1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568
|
<?php
/**
* PHP_LexerGenerator, a php 5 lexer generator.
*
* This lexer generator translates a file in a format similar to
* re2c ({@link http://re2c.org}) and translates it into a PHP 5-based lexer
*
* PHP version 5
*
* LICENSE: This source file is subject to version 3.01 of the PHP license
* that is available through the world-wide-web at the following URI:
* http://www.php.net/license/3_01.txt. If you did not receive a copy of
* the PHP License and are unable to obtain it through the web, please
* send a note to license@php.net so we can mail you a copy immediately.
*
* @category php
* @package PHP_LexerGenerator
* @author Gregory Beaver <cellog@php.net>
* @copyright 2006 Gregory Beaver
* @license http://www.php.net/license/3_01.txt PHP License 3.01
* @version CVS: $Id: Lexer.php 246683 2007-11-22 04:43:52Z instance $
* @since File available since Release 0.1.0
*/
require_once 'smarty-lexer/LexerGenerator/Parser.php';
/**
* Token scanner for plex files.
*
* This scanner detects comments beginning with "/*!lex2php" and
* then returns their components (processing instructions, patterns, strings
* action code, and regexes)
* @package PHP_LexerGenerator
* @author Gregory Beaver <cellog@php.net>
* @copyright 2006 Gregory Beaver
* @license http://www.php.net/license/3_01.txt PHP License 3.01
* @version @package_version@
* @since Class available since Release 0.1.0
*/
class PHP_LexerGenerator_Lexer
{
private $data;
private $N;
private $state;
/**
* Current line number in input
* @var int
*/
public $line;
/**
* Number of scanning errors detected
* @var int
*/
public $errors = 0;
/**
* integer identifier of the current token
* @var int
*/
public $token;
/**
* string content of current token
* @var string
*/
public $value;
const CODE = PHP_LexerGenerator_Parser::CODE;
const COMMENTEND = PHP_LexerGenerator_Parser::COMMENTEND;
const COMMENTSTART = PHP_LexerGenerator_Parser::COMMENTSTART;
const PATTERN = PHP_LexerGenerator_Parser::PATTERN;
const PHPCODE = PHP_LexerGenerator_Parser::PHPCODE;
const PI = PHP_LexerGenerator_Parser::PI;
const QUOTE = PHP_LexerGenerator_Parser::QUOTE;
const SINGLEQUOTE = PHP_LexerGenerator_Parser::SINGLEQUOTE;
const SUBPATTERN = PHP_LexerGenerator_Parser::SUBPATTERN;
/**
* prepare scanning
* @param string the input
*/
public function __construct($data)
{
$this->data = str_replace("\r\n", "\n", $data);
$this->N = 0;
$this->line = 1;
$this->state = 'Start';
$this->errors = 0;
}
/**
* Output an error message
* @param string
*/
private function error($msg)
{
echo 'Error on line ' . $this->line . ': ' . $msg;
$this->errors++;
}
/**
* Initial scanning state lexer
* @return boolean
*/
private function lexStart()
{
if ($this->N >= strlen($this->data)) {
return false;
}
$a = strpos($this->data, '/*!lex2php' . "\n", $this->N);
if ($a === false) {
$this->value = substr($this->data, $this->N);
$this->N = strlen($this->data);
$this->token = self::PHPCODE;
return true;
}
if ($a > $this->N) {
$this->value = substr($this->data, $this->N, $a - $this->N);
$this->N = $a;
$this->token = self::PHPCODE;
return true;
}
$this->value = '/*!lex2php' . "\n";
$this->N += 11; // strlen("/*lex2php\n")
$this->token = self::COMMENTSTART;
$this->state = 'Declare';
return true;
}
/**
* lexer for top-level canning state after the initial declaration comment
* @return boolean
*/
private function lexStartNonDeclare()
{
if ($this->N >= strlen($this->data)) {
return false;
}
$a = strpos($this->data, '/*!lex2php' . "\n", $this->N);
if ($a === false) {
$this->value = substr($this->data, $this->N);
$this->N = strlen($this->data);
$this->token = self::PHPCODE;
return true;
}
if ($a > $this->N) {
$this->value = substr($this->data, $this->N, $a - $this->N);
$this->N = $a;
$this->token = self::PHPCODE;
return true;
}
$this->value = '/*!lex2php' . "\n";
$this->N += 11; // strlen("/*lex2php\n")
$this->token = self::COMMENTSTART;
$this->state = 'Rule';
return true;
}
/**
* lexer for declaration comment state
* @return boolean
*/
private function lexDeclare()
{
while (true) {
$this -> skipWhitespaceEol();
if (
$this->N + 1 >= strlen($this->data)
|| $this->data[$this->N] != '/'
|| $this->data[$this->N + 1] != '/'
