cpython/Python/compile.c at 3.11 · python/cpython · GitHub

Repository navigation

History

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

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

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

906

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

* This file compiles an abstract syntax tree (AST) into Python bytecode.

* The primary entry point is _PyAST_Compile(), which returns a

* PyCodeObject. The compiler makes several passes to build the code

* object:

* 1. Checks for future statements. See future.c

* 2. Builds a symbol table. See symtable.c.

* 3. Generate code for basic blocks. See compiler_mod() in this file.

* 4. Assemble the basic blocks into final code. See assemble() in

* this file.

* 5. Optimize the byte code (peephole optimizations).

* Note that compiler_mod() suggests module, but the module ast type

* (mod_ty) has cases for expressions and interactive statements.

* CAUTION: The VISIT_* macros abort the current function when they

* encounter a problem. So don't invoke them when there is memory

* which needs to be released. Code blocks are OK, as the compiler

* structure takes care of releasing those. Use the arena to manage

* objects.

#include <stdbool.h>

// Need _PyOpcode_RelativeJump of pycore_opcode.h

#define NEED_OPCODE_TABLES

#include "Python.h"

#include "pycore_ast.h" // _PyAST_GetDocString()

#include "pycore_code.h" // _PyCode_New()

#include "pycore_compile.h" // _PyFuture_FromAST()

#include "pycore_long.h" // _PyLong_GetZero()

#include "pycore_opcode.h" // _PyOpcode_Caches

#include "pycore_pymem.h" // _PyMem_IsPtrFreed()

#include "pycore_symtable.h" // PySTEntryObject

#define DEFAULT_BLOCK_SIZE 16

#define DEFAULT_CODE_SIZE 128

#define DEFAULT_LNOTAB_SIZE 16

#define DEFAULT_CNOTAB_SIZE 32

#define COMP_GENEXP 0

#define COMP_LISTCOMP 1

#define COMP_SETCOMP 2

#define COMP_DICTCOMP 3

/* A soft limit for stack use, to avoid excessive

* memory use for large constants, etc.

* The value 30 is plucked out of thin air.

* Code that could use more stack than this is

* rare, so the exact value is unimportant.

#define STACK_USE_GUIDELINE 30

/* If we exceed this limit, it should

* be considered a compiler bug.

* Currently it should be impossible

* to exceed STACK_USE_GUIDELINE * 100,

* as 100 is the maximum parse depth.

* For performance reasons we will

* want to reduce this to a

* few hundred in the future.

* NOTE: Whatever MAX_ALLOWED_STACK_USE is

* set to, it should never restrict what Python

* we can write, just how we compile it.

#define MAX_ALLOWED_STACK_USE (STACK_USE_GUIDELINE * 100)

/* Pseudo-instructions used in the compiler,

* but turned into NOPs or other instructions

* by the assembler. */

#define SETUP_FINALLY -1

#define SETUP_CLEANUP -2

#define SETUP_WITH -3

#define POP_BLOCK -4

#define JUMP -5

#define JUMP_NO_INTERRUPT -6

#define POP_JUMP_IF_FALSE -7

#define POP_JUMP_IF_TRUE -8

#define POP_JUMP_IF_NONE -9

#define POP_JUMP_IF_NOT_NONE -10

#define MIN_VIRTUAL_OPCODE -10

#define MAX_ALLOWED_OPCODE 254

#define IS_WITHIN_OPCODE_RANGE(opcode) \

((opcode) >= MIN_VIRTUAL_OPCODE && (opcode) <= MAX_ALLOWED_OPCODE)

#define IS_VIRTUAL_OPCODE(opcode) ((opcode) < 0)

#define IS_VIRTUAL_JUMP_OPCODE(opcode) \

((opcode) == JUMP || \

(opcode) == JUMP_NO_INTERRUPT || \

(opcode) == POP_JUMP_IF_NONE || \

(opcode) == POP_JUMP_IF_NOT_NONE || \

(opcode) == POP_JUMP_IF_FALSE || \

(opcode) == POP_JUMP_IF_TRUE)

