From baa64fa4e66465c63f84baaae204734aa19efb3f Mon Sep 17 00:00:00 2001 From: Oneric Date: Mon, 19 Feb 2024 22:42:25 +0100 Subject: [PATCH] avcodec/ass,webvttdec: fix handling of backslashes Backslashes cannot be escaped by a backslash in any ASS renderer, but unless followed by specific characters it is just printed out. Insert a word-joiner character after a backslash to break up active sequences without changing the visual output. --- libavcodec/ass.c | 9 ++++++++- libavcodec/webvttdec.c | 2 +- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/libavcodec/ass.c b/libavcodec/ass.c index 5ff4ac8e07..c5abf15122 100644 --- a/libavcodec/ass.c +++ b/libavcodec/ass.c @@ -183,9 +183,16 @@ void ff_ass_bprint_text_event(AVBPrint *buf, const char *p, int size, /* standard ASS escaping so random characters don't get mis-interpreted * as ASS */ - } else if (!keep_ass_markup && strchr("{}\\", *p)) { + } else if (!keep_ass_markup && strchr("{}", *p)) { av_bprintf(buf, "\\%c", *p); + /* append word-joiner U+2060 as UTF-8 to break up sequences like \N */ + } else if (!keep_ass_markup && *p == '\\') { + if (p_end - p <= 3 || strncmp(p + 1, "\xe2\x81\xa0", 3)) + av_bprintf(buf, "\\\xe2\x81\xa0"); + else + av_bprintf(buf, "\\"); + /* some packets might end abruptly (no \0 at the end, like for example * in some cases of demuxing from a classic video container), some * might be terminated with \n or \r\n which we have to remove (for diff --git a/libavcodec/webvttdec.c b/libavcodec/webvttdec.c index 990d150f16..6e55bc5499 100644 --- a/libavcodec/webvttdec.c +++ b/libavcodec/webvttdec.c @@ -37,7 +37,7 @@ static const struct { {"", "{\\i1}"}, {"", "{\\i0}"}, {"", "{\\b1}"}, {"", "{\\b0}"}, {"", "{\\u1}"}, {"", "{\\u0}"}, - {"{", "\\{"}, {"}", "\\}"}, // escape to avoid ASS markup conflicts + {"{", "\\{"}, {"}", "\\}"}, {"\\", "\\\xe2\x81\xa0"}, // escape to avoid ASS markup conflicts {">", ">"}, {"<", "<"}, {"‎", "\xe2\x80\x8e"}, {"‏", "\xe2\x80\x8f"}, {"&", "&"}, {" ", "\\h"},