graalpython/graalpython/python-libbz2/src/bz2.c at master · oracle/graalpython · GitHub

History

543 lines (486 loc) · 16.5 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.

* The Universal Permissive License (UPL), Version 1.0

* Subject to the condition set forth below, permission is hereby granted to any

* person obtaining a copy of this software, associated documentation and/or

* data (collectively the "Software"), free of charge and under any and all

* copyright rights in the Software, and any and all patent rights owned or

* freely licensable by each licensor hereunder covering either (i) the

* unmodified Software as contributed to or provided by such licensor, or (ii)

* the Larger Works (as defined below), to deal in both

* (a) the Software, and

* (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if

* one is included with the Software each a "Larger Work" to which the Software

* is contributed by such licensors),

* without restriction, including without limitation the rights to copy, create

* derivative works of, display, perform, and distribute the Software and make,

* use, sell, offer for sale, import, export, have made, and have sold the

* Software and the Larger Work(s), and to sublicense the foregoing rights on

* either these or other terms.

* This license is subject to the following condition:

* The above copyright notice and either this complete permission notice or at a

* minimum a reference to the UPL must be included in all copies or substantial

* portions of the Software.

* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE

* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE

* SOFTWARE.

* This implementation emulate CPython's bz2

* see cpython/Modules/_bz2module.c

#define DEBUG 500

// #define BENCHMARK

#include <limits.h>

#include <stdlib.h>

#include <string.h>

#include <bzlib.h>

typedef char Byte; /* 8 bits */

#if defined(_MSC_VER)

#include <BaseTsd.h>

typedef SSIZE_T ssize_t;

#define API_FUNC __declspec(dllexport)

#else

#define API_FUNC

#endif

// Integer.MAX_INT

#define GRAALPYTHON_MAX_SIZE (INT_MAX)

#ifndef NDEBUG

#include <stdio.h>

#include <stdarg.h>

static void debug_log(int level, char *file, int line, char *format, ...) {

if (DEBUG > level) {

return;

}

char *type = "ALL";

switch (level) {

case 1000: type = "SEVERE"; break;

case 900: type = "WARNING"; break;

case 800: type = "INFO"; break;

case 700: type = "CONFIG"; break;

case 500: type = "FINE"; break;

case 400: type = "FINER"; break;

case 300: type = "FINEST"; break;

}

va_list args;

va_start(args, format);

fprintf(stderr, "[%s %s:%d] ", type, file, line);

vfprintf(stderr, format, args);

// fprintf(stderr, "\n");

va_end(args);

}

#define LOG_SEVERE(format, ...) \

debug_log(1000, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_WARNING(format, ...) \

debug_log(900, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_INFO(format, ...) \

debug_log(800, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_CONFIG(format, ...) \

debug_log(700, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_FINE(format, ...) \

debug_log(500, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_FINER(format, ...) \

debug_log(400, __FILE__, __LINE__, format, ## __VA_ARGS__);

#define LOG_FINEST(format, ...) \

debug_log(300, __FILE__, __LINE__, format, ## __VA_ARGS__);

#else

#define LOG_SEVERE(format, ...)

#define LOG_WARNING(format, ...)

#define LOG_INFO(format, ...)

#define LOG_CONFIG(format, ...)

#define LOG_FINE(format, ...)

#define LOG_FINER(format, ...)

#define LOG_FINEST(format, ...)

#endif

#ifdef BENCHMARK

#include <sys/time.h>

#include <sys/resource.h>

double get_time()

{

struct timeval t;

struct timezone tzp;

gettimeofday(&t, &tzp);

return t.tv_sec + t.tv_usec*1e-6;

}

#define START_TIME double start_time = get_time();

#define END_TIME(bzst) bzst->timeElapsed += get_time() - start_time;

#else

#define START_TIME

#define END_TIME(bzst)

#endif

// The ref_count is important for `copy` as we

// share off heap storage between native objects.

typedef struct

{

size_t ref_count;

size_t size;

Byte *buf;

} off_heap_buffer;

#define NOT_INITIALIZED 0

#define COMPRESS_TYPE 1

#define DECOMPRESS_TYPE 2

typedef struct

{

bz_stream bzs;

int bzs_type;

off_heap_buffer *output;

size_t output_size;

ssize_t next_in_index;

ssize_t bzs_avail_in_real;

#ifdef BENCHMARK

double timeElapsed;

