Module: MultiCompress

Defined in:
lib/multi_compress.rb,
lib/multi_compress/version.rb,
ext/multi_compress/multi_compress.c

Defined Under Namespace

Modules: Brotli, LZ4, Zstd Classes: DataError, Deflater, Dictionary, Error, Inflater, LevelError, MemError, Reader, StreamError, UnsupportedError, Writer

Constant Summary collapse

FASTEST =
:fastest
DEFAULT =
:default
BEST =
:best
VERSION =
"0.2.0"

Class Method Summary collapse

Class Method Details

.adler32(*args) ⇒ Object



1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
# File 'ext/multi_compress/multi_compress.c', line 1247

static VALUE compress_adler32(int argc, VALUE *argv, VALUE self) {
    VALUE data, prev;
    rb_scan_args(argc, argv, "11", &data, &prev);
    StringValue(data);

    const uint8_t *src = (const uint8_t *)RSTRING_PTR(data);
    size_t len = RSTRING_LEN(data);
    uint32_t adler = NIL_P(prev) ? 1 : NUM2UINT(prev);

    uint32_t s1 = adler & 0xFFFF;
    uint32_t s2 = (adler >> 16) & 0xFFFF;
    const uint32_t BASE = 65521;

    while (len > 0) {
        size_t chunk = len > 5552 ? 5552 : len;
        len -= chunk;
        for (size_t i = 0; i < chunk; i++) {
            s1 += src[i];
            s2 += s1;
        }
        s1 %= BASE;
        s2 %= BASE;
        src += chunk;
    }

    return UINT2NUM((s2 << 16) | s1);
}

.algo_from_ext(path) ⇒ Object



57
58
59
# File 'lib/multi_compress.rb', line 57

def self.algo_from_ext(path)
  EXTENSION_MAP[File.extname(path).downcase]
end

.algorithmsObject



1275
1276
1277
1278
1279
1280
1281
# File 'ext/multi_compress/multi_compress.c', line 1275

static VALUE compress_algorithms(VALUE self) {
    VALUE ary = rb_ary_new_capa(3);
    rb_ary_push(ary, ID2SYM(rb_intern("zstd")));
    rb_ary_push(ary, ID2SYM(rb_intern("lz4")));
    rb_ary_push(ary, ID2SYM(rb_intern("brotli")));
    return ary;
}

.available?(algo_sym) ⇒ Boolean

Returns:

  • (Boolean)


1283
1284
1285
1286
# File 'ext/multi_compress/multi_compress.c', line 1283

static VALUE compress_available_p(VALUE self, VALUE algo_sym) {
    sym_to_algo(algo_sym);
    return Qtrue;
}

.brotli(data, level: nil) ⇒ Object



41
42
43
# File 'lib/multi_compress.rb', line 41

def self.brotli(data, level: nil)
  compress(data, algo: :brotli, **level_opts(level))
end

.brotli_decompress(data) ⇒ Object



53
54
55
# File 'lib/multi_compress.rb', line 53

def self.brotli_decompress(data)
  decompress(data, algo: :brotli)
end

.compress(*args) ⇒ Object



617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
# File 'ext/multi_compress/multi_compress.c', line 617

static VALUE compress_compress(int argc, VALUE *argv, VALUE self) {
    VALUE data, opts;
    rb_scan_args(argc, argv, "1:", &data, &opts);
    StringValue(data);

    VALUE algo_sym = Qnil, level_val = Qnil, dict_val = Qnil;
    if (!NIL_P(opts)) {
        algo_sym = rb_hash_aref(opts, ID2SYM(rb_intern("algo")));
        level_val = rb_hash_aref(opts, ID2SYM(rb_intern("level")));
        dict_val = rb_hash_aref(opts, ID2SYM(rb_intern("dictionary")));
    }

    compress_algo_t algo = NIL_P(algo_sym) ? ALGO_ZSTD : sym_to_algo(algo_sym);
    int level = resolve_level(algo, level_val);

    dictionary_t *dict = NULL;
    if (!NIL_P(dict_val)) {
        if (algo == ALGO_LZ4) {
            rb_raise(eUnsupportedError, "LZ4 does not support dictionaries");
        }
        TypedData_Get_Struct(dict_val, dictionary_t, &dictionary_type, dict);
    }

    const char *src = RSTRING_PTR(data);
    size_t slen = RSTRING_LEN(data);

    switch (algo) {
    case ALGO_ZSTD: {
        size_t bound = ZSTD_compressBound(slen);

