使用ffmpeg进行图片格式转换和图片缩放—jpg to yuv420/.mp4 to yuv420

//.h

#ifndef   _JPG_PROCESS_H
#define   _JPG_PROCESS_H


#if !defined PRId64 || PRI_MACROS_BROKEN
# undef PRId64
# define PRId64 "lld"
#endif


#ifndef INT64_C
#define INT64_C
#define UINT64_C
#endif

#include <stdlib.h> 

namespace ffmpeg{
extern "C"
{
#include <libavutil/imgutils.h>
#include <libavutil/samplefmt.h>
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
#include <libavutil/parseutils.h>
#include <libswscale/swscale.h>
}
}

using namespace ffmpeg;

struct JpgProcessParam
{
    AVFormatContext *fmt_ctx;
    AVCodecContext *video_dec_ctx, *audio_dec_ctx;
    AVStream *video_stream, *audio_stream;

    char *in_filename;
    char *out_filename;
    char *audio_dst_filename;

    FILE *video_dst_file;
    FILE *audio_dst_file;

    uint8_t *video_dst_data[4];
    int      video_dst_linesize[4];
    int video_dst_bufsize;

    int video_stream_idx, audio_stream_idx;
    AVFrame *frame;
    AVPacket pkt;
    int video_frame_count;
    int audio_frame_count;
};

class JpgProcess
{
private:
    int decode_packet(int *got_frame, int cached);
    int open_codec_context(int *stream_idx, AVFormatContext *fmt_ctx, enum AVMediaType type);
    int get_format_from_sample_fmt(const char **fmt, enum AVSampleFormat sample_fmt);
    int main_jpg();

    JpgProcessParam jpgProcessParam;

public:
    bool jpgprocess(char *src_filename, char *dst_filename);
     
};

#endif 

//.cpp

#include "jpgprocess.h"

bool JpgProcess::jpgprocess(char *src_filename, char *dst_filename)
{
    if ((NULL == src_filename) || (NULL == dst_filename))
        return false;

    memset(&jpgProcessParam, 0x00, sizeof(jpgProcessParam));

    jpgProcessParam.in_filename = src_filename;
    jpgProcessParam.out_filename = dst_filename;

    main_jpg();
   
    return true;
}

int JpgProcess::main_jpg()
{
    int ret = 0, got_frame;

    /* register all formats and codecs */
    av_register_all();

    /* open input file, and allocate format context */
    if (avformat_open_input(&jpgProcessParam.fmt_ctx, jpgProcessParam.in_filename, NULL, NULL) < 0) {
        fprintf(stderr, "Could not open source file %s\n", jpgProcessParam.in_filename);
        exit(1);
    }

    /* retrieve stream information */
    if (avformat_find_stream_info(jpgProcessParam.fmt_ctx, NULL) < 0) {
        fprintf(stderr, "Could not find stream information\n");
        exit(1);
    }

    if (open_codec_context(&jpgProcessParam.video_stream_idx, jpgProcessParam.fmt_ctx, AVMEDIA_TYPE_VIDEO) >= 0) {
        jpgProcessParam.video_stream = jpgProcessParam.fmt_ctx->streams[jpgProcessParam.video_stream_idx];
        jpgProcessParam.video_dec_ctx = jpgProcessParam.video_stream->codec;

        jpgProcessParam.video_dst_file = fopen(jpgProcessParam.out_filename, "wb");
        if (!jpgProcessParam.video_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", jpgProcessParam.out_filename);
            ret = 1;
            goto end;
        }

        /* allocate image where the decoded image will be put */
        ret = av_image_alloc(jpgProcessParam.video_dst_data, jpgProcessParam.video_dst_linesize,
                             jpgProcessParam.video_dec_ctx->width, jpgProcessParam.video_dec_ctx->height,
                             jpgProcessParam.video_dec_ctx->pix_fmt, 1);
        if (ret < 0) {
            fprintf(stderr, "Could not allocate raw video buffer\n");
            goto end;
        }

        jpgProcessParam.video_dst_bufsize = ret;
    }

    if (open_codec_context(&jpgProcessParam.audio_stream_idx, jpgProcessParam.fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
        jpgProcessParam.audio_stream = jpgProcessParam.fmt_ctx->streams[jpgProcessParam.audio_stream_idx];
        jpgProcessParam.audio_dec_ctx = jpgProcessParam.audio_stream->codec;
        jpgProcessParam.audio_dst_file = fopen(jpgProcessParam.audio_dst_filename, "wb");
        if (!jpgProcessParam.audio_dst_file) {
            fprintf(stderr, "Could not open destination file %s\n", jpgProcessParam.out_filename);
            ret = 1;
            goto end;
        }
    }

