Merge branch 'lt/merge-tree'

* lt/merge-tree:
  Improved three-way blob merging code
  Prepare "git-merge-tree" for future work
  xdiff: generate "anti-diffs" aka what is common to two files

5 files changed, 378 insertions, 16 deletions

diff --git a/Makefile b/Makefile
index e75fb133a..649ed4cdc 100644
--- a/Makefile
+++ b/Makefile
@@ -222,7 +222,7 @@ LIB_OBJS = \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	fetch-clone.o revision.o pager.o tree-walk.o xdiff-interface.o \
-	alloc.o $(DIFF_OBJS)
+	alloc.o merge-file.o $(DIFF_OBJS)
 
 BUILTIN_OBJS = \
 	builtin-log.o builtin-help.o builtin-count.o builtin-diff.o builtin-push.o \
diff --git a/merge-file.c b/merge-file.c
new file mode 100644
index 000000000..f32c65382
--- /dev/null
+++ b/merge-file.c
@@ -0,0 +1,166 @@
+#include "cache.h"
+#include "run-command.h"
+#include "xdiff-interface.h"
+#include "blob.h"
+
+static void rm_temp_file(const char *filename)
+{
+	unlink(filename);
+	free((void *)filename);
+}
+
+static const char *write_temp_file(mmfile_t *f)
+{
+	int fd;
+	const char *tmp = getenv("TMPDIR");
+	char *filename;
+
+	if (!tmp)
+		tmp = "/tmp";
+	filename = mkpath("%s/%s", tmp, "git-tmp-XXXXXX");
+	fd = mkstemp(filename);
+	if (fd < 0)
+		return NULL;
+	filename = strdup(filename);
+	if (f->size != xwrite(fd, f->ptr, f->size)) {
+		rm_temp_file(filename);
+		return NULL;
+	}
+	close(fd);
+	return filename;
+}
+
+static void *read_temp_file(const char *filename, unsigned long *size)
+{
+	struct stat st;
+	char *buf = NULL;
+	int fd = open(filename, O_RDONLY);
+	if (fd < 0)
+		return NULL;
+	if (!fstat(fd, &st)) {
+		*size = st.st_size;
+		buf = xmalloc(st.st_size);
+		if (st.st_size != xread(fd, buf, st.st_size)) {
+			free(buf);
+			buf = NULL;
+		}
+	}
+	close(fd);
+	return buf;
+}
+
+static int fill_mmfile_blob(mmfile_t *f, struct blob *obj)
+{
+	void *buf;
+	unsigned long size;
+	char type[20];
+
+	buf = read_sha1_file(obj->object.sha1, type, &size);
+	if (!buf)
+		return -1;
+	if (strcmp(type, blob_type))
+		return -1;
+	f->ptr = buf;
+	f->size = size;
+	return 0;
+}
+
+static void free_mmfile(mmfile_t *f)
+{
+	free(f->ptr);
+}
+
+static void *three_way_filemerge(mmfile_t *base, mmfile_t *our, mmfile_t *their, unsigned long *size)
+{
+	void *res;