        ZSTD_CDict *cdict = NULL;
        if (dict) {
            cdict = dict_get_cdict(dict, level);
            if (!cdict)
                rb_raise(eMemError, "zstd: failed to create/get cdict");
        }

        if (slen < GVL_UNLOCK_THRESHOLD) {
            VALUE dst = rb_binary_str_buf_reserve(bound);
            size_t csize;
            if (cdict) {
                ZSTD_CCtx *cctx = ZSTD_createCCtx();
                if (!cctx)
                    rb_raise(eMemError, "zstd: failed to create context");
                csize = ZSTD_compress_usingCDict(cctx, RSTRING_PTR(dst), bound, src, slen, cdict);
                ZSTD_freeCCtx(cctx);
            } else {
                csize = ZSTD_compress(RSTRING_PTR(dst), bound, src, slen, level);
            }
            if (ZSTD_isError(csize))
                rb_raise(eError, "zstd compress: %s", ZSTD_getErrorName(csize));
            rb_str_set_len(dst, (long)csize);
            RB_GC_GUARD(data);
            return dst;
        }

        {
            VALUE scheduler = current_fiber_scheduler();
            if (scheduler != Qnil) {
                char *out_buf = (char *)malloc(bound);
                if (!out_buf)
                    rb_raise(eMemError, "zstd: malloc failed");

                VALUE blocker = rb_obj_alloc(rb_cObject);

                zstd_fiber_compress_t fargs = {
                    .src       = src,
                    .src_len   = slen,
                    .level     = level,
                    .cdict     = cdict,
                    .dst       = out_buf,
                    .dst_cap   = bound,
                    .result    = 0,
                    .error     = 0,
                    .scheduler = scheduler,
                    .blocker   = blocker,
                    .fiber     = rb_fiber_current(),
                };

                VALUE rb_thread = rb_thread_create(zstd_fiber_compress_thread, &fargs);
                rb_fiber_scheduler_block(scheduler, blocker, Qnil);
                rb_funcall(rb_thread, rb_intern("join"), 0);

                if (fargs.error) {
                    free(out_buf);
                    rb_raise(eMemError, "zstd: failed to create context");
                }
                if (ZSTD_isError(fargs.result)) {
                    free(out_buf);
                    rb_raise(eError, "zstd compress: %s", ZSTD_getErrorName(fargs.result));
                }

                VALUE result = rb_binary_str_new(out_buf, (long)fargs.result);
                free(out_buf);
                RB_GC_GUARD(data);
                return result;
            }
        }

        {
            VALUE dst = rb_binary_str_buf_reserve(bound);
            zstd_compress_args_t args = {
                .src     = src,
                .src_len = slen,
                .dst     = RSTRING_PTR(dst),
                .dst_cap = bound,
                .level   = level,
                .cdict   = cdict,
                .result  = 0,
                .error   = 0,
            };
            run_without_gvl(zstd_compress_nogvl, &args);

            if (args.error)
                rb_raise(eMemError, "zstd: failed to create context");
            if (ZSTD_isError(args.result))
                rb_raise(eError, "zstd compress: %s", ZSTD_getErrorName(args.result));

            rb_str_set_len(dst, (long)args.result);
            RB_GC_GUARD(data);
            return dst;
        }
    }
    case ALGO_LZ4: {
        if (slen > (size_t)INT_MAX)
            rb_raise(eError, "lz4: input too large (max 2GB)");
        int bound = LZ4_compressBound((int)slen);

