JavaRes/src/atp/Lexer.java at master · eprover/JavaRes · GitHub

History

670 lines (589 loc) · 25.4 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

A simple lexical analyser that converts a string into a sequence of

tokens. Java's StreamTokenizer can't be used since it only can

"push back" one token.

This will convert a string into a sequence of

tokens that can be inspected and processed in-order. It is a bit

of an overkill for the simple application, but makes actual

parsing later much easier and more robust than a quicker hack.

This program is free software; you can redistribute it and/or modify

it under the terms of the GNU General Public License as published by

the Free Software Foundation; either version 2 of the License, or

(at your option) any later version.

This program is distributed in the hope that it will be useful,

but WITHOUT ANY WARRANTY; without even the implied warranty of

MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the

GNU General Public License for more details.

You should have received a copy of the GNU General Public License

along with this program ; if not, write to the Free Software

Foundation, Inc., 59 Temple Place, Suite 330, Boston,

MA 02111-1307 USA

package atp;

import java.io.*;

import java.util.*;

import java.util.regex.*;

import java.text.*;

public class Lexer {

public int ttype = 0;

public String sval = "";

public static final String NoToken = "No Token";

public static final String WhiteSpace = "White Space";

public static final String Newline = "Newline";

public static final String HashComment = "HashComment";

public static final String PerComment = "PerComment";

public static final String IdentUpper = "Identifier starting with capital letter";

public static final String IdentLower = "Identifier starting with lower case letter";

public static final String DefFunctor = "Defined symbol (starting with a $)";

public static final String Number = "Positive or negative Integer or real";

public static final String QuotedString = "Quoted string";

public static final String FullStop = ". (full stop)";

public static final String OpenPar = "(";

public static final String ClosePar = ")";

public static final String OpenSquare = "[";

public static final String CloseSquare = "]";

public static final String Comma = ",";

public static final String Colon = ":";

public static final String EqualSign = "=";

public static final String NotEqualSign = "!=";

public static final String Nand = "~&";

public static final String Nor = "~|";

public static final String Or = "|";

public static final String And = "&";

public static final String Implies = "=>";

public static final String BImplies = "<=";

public static final String Equiv = "<=>";

public static final String Xor = "<~>";

public static final String Universal = "!";

public static final String Existential = "?";

public static final String Negation = "~";

public static final String EOFToken = "*EOF*";

public String filename = "";

public String type = "";

public String literal = "";

public String line = null;

public String SZS = "";

public int pos = 0; // character position on the current line

public LineNumberReader input = null;

public ArrayDeque<String> tokenStack = new ArrayDeque<String>();

/** This array contains all of the compiled Pattern objects that

* will be used by methods in this file. */

private static LinkedHashMap<String,Pattern> tokenDefs = new LinkedHashMap<String,Pattern>();

public static ArrayList<String> andOr = new ArrayList<String>();

public static ArrayList<String> binaryRel = new ArrayList<String>();

public static ArrayList<String> quant = new ArrayList<String>();

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

public Lexer() {

init();

}

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

public Lexer(String s) {

init();

//source = s;

input = new LineNumberReader(new StringReader(s));

}

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

public Lexer(File f) {

init();

//source = file2string(f);

try {

input = new LineNumberReader(new FileReader(f));

}

catch (FileNotFoundException fnf) {

System.out.println("Error in Lexer(): File not found: " + f);

System.out.println(fnf.getMessage());

fnf.printStackTrace();

}

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

public String file2string(File f) {

String result = null;

DataInputStream in = null;

try {

byte[] buffer = new byte[(int) f.length()];

in = new DataInputStream(new FileInputStream(f));

in.readFully(buffer);

result = new String(buffer);

}

catch (IOException e) {

throw new RuntimeException("IO problem in fileToString", e);

}

finally {

try {

in.close();

}

catch (IOException e) { /* ignore it */

}

return result;

}

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

* Return the line number of the token by counting all the

* newlines in the position up to the current token.

private int linepos() {

return input.getLineNumber();

//return source.substring(0,pos).split(" ").length + 1;

