From 39bdd84eaf646aa73a3709b0eb8be3f47378708f Mon Sep 17 00:00:00 2001 From: Phillip Wood Date: Sat, 20 Jul 2024 16:01:59 +0000 Subject: add-patch: handle splitting hunks with diff.suppressBlankEmpty When "add -p" parses diffs, it looks for context lines starting with a single space. But when diff.suppressBlankEmpty is in effect, an empty context line will omit the space, giving us a true empty line. This confuses the parser, which is unable to split based on such a line. It's tempting to say that we should just make sure that we generate a diff without that option. However, although we do not parse hunks that the user has manually edited with parse_diff() we do allow the user to split such hunks. As POSIX calls the decision of whether to print the space here "implementation-defined" we need to handle edited hunks where empty context lines omit the space. So let's handle both cases: a context line either starts with a space or consists of a totally empty line by normalizing the first character to a space when we parse them. Normalizing the first character rather than changing the code to check for a space or newline will hopefully future proof against introducing similar bugs if the code is changed. Reported-by: Ilya Tumaykin Helped-by: Jeff King Signed-off-by: Phillip Wood Signed-off-by: Junio C Hamano --- add-patch.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) (limited to 'add-patch.c') diff --git a/add-patch.c b/add-patch.c index 79eda168eb..1c28a7fa1f 100644 --- a/add-patch.c +++ b/add-patch.c @@ -400,6 +400,12 @@ static void complete_file(char marker, struct hunk *hunk) hunk->splittable_into++; } +/* Empty context lines may omit the leading ' ' */ +static int normalize_marker(const char *p) +{ + return p[0] == '\n' || (p[0] == '\r' && p[1] == '\n') ? ' ' : p[0]; +} + static int parse_diff(struct add_p_state *s, const struct pathspec *ps) { struct strvec args = STRVEC_INIT; @@ -485,6 +491,7 @@ static int parse_diff(struct add_p_state *s, const struct pathspec *ps) while (p != pend) { char *eol = memchr(p, '\n', pend - p); const char *deleted = NULL, *mode_change = NULL; + char ch = normalize_marker(p); if (!eol) eol = pend; @@ -532,7 +539,7 @@ static int parse_diff(struct add_p_state *s, const struct pathspec *ps) * Start counting into how many hunks this one can be * split */ - marker = *p; + marker = ch; } else if (hunk == &file_diff->head && starts_with(p, "new file")) { file_diff->added = 1; @@ -586,10 +593,10 @@ static int parse_diff(struct add_p_state *s, const struct pathspec *ps) (int)(eol - (plain->buf + file_diff->head.start)), plain->buf + file_diff->head.start); - if ((marker == '-' || marker == '+') && *p == ' ') + if ((marker == '-' || marker == '+') && ch == ' ') hunk->splittable_into++; - if (marker && *p != '\\') - marker = *p; + if (marker && ch != '\\') + marker = ch; p = eol == pend ? pend : eol + 1; hunk->end = p - plain->buf; @@ -813,7 +820,7 @@ static int merge_hunks(struct add_p_state *s, struct file_diff *file_diff, (int)(hunk->end - hunk->start), plain + hunk->start); - if (plain[overlap_end] != ' ') + if (normalize_marker(&plain[overlap_end]) != ' ') return error(_("expected context line " "#%d in\n%.*s"), (int)(j + 1), @@ -953,7 +960,7 @@ static int split_hunk(struct add_p_state *s, struct file_diff *file_diff, context_line_count = 0; while (splittable_into > 1) { - ch = s->plain.buf[current]; + ch = normalize_marker(&s->plain.buf[current]); if (!ch) BUG("buffer overrun while splitting hunks"); -- cgit v1.3