Re: [FFmpeg-devel] [PATCH v2] avcodec/webvttdec: strip classes

[Leon Grutters <gruttersleonbot2@gmail.com>]

On 3/21/25 4:55 PM, Leon Grutters wrote:
> If a supported tag has a class, e.g "<i.bold>" it is ignored entirely;
> so for example "<i.bold>Hello</i>" would be converted to "Hello{\i0}"
> instead of the intended "{\i1}Hello{\i0}".
>
> Signed-off-by: Leon Grutters<gruttersleonbot2@gmail.com>
Ping.
> ---
>   libavcodec/webvttdec.c | 39 ++++++++++++++++++++++++++++-----------
>   1 file changed, 28 insertions(+), 11 deletions(-)
>
> diff --git a/libavcodec/webvttdec.c b/libavcodec/webvttdec.c
> index 733fdee685..c375867643 100644
> --- a/libavcodec/webvttdec.c
> +++ b/libavcodec/webvttdec.c
> @@ -34,20 +34,41 @@ static const struct {
>       const char *from;
>       const char *to;
>   } webvtt_tag_replace[] = {
> -    {"<i>", "{\\i1}"}, {"</i>", "{\\i0}"},
> -    {"<b>", "{\\b1}"}, {"</b>", "{\\b0}"},
> -    {"<u>", "{\\u1}"}, {"</u>", "{\\u0}"},
>       {"{", "\\{{}"}, {"\\", "\\\xe2\x81\xa0"}, // escape to avoid ASS markup conflicts
>       {"&gt;", ">"}, {"&lt;", "<"},
>       {"&lrm;", "\xe2\x80\x8e"}, {"&rlm;", "\xe2\x80\x8f"},
>       {"&amp;", "&"}, {"&nbsp;", "\\h"},
>   };
> +static const struct {
> +    const char from[6];
> +    const char to[6];
> +} webvtt_valid_tags[] = {
> +    {"i", "{\\i1}"}, {"/i", "{\\i0}"},
> +    {"b", "{\\b1}"}, {"/b", "{\\b0}"},
> +    {"u", "{\\u1}"}, {"/u", "{\\u0}"},
> +};
>   
>   static int webvtt_event_to_ass(AVBPrint *buf, const char *p)
>   {
> -    int i, again = 0, skip = 0;
> +    int i, again = 0;
>   
>       while (*p) {
> +        if (*p == '<') {
> +            const char *tag_end = strchr(p, '>');
> +            ptrdiff_t len;
> +            if (!tag_end)
> +                break;
> +            len = tag_end - p + 1;
> +            for (i = 0; i < FF_ARRAY_ELEMS(webvtt_valid_tags); i++) {
> +                const char *from = webvtt_valid_tags[i].from;
> +                if(!strncmp(p + 1, from, strlen(from))) {
> +                    av_bprintf(buf, "%s", webvtt_valid_tags[i].to);
> +                    break;
> +                }
> +            }
> +            p += len;
> +            again = 1;
> +        }
>   
>           for (i = 0; i < FF_ARRAY_ELEMS(webvtt_tag_replace); i++) {
>               const char *from = webvtt_tag_replace[i].from;
> @@ -59,21 +80,17 @@ static int webvtt_event_to_ass(AVBPrint *buf, const char *p)
>                   break;
>               }
>           }
> +
>           if (!*p)
>               break;
>   
>           if (again) {
>               again = 0;
> -            skip = 0;
>               continue;
>           }
> -        if (*p == '<')
> -            skip = 1;
> -        else if (*p == '>')
> -            skip = 0;
> -        else if (p[0] == '\n' && p[1])
> +        if (p[0] == '\n' && p[1])
>               av_bprintf(buf, "\\N");
> -        else if (!skip && *p != '\r')
> +        else if (*p != '\r')
>               av_bprint_chars(buf, *p, 1);
>           p++;
>       }


_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".