/usr/share/php/PhpParser/Lexer.php is in php-parser 1.4.1-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | <?php
namespace PhpParser;
class Lexer
{
protected $code;
protected $tokens;
protected $pos;
protected $line;
protected $filePos;
protected $tokenMap;
protected $dropTokens;
protected $usedAttributes;
/**
* Creates a Lexer.
*
* @param array $options Options array. Currently only the 'usedAttributes' option is supported,
* which is an array of attributes to add to the AST nodes. Possible attributes
* are: 'comments', 'startLine', 'endLine', 'startTokenPos', 'endTokenPos',
* 'startFilePos', 'endFilePos'. The option defaults to the first three.
* For more info see getNextToken() docs.
*/
public function __construct(array $options = array()) {
// map from internal tokens to PhpParser tokens
$this->tokenMap = $this->createTokenMap();
// map of tokens to drop while lexing (the map is only used for isset lookup,
// that's why the value is simply set to 1; the value is never actually used.)
$this->dropTokens = array_fill_keys(array(T_WHITESPACE, T_OPEN_TAG), 1);
// the usedAttributes member is a map of the used attribute names to a dummy
// value (here "true")
$options += array(
'usedAttributes' => array('comments', 'startLine', 'endLine'),
);
$this->usedAttributes = array_fill_keys($options['usedAttributes'], true);
}
/**
* Initializes the lexer for lexing the provided source code.
*
* @param string $code The source code to lex
*
* @throws Error on lexing errors (unterminated comment or unexpected character)
*/
public function startLexing($code) {
$scream = ini_set('xdebug.scream', '0');
$this->resetErrors();
$this->tokens = @token_get_all($code);
$this->handleErrors();
if (false !== $scream) {
ini_set('xdebug.scream', $scream);
}
$this->code = $code; // keep the code around for __halt_compiler() handling
$this->pos = -1;
$this->line = 1;
$this->filePos = 0;
}
protected function resetErrors() {
// set error_get_last() to defined state by forcing an undefined variable error
set_error_handler(function() { return false; }, 0);
@$undefinedVariable;
restore_error_handler();
}
protected function handleErrors() {
$error = error_get_last();
if (preg_match(
'~^Unterminated comment starting line ([0-9]+)$~',
$error['message'], $matches
)) {
throw new Error('Unterminated comment', (int) $matches[1]);
}
if (preg_match(
'~^Unexpected character in input: \'(.)\' \(ASCII=([0-9]+)\)~s',
$error['message'], $matches
)) {
throw new Error(sprintf(
'Unexpected character "%s" (ASCII %d)',
$matches[1], $matches[2]
));
}
// PHP cuts error message after null byte, so need special case
if (preg_match('~^Unexpected character in input: \'$~', $error['message'])) {
throw new Error('Unexpected null byte');
}
}
/**
* Fetches the next token.
*
* The available attributes are determined by the 'usedAttributes' option, which can
* be specified in the constructor. The following attributes are supported:
*
* * 'comments' => Array of PhpParser\Comment or PhpParser\Comment\Doc instances,
* representing all comments that occurred between the previous
* non-discarded token and the current one.
* * 'startLine' => Line in which the node starts.
* * 'endLine' => Line in which the node ends.
* * 'startTokenPos' => Offset into the token array of the first token in the node.
* * 'endTokenPos' => Offset into the token array of the last token in the node.
* * 'startFilePos' => Offset into the code string of the first character that is part of the node.
