Class: MultiCompress::Deflater

Inherits:
Object
  • Object
show all
Defined in:
ext/multi_compress/multi_compress.c

Instance Method Summary collapse

Constructor Details

#initialize(*args) ⇒ Object



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
# File 'ext/multi_compress/multi_compress.c', line 1066

static VALUE deflater_initialize(int argc, VALUE *argv, VALUE self) {
    VALUE opts;
    rb_scan_args(argc, argv, "0:", &opts);

    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);

    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")));
    }

    d->algo = NIL_P(algo_sym) ? ALGO_ZSTD : sym_to_algo(algo_sym);
    d->level = resolve_level(d->algo, level_val);
    d->closed = 0;
    d->finished = 0;

    dictionary_t *dict = NULL;
    if (!NIL_P(dict_val)) {
        if (d->algo == ALGO_LZ4) {
            rb_raise(eUnsupportedError, "LZ4 does not support dictionaries");
        }
        TypedData_Get_Struct(dict_val, dictionary_t, &dictionary_type, dict);
        rb_ivar_set(self, rb_intern("@dictionary"), dict_val);
    }

    switch (d->algo) {
    case ALGO_ZSTD: {
        d->ctx.zstd = ZSTD_createCStream();
        if (!d->ctx.zstd)
            rb_raise(eMemError, "zstd: failed to create stream");

        if (dict) {
            ZSTD_CCtx_reset(d->ctx.zstd, ZSTD_reset_session_only);
            ZSTD_CCtx_setParameter(d->ctx.zstd, ZSTD_c_compressionLevel, d->level);
            size_t r = ZSTD_CCtx_loadDictionary(d->ctx.zstd, dict->data, dict->size);
            if (ZSTD_isError(r))
                rb_raise(eError, "zstd dict load: %s", ZSTD_getErrorName(r));
        } else {
            size_t r = ZSTD_initCStream(d->ctx.zstd, d->level);
            if (ZSTD_isError(r))
                rb_raise(eError, "zstd init: %s", ZSTD_getErrorName(r));
        }
        break;
    }
    case ALGO_BROTLI: {
        d->ctx.brotli = BrotliEncoderCreateInstance(NULL, NULL, NULL);
        if (!d->ctx.brotli)
            rb_raise(eMemError, "brotli: failed to create encoder");
        if (!BrotliEncoderSetParameter(d->ctx.brotli, BROTLI_PARAM_QUALITY, d->level)) {
            BrotliEncoderDestroyInstance(d->ctx.brotli);
            d->ctx.brotli = NULL;
            rb_raise(eError, "brotli: failed to set quality parameter");
        }
        if (dict) {
            BrotliEncoderPreparedDictionary *pd =
                BrotliEncoderPrepareDictionary(BROTLI_SHARED_DICTIONARY_RAW, dict->size, dict->data,
                                               BROTLI_MAX_QUALITY, NULL, NULL, NULL);
            if (!pd) {
                BrotliEncoderDestroyInstance(d->ctx.brotli);
                d->ctx.brotli = NULL;
                rb_raise(eMemError, "brotli: failed to prepare dictionary");
            }
            if (!BrotliEncoderAttachPreparedDictionary(d->ctx.brotli, pd)) {
                BrotliEncoderDestroyPreparedDictionary(pd);
                BrotliEncoderDestroyInstance(d->ctx.brotli);
                d->ctx.brotli = NULL;
                rb_raise(eError, "brotli: failed to attach dictionary");
            }
            BrotliEncoderDestroyPreparedDictionary(pd);
        }
        break;
    }
    case ALGO_LZ4: {
        d->ctx.lz4 = LZ4_createStream();
        if (!d->ctx.lz4)
            rb_raise(eMemError, "lz4: failed to create stream");
        LZ4_resetStream(d->ctx.lz4);
        d->lz4_ring.buf = ALLOC_N(char, LZ4_RING_BUFFER_TOTAL);
        d->lz4_ring.ring_offset = 0;
        d->lz4_ring.pending = 0;
        break;
    }
    }

    return self;
}

Instance Method Details

#closeObject



1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
# File 'ext/multi_compress/multi_compress.c', line 1547

static VALUE deflater_close(VALUE self) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);
    if (d->closed)
        return Qnil;

    switch (d->algo) {
    case ALGO_ZSTD:
        if (d->ctx.zstd) {
            ZSTD_freeCStream(d->ctx.zstd);
            d->ctx.zstd = NULL;
        }
        break;
    case ALGO_BROTLI:
        if (d->ctx.brotli) {
            BrotliEncoderDestroyInstance(d->ctx.brotli);
            d->ctx.brotli = NULL;
        }
        break;
    case ALGO_LZ4:
        if (d->ctx.lz4) {
            LZ4_freeStream(d->ctx.lz4);
            d->ctx.lz4 = NULL;
        }
        break;
    }
    d->closed = 1;
    return Qnil;
}

