Skip UTF-8 BOM in binary detection When a git_buf contains a UTF-8 BOM, the three bytes comprising that BOM are treated as unprintable characters. For a small git_buf, the three BOM characters overwhelm the printable characters. This is problematic when trying to check out a small file as the CR/LF filtering will not apply.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
diff --git a/src/buf_text.c b/src/buf_text.c
index 472339d..ecf592b 100644
--- a/src/buf_text.c
+++ b/src/buf_text.c
@@ -170,8 +170,14 @@ int git_buf_text_common_prefix(git_buf *buf, const git_strarray *strings)
bool git_buf_text_is_binary(const git_buf *buf)
{
const char *scan = buf->ptr, *end = buf->ptr + buf->size;
+ git_bom_t bom;
int printable = 0, nonprintable = 0;
+ scan += git_buf_text_detect_bom(&bom, buf, 0);
+
+ if (bom > GIT_BOM_UTF8)
+ return 1;
+
while (scan < end) {
unsigned char c = *scan++;
diff --git a/tests-clar/core/buffer.c b/tests-clar/core/buffer.c
index 9d9628c..8a0b671 100644
--- a/tests-clar/core/buffer.c
+++ b/tests-clar/core/buffer.c
@@ -718,6 +718,8 @@ void test_core_buffer__classify_with_utf8(void)
size_t data1len = 31;
char *data2 = "Internal NUL!!!\000\n\nI see you!\n";
size_t data2len = 29;
+ char *data3 = "\xef\xbb\xbfThis is UTF-8 with a BOM.\n";
+ size_t data3len = 20;
git_buf b;
b.ptr = data0; b.size = b.asize = data0len;
@@ -731,6 +733,10 @@ void test_core_buffer__classify_with_utf8(void)
b.ptr = data2; b.size = b.asize = data2len;
cl_assert(git_buf_text_is_binary(&b));
cl_assert(git_buf_text_contains_nul(&b));
+
+ b.ptr = data3; b.size = b.asize = data3len;
+ cl_assert(!git_buf_text_is_binary(&b));
+ cl_assert(!git_buf_text_contains_nul(&b));
}
#define SIMILARITY_TEST_DATA_1 \