diff --git a/doc/APIchanges b/doc/APIchanges index ba137650b6..c8c2a219f6 100644 --- a/doc/APIchanges +++ b/doc/APIchanges @@ -13,6 +13,10 @@ libavutil: 2015-08-28 API changes, most recent first: +2016-xx-xx - xxxxxxx - lavc 57.31.0 - avcodec.h + Add AVCodecContext.apply_cropping to control whether cropping + is handled by libavcodec or the caller. + 2016-xx-xx - xxxxxxx - lavu 55.30.0 - frame.h Add AVFrame.crop_left/right/top/bottom fields for attaching cropping information to video frames. diff --git a/libavcodec/avcodec.h b/libavcodec/avcodec.h index 95da50b0e7..18721561d5 100644 --- a/libavcodec/avcodec.h +++ b/libavcodec/avcodec.h @@ -3112,6 +3112,33 @@ typedef struct AVCodecContext { * This field should be set before avcodec_open2() is called. */ AVBufferRef *hw_frames_ctx; + + /** + * Video decoding only. Certain video codecs support cropping, meaning that + * only a sub-rectangle of the decoded frame is intended for display. This + * option controls how cropping is handled by libavcodec. + * + * When set to 1 (the default), libavcodec will apply cropping internally. + * I.e. it will modify the output frame width/height fields and offset the + * data pointers (only by as much as possible while preserving alignment, or + * by the full amount if the AV_CODEC_FLAG_UNALIGNED flag is set) so that + * the frames output by the decoder refer only to the cropped area. The + * crop_* fields of the output frames will be zero. + * + * When set to 0, the width/height fields of the output frames will be set + * to the coded dimensions and the crop_* fields will describe the cropping + * rectangle. Applying the cropping is left to the caller. + * + * @warning When hardware acceleration with opaque output frames is used, + * libavcodec is unable to apply cropping from the top/left border. + * + * @note when this option is set to zero, the width/height fields of the + * AVCodecContext and output AVFrames have different meanings. The codec + * context fields store display dimensions (with the coded dimensions in + * coded_width/height), while the frame fields store the coded dimensions + * (with the display dimensions being determined by the crop_* fields). + */ + int apply_cropping; } AVCodecContext; /** diff --git a/libavcodec/decode.c b/libavcodec/decode.c index 0fd41ab482..f4088cdae8 100644 --- a/libavcodec/decode.c +++ b/libavcodec/decode.c @@ -29,6 +29,7 @@ #include "libavutil/frame.h" #include "libavutil/hwcontext.h" #include "libavutil/imgutils.h" +#include "libavutil/intmath.h" #include "avcodec.h" #include "bytestream.h" @@ -450,6 +451,111 @@ int attribute_align_arg avcodec_send_packet(AVCodecContext *avctx, const AVPacke return 0; } +static int calc_cropping_offsets(size_t offsets[4], const AVFrame *frame, + const AVPixFmtDescriptor *desc) +{ + int i, j; + + for (i = 0; frame->data[i]; i++) { + const AVComponentDescriptor *comp = NULL; + int shift_x = (i == 1 || i == 2) ? desc->log2_chroma_w : 0; + int shift_y = (i == 1 || i == 2) ? desc->log2_chroma_h : 0; + + if (desc->flags & (AV_PIX_FMT_FLAG_PAL | AV_PIX_FMT_FLAG_PSEUDOPAL) && i == 1) { + offsets[i] = 0; + break; + } + + /* find any component descriptor for this plane */ + for (j = 0; j < desc->nb_components; j++) { + if (desc->comp[j].plane == i) { + comp = &desc->comp[j]; + break; + } + } + if (!comp) + return AVERROR_BUG; + + offsets[i] = (frame->crop_top >> shift_y) * frame->linesize[i] + + (frame->crop_left >> shift_x) * comp->step; + } + + return 0; +} + +static int apply_cropping(AVCodecContext *avctx, AVFrame *frame) +{ + const AVPixFmtDescriptor *desc; + size_t offsets[4]; + int i; + + /* make sure we are noisy about decoders returning invalid cropping data */ + if (frame->crop_left >= INT_MAX - frame->crop_right || + frame->crop_top >= INT_MAX - frame->crop_bottom || + (frame->crop_left + frame->crop_right) >= frame->width || + (frame->crop_top + frame->crop_bottom) >= frame->height) { + av_log(avctx, AV_LOG_WARNING, + "Invalid cropping information set by a decoder: %zu/%zu/%zu/%zu " + "(frame size %dx%d). This is a