#closed?Boolean

Returns:

  • (Boolean)


1577
1578
1579
1580
1581
# File 'ext/multi_compress/multi_compress.c', line 1577

static VALUE deflater_closed_p(VALUE self) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);
    return d->closed ? Qtrue : Qfalse;
}

#finishObject



1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
# File 'ext/multi_compress/multi_compress.c', line 1390

static VALUE deflater_finish(VALUE self) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);
    if (d->closed)
        rb_raise(eStreamError, "stream is closed");
    if (d->finished)
        return rb_binary_str_new("", 0);
    d->finished = 1;

    switch (d->algo) {
    case ALGO_ZSTD: {
        size_t out_cap = ZSTD_CStreamOutSize();
        size_t result_cap = out_cap;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;
        size_t ret;

        do {
            if (result_len + out_cap > result_cap) {
                result_cap *= 2;
                grow_binary_str(result, result_len, result_cap);
            }

            ZSTD_outBuffer output = {RSTRING_PTR(result) + result_len, out_cap, 0};
            ret = ZSTD_endStream(d->ctx.zstd, &output);
            if (ZSTD_isError(ret))
                rb_raise(eError, "zstd end stream: %s", ZSTD_getErrorName(ret));
            result_len += output.pos;
        } while (ret > 0);

        rb_str_set_len(result, result_len);
        return result;
    }
    case ALGO_BROTLI: {
        size_t available_in = 0;
        const uint8_t *next_in = NULL;
        size_t result_cap = 1024;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;

        do {
            size_t available_out = 0;
            uint8_t *next_out = NULL;
            BROTLI_BOOL ok =
                BrotliEncoderCompressStream(d->ctx.brotli, BROTLI_OPERATION_FINISH, &available_in,
                                            &next_in, &available_out, &next_out, NULL);
            if (!ok)
                rb_raise(eError, "brotli finish failed");
            const uint8_t *out_data;
            size_t out_size = 0;
            out_data = BrotliEncoderTakeOutput(d->ctx.brotli, &out_size);
            if (out_size > 0) {
                if (result_len + out_size > result_cap) {
                    result_cap = (result_len + out_size) * 2;
                    grow_binary_str(result, result_len, result_cap);
                }

                memcpy(RSTRING_PTR(result) + result_len, out_data, out_size);
                result_len += out_size;
            }
        } while (BrotliEncoderHasMoreOutput(d->ctx.brotli) ||
                 !BrotliEncoderIsFinished(d->ctx.brotli));

        rb_str_set_len(result, result_len);
        return result;
    }
    case ALGO_LZ4: {
        size_t result_cap = 256;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;

        if (d->lz4_ring.pending > 0) {
            VALUE block = lz4_compress_ring_block(d);
            size_t blen = RSTRING_LEN(block);
            if (blen > 0) {
                if (blen + 4 > result_cap) {
                    result_cap = blen + 4;
                    grow_binary_str(result, result_len, result_cap);
                }

                memcpy(RSTRING_PTR(result), RSTRING_PTR(block), blen);
                result_len = blen;
            }
        }

        if (result_len + 4 > result_cap) {
            result_cap = result_len + 4;
            grow_binary_str(result, result_len, result_cap);
        }

        char *out = RSTRING_PTR(result) + result_len;
        out[0] = out[1] = out[2] = out[3] = 0;
        result_len += 4;

        rb_str_set_len(result, result_len);
        return result;
    }
    }
    return rb_binary_str_new("", 0);
}

#flushObject



1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
# File 'ext/multi_compress/multi_compress.c', line 1320

static VALUE deflater_flush(VALUE self) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);
    if (d->closed)
        rb_raise(eStreamError, "stream is closed");
    if (d->finished)
        rb_raise(eStreamError, "stream is already finished");

    switch (d->algo) {
    case ALGO_ZSTD: {
        size_t out_cap = ZSTD_CStreamOutSize();
        size_t result_cap = out_cap;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;
        size_t ret;

        do {
            if (result_len + out_cap > result_cap) {
                result_cap *= 2;
                grow_binary_str(result, result_len, result_cap);
            }

