[FFmpeg-devel,v2,4/9] vp9_parser: Return stream properties

Submitted by Mark Thompson on April 1, 2019, 11:39 p.m.

Details

Message ID 20190401233940.5941-4-sw@jkqxz.net
State New
Headers show

Commit Message

Mark Thompson April 1, 2019, 11:39 p.m.
Rewrites the parser entirely, using CBS for header parsing.
---
 libavcodec/vp9_parser.c | 112 +++++++++++++++++++++++++++++-----------
 1 file changed, 82 insertions(+), 30 deletions(-)

Comments

Zhong Li April 2, 2019, 4:04 a.m.
> From: ffmpeg-devel [mailto:ffmpeg-devel-bounces@ffmpeg.org] On Behalf

> Of Mark Thompson

> Sent: Tuesday, April 2, 2019 7:40 AM

> To: ffmpeg-devel@ffmpeg.org

> Subject: [FFmpeg-devel] [PATCH v2 4/9] vp9_parser: Return stream

> properties

> 

> Rewrites the parser entirely, using CBS for header parsing.

> ---

>  libavcodec/vp9_parser.c | 112 +++++++++++++++++++++++++++++-----------

>  1 file changed, 82 insertions(+), 30 deletions(-)

> 

> diff --git a/libavcodec/vp9_parser.c b/libavcodec/vp9_parser.c index

> c957a75667..6bf4f30e80 100644

> --- a/libavcodec/vp9_parser.c

> +++ b/libavcodec/vp9_parser.c

> @@ -1,8 +1,5 @@

>  /*

> - * VP9 compatible video decoder

> - *

> - * Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com>

> - * Copyright (C) 2013 Clément Bœsch <u pkh me>

> + * VP9 parser

>   *

>   * This file is part of FFmpeg.

>   *

> @@ -21,50 +18,105 @@

>   * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301

> USA

>   */

> 

> -#include "libavutil/intreadwrite.h"

> -#include "libavcodec/get_bits.h"

> +#include "libavutil/avassert.h"

> +#include "cbs.h"

> +#include "cbs_vp9.h"

>  #include "parser.h"

> 

> -static int parse(AVCodecParserContext *ctx,

> -                 AVCodecContext *avctx,

> -                 const uint8_t **out_data, int *out_size,

> -                 const uint8_t *data, int size)

> +typedef struct VP9ParserContext {

> +    CodedBitstreamContext *cbc;

> +    VP9RawFrameHeader frame_header;

> +} VP9ParserContext;

> +

> +static const enum AVPixelFormat vp9_pix_fmts[3][2][2] = {

> +    { // 8-bit.

> +        { AV_PIX_FMT_YUV444P, AV_PIX_FMT_YUV440P },

> +        { AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUV420P },

> +    },

> +    { // 10-bit.

> +        { AV_PIX_FMT_YUV444P10, AV_PIX_FMT_YUV440P10 },

> +        { AV_PIX_FMT_YUV422P10, AV_PIX_FMT_YUV420P10 },

> +    },

> +    { // 12-bit.

> +        { AV_PIX_FMT_YUV444P12, AV_PIX_FMT_YUV440P12 },

> +        { AV_PIX_FMT_YUV422P12, AV_PIX_FMT_YUV420P12 },

> +    },

> +};

> +

> +static int vp9_parser_parse(AVCodecParserContext *ctx,

> +                            AVCodecContext *avctx,

> +                            const uint8_t **out_data, int *out_size,

> +                            const uint8_t *data, int size)

>  {

> -    GetBitContext gb;

> -    int res, profile, keyframe;

> +    VP9ParserContext *s = ctx->priv_data;

> +    const CodedBitstreamVP9Context *vp9 = s->cbc->priv_data;

> +    const VP9RawFrameHeader *fh;

> +    int err;

> 

>      *out_data = data;

>      *out_size = size;

> 

> -    if (!size || (res = init_get_bits8(&gb, data, size)) < 0)

