codeql/python/extractor/tsg-python/src/main.rs at main · github/codeql · GitHub

History

715 lines (643 loc) · 22.9 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

// -*- coding: utf-8 -*-

// ------------------------------------------------------------------------------------------------

// Licensed under either of Apache License, Version 2.0, or MIT license, at your option.

// Please see the LICENSE-APACHE or LICENSE-MIT files in this distribution for license details.

// ------------------------------------------------------------------------------------------------

use std::path::Path;

use anyhow::Context as _;

use anyhow::Result;

use anyhow::anyhow;

use clap::{Arg, ArgAction, Command};

use tree_sitter::Parser;

use tree_sitter_graph::ExecutionConfig;

use tree_sitter_graph::Identifier;

use tree_sitter_graph::NoCancellation;

use tree_sitter_graph::Variables;

use tree_sitter_graph::ast::File;

use tree_sitter_graph::functions::Functions;

const BUILD_VERSION: &str = env!("CARGO_PKG_VERSION");

pub mod extra_functions {

use tree_sitter_graph::functions::{Function, Parameters};

use tree_sitter_graph::graph::{Graph, Value};

use tree_sitter_graph::{ExecutionError, Identifier};

pub struct Location;

fn get_location(node: Value, graph: &Graph) -> Result<Value, ExecutionError> {

let node = graph[node.into_syntax_node_ref()?];

let start = node.start_position();

let end = node.end_position();

Ok(Value::List(

vec![start.row, start.column, end.row, end.column]

.into_iter()

.map(|v| Value::from(v as u32))

.collect(),

))

}

impl Function for Location {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = parameters.param()?;

parameters.finish()?;

get_location(node, graph)

}

pub struct LocationStart;

impl Function for LocationStart {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let start = node.start_position();

Ok(Value::List(

vec![start.row, start.column]

.into_iter()

.map(|v| Value::from(v as u32))

.collect(),

))

}

pub struct LocationEnd;

impl Function for LocationEnd {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let end = node.end_position();

Ok(Value::List(

vec![end.row, end.column]

.into_iter()

.map(|v| Value::from(v as u32))

.collect(),

))

}

pub struct AstNode;

impl Function for AstNode {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let tree_sitter_node = parameters.param()?;

let kind = parameters.param()?;

parameters.finish()?;

let node = graph.add_graph_node();

let loc = get_location(tree_sitter_node, graph)?;

graph[node]

.attributes

.add(Identifier::from("_location"), loc)

.map_err(|_| {

ExecutionError::DuplicateAttribute(format!(

" _location on graph node ({:?})",

node

))

})?;

graph[node]

.attributes

.add(Identifier::from("_kind"), kind)

.map_err(|_| {

ExecutionError::DuplicateAttribute(format!(" _kind on graph node ({:?})", node))

})?;

Ok(Value::GraphNode(node))

}

/// A struct representing the prefix on a Python string.

struct Prefix {

flags: String,

quotes: String,

}

impl Prefix {

fn full(&self) -> String {

format!("{}{}", self.flags, self.quotes)

}

fn safe(&self) -> Prefix {

// Remove format (f/F) and template (t/T) flags when generating a safe prefix.

Prefix {

flags: self

.flags

.clone()

.replace("f", "")

.replace("F", "")

.replace("t", "")

.replace("T", ""),

quotes: self.quotes.clone(),

}

fn get_prefix(s: &str) -> Prefix {

let flags_matcher = regex::Regex::new("^[bfurtBFURT]{0,2}").unwrap();

let mut end = 0;

let flags = match flags_matcher.find(s) {

Some(m) => {

end = m.end();

&s[m.start()..m.end()]

}

None => "",

};

let mut quotes = "";

if s[end..].starts_with("\"\"\"") {

quotes = "\"\"\"";

} else if s[end..].starts_with("'''") {

quotes = "'''";

} else if s[end..].starts_with('"') {

quotes = "\"";

} else if s[end..].starts_with('\'') {

quotes = "'";

} else if s[end..].starts_with('}') {

quotes = "}";

