dotpython/src/DotPython.ParserGenerator/PythonParser.cs at main · kidoz/dotpython · GitHub

History

3791 lines (3393 loc) · 130 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

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

using System.Collections.ObjectModel;

using DotPython.Language.Ast;

using DotPython.Language.Diagnostics;

using DotPython.Language.Syntax;

using DotPython.Language.Text;

using DotPython.ParserGenerator.Generation;

namespace DotPython.ParserGenerator;

public static class PythonParser

{

public static PythonParseResult Parse(SourceText source)

{

ArgumentNullException.ThrowIfNull(source);

var tokenization = PythonTokenizer.Tokenize(source);

var executableTokens = tokenization

.Tokens.Where(token => token.Kind != SyntaxTokenKind.NonSignificantNewLine)

.ToArray();

var grammarMatch = GeneratedPythonGrammar.Grammar.Match(executableTokens);

var result = new Parser(tokenization).Parse();

if (!result.Success || grammarMatch.Success)

{

return result;

}

var tokenIndex = Math.Min(grammarMatch.FurthestTokenIndex, executableTokens.Length - 1);

var diagnostics = new List<Diagnostic>(result.Diagnostics)

{

new(

"DPY2011",

"The generated Python grammar rejected syntax accepted by the AST builder.",

DiagnosticSeverity.Error,

executableTokens[tokenIndex].Span

};

return new PythonParseResult(source, result.Module, diagnostics);

}

private sealed class Parser

{

private readonly List<Diagnostic> _diagnostics;

private readonly SourceText _source;

private readonly SyntaxToken[] _tokens;

private int _functionDepth;

private readonly List<bool> _functionYieldFlags = [];

private readonly List<bool> _functionAsyncFlags = [];

private int _position;

internal Parser(TokenizationResult tokenization)

{

_source = tokenization.Source;

_diagnostics = [.. tokenization.Diagnostics];

_tokens =

[

.. tokenization.Tokens.Where(token =>

token.Kind != SyntaxTokenKind.NonSignificantNewLine

];

}

internal PythonParseResult Parse()

{

var statements = ParseStatements(stopAtDedent: false);

var moduleSpan =

statements.Count == 0

? new TextSpan(0, 0)

: TextSpan.FromBounds(statements[0].Span.Start, statements[^1].Span.End);

var module = new PythonModule(statements, moduleSpan);

return new PythonParseResult(_source, module, _diagnostics);

}

private ReadOnlyCollection<PythonStatement> ParseStatements(bool stopAtDedent)

{

var statements = new List<PythonStatement>();

SkipNewLines();

while (

Current.Kind != SyntaxTokenKind.EndOfFile

&& !(stopAtDedent && Current.Kind == SyntaxTokenKind.Dedent)

)

{

var start = _position;

if (Current.Kind == SyntaxTokenKind.Indent)

{

Report("DPY2006", "Unexpected indentation.", Current.Span);

_position++;

}

else if (Current.Kind == SyntaxTokenKind.Dedent)

{

Report("DPY2007", "Unexpected dedent.", Current.Span);

_position++;

}

else if (IsKeyword("if"))

{

statements.Add(ParseIfStatement());

}

else if (IsKeyword("while"))

{

statements.Add(ParseWhileStatement());

}

else if (IsKeyword("for"))

{

statements.Add(ParseForStatement());

}

else if (IsKeyword("with"))

{

statements.Add(ParseWithStatement());

}

else if (IsKeyword("try"))

{

statements.Add(ParseTryStatement());

}

else if (IsKeyword("def"))

{

statements.Add(ParseFunctionDefinition(Array.Empty<PythonExpression>()));

}

else if (IsKeyword("class"))

{

statements.Add(ParseClassDefinition(Array.Empty<PythonExpression>()));

}

else if (IsKeyword("async"))

{

var asyncStatement = ParseAsyncStatement();

if (asyncStatement is not null)

{

statements.Add(asyncStatement);