> -        return size; // parsers can't return errors

> -    get_bits(&gb, 2); // frame marker

> -    profile  = get_bits1(&gb);

> -    profile |= get_bits1(&gb) << 1;

> -    if (profile == 3) profile += get_bits1(&gb);

> -    if (profile > 3)

> -        return size;

> +    ctx->key_frame         = -1;

> +    ctx->pict_type         = AV_PICTURE_TYPE_NONE;

> +    ctx->picture_structure = AV_PICTURE_STRUCTURE_UNKNOWN;

> 

> -    avctx->profile = profile;

> +    if (!size)

> +        return 0;

> 

> -    if (get_bits1(&gb)) {

> -        keyframe = 0;

> -    } else {

> -        keyframe  = !get_bits1(&gb);

> +    s->cbc->log_ctx = avctx;

> +

> +    err = ff_cbs_parse_headers(s->cbc, &s->frame_header, data, size);

> +    if (err < 0) {

> +        av_log(avctx, AV_LOG_WARNING, "Failed to parse VP9 frame

> headers.\n");

> +        goto end;

>      }

> +    fh = &s->frame_header;

> 

> -    if (!keyframe) {

> -        ctx->pict_type = AV_PICTURE_TYPE_P;

> -        ctx->key_frame = 0;

> -    } else {

> +    avctx->profile = vp9->profile;

> +    avctx->level   = FF_LEVEL_UNKNOWN;

> +

> +    ctx->width  = ctx->coded_width  = vp9->frame_width;

> +    ctx->height = ctx->coded_height = vp9->frame_height;

> +

> +    if (fh->frame_type == VP9_KEY_FRAME) {

>          ctx->pict_type = AV_PICTURE_TYPE_I;

>          ctx->key_frame = 1;

> +    } else {

> +        ctx->pict_type = fh->intra_only ? AV_PICTURE_TYPE_I :

> AV_PICTURE_TYPE_P;

> +        ctx->key_frame = 0;

>      }

> 

> +    ctx->picture_structure = AV_PICTURE_STRUCTURE_FRAME;

> +

> +    av_assert0(vp9->bit_depth == 8  ||

> +               vp9->bit_depth == 10 ||

> +               vp9->bit_depth == 12);

> +

> +    ctx->format = vp9_pix_fmts[(vp9->bit_depth - 8) / 2]

> +

> [vp9->subsampling_x][vp9->subsampling_y];

> +

> +end:

> +    s->cbc->log_ctx = NULL;

> +

>      return size;

>  }

> 

> +static av_cold int vp9_parser_init(AVCodecParserContext *ctx) {

> +    VP9ParserContext *s = ctx->priv_data;

> +    return ff_cbs_init(&s->cbc, AV_CODEC_ID_VP9, NULL); }

> +

> +static av_cold void vp9_parser_close(AVCodecParserContext *ctx) {

> +    VP9ParserContext *s = ctx->priv_data;

> +    ff_cbs_close(&s->cbc);

> +}

> +

>  AVCodecParser ff_vp9_parser = {

>      .codec_ids      = { AV_CODEC_ID_VP9 },

> -    .parser_parse   = parse,

> +    .priv_data_size = sizeof(VP9ParserContext),

> +    .parser_init    = &vp9_parser_init,

> +    .parser_close   = &vp9_parser_close,

> +    .parser_parse   = &vp9_parser_parse,

>  };

> --

> 2.20.1


LGTM
Zhong Li April 28, 2019, 10:23 a.m.
> From: ffmpeg-devel [mailto:ffmpeg-devel-bounces@ffmpeg.org] On Behalf

> Of Mark Thompson

> Sent: Tuesday, April 2, 2019 7:40 AM

> To: ffmpeg-devel@ffmpeg.org

> Subject: [FFmpeg-devel] [PATCH v2 4/9] vp9_parser: Return stream

> properties

> 

> Rewrites the parser entirely, using CBS for header parsing.

