[FFmpeg-devel] [PATCH 3/4] avformat/samidec: UTF-16 support

[Clément Bœsch]

On Tue, Sep 02, 2014 at 08:56:11PM +0200, wm4 wrote:
> ff_smil_extract_next_chunk() is still used by RealText.
> ---
>  libavformat/samidec.c   | 17 ++++++++++-------
>  libavformat/subtitles.c | 15 ++++++++++++---
>  libavformat/subtitles.h |  5 +++++
>  3 files changed, 27 insertions(+), 10 deletions(-)
> 
> diff --git a/libavformat/samidec.c b/libavformat/samidec.c
> index 1a12eca..4dbf2cf 100644
> --- a/libavformat/samidec.c
> +++ b/libavformat/samidec.c
> @@ -38,11 +38,12 @@ typedef struct {
>  
>  static int sami_probe(AVProbeData *p)
>  {
> -    const unsigned char *ptr = p->buf;
> +    char buf[6];
> +    FFTextReader tr;
> +    ff_text_init_buf(&tr, p->buf, p->buf_size);
> +    ff_text_read(&tr, buf, sizeof(buf));
>  
> -    if (AV_RB24(ptr) == 0xEFBBBF)
> -        ptr += 3;  /* skip UTF-8 BOM */
> -    return !strncmp(ptr, "<SAMI>", 6) ? AVPROBE_SCORE_MAX : 0;
> +    return !strncmp(buf, "<SAMI>", 6) ? AVPROBE_SCORE_MAX : 0;
>  }
>  
>  static int sami_read_header(AVFormatContext *s)
> @@ -52,6 +53,8 @@ static int sami_read_header(AVFormatContext *s)
>      AVBPrint buf, hdr_buf;
>      char c = 0;
>      int res = 0, got_first_sync_point = 0;
> +    FFTextReader tr;
> +    ff_text_init_avio(&tr, s->pb);
>  
>      if (!st)
>          return AVERROR(ENOMEM);
> @@ -62,10 +65,10 @@ static int sami_read_header(AVFormatContext *s)
>      av_bprint_init(&buf,     0, AV_BPRINT_SIZE_UNLIMITED);
>      av_bprint_init(&hdr_buf, 0, AV_BPRINT_SIZE_UNLIMITED);
>  
> -    while (!avio_feof(s->pb)) {
> +    while (!ff_text_eof(&tr)) {
>          AVPacket *sub;
> -        const int64_t pos = avio_tell(s->pb) - (c != 0);
> -        int is_sync, n = ff_smil_extract_next_chunk(s->pb, &buf, &c);
> +        const int64_t pos = ff_text_pos(&tr) - (c != 0);
> +        int is_sync, n = ff_smil_extract_next_text_chunk(&tr, &buf, &c);
>  
>          if (n == 0)
>              break;
> diff --git a/libavformat/subtitles.c b/libavformat/subtitles.c
> index 1641aae..b8b680e 100644
> --- a/libavformat/subtitles.c
> +++ b/libavformat/subtitles.c
> @@ -272,20 +272,20 @@ void ff_subtitles_queue_clean(FFDemuxSubtitlesQueue *q)
>      q->nb_subs = q->allocated_size = q->current_sub_idx = 0;
>  }
>  
> -int ff_smil_extract_next_chunk(AVIOContext *pb, AVBPrint *buf, char *c)
> +int ff_smil_extract_next_text_chunk(FFTextReader *tr, AVBPrint *buf, char *c)
>  {
>      int i = 0;
>      char end_chr;
>  
>      if (!*c) // cached char?
> -        *c = avio_r8(pb);
> +        *c = ff_text_r8(tr);
>      if (!*c)
>          return 0;
>  
>      end_chr = *c == '<' ? '>' : '<';
>      do {
>          av_bprint_chars(buf, *c, 1);
> -        *c = avio_r8(pb);
> +        *c = ff_text_r8(tr);
>          i++;
>      } while (*c != end_chr && *c);
>      if (end_chr == '>') {
> @@ -295,6 +295,15 @@ int ff_smil_extract_next_chunk(AVIOContext *pb, AVBPrint *buf, char *c)
>      return i;
>  }
>  

> +int ff_smil_extract_next_chunk(AVIOContext *pb, AVBPrint *buf, char *c)
> +{
> +    FFTextReader tr;
> +    tr.buf_pos = tr.buf_len = 0;
> +    tr.type = 0;
> +    tr.pb = pb;
> +    return ff_smil_extract_next_text_chunk(&tr, buf, c);

How can this work with utf-16? Aren't you supposed to use the type
obtained after the ff_text_init_avio() in sami_read_header() or something
along those lines?

[...]

-- 
Clément B.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 473 bytes
Desc: not available
URL: <https://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20140903/6be702ea/attachment.asc>