[PATCH v3] ref-filter: trim end whitespace in subject

From

DOAN Tran Cong Danh <congdanhqx@gmail.com>

Date

May 22, 2017, 17:10 UTC

Message-ID

<20170522171014.33384-1-congdanhqx@gmail.com>

In-Reply-To

<20170522145753.83810-1-congdanhqx@gmail.com>

From: ĐOÀN Trần Công Danh <congdanhqx@gmail.com>

Quote from git mailing-list:

> Here is a recipe to reproduce the error:
>
>    git init
>    git commit --allow-empty -m initial
>    git branch crlf $(printf '%s\r\n' subject '' line3_long line4 |
>        git commit-tree HEAD:)
> The reason for the "bug" is obviously that a line having CR in addition
> to LF is not "an empty line". Consequently, the second line is not
> treated as a separator between subject and body, whereupon Git
> concatenates all line into one large subject line. This strips the LFs
> but leaves the CRS in tact, which, when printed on a terminal move the
> cursor to the beginning of the line, so that text after the CRs
> overwrites what is already in the terminal.

Reported-by: Animi Vulpis <animi.vulpis@gmail.com>
Helped-by: Johannes Sixt <j6t@kbdg.org>
Signed-off-by: ĐOÀN Trần Công Danh <congdanhqx@gmail.com>
---
Sorry for the noise, after sending out v2,
I found that the body is calculated incorrectly.

 ref-filter.c             | 40 ++++++++++++++++++++++++++++++++--------
 t/t3203-branch-output.sh |  3 ++-
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/ref-filter.c b/ref-filter.c
index 1fc5e9970..4b30edf61 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -942,6 +942,25 @@ static void grab_person(const char *who, struct atom_value *val, int deref, stru
 	}
 }
 
+/*
+ * check if line in range [start, end) is a blank line or not
+ * data in range [start, end) must be valid before calling this function
+ */
+static int is_blank_line(const char *start, const char *end)
+{
+	while (start != end && isspace(*start))
+		start++;
+	return start == end;
+}
+
+static const char* find_next_eol(const char *buf)
+{
+	const char* eol = strchrnul(buf, '\n');
+	if (*eol)
+		eol++;
+	return eol;
+}
+
 static void find_subpos(const char *buf, unsigned long sz,
 			const char **sub, unsigned long *sublen,
 			const char **body, unsigned long *bodylen,
@@ -949,6 +968,7 @@ static void find_subpos(const char *buf, unsigned long sz,
 			const char **sig, unsigned long *siglen)
 {
 	const char *eol;
+	int has_empty_line = 0;
 	/* skip past header until we hit empty line */
 	while (*buf && *buf != '\n') {
 		eol = strchrnul(buf, '\n');
@@ -967,20 +987,24 @@ static void find_subpos(const char *buf, unsigned long sz,
 	/* subject is first non-empty line */
 	*sub = buf;
 	/* subject goes to first empty line */
-	while (buf < *sig && *buf && *buf != '\n') {
-		eol = strchrnul(buf, '\n');
-		if (*eol)
-			eol++;
+	while (buf < *sig && !has_empty_line) {
+		eol = find_next_eol(buf);
+		has_empty_line = is_blank_line(buf, eol);
 		buf = eol;
 	}
 	*sublen = buf - *sub;
-	/* drop trailing newline, if present */
-	if (*sublen && (*sub)[*sublen - 1] == '\n')
+	/* drop trailing whitespace, if present */
+	while (*sublen && isspace((*sub)[*sublen - 1]))
 		*sublen -= 1;
 
 	/* skip any empty lines */
-	while (*buf == '\n')
-		buf++;
+	while (buf < *sig) {
+		eol = find_next_eol(buf);
+		if (is_blank_line(buf, eol))
+			buf = eol;
+		else
+			break;
+	}
 	*body = buf;
 	*bodylen = strlen(buf);
 	*nonsiglen = *sig - buf;
diff --git a/t/t3203-branch-output.sh b/t/t3203-branch-output.sh
index 5778c0afe..fa4441868 100755
--- a/t/t3203-branch-output.sh
+++ b/t/t3203-branch-output.sh
@@ -13,7 +13,8 @@ test_expect_success 'make commits' '
 
 test_expect_success 'make branches' '
 	git branch branch-one &&
-	git branch branch-two HEAD^
+	git branch branch-two $(printf "%s\r\n" one " " line3_long line4 |
+	     git commit-tree HEAD:)
 '
 
 test_expect_success 'make remote branches' '

-- 
Danh