patch-id: make it stable against hunk reordering

Patch id changes if users reorder file diffs that make up a patch.

As the result is functionally equivalent, a different patch id is
surprising to many users.
In particular, reordering files using diff -O is helpful to make patches
more readable (e.g. API header diff before implementation diff).

Add an option to change patch-id behaviour making it stable against
these kinds of patch change:
calculate SHA1 hash for each hunk separately and sum all hashes
(using a symmetrical sum) to get patch id

We use a 20byte sum and not xor - since xor would give 0 output
for patches that have two identical diffs, which isn't all that
unlikely (e.g. append the same line in two places).

The new behaviour is enabled
- when patchid.stable is true
- when --stable flag is present

Using a new flag --unstable or setting patchid.stable to false force
the historical behaviour.

In the documentation, clarify that patch ID can now be a sum of hashes,
not a hash.
Document how command line and config options affect the
behaviour.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 59 insertions, 15 deletions

diff --git a/builtin/patch-id.c b/builtin/patch-id.c
index 3cfe02d5a5..77db8739b5 100644
--- a/builtin/patch-id.c
+++ b/builtin/patch-id.c
@@ -1,17 +1,14 @@
 #include "builtin.h"
 
-static void flush_current_id(int patchlen, unsigned char *id, git_SHA_CTX *c)
+static void flush_current_id(int patchlen, unsigned char *id, unsigned char *result)
 {
-	unsigned char result[20];
 	char name[50];
 
 	if (!patchlen)
 		return;
 
-	git_SHA1_Final(result, c);
 	memcpy(name, sha1_to_hex(id), 41);
 	printf("%s %s\n", sha1_to_hex(result), name);
-	git_SHA1_Init(c);
 }
 
 static int remove_space(char *line)
@@ -56,10 +53,31 @@ static int scan_hunk_header(const char *p, int *p_before, int *p_after)
 	return 1;
 }
 
-static int get_one_patchid(unsigned char *next_sha1, git_SHA_CTX *ctx, struct strbuf *line_buf)
+static void flush_one_hunk(unsigned char *result, git_SHA_CTX *ctx)
+{
+	unsigned char hash[20];
+	unsigned short carry = 0;
+	int i;
+
+	git_SHA1_Final(hash, ctx);
+	git_SHA1_Init(ctx);
+	/* 20-byte sum, with carry */
+	for (i = 0; i < 20; ++i) {
+		carry += result[i] + hash[i];
+		result[i] = carry;
+		carry >>= 8;
+	}
+}
+
+static int get_one_patchid(unsigned char *next_sha1, unsigned char *result,
+			   struct strbuf *line_buf, int stable)
 {
 	int patchlen = 0, found_next = 0;
 	int before = -1, after = -1;
+	git_SHA_CTX ctx;
+
+	git_SHA1_Init(&ctx);
+	hashclr(result);
 
 	while (strbuf_getwholeline(line_buf, stdin, '\n') != EOF) {
 		char *line = line_buf->buf;
@@ -107,6 +125,8 @@ static int get_one_patchid(unsigned char *next_sha1, git_SHA_CTX *ctx, struct st
 				break;
 
 			/* Else we're parsing another header.  */
+			if (stable)
+				flush_one_hunk(result, &ctx);
 			before = after = -1;
 		}
 
@@ -119,39 +139,63 @@ static int get_one_patchid(unsigned char *next_sha1, git_SHA_CTX *ctx, struct st
 		/* Compute the sha without whitespace */
 		len = remove_space(line);
 		patchlen += len;
-		git_SHA1_Update(ctx, line, len);
+		git_SHA1_Update(&ctx, line, len);
 	}
 
 	if (!found_next)
 		hashclr(next_sha1);
 
+	flush_one_hunk(result, &ctx);
+
 	return patchlen;
 }
 
-static void generate_id_list(void)
+static void generate_id_list(int stable)
 {
-	unsigned char sha1[20], n[20];
-	git_SHA_CTX ctx;
+	unsigned char sha1[20], n[20], result[20];
 	int patchlen;
 	struct strbuf line_buf = STRBUF_INIT;
 
-	git_SHA1_Init(&ctx);
 	hashclr(sha1);
 	while (!feof(stdin)) {
-		patchlen = get_one_patchid(n, &ctx, &line_buf);
-		flush_current_id(patchlen, sha1, &ctx);
+		patchlen = get_one_patchid(n, result, &line_buf, stable);
+		flush_current_id(patchlen, sha1, result);
 		hashcpy(sha1, n);
 	}
 	strbuf_release(&line_buf);
 }
 
-static const char patch_id_usage[] = "git patch-id < patch";
+static const char patch_id_usage[] = "git patch-id [--stable | --unstable] < patch";
+
+static int git_patch_id_config(const char *var, const char *value, void *cb)
+{
+	int *stable = cb;
+
+	if (!strcmp(var, "patchid.stable")) {
+		*stable = git_config_bool(var, value);
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
 
 int cmd_patch_id(int argc, const char **argv, const char *prefix)
 {
-	if (argc != 1)
+	int stable = -1;
+
+	git_config(git_patch_id_config, &stable);
+
+	/* If nothing is set, default to unstable. */
+	if (stable < 0)
+		stable = 0;
+
+	if (argc == 2 && !strcmp(argv[1], "--stable"))
+		stable = 1;
+	else if (argc == 2 && !strcmp(argv[1], "--unstable"))
+		stable = 0;
+	else if (argc != 1)
 		usage(patch_id_usage);
 
-	generate_id_list();
+	generate_id_list(stable);
 	return 0;
 }