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.
This commit is contained in:
Oneric 2024-02-19 22:42:25 +01:00 committed by Stefano Sabatini
parent 7b8b4cdd96
commit baa64fa4e6
2 changed files with 9 additions and 2 deletions

View File

@ -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

View File

@ -37,7 +37,7 @@ static const struct {
{"<i>", "{\\i1}"}, {"</i>", "{\\i0}"},
{"<b>", "{\\b1}"}, {"</b>", "{\\b0}"},
{"<u>", "{\\u1}"}, {"</u>", "{\\u0}"},
{"{", "\\{"}, {"}", "\\}"}, // escape to avoid ASS markup conflicts
{"{", "\\{"}, {"}", "\\}"}, {"\\", "\\\xe2\x81\xa0"}, // escape to avoid ASS markup conflicts
{"&gt;", ">"}, {"&lt;", "<"},
{"&lrm;", "\xe2\x80\x8e"}, {"&rlm;", "\xe2\x80\x8f"},
{"&amp;", "&"}, {"&nbsp;", "\\h"},