}

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

private static void init() {

tokenDefs.put(FullStop, Pattern.compile("\\."));

tokenDefs.put(OpenPar, Pattern.compile("\\("));

tokenDefs.put(ClosePar, Pattern.compile("\\)"));

tokenDefs.put(OpenSquare, Pattern.compile("\\["));

tokenDefs.put(CloseSquare, Pattern.compile("\\]"));

tokenDefs.put(Comma, Pattern.compile(","));

tokenDefs.put(Colon, Pattern.compile(":"));

tokenDefs.put(Nor, Pattern.compile("~\\|"));

tokenDefs.put(Nand, Pattern.compile("~&"));

tokenDefs.put(Or, Pattern.compile("\\|"));

tokenDefs.put(And, Pattern.compile("&"));

tokenDefs.put(Implies, Pattern.compile("=>"));

tokenDefs.put(Equiv, Pattern.compile("<=>"));

tokenDefs.put(BImplies, Pattern.compile("<="));

tokenDefs.put(Xor, Pattern.compile("<~>"));

tokenDefs.put(EqualSign, Pattern.compile("="));

tokenDefs.put(NotEqualSign, Pattern.compile("!="));

tokenDefs.put(Negation, Pattern.compile("~"));

tokenDefs.put(Universal, Pattern.compile("!"));

tokenDefs.put(Existential, Pattern.compile("\\?"));

tokenDefs.put(Newline, Pattern.compile("\\n"));

tokenDefs.put(WhiteSpace, Pattern.compile("\\s+"));

tokenDefs.put(IdentLower, Pattern.compile("[a-z][_a-z0-9_A-Z]*"));

tokenDefs.put(IdentUpper, Pattern.compile("[_A-Z][_a-z0-9_A-Z]*"));

tokenDefs.put(DefFunctor, Pattern.compile("\\$[_a-z0-9_A-Z]*"));

tokenDefs.put(Number, Pattern.compile("-?[0-9]?[0-9\\.]+E?-?[0-9]*"));

tokenDefs.put(HashComment, Pattern.compile("#[^\\n]*"));

tokenDefs.put(PerComment, Pattern.compile("\\%[^\\n]*"));

tokenDefs.put(QuotedString,Pattern.compile("'[^']*'"));

andOr.add(And);

andOr.add(Or);

binaryRel.add(Nor);

binaryRel.add(Xor);

binaryRel.add(Nand);

binaryRel.add(Equiv);

binaryRel.add(Implies);

binaryRel.add(BImplies);

quant.add(Universal);

quant.add(Existential);

}

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

* Return the next token without consuming it.

public String look() throws ParseException {

String res = next();

//System.out.println("INFO in Lexer.look(): " + res);

tokenStack.push(res);

return res;

}

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

* Return the literal value of the next token, i.e. the string

* generating the token.

public String lookLit() throws ParseException {

look();

return literal;

}

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

* Take a list of expected token types. Return True if the

* next token is expected, False otherwise.

public boolean testTok(ArrayList<String> tokens) throws ParseException {

look();

for (int i = 0; i < tokens.size(); i++) {

if (type.equals(tokens.get(i))) {

//System.out.println("INFO in Lexer.testTok(): found token");

return true;

}

//System.out.println("INFO in Lexer.testTok(): didn't find tokens with type: " + type + " for list " + tokens);

return false;

}

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

* Convenience method

public boolean testTok(String tok) throws ParseException {

ArrayList<String> tokens = new ArrayList<String>();

tokens.add(tok);

return testTok(tokens);

}

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

* Take a list of expected token types. If the next token is

* not among the expected ones, exit with an error. Otherwise do

* nothing.

public void checkTok(String tok) throws ParseException {

ArrayList<String> tokens = new ArrayList<String>();

tokens.add(tok);

checkTok(tokens);

}

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

* Take a list of expected token types. If the next token is

* not among the expected ones, exit with an error. Otherwise do

* nothing.

public void checkTok(ArrayList<String> tokens) throws ParseException {

look();

for (int i = 0; i < tokens.size(); i++) {

if (type.equals(tokens.get(i)))

return;

}

throw new ParseException("Error in Lexer.checkTok(): Unexpected token '" + type + "'",linepos());

}

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

public String acceptTok(String token) throws ParseException {

ArrayList<String> tokens = new ArrayList<String>();

tokens.add(token);

checkTok(tokens);

return next();

}

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

* Take a list of expected token types. If the next token is

* among the expected ones, consume and return it. Otherwise, exit

* with an error.

public String acceptTok(ArrayList<String> tokens) throws ParseException {

checkTok(tokens);

return next();

}

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

public boolean testLit(String litval) throws ParseException {

ArrayList<String> litvals = new ArrayList<String>();

litvals.add(litval);

return testLit(litvals);

}

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

* Take a list of expected literal strings. Return True if the

* next token's string value is among them, False otherwise.

public boolean testLit(ArrayList<String> litvals) throws ParseException {

lookLit();

for (int i = 0; i < litvals.size(); i++) {

if (literal.equals(litvals.get(i)))

return true;