        int csize;
        if (slen >= GVL_UNLOCK_THRESHOLD) {
            VALUE dst = rb_binary_str_buf_reserve(8 + (size_t)bound + 4);
            char *out = RSTRING_PTR(dst);

            out[0] = (slen >> 0) & 0xFF;
            out[1] = (slen >> 8) & 0xFF;
            out[2] = (slen >> 16) & 0xFF;
            out[3] = (slen >> 24) & 0xFF;

            lz4_compress_args_t args = {
                .src = src,
                .src_len = (int)slen,
                .dst = out + 8,
                .dst_cap = bound,
                .level = level,
            };

            VALUE scheduler = current_fiber_scheduler();
            if (scheduler != Qnil) {
                run_via_fiber_worker(scheduler, lz4_compress_nogvl, &args);
            } else {
                run_without_gvl(lz4_compress_nogvl, &args);
            }
            csize = args.result;

            if (csize <= 0)
                rb_raise(eError, "lz4 compress failed");

            out[4] = (csize >> 0) & 0xFF;
            out[5] = (csize >> 8) & 0xFF;
            out[6] = (csize >> 16) & 0xFF;
            out[7] = (csize >> 24) & 0xFF;

            size_t total = 8 + (size_t)csize;
            out[total] = 0;
            out[total + 1] = 0;
            out[total + 2] = 0;
            out[total + 3] = 0;

            rb_str_set_len(dst, (long)(total + 4));
            RB_GC_GUARD(data);
            return dst;
        } else {
            VALUE dst = rb_binary_str_buf_reserve(8 + bound + 4);
            char *out = RSTRING_PTR(dst);

            out[0] = (slen >> 0) & 0xFF;
            out[1] = (slen >> 8) & 0xFF;
            out[2] = (slen >> 16) & 0xFF;
            out[3] = (slen >> 24) & 0xFF;

            if (level > 1) {
                csize = LZ4_compress_HC(src, out + 8, (int)slen, bound, level);
            } else {
                csize = LZ4_compress_default(src, out + 8, (int)slen, bound);
            }
            if (csize <= 0)
                rb_raise(eError, "lz4 compress failed");

            out[4] = (csize >> 0) & 0xFF;
            out[5] = (csize >> 8) & 0xFF;
            out[6] = (csize >> 16) & 0xFF;
            out[7] = (csize >> 24) & 0xFF;

            size_t total = 8 + csize;
            out[total] = 0;
            out[total + 1] = 0;
            out[total + 2] = 0;
            out[total + 3] = 0;

            rb_str_set_len(dst, total + 4);
            RB_GC_GUARD(data);
            return dst;
        }
    }
    case ALGO_BROTLI: {
        size_t out_len = BrotliEncoderMaxCompressedSize(slen);
        if (out_len == 0)
            out_len = slen + (slen >> 2) + 1024;

        if (dict) {
            VALUE dst = rb_binary_str_buf_reserve(out_len);
            BrotliEncoderState *enc = BrotliEncoderCreateInstance(NULL, NULL, NULL);
            if (!enc)
                rb_raise(eMemError, "brotli: failed to create encoder");

            BrotliEncoderPreparedDictionary *pd =
                BrotliEncoderPrepareDictionary(BROTLI_SHARED_DICTIONARY_RAW, dict->size, dict->data,
                                               BROTLI_MAX_QUALITY, NULL, NULL, NULL);
            if (!pd) {
                BrotliEncoderDestroyInstance(enc);
                rb_raise(eMemError, "brotli: failed to prepare dictionary");
            }

            if (!BrotliEncoderSetParameter(enc, BROTLI_PARAM_QUALITY, level) ||
                !BrotliEncoderAttachPreparedDictionary(enc, pd)) {
                BrotliEncoderDestroyPreparedDictionary(pd);
                BrotliEncoderDestroyInstance(enc);
                rb_raise(eError, "brotli: failed to attach dictionary");
            }

            size_t available_in = slen;
            const uint8_t *next_in = (const uint8_t *)src;
            size_t available_out = out_len;
            uint8_t *next_out = (uint8_t *)RSTRING_PTR(dst);
            size_t initial_out = available_out;

