lavc/rawdec: Use 16-byte line alignment for 1, 2, 4 and 8 bpp

This patch aligns the lines of 1 bpp depth for QuickTime, and 2, 4 and 8
bpp depths for AVI and QuickTime, on 16-byte boundaries. At the same
time, the packet row stride is properly catered for.

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This commit is contained in:
Mats Peterson 2016-01-25 03:59:49 +01:00 committed by Michael Niedermayer
parent fe7639b1c8
commit 82325dbec1

View File

@ -41,7 +41,7 @@ typedef struct RawVideoContext {
AVBufferRef *palette;
int frame_size; /* size of the frame in bytes */
int flip;
int is_1_2_4_bpp; // 1 bpp raw in mov, and 2 or 4 bpp raw in avi/mov
int is_1_2_4_8_bpp; // 1 bpp in mov, and 2, 4 and 8 bpp in avi/mov
int is_yuv2;
int is_lt_16bpp; // 16bpp pixfmt and bits_per_coded_sample < 16
int tff;
@ -156,19 +156,20 @@ static int raw_decode(AVCodecContext *avctx, void *data, int *got_frame,
RawVideoContext *context = avctx->priv_data;
const uint8_t *buf = avpkt->data;
int buf_size = avpkt->size;
int avpkt_stride = avpkt->size / avctx->height;
int linesize_align = 4;
int res, len;
int need_copy;
AVFrame *frame = data;
if ((avctx->bits_per_coded_sample == 4 || avctx->bits_per_coded_sample == 2
|| avctx->bits_per_coded_sample == 1) &&
if ((avctx->bits_per_coded_sample == 8 || avctx->bits_per_coded_sample == 4
|| avctx->bits_per_coded_sample == 2 || avctx->bits_per_coded_sample == 1) &&
avctx->pix_fmt == AV_PIX_FMT_PAL8 &&
(!avctx->codec_tag || avctx->codec_tag == MKTAG('r','a','w',' '))) {
context->is_1_2_4_bpp = 1;
context->is_1_2_4_8_bpp = 1;
context->frame_size = av_image_get_buffer_size(avctx->pix_fmt,
FFALIGN(avctx->width, 32),
FFALIGN(avctx->width, 16),
avctx->height, 1);
} else {
context->is_lt_16bpp = av_get_bits_per_pixel(desc) == 16 && avctx->bits_per_coded_sample && avctx->bits_per_coded_sample < 16;
@ -178,7 +179,7 @@ static int raw_decode(AVCodecContext *avctx, void *data, int *got_frame,
if (context->frame_size < 0)
return context->frame_size;
need_copy = !avpkt->buf || context->is_1_2_4_bpp || context->is_yuv2 || context->is_lt_16bpp;
need_copy = !avpkt->buf || context->is_1_2_4_8_bpp || context->is_yuv2 || context->is_lt_16bpp;
frame->pict_type = AV_PICTURE_TYPE_I;
frame->key_frame = 1;
@ -205,39 +206,65 @@ static int raw_decode(AVCodecContext *avctx, void *data, int *got_frame,
if (!frame->buf[0])
return AVERROR(ENOMEM);
// 1 bpp raw in mov, and 2 or 4 bpp raw in avi/mov
if (context->is_1_2_4_bpp) {
int i;
// 1 bpp in mov, and 2, 4 and 8 bpp in avi/mov
if (context->is_1_2_4_8_bpp) {
int i, j, row_pix = 0;
uint8_t *dst = frame->buf[0]->data;
buf_size = context->frame_size - AVPALETTE_SIZE;
if (avctx->bits_per_coded_sample == 4) {
for (i = 0; 2 * i + 1 < buf_size && i<avpkt->size; i++) {
dst[2 * i + 0] = buf[i] >> 4;
dst[2 * i + 1] = buf[i] & 15;
if (avctx->bits_per_coded_sample == 8) {
for (i = 0, j = 0; j < buf_size && i<avpkt->size; i++, j++) {
dst[j] = buf[i];
row_pix++;
if (row_pix == avctx->width) {
i += avpkt_stride - (i % avpkt_stride) - 1;
j += 16 - (j % 16) - 1;
row_pix = 0;
}
}
} else if (avctx->bits_per_coded_sample == 4) {
for (i = 0, j = 0; 2 * j + 1 < buf_size && i<avpkt->size; i++, j++) {
dst[2 * j + 0] = buf[i] >> 4;
dst[2 * j + 1] = buf[i] & 15;
row_pix += 2;
if (row_pix >= avctx->width) {
i += avpkt_stride - (i % avpkt_stride) - 1;
j += 8 - (j % 8) - 1;
row_pix = 0;
}
}
linesize_align = 8;
} else if (avctx->bits_per_coded_sample == 2) {
for (i = 0; 4 * i + 3 < buf_size && i<avpkt->size; i++) {
dst[4 * i + 0] = buf[i] >> 6;
dst[4 * i + 1] = buf[i] >> 4 & 3;
dst[4 * i + 2] = buf[i] >> 2 & 3;
dst[4 * i + 3] = buf[i] & 3;
for (i = 0, j = 0; 4 * j + 3 < buf_size && i<avpkt->size; i++, j++) {
dst[4 * j + 0] = buf[i] >> 6;
dst[4 * j + 1] = buf[i] >> 4 & 3;
dst[4 * j + 2] = buf[i] >> 2 & 3;
dst[4 * j + 3] = buf[i] & 3;
row_pix += 4;
if (row_pix >= avctx->width) {
i += avpkt_stride - (i % avpkt_stride) - 1;
j += 4 - (j % 4) - 1;
row_pix = 0;
}
}
linesize_align = 16;
} else {
av_assert0(avctx->bits_per_coded_sample == 1);
for (i = 0; 8 * i + 7 < buf_size && i<avpkt->size; i++) {
dst[8 * i + 0] = buf[i] >> 7 & 1;
dst[8 * i + 1] = buf[i] >> 6 & 1;
dst[8 * i + 2] = buf[i] >> 5 & 1;
dst[8 * i + 3] = buf[i] >> 4 & 1;
dst[8 * i + 4] = buf[i] >> 3 & 1;
dst[8 * i + 5] = buf[i] >> 2 & 1;
dst[8 * i + 6] = buf[i] >> 1 & 1;
dst[8 * i + 7] = buf[i] & 1;
for (i = 0, j = 0; 8 * j + 7 < buf_size && i<avpkt->size; i++, j++) {
dst[8 * j + 0] = buf[i] >> 7;
dst[8 * j + 1] = buf[i] >> 6 & 1;
dst[8 * j + 2] = buf[i] >> 5 & 1;
dst[8 * j + 3] = buf[i] >> 4 & 1;
dst[8 * j + 4] = buf[i] >> 3 & 1;
dst[8 * j + 5] = buf[i] >> 2 & 1;
dst[8 * j + 6] = buf[i] >> 1 & 1;
dst[8 * j + 7] = buf[i] & 1;
row_pix += 8;
if (row_pix >= avctx->width) {
i += avpkt_stride - (i % avpkt_stride) - 1;
j += 2 - (j % 2) - 1;
row_pix = 0;
}
}
linesize_align = 32;
}
linesize_align = 16;
buf = dst;
} else if (context->is_lt_16bpp) {
uint8_t *dst = frame->buf[0]->data;