> ---

>  libavcodec/vp9_parser.c | 112 +++++++++++++++++++++++++++++-----------

>  1 file changed, 82 insertions(+), 30 deletions(-)

> 

> diff --git a/libavcodec/vp9_parser.c b/libavcodec/vp9_parser.c index

> c957a75667..6bf4f30e80 100644

> --- a/libavcodec/vp9_parser.c

> +++ b/libavcodec/vp9_parser.c

> @@ -1,8 +1,5 @@

>  /*

> - * VP9 compatible video decoder

> - *

> - * Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com>

> - * Copyright (C) 2013 Clément Bœsch <u pkh me>

> + * VP9 parser

>   *

>   * This file is part of FFmpeg.

>   *

> @@ -21,50 +18,105 @@

>   * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301

> USA

>   */

> 

> -#include "libavutil/intreadwrite.h"

> -#include "libavcodec/get_bits.h"

> +#include "libavutil/avassert.h"

> +#include "cbs.h"

> +#include "cbs_vp9.h"

>  #include "parser.h"

> 

> -static int parse(AVCodecParserContext *ctx,

> -                 AVCodecContext *avctx,

> -                 const uint8_t **out_data, int *out_size,

> -                 const uint8_t *data, int size)

> +typedef struct VP9ParserContext {

> +    CodedBitstreamContext *cbc;

> +    VP9RawFrameHeader frame_header;

> +} VP9ParserContext;

> +

> +static const enum AVPixelFormat vp9_pix_fmts[3][2][2] = {

> +    { // 8-bit.

> +        { AV_PIX_FMT_YUV444P, AV_PIX_FMT_YUV440P },

> +        { AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUV420P },

> +    },

> +    { // 10-bit.

> +        { AV_PIX_FMT_YUV444P10, AV_PIX_FMT_YUV440P10 },

> +        { AV_PIX_FMT_YUV422P10, AV_PIX_FMT_YUV420P10 },

> +    },

> +    { // 12-bit.

> +        { AV_PIX_FMT_YUV444P12, AV_PIX_FMT_YUV440P12 },

> +        { AV_PIX_FMT_YUV422P12, AV_PIX_FMT_YUV420P12 },

> +    },

> +};

> +

> +static int vp9_parser_parse(AVCodecParserContext *ctx,

> +                            AVCodecContext *avctx,

> +                            const uint8_t **out_data, int *out_size,

> +                            const uint8_t *data, int size)

>  {

> -    GetBitContext gb;

> -    int res, profile, keyframe;

> +    VP9ParserContext *s = ctx->priv_data;

> +    const CodedBitstreamVP9Context *vp9 = s->cbc->priv_data;

> +    const VP9RawFrameHeader *fh;

> +    int err;

> 

>      *out_data = data;

>      *out_size = size;

> 

> -    if (!size || (res = init_get_bits8(&gb, data, size)) < 0)

> -        return size; // parsers can't return errors

> -    get_bits(&gb, 2); // frame marker

> -    profile  = get_bits1(&gb);

> -    profile |= get_bits1(&gb) << 1;

> -    if (profile == 3) profile += get_bits1(&gb);

> -    if (profile > 3)

> -        return size;

> +    ctx->key_frame         = -1;

> +    ctx->pict_type         = AV_PICTURE_TYPE_NONE;

> +    ctx->picture_structure = AV_PICTURE_STRUCTURE_UNKNOWN;

> 

> -    avctx->profile = profile;

> +    if (!size)

> +        return 0;

> 

> -    if (get_bits1(&gb)) {

> -        keyframe = 0;

> -    } else {

> -        keyframe  = !get_bits1(&gb);

> +    s->cbc->log_ctx = avctx;

> +

> +    err = ff_cbs_parse_headers(s->cbc, &s->frame_header, data, size);

> +    if (err < 0) {

> +        av_log(avctx, AV_LOG_WARNING, "Failed to parse VP9 frame

> headers.\n");

> +        goto end;

>      }

> +    fh = &s->frame_header;

> 

> -    if (!keyframe) {

> -        ctx->pict_type = AV_PICTURE_TYPE_P;

