[PATCH v3 6/9] trailer: find the end of the log message

From: Linus Arver via GitGitGadget <gitgitgadget@gmail.com>
Date: Sep 22, 2023, 19:50 UTC
Message-ID: <ab8a6ced1435580ad3e8585e464e447d40805232.1695412245.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1563.v3.git.1695412245.gitgitgadget@gmail.com>

From: Linus Arver <linusa@google.com>

Previously, trailer_info_get() computed the trailer block end position by

(1) checking for the opts->no_divider flag and optionally calling
    find_patch_start() to find the "patch start" location (patch_start), and
(2) calling find_trailer_end() to find the end of the trailer block
    using patch_start as a guide, saving the return value into
    "trailer_end".

The logic in (1) was awkward because the variable "patch_start" is misleading if there is no patch in the input. The logic in (2) was misleading because it could be the case that no trailers are in the input (yet we are setting a "trailer_end" variable before even searching for trailers, which happens later in find_trailer_start()). The name "find_trailer_end" was misleading because that function did not look for any trailer block itself --- instead it just computed the end position of the log message in the input where the end of the trailer block (if it exists) would be (because trailer blocks must always come after the end of the log message).

Combine the logic in (1) and (2) together into find_patch_start() by renaming it to find_end_of_log_message(). The end of the log message is the starting point which find_trailer_start() needs to start searching backward to parse individual trailers (if any).

Helped-by: Junio C Hamano <gitster@pobox.com>
Signed-off-by: Linus Arver <linusa@google.com>
---
 trailer.c | 61 ++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 38 insertions(+), 23 deletions(-)

diff --git a/trailer.c b/trailer.c
index 185b3e2707f..9da89df9d8a 100644
--- a/trailer.c
+++ b/trailer.c
@@ -812,21 +812,47 @@ static ssize_t last_line(const char *buf, size_t len)
 }
 
 /*
- * Return the position of the start of the patch or the length of str if there
- * is no patch in the message.
+ * Find the end of the log message as an offset from the start of the input
+ * (where callers of this function are interested in looking for a trailers
+ * block in the same input). We have to consider two categories of content that
+ * can come at the end of the input which we want to ignore (because they don't
+ * belong in the log message):
+ *
+ * (1) the "patch part" which begins with a "---" divider and has patch
+ * information (like the output of git-format-patch), and
+ *
+ * (2) any trailing comment lines, blank lines like in the output of "git
+ * commit -v", or stuff below the "cut" (scissor) line.
+ *
+ * As a formula, the situation looks like this:
+ *
+ *     INPUT = LOG MESSAGE + IGNORED
+ *
+ * where IGNORED can be either of the two categories described above. It may be
+ * that there is nothing to ignore. Now it may be the case that the LOG MESSAGE
+ * contains a trailer block, but that's not the concern of this function.
  */
-static size_t find_patch_start(const char *str)
+static size_t find_end_of_log_message(const char *input, int no_divider)
 {
+	size_t end;
+
 	const char *s;
 
-	for (s = str; *s; s = next_line(s)) {
+	/* Assume the naive end of the input is already what we want. */
+	end = strlen(input);
+
+	/* Optionally skip over any patch part ("---" line and below). */
+	for (s = input; *s; s = next_line(s)) {
 		const char *v;
 
-		if (skip_prefix(s, "---", &v) && isspace(*v))
-			return s - str;
+		if (!no_divider && skip_prefix(s, "---", &v) && isspace(*v)) {
+			end = s - input;
+			break;
+		}
 	}
 
-	return s - str;
+	/* Skip over other ignorable bits. */
+	return end - ignored_log_message_bytes(input, end);
 }
 
 /*
@@ -928,12 +954,6 @@ continue_outer_loop:
 	return len;
 }
 
-/* Return the position of the end of the trailers. */
-static size_t find_trailer_end(const char *buf, size_t len)
-{
-	return len - ignored_log_message_bytes(buf, len);
-}
-
 static int ends_with_blank_line(const char *buf, size_t len)
 {
 	ssize_t ll = last_line(buf, len);
@@ -1104,7 +1124,7 @@ void process_trailers(const char *file,
 void trailer_info_get(struct trailer_info *info, const char *str,
 		      const struct process_trailer_options *opts)
 {
-	int patch_start, trailer_end, trailer_start;
+	int end_of_log_message, trailer_start;
 	struct strbuf **trailer_lines, **ptr;
 	char **trailer_strings = NULL;
 	size_t nr = 0, alloc = 0;
@@ -1112,16 +1132,11 @@ void trailer_info_get(struct trailer_info *info, const char *str,
 
 	ensure_configured();
 
-	if (opts->no_divider)
-		patch_start = strlen(str);
-	else
-		patch_start = find_patch_start(str);
-
-	trailer_end = find_trailer_end(str, patch_start);
-	trailer_start = find_trailer_start(str, trailer_end);
+	end_of_log_message = find_end_of_log_message(str, opts->no_divider);
+	trailer_start = find_trailer_start(str, end_of_log_message);
 
 	trailer_lines = strbuf_split_buf(str + trailer_start,
-					 trailer_end - trailer_start,
+					 end_of_log_message - trailer_start,
 					 '\n',
 					 0);
 	for (ptr = trailer_lines; *ptr; ptr++) {
@@ -1144,7 +1159,7 @@ void trailer_info_get(struct trailer_info *info, const char *str,
 	info->blank_line_before_trailer = ends_with_blank_line(str,
 							       trailer_start);
 	info->trailer_start = str + trailer_start;
-	info->trailer_end = str + trailer_end;
+	info->trailer_end = str + end_of_log_message;
 	info->trailers = trailer_strings;
 	info->trailer_nr = nr;
 }

-- 
gitgitgadget