#endif

} bzst_stream;

static void* BZ2_Malloc(void* ctx, int items, int size)

{

void *m = malloc((size_t)items * (size_t)size);

LOG_FINER("malloc(address: %p, items: %u, size: %u)\n", m, items, size);

return m;

}

static void BZ2_Free(void* ctx, void *ptr)

{

LOG_FINER("free(%p)\n", ptr);

free(ptr);

}

static off_heap_buffer* bz_allocate_buffer(size_t items)

{

size_t size = items * sizeof(Byte);

if (!size) {

LOG_SEVERE("Creating Empty Buffer!!\n");

size = sizeof(Byte);

}

off_heap_buffer *o = (off_heap_buffer*) malloc(sizeof(off_heap_buffer));

if (!o) {

return NULL;

}

Byte *buf = (Byte*) malloc(size);

if (!buf) {

LOG_SEVERE("Memory Error!!\n");

}

o->ref_count = 1;

o->buf = buf;

o->size = items;

LOG_FINER("malloc[off_heap_buffer](address: %p, buf: %p, items: %zu, ref_count: %zu)\n", o, buf, items, o->ref_count);

return o;

}

static void bz_release_buffer(off_heap_buffer *o) {

if (!o) {

return;

}

if (o->ref_count == 0) {

LOG_SEVERE("trying to double free(%p)!!\n", o);

return;

}

LOG_FINEST("off_heap_buffer(address: %p, ref_count: %zu - 1)\n", o, o->ref_count);

o->ref_count--;

if (o->ref_count > 0) {

return;

}

LOG_FINER("free(%p)\n", o);

free(o->buf);

free(o);

}

API_FUNC bzst_stream *bz_create_bzst_stream() {

bzst_stream *bzst = (bzst_stream *) malloc(sizeof(bzst_stream));

bzst->bzs.opaque = NULL;

bzst->bzs.bzalloc = BZ2_Malloc;

bzst->bzs.bzfree = BZ2_Free;

bzst->bzs_type = NOT_INITIALIZED;

bzst->output = bz_allocate_buffer(1);

bzst->output->size = 0;

bzst->output_size = 0;

bzst->next_in_index = 0;

bzst->bzs_avail_in_real = 0;

#ifdef BENCHMARK

bzst->timeElapsed = 0;

#endif

LOG_INFO("bzst_stream(%p)\n", bzst);

return bzst;

}

API_FUNC double bz_get_timeElapsed(bzst_stream* zst) {

#ifdef BENCHMARK

double t = bzst->timeElapsed;

LOG_FINEST("time Elapsed: %.2f\n", t);

bzst->timeElapsed = 0;

return t;

#else

return -1.0;

#endif

}

API_FUNC void bz_free_stream(bzst_stream* bzst) {

if (!bzst) {

return;

}

if(bzst->bzs_type) {

if (bzst->bzs_type == COMPRESS_TYPE) {

BZ2_bzCompressEnd(&bzst->bzs);

} else {

BZ2_bzDecompressEnd(&bzst->bzs);

}

bz_release_buffer(bzst->output);

LOG_INFO("free bzst_stream(%p)\n", bzst);

free(bzst);

}

API_FUNC void bz_gc_helper(bzst_stream* bzst) {

bz_free_stream(bzst);

}

API_FUNC ssize_t bz_get_next_in_index(bzst_stream *bzst) {

return bzst->next_in_index;

}

API_FUNC ssize_t bz_get_bzs_avail_in_real(bzst_stream *bzst) {

return bzst->bzs_avail_in_real;

}

API_FUNC void bz_set_bzs_avail_in_real(bzst_stream *bzst, ssize_t v) {

bzst->bzs_avail_in_real = v;

}

API_FUNC size_t bz_get_output_buffer_size(bzst_stream *bzst) {

LOG_INFO("bz_get_output_buffer_size(%p)\n", bzst);

size_t size = bzst->output_size;

if (size > GRAALPYTHON_MAX_SIZE) {

LOG_SEVERE("buffer size is larger than max: %zd > %zd!!\n", size, (ssize_t) GRAALPYTHON_MAX_SIZE);

return GRAALPYTHON_MAX_SIZE;

}

return size;

}

static void clear_output(bzst_stream *bzst) {

bz_release_buffer(bzst->output);

bzst->output = bz_allocate_buffer(1);

bzst->output->size = 0;

bzst->output_size = 0;

