mirror_php/PHP-Parser
1
0
Fork 0
mirror of https://github.com/nikic/PHP-Parser.git synced 2025-06-05 03:24:50 +02:00
Code Issues Packages Projects Releases Wiki Activity

Don't parse unicode escapes for PHP < 7.0

Browse Source 
We still had the option for this but were hardcoding it to true.
Make it conditional on the PHP version instead.
This commit is contained in:
Nikita Popov 2023-09-23 17:35:51 +02:00
parent f4961b89ac
commit d8e8065313
7 changed files with 102 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
UPGRADE-5.0.md
View File

@ -13,6 +13,7 @@ In particular, if an older `PhpVersion` is specified, then:
* For versions before PHP 7.0, `$foo =& new Bar()` assignments are allowed without error. * For versions before PHP 7.0, `$foo =& new Bar()` assignments are allowed without error.
* For versions before PHP 7.0, invalid octal literals `089` are allowed without error. * For versions before PHP 7.0, invalid octal literals `089` are allowed without error.
* For versions before PHP 7.0, unicode escape sequences `\u{123}` in strings are not parsed.
* Type hints are interpreted as a class `Name` or as a built-in `Identifier` depending on PHP * Type hints are interpreted as a class `Name` or as a built-in `Identifier` depending on PHP
version, for example `int` is treated as a class name on PHP 5.6 and as a built-in on PHP 7.0. version, for example `int` is treated as a class name on PHP 5.6 and as a built-in on PHP 7.0.

44
grammar/parser.template
View File

@ -28,68 +28,68 @@ class #(-p) extends \PhpParser\ParserAbstract
public const %s = %n; public const %s = %n;
#endtokenval #endtokenval
protected $tokenToSymbolMapSize = #(YYMAXLEX); protected int $tokenToSymbolMapSize = #(YYMAXLEX);
protected $actionTableSize = #(YYLAST); protected int $actionTableSize = #(YYLAST);
protected $gotoTableSize = #(YYGLAST); protected int $gotoTableSize = #(YYGLAST);
protected $invalidSymbol = #(YYBADCH); protected int $invalidSymbol = #(YYBADCH);
protected $errorSymbol = #(YYINTERRTOK); protected int $errorSymbol = #(YYINTERRTOK);
protected $defaultAction = #(YYDEFAULT); protected int $defaultAction = #(YYDEFAULT);
protected $unexpectedTokenRule = #(YYUNEXPECTED); protected int $unexpectedTokenRule = #(YYUNEXPECTED);
protected $YY2TBLSTATE = #(YY2TBLSTATE); protected int $YY2TBLSTATE = #(YY2TBLSTATE);
protected $numNonLeafStates = #(YYNLSTATES); protected int $numNonLeafStates = #(YYNLSTATES);
protected $symbolToName = array( protected array $symbolToName = array(
#listvar terminals #listvar terminals
); );
protected $tokenToSymbol = array( protected array $tokenToSymbol = array(
#listvar yytranslate #listvar yytranslate
); );
protected $action = array( protected array $action = array(
#listvar yyaction #listvar yyaction
); );
protected $actionCheck = array( protected array $actionCheck = array(
#listvar yycheck #listvar yycheck
); );
protected $actionBase = array( protected array $actionBase = array(
#listvar yybase #listvar yybase
); );
protected $actionDefault = array( protected array $actionDefault = array(
#listvar yydefault #listvar yydefault
); );
protected $goto = array( protected array $goto = array(
#listvar yygoto #listvar yygoto
); );
protected $gotoCheck = array( protected array $gotoCheck = array(
#listvar yygcheck #listvar yygcheck
); );
protected $gotoBase = array( protected array $gotoBase = array(
#listvar yygbase #listvar yygbase
); );
protected $gotoDefault = array( protected array $gotoDefault = array(
#listvar yygdefault #listvar yygdefault
); );
protected $ruleToNonTerminal = array( protected array $ruleToNonTerminal = array(
#listvar yylhs #listvar yylhs
); );
protected $ruleToLength = array( protected array $ruleToLength = array(
#listvar yylen #listvar yylen
); );
#if -t #if -t
protected $productions = array( protected array $productions = array(
#production-strings; #production-strings;
); );
#endif #endif