            BROTLI_BOOL ok =
                BrotliEncoderCompressStream(enc, BROTLI_OPERATION_FINISH, &available_in, &next_in,
                                            &available_out, &next_out, NULL);

            BrotliEncoderDestroyPreparedDictionary(pd);
            BrotliEncoderDestroyInstance(enc);
            if (!ok)
                rb_raise(eError, "brotli compress with dict failed");

            rb_str_set_len(dst, initial_out - available_out);
            RB_GC_GUARD(data);
            return dst;
        } else if (slen >= GVL_UNLOCK_THRESHOLD) {
            VALUE dst = rb_binary_str_buf_reserve(out_len);
            size_t actual_out_len = out_len;

            brotli_compress_args_t args = {
                .level = level,
                .src_len = slen,
                .src = (const uint8_t *)src,
                .out_len = &actual_out_len,
                .dst = (uint8_t *)RSTRING_PTR(dst),
            };

            VALUE scheduler = current_fiber_scheduler();
            if (scheduler != Qnil) {
                run_via_fiber_worker(scheduler, brotli_compress_nogvl, &args);
            } else {
                run_without_gvl(brotli_compress_nogvl, &args);
            }

            if (!args.result)
                rb_raise(eError, "brotli compress failed");

            rb_str_set_len(dst, (long)actual_out_len);
            RB_GC_GUARD(data);
            return dst;
        } else {
            VALUE dst = rb_binary_str_buf_reserve(out_len);
            BROTLI_BOOL ok =
                BrotliEncoderCompress(level, BROTLI_DEFAULT_WINDOW, BROTLI_DEFAULT_MODE, slen,
                                      (const uint8_t *)src, &out_len, (uint8_t *)RSTRING_PTR(dst));
            if (!ok)
                rb_raise(eError, "brotli compress failed");
            rb_str_set_len(dst, out_len);
            RB_GC_GUARD(data);
            return dst;
        }
    }
    }

    return Qnil;
}

.crc32(*args) ⇒ Object



1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
# File 'ext/multi_compress/multi_compress.c', line 1235

static VALUE compress_crc32(int argc, VALUE *argv, VALUE self) {
    VALUE data, prev;
    rb_scan_args(argc, argv, "11", &data, &prev);
    StringValue(data);

    const uint8_t *src = (const uint8_t *)RSTRING_PTR(data);
    size_t len = RSTRING_LEN(data);
    uint32_t crc = NIL_P(prev) ? 0 : NUM2UINT(prev);

    return UINT2NUM(crc32_compute(src, len, crc));
}

.decompress(*args) ⇒ Object



907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
# File 'ext/multi_compress/multi_compress.c', line 907

static VALUE compress_decompress(int argc, VALUE *argv, VALUE self) {
    VALUE data, opts;
    rb_scan_args(argc, argv, "1:", &data, &opts);
    StringValue(data);

    VALUE algo_sym = Qnil, dict_val = Qnil;
    if (!NIL_P(opts)) {
        algo_sym = rb_hash_aref(opts, ID2SYM(rb_intern("algo")));
        dict_val = rb_hash_aref(opts, ID2SYM(rb_intern("dictionary")));
    }

    const uint8_t *src = (const uint8_t *)RSTRING_PTR(data);
    size_t slen = RSTRING_LEN(data);

    compress_algo_t algo;
    if (NIL_P(algo_sym)) {
        algo = detect_algo(src, slen);
    } else {
        algo = sym_to_algo(algo_sym);
    }

    dictionary_t *dict = NULL;
    if (!NIL_P(dict_val)) {
        if (algo == ALGO_LZ4) {
            rb_raise(eUnsupportedError, "LZ4 does not support dictionaries");
        }
        TypedData_Get_Struct(dict_val, dictionary_t, &dictionary_type, dict);
    }

