streaming_decompression.c

/*
 * Copyright (c) Yann Collet, Facebook, Inc.
 * All rights reserved.
 *
 * This source code is licensed under both the BSD-style license (found in the
 * LICENSE file in the root directory of this source tree) and the GPLv2 (found
 * in the COPYING file in the root directory of this source tree).
 * You may select, at your option, one of the above-listed licenses.
 */


#include <stdio.h>     // fprintf
#include <stdlib.h>    // free
#include <zstd.h>      // presumes zstd library is installed
#include "common.h"    // Helper functions, CHECK(), and CHECK_ZSTD()

static void decompressFile_orDie(const char* fname)
{
    FILE* const fin  = fopen_orDie(fname, "rb");
    size_t const buffInSize = ZSTD_DStreamInSize();
    void*  const buffIn  = malloc_orDie(buffInSize);
    FILE* const fout = stdout;
    size_t const buffOutSize = ZSTD_DStreamOutSize();  /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */
    void*  const buffOut = malloc_orDie(buffOutSize);

    ZSTD_DCtx* const dctx = ZSTD_createDCtx();
    CHECK(dctx != NULL, "ZSTD_createDCtx() failed!");

    /* This loop assumes that the input file is one or more concatenated zstd
     * streams. This example won't work if there is trailing non-zstd data at
     * the end, but streaming decompression in general handles this case.
     * ZSTD_decompressStream() returns 0 exactly when the frame is completed,
     * and doesn't consume input after the frame.
     */
    size_t const toRead = buffInSize;
    size_t read;
    size_t lastRet = 0;
    int isEmpty = 1;
    while ( (read = fread_orDie(buffIn, toRead, fin)) ) {
        isEmpty = 0;
        ZSTD_inBuffer input = { buffIn, read, 0 };
        /* Given a valid frame, zstd won't consume the last byte of the frame
         * until it has flushed all of the decompressed data of the frame.
         * Therefore, instead of checking if the return code is 0, we can
         * decompress just check if input.pos < input.size.
         */
        while (input.pos < input.size) {
            ZSTD_outBuffer output = { buffOut, buffOutSize, 0 };
            /* The return code is zero if the frame is complete, but there may
             * be multiple frames concatenated together. Zstd will automatically
             * reset the context when a frame is complete. Still, calling
             * ZSTD_DCtx_reset() can be useful to reset the context to a clean
             * state, for instance if the last decompression call returned an
             * error.
             */
            size_t const ret = ZSTD_decompressStream(dctx, &output , &input);
            CHECK_ZSTD(ret);
            fwrite_orDie(buffOut, output.pos, fout);
            lastRet = ret;
        }
    }

    if (isEmpty) {
        fprintf(stderr, "input is empty\n");
        exit(1);
    }

    if (lastRet != 0) {
        /* The last return value from ZSTD_decompressStream did not end on a
         * frame, but we reached the end of the file! We assume this is an
         * error, and the input was truncated.
         */
        fprintf(stderr, "EOF before end of stream: %zu\n", lastRet);
        exit(1);
    }

    ZSTD_freeDCtx(dctx);
    fclose_orDie(fin);
    fclose_orDie(fout);
    free(buffIn);
    free(buffOut);
}


int main(int argc, const char** argv)
{
    const char* const exeName = argv[0];

    if (argc!=2) {
        fprintf(stderr, "wrong arguments\n");
        fprintf(stderr, "usage:\n");
        fprintf(stderr, "%s FILE\n", exeName);
        return 1;
    }

    const char* const inFilename = argv[1];

    decompressFile_orDie(inFilename);
    return 0;
}