> -        ctx->key_frame = 0;

> -    } else {

> +    avctx->profile = vp9->profile;

> +    avctx->level   = FF_LEVEL_UNKNOWN;

> +

> +    ctx->width  = ctx->coded_width  = vp9->frame_width;

> +    ctx->height = ctx->coded_height = vp9->frame_height;

> +

> +    if (fh->frame_type == VP9_KEY_FRAME) {

>          ctx->pict_type = AV_PICTURE_TYPE_I;

>          ctx->key_frame = 1;

> +    } else {

> +        ctx->pict_type = fh->intra_only ? AV_PICTURE_TYPE_I :

> AV_PICTURE_TYPE_P;

> +        ctx->key_frame = 0;

>      }

> 

> +    ctx->picture_structure = AV_PICTURE_STRUCTURE_FRAME;

> +

> +    av_assert0(vp9->bit_depth == 8  ||

> +               vp9->bit_depth == 10 ||

> +               vp9->bit_depth == 12);

> +

> +    ctx->format = vp9_pix_fmts[(vp9->bit_depth - 8) / 2]

> +

> [vp9->subsampling_x][vp9->subsampling_y];

> +

> +end:

> +    s->cbc->log_ctx = NULL;

> +

>      return size;

>  }

> 

> +static av_cold int vp9_parser_init(AVCodecParserContext *ctx) {

> +    VP9ParserContext *s = ctx->priv_data;

> +    return ff_cbs_init(&s->cbc, AV_CODEC_ID_VP9, NULL); }

> +

> +static av_cold void vp9_parser_close(AVCodecParserContext *ctx) {

> +    VP9ParserContext *s = ctx->priv_data;

> +    ff_cbs_close(&s->cbc);

> +}

> +

>  AVCodecParser ff_vp9_parser = {

>      .codec_ids      = { AV_CODEC_ID_VP9 },

> -    .parser_parse   = parse,

> +    .priv_data_size = sizeof(VP9ParserContext),

> +    .parser_init    = &vp9_parser_init,

> +    .parser_close   = &vp9_parser_close,

> +    .parser_parse   = &vp9_parser_parse,

>  };

> --

> 2.20.1


Ping? Any issue block it to be merged?

Patch hide | download patch | download mbox

diff --git a/libavcodec/vp9_parser.c b/libavcodec/vp9_parser.c
index c957a75667..6bf4f30e80 100644
--- a/libavcodec/vp9_parser.c
+++ b/libavcodec/vp9_parser.c
@@ -1,8 +1,5 @@ 
 /*
- * VP9 compatible video decoder
- *
- * Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com>
- * Copyright (C) 2013 Clément Bœsch <u pkh me>
+ * VP9 parser
  *
  * This file is part of FFmpeg.
  *
@@ -21,50 +18,105 @@ 
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "libavutil/intreadwrite.h"
-#include "libavcodec/get_bits.h"
+#include "libavutil/avassert.h"
+#include "cbs.h"
+#include "cbs_vp9.h"
 #include "parser.h"
 
-static int parse(AVCodecParserContext *ctx,
-                 AVCodecContext *avctx,
-                 const uint8_t **out_data, int *out_size,
-                 const uint8_t *data, int size)
+typedef struct VP9ParserContext {
+    CodedBitstreamContext *cbc;
+    VP9RawFrameHeader frame_header;
+} VP9ParserContext;
+
+static const enum AVPixelFormat vp9_pix_fmts[3][2][2] = {
+    { // 8-bit.
+        { AV_PIX_FMT_YUV444P, AV_PIX_FMT_YUV440P },
+        { AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUV420P },
+    },
+    { // 10-bit.
+        { AV_PIX_FMT_YUV444P10, AV_PIX_FMT_YUV440P10 },
+        { AV_PIX_FMT_YUV422P10, AV_PIX_FMT_YUV420P10 },
+    },
+    { // 12-bit.
+        { AV_PIX_FMT_YUV444P12, AV_PIX_FMT_YUV440P12 },
+        { AV_PIX_FMT_YUV422P12, AV_PIX_FMT_YUV420P12 },
+    },
+};
+
+static int vp9_parser_parse(AVCodecParserContext *ctx,
+                            AVCodecContext *avctx,
+                            const uint8_t **out_data, int *out_size,
+                            const uint8_t *data, int size)
 {
-    GetBitContext gb;
-    int res, profile, keyframe;
+    VP9ParserContext *s = ctx->priv_data;
+    const CodedBitstreamVP9Context *vp9 = s->cbc->priv_data;
+    const VP9RawFrameHeader *fh;
+    int err;
 