/* opcodes which are not emitted in codegen stage, only by the assembler */

#define IS_ASSEMBLER_OPCODE(opcode) \

((opcode) == JUMP_FORWARD || \

(opcode) == JUMP_BACKWARD || \

(opcode) == JUMP_BACKWARD_NO_INTERRUPT || \

(opcode) == POP_JUMP_FORWARD_IF_NONE || \

(opcode) == POP_JUMP_BACKWARD_IF_NONE || \

(opcode) == POP_JUMP_FORWARD_IF_NOT_NONE || \

(opcode) == POP_JUMP_BACKWARD_IF_NOT_NONE || \

(opcode) == POP_JUMP_FORWARD_IF_TRUE || \

(opcode) == POP_JUMP_BACKWARD_IF_TRUE || \

(opcode) == POP_JUMP_FORWARD_IF_FALSE || \

(opcode) == POP_JUMP_BACKWARD_IF_FALSE)

#define IS_BACKWARDS_JUMP_OPCODE(opcode) \

((opcode) == JUMP_BACKWARD || \

(opcode) == JUMP_BACKWARD_NO_INTERRUPT || \

(opcode) == POP_JUMP_BACKWARD_IF_NONE || \

(opcode) == POP_JUMP_BACKWARD_IF_NOT_NONE || \

(opcode) == POP_JUMP_BACKWARD_IF_TRUE || \

(opcode) == POP_JUMP_BACKWARD_IF_FALSE)

#define IS_TOP_LEVEL_AWAIT(c) ( \

(c->c_flags->cf_flags & PyCF_ALLOW_TOP_LEVEL_AWAIT) \

&& (c->u->u_ste->ste_type == ModuleBlock))

struct instr {

int i_opcode;

int i_oparg;

/* target block (if jump instruction) */

struct basicblock_ *i_target;

/* target block when exception is raised, should not be set by front-end. */

struct basicblock_ *i_except;

int i_lineno;

int i_end_lineno;

int i_col_offset;

int i_end_col_offset;

};

typedef struct excepthandler {

struct instr *setup;

int offset;

} ExceptHandler;

typedef struct exceptstack {

struct basicblock_ *handlers[CO_MAXBLOCKS+1];

int depth;

} ExceptStack;

#define LOG_BITS_PER_INT 5

#define MASK_LOW_LOG_BITS 31

static inline int

is_bit_set_in_table(const uint32_t *table, int bitindex) {

/* Is the relevant bit set in the relevant word? */

/* 256 bits fit into 8 32-bits words.

* Word is indexed by (bitindex>>ln(size of int in bits)).

* Bit within word is the low bits of bitindex.

if (bitindex >= 0 && bitindex < 256) {

uint32_t word = table[bitindex >> LOG_BITS_PER_INT];

return (word >> (bitindex & MASK_LOW_LOG_BITS)) & 1;

}

else {

return 0;

}

static inline int

is_relative_jump(struct instr *i)

{

return is_bit_set_in_table(_PyOpcode_RelativeJump, i->i_opcode);

}

static inline int

is_block_push(struct instr *instr)

{

int opcode = instr->i_opcode;

return opcode == SETUP_FINALLY || opcode == SETUP_WITH || opcode == SETUP_CLEANUP;

}

static inline int

is_jump(struct instr *i)

{

return IS_VIRTUAL_JUMP_OPCODE(i->i_opcode) ||

is_bit_set_in_table(_PyOpcode_Jump, i->i_opcode);

}

static int

instr_size(struct instr *instruction)

{

int opcode = instruction->i_opcode;

assert(!IS_VIRTUAL_OPCODE(opcode));

int oparg = HAS_ARG(opcode) ? instruction->i_oparg : 0;

int extended_args = (0xFFFFFF < oparg) + (0xFFFF < oparg) + (0xFF < oparg);

int caches = _PyOpcode_Caches[opcode];

return extended_args + 1 + caches;

}

static void

write_instr(_Py_CODEUNIT *codestr, struct instr *instruction, int ilen)

{

int opcode = instruction->i_opcode;

assert(!IS_VIRTUAL_OPCODE(opcode));

int oparg = HAS_ARG(opcode) ? instruction->i_oparg : 0;

int caches = _PyOpcode_Caches[opcode];

switch (ilen - caches) {

case 4:

*codestr++ = _Py_MAKECODEUNIT(EXTENDED_ARG, (oparg >> 24) & 0xFF);