}

else if (LooksLikeMatchStatement())

{

statements.Add(ParseMatchStatement());

}

else if (Current.Kind == SyntaxTokenKind.At)

{

var decorated = ParseDecoratedDefinition();

if (decorated is not null)

{

statements.Add(decorated);

}

else

{

ParseSimpleStatements(statements);

}

if (_position == start)

{

ReportExpected("a statement", Current.Span);

_position++;

}

SkipNewLines();

}

return statements.AsReadOnly();

}

private PythonIfStatement ParseIfStatement()

{

var start = Advance().Span.Start;

var clauses = new List<PythonConditionalClause>();

while (true)

{

var condition = ParseRequiredExpression("a condition after 'if' or 'elif'");

var colon = Expect(SyntaxTokenKind.Colon, "':' after the condition");

var body = ParseSuite();

var clauseEnd = GetBodyEnd(body, colon.Span.End);

clauses.Add(

new PythonConditionalClause(

condition,

body,

TextSpan.FromBounds(condition.Span.Start, clauseEnd)

)

);

if (!MatchKeyword("elif", out _))

{

break;

}

IReadOnlyList<PythonStatement> elseBody = Array.Empty<PythonStatement>();

var end = clauses[^1].Span.End;

if (MatchKeyword("else", out _))

{

var colon = Expect(SyntaxTokenKind.Colon, "':' after 'else'");

elseBody = ParseSuite();

end = GetBodyEnd(elseBody, colon.Span.End);

}

return new PythonIfStatement(

clauses.AsReadOnly(),

elseBody,

TextSpan.FromBounds(start, end)

);

}

private PythonWhileStatement ParseWhileStatement()

{

var start = Advance().Span.Start;

var condition = ParseRequiredExpression("a condition after 'while'");

var colon = Expect(SyntaxTokenKind.Colon, "':' after the condition");

var body = ParseSuite();

IReadOnlyList<PythonStatement> elseBody = Array.Empty<PythonStatement>();

var end = GetBodyEnd(body, colon.Span.End);

if (MatchKeyword("else", out _))

{

var elseColon = Expect(SyntaxTokenKind.Colon, "':' after 'else'");

elseBody = ParseSuite();

end = GetBodyEnd(elseBody, elseColon.Span.End);

}

return new PythonWhileStatement(

condition,

body,

elseBody,

TextSpan.FromBounds(start, end)

);

}

private PythonForStatement ParseForStatement(int? asyncStart = null)

{

var start = asyncStart ?? Current.Span.Start;

Advance();

var target = ParseForTargets();

if (!MatchKeyword("in", out _))

{

ReportExpected("'in' after the loop target", Current.Span);

}

var iterable = ParseRequiredExpressionList("an iterable after 'in'");

var colon = Expect(SyntaxTokenKind.Colon, "':' after the iterable");

var body = ParseSuite();

IReadOnlyList<PythonStatement> elseBody = Array.Empty<PythonStatement>();

var end = GetBodyEnd(body, colon.Span.End);

if (MatchKeyword("else", out _))

{

var elseColon = Expect(SyntaxTokenKind.Colon, "':' after 'else'");

elseBody = ParseSuite();

end = GetBodyEnd(elseBody, elseColon.Span.End);

}

return new PythonForStatement(

target,

iterable,

body,

elseBody,

TextSpan.FromBounds(start, end),

asyncStart is not null

);

}

private PythonExpression ParseForTargets()

{

var first = ParseForTargetAtom();

if (Current.Kind != SyntaxTokenKind.Comma)

{

return first;

}

var elements = new List<PythonExpression> { first };

while (Match(SyntaxTokenKind.Comma))

{

if (IsKeyword("in") || Current.Kind == SyntaxTokenKind.Colon)

{

break;

}

elements.Add(ParseForTargetAtom());

}

return new PythonTupleExpression(

elements.AsReadOnly(),

TextSpan.FromBounds(elements[0].Span.Start, elements[^1].Span.End)

);

