Merge branch 'pb/patch-id-plus'

* pb/patch-id-plus:
  patch-id: Add support for mbox format
  patch-id: extract parsing one diff out of generate_id_list

2 files changed, 116 insertions, 19 deletions

diff --git a/builtin/patch-id.c b/builtin/patch-id.c
index af0911e4b..512530022 100644
--- a/builtin/patch-id.c
+++ b/builtin/patch-id.c
@@ -28,16 +28,42 @@ static int remove_space(char *line)
 	return dst - line;
 }
 
-static void generate_id_list(void)
+static int scan_hunk_header(const char *p, int *p_before, int *p_after)
+{
+	static const char digits[] = "0123456789";
+	const char *q, *r;
+	int n;
+
+	q = p + 4;
+	n = strspn(q, digits);
+	if (q[n] == ',') {
+		q += n + 1;
+		n = strspn(q, digits);
+	}
+	if (n == 0 || q[n] != ' ' || q[n+1] != '+')
+		return 0;
+
+	r = q + n + 2;
+	n = strspn(r, digits);
+	if (r[n] == ',') {
+		r += n + 1;
+		n = strspn(r, digits);
+	}
+	if (n == 0)
+		return 0;
+
+	*p_before = atoi(q);
+	*p_after = atoi(r);
+	return 1;
+}
+
+int get_one_patchid(unsigned char *next_sha1, git_SHA_CTX *ctx)
 {
-	static unsigned char sha1[20];
 	static char line[1000];
-	git_SHA_CTX ctx;
-	int patchlen = 0;
+	int patchlen = 0, found_next = 0;
+	int before = -1, after = -1;
 
-	git_SHA1_Init(&ctx);
 	while (fgets(line, sizeof(line), stdin) != NULL) {
-		unsigned char n[20];
 		char *p = line;
 		int len;
 
@@ -45,32 +71,75 @@ static void generate_id_list(void)
 			p += 10;
 		else if (!memcmp(line, "commit ", 7))
 			p += 7;
+		else if (!memcmp(line, "From ", 5))
+			p += 5;
 
-		if (!get_sha1_hex(p, n)) {
-			flush_current_id(patchlen, sha1, &ctx);
-			hashcpy(sha1, n);
-			patchlen = 0;
-			continue;
+		if (!get_sha1_hex(p, next_sha1)) {
+			found_next = 1;
+			break;
 		}
 
 		/* Ignore commit comments */
 		if (!patchlen && memcmp(line, "diff ", 5))
 			continue;
 
-		/* Ignore git-diff index header */
-		if (!memcmp(line, "index ", 6))
-			continue;
+		/* Parsing diff header?  */
+		if (before == -1) {
+			if (!memcmp(line, "index ", 6))
+				continue;
+			else if (!memcmp(line, "--- ", 4))
+				before = after = 1;
+			else if (!isalpha(line[0]))
+				break;
+		}
 
-		/* Ignore line numbers when computing the SHA1 of the patch */
-		if (!memcmp(line, "@@ -", 4))
-			continue;
+		/* Looking for a valid hunk header?  */
+		if (before == 0 && after == 0) {
+			if (!memcmp(line, "@@ -", 4)) {
+				/* Parse next hunk, but ignore line numbers.  */
+				scan_hunk_header(line, &before, &after);
+				continue;
+			}
+
+			/* Split at the end of the patch.  */
+			if (memcmp(line, "diff ", 5))
+				break;
+
+			/* Else we're parsing another header.  */
+			before = after = -1;
+		}
+
+		/* If we get here, we're inside a hunk.  */
+		if (line[0] == '-' || line[0] == ' ')
+			before--;
+		if (line[0] == '+' || line[0] == ' ')
+			after--;
 
 		/* 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);
+
+	return patchlen;
+}
+
+static void generate_id_list(void)
+{
+	unsigned char sha1[20], n[20];
+	git_SHA_CTX ctx;
+	int patchlen;
+
+	git_SHA1_Init(&ctx);
+	hashclr(sha1);
+	while (!feof(stdin)) {
+		patchlen = get_one_patchid(n, &ctx);
+		flush_current_id(patchlen, sha1, &ctx);
+		hashcpy(sha1, n);
 	}
-	flush_current_id(patchlen, sha1, &ctx);
 }
 
 static const char patch_id_usage[] = "git patch-id < patch";
diff --git a/t/t4204-patch-id.sh b/t/t4204-patch-id.sh
index 04f7bae85..68e265281 100755
--- a/t/t4204-patch-id.sh
+++ b/t/t4204-patch-id.sh
@@ -18,6 +18,11 @@ test_expect_success 'patch-id output is well-formed' '
 	grep "^[a-f0-9]\{40\} $(git rev-parse HEAD)$" output
 '
 
+calc_patch_id () {
+	git patch-id |
+		sed "s# .*##" > patch-id_"$1"
+}
+
 get_patch_id () {
 	git log -p -1 "$1" | git patch-id |
 		sed "s# .*##" > patch-id_"$1"
@@ -35,4 +40,27 @@ test_expect_success 'patch-id detects inequality' '
 	! test_cmp patch-id_master patch-id_notsame
 '
 
+test_expect_success 'patch-id supports git-format-patch output' '
+	get_patch_id master &&
+	git checkout same &&
+	git format-patch -1 --stdout | calc_patch_id same &&
+	test_cmp patch-id_master patch-id_same &&
+	set `git format-patch -1 --stdout | git patch-id` &&
+	test "$2" = `git rev-parse HEAD`
+'
+
+test_expect_success 'whitespace is irrelevant in footer' '
+	get_patch_id master &&
+	git checkout same &&
+	git format-patch -1 --stdout | sed "s/ \$//" | calc_patch_id same &&
+	test_cmp patch-id_master patch-id_same
+'
+
+test_expect_success 'patch-id supports git-format-patch MIME output' '
+	get_patch_id master &&
+	git checkout same &&
+	git format-patch -1 --attach --stdout | calc_patch_id same &&
+	test_cmp patch-id_master patch-id_same
+'
+
 test_done