) {
break;
}
// Skip single-line comment
while (
$this->N < strlen($this->data)
&& $this->data[$this->N] != "\n"
) {
++$this->N;
}
}
if ($this->data[$this->N] == '*' && $this->data[$this->N + 1] == '/') {
$this->state = 'StartNonDeclare';
$this->value = '*/';
$this->N += 2;
$this->token = self::COMMENTEND;
return true;
}
if (preg_match('/\G%([a-z]+)/', $this->data, $token, null, $this->N)) {
$this->value = $token[1];
$this->N += strlen($token[1]) + 1;
$this->state = 'DeclarePI';
$this->token = self::PI;
return true;
}
if (preg_match('/\G[a-zA-Z_][a-zA-Z0-9_]*/', $this->data, $token, null, $this->N)) {
$this->value = $token[0];
$this->token = self::PATTERN;
$this->N += strlen($token[0]);
$this->state = 'DeclareEquals';
return true;
}
$this->error('expecting declaration of sub-patterns');
return false;
}
/**
* lexer for processor instructions within declaration comment
* @return boolean
*/
private function lexDeclarePI()
{
$this -> skipWhitespace();
if ($this->data[$this->N] == "\n") {
$this->N++;
$this->state = 'Declare';
$this->line++;
return $this->lexDeclare();
}
if ($this->data[$this->N] == '{') {
return $this->lexCode();
}
if (!preg_match("/\G[^\n]+/", $this->data, $token, null, $this->N)) {
$this->error('Unexpected end of file');
return false;
}
$this->value = $token[0];
$this->N += strlen($this->value);
$this->token = self::SUBPATTERN;
return true;
}
/**
* lexer for processor instructions inside rule comments
* @return boolean
*/
private function lexDeclarePIRule()
{
$this -> skipWhitespace();
if ($this->data[$this->N] == "\n") {
$this->N++;
$this->state = 'Rule';
$this->line++;
return $this->lexRule();
}
if ($this->data[$this->N] == '{') {
return $this->lexCode();
}
if (!preg_match("/\G[^\n]+/", $this->data, $token, null, $this->N)) {
$this->error('Unexpected end of file');
return false;
}
$this->value = $token[0];
$this->N += strlen($this->value);
$this->token = self::SUBPATTERN;
return true;
}
/**
* lexer for the state representing scanning between a pattern and the "=" sign
* @return boolean
*/
private function lexDeclareEquals()
{
$this -> skipWhitespace();
if ($this->N >= strlen($this->data)) {
$this->error('unexpected end of input, expecting "=" for sub-pattern declaration');
}
if ($this->data[$this->N] != '=') {
$this->error('expecting "=" for sub-pattern declaration');
return false;
}
$this->N++;
$this->state = 'DeclareRightside';
$this -> skipWhitespace();
if ($this->N >= strlen($this->data)) {
$this->error('unexpected end of file, expecting right side of sub-pattern declaration');
return false;
}
return $this->lexDeclareRightside();
}
/**
* lexer for the right side of a pattern, detects quotes or regexes
* @return boolean
*/
private function lexDeclareRightside()
{
if ($this->data[$this->N] == "\n") {
$this->state = 'lexDeclare';
$this->N++;
$this->line++;
return $this->lexDeclare();
}
if ($this->data[$this->N] == '"') {
return $this->lexQuote();
}
if ($this->data[$this->N] == '\'') {
return $this->lexQuote('\'');
}
$this -> skipWhitespace();
// match a pattern
$test = $this->data[$this->N];
$token = $this->N + 1;
$a = 0;
do {
if ($a++) {
$token++;
}
$token = strpos($this->data, $test, $token);
} while ($token !== false && ($this->data[$token - 1] == '\\'
&& $this->data[$token - 2] != '\\'));
if ($token === false) {
$this->error('Unterminated regex pattern (started with "' . $test . '"');
return false;
}
if (substr_count($this->data, "\n", $this->N, $token - $this->N)) {
$this->error('Regex pattern extends over multiple lines');
return false;
}
$this->value = substr($this->data, $this->N + 1, $token - $this->N - 1);
// unescape the regex marker
// we will re-escape when creating the final regex
$this->value = str_replace('\\' . $test, $test, $this->value);
$this->N = $token + 1;
$this->token = self::SUBPATTERN;
return true;
}
/**
* lexer for quoted literals
* @return boolean
*/
private function lexQuote($quote = '"')
{
$token = $this->N + 1;
$a = 0;
do {
if ($a++) {
$token++;
}
$token = strpos($this->data, $quote, $token);
} while ($token !== false && $token < strlen($this->data) &&
($this->data[$token - 1] == '\\' && $this->data[$token - 2] != '\\'));
if ($token === false) {
$this->error('unterminated quote');
return false;
