From: Darrick J. Wong <djwong@xxxxxxxxxx> I missed a few non-rendering code points in the "zero width" classification code. Add them now, and sort the list. $ wget https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt $ grep -E '(zero width|invisible|joiner|application)' -i UnicodeData.txt Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx> --- scrub/unicrash.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/scrub/unicrash.c b/scrub/unicrash.c index 96e20114c48..fc1adb2caab 100644 --- a/scrub/unicrash.c +++ b/scrub/unicrash.c @@ -351,15 +351,17 @@ name_entry_examine( while ((uchr = uiter_next32(&uiter)) != U_SENTINEL) { /* zero width character sequences */ switch (uchr) { + case 0x034F: /* combining grapheme joiner */ case 0x200B: /* zero width space */ case 0x200C: /* zero width non-joiner */ case 0x200D: /* zero width joiner */ - case 0xFEFF: /* zero width non breaking space */ case 0x2060: /* word joiner */ case 0x2061: /* function application */ case 0x2062: /* invisible times (multiply) */ case 0x2063: /* invisible separator (comma) */ case 0x2064: /* invisible plus (addition) */ + case 0x2D7F: /* tifinagh consonant joiner */ + case 0xFEFF: /* zero width non breaking space */ *badflags |= UNICRASH_ZERO_WIDTH; break; }