9
grammar/php.y
View File

@ -1152,8 +1152,8 @@ exit_expr:
backticks_expr: backticks_expr:
/* empty */ { $$ = array(); } /* empty */ { $$ = array(); }
| T_ENCAPSED_AND_WHITESPACE | T_ENCAPSED_AND_WHITESPACE
{ $$ = array(Node\InterpolatedStringPart[Scalar\String_::parseEscapeSequences($1, '`')]); } { $$ = array(Node\InterpolatedStringPart[Scalar\String_::parseEscapeSequences($1, '`', $this->phpVersion->supportsUnicodeEscapes())]); }
| encaps_list { parseEncapsed($1, '`', true); $$ = $1; } | encaps_list { parseEncapsed($1, '`', $this->phpVersion->supportsUnicodeEscapes()); $$ = $1; }
; ;
ctor_arguments: ctor_arguments:
@ -1196,10 +1196,11 @@ dereferencable_scalar:
$$ = new Expr\Array_($3, $attrs); $$ = new Expr\Array_($3, $attrs);
$this->createdArrays->attach($$); } $this->createdArrays->attach($$); }
| array_short_syntax { $$ = $1; $this->createdArrays->attach($$); } | array_short_syntax { $$ = $1; $this->createdArrays->attach($$); }
| T_CONSTANT_ENCAPSED_STRING { $$ = Scalar\String_::fromString($1, attributes()); } | T_CONSTANT_ENCAPSED_STRING
{ $$ = Scalar\String_::fromString($1, attributes(), $this->phpVersion->supportsUnicodeEscapes()); }
| '"' encaps_list '"' | '"' encaps_list '"'
{ $attrs = attributes(); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED; { $attrs = attributes(); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED;
parseEncapsed($2, '"', true); $$ = new Scalar\InterpolatedString($2, $attrs); } parseEncapsed($2, '"', $this->phpVersion->supportsUnicodeEscapes()); $$ = new Scalar\InterpolatedString($2, $attrs); }
; ;
scalar: scalar:

8
lib/PhpParser/Parser/Php7.php
View File

@ -2455,10 +2455,10 @@ class Php7 extends \PhpParser\ParserAbstract
$this->semValue = array(); $this->semValue = array();
}, },
511 => function ($stackPos) { 511 => function ($stackPos) {
$this->semValue = array(new Node\InterpolatedStringPart(Scalar\String_::parseEscapeSequences($this->semStack[$stackPos-(1-1)], '`'), $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]))); $this->semValue = array(new Node\InterpolatedStringPart(Scalar\String_::parseEscapeSequences($this->semStack[$stackPos-(1-1)], '`', $this->phpVersion->supportsUnicodeEscapes()), $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos])));
}, },
512 => function ($stackPos) { 512 => function ($stackPos) {
foreach ($this->semStack[$stackPos-(1-1)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '`', true); } }; $this->semValue = $this->semStack[$stackPos-(1-1)]; foreach ($this->semStack[$stackPos-(1-1)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '`', $this->phpVersion->supportsUnicodeEscapes()); } }; $this->semValue = $this->semStack[$stackPos-(1-1)];
}, },
513 => function ($stackPos) { 513 => function ($stackPos) {
$this->semValue = array(); $this->semValue = array();
@ -2513,11 +2513,11 @@ class Php7 extends \PhpParser\ParserAbstract
$this->semValue = $this->semStack[$stackPos-(1-1)]; $this->createdArrays->attach($this->semValue); $this->semValue = $this->semStack[$stackPos-(1-1)]; $this->createdArrays->attach($this->semValue);
}, },
530 => function ($stackPos) { 530 => function ($stackPos) {
$this->semValue = Scalar\String_::fromString($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos])); $this->semValue = Scalar\String_::fromString($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->supportsUnicodeEscapes());
}, },
531 => function ($stackPos) { 531 => function ($stackPos) {
$attrs = $this->getAttributes($this->tokenStartStack[$stackPos-(3-1)], $this->tokenEndStack[$stackPos]); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED; $attrs = $this->getAttributes($this->tokenStartStack[$stackPos-(3-1)], $this->tokenEndStack[$stackPos]); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED;
foreach ($this->semStack[$stackPos-(3-2)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '"', true); } }; $this->semValue = new Scalar\InterpolatedString($this->semStack[$stackPos-(3-2)], $attrs); foreach ($this->semStack[$stackPos-(3-2)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '"', $this->phpVersion->supportsUnicodeEscapes()); } }; $this->semValue = new Scalar\InterpolatedString($this->semStack[$stackPos-(3-2)], $attrs);
}, },
532 => function ($stackPos) { 532 => function ($stackPos) {
$this->semValue = $this->parseLNumber($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->allowsInvalidOctals()); $this->semValue = $this->parseLNumber($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->allowsInvalidOctals());