/* fall through */

case 3:

*codestr++ = _Py_MAKECODEUNIT(EXTENDED_ARG, (oparg >> 16) & 0xFF);

/* fall through */

case 2:

*codestr++ = _Py_MAKECODEUNIT(EXTENDED_ARG, (oparg >> 8) & 0xFF);

/* fall through */

case 1:

*codestr++ = _Py_MAKECODEUNIT(opcode, oparg & 0xFF);

break;

default:

Py_UNREACHABLE();

}

while (caches--) {

*codestr++ = _Py_MAKECODEUNIT(CACHE, 0);

}

typedef struct basicblock_ {

/* Each basicblock in a compilation unit is linked via b_list in the

reverse order that the block are allocated. b_list points to the next

block, not to be confused with b_next, which is next by control flow. */

struct basicblock_ *b_list;

/* Exception stack at start of block, used by assembler to create the exception handling table */

ExceptStack *b_exceptstack;

/* pointer to an array of instructions, initially NULL */

struct instr *b_instr;

/* If b_next is non-NULL, it is a pointer to the next

block reached by normal control flow. */

struct basicblock_ *b_next;

/* number of instructions used */

int b_iused;

/* length of instruction array (b_instr) */

int b_ialloc;

/* Number of predecssors that a block has. */

int b_predecessors;

/* depth of stack upon entry of block, computed by stackdepth() */

int b_startdepth;

/* instruction offset for block, computed by assemble_jump_offsets() */

int b_offset;

/* Basic block has no fall through (it ends with a return, raise or jump) */

unsigned b_nofallthrough : 1;

/* Basic block is an exception handler that preserves lasti */

unsigned b_preserve_lasti : 1;

/* Used by compiler passes to mark whether they have visited a basic block. */

unsigned b_visited : 1;

/* Basic block exits scope (it ends with a return or raise) */

unsigned b_exit : 1;

/* b_return is true if a RETURN_VALUE opcode is inserted. */

unsigned b_return : 1;

} basicblock;

/* fblockinfo tracks the current frame block.

A frame block is used to handle loops, try/except, and try/finally.

It's called a frame block to distinguish it from a basic block in the

compiler IR.

enum fblocktype { WHILE_LOOP, FOR_LOOP, TRY_EXCEPT, FINALLY_TRY, FINALLY_END,

WITH, ASYNC_WITH, HANDLER_CLEANUP, POP_VALUE, EXCEPTION_HANDLER,

EXCEPTION_GROUP_HANDLER, ASYNC_COMPREHENSION_GENERATOR };

struct fblockinfo {

enum fblocktype fb_type;

basicblock *fb_block;

/* (optional) type-specific exit or cleanup block */

basicblock *fb_exit;

/* (optional) additional information required for unwinding */

void *fb_datum;

};

enum {

COMPILER_SCOPE_MODULE,

COMPILER_SCOPE_CLASS,

COMPILER_SCOPE_FUNCTION,

COMPILER_SCOPE_ASYNC_FUNCTION,

COMPILER_SCOPE_LAMBDA,

COMPILER_SCOPE_COMPREHENSION,

};

/* The following items change on entry and exit of code blocks.

They must be saved and restored when returning to a block.

struct compiler_unit {

PySTEntryObject *u_ste;

PyObject *u_name;

PyObject *u_qualname; /* dot-separated qualified name (lazy) */

int u_scope_type;

/* The following fields are dicts that map objects to

the index of them in co_XXX. The index is used as

the argument for opcodes that refer to those collections.

PyObject *u_consts; /* all constants */

PyObject *u_names; /* all names */

PyObject *u_varnames; /* local variables */

PyObject *u_cellvars; /* cell variables */

PyObject *u_freevars; /* free variables */

PyObject *u_private; /* for private name mangling */

Py_ssize_t u_argcount; /* number of arguments for block */

Py_ssize_t u_posonlyargcount; /* number of positional only arguments for block */

Py_ssize_t u_kwonlyargcount; /* number of keyword only arguments for block */

/* Pointer to the most recently allocated block. By following b_list

members, you can reach all early allocated blocks. */

basicblock *u_blocks;

basicblock *u_curblock; /* pointer to current block */

int u_nfblocks;

struct fblockinfo u_fblock[CO_MAXBLOCKS];

int u_firstlineno; /* the first lineno of the block */

int u_lineno; /* the lineno for the current stmt */

int u_col_offset; /* the offset of the current stmt */

int u_end_lineno; /* the end line of the current stmt */

int u_end_col_offset; /* the end offset of the current stmt */

/* true if we need to create an implicit basicblock before the next instr */

int u_need_new_implicit_block;

};

/* This struct captures the global state of a compilation.