            ZSTD_outBuffer output = {RSTRING_PTR(result) + result_len, out_cap, 0};
            ret = ZSTD_flushStream(d->ctx.zstd, &output);
            if (ZSTD_isError(ret))
                rb_raise(eError, "zstd flush: %s", ZSTD_getErrorName(ret));
            result_len += output.pos;
        } while (ret > 0);

        rb_str_set_len(result, result_len);
        return result;
    }
    case ALGO_BROTLI: {
        size_t available_in = 0;
        const uint8_t *next_in = NULL;
        size_t result_cap = 1024;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;

        do {
            size_t available_out = 0;
            uint8_t *next_out = NULL;
            BROTLI_BOOL ok =
                BrotliEncoderCompressStream(d->ctx.brotli, BROTLI_OPERATION_FLUSH, &available_in,
                                            &next_in, &available_out, &next_out, NULL);
            if (!ok)
                rb_raise(eError, "brotli flush failed");
            const uint8_t *out_data;
            size_t out_size = 0;
            out_data = BrotliEncoderTakeOutput(d->ctx.brotli, &out_size);
            if (out_size > 0) {
                if (result_len + out_size > result_cap) {
                    result_cap = (result_len + out_size) * 2;
                    grow_binary_str(result, result_len, result_cap);
                }

                memcpy(RSTRING_PTR(result) + result_len, out_data, out_size);
                result_len += out_size;
            }
        } while (BrotliEncoderHasMoreOutput(d->ctx.brotli));

        rb_str_set_len(result, result_len);
        return result;
    }
    case ALGO_LZ4:
        return lz4_compress_ring_block(d);
    }
    return rb_binary_str_new("", 0);
}

#resetObject



1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
# File 'ext/multi_compress/multi_compress.c', line 1491

static VALUE deflater_reset(VALUE self) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);

    VALUE dict_val = rb_attr_get(self, rb_intern("@dictionary"));
    dictionary_t *dict = NULL;
    if (!NIL_P(dict_val)) {
        TypedData_Get_Struct(dict_val, dictionary_t, &dictionary_type, dict);
    }

    switch (d->algo) {
    case ALGO_ZSTD:
        if (d->ctx.zstd) {
            ZSTD_CCtx_reset(d->ctx.zstd, ZSTD_reset_session_only);
            ZSTD_CCtx_setParameter(d->ctx.zstd, ZSTD_c_compressionLevel, d->level);
            if (dict) {
                size_t r = ZSTD_CCtx_loadDictionary(d->ctx.zstd, dict->data, dict->size);
                if (ZSTD_isError(r))
                    rb_raise(eError, "zstd dict reload on reset: %s", ZSTD_getErrorName(r));
            }
        }
        break;
    case ALGO_BROTLI:
        if (d->ctx.brotli) {
            BrotliEncoderDestroyInstance(d->ctx.brotli);
            d->ctx.brotli = BrotliEncoderCreateInstance(NULL, NULL, NULL);
            if (!d->ctx.brotli)
                rb_raise(eMemError, "brotli: failed to recreate encoder");
            if (!BrotliEncoderSetParameter(d->ctx.brotli, BROTLI_PARAM_QUALITY, d->level))
                rb_raise(eError, "brotli: failed to set quality on reset");
            if (dict) {
                BrotliEncoderPreparedDictionary *pd = BrotliEncoderPrepareDictionary(
                    BROTLI_SHARED_DICTIONARY_RAW, dict->size, dict->data, BROTLI_MAX_QUALITY, NULL,
                    NULL, NULL);
                if (!pd)
                    rb_raise(eMemError, "brotli: failed to prepare dictionary on reset");
                if (!BrotliEncoderAttachPreparedDictionary(d->ctx.brotli, pd)) {
                    BrotliEncoderDestroyPreparedDictionary(pd);
                    rb_raise(eError, "brotli: failed to reattach dictionary on reset");
                }
                BrotliEncoderDestroyPreparedDictionary(pd);
            }
        }
        break;
    case ALGO_LZ4:
        if (d->ctx.lz4)
            LZ4_resetStream(d->ctx.lz4);
        d->lz4_ring.ring_offset = 0;
        d->lz4_ring.pending = 0;
        break;
    }
    d->closed = 0;
    d->finished = 0;
    return self;
}

