[PATCH v4 2/3] Try normalizing files to avoid delete/modify conflicts when merging

[Eyvind Bernhardsen <eyvind.bernhardsen@gmail.com>]

If a file is modified due to normalization on one branch, and deleted on
another, a merge of the two branches will result in a delete/modify
conflict for that file even if it is otherwise unchanged.

Try to avoid the conflict by normalizing and comparing the "base" file
and the modified file when their sha1s differ.  If they compare equal,
the file is considered unmodified and is deleted.

Signed-off-by: Eyvind Bernhardsen <eyvind.bernhardsen@gmail.com>
---
 merge-recursive.c          |   44 ++++++++++++++++++++++++++++++++++++++++++--
 t/t6038-merge-text-auto.sh |    2 +-
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/merge-recursive.c b/merge-recursive.c
index 206c103..f4f09a2 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -1056,6 +1056,44 @@ static unsigned char *stage_sha(const unsigned char *sha, unsigned mode)
 	return (is_null_sha1(sha) || mode == 0) ? NULL: (unsigned char *)sha;
 }
 
+static int read_sha1_strbuf(const unsigned char *sha, const char *path,
+			    struct strbuf *dst)
+{
+	void *buf;
+	enum object_type type;
+	unsigned long size;
+	buf = read_sha1_file(sha, &type, &size);
+	if (!buf)
+		return 0;
+	if (type != OBJ_BLOB) {
+		free(buf);
+		return 0;
+	}
+	strbuf_attach(dst, buf, size, size + 1);
+	return 1;
+}
+
+static int normalized_eq(const unsigned char *a_sha,
+			 const unsigned char *b_sha,
+			 const char *path)
+{
+	struct strbuf a = STRBUF_INIT;
+	struct strbuf b = STRBUF_INIT;
+	int ret = 0;
+	if (a_sha && b_sha &&
+	    read_sha1_strbuf(a_sha, path, &a) &&
+	    read_sha1_strbuf(b_sha, path, &b)) {
+		/* Both files must be normalized, so we can't use || */
+		if ((renormalize_buffer(path, a.buf, a.len, &a) |
+		     renormalize_buffer(path, b.buf, b.len, &b)) &&
+		    (a.len == b.len))
+			ret = memcmp(a.buf, b.buf, a.len) == 0;
+	}
+	strbuf_release(&a);
+	strbuf_release(&b);
+	return ret;
+}
+
 /* Per entry merge function */
 static int process_entry(struct merge_options *o,
 			 const char *path, struct stage_data *entry)
@@ -1075,8 +1113,10 @@ static int process_entry(struct merge_options *o,
 	if (o_sha && (!a_sha || !b_sha)) {
 		/* Case A: Deleted in one */
 		if ((!a_sha && !b_sha) ||
-		    (sha_eq(a_sha, o_sha) && !b_sha) ||
-		    (!a_sha && sha_eq(b_sha, o_sha))) {
+		    (!b_sha && sha_eq(a_sha, o_sha) ||
+		     normalized_eq(a_sha, o_sha, path)) ||
+		    (!a_sha && sha_eq(b_sha, o_sha) ||
+		     normalized_eq(b_sha, o_sha, path))) {
 			/* Deleted in both or deleted in one and
 			 * unchanged in the other */
 			if (a_sha)
diff --git a/t/t6038-merge-text-auto.sh b/t/t6038-merge-text-auto.sh
index 44e6003..5e45256 100755
--- a/t/t6038-merge-text-auto.sh
+++ b/t/t6038-merge-text-auto.sh
@@ -45,7 +45,7 @@ test_expect_success 'Check merging addition of text=auto' '
 	test_cmp file file.temp
 '
 
-test_expect_failure 'Test delete/normalize conflict' '
+test_expect_success 'Test delete/normalize conflict' '
 	git checkout side &&
 	git reset --hard initial &&
 	git rm file &&
-- 
1.7.1.575.g383de