This is an automated email from the git hooks/post-receive script. Git pushed a commit to branch master in repository ffmpeg.
commit 4eb9cb07d9e8b9f6de4890be0bd743695e2c0396 Author: Jun Zhao <[email protected]> AuthorDate: Mon Sep 28 07:00:19 2026 +0800 Commit: Jun Zhao <[email protected]> CommitDate: Mon Sep 28 01:08:27 2026 +0000 avcodec/webvttenc: convert ASS karaoke tags into WebVTT cue timestamps Synthesize WebVTT inline cue timestamps (<MM:SS.mmm> or <HH:MM:SS.mmm>) from ASS karaoke overrides (\k, \K, \kf, \ko) using the subtitle PTS and duration baseline. Per W3C WebVTT specification and webvttdec compatibility: - Timestamps represent absolute positions on the media timeline. - Inline timestamps must fall strictly within the cue boundary (cue_start < timestamp < cue_end) and remain strictly monotonic. - Consecutive syllable durations are accumulated and flushed upon subsequent syllable tags or cue completion. - Ending timestamps matching cue_end are omitted; webvttdec automatically telescopes the final duration up to cue_end on decoding. - If PTS is unavailable, or the subtitle contains more than one rectangle, timestamps are suppressed and plain text is emitted as fallback. Independent rectangles cannot be concatenated into one monotonic cue. Fixes: ticket #23879 Signed-off-by: Jun Zhao <[email protected]> --- libavcodec/webvttenc.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 61 insertions(+), 1 deletion(-) diff --git a/libavcodec/webvttenc.c b/libavcodec/webvttenc.c index d5d3ddd17c..d538f45271 100644 --- a/libavcodec/webvttenc.c +++ b/libavcodec/webvttenc.c @@ -34,6 +34,11 @@ typedef struct { AVBPrint buffer; unsigned timestamp_end; int count; + int64_t cue_start_ms; + int64_t cue_end_ms; + int64_t current_time_ms; + int64_t last_timestamp_ms; + int64_t pending_duration_ms; char stack[WEBVTT_STACK_SIZE]; int stack_ptr; } WebVTTContext; @@ -106,6 +111,37 @@ static void webvtt_style_apply(WebVTTContext *s, const char *style) } } +static void webvtt_print_timestamp(WebVTTContext *s, int64_t millisec) +{ + int64_t sec = millisec / 1000; + millisec %= 1000; + int64_t min = sec / 60; + sec %= 60; + int64_t hour = min / 60; + min %= 60; + if (hour > 0) { + webvtt_print(s, "<%02"PRId64":%02"PRId64":%02"PRId64".%03"PRId64">", hour, min, sec, millisec); + } else { + webvtt_print(s, "<%02"PRId64":%02"PRId64".%03"PRId64">", min, sec, millisec); + } +} + +static void webvtt_flush_karaoke_timestamp(WebVTTContext *s) +{ + if (s->pending_duration_ms <= 0) + return; + + int64_t next_ts = s->current_time_ms <= INT64_MAX - s->pending_duration_ms ? + s->current_time_ms + s->pending_duration_ms : INT64_MAX; + if (next_ts > s->cue_start_ms && next_ts < s->cue_end_ms && + next_ts > s->last_timestamp_ms) { + webvtt_print_timestamp(s, next_ts); + s->last_timestamp_ms = next_ts; + } + s->current_time_ms = next_ts; + s->pending_duration_ms = 0; +} + static void webvtt_text_cb(void *priv, const char *text, int len) { WebVTTContext *s = priv; @@ -114,7 +150,16 @@ static void webvtt_text_cb(void *priv, const char *text, int len) static void webvtt_new_line_cb(void *priv, int forced) { - webvtt_print(priv, "\n"); + WebVTTContext *s = priv; + webvtt_print(s, "\n"); +} + +static void webvtt_karaoke_cb(void *priv, unsigned int duration) +{ + WebVTTContext *s = priv; + + webvtt_flush_karaoke_timestamp(s); + s->pending_duration_ms = (int64_t)duration * 10; } static void webvtt_style_cb(void *priv, char style, int close) @@ -135,6 +180,8 @@ static void webvtt_cancel_overrides_cb(void *priv, const char *style) static void webvtt_end_cb(void *priv) { + WebVTTContext *s = priv; + webvtt_flush_karaoke_timestamp(s); webvtt_stack_push_pop(priv, 0, 1); } @@ -148,6 +195,7 @@ static const ASSCodesCallbacks webvtt_callbacks = { .alignment = NULL, .cancel_overrides = webvtt_cancel_overrides_cb, .move = NULL, + .karaoke = webvtt_karaoke_cb, .end = webvtt_end_cb, }; @@ -160,6 +208,18 @@ static int webvtt_encode_frame(AVCodecContext *avctx, av_bprint_init_for_buffer(&s->buffer, buf, bufsize); + /* Multiple rectangles are independent overlays. One monotonic WebVTT + * cue cannot represent them, so keep the previous plain-text path. */ + if (sub->pts != AV_NOPTS_VALUE && sub->num_rects == 1) { + s->cue_start_ms = av_rescale_q(sub->pts, AV_TIME_BASE_Q, (AVRational){ 1, 1000 }); + s->cue_end_ms = s->cue_start_ms + sub->end_display_time; + } else { + s->cue_start_ms = s->cue_end_ms = 0; + } + s->current_time_ms = s->cue_start_ms; + s->last_timestamp_ms = -1; + s->pending_duration_ms = 0; + for (i=0; i<sub->num_rects; i++) { const char *ass = sub->rects[i]->ass; -- To stop receiving notification emails like this one, please contact [email protected]. _______________________________________________ ffmpeg-cvslog mailing list -- [email protected] To unsubscribe send an email to [email protected]