+	const char *t1, *t2, *t3;
+
+	t1 = write_temp_file(base);
+	t2 = write_temp_file(our);
+	t3 = write_temp_file(their);
+	res = NULL;
+	if (t1 && t2 && t3) {
+		int code = run_command("merge", t2, t1, t3, NULL);
+		if (!code || code == -1)
+			res = read_temp_file(t2, size);
+	}
+	rm_temp_file(t1);
+	rm_temp_file(t2);
+	rm_temp_file(t3);
+	return res;
+}
+
+static int common_outf(void *priv_, mmbuffer_t *mb, int nbuf)
+{
+	int i;
+	mmfile_t *dst = priv_;
+
+	for (i = 0; i < nbuf; i++) {
+		memcpy(dst->ptr + dst->size, mb[i].ptr, mb[i].size);
+		dst->size += mb[i].size;
+	}
+	return 0;
+}
+
+static int generate_common_file(mmfile_t *res, mmfile_t *f1, mmfile_t *f2)
+{
+	unsigned long size = f1->size < f2->size ? f1->size : f2->size;
+	void *ptr = xmalloc(size);
+	xpparam_t xpp;
+	xdemitconf_t xecfg;
+	xdemitcb_t ecb;
+
+	xpp.flags = XDF_NEED_MINIMAL;
+	xecfg.ctxlen = 3;
+	xecfg.flags = XDL_EMIT_COMMON;
+	ecb.outf = common_outf;
+
+	res->ptr = ptr;
+	res->size = 0;
+
+	ecb.priv = res;
+	return xdl_diff(f1, f2, &xpp, &xecfg, &ecb);
+}
+
+void *merge_file(struct blob *base, struct blob *our, struct blob *their, unsigned long *size)
+{
+	void *res = NULL;
+	mmfile_t f1, f2, common;
+
+	/*
+	 * Removed in either branch?
+	 *
+	 * NOTE! This depends on the caller having done the
+	 * proper warning about removing a file that got
+	 * modified in the other branch!
+	 */
+	if (!our || !their) {
+		char type[20];
+		if (base)
+			return NULL;
+		if (!our)
+			our = their;
+		return read_sha1_file(our->object.sha1, type, size);
+	}
+
+	if (fill_mmfile_blob(&f1, our) < 0)
+		goto out_no_mmfile;
+	if (fill_mmfile_blob(&f2, their) < 0)
+		goto out_free_f1;
+
+	if (base) {
+		if (fill_mmfile_blob(&common, base) < 0)
+			goto out_free_f2_f1;
+	} else {
+		if (generate_common_file(&common, &f1, &f2) < 0)
+			goto out_free_f2_f1;
+	}
+	res = three_way_filemerge(&common, &f1, &f2, size);
+	free_mmfile(&common);
+out_free_f2_f1:
+	free_mmfile(&f2);
+out_free_f1:
+	free_mmfile(&f1);
+out_no_mmfile:
+	return res;
+}
diff --git a/merge-tree.c b/merge-tree.c
index 9dcaab7a8..7cf00be6d 100644
--- a/merge-tree.c
+++ b/merge-tree.c
@@ -1,11 +1,152 @@
 #include "cache.h"
 #include "tree-walk.h"
+#include "xdiff-interface.h"
+#include "blob.h"
 