    switch (algo) {
    case ALGO_ZSTD: {
        unsigned long long frame_size = ZSTD_getFrameContentSize(src, slen);
        if (frame_size == ZSTD_CONTENTSIZE_ERROR) {
            rb_raise(eDataError, "zstd: not valid compressed data");
        }

        if (frame_size != ZSTD_CONTENTSIZE_UNKNOWN && frame_size <= MAX_DECOMPRESS_SIZE) {
            size_t dsize;

            if (frame_size >= GVL_UNLOCK_THRESHOLD) {
                VALUE dst = rb_binary_str_buf_reserve((size_t)frame_size);

                ZSTD_DDict *ddict = NULL;
                if (dict) {
                    ddict = dict_get_ddict(dict);
                    if (!ddict)
                        rb_raise(eMemError, "zstd: failed to create ddict");
                }

                zstd_decompress_args_t args = {
                    .src = src,
                    .src_len = slen,
                    .dst = RSTRING_PTR(dst),
                    .dst_cap = (size_t)frame_size,
                    .ddict = ddict,
                };

                VALUE scheduler = current_fiber_scheduler();
                if (scheduler != Qnil) {
                    run_via_fiber_worker(scheduler, zstd_decompress_nogvl, &args);
                } else {
                    run_without_gvl(zstd_decompress_nogvl, &args);
                }

                if (args.error)
                    rb_raise(eMemError, "zstd: failed to create dctx");
                dsize = args.result;
                if (ZSTD_isError(dsize))
                    rb_raise(eDataError, "zstd decompress: %s", ZSTD_getErrorName(dsize));

                rb_str_set_len(dst, (long)dsize);
                RB_GC_GUARD(data);
                return dst;
            } else {
                VALUE dst = rb_binary_str_buf_reserve((size_t)frame_size);

                if (dict) {
                    ZSTD_DDict *ddict = dict_get_ddict(dict);
                    if (!ddict)
                        rb_raise(eMemError, "zstd: failed to create ddict");
                    ZSTD_DCtx *dctx = ZSTD_createDCtx();
                    if (!dctx)
                        rb_raise(eMemError, "zstd: failed to create dctx");
                    dsize = ZSTD_decompress_usingDDict(dctx, RSTRING_PTR(dst), (size_t)frame_size,
                                                       src, slen, ddict);
                    ZSTD_freeDCtx(dctx);
                } else {
                    dsize = ZSTD_decompress(RSTRING_PTR(dst), (size_t)frame_size, src, slen);
                }

                if (ZSTD_isError(dsize))
                    rb_raise(eDataError, "zstd decompress: %s", ZSTD_getErrorName(dsize));
                rb_str_set_len(dst, dsize);
                RB_GC_GUARD(data);
                return dst;
            }
        }

        ZSTD_DCtx *dctx = ZSTD_createDCtx();
        if (!dctx)
            rb_raise(eMemError, "zstd: failed to create dctx");

        if (dict) {
            ZSTD_DDict *ddict = dict_get_ddict(dict);
            if (ddict) {
                size_t r = ZSTD_DCtx_refDDict(dctx, ddict);
                if (ZSTD_isError(r)) {
                    ZSTD_freeDCtx(dctx);
                    rb_raise(eError, "zstd dict ref: %s", ZSTD_getErrorName(r));
                }
            }
        }

        size_t alloc_size = (slen > MAX_DECOMPRESS_SIZE / 8) ? MAX_DECOMPRESS_SIZE : slen * 8;
        if (alloc_size < 4096)
            alloc_size = 4096;

        VALUE dst = rb_binary_str_buf_reserve(alloc_size);
        size_t total_out = 0;

