Improved three-way blob merging code

This fleshes out the code that generates a three-way merge of a set of
blobs.

It still actually does the three-way merge using an external executable
(ie just calling "merge"), but the interfaces have been cleaned up a lot
and are now fully based on the 'mmfile_t' interface, so if libxdiff were
to ever grow a compatible three-way-merge, it could probably be directly
plugged in.

It also uses the previous XDL_EMIT_COMMON functionality extension to
libxdiff to generate a made-up base file for the merge for the case where
no base file previously existed. This should be equivalent to what we
currently do in git-merge-one-file.sh:

	diff -u -La/$orig -Lb/$orig $orig $src2 | git-apply --no-add

except it should be much simpler and can be done using the direct libxdiff
interfaces.

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

3 files changed, 240 insertions, 1 deletions

diff --git a/Makefile b/Makefile
index cde619c498..e880457526 100644
--- a/Makefile
+++ b/Makefile
@@ -217,7 +217,7 @@ 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 0000000000..f32c653825
--- /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 fd0c2111c4..7cf00be6d5 100644
--- a/merge-tree.c
+++ b/merge-tree.c
@@ -1,5 +1,6 @@
 #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>";
@@ -52,6 +53,77 @@ static const char *explanation(struct merge_list *entry)
 	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));
@@ -70,6 +142,7 @@ static void show_result(void)
 	walk = merge_result;
 	while (walk) {
 		show_result_list(walk);
+		show_diff(walk);
 		walk = walk->next;
 	}
 }