}

Prefix {

flags: flags.to_owned(),

quotes: quotes.to_owned(),

}

#[test]

fn test_get_prefix() {

let p = get_prefix("rb'''hello'''");

assert_eq!(p.flags, "rb");

assert_eq!(p.quotes, "'''");

let p = get_prefix("Br\"\"\"hello\"\"\"");

assert_eq!(p.flags, "Br");

assert_eq!(p.quotes, "\"\"\"");

let p = get_prefix("FR\"hello\"");

assert_eq!(p.flags, "FR");

assert_eq!(p.quotes, "\"");

let p = get_prefix("uR'hello'");

assert_eq!(p.flags, "uR");

assert_eq!(p.quotes, "'");

let p = get_prefix("''");

assert_eq!(p.flags, "");

assert_eq!(p.quotes, "'");

let p = get_prefix("\"\"");

assert_eq!(p.flags, "");

assert_eq!(p.quotes, "\"");

let p = get_prefix("\"\"\"\"\"\"");

assert_eq!(p.flags, "");

assert_eq!(p.quotes, "\"\"\"");

let p = get_prefix("t\"hello\"");

assert_eq!(p.flags, "t");

assert_eq!(p.quotes, "\"");

let p = get_prefix("Tr'world'");

assert_eq!(p.flags, "Tr");

assert_eq!(p.quotes, "'");

}

fn get_string_contents(s: String) -> String {

let prefix = get_prefix(&s);

let contents = s.clone();

let contents = contents.strip_prefix(prefix.full().as_str()).unwrap();

let contents = contents.strip_suffix(prefix.quotes.as_str()).unwrap();

contents.to_owned()

}

#[test]

fn test_get_string_contents() {

let s = "rb'''hello'''";

assert_eq!(get_string_contents(s.to_owned()), "hello");

let s = "Br\"\"\"hello\"\"\"";

assert_eq!(get_string_contents(s.to_owned()), "hello");

let s = "FR\"hello\"";

assert_eq!(get_string_contents(s.to_owned()), "hello");

let s = "uR'hello'";

assert_eq!(get_string_contents(s.to_owned()), "hello");

let s = "''";

assert_eq!(get_string_contents(s.to_owned()), "");

let s = "\"\"";

assert_eq!(get_string_contents(s.to_owned()), "");

let s = "\"\"\"\"\"\"";

assert_eq!(get_string_contents(s.to_owned()), "");

let s = "''''''";

assert_eq!(get_string_contents(s.to_owned()), "");

let s = "t\"tmpl\"";

assert_eq!(get_string_contents(s.to_owned()), "tmpl");

let s = "Tr'world'";

assert_eq!(get_string_contents(s.to_owned()), "world");

}

pub struct StringPrefix;

impl Function for StringPrefix {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let prefix = get_prefix(&source[node.byte_range()]).full();

Ok(Value::String(prefix))

}

pub struct StringContents;

impl Function for StringContents {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let contents = get_string_contents(source[node.byte_range()].to_owned());

Ok(Value::String(contents))

}

pub struct StringQuotes;

impl Function for StringQuotes {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let prefix = get_prefix(&source[node.byte_range()]);

Ok(Value::String(prefix.quotes))

}

// Gets a version of the prefix that can be used in a call to `literal_eval`. To do so, we must remove

// any `f` or `F` characters, if present.

pub struct StringSafePrefix;

impl Function for StringSafePrefix {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let prefix = get_prefix(&source[node.byte_range()]).full();

let prefix = prefix

.replace("f", "")

.replace("F", "")

.replace("t", "")

.replace("T", "");

Ok(Value::String(prefix))

}

// Gets a version of the string where `f` and `F` have been stripped from the prefix.

pub struct SafeString;

impl Function for SafeString {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let prefix = get_prefix(&source[node.byte_range()]);

let contents = get_string_contents(source[node.byte_range()].to_owned());

let s = format!("{}{}{}", prefix.safe().full(), contents, prefix.quotes);

Ok(Value::String(s))

}

pub struct UnnamedChildIndex;

impl Function for UnnamedChildIndex {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let parent = match node.parent() {

Some(parent) => parent,

None => {

return Err(ExecutionError::FunctionFailed(

"unnamed-child-index".into(),

"Cannot call child-index on the root node".to_string(),

));

}

};

let mut tree_cursor = parent.walk();

let index = parent

.children(&mut tree_cursor)

.position(|child| child == node)

.ok_or_else(|| {

ExecutionError::FunctionFailed(

"unnamed-child-index".into(),

"Called child-index on a non-named child".to_string(),

)

})?;

Ok(Value::Integer(index as u32))