    /* dump input information to stderr */
    av_dump_format(jpgProcessParam.fmt_ctx, 0, jpgProcessParam.in_filename, 0);

    if (!jpgProcessParam.audio_stream && !jpgProcessParam.video_stream) {
        fprintf(stderr, "Could not find audio or video stream in the input, aborting\n");
        ret = 1;
        goto end;
    }

    jpgProcessParam.frame = avcodec_alloc_frame();
    if (!jpgProcessParam.frame) {
        fprintf(stderr, "Could not allocate frame\n");
        ret = AVERROR(ENOMEM);
        goto end;
    }

    /* initialize packet, set data to NULL, let the demuxer fill it */
    av_init_packet(&jpgProcessParam.pkt);
    jpgProcessParam.pkt.data = NULL;
    jpgProcessParam.pkt.size = 0;

    if (jpgProcessParam.video_stream)
        printf("Demuxing video from file '%s' into '%s'\n", jpgProcessParam.in_filename, jpgProcessParam.out_filename);
    if (jpgProcessParam.audio_stream)
        printf("Demuxing audio from file '%s' into '%s'\n", jpgProcessParam.in_filename, jpgProcessParam.audio_dst_filename);

    /* read frames from the file */
    while (av_read_frame(jpgProcessParam.fmt_ctx, &jpgProcessParam.pkt) >= 0) {
        AVPacket orig_pkt = jpgProcessParam.pkt;
        do {
            ret = decode_packet(&got_frame, 0);
            if (ret < 0)
                break;
            jpgProcessParam.pkt.data += ret;
            jpgProcessParam.pkt.size -= ret;
        } while (jpgProcessParam.pkt.size > 0);
        av_free_packet(&orig_pkt);
    }

    /* flush cached frames */
    jpgProcessParam.pkt.data = NULL;
    jpgProcessParam.pkt.size = 0;
    do {
        decode_packet(&got_frame, 1);
    } while (got_frame);

    printf("Demuxing succeeded.\n");

    if (jpgProcessParam.video_stream) {
        printf("Play the output video file with the command:\n"
               "ffplay -f rawvideo -pix_fmt %s -video_size %dx%d %s\n",
               av_get_pix_fmt_name(jpgProcessParam.video_dec_ctx->pix_fmt), jpgProcessParam.video_dec_ctx->width, jpgProcessParam.video_dec_ctx->height,
               jpgProcessParam.out_filename);
    }

    if (jpgProcessParam.audio_stream) {
        enum AVSampleFormat sfmt = jpgProcessParam.audio_dec_ctx->sample_fmt;
        int n_channels = jpgProcessParam.audio_dec_ctx->channels;
        const char *fmt;

        if (av_sample_fmt_is_planar(sfmt)) {
            const char *packed = av_get_sample_fmt_name(sfmt);
            printf("Warning: the sample format the decoder produced is planar "
                   "(%s). This example will output the first channel only.\n",
                   packed ? packed : "?");
            sfmt = av_get_packed_sample_fmt(sfmt);
            n_channels = 1;
        }

        if ((ret = get_format_from_sample_fmt(&fmt, sfmt)) < 0)
            goto end;           

        printf("Play the output audio file with the command:\n"
               "ffplay -f %s -ac %d -ar %d %s\n",
               fmt, n_channels, jpgProcessParam.audio_dec_ctx->sample_rate,
               jpgProcessParam.audio_dst_filename);
    }

    end:

    if (jpgProcessParam.video_dec_ctx)
        avcodec_close(jpgProcessParam.video_dec_ctx);
    if (jpgProcessParam.audio_dec_ctx)
        avcodec_close(jpgProcessParam.audio_dec_ctx);
    avformat_close_input(&jpgProcessParam.fmt_ctx);
    if (jpgProcessParam.video_dst_file)
        fclose(jpgProcessParam.video_dst_file);
    if (jpgProcessParam.audio_dst_file)
        fclose(jpgProcessParam.audio_dst_file);
    av_free(jpgProcessParam.frame);
    av_free(jpgProcessParam.video_dst_data[0]);

    return ret < 0;
}

int JpgProcess::decode_packet(int *got_frame, int cached)
{
    int ret = 0;
    int decoded = jpgProcessParam.pkt.size;

    if (jpgProcessParam.pkt.stream_index == jpgProcessParam.video_stream_idx) {
        /* decode video frame */
        ret = avcodec_decode_video2(jpgProcessParam.video_dec_ctx, jpgProcessParam.frame, got_frame, &jpgProcessParam.pkt);
        if (ret < 0) {
            fprintf(stderr, "Error decoding video frame\n");
            return ret;
        }

        if (*got_frame) {
            printf("video_frame%s n:%d coded_n:%d pts:%s\n",
                   cached ? "(cached)" : "",
                   jpgProcessParam.video_frame_count++, jpgProcessParam.frame->coded_picture_number,
                   av_ts2timestr(jpgProcessParam.frame->pts, &jpgProcessParam.video_dec_ctx->time_base));

            /* copy decoded frame to destination buffer:
             * this is required since rawvideo expects non aligned data */
            av_image_copy(jpgProcessParam.video_dst_data, jpgProcessParam.video_dst_linesize,
                          (const uint8_t **)(jpgProcessParam.frame->data), jpgProcessParam.frame->linesize,
                          jpgProcessParam.video_dec_ctx->pix_fmt, jpgProcessParam.video_dec_ctx->width, jpgProcessParam.video_dec_ctx->height);

            /* write to rawvideo file */
 //           fwrite(jpgProcessParam.video_dst_data[0], 1, jpgProcessParam.video_dst_bufsize, jpgProcessParam.video_dst_file);
//ÍŒÏñËõС³Écif
			{
			    uint8_t *dst_data[4];
			    int dst_linesize[4];
			    int dst_w = 352, dst_h = 288;
			    enum AVPixelFormat dst_pix_fmt = AV_PIX_FMT_YUV420P;
			    int dst_bufsize;
			    struct SwsContext *sws_ctx;

			    sws_ctx = sws_getContext(jpgProcessParam.video_dec_ctx->width, 
			                             jpgProcessParam.video_dec_ctx->height, 
			                             jpgProcessParam.video_dec_ctx->pix_fmt,
                                         dst_w, dst_h, dst_pix_fmt,
                                         SWS_BICUBIC, NULL, NULL, NULL);
			    if (!sws_ctx) {
			        fprintf(stderr,
				        "Impossible to create scale context for the conversion "
						"fmt:%s s:%dx%d -> fmt:%s s:%dx%d\n",
		                av_get_pix_fmt_name(jpgProcessParam.video_dec_ctx->pix_fmt), 
		                jpgProcessParam.video_dec_ctx->width, 
		                jpgProcessParam.video_dec_ctx->height,
				        av_get_pix_fmt_name(dst_pix_fmt), dst_w, dst_h);
				        
			        ret = AVERROR(EINVAL);
					exit(1);
			    }

			    /* allocate source and destination image buffers */
                /*
			    if ((ret = av_image_alloc(src_data, src_linesize,
                          jpgProcessParam.video_dec_ctx->width, jpgProcessParam.video_dec_ctx->height, src_pix_fmt, 16)) < 0) {
				    fprintf(stderr, "Could not allocate source image\n");
					exit(1);
			    }
                */
			    /* buffer is going to be written to rawvideo file, no alignment */
			    if ((ret = av_image_alloc(dst_data, dst_linesize,
                              dst_w, dst_h, dst_pix_fmt, 1)) < 0) {
				    fprintf(stderr, "Could not allocate destination image\n");
					exit(1);
			    }
			    dst_bufsize = ret;
		        /* convert to destination format */
				sws_scale(sws_ctx, (const uint8_t * const*)jpgProcessParam.video_dst_data,
						  jpgProcessParam.video_dst_linesize, 0, jpgProcessParam.video_dec_ctx->width, dst_data, dst_linesize);
				fwrite(dst_data[0], 1, dst_bufsize, jpgProcessParam.video_dst_file);
			    av_freep(&dst_data[0]);
			    sws_freeContext(sws_ctx);