The u pointer points to the current compilation unit, while units

for enclosing blocks are stored in c_stack. The u and c_stack are

managed by compiler_enter_scope() and compiler_exit_scope().

Note that we don't track recursion levels during compilation - the

task of detecting and rejecting excessive levels of nesting is

handled by the symbol analysis pass.

struct compiler {

PyObject *c_filename;

struct symtable *c_st;

PyFutureFeatures *c_future; /* pointer to module's __future__ */

PyCompilerFlags *c_flags;

int c_optimize; /* optimization level */

int c_interactive; /* true if in interactive mode */

int c_nestlevel;

PyObject *c_const_cache; /* Python dict holding all constants,

including names tuple */

struct compiler_unit *u; /* compiler state for current block */

PyObject *c_stack; /* Python list holding compiler_unit ptrs */

PyArena *c_arena; /* pointer to memory allocation arena */

};

typedef struct {

// A list of strings corresponding to name captures. It is used to track:

// - Repeated name assignments in the same pattern.

// - Different name assignments in alternatives.

// - The order of name assignments in alternatives.

PyObject *stores;

// If 0, any name captures against our subject will raise.

int allow_irrefutable;

// An array of blocks to jump to on failure. Jumping to fail_pop[i] will pop

// i items off of the stack. The end result looks like this (with each block

// falling through to the next):

// fail_pop[4]: POP_TOP

// fail_pop[3]: POP_TOP

// fail_pop[2]: POP_TOP

// fail_pop[1]: POP_TOP

// fail_pop[0]: NOP

basicblock **fail_pop;

// The current length of fail_pop.

Py_ssize_t fail_pop_size;

// The number of items on top of the stack that need to *stay* on top of the

// stack. Variable captures go beneath these. All of them will be popped on

// failure.

Py_ssize_t on_top;

} pattern_context;

static int compiler_enter_scope(struct compiler *, identifier, int, void *, int);

static void compiler_free(struct compiler *);

static basicblock *compiler_new_block(struct compiler *);

static int compiler_next_instr(basicblock *);

static int compiler_addop(struct compiler *, int);

static int compiler_addop_i(struct compiler *, int, Py_ssize_t);

static int compiler_addop_j(struct compiler *, int, basicblock *);

static int compiler_addop_j_noline(struct compiler *, int, basicblock *);

static int compiler_error(struct compiler *, const char *, ...);

static int compiler_warn(struct compiler *, const char *, ...);

static int compiler_nameop(struct compiler *, identifier, expr_context_ty);

static PyCodeObject *compiler_mod(struct compiler *, mod_ty);

static int compiler_visit_stmt(struct compiler *, stmt_ty);

static int compiler_visit_keyword(struct compiler *, keyword_ty);

static int compiler_visit_expr(struct compiler *, expr_ty);

static int compiler_augassign(struct compiler *, stmt_ty);

static int compiler_annassign(struct compiler *, stmt_ty);

static int compiler_subscript(struct compiler *, expr_ty);

static int compiler_slice(struct compiler *, expr_ty);

static int are_all_items_const(asdl_expr_seq *, Py_ssize_t, Py_ssize_t);

static int compiler_with(struct compiler *, stmt_ty, int);

static int compiler_async_with(struct compiler *, stmt_ty, int);

static int compiler_async_for(struct compiler *, stmt_ty);

static int validate_keywords(struct compiler *c, asdl_keyword_seq *keywords);

static int compiler_call_simple_kw_helper(struct compiler *c,

asdl_keyword_seq *keywords,

Py_ssize_t nkwelts);

static int compiler_call_helper(struct compiler *c, int n,

asdl_expr_seq *args,

asdl_keyword_seq *keywords);

static int compiler_try_except(struct compiler *, stmt_ty);