}

pub struct ConcatenateStrings;

impl Function for ConcatenateStrings {

fn call(

&self,

_graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let mut result = String::new();

while let Ok(param) = parameters.param() {

let string = param.into_string()?;

result.push_str(string.as_str());

}

Ok(Value::String(result))

}

pub struct InstanceOf;

impl Function for InstanceOf {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

let class_name = parameters.param()?.into_string()?;

parameters.finish()?;

let node_type = node.kind();

let class_name = class_name.as_str();

let is_instance = node_type == class_name;

Ok(Value::Boolean(is_instance))

}

pub struct GetParent;

impl Function for GetParent {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

parameters.finish()?;

let parent = node.parent().ok_or_else(|| {

ExecutionError::FunctionFailed(

"get-parent".into(),

"Cannot call get-parent on the root node".to_string(),

)

})?;

Ok(Value::SyntaxNode(graph.add_syntax_node(parent)))

}

pub struct HasNamedChild;

impl Function for HasNamedChild {

fn call(

&self,

graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

let field_name = parameters.param()?.into_string()?;

parameters.finish()?;

let field_name = field_name.as_str();

let has_named_child = node.child_by_field_name(field_name).is_some();

Ok(Value::Boolean(has_named_child))

}

pub struct IsBooleanOperator;

impl Function for IsBooleanOperator {

fn call(

&self,

graph: &mut Graph,

source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let node = graph[parameters.param()?.into_syntax_node_ref()?];

let expected_op_type = parameters.param()?.into_string()?;

parameters.finish()?;

if let Some(op) = node.child_by_field_name("operator") {

let op_type = source[op.byte_range()].to_string();

let is_boolean_op = expected_op_type == op_type;

Ok(Value::Boolean(is_boolean_op))

} else {

Ok(Value::Boolean(false))

}

pub struct Modulo;

impl Function for Modulo {

fn call(

&self,

_graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let left = parameters.param()?.into_integer()?;

let right = parameters.param()?.into_integer()?;

parameters.finish()?;

Ok(Value::Integer(left % right))

}

pub struct GetLastElement;

impl Function for GetLastElement {

fn call(

&self,

_graph: &mut Graph,

_source: &str,

parameters: &mut dyn Parameters,

) -> Result<Value, ExecutionError> {

let list = parameters.param()?.into_list()?;

parameters.finish()?;

let last = list.last().unwrap_or(&Value::Null).clone();

Ok(last)

}

struct TreeIterator<'a> {

nodes_to_visit: Vec<tree_sitter::Node<'a>>,

}

impl<'a> TreeIterator<'a> {

fn new(root: tree_sitter::Node<'a>) -> Self {

Self {

nodes_to_visit: vec![root],

}

impl<'a> Iterator for TreeIterator<'a> {

type Item = tree_sitter::Node<'a>;

fn next(&mut self) -> Option<Self::Item> {

if let Some(node) = self.nodes_to_visit.pop() {

// Add all children to the queue for processing

let children: Vec<_> = (0..node.child_count())

.rev()

.filter_map(|i| node.child(i))

.collect();

self.nodes_to_visit.extend(children);

Some(node)

} else {

None

}

#[derive(Debug, Clone)]

struct SyntaxError {

start_pos: tree_sitter::Point,

end_pos: tree_sitter::Point,

source: String,

}

fn syntax_errors_from_tree<'a>(

root: tree_sitter::Node<'a>,

source: &'a str,

) -> impl Iterator<Item = SyntaxError> + 'a {

TreeIterator::new(root)

.filter(|&node| node.is_error() || node.is_missing())

.map(move |node| {

let start_pos = node.start_position();

let end_pos = node.end_position();

let text = &source.get(node.byte_range()).unwrap_or("");

SyntaxError {

start_pos,

end_pos,

source: text.to_string(),

}

})

}

fn add_syntax_error_nodes(graph: &mut tree_sitter_graph::graph::Graph, errors: &[SyntaxError]) {

for error in errors {

let error_node = graph.add_graph_node();

// Add _kind attribute

graph[error_node]

.attributes

.add(

tree_sitter_graph::Identifier::from("_kind"),

tree_sitter_graph::graph::Value::String("SyntaxErrorNode".to_string()),

)

.expect("Fresh node should not have duplicate attributes");

// Add _location attribute

let location = tree_sitter_graph::graph::Value::List(

vec![

error.start_pos.row,

error.start_pos.column,

error.end_pos.row,

error.end_pos.column,

]

.into_iter()

