[PATCH v4 08/11] rerere: factor out handle_conflict function

From: Thomas Gummerer <t.gummerer@gmail.com>
Date: Aug 5, 2018, 17:20 UTC
Message-ID: <20180805172037.12530-9-t.gummerer@gmail.com>
In-Reply-To: <20180805172037.12530-1-t.gummerer@gmail.com>

Factor out the handle_conflict function, which handles a single conflict in a path. This is in preparation for a subsequent commit, where this function will be re-used.

Note that this does change the behaviour of 'git rerere' slightly. Where previously we'd consider all files where an unmatched conflict marker is found as invalid, we now only consider files invalid when the "ours" conflict marker ("<<<<<<< <text>") is unmatched, not when other conflict markers (e.g. "=======") is unmatched.

Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
 rerere.c | 87 ++++++++++++++++++++++++++++++--------------------------
 1 file changed, 47 insertions(+), 40 deletions(-)

diff --git a/rerere.c b/rerere.c
index bf803043e2..2d62251943 100644
--- a/rerere.c
+++ b/rerere.c
@@ -384,85 +384,92 @@ static int is_cmarker(char *buf, int marker_char, int marker_size)
 	return isspace(*buf);
 }
 
-/*
- * Read contents a file with conflicts, normalize the conflicts
- * by (1) discarding the common ancestor version in diff3-style,
- * (2) reordering our side and their side so that whichever sorts
- * alphabetically earlier comes before the other one, while
- * computing the "conflict ID", which is just an SHA-1 hash of
- * one side of the conflict, NUL, the other side of the conflict,
- * and NUL concatenated together.
- *
- * Return 1 if conflict hunks are found, 0 if there are no conflict
- * hunks and -1 if an error occured.
- */
-static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_size)
+static int handle_conflict(struct rerere_io *io, int marker_size, git_SHA_CTX *ctx)
 {
-	git_SHA_CTX ctx;
-	int has_conflicts = 0;
 	enum {
-		RR_CONTEXT = 0, RR_SIDE_1, RR_SIDE_2, RR_ORIGINAL
-	} hunk = RR_CONTEXT;
+		RR_SIDE_1 = 0, RR_SIDE_2, RR_ORIGINAL
+	} hunk = RR_SIDE_1;
 	struct strbuf one = STRBUF_INIT, two = STRBUF_INIT;
 	struct strbuf buf = STRBUF_INIT;
-
-	if (sha1)
-		git_SHA1_Init(&ctx);
+	int has_conflicts = -1;
 
 	while (!io->getline(&buf, io)) {
 		if (is_cmarker(buf.buf, '<', marker_size)) {
-			if (hunk != RR_CONTEXT)
-				goto bad;
-			hunk = RR_SIDE_1;
+			break;
 		} else if (is_cmarker(buf.buf, '|', marker_size)) {
 			if (hunk != RR_SIDE_1)
-				goto bad;
+				break;
 			hunk = RR_ORIGINAL;
 		} else if (is_cmarker(buf.buf, '=', marker_size)) {
 			if (hunk != RR_SIDE_1 && hunk != RR_ORIGINAL)
-				goto bad;
+				break;
 			hunk = RR_SIDE_2;
 		} else if (is_cmarker(buf.buf, '>', marker_size)) {
 			if (hunk != RR_SIDE_2)
-				goto bad;
+				break;
 			if (strbuf_cmp(&one, &two) > 0)
 				strbuf_swap(&one, &two);
 			has_conflicts = 1;
-			hunk = RR_CONTEXT;
 			rerere_io_putconflict('<', marker_size, io);
 			rerere_io_putmem(one.buf, one.len, io);
 			rerere_io_putconflict('=', marker_size, io);
 			rerere_io_putmem(two.buf, two.len, io);
 			rerere_io_putconflict('>', marker_size, io);
-			if (sha1) {
-				git_SHA1_Update(&ctx, one.buf ? one.buf : "",
+			if (ctx) {
+				git_SHA1_Update(ctx, one.buf ? one.buf : "",
 					    one.len + 1);
-				git_SHA1_Update(&ctx, two.buf ? two.buf : "",
+				git_SHA1_Update(ctx, two.buf ? two.buf : "",
 					    two.len + 1);
 			}
-			strbuf_reset(&one);
-			strbuf_reset(&two);
+			break;
 		} else if (hunk == RR_SIDE_1)
 			strbuf_addbuf(&one, &buf);
 		else if (hunk == RR_ORIGINAL)
 			; /* discard */
 		else if (hunk == RR_SIDE_2)
 			strbuf_addbuf(&two, &buf);
-		else
-			rerere_io_putstr(buf.buf, io);
-		continue;
-	bad:
-		hunk = 99; /* force error exit */
-		break;
 	}
 	strbuf_release(&one);
 	strbuf_release(&two);
 	strbuf_release(&buf);
 
+	return has_conflicts;
+}
+
+/*
+ * Read contents a file with conflicts, normalize the conflicts
+ * by (1) discarding the common ancestor version in diff3-style,
+ * (2) reordering our side and their side so that whichever sorts
+ * alphabetically earlier comes before the other one, while
+ * computing the "conflict ID", which is just an SHA-1 hash of
+ * one side of the conflict, NUL, the other side of the conflict,
+ * and NUL concatenated together.
+ *
+ * Return 1 if conflict hunks are found, 0 if there are no conflict
+ * hunks and -1 if an error occured.
+ */
+static int handle_path(unsigned char *sha1, struct rerere_io *io, int marker_size)
+{
+	git_SHA_CTX ctx;
+	struct strbuf buf = STRBUF_INIT;
+	int has_conflicts = 0;
+	if (sha1)
+		git_SHA1_Init(&ctx);
+
+	while (!io->getline(&buf, io)) {
+		if (is_cmarker(buf.buf, '<', marker_size)) {
+			has_conflicts = handle_conflict(io, marker_size,
+							sha1 ? &ctx : NULL);
+			if (has_conflicts < 0)
+				break;
+		} else
+			rerere_io_putstr(buf.buf, io);
+	}
+	strbuf_release(&buf);
+
 	if (sha1)
 		git_SHA1_Final(sha1, &ctx);
-	if (hunk != RR_CONTEXT)
-		return -1;
+
 	return has_conflicts;
 }

-- 
2.18.0.720.gf7a957e2e7