static int compiler_try_star_except(struct compiler *, stmt_ty);

static int compiler_set_qualname(struct compiler *);

static int compiler_sync_comprehension_generator(

struct compiler *c,

asdl_comprehension_seq *generators, int gen_index,

int depth,

expr_ty elt, expr_ty val, int type);

static int compiler_async_comprehension_generator(

struct compiler *c,

asdl_comprehension_seq *generators, int gen_index,

int depth,

expr_ty elt, expr_ty val, int type);

static int compiler_pattern(struct compiler *, pattern_ty, pattern_context *);

static int compiler_match(struct compiler *, stmt_ty);

static int compiler_pattern_subpattern(struct compiler *, pattern_ty,

pattern_context *);

static void clean_basic_block(basicblock *bb);

static PyCodeObject *assemble(struct compiler *, int addNone);

#define CAPSULE_NAME "compile.c compiler unit"

PyObject *

_Py_Mangle(PyObject *privateobj, PyObject *ident)

{

/* Name mangling: __private becomes _classname__private.

This is independent from how the name is used. */

PyObject *result;

size_t nlen, plen, ipriv;

Py_UCS4 maxchar;

if (privateobj == NULL || !PyUnicode_Check(privateobj) ||

PyUnicode_READ_CHAR(ident, 0) != '_' ||

PyUnicode_READ_CHAR(ident, 1) != '_') {

Py_INCREF(ident);

return ident;

}

nlen = PyUnicode_GET_LENGTH(ident);

plen = PyUnicode_GET_LENGTH(privateobj);

/* Don't mangle __id__ or names with dots.

The only time a name with a dot can occur is when

we are compiling an import statement that has a

package name.

TODO(jhylton): Decide whether we want to support

mangling of the module name, e.g. __M.X.

if ((PyUnicode_READ_CHAR(ident, nlen-1) == '_' &&

PyUnicode_READ_CHAR(ident, nlen-2) == '_') ||

PyUnicode_FindChar(ident, '.', 0, nlen, 1) != -1) {

Py_INCREF(ident);

return ident; /* Don't mangle __whatever__ */

}

/* Strip leading underscores from class name */

ipriv = 0;

while (PyUnicode_READ_CHAR(privateobj, ipriv) == '_')

ipriv++;

if (ipriv == plen) {

Py_INCREF(ident);

return ident; /* Don't mangle if class is just underscores */

}

plen -= ipriv;

if (plen + nlen >= PY_SSIZE_T_MAX - 1) {

PyErr_SetString(PyExc_OverflowError,

"private identifier too large to be mangled");

return NULL;

}

maxchar = PyUnicode_MAX_CHAR_VALUE(ident);

if (PyUnicode_MAX_CHAR_VALUE(privateobj) > maxchar)

maxchar = PyUnicode_MAX_CHAR_VALUE(privateobj);

result = PyUnicode_New(1 + nlen + plen, maxchar);

if (!result)

return 0;

/* ident = "_" + priv[ipriv:] + ident # i.e. 1+plen+nlen bytes */

PyUnicode_WRITE(PyUnicode_KIND(result), PyUnicode_DATA(result), 0, '_');

if (PyUnicode_CopyCharacters(result, 1, privateobj, ipriv, plen) < 0) {

Py_DECREF(result);

return NULL;

}

if (PyUnicode_CopyCharacters(result, plen+1, ident, 0, nlen) < 0) {

Py_DECREF(result);

return NULL;

}

assert(_PyUnicode_CheckConsistency(result, 1));

return result;

}

static int

compiler_init(struct compiler *c)

{

memset(c, 0, sizeof(struct compiler));

c->c_const_cache = PyDict_New();

if (!c->c_const_cache) {

return 0;

}

c->c_stack = PyList_New(0);

if (!c->c_stack) {

Py_CLEAR(c->c_const_cache);

return 0;

}

return 1;

}

PyCodeObject *

_PyAST_Compile(mod_ty mod, PyObject *filename, PyCompilerFlags *flags,

int optimize, PyArena *arena)

{

struct compiler c;

PyCodeObject *co = NULL;

PyCompilerFlags local_flags = _PyCompilerFlags_INIT;

int merged;

if (!compiler_init(&c))

return NULL;