}
if (substr_count($this->data, "\n", $this->N, $token - $this->N)) {
$this->error('quote extends over multiple lines');
return false;
}
$this->value = substr($this->data, $this->N + 1, $token - $this->N - 1);
$this->value = str_replace('\\'.$quote, $quote, $this->value);
$this->value = str_replace('\\\\', '\\', $this->value);
$this->N = $token + 1;
if ($quote == '\'') {
$this->token = self::SINGLEQUOTE;
} else {
$this->token = self::QUOTE;
}
return true;
}
/**
* lexer for rules
* @return boolean
*/
private function lexRule()
{
while (
$this->N < strlen($this->data)
&& (
$this->data[$this->N] == ' '
|| $this->data[$this->N] == "\t"
|| $this->data[$this->N] == "\n"
) || (
$this->N < strlen($this->data) - 1
&& $this->data[$this->N] == '/'
&& $this->data[$this->N + 1] == '/'
)
) {
if ($this->data[$this->N] == '/' && $this->data[$this->N + 1] == '/') {
// Skip single line comments
$next_newline = strpos($this->data, "\n", $this->N) + 1;
if ($next_newline) {
$this->N = $next_newline;
} else {
$this->N = sizeof($this->data);
}
$this->line++;
} else {
if ($this->data[$this->N] == "\n") {
$this->line++;
}
$this->N++; // skip all whitespace
}
}
if ($this->N >= strlen($this->data)) {
$this->error('unexpected end of input, expecting rule declaration');
}
if ($this->data[$this->N] == '*' && $this->data[$this->N + 1] == '/') {
$this->state = 'StartNonDeclare';
$this->value = '*/';
$this->N += 2;
$this->token = self::COMMENTEND;
return true;
}
if ($this->data[$this->N] == '\'') {
return $this->lexQuote('\'');
}
if (preg_match('/\G%([a-zA-Z_]+)/', $this->data, $token, null, $this->N)) {
$this->value = $token[1];
$this->N += strlen($token[1]) + 1;
$this->state = 'DeclarePIRule';
$this->token = self::PI;
return true;
}
if ($this->data[$this->N] == "{") {
return $this->lexCode();
}
if ($this->data[$this->N] == '"') {
return $this->lexQuote();
}
if (preg_match('/\G[a-zA-Z_][a-zA-Z0-9_]*/', $this->data, $token, null, $this->N)) {
$this->value = $token[0];
$this->N += strlen($token[0]);
$this->token = self::SUBPATTERN;
return true;
} else {
$this->error('expecting token rule (quotes or sub-patterns)');
return false;
}
}
/**
* lexer for php code blocks
* @return boolean
*/
private function lexCode()
{
$cp = $this->N + 1;
for ($level = 1; $cp < strlen($this->data) && ($level > 1 || $this->data[$cp] != '}'); $cp++) {
if ($this->data[$cp] == '{') {
$level++;
} elseif ($this->data[$cp] == '}') {
$level--;
} elseif ($this->data[$cp] == '/' && $this->data[$cp + 1] == '/') {
/* Skip C++ style comments */
$cp += 2;
$z = strpos($this->data, "\n", $cp);
if ($z === false) {
$cp = strlen($this->data);
break;
}
$cp = $z;
} elseif ($this->data[$cp] == "'" || $this->data[$cp] == '"') {
/* String a character literals */
$startchar = $this->data[$cp];
$prevc = 0;
for ($cp++; $cp < strlen($this->data) && ($this->data[$cp] != $startchar || $prevc === '\\'); $cp++) {
if ($prevc === '\\') {
$prevc = 0;
} else {
$prevc = $this->data[$cp];
}
}
}
}
if ($cp >= strlen($this->data)) {
$this->error("PHP code starting on this line is not terminated before the end of the file.");
$this->error++;
return false;
} else {
$this->value = substr($this->data, $this->N + 1, $cp - $this->N - 1);
$this->token = self::CODE;
$this->N = $cp + 1;
return true;
}
}
/**
* Skip whitespace characters
*/
private function skipWhitespace()
{
while (
$this->N < strlen($this->data)
&& (
$this->data[$this->N] == ' '
|| $this->data[$this->N] == "\t"
)
) {
$this->N++; // skip whitespace
}
}
/**
* Skip whitespace and EOL characters
*/
private function skipWhitespaceEol()
{
while (
$this->N < strlen($this->data)
&& (
$this->data[$this->N] == ' '
|| $this->data[$this->N] == "\t"
|| $this->data[$this->N] == "\n"
)
) {
if ($this->data[$this->N] == "\n") {
++$this -> line;
}
$this->N++; // skip whitespace
}
}
/**
* Primary scanner
*
* In addition to lexing, this properly increments the line number of lexing.
* This calls the proper sub-lexer based on the parser state
* @param unknown_type $parser
* @return unknown
*/
public function advance($parser)
{
if ($this->N >= strlen($this->data)) {
return false;
}
if ($this->{'lex' . $this->state}()) {
$this->line += substr_count($this->value, "\n");
return true;
}
return false;
}
}
|