bug, please report it\n", + frame->crop_left, frame->crop_right, frame->crop_top, frame->crop_bottom, + frame->width, frame->height); + frame->crop_left = 0; + frame->crop_right = 0; + frame->crop_top = 0; + frame->crop_bottom = 0; + return 0; + } + + if (!avctx->apply_cropping) + return 0; + + desc = av_pix_fmt_desc_get(frame->format); + if (!desc) + return AVERROR_BUG; + + /* Apply just the right/bottom cropping for hwaccel formats. Bitstream + * formats cannot be easily handled here either (and corresponding decoders + * should not export any cropping anyway), so do the same for those as well. + * */ + if (desc->flags & (AV_PIX_FMT_FLAG_BITSTREAM | AV_PIX_FMT_FLAG_HWACCEL)) { + frame->width -= frame->crop_right; + frame->height -= frame->crop_bottom; + frame->crop_right = 0; + frame->crop_bottom = 0; + return 0; + } + + /* calculate the offsets for each plane */ + calc_cropping_offsets(offsets, frame, desc); + + /* adjust the offsets to avoid breaking alignment */ + if (!(avctx->flags & AV_CODEC_FLAG_UNALIGNED)) { + int min_log2_align = INT_MAX; + + for (i = 0; frame->data[i]; i++) { + int log2_align = offsets[i] ? av_ctz(offsets[i]) : INT_MAX; + min_log2_align = FFMIN(log2_align, min_log2_align); + } + + if (min_log2_align < 5) { + frame->crop_left &= ~((1 << min_log2_align) - 1); + calc_cropping_offsets(offsets, frame, desc); + } + } + + for (i = 0; frame->data[i]; i++) + frame->data[i] += offsets[i]; + + frame->width -= (frame->crop_left + frame->crop_right); + frame->height -= (frame->crop_top + frame->crop_bottom); + frame->crop_left = 0; + frame->crop_right = 0; + frame->crop_top = 0; + frame->crop_bottom = 0; + + return 0; +} + int attribute_align_arg avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame) { AVCodecInternal *avci = avctx->internal; @@ -472,6 +578,14 @@ int attribute_align_arg avcodec_receive_frame(AVCodecContext *avctx, AVFrame *fr return ret; } + if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) { + ret = apply_cropping(avctx, frame); + if (ret < 0) { + av_frame_unref(frame); + return ret; + } + } + avctx->frame_number++; return 0; @@ -1029,7 +1143,8 @@ int ff_get_buffer(AVCodecContext *avctx, AVFrame *frame, int flags) ret = avctx->get_buffer2(avctx, frame, flags); end: - if (avctx->codec_type == AVMEDIA_TYPE_VIDEO && !override_dimensions) { + if (avctx->codec_type == AVMEDIA_TYPE_VIDEO && !override_dimensions && + !(avctx->codec->caps_internal & FF_CODEC_CAP_EXPORTS_CROPPING)) { frame->width = avctx->width; frame->height = avctx->height; } diff --git a/libavcodec/internal.h b/libavcodec/internal.h index 796d45ff6e..5b82504bfb 100644 --- a/libavcodec/internal.h +++ b/libavcodec/internal.h @@ -53,6 +53,12 @@ * from the input AVPacket. */ #define FF_CODEC_CAP_SETS_PKT_DTS (1 << 2) +/** + * The decoder sets the cropping fields in the output frames manually. + * If this cap is set, the generic code will initialize output frame + * dimensions to coded rather than display values. + */ +#define FF_CODEC_CAP_EXPORTS_CROPPING (1 << 3) #ifdef DEBUG # define ff_dlog(ctx, ...) av_log(ctx, AV_LOG_DEBUG, __VA_ARGS__) diff --git a/libavcodec/options_table.h b/libavcodec/options_table.h index 4deb223552..3ac53fb748 100644 --- a/libavcodec/options_table.h +++ b/libavcodec/options_table.h @@ -531,6 +531,7 @@ static const AVOption avcodec_options[] = { #if FF_API_SIDEDATA_ONLY_PKT {"side_data_only_packets", NULL, OFFSET(side_data_only_packets), AV_OPT_TYPE_INT, { .i64 = 1 }, 0, 1, A|V|E }, #endif +{"apply_cropping", NULL, OFFSET(apply_cropping), AV_OPT_TYPE_INT, { .i64 = 1 }, 0, 1, V | D }, {NULL}, }; diff --git a/libavcodec/version.h b/libavcodec/version.h index 106543de53..df0c01f4cc 100644 --- a/libavcodec/version.h +++ b/libavcodec/version.h @@ -28,8 +28,8 @@ #include "libavutil/version.h" #define LIBAVCODEC_VERSION_MAJOR 57 -#define LIBAVCODEC_VERSION_MINOR 30 -#define LIBAVCODEC_VERSION_MICRO 4 +#define LIBAVCODEC_VERSION_MINOR 31 +#define LIBAVCODEC_VERSION_MICRO 0 #define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \ LIBAVCODEC_VERSION_MINOR, \