Py_INCREF(filename);

c.c_filename = filename;

c.c_arena = arena;

c.c_future = _PyFuture_FromAST(mod, filename);

if (c.c_future == NULL)

goto finally;

if (!flags) {

flags = &local_flags;

}

merged = c.c_future->ff_features | flags->cf_flags;

c.c_future->ff_features = merged;

flags->cf_flags = merged;

c.c_flags = flags;

c.c_optimize = (optimize == -1) ? _Py_GetConfig()->optimization_level : optimize;

c.c_nestlevel = 0;

_PyASTOptimizeState state;

state.optimize = c.c_optimize;

state.ff_features = merged;

if (!_PyAST_Optimize(mod, arena, &state)) {

goto finally;

}

c.c_st = _PySymtable_Build(mod, filename, c.c_future);

if (c.c_st == NULL) {

if (!PyErr_Occurred())

PyErr_SetString(PyExc_SystemError, "no symtable");

goto finally;

}

co = compiler_mod(&c, mod);

finally:

compiler_free(&c);

assert(co || PyErr_Occurred());

return co;

}

static void

compiler_free(struct compiler *c)

{

if (c->c_st)

_PySymtable_Free(c->c_st);

if (c->c_future)

PyObject_Free(c->c_future);

Py_XDECREF(c->c_filename);

Py_DECREF(c->c_const_cache);

Py_DECREF(c->c_stack);

}

static PyObject *

list2dict(PyObject *list)

{

Py_ssize_t i, n;

PyObject *v, *k;

PyObject *dict = PyDict_New();

if (!dict) return NULL;

n = PyList_Size(list);

for (i = 0; i < n; i++) {

v = PyLong_FromSsize_t(i);

if (!v) {

Py_DECREF(dict);

return NULL;

}

k = PyList_GET_ITEM(list, i);

if (PyDict_SetItem(dict, k, v) < 0) {

Py_DECREF(v);

Py_DECREF(dict);

return NULL;

}

Py_DECREF(v);

}

return dict;

}

/* Return new dict containing names from src that match scope(s).

src is a symbol table dictionary. If the scope of a name matches

either scope_type or flag is set, insert it into the new dict. The

values are integers, starting at offset and increasing by one for

each key.

static PyObject *

dictbytype(PyObject *src, int scope_type, int flag, Py_ssize_t offset)

{

Py_ssize_t i = offset, scope, num_keys, key_i;

PyObject *k, *v, *dest = PyDict_New();

PyObject *sorted_keys;

assert(offset >= 0);

if (dest == NULL)

return NULL;

/* Sort the keys so that we have a deterministic order on the indexes

saved in the returned dictionary. These indexes are used as indexes

into the free and cell var storage. Therefore if they aren't

deterministic, then the generated bytecode is not deterministic.

sorted_keys = PyDict_Keys(src);

if (sorted_keys == NULL)

return NULL;

if (PyList_Sort(sorted_keys) != 0) {

Py_DECREF(sorted_keys);

return NULL;

}

num_keys = PyList_GET_SIZE(sorted_keys);

for (key_i = 0; key_i < num_keys; key_i++) {

/* XXX this should probably be a macro in symtable.h */

long vi;

k = PyList_GET_ITEM(sorted_keys, key_i);

v = PyDict_GetItemWithError(src, k);

assert(v && PyLong_Check(v));

vi = PyLong_AS_LONG(v);

scope = (vi >> SCOPE_OFFSET) & SCOPE_MASK;

if (scope == scope_type || vi & flag) {

PyObject *item = PyLong_FromSsize_t(i);

if (item == NULL) {

Py_DECREF(sorted_keys);

Py_DECREF(dest);

return NULL;

}

i++;

if (PyDict_SetItem(dest, k, item) < 0) {

Py_DECREF(sorted_keys);

Py_DECREF(item);

Py_DECREF(dest);

return NULL;

}

Py_DECREF(item);

}

Py_DECREF(sorted_keys);

return dest;

}

static void

compiler_unit_check(struct compiler_unit *u)

{

basicblock *block;

for (block = u->u_blocks; block != NULL; block = block->b_list) {

assert(!_PyMem_IsPtrFreed(block));

if (block->b_instr != NULL) {

assert(block->b_ialloc > 0);

assert(block->b_iused >= 0);

assert(block->b_ialloc >= block->b_iused);

