, &st))
+		return error("Could not stat %s", filename);
+	if ((f = fopen(filename, "rb")) == NULL)
+		return error("Could not open %s", filename);
+	ptr->ptr = xmalloc(st.st_size);
+	if (fread(ptr->ptr, st.st_size, 1, f) != 1)
+		return error("Could not read %s", filename);
+	fclose(f);
+	ptr->size = st.st_size;
+	return 0;
+}
+
+
diff --git a/xdiff-interface.h b/xdiff-interface.h
index 1346908be..191880808 100644
--- a/xdiff-interface.h
+++ b/xdiff-interface.h
@@ -17,5 +17,6 @@ int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf);
 int parse_hunk_header(char *line, int len,
 		      int *ob, int *on,
 		      int *nb, int *nn);
+int read_mmfile(mmfile_t *ptr, const char *filename);
 
 #endif