        ZSTD_inBuffer input = {src, slen, 0};
        while (input.pos < input.size) {
            if (total_out >= alloc_size) {
                if (alloc_size >= MAX_DECOMPRESS_SIZE) {
                    ZSTD_freeDCtx(dctx);
                    rb_raise(eDataError, "zstd: decompressed size exceeds limit (%lluMB)",
                             (unsigned long long)(MAX_DECOMPRESS_SIZE / (1024 * 1024)));
                }
                alloc_size *= 2;
                if (alloc_size > MAX_DECOMPRESS_SIZE)
                    alloc_size = MAX_DECOMPRESS_SIZE;
                grow_binary_str(dst, total_out, alloc_size);
            }

            ZSTD_outBuffer output = {RSTRING_PTR(dst) + total_out, alloc_size - total_out, 0};
            size_t ret = ZSTD_decompressStream(dctx, &output, &input);
            if (ZSTD_isError(ret)) {
                ZSTD_freeDCtx(dctx);
                rb_raise(eDataError, "zstd decompress: %s", ZSTD_getErrorName(ret));
            }
            total_out += output.pos;
            if (ret == 0)
                break;
        }

        ZSTD_freeDCtx(dctx);
        rb_str_set_len(dst, total_out);
        RB_GC_GUARD(data);
        return dst;
    }
    case ALGO_LZ4: {
        if (slen < 4)
            rb_raise(eDataError, "lz4: data too short");

        size_t total_orig = 0;
        size_t scan_pos = 0;
        while (scan_pos + 4 <= slen) {
            uint32_t orig_size = (uint32_t)src[scan_pos] | ((uint32_t)src[scan_pos + 1] << 8) |
                                 ((uint32_t)src[scan_pos + 2] << 16) |
                                 ((uint32_t)src[scan_pos + 3] << 24);
            if (orig_size == 0)
                break;
            if (scan_pos + 8 > slen)
                rb_raise(eDataError, "lz4: truncated block header");
            uint32_t comp_size = (uint32_t)src[scan_pos + 4] | ((uint32_t)src[scan_pos + 5] << 8) |
                                 ((uint32_t)src[scan_pos + 6] << 16) |
                                 ((uint32_t)src[scan_pos + 7] << 24);
            if (scan_pos + 8 + comp_size > slen)
                rb_raise(eDataError, "lz4: truncated block data");
            if (orig_size > 256 * 1024 * 1024)
                rb_raise(eDataError, "lz4: block too large (%u)", orig_size);
            total_orig += orig_size;
            if (total_orig > MAX_DECOMPRESS_SIZE)
                rb_raise(eDataError, "lz4: total decompressed size exceeds limit");
            scan_pos += 8 + comp_size;
        }

        VALUE result = rb_binary_str_buf_reserve(total_orig);

        lz4_decompress_all_args_t args = {
            .src = src,
            .src_len = slen,
            .dst = RSTRING_PTR(result),
            .out_offset = 0,
            .error = 0,
        };

        if (total_orig >= GVL_UNLOCK_THRESHOLD) {
            VALUE scheduler = current_fiber_scheduler();
            if (scheduler != Qnil) {
                run_via_fiber_worker(scheduler, lz4_decompress_all_nogvl, &args);
            } else {
                run_without_gvl(lz4_decompress_all_nogvl, &args);
            }
        } else {
            lz4_decompress_all_nogvl(&args);
        }

        if (args.error)
            rb_raise(eDataError, "%s", args.err_msg);

        rb_str_set_len(result, args.out_offset);
        RB_GC_GUARD(data);
        return result;
    }
    case ALGO_BROTLI: {
        size_t alloc_size = (slen > MAX_DECOMPRESS_SIZE / 4) ? MAX_DECOMPRESS_SIZE : slen * 4;
        if (alloc_size < 1024)
            alloc_size = 1024;

        BrotliDecoderState *dec = BrotliDecoderCreateInstance(NULL, NULL, NULL);
        if (!dec)
            rb_raise(eMemError, "brotli: failed to create decoder");

        if (dict) {
            BrotliDecoderAttachDictionary(dec, BROTLI_SHARED_DICTIONARY_RAW, dict->size,
                                          dict->data);
        }