}

else {

assert (block->b_iused == 0);

assert (block->b_ialloc == 0);

}

static void

compiler_unit_free(struct compiler_unit *u)

{

basicblock *b, *next;

compiler_unit_check(u);

b = u->u_blocks;

while (b != NULL) {

if (b->b_instr)

PyObject_Free((void *)b->b_instr);

next = b->b_list;

PyObject_Free((void *)b);

b = next;

}

Py_CLEAR(u->u_ste);

Py_CLEAR(u->u_name);

Py_CLEAR(u->u_qualname);

Py_CLEAR(u->u_consts);

Py_CLEAR(u->u_names);

Py_CLEAR(u->u_varnames);

Py_CLEAR(u->u_freevars);

Py_CLEAR(u->u_cellvars);

Py_CLEAR(u->u_private);

PyObject_Free(u);

}

static int

compiler_set_qualname(struct compiler *c)

{

Py_ssize_t stack_size;

struct compiler_unit *u = c->u;

PyObject *name, *base;

base = NULL;

stack_size = PyList_GET_SIZE(c->c_stack);

assert(stack_size >= 1);

if (stack_size > 1) {

int scope, force_global = 0;

struct compiler_unit *parent;

PyObject *mangled, *capsule;

capsule = PyList_GET_ITEM(c->c_stack, stack_size - 1);

parent = (struct compiler_unit *)PyCapsule_GetPointer(capsule, CAPSULE_NAME);

assert(parent);

if (u->u_scope_type == COMPILER_SCOPE_FUNCTION

|| u->u_scope_type == COMPILER_SCOPE_ASYNC_FUNCTION

|| u->u_scope_type == COMPILER_SCOPE_CLASS) {

assert(u->u_name);

mangled = _Py_Mangle(parent->u_private, u->u_name);

if (!mangled)

return 0;

scope = _PyST_GetScope(parent->u_ste, mangled);

Py_DECREF(mangled);

assert(scope != GLOBAL_IMPLICIT);

if (scope == GLOBAL_EXPLICIT)

force_global = 1;

}

if (!force_global) {

if (parent->u_scope_type == COMPILER_SCOPE_FUNCTION

|| parent->u_scope_type == COMPILER_SCOPE_ASYNC_FUNCTION

|| parent->u_scope_type == COMPILER_SCOPE_LAMBDA)

{

_Py_DECLARE_STR(dot_locals, ".<locals>");

base = PyUnicode_Concat(parent->u_qualname,

&_Py_STR(dot_locals));

if (base == NULL)

return 0;

}

else {

Py_INCREF(parent->u_qualname);

base = parent->u_qualname;

}

if (base != NULL) {

_Py_DECLARE_STR(dot, ".");

name = PyUnicode_Concat(base, &_Py_STR(dot));

Py_DECREF(base);

if (name == NULL)

return 0;

PyUnicode_Append(&name, u->u_name);

if (name == NULL)

return 0;

}

else {

Py_INCREF(u->u_name);

name = u->u_name;

}

u->u_qualname = name;

return 1;

}

/* Allocate a new block and return a pointer to it.

Returns NULL on error.

static basicblock *

compiler_new_block(struct compiler *c)

{

basicblock *b;

struct compiler_unit *u;

u = c->u;

b = (basicblock *)PyObject_Calloc(1, sizeof(basicblock));

if (b == NULL) {

PyErr_NoMemory();

return NULL;

}

/* Extend the singly linked list of blocks with new block. */

b->b_list = u->u_blocks;

u->u_blocks = b;

return b;

}

static basicblock *

compiler_use_next_block(struct compiler *c, basicblock *block)

{

assert(block != NULL);

c->u->u_curblock->b_next = block;

c->u->u_curblock = block;

c->u->u_need_new_implicit_block = 0;

return block;

}

static basicblock *

compiler_copy_block(struct compiler *c, basicblock *block)

{

/* Cannot copy a block if it has a fallthrough, since

* a block can only have one fallthrough predecessor.

assert(block->b_nofallthrough);

basicblock *result = compiler_new_block(c);

if (result == NULL) {

return NULL;

}

for (int i = 0; i < block->b_iused; i++) {

int n = compiler_next_instr(result);

if (n < 0) {

return NULL;

}

result->b_instr[n] = block->b_instr[i];

}

result->b_exit = block->b_exit;

result->b_nofallthrough = 1;

return result;

}

/* Returns the offset of the next instruction in the current block's

b_instr array. Resizes the b_instr as necessary.