}

return false;

}

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

private void checkLit(String litval) throws ParseException {

ArrayList<String> litvals = new ArrayList<String>();

litvals.add(litval);

checkLit(litvals);

}

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

* Take a list of expected literal strings. If the next token's

* literal is not among the expected ones, exit with an

* error. Otherwise do nothing.

private void checkLit(ArrayList<String> litvals) throws ParseException {

if (!testLit(litvals)) {

look();

throw new ParseException("Error in Lexer.checkLit(): " + literal + " not in " + litvals, linepos());

}

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

* Take a list of expected literal strings. If the next token's

* literal is among the expected ones, consume and return the

* literal. Otherwise, exit with an error.

public String acceptLit(ArrayList<String> litvals) throws ParseException {

checkLit(litvals);

return next();

}

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

* Take a list of expected literal strings. If the next token's

* literal is among the expected ones, consume and return the

* literal. Otherwise, exit with an error.

public String acceptLit(String litval) throws ParseException {

ArrayList<String> litvals = new ArrayList<String>();

litvals.add(litval);

checkLit(litvals);

return next();

}

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

public void processComment(String line) {

Pattern value = Pattern.compile("\\%\\sStatus[\\s]+([^\\n]*)");

//Pattern value = Pattern.compile("\\%\\sStatus");

Matcher m = value.matcher(line);

//System.out.println("INFO in processComment(): comment: " + line);

if (m.lookingAt()) {

if (m.group(1).indexOf("Unsatisfiable") > -1 || m.group().indexOf("Theorem") > -1)

SZS = m.group(1);

if (m.group(1).indexOf("Satisfiable") > -1 || m.group().indexOf("CounterSatisfiable") > -1)

SZS = m.group(1);

//System.out.println("# problem SZS status: " + SZS);

}

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

* Return next semantically relevant token.

public String next() throws ParseException {

String res = nextUnfiltered();

while ((type.equals(WhiteSpace) || type.equals(HashComment) ||

type.equals(PerComment)) && !res.equals(EOFToken)) {

//System.out.println(type + ":" + line);

if (type.equals(HashComment) || type.equals(PerComment))

processComment(line);

res = nextUnfiltered();

}

//System.out.println("INFO in next(): returning token: " + res);

return res;

}

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

* Return next token, including tokens ignored by most languages.

private String nextUnfiltered() throws ParseException {

if (tokenStack.size() > 0)

return tokenStack.pop();

else {

if (line == null || line.length() <= pos) {

try {

do {

line = input.readLine();

} while (line != null && line.length() == 0);

//System.out.println("INFO in Lexer.nextUnfiltered(): " + line);

pos = 0;

}

catch (IOException ioe) {

System.out.println("Error in Lexer.nextUnfiltered()");

System.out.println(ioe.getMessage());

ioe.printStackTrace();

return EOFToken;

}

if (line == null) {

//System.out.println("INFO in Lexer.nextUnfiltered(): returning eof");

type = EOFToken;

return EOFToken;

}

Iterator<String> it = tokenDefs.keySet().iterator();

while (it.hasNext()) { // Go through all the token definitions and process the first one that matches

String key = it.next();

Pattern value = tokenDefs.get(key);

Matcher m = value.matcher(line.substring(pos));

//System.out.println("INFO in Lexer.nextUnfiltered(): checking: " + key + " against: " + source.substring(pos));

if (m.lookingAt()) {

//System.out.println("INFO in Lexer.nextUnfiltered(): got token against source: " + source.substring(pos));

literal = line.substring(pos + m.start(),pos + m.end());

pos = pos + m.end();

type = key;

//System.out.println("INFO in Lexer.nextUnfiltered(): got token: " + literal + " type: " + type +

// " at pos: " + pos + " with regex: " + value);

return m.group();

}

if (pos + 4 > line.length())

if (pos - 4 < 0)

throw new ParseException("Error in Lexer.nextUnfiltered(): no matches in token list for " +

line.substring(0,line.length()) + "... at line " + input.getLineNumber(),pos);

else

throw new ParseException("Error in Lexer.nextUnfiltered(): no matches in token list for " +

line.substring(pos - 4,line.length()) + "... at line " + input.getLineNumber(),pos);

else

throw new ParseException("Error in Lexer.nextUnfiltered(): no matches in token list for " +

line.substring(pos,pos+4) + "... at line " + input.getLineNumber(),pos);

}

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

* Return a list of all tokens in the source.

private ArrayList<String> lex() throws ParseException {

ArrayList<String> res = new ArrayList<String>();

while (!testTok(EOFToken)) {

String tok = next();