8
lib/PhpParser/Parser/Php8.php
View File

@ -2463,10 +2463,10 @@ class Php8 extends \PhpParser\ParserAbstract
$this->semValue = array(); $this->semValue = array();
}, },
511 => function ($stackPos) { 511 => function ($stackPos) {
$this->semValue = array(new Node\InterpolatedStringPart(Scalar\String_::parseEscapeSequences($this->semStack[$stackPos-(1-1)], '`'), $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]))); $this->semValue = array(new Node\InterpolatedStringPart(Scalar\String_::parseEscapeSequences($this->semStack[$stackPos-(1-1)], '`', $this->phpVersion->supportsUnicodeEscapes()), $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos])));
}, },
512 => function ($stackPos) { 512 => function ($stackPos) {
foreach ($this->semStack[$stackPos-(1-1)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '`', true); } }; $this->semValue = $this->semStack[$stackPos-(1-1)]; foreach ($this->semStack[$stackPos-(1-1)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '`', $this->phpVersion->supportsUnicodeEscapes()); } }; $this->semValue = $this->semStack[$stackPos-(1-1)];
}, },
513 => function ($stackPos) { 513 => function ($stackPos) {
$this->semValue = array(); $this->semValue = array();
@ -2521,11 +2521,11 @@ class Php8 extends \PhpParser\ParserAbstract
$this->semValue = $this->semStack[$stackPos-(1-1)]; $this->createdArrays->attach($this->semValue); $this->semValue = $this->semStack[$stackPos-(1-1)]; $this->createdArrays->attach($this->semValue);
}, },
530 => function ($stackPos) { 530 => function ($stackPos) {
$this->semValue = Scalar\String_::fromString($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos])); $this->semValue = Scalar\String_::fromString($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->supportsUnicodeEscapes());
}, },
531 => function ($stackPos) { 531 => function ($stackPos) {
$attrs = $this->getAttributes($this->tokenStartStack[$stackPos-(3-1)], $this->tokenEndStack[$stackPos]); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED; $attrs = $this->getAttributes($this->tokenStartStack[$stackPos-(3-1)], $this->tokenEndStack[$stackPos]); $attrs['kind'] = Scalar\String_::KIND_DOUBLE_QUOTED;
foreach ($this->semStack[$stackPos-(3-2)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '"', true); } }; $this->semValue = new Scalar\InterpolatedString($this->semStack[$stackPos-(3-2)], $attrs); foreach ($this->semStack[$stackPos-(3-2)] as $s) { if ($s instanceof Node\InterpolatedStringPart) { $s->value = Node\Scalar\String_::parseEscapeSequences($s->value, '"', $this->phpVersion->supportsUnicodeEscapes()); } }; $this->semValue = new Scalar\InterpolatedString($this->semStack[$stackPos-(3-2)], $attrs);
}, },
532 => function ($stackPos) { 532 => function ($stackPos) {
$this->semValue = $this->parseLNumber($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->allowsInvalidOctals()); $this->semValue = $this->parseLNumber($this->semStack[$stackPos-(1