* * 'endFilePos' => Offset into the code string of the last character that is part of the node
*
* @param mixed $value Variable to store token content in
* @param mixed $startAttributes Variable to store start attributes in
* @param mixed $endAttributes Variable to store end attributes in
*
* @return int Token id
*/
public function getNextToken(&$value = null, &$startAttributes = null, &$endAttributes = null) {
$startAttributes = array();
$endAttributes = array();
while (1) {
if (isset($this->tokens[++$this->pos])) {
$token = $this->tokens[$this->pos];
} else {
// EOF token with ID 0
$token = "\0";
}
if (isset($this->usedAttributes['startTokenPos'])) {
$startAttributes['startTokenPos'] = $this->pos;
}
if (isset($this->usedAttributes['startFilePos'])) {
$startAttributes['startFilePos'] = $this->filePos;
}
if (is_string($token)) {
// bug in token_get_all
if ('b"' === $token) {
$value = 'b"';
$this->filePos += 2;
$id = ord('"');
} else {
$value = $token;
$this->filePos += 1;
$id = ord($token);
}
if (isset($this->usedAttributes['startLine'])) {
$startAttributes['startLine'] = $this->line;
}
if (isset($this->usedAttributes['endLine'])) {
$endAttributes['endLine'] = $this->line;
}
if (isset($this->usedAttributes['endTokenPos'])) {
$endAttributes['endTokenPos'] = $this->pos;
}
if (isset($this->usedAttributes['endFilePos'])) {
$endAttributes['endFilePos'] = $this->filePos - 1;
}
return $id;
} else {
$this->line += substr_count($token[1], "\n");
$this->filePos += strlen($token[1]);
if (T_COMMENT === $token[0]) {
if (isset($this->usedAttributes['comments'])) {
$startAttributes['comments'][] = new Comment($token[1], $token[2]);
}
} elseif (T_DOC_COMMENT === $token[0]) {
if (isset($this->usedAttributes['comments'])) {
$startAttributes['comments'][] = new Comment\Doc($token[1], $token[2]);
}
} elseif (!isset($this->dropTokens[$token[0]])) {
$value = $token[1];
if (isset($this->usedAttributes['startLine'])) {
$startAttributes['startLine'] = $token[2];
}
if (isset($this->usedAttributes['endLine'])) {
$endAttributes['endLine'] = $this->line;
}
if (isset($this->usedAttributes['endTokenPos'])) {
$endAttributes['endTokenPos'] = $this->pos;
}
if (isset($this->usedAttributes['endFilePos'])) {
$endAttributes['endFilePos'] = $this->filePos - 1;
}
return $this->tokenMap[$token[0]];
}
}
}
throw new \RuntimeException('Reached end of lexer loop');
}
/**
* Returns the token array for current code.
*
* The token array is in the same format as provided by the
* token_get_all() function and does not discard tokens (i.e.
* whitespace and comments are included). The token position
* attributes are against this token array.
*
* @return array Array of tokens in token_get_all() format
*/
public function getTokens() {
return $this->tokens;
}
/**
* Handles __halt_compiler() by returning the text after it.
*
* @return string Remaining text
*/
public function handleHaltCompiler() {
// text after T_HALT_COMPILER, still including ();
$textAfter = substr($this->code, $this->filePos);
// ensure that it is followed by ();
// this simplifies the situation, by not allowing any comments
// in between of the tokens.
if (!preg_match('~^\s*\(\s*\)\s*(?:;|\?>\r?\n?)~', $textAfter, $matches)) {
throw new Error('__HALT_COMPILER must be followed by "();"');
}
// prevent the lexer from returning any further tokens
$this->pos = count($this->tokens);
// return with (); removed
return (string) substr($textAfter, strlen($matches[0])); // (string) converts false to ''
}
/**
* Creates the token map.
*
* The token map maps the PHP internal token identifiers
* to the identifiers used by the Parser. Additionally it
* maps T_OPEN_TAG_WITH_ECHO to T_ECHO and T_CLOSE_TAG to ';'.
*
* @return array The token map
*/
protected function createTokenMap() {
$tokenMap = array();
// 256 is the minimum possible token number, as everything below
// it is an ASCII value
for ($i = 256; $i < 1000; ++$i) {
if (T_DOUBLE_COLON === $i) {
// T_DOUBLE_COLON is equivalent to T_PAAMAYIM_NEKUDOTAYIM
$tokenMap[$i] = Parser::T_PAAMAYIM_NEKUDOTAYIM;
} elseif(T_OPEN_TAG_WITH_ECHO === $i) {
// T_OPEN_TAG_WITH_ECHO with dropped T_OPEN_TAG results in T_ECHO
$tokenMap[$i] = Parser::T_ECHO;
} elseif(T_CLOSE_TAG === $i) {
// T_CLOSE_TAG is equivalent to ';'
$tokenMap[$i] = ord(';');
} elseif ('UNKNOWN' !== $name = token_name($i)) {
if ('T_HASHBANG' === $name) {
// HHVM uses a special token for #! hashbang lines
$tokenMap[$i] = Parser::T_INLINE_HTML;
} else if (defined($name = 'PhpParser\Parser::' . $name)) {
// Other tokens can be mapped directly
$tokenMap[$i] = constant($name);
}
}
}
// HHVM uses a special token for numbers that overflow to double
if (defined('T_ONUMBER')) {
$tokenMap[T_ONUMBER] = Parser::T_DNUMBER;
}
// HHVM also has a separate token for the __COMPILER_HALT_OFFSET__ constant
if (defined('T_COMPILER_HALT_OFFSET')) {
$tokenMap[T_COMPILER_HALT_OFFSET] = Parser::T_STRING;
}
return $tokenMap;
}
}
|