//System.out.println("INFO in Lexer.lex(): " + tok);

res.add(tok);

}

return res;

}

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

** ***************************************************************

private static String example1 = "f(X,g(a,b))";

private static String example2 = "# Comment\nf(X,g(a,b))";

private static String example3 = "cnf(test,axiom,p(a)|p(f(X))).";

private static String example4 = "^";

private static String example5 = "fof(test,axiom,![X,Y]:?[Z]:~p(X,Y,Z)).";

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

* Test that comments and whitespace are normally ignored.

private static void testLex() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testLex()");

Lexer lex1 = new Lexer(example1);

Lexer lex2 = new Lexer(example2);

try {

ArrayList<String> res1 = lex1.lex();

System.out.println("INFO in Lexer.testLex(): completed parsing example 1: " + example1);

ArrayList<String> res2 = lex2.lex();

System.out.println("INFO in Lexer.testLex(): should be true: " + res1.equals(res2));

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

* Test that self.example 1 is split into the expected tokens.

private static void testTerm() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testTerm()");

Lexer lex1 = new Lexer(example1);

try {

lex1.acceptTok(IdentLower); // f

lex1.acceptTok(OpenPar); // (

lex1.acceptTok(IdentUpper); // X

lex1.acceptTok(Comma); // ,

lex1.acceptTok(IdentLower); // g

lex1.acceptTok(OpenPar); // (

lex1.acceptTok(IdentLower); // a

lex1.acceptTok(Comma); // ,

lex1.acceptTok(IdentLower); // b

lex1.acceptTok(ClosePar); // )

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

private static boolean compareArrays(ArrayList<String> s1, ArrayList<String> s2) {

if (s1.size() != s2.size())

return false;

for (int i = 0; i < s1.size(); i++)

if (!s1.get(i).equals(s2.get(i)))

return false;

return true;

}

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

* Perform lexical analysis of a clause, then rebuild it and

* compare that the strings are the same.

private static void testClause() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testClause()");

Lexer lex = new Lexer(example3);

try {

ArrayList<String> toks = lex.lex();

System.out.println(toks);

System.out.println("Should be true: (tokens == 20): " + (toks.size() == 20) + " actual: " + toks);

StringBuffer rebuild = new StringBuffer();

for (int i = 0; i < toks.size(); i++)

rebuild.append(toks.get(i));

System.out.println(rebuild.toString() + " " + example3);

System.out.println("Should be true: " + rebuild.toString().equals(example3));

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

* Perform lexical analysis of a formula, then rebuild it and

* compare that the strings are the same.

private static void testFormula() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testFormula()");

Lexer lex = new Lexer(example5);

try {

ArrayList<String> toks = lex.lex();

System.out.println(toks);

System.out.println("Should be true: (tokens == 29): " + (toks.size() == 29));

StringBuffer rebuild = new StringBuffer();

for (int i = 0; i < toks.size(); i++)

rebuild.append(toks.get(i));

System.out.println(rebuild.toString());

System.out.println("Should be true: " + rebuild.toString().equals(example5));

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

* Check the positive case of AcceptLit().

private static void testAcceptLit() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testAcceptLit()");

Lexer lex = new Lexer(example3);

try {

lex.acceptLit("cnf");

lex.acceptLit("(");

lex.acceptLit("test");

lex.acceptLit(",");

lex.acceptLit("axiom");

lex.acceptLit(",");

lex.acceptLit("p");

lex.acceptLit("(");

lex.acceptLit("a");

lex.acceptLit(")");

lex.acceptLit("|");

lex.acceptLit("p");

lex.acceptLit("(");

lex.acceptLit("f");

lex.acceptLit("(");

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

* Provoke different errors.

private static void testErrors() {

System.out.println("-------------------------------------------------");

System.out.println("INFO in Lexer.testErrors(): Should throw three errors");

Lexer lex = null;

try {

lex = new Lexer(example4);

lex.look();

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

try {

lex = new Lexer(example1);

lex.checkTok(EqualSign);

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

try {

lex = new Lexer(example1);

lex.checkLit("abc");

}

catch (Exception e) {

System.out.println(e.getMessage());

e.printStackTrace();

}

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

public static void main(String[] args) {

testLex();

testTerm();

testClause();

testFormula();

testAcceptLit();

testErrors();

}

JavaRes/src/atp/Lexer.java at master · eprover/JavaRes · GitHub

Uh oh!

Expand file tree

Breadcrumbs

Lexer.java

Latest commit

History

Breadcrumbs

Lexer.java

File metadata and controls