}

API_FUNC void bz_get_output_buffer(bzst_stream *bzst, Byte *dest) {

LOG_INFO("bz_get_off_heap_buffer(%p)\n", bzst);

off_heap_buffer *buffer = bzst->output;

size_t size = bzst->output_size;

if (!size) {

return;

}

memcpy(dest, buffer->buf, size);

clear_output(bzst);

}

static int resize_output_buffer(bzst_stream *bzst, ssize_t length) {

LOG_INFO("resize_output_buffer(%p, %zd)\n", bzst, length);

off_heap_buffer *current = bzst->output;

off_heap_buffer *resized = bz_allocate_buffer(length);

if (!resized) {

return -1;

}

memcpy(resized->buf, current->buf, bzst->output->size);

bz_release_buffer(current);

bzst->output = resized;

return 0;

}

static int bz_prepare_output_buffer(bzst_stream *bzst, ssize_t len) {

LOG_INFO("bz_prepare_output_buffer(%p, %zd)\n", bzst, len);

bz_release_buffer(bzst->output);

bzst->output = bz_allocate_buffer(len);

if (!bzst->output) {

return -1;

}

bzst->output_size = 0;

return 0;

}

static int isOK(int bzerror) {

switch(bzerror) {

case BZ_OK:

case BZ_RUN_OK:

case BZ_FLUSH_OK:

case BZ_FINISH_OK:

case BZ_STREAM_END:

return 1;

default:

return 0;

}

static int

grow_buffer(bzst_stream *bzst, ssize_t max_length) {

LOG_INFO("grow_buffer(%p, %zd)\n", bzst, max_length);

/* Expand the buffer by an amount proportional to the current size,

giving us amortized linear-time behavior. Use a less-than-double

growth factor to avoid excessive allocation. */

size_t size = bzst->output->size;

size_t new_size = size + (size >> 3) + 6;

if (max_length > 0 && new_size > (size_t) max_length)

new_size = (size_t) max_length;

if (new_size > size) {

return resize_output_buffer(bzst, new_size);

} else { /* overflow */

return -1;

}

/************************************************

* Compress Object *

************************************************/

API_FUNC int bz_compressor_init(bzst_stream *bzst, int compresslevel) {

LOG_INFO("bz_compressor_init(%p, %d)\n", bzst, compresslevel);

int bzerror = BZ2_bzCompressInit(&bzst->bzs, compresslevel, 0, 0);

if (!isOK(bzerror)) {

return bzerror;

}

bzst->bzs_type = COMPRESS_TYPE;

return BZ_OK;

}

API_FUNC int bz_compress(bzst_stream *bzst, Byte *data, ssize_t len, int action, ssize_t bufsize) {

LOG_INFO("bz_compress(%p, %zd, %d, %zd)\n", bzst, len, action, bufsize);

size_t data_size = 0;

if (bz_prepare_output_buffer(bzst, bufsize) < 0) {

return BZ_MEM_ERROR;

}

if (len == 0) {

bzst->bzs.next_in = NULL;

} else {

bzst->bzs.next_in = data;

}

bzst->bzs.avail_in = 0;

bzst->bzs.next_out = bzst->output->buf;

bzst->bzs.avail_out = bzst->output->size;

for (;;) {

char *this_out;

int bzerror;

/* On a 64-bit system, len might not fit in avail_in (an unsigned int).

Do compression in chunks of no more than UINT_MAX bytes each. */

if (bzst->bzs.avail_in == 0 && len > 0) {

if (len > GRAALPYTHON_MAX_SIZE) {

bzst->bzs.avail_in = GRAALPYTHON_MAX_SIZE;

} else {

bzst->bzs.avail_in = len;

}

len -= bzst->bzs.avail_in;

}

/* In regular compression mode, stop when input data is exhausted. */

if (action == BZ_RUN && bzst->bzs.avail_in == 0)

break;

if (bzst->bzs.avail_out == 0) {

size_t buffer_left = bzst->output->size - data_size;

if (buffer_left == 0) {

if (grow_buffer(bzst, -1) < 0) {

clear_output(bzst);

return BZ_MEM_ERROR;

}

bzst->bzs.next_out = bzst->output->buf + data_size;

buffer_left = bzst->output->size - data_size;

}

if (buffer_left > GRAALPYTHON_MAX_SIZE) {

bzst->bzs.avail_out = GRAALPYTHON_MAX_SIZE;