Returns -1 on failure.

static int

compiler_next_instr(basicblock *b)

{

assert(b != NULL);

if (b->b_instr == NULL) {

b->b_instr = (struct instr *)PyObject_Calloc(

DEFAULT_BLOCK_SIZE, sizeof(struct instr));

if (b->b_instr == NULL) {

PyErr_NoMemory();

return -1;

}

b->b_ialloc = DEFAULT_BLOCK_SIZE;

}

else if (b->b_iused == b->b_ialloc) {

struct instr *tmp;

size_t oldsize, newsize;

oldsize = b->b_ialloc * sizeof(struct instr);

newsize = oldsize << 1;

if (oldsize > (SIZE_MAX >> 1)) {

PyErr_NoMemory();

return -1;

}

if (newsize == 0) {

PyErr_NoMemory();

return -1;

}

b->b_ialloc <<= 1;

tmp = (struct instr *)PyObject_Realloc(

(void *)b->b_instr, newsize);

if (tmp == NULL) {

PyErr_NoMemory();

return -1;

}

b->b_instr = tmp;

memset((char *)b->b_instr + oldsize, 0, newsize - oldsize);

}

return b->b_iused++;

}

/* Set the line number and column offset for the following instructions.

The line number is reset in the following cases:

- when entering a new scope

- on each statement

- on each expression and sub-expression

- before the "except" and "finally" clauses

#define SET_LOC(c, x) \

(c)->u->u_lineno = (x)->lineno; \

(c)->u->u_col_offset = (x)->col_offset; \

(c)->u->u_end_lineno = (x)->end_lineno; \

(c)->u->u_end_col_offset = (x)->end_col_offset;

// Artificial instructions

#define UNSET_LOC(c) \

(c)->u->u_lineno = -1; \

(c)->u->u_col_offset = -1; \

(c)->u->u_end_lineno = -1; \

(c)->u->u_end_col_offset = -1;

#define COPY_INSTR_LOC(old, new) \

(new).i_lineno = (old).i_lineno; \

(new).i_col_offset = (old).i_col_offset; \

(new).i_end_lineno = (old).i_end_lineno; \

(new).i_end_col_offset = (old).i_end_col_offset;

/* Return the stack effect of opcode with argument oparg.

Some opcodes have different stack effect when jump to the target and

when not jump. The 'jump' parameter specifies the case:

* 0 -- when not jump

* 1 -- when jump

* -1 -- maximal

static int

stack_effect(int opcode, int oparg, int jump)

{

switch (opcode) {

case NOP:

case EXTENDED_ARG:

case RESUME:

case CACHE:

return 0;

/* Stack manipulation */

case POP_TOP:

return -1;

case SWAP:

return 0;

/* Unary operators */

case UNARY_POSITIVE:

case UNARY_NEGATIVE:

case UNARY_NOT:

case UNARY_INVERT:

return 0;

case SET_ADD:

case LIST_APPEND:

return -1;

case MAP_ADD:

return -2;

case BINARY_SUBSCR:

return -1;

case STORE_SUBSCR:

return -3;

case DELETE_SUBSCR:

return -2;

case GET_ITER:

return 0;

case PRINT_EXPR:

return -1;

case LOAD_BUILD_CLASS:

return 1;

case RETURN_VALUE:

return -1;

case IMPORT_STAR:

return -1;

case SETUP_ANNOTATIONS:

return 0;

case ASYNC_GEN_WRAP:

case YIELD_VALUE:

return 0;

case POP_BLOCK:

return 0;

case POP_EXCEPT:

return -1;

View remainder of file in raw view

cpython/Python/compile.c at 3.11 · python/cpython · GitHub

Navigation Menu

Repository navigation

Expand file tree

Breadcrumbs

compile.c

Latest commit

History

Breadcrumbs

compile.c

File metadata and controls

Footer

Footer navigation