}

private PythonExpression ParseForTargetAtom()

{

if (Match(SyntaxTokenKind.LeftParenthesis, out var leftParenthesis))

{

var inner = ParseForTargets();

var end = ExpectClosingDelimiter(

SyntaxTokenKind.RightParenthesis,

"')'",

inner.Span.End

);

return inner is PythonTupleExpression tuple

? tuple with

{

Span = TextSpan.FromBounds(leftParenthesis.Span.Start, end),

}

: inner;

}

if (Match(SyntaxTokenKind.Star, out var starToken))

{

var starred = ParseForTargetAtom();

return new PythonStarredExpression(

starred,

TextSpan.FromBounds(starToken.Span.Start, starred.Span.End)

);

}

var targetToken = Expect(SyntaxTokenKind.Identifier, "a target after 'for'");

if (targetToken.Text.Length != 0 && IsReservedKeyword(targetToken.Text))

{

Report(

"DPY2010",

$"The keyword '{targetToken.Text}' cannot be used as a loop target.",

targetToken.Span

);

}

return new PythonNameExpression(targetToken.Text, targetToken.Span);

}

/// <summary>

/// `match` is a soft keyword: this is a match statement only when the next token

/// can start a subject expression and the logical line ends with ':' at bracket

/// depth zero. `match = 5`, `match(x)`, and `match[0]: int = 5` stay expressions.

/// </summary>

private bool LooksLikeMatchStatement()

{

if (Current.Kind != SyntaxTokenKind.Identifier || Current.Text != "match")

{

return false;

}

var next = Peek(1);

var startsSubject = next.Kind switch

{

SyntaxTokenKind.Identifier => next.Text is "not" or "lambda"

|| !IsExpressionKeyword(next.Text),

SyntaxTokenKind.IntegerLiteral

or SyntaxTokenKind.FloatLiteral

or SyntaxTokenKind.ImaginaryLiteral

or SyntaxTokenKind.StringLiteral

or SyntaxTokenKind.BytesLiteral

or SyntaxTokenKind.FormattedStringLiteral

or SyntaxTokenKind.TemplateStringLiteral

or SyntaxTokenKind.LeftParenthesis

or SyntaxTokenKind.LeftBracket

or SyntaxTokenKind.LeftBrace

or SyntaxTokenKind.Minus

or SyntaxTokenKind.Plus

or SyntaxTokenKind.Star => true,

_ => false,

};

if (!startsSubject)

{

return false;

}

return LogicalLineEndsWithColon(offset: 1);

}

private bool LogicalLineEndsWithColon(int offset)

{

var depth = 0;

var sawColonLast = false;

for (var index = offset; ; index++)

{

var token = Peek(index);

switch (token.Kind)

{

case SyntaxTokenKind.LeftParenthesis

or SyntaxTokenKind.LeftBracket

or SyntaxTokenKind.LeftBrace:

depth++;

sawColonLast = false;

break;

case SyntaxTokenKind.RightParenthesis

or SyntaxTokenKind.RightBracket

or SyntaxTokenKind.RightBrace:

depth--;

sawColonLast = false;

break;

case SyntaxTokenKind.NewLine or SyntaxTokenKind.EndOfFile:

return sawColonLast;

case SyntaxTokenKind.Colon when depth == 0:

sawColonLast = true;

break;

default:

sawColonLast = false;

break;

}

private PythonMatchStatement ParseMatchStatement()

{

var start = Advance().Span.Start;

var subject = ParseRequiredExpressionList("a subject after 'match'");

Expect(SyntaxTokenKind.Colon, "':' after the match subject");

if (!Match(SyntaxTokenKind.NewLine))

{

ReportExpected("a new line after ':'", Current.Span);

}

SkipNewLines();

if (!Match(SyntaxTokenKind.Indent))

{

ReportExpected("an indented case block", Current.Span);

return new PythonMatchStatement(

subject,

[],

TextSpan.FromBounds(start, subject.Span.End)