.map(|v| tree_sitter_graph::graph::Value::from(v as u32))

.collect(),

);

graph[error_node]

.attributes

.add(tree_sitter_graph::Identifier::from("_location"), location)

.expect("Fresh node should not have duplicate attributes");

// Add source attribute

graph[error_node]

.attributes

.add(

tree_sitter_graph::Identifier::from("source"),

tree_sitter_graph::graph::Value::String(error.source.clone()),

)

.expect("Fresh node should not have duplicate attributes");

}

fn main() -> Result<()> {

let matches = Command::new("tsg-python")

.version(BUILD_VERSION)

.author("Taus Brock-Nannestad <tausbn@github.com>")

.about("Extracts a Python AST from the parse tree given by tree-sitter-python")

.arg(

Arg::new("tsg")

.short('t')

.long("tsg")

.action(ArgAction::Set)

.required(false),

)

.arg(Arg::new("source").index(1).required(true))

.get_matches();

let tsg_path = matches

.get_one::<String>("tsg")

.map(|s| Path::new(s).display().to_string())

.unwrap_or_else(|| "bundled `python.tsg`".to_owned());

let source_path = Path::new(matches.get_one::<String>("source").unwrap());

let language = tsp::language();

let mut parser = Parser::new();

parser.set_language(&language)?;

// Statically include `python.tsg`:

let tsg = if matches.contains_id("tsg") {

std::fs::read(&tsg_path).with_context(|| format!("Error reading TSG file {}", tsg_path))?

} else {

include_bytes!("../python.tsg").to_vec()

};

let tsg = String::from_utf8(tsg)?;

let source = std::fs::read(source_path)

.with_context(|| format!("Error reading source file {}", source_path.display()))?;

let source = String::from_utf8(source)?;

let tree = parser

.parse(&source, None)

.ok_or_else(|| anyhow!("Could not parse {}", source_path.display()))?;

let file = File::from_str(language, &tsg)

.with_context(|| anyhow!("Error parsing TSG file {}", tsg_path))?;

let mut functions = Functions::stdlib();

functions.add(Identifier::from("location"), extra_functions::Location);

functions.add(

Identifier::from("location-start"),

extra_functions::LocationStart,

);

functions.add(

Identifier::from("location-end"),

extra_functions::LocationEnd,

);

functions.add(

Identifier::from("string-prefix"),

extra_functions::StringPrefix,

);

functions.add(

Identifier::from("string-contents"),

extra_functions::StringContents,

);

functions.add(

Identifier::from("string-quotes"),

extra_functions::StringQuotes,

);

functions.add(

Identifier::from("string-safe-prefix"),

extra_functions::StringSafePrefix,

);

functions.add(Identifier::from("safe-string"), extra_functions::SafeString);

functions.add(

Identifier::from("unnamed-child-index"),

extra_functions::UnnamedChildIndex,

);

functions.add(Identifier::from("ast-node"), extra_functions::AstNode);

functions.add(

Identifier::from("concatenate-strings"),

extra_functions::ConcatenateStrings,

);

functions.add(Identifier::from("instance-of"), extra_functions::InstanceOf);

functions.add(Identifier::from("get-parent"), extra_functions::GetParent);

functions.add(

Identifier::from("has-named-child"),

extra_functions::HasNamedChild,

);

functions.add(

Identifier::from("is-boolean-operator"),

extra_functions::IsBooleanOperator,

);

functions.add(Identifier::from("mod"), extra_functions::Modulo);

functions.add(

Identifier::from("get-last-element"),

extra_functions::GetLastElement,

);

let globals = Variables::new();

let config = ExecutionConfig::new(&functions, &globals).lazy(false);

let mut graph = file

.execute(&tree, &source, &config, &NoCancellation)

.with_context(|| format!("Could not execute TSG file {}", tsg_path))?;

// Collect and add syntax error nodes to the graph

if tree.root_node().has_error() {

let syntax_errors: Vec<SyntaxError> =

syntax_errors_from_tree(tree.root_node(), &source).collect();

add_syntax_error_nodes(&mut graph, &syntax_errors);

}

print!("{}", graph.pretty_print());

Ok(())

}

codeql/python/extractor/tsg-python/src/main.rs at main · github/codeql · GitHub

Uh oh!

Expand file tree

Breadcrumbs

main.rs

Latest commit

History

Breadcrumbs

main.rs

File metadata and controls