[FFmpeg-devel] [PATCH v4 2/4] avcodec/{ass, webvttdec}: fix handling of backslashes
Oneric
oneric at oneric.de
Mon Feb 19 23:42:25 EET 2024
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 5058dc8337..a68d3568b4 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 {
{"<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
{">", ">"}, {"<", "<"},
{"", "\xe2\x80\x8e"}, {"", "\xe2\x80\x8f"},
{"&", "&"}, {" ", "\\h"},
--
2.39.2
More information about the ffmpeg-devel
mailing list