);

}

var cases = new List<PythonMatchCase>();

while (Current.Kind == SyntaxTokenKind.Identifier && Current.Text == "case")

{

cases.Add(ParseCaseBlock());

SkipNewLines();

}

if (cases.Count == 0)

{

Report("DPY2024", "A match statement requires at least one case.", Current.Span);

}

if (!Match(SyntaxTokenKind.Dedent))

{

ReportExpected("the end of the match statement", Current.Span);

}

var end = cases.Count == 0 ? subject.Span.End : cases[^1].Span.End;

return new PythonMatchStatement(

subject,

cases.AsReadOnly(),

TextSpan.FromBounds(start, end)

);

}

private PythonMatchCase ParseCaseBlock()

{

var start = Advance().Span.Start;

var pattern = ParseStarCasePattern();

if (Current.Kind == SyntaxTokenKind.Comma || pattern is PythonSequenceStarMarker)

{

var elements = new List<PythonPattern> { pattern };

while (Match(SyntaxTokenKind.Comma))

{

if (Current.Kind == SyntaxTokenKind.Colon || IsKeyword("if"))

{

break;

}

elements.Add(ParseStarCasePattern());

}

pattern = BuildSequencePattern(

elements,

TextSpan.FromBounds(elements[0].Span.Start, elements[^1].Span.End)

);

}

PythonExpression? guard = null;

if (MatchKeyword("if", out _))

{

guard = ParseRequiredExpression("a guard condition after 'if'");

}

var colon = Expect(SyntaxTokenKind.Colon, "':' after the case pattern");

var body = ParseSuite();

return new PythonMatchCase(

pattern,

guard,

body,

TextSpan.FromBounds(start, GetBodyEnd(body, colon.Span.End))

);

}

/// <summary>Internal marker for a parsed `*name` element; never leaves the parser.</summary>

private sealed record PythonSequenceStarMarker(string? Name, TextSpan Span)

: PythonPattern(Span);

private PythonPattern ParseStarCasePattern()

{

if (Match(SyntaxTokenKind.Star, out var starToken))

{

var nameToken = Expect(SyntaxTokenKind.Identifier, "a name after '*'");

return new PythonSequenceStarMarker(

nameToken.Text == "_" ? null : nameToken.Text,

TextSpan.FromBounds(starToken.Span.Start, nameToken.Span.End)

);

}

return ParseAsPattern();

}

private PythonSequencePattern BuildSequencePattern(

List<PythonPattern> elements,

TextSpan span

)

{

var starIndex = -1;

string? starName = null;

var patterns = new List<PythonPattern>();

for (var index = 0; index < elements.Count; index++)

{

if (elements[index] is PythonSequenceStarMarker marker)

{

if (starIndex >= 0)

{

Report(

"DPY2024",

"Only one starred sub-pattern is allowed in a sequence pattern.",

marker.Span

);

continue;

}

starIndex = patterns.Count;

starName = marker.Name;

}

else

{

patterns.Add(elements[index]);

}

return new PythonSequencePattern(patterns.AsReadOnly(), starIndex, starName, span);

}

private PythonClassPattern ParseClassPattern(PythonExpression cls)

{

Advance();

var positional = new List<PythonPattern>();

var keyword = new List<PythonClassPatternKeyword>();

while (Current.Kind != SyntaxTokenKind.RightParenthesis)

{

if (

Current.Kind == SyntaxTokenKind.Identifier

&& Peek(1).Kind == SyntaxTokenKind.Equal

&& !IsReservedKeyword(Current.Text)

)

{

var nameToken = Advance();

Advance();

var valuePattern = ParseAsPattern();

keyword.Add(

new PythonClassPatternKeyword(

nameToken.Text,

valuePattern,

TextSpan.FromBounds(nameToken.Span.Start, valuePattern.Span.End)

)

);

}

else

{

if (keyword.Count != 0)

{

Report(

"DPY2024",

"A positional sub-pattern follows a keyword sub-pattern.",

Current.Span

);