        VALUE dst = rb_binary_str_buf_reserve(alloc_size);
        size_t total_out = 0;

        size_t available_in = slen;
        const uint8_t *next_in = src;

        VALUE scheduler = current_fiber_scheduler();

        BrotliDecoderResult res = BROTLI_DECODER_RESULT_NEEDS_MORE_OUTPUT;
        while (res == BROTLI_DECODER_RESULT_NEEDS_MORE_OUTPUT) {
            size_t available_out = alloc_size - total_out;
            uint8_t *next_out = (uint8_t *)RSTRING_PTR(dst) + total_out;

            if (scheduler != Qnil && available_in >= FIBER_STREAM_THRESHOLD) {
                brotli_decompress_stream_args_t sargs = {
                    .dec           = dec,
                    .available_in  = &available_in,
                    .next_in       = &next_in,
                    .available_out = &available_out,
                    .next_out      = &next_out,
                    .result        = BROTLI_DECODER_RESULT_ERROR,
                };
                run_via_fiber_worker(scheduler, brotli_decompress_stream_nogvl, &sargs);
                res = sargs.result;
            } else {
                res = BrotliDecoderDecompressStream(dec, &available_in, &next_in, &available_out,
                                                    &next_out, NULL);
            }

            total_out = next_out - (uint8_t *)RSTRING_PTR(dst);

            if (res == BROTLI_DECODER_RESULT_NEEDS_MORE_OUTPUT) {
                if (alloc_size >= MAX_DECOMPRESS_SIZE) {
                    BrotliDecoderDestroyInstance(dec);
                    rb_raise(eDataError, "brotli: decompressed size exceeds limit (%lluMB)",
                             (unsigned long long)(MAX_DECOMPRESS_SIZE / (1024 * 1024)));
                }
                alloc_size *= 2;
                if (alloc_size > MAX_DECOMPRESS_SIZE)
                    alloc_size = MAX_DECOMPRESS_SIZE;
                grow_binary_str(dst, total_out, alloc_size);
            }
        }

        BrotliDecoderDestroyInstance(dec);

        if (res != BROTLI_DECODER_RESULT_SUCCESS) {
            rb_raise(eDataError, "brotli decompress failed");
        }
        rb_str_set_len(dst, total_out);
        RB_GC_GUARD(data);
        return dst;
    }
    }

    return Qnil;
}

.lz4(data, level: nil) ⇒ Object



37
38
39
# File 'lib/multi_compress.rb', line 37

def self.lz4(data, level: nil)
  compress(data, algo: :lz4, **level_opts(level))
end

.lz4_decompress(data) ⇒ Object



49
50
51
# File 'lib/multi_compress.rb', line 49

def self.lz4_decompress(data)
  decompress(data, algo: :lz4)
end

.version(algo_sym) ⇒ Object



1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
# File 'ext/multi_compress/multi_compress.c', line 1288

static VALUE compress_version(VALUE self, VALUE algo_sym) {
    compress_algo_t algo = sym_to_algo(algo_sym);
    switch (algo) {
    case ALGO_ZSTD:
        return rb_str_new_cstr(ZSTD_versionString());
    case ALGO_LZ4:
        return rb_sprintf("%d.%d.%d", LZ4_VERSION_MAJOR, LZ4_VERSION_MINOR, LZ4_VERSION_RELEASE);
    case ALGO_BROTLI:
        return rb_sprintf("%d.%d.%d", BrotliEncoderVersion() >> 24,
                          (BrotliEncoderVersion() >> 12) & 0xFFF, BrotliEncoderVersion() & 0xFFF);
    }
    return Qnil;
}

.zstd(data, level: nil) ⇒ Object



33
34
35
# File 'lib/multi_compress.rb', line 33

def self.zstd(data, level: nil)
  compress(data, algo: :zstd, **level_opts(level))
end

.zstd_decompress(data) ⇒ Object



45
46
47
# File 'lib/multi_compress.rb', line 45

def self.zstd_decompress(data)
  decompress(data, algo: :zstd)
end