 static const char merge_tree_usage[] = "git-merge-tree <base-tree> <branch1> <branch2>";
 static int resolve_directories = 1;
 
+struct merge_list {
+	struct merge_list *next;
+	struct merge_list *link;	/* other stages for this object */
+
+	unsigned int stage : 2,
+		     flags : 30;
+	unsigned int mode;
+	const char *path;
+	struct blob *blob;
+};
+
+static struct merge_list *merge_result, **merge_result_end = &merge_result;
+
+static void add_merge_entry(struct merge_list *entry)
+{
+	*merge_result_end = entry;
+	merge_result_end = &entry->next;
+}
+
 static void merge_trees(struct tree_desc t[3], const char *base);
 
+static const char *explanation(struct merge_list *entry)
+{
+	switch (entry->stage) {
+	case 0:
+		return "merged";
+	case 3:
+		return "added in remote";
+	case 2:
+		if (entry->link)
+			return "added in both";
+		return "added in local";
+	}
+
+	/* Existed in base */
+	entry = entry->link;
+	if (!entry)
+		return "removed in both";
+
+	if (entry->link)
+		return "changed in both";
+
+	if (entry->stage == 3)
+		return "removed in local";
+	return "removed in remote";
+}
+
+extern void *merge_file(struct blob *, struct blob *, struct blob *, unsigned long *);
+
+static void *result(struct merge_list *entry, unsigned long *size)
+{
+	char type[20];
+	struct blob *base, *our, *their;
+
+	if (!entry->stage)
+		return read_sha1_file(entry->blob->object.sha1, type, size);
+	base = NULL;
+	if (entry->stage == 1) {
+		base = entry->blob;
+		entry = entry->link;
+	}
+	our = NULL;
+	if (entry && entry->stage == 2) {
+		our = entry->blob;
+		entry = entry->link;
+	}
+	their = NULL;
+	if (entry)
+		their = entry->blob;
+	return merge_file(base, our, their, size);
+}
+
+static void *origin(struct merge_list *entry, unsigned long *size)
+{
+	char type[20];
+	while (entry) {
+		if (entry->stage == 2)
+			return read_sha1_file(entry->blob->object.sha1, type, size);
+		entry = entry->link;
+	}
+	return NULL;
+}
+
+static int show_outf(void *priv_, mmbuffer_t *mb, int nbuf)
+{
+	int i;
+	for (i = 0; i < nbuf; i++)
+		printf("%.*s", (int) mb[i].size, mb[i].ptr);
+	return 0;
+}
+
+static void show_diff(struct merge_list *entry)
+{
+	unsigned long size;
+	mmfile_t src, dst;
+	xpparam_t xpp;
+	xdemitconf_t xecfg;
+	xdemitcb_t ecb;
+
+	xpp.flags = XDF_NEED_MINIMAL;
+	xecfg.ctxlen = 3;
+	xecfg.flags = 0;
+	ecb.outf = show_outf;
+	ecb.priv = NULL;
+
+	src.ptr = origin(entry, &size);
+	if (!src.ptr)
+		size = 0;
+	src.size = size;
+	dst.ptr = result(entry, &size);
+	if (!dst.ptr)
+		size = 0;
+	dst.size = size;
+	xdl_diff(&src, &dst, &xpp, &xecfg, &ecb);
+	free(src.ptr);
+	free(dst.ptr);
+}
+
+static void show_result_list(struct merge_list *entry)
+{
+	printf("%s\n", explanation(entry));
+	do {
+		struct merge_list *link = entry->link;
+		static const char *desc[4] = { "result", "base", "our", "their" };
+		printf("  %-6s %o %s %s\n", desc[entry->stage], entry->mode, sha1_to_hex(entry->blob->object.sha1), entry->path);
+		entry = link;
+	} while (entry);
+}
+
+static void show_result(void)
+{
+	struct merge_list *walk;
+
+	walk = merge_result;
+	while (walk) {
+		show_result_list(walk);
+		show_diff(walk);
+		walk = walk->next;
+	}
+}
+
 /* An empty entry never compares same, not even to another empty entry */
 static int same_entry(struct name_entry *a, struct name_entry *b)
 {
@@ -15,24 +156,34 @@ static int same_entry(struct name_entry *a, struct name_entry *b)
 		a->mode == b->mode;
 }
 
-static const char *sha1_to_hex_zero(const unsigned char *sha1)
+static struct merge_list *create_entry(unsigned stage, unsigned mode, const unsigned char *sha1, const char *path)
 {
-	if (sha1)
-		return sha1_to_hex(sha1);
-	return "0000000000000000000000000000000000000000";
+	struct merge_list *res = xmalloc(sizeof(*res));
+
+	memset(res, 0, sizeof(*res));
+	res->stage = stage;
+	res->path = path;
+	res->mode = mode;
+	res->blob = lookup_blob(sha1);
+	return res;
 }
 
 static void resolve(const char *base, struct name_entry *branch1, struct name_entry *result)
 {
+	struct merge_list *orig, *final;
+	const char *path;
+
 	/* If it's already branch1, don't bother showing it */
 	if (!branch1)
 		return;
 
-	printf("0 %06o->%06o %s->%s %s%s\n",
-		branch1->mode, result->mode,
-		sha1_to_hex_zero(branch1->sha1),
-		sha1_to_hex_zero(result->sha1),
-		base, result->path);
+	path = strdup(mkpath("%s%s", base, result->path));
+	orig = create_entry(2, branch1->mode, branch1->sha1, path);
+	final = create_entry(0, result->mode, result->sha1, path);
+
+	final->link = orig;
+
+	add_merge_entry(final);
 }
 
 static int unresolved_directory(const char *base, struct name_entry n[3])
@@ -71,16 +222,40 @@ static int unresolved_directory(const char *base, struct name_entry n[3])
 	return 1;
 }
 