			}
        }
    } else if (jpgProcessParam.pkt.stream_index == jpgProcessParam.audio_stream_idx) {
        /* decode audio frame */
        ret = avcodec_decode_audio4(jpgProcessParam.audio_dec_ctx, jpgProcessParam.frame, got_frame, &jpgProcessParam.pkt);
        if (ret < 0) {
            fprintf(stderr, "Error decoding audio frame\n");
            return ret;
        }
        /* Some audio decoders decode only part of the packet, and have to be
         * called again with the remainder of the packet data.
         * Sample: fate-suite/lossless-audio/luckynight-partial.shn
         * Also, some decoders might over-read the packet. */
        decoded = FFMIN(ret, jpgProcessParam.pkt.size);

        if (*got_frame) {
            size_t unpadded_linesize = jpgProcessParam.frame->nb_samples * av_get_bytes_per_sample((AVSampleFormat)jpgProcessParam.frame->format);
            printf("audio_frame%s n:%d nb_samples:%d pts:%s\n",
                   cached ? "(cached)" : "",
                   jpgProcessParam.audio_frame_count++, jpgProcessParam.frame->nb_samples,
                   av_ts2timestr(jpgProcessParam.frame->pts, &jpgProcessParam.audio_dec_ctx->time_base));

            /* Write the raw audio data samples of the first plane. This works
             * fine for packed formats (e.g. AV_SAMPLE_FMT_S16). However,
             * most audio decoders output planar audio, which uses a separate
             * plane of audio samples for each channel (e.g. AV_SAMPLE_FMT_S16P).
             * In other words, this code will write only the first audio channel
             * in these cases.
             * You should use libswresample or libavfilter to convert the frame
             * to packed data. */
            fwrite(jpgProcessParam.frame->extended_data[0], 1, unpadded_linesize, jpgProcessParam.audio_dst_file);
        }
    }

    return decoded;
}

int JpgProcess::open_codec_context(int *stream_idx, AVFormatContext *fmt_ctx, enum AVMediaType type)
{
    int ret;
    AVStream *st;
    AVCodecContext *dec_ctx = NULL;
    AVCodec *dec = NULL;

    ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
    if (ret < 0) {
        fprintf(stderr, "Could not find %s stream in input file '%s'\n",
                av_get_media_type_string(type), jpgProcessParam.in_filename);
        return ret;
    } else {
        *stream_idx = ret;
        st = fmt_ctx->streams[*stream_idx];

        /* find decoder for the stream */
        dec_ctx = st->codec;
        dec = avcodec_find_decoder(dec_ctx->codec_id);
        if (!dec) {
            fprintf(stderr, "Failed to find %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }

        if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) {
            fprintf(stderr, "Failed to open %s codec\n",
                    av_get_media_type_string(type));
            return ret;
        }
    }

    return 0;
}

int JpgProcess::get_format_from_sample_fmt(const char **fmt, enum AVSampleFormat sample_fmt)
{
    int i;
    struct sample_fmt_entry {
        enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le;
    } sample_fmt_entries[] = {
        { AV_SAMPLE_FMT_U8,  "u8",    "u8"    },
        { AV_SAMPLE_FMT_S16, "s16be", "s16le" },
        { AV_SAMPLE_FMT_S32, "s32be", "s32le" },
        { AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
        { AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
    };
    *fmt = NULL;

    for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
        struct sample_fmt_entry *entry = &sample_fmt_entries[i];
        if (sample_fmt == entry->sample_fmt) {
            *fmt = AV_NE(entry->fmt_be, entry->fmt_le);
            return 0;
        }
    }

    fprintf(stderr,
            "sample format %s is not supported as output format\n",
            av_get_sample_fmt_name(sample_fmt));
    return -1;
}