}

positional.Add(ParseAsPattern());

}

if (!Match(SyntaxTokenKind.Comma))

{

break;

}

var end = ExpectClosingDelimiter(SyntaxTokenKind.RightParenthesis, "')'", cls.Span.End);

return new PythonClassPattern(

cls,

positional.AsReadOnly(),

keyword.AsReadOnly(),

TextSpan.FromBounds(cls.Span.Start, end)

);

}

private PythonPattern ParseAsPattern()

{

var pattern = ParseOrPattern();

if (MatchKeyword("as", out _))

{

var nameToken = Expect(SyntaxTokenKind.Identifier, "a name after 'as'");

if (IsReservedKeyword(nameToken.Text))

{

Report(

"DPY2010",

$"The keyword '{nameToken.Text}' cannot be used as a capture name.",

nameToken.Span

);

}

return new PythonAsPattern(

pattern,

nameToken.Text,

TextSpan.FromBounds(pattern.Span.Start, nameToken.Span.End)

);

}

return pattern;

}

private PythonPattern ParseOrPattern()

{

var first = ParseClosedPattern();

if (Current.Kind != SyntaxTokenKind.VerticalBar)

{

return first;

}

var alternatives = new List<PythonPattern> { first };

while (Match(SyntaxTokenKind.VerticalBar))

{

alternatives.Add(ParseClosedPattern());

}

return new PythonOrPattern(

alternatives.AsReadOnly(),

TextSpan.FromBounds(first.Span.Start, alternatives[^1].Span.End)

);

}

private PythonPattern ParseClosedPattern()

{

if (Match(SyntaxTokenKind.LeftParenthesis, out var leftParenthesisToken))

{

if (Match(SyntaxTokenKind.RightParenthesis, out var emptyClose))

{

return new PythonSequencePattern(

[],

-1,

null,

TextSpan.FromBounds(leftParenthesisToken.Span.Start, emptyClose.Span.End)

);

}

var first = ParseStarCasePattern();

if (Current.Kind != SyntaxTokenKind.Comma && first is not PythonSequenceStarMarker)

{

ExpectClosingDelimiter(SyntaxTokenKind.RightParenthesis, "')'", first.Span.End);

return first;

}

var elements = new List<PythonPattern> { first };

while (Match(SyntaxTokenKind.Comma))

{

if (Current.Kind == SyntaxTokenKind.RightParenthesis)

{

break;

}

elements.Add(ParseStarCasePattern());

}

var tupleEnd = ExpectClosingDelimiter(

SyntaxTokenKind.RightParenthesis,

"')'",

elements[^1].Span.End

);

return BuildSequencePattern(

elements,

TextSpan.FromBounds(leftParenthesisToken.Span.Start, tupleEnd)

);

}

if (Match(SyntaxTokenKind.LeftBracket, out var leftBracketToken))

{

var elements = new List<PythonPattern>();

while (Current.Kind != SyntaxTokenKind.RightBracket)

{

elements.Add(ParseStarCasePattern());

if (!Match(SyntaxTokenKind.Comma))

{

break;

}

var end = ExpectClosingDelimiter(

SyntaxTokenKind.RightBracket,

"']'",

elements.Count == 0 ? leftBracketToken.Span.End : elements[^1].Span.End

);

return BuildSequencePattern(

elements,

TextSpan.FromBounds(leftBracketToken.Span.Start, end)

);

}

if (Match(SyntaxTokenKind.LeftBrace, out var leftBraceToken))

{

var items = new List<PythonMappingPatternItem>();

string? restName = null;

while (Current.Kind != SyntaxTokenKind.RightBrace)

{

if (Match(SyntaxTokenKind.DoubleStar, out var restToken))

{

var restIdentifier = Expect(

SyntaxTokenKind.Identifier,

"a name after '**'"

);

if (restName is not null)

{

Report(

"DPY2024",

"Only one '**' rest sub-pattern is allowed.",

restToken.Span

);