#write(chunk) ⇒ Object



1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
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
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
# File 'ext/multi_compress/multi_compress.c', line 1191

static VALUE deflater_write(VALUE self, VALUE chunk) {
    deflater_t *d;
    TypedData_Get_Struct(self, deflater_t, &deflater_type, d);
    if (d->closed)
        rb_raise(eStreamError, "stream is closed");
    if (d->finished)
        rb_raise(eStreamError, "stream is already finished");
    StringValue(chunk);

    const char *src = RSTRING_PTR(chunk);
    size_t slen = RSTRING_LEN(chunk);
    if (slen == 0)
        return rb_binary_str_new("", 0);

    switch (d->algo) {
    case ALGO_ZSTD: {
        ZSTD_inBuffer input = {src, slen, 0};
        size_t out_cap = ZSTD_CStreamOutSize();
        size_t result_cap = out_cap > slen ? out_cap : slen;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;
        int use_fiber = has_fiber_scheduler();
        size_t fiber_counter = 0;

        while (input.pos < input.size) {
            if (result_len + out_cap > result_cap) {
                result_cap = result_cap * 2;
                grow_binary_str(result, result_len, result_cap);
            }

            ZSTD_outBuffer output = {RSTRING_PTR(result) + result_len, out_cap, 0};
            size_t ret = ZSTD_compressStream(d->ctx.zstd, &output, &input);
            if (ZSTD_isError(ret))
                rb_raise(eError, "zstd compress stream: %s", ZSTD_getErrorName(ret));
            result_len += output.pos;
            if (use_fiber) {
                int did_yield = 0;
                fiber_counter = fiber_maybe_yield(fiber_counter, output.pos, &did_yield);
                (void)did_yield;
            }
        }
        rb_str_set_len(result, result_len);
        RB_GC_GUARD(chunk);
        return result;
    }
    case ALGO_BROTLI: {
        size_t available_in = slen;
        const uint8_t *next_in = (const uint8_t *)src;
        size_t result_cap = slen;
        if (result_cap < 1024)
            result_cap = 1024;
        VALUE result = rb_binary_str_buf_reserve(result_cap);
        size_t result_len = 0;
        int use_fiber = has_fiber_scheduler();
        size_t fiber_counter = 0;

        while (available_in > 0 || BrotliEncoderHasMoreOutput(d->ctx.brotli)) {
            size_t available_out = 0;
            uint8_t *next_out = NULL;
            BROTLI_BOOL ok =
                BrotliEncoderCompressStream(d->ctx.brotli, BROTLI_OPERATION_PROCESS, &available_in,
                                            &next_in, &available_out, &next_out, NULL);
            if (!ok)
                rb_raise(eError, "brotli compress stream failed");

            const uint8_t *out_data;
            size_t out_size = 0;
            out_data = BrotliEncoderTakeOutput(d->ctx.brotli, &out_size);
            if (out_size > 0) {
                if (result_len + out_size > result_cap) {
                    result_cap = (result_len + out_size) * 2;
                    grow_binary_str(result, result_len, result_cap);
                }

                memcpy(RSTRING_PTR(result) + result_len, out_data, out_size);
                result_len += out_size;
                if (use_fiber) {
                    int did_yield = 0;
                    fiber_counter = fiber_maybe_yield(fiber_counter, out_size, &did_yield);
                    (void)did_yield;
                }
            }
        }
        rb_str_set_len(result, result_len);
        RB_GC_GUARD(chunk);
        return result;
    }
    case ALGO_LZ4: {
        VALUE result = rb_binary_str_buf_reserve(0);
        size_t result_len = 0;
        size_t result_cap = 0;

        while (slen > 0) {
            size_t space = LZ4_RING_BUFFER_SIZE - d->lz4_ring.pending;
            size_t copy = slen < space ? slen : space;

            if (d->lz4_ring.ring_offset + copy > LZ4_RING_BUFFER_TOTAL) {
                rb_raise(eError, "lz4: ring buffer overflow");
            }

            memcpy(d->lz4_ring.buf + d->lz4_ring.ring_offset, src, copy);
            d->lz4_ring.ring_offset += copy;
            d->lz4_ring.pending += copy;
            src += copy;
            slen -= copy;

            if (d->lz4_ring.pending >= (size_t)LZ4_RING_BUFFER_SIZE) {
                VALUE block = lz4_compress_ring_block(d);
                size_t blen = RSTRING_LEN(block);
                if (blen > 0) {
                    if (result_len + blen > result_cap) {
                        result_cap = (result_len + blen) * 2;
                        if (result_cap < 256)
                            result_cap = 256;
                        grow_binary_str(result, result_len, result_cap);
                    }
                    memcpy(RSTRING_PTR(result) + result_len, RSTRING_PTR(block), blen);
                    result_len += blen;
                }
            }
        }
        rb_str_set_len(result, result_len);
        RB_GC_GUARD(chunk);
        return result;
    }
    }
    return rb_binary_str_new("", 0);
}