} else {

bzst->bzs.avail_out = buffer_left;

}

this_out = bzst->bzs.next_out;

bzerror = BZ2_bzCompress(&bzst->bzs, action);

data_size += bzst->bzs.next_out - this_out;

if (!isOK(bzerror)) {

clear_output(bzst);

return bzerror;

}

/* In flushing mode, stop when all buffered data has been flushed. */

if (action == BZ_FINISH && bzerror == BZ_STREAM_END)

break;

}

bzst->output_size = data_size;

return BZ_OK;

}

/************************************************

* Decompress Object *

************************************************/

API_FUNC int bz_decompress_init(bzst_stream *bzst) {

LOG_INFO("bz_decompress_init(%p)\n", bzst);

int bzerror = BZ2_bzDecompressInit(&bzst->bzs, 0, 0);

if (!isOK(bzerror)) {

return bzerror;

}

bzst->bzs_type = DECOMPRESS_TYPE;

return BZ_OK;

}

/* Decompress data of length d->bzs_avail_in_real in d->bzs.next_in. The output

buffer is allocated dynamically and returned. At most max_length bytes are

returned, so some of the input may not be consumed. d->bzs.next_in and

d->bzs_avail_in_real are updated to reflect the consumed input. */

API_FUNC int bz_decompress(bzst_stream *bzst,

Byte *input_buffer, ssize_t offset,

ssize_t max_length,

ssize_t bufsize, ssize_t bzs_avail_in_real) {

LOG_INFO("bz_decompress(%p, %p, %zd, %zd, %zd)\n", bzst, input_buffer, offset, max_length, bufsize);

/* data_size is strictly positive, but because we repeatedly have to

compare against max_length and PyBytes_GET_SIZE we declare it as

signed */

ssize_t data_size = 0;

bz_stream *bzs = &bzst->bzs;

bzst->bzs_avail_in_real = bzs_avail_in_real;

if (offset < 0) {

bzs->next_in = NULL;

} else {

bzs->next_in = input_buffer + offset;

}

int check_alloc;

if (max_length < 0 || max_length >= bufsize) {

check_alloc = bz_prepare_output_buffer(bzst, bufsize);

} else {

check_alloc = bz_prepare_output_buffer(bzst, max_length);

}

if (check_alloc < 0) {

return BZ_MEM_ERROR;

}

bzs->next_out = bzst->output->buf;

int ret = BZ_OK;

for (;;) {

int bzret;

size_t avail;

/* On a 64-bit system, buffer length might not fit in avail_out, so we

do decompression in chunks of no more than UINT_MAX bytes

each. Note that the expression for `avail` is guaranteed to be

positive, so the cast is safe. */

avail = (size_t) (bzst->output->size - data_size);

if (avail > GRAALPYTHON_MAX_SIZE) {

bzs->avail_out = (unsigned int) GRAALPYTHON_MAX_SIZE;

} else {

bzs->avail_out = (unsigned int) avail;

}

if (bzst->bzs_avail_in_real > GRAALPYTHON_MAX_SIZE) {

bzs->avail_in = (unsigned int) GRAALPYTHON_MAX_SIZE;

} else {

bzs->avail_in = (unsigned int) bzst->bzs_avail_in_real;

}

bzst->bzs_avail_in_real -= bzs->avail_in;

bzret = BZ2_bzDecompress(bzs);

data_size = bzs->next_out - bzst->output->buf;

bzst->next_in_index = bzs->next_in - input_buffer;

bzst->bzs_avail_in_real += bzs->avail_in;

if (!isOK(bzret)) {

clear_output(bzst);

return bzret;

}

if (bzret == BZ_STREAM_END) {

// d->eof = 1; // it will be set on the java-side

ret = bzret;

break;

} else if (bzst->bzs_avail_in_real == 0) {

break;

} else if (bzs->avail_out == 0) {

if (data_size == max_length) {

break;

}

if (data_size == bzst->output->size && grow_buffer(bzst, max_length) < 0) {

clear_output(bzst);

return BZ_MEM_ERROR;

}

bzs->next_out = bzst->output->buf + data_size;

}

bzst->output_size = data_size;

return ret;

}

graalpython/graalpython/python-libbz2/src/bz2.c at master · oracle/graalpython · GitHub

Uh oh!

Expand file tree

Breadcrumbs

bz2.c

Latest commit

History

Breadcrumbs

bz2.c

File metadata and controls