}

restName = restIdentifier.Text;

}

else

{

var key = ParseDisjunction();

if (key is null)

{

ReportExpected("a mapping pattern key", Current.Span);

break;

}

Expect(SyntaxTokenKind.Colon, "':' after the mapping pattern key");

var valuePattern = ParseAsPattern();

items.Add(

new PythonMappingPatternItem(

key,

valuePattern,

TextSpan.FromBounds(key.Span.Start, valuePattern.Span.End)

)

);

}

if (!Match(SyntaxTokenKind.Comma))

{

break;

}

var braceEnd = ExpectClosingDelimiter(

SyntaxTokenKind.RightBrace,

"'}'",

items.Count == 0 ? leftBraceToken.Span.End : items[^1].Span.End

);

return new PythonMappingPattern(

items.AsReadOnly(),

restName,

TextSpan.FromBounds(leftBraceToken.Span.Start, braceEnd)

);

}

if (

Current.Kind

is SyntaxTokenKind.IntegerLiteral

or SyntaxTokenKind.FloatLiteral

or SyntaxTokenKind.ImaginaryLiteral

or SyntaxTokenKind.StringLiteral

or SyntaxTokenKind.BytesLiteral

|| (

Current.Kind is SyntaxTokenKind.Minus or SyntaxTokenKind.Plus

&& Peek(1).Kind

is SyntaxTokenKind.IntegerLiteral

or SyntaxTokenKind.FloatLiteral

or SyntaxTokenKind.ImaginaryLiteral

)

{

var literal = ParseDisjunction();

if (literal is null)

{

ReportExpected("a literal pattern", Current.Span);

return new PythonCapturePattern(null, Current.Span);

}

return new PythonLiteralPattern(literal, UseIdentity: false, literal.Span);

}

if (Current.Kind == SyntaxTokenKind.Identifier)

{

if (Current.Text is "None" or "True" or "False")

{

var constant = ParseDisjunction()!;

return new PythonLiteralPattern(constant, UseIdentity: true, constant.Span);

}

if (IsReservedKeyword(Current.Text) || IsExpressionKeyword(Current.Text))

{

Report("DPY2024", $"'{Current.Text}' cannot start a pattern.", Current.Span);

return new PythonCapturePattern(null, Advance().Span);

}

var nameToken = Advance();

PythonExpression reference = new PythonNameExpression(

nameToken.Text,

nameToken.Span

);

var isDotted = Current.Kind == SyntaxTokenKind.Dot;

while (Match(SyntaxTokenKind.Dot))

{

var attribute = Expect(

SyntaxTokenKind.Identifier,

"an attribute name after '.'"

);

reference = new PythonAttributeExpression(

reference,

attribute.Text,

TextSpan.FromBounds(reference.Span.Start, attribute.Span.End)

);

}

if (Current.Kind == SyntaxTokenKind.LeftParenthesis)

{

return ParseClassPattern(reference);

}

if (isDotted)

{

return new PythonValuePattern(reference, reference.Span);

}

return new PythonCapturePattern(

nameToken.Text == "_" ? null : nameToken.Text,

nameToken.Span

);

}

ReportExpected("a pattern", Current.Span);

return new PythonCapturePattern(null, Current.Span);

}

private PythonWithStatement ParseWithStatement(int? asyncStart = null)

{

var start = asyncStart ?? Current.Span.Start;

Advance();

var items = new List<PythonWithItem>();

while (true)

{

var context = ParseRequiredExpression("a context manager after 'with'");

PythonExpression? target = null;

if (MatchKeyword("as", out _))

{

target = ParseExpression();

if (target is null)

{

ReportExpected("a target after 'as'", Current.Span);

}

else if (!IsAssignableTarget(target))

{

Report("DPY2005", "This expression cannot be assigned to.", target.Span);

target = null;

}

items.Add(

new PythonWithItem(

context,

target,

TextSpan.FromBounds(

context.Span.Start,

target?.Span.End ?? context.Span.End

)