+
+static struct merge_list *link_entry(unsigned stage, const char *base, struct name_entry *n, struct merge_list *entry)
+{
+	const char *path;
+	struct merge_list *link;
+
+	if (!n->mode)
+		return entry;
+	if (entry)
+		path = entry->path;
+	else
+		path = strdup(mkpath("%s%s", base, n->path));
+	link = create_entry(stage, n->mode, n->sha1, path);
+	link->link = entry;
+	return link;
+}
+
 static void unresolved(const char *base, struct name_entry n[3])
 {
+	struct merge_list *entry = NULL;
+
 	if (unresolved_directory(base, n))
 		return;
-	if (n[0].sha1)
-		printf("1 %06o %s %s%s\n", n[0].mode, sha1_to_hex(n[0].sha1), base, n[0].path);
-	if (n[1].sha1)
-		printf("2 %06o %s %s%s\n", n[1].mode, sha1_to_hex(n[1].sha1), base, n[1].path);
-	if (n[2].sha1)
-		printf("3 %06o %s %s%s\n", n[2].mode, sha1_to_hex(n[2].sha1), base, n[2].path);
+
+	/*
+	 * Do them in reverse order so that the resulting link
+	 * list has the stages in order - link_entry adds new
+	 * links at the front.
+	 */
+	entry = link_entry(3, base, n + 2, entry);
+	entry = link_entry(2, base, n + 1, entry);
+	entry = link_entry(1, base, n + 0, entry);
+
+	add_merge_entry(entry);
 }
 
 /*
@@ -172,5 +347,7 @@ int main(int argc, char **argv)
 	free(buf1);
 	free(buf2);
 	free(buf3);
+
+	show_result();
 	return 0;
 }
diff --git a/xdiff/xdiff.h b/xdiff/xdiff.h
index 2ce10b4c0..c9f817818 100644
--- a/xdiff/xdiff.h
+++ b/xdiff/xdiff.h
@@ -39,6 +39,7 @@ extern "C" {
 #define XDL_PATCH_IGNOREBSPACE (1 << 8)
 
 #define XDL_EMIT_FUNCNAMES (1 << 0)
+#define XDL_EMIT_COMMON (1 << 1)
 
 #define XDL_MMB_READONLY (1 << 0)
 
diff --git a/xdiff/xemit.c b/xdiff/xemit.c
index ad5bfb191..714c56354 100644
--- a/xdiff/xemit.c
+++ b/xdiff/xemit.c
@@ -100,6 +100,21 @@ static void xdl_find_func(xdfile_t *xf, long i, char *buf, long sz, long *ll) {
 }
 
 
+int xdl_emit_common(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
+		    xdemitconf_t const *xecfg) {
+	xdfile_t *xdf = &xe->xdf1;
+	const char *rchg = xdf->rchg;
+	long ix;
+
+	for (ix = 0; ix < xdf->nrec; ix++) {
+		if (rchg[ix])
+			continue;
+		if (xdl_emit_record(xdf, ix, "", ecb))
+			return -1;
+	}
+	return 0;
+}
+
 int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 		  xdemitconf_t const *xecfg) {
 	long s1, s2, e1, e2, lctx;
@@ -107,6 +122,9 @@ int xdl_emit_diff(xdfenv_t *xe, xdchange_t *xscr, xdemitcb_t *ecb,
 	char funcbuf[40];
 	long funclen = 0;
 
+	if (xecfg->flags & XDL_EMIT_COMMON)
+		return xdl_emit_common(xe, xscr, ecb, xecfg);
+
 	for (xch = xche = xscr; xch; xch = xche->next) {
 		xche = xdl_get_hunk(xch, xecfg);