     *out_data = data;
     *out_size = size;
 
-    if (!size || (res = init_get_bits8(&gb, data, size)) < 0)
-        return size; // parsers can't return errors
-    get_bits(&gb, 2); // frame marker
-    profile  = get_bits1(&gb);
-    profile |= get_bits1(&gb) << 1;
-    if (profile == 3) profile += get_bits1(&gb);
-    if (profile > 3)
-        return size;
+    ctx->key_frame         = -1;
+    ctx->pict_type         = AV_PICTURE_TYPE_NONE;
+    ctx->picture_structure = AV_PICTURE_STRUCTURE_UNKNOWN;
 
-    avctx->profile = profile;
+    if (!size)
+        return 0;
 
-    if (get_bits1(&gb)) {
-        keyframe = 0;
-    } else {
-        keyframe  = !get_bits1(&gb);
+    s->cbc->log_ctx = avctx;
+
+    err = ff_cbs_parse_headers(s->cbc, &s->frame_header, data, size);
+    if (err < 0) {
+        av_log(avctx, AV_LOG_WARNING, "Failed to parse VP9 frame headers.\n");
+        goto end;
     }
+    fh = &s->frame_header;
 
-    if (!keyframe) {
-        ctx->pict_type = AV_PICTURE_TYPE_P;
-        ctx->key_frame = 0;
-    } else {
+    avctx->profile = vp9->profile;
+    avctx->level   = FF_LEVEL_UNKNOWN;
+
+    ctx->width  = ctx->coded_width  = vp9->frame_width;
+    ctx->height = ctx->coded_height = vp9->frame_height;
+
+    if (fh->frame_type == VP9_KEY_FRAME) {
         ctx->pict_type = AV_PICTURE_TYPE_I;
         ctx->key_frame = 1;
+    } else {
+        ctx->pict_type = fh->intra_only ? AV_PICTURE_TYPE_I : AV_PICTURE_TYPE_P;
+        ctx->key_frame = 0;
     }
 
+    ctx->picture_structure = AV_PICTURE_STRUCTURE_FRAME;
+
+    av_assert0(vp9->bit_depth == 8  ||
+               vp9->bit_depth == 10 ||
+               vp9->bit_depth == 12);
+
+    ctx->format = vp9_pix_fmts[(vp9->bit_depth - 8) / 2]
+                              [vp9->subsampling_x][vp9->subsampling_y];
+
+end:
+    s->cbc->log_ctx = NULL;
+
     return size;
 }
 
+static av_cold int vp9_parser_init(AVCodecParserContext *ctx)
+{
+    VP9ParserContext *s = ctx->priv_data;
+    return ff_cbs_init(&s->cbc, AV_CODEC_ID_VP9, NULL);
+}
+
+static av_cold void vp9_parser_close(AVCodecParserContext *ctx)
+{
+    VP9ParserContext *s = ctx->priv_data;
+    ff_cbs_close(&s->cbc);
+}
+
 AVCodecParser ff_vp9_parser = {
     .codec_ids      = { AV_CODEC_ID_VP9 },
-    .parser_parse   = parse,
+    .priv_data_size = sizeof(VP9ParserContext),
+    .parser_init    = &vp9_parser_init,
+    .parser_close   = &vp9_parser_close,
+    .parser_parse   = &vp9_parser_parse,
 };