);

if (!Match(SyntaxTokenKind.Comma))

{

break;

}

var colon = Expect(SyntaxTokenKind.Colon, "':' after the context managers");

var body = ParseSuite();

var end = GetBodyEnd(body, colon.Span.End);

return new PythonWithStatement(

items.AsReadOnly(),

body,

TextSpan.FromBounds(start, end),

asyncStart is not null

);

}

private PythonTryStatement ParseTryStatement()

{

var start = Advance().Span.Start;

var colon = Expect(SyntaxTokenKind.Colon, "':' after 'try'");

var body = ParseSuite();

var handlers = new List<PythonExceptHandler>();

var sawBareHandler = false;

var end = GetBodyEnd(body, colon.Span.End);

while (MatchKeyword("except", out var exceptToken))

{

var isStar = Match(SyntaxTokenKind.Star);

if (handlers.Count != 0 && handlers[0].IsStar != isStar)

{

Report(

"DPY2028",

"cannot have both 'except' and 'except*' on the same 'try'",

exceptToken.Span

);

}

if (isStar && Current.Kind == SyntaxTokenKind.Colon)

{

Report("DPY2028", "expected one or more exception types", Current.Span);

}

PythonExpression? type = null;

PythonNameExpression? target = null;

if (Current.Kind != SyntaxTokenKind.Colon)

{

type = ParseRequiredExpression("an exception type after 'except'");

if (MatchKeyword("as", out _))

{

var targetToken = Expect(SyntaxTokenKind.Identifier, "a target after 'as'");

if (IsReservedKeyword(targetToken.Text))

{

Report(

"DPY2010",

$"The keyword '{targetToken.Text}' cannot be used as an exception target.",

targetToken.Span

);

}

target = new PythonNameExpression(targetToken.Text, targetToken.Span);

}

else

{

if (sawBareHandler)

{

Report(

"DPY2012",

"A try statement cannot contain more than one bare except clause.",

exceptToken.Span

);

}

sawBareHandler = true;

}

var handlerColon = Expect(SyntaxTokenKind.Colon, "':' after the except clause");

var handlerBody = ParseSuite();

end = GetBodyEnd(handlerBody, handlerColon.Span.End);

handlers.Add(

new PythonExceptHandler(

type,

target,

handlerBody,

TextSpan.FromBounds(exceptToken.Span.Start, end),

isStar

)

);

if (sawBareHandler && IsKeyword("except"))

{

Report(

"DPY2013",

"A bare except clause must be the last exception handler.",

Current.Span

);

}

IReadOnlyList<PythonStatement> elseBody = Array.Empty<PythonStatement>();

if (MatchKeyword("else", out var elseToken))

{

if (handlers.Count == 0)

{

Report(

"DPY2014",

"A try statement requires an except clause before 'else'.",

elseToken.Span

);

}

var elseColon = Expect(SyntaxTokenKind.Colon, "':' after 'else'");

elseBody = ParseSuite();

end = GetBodyEnd(elseBody, elseColon.Span.End);

}

IReadOnlyList<PythonStatement> finallyBody = Array.Empty<PythonStatement>();

if (MatchKeyword("finally", out _))

{

var finallyColon = Expect(SyntaxTokenKind.Colon, "':' after 'finally'");

finallyBody = ParseSuite();

end = GetBodyEnd(finallyBody, finallyColon.Span.End);

}

if (handlers.Count == 0 && finallyBody.Count == 0)

{

Report(

"DPY2015",

"A try statement requires at least one except or finally clause.",

new TextSpan(start, Math.Max(1, end - start))

View remainder of file in raw view

dotpython/src/DotPython.ParserGenerator/PythonParser.cs at main · kidoz/dotpython · GitHub

Navigation Menu

Expand file tree

Breadcrumbs

PythonParser.cs

Latest commit

History

Breadcrumbs

PythonParser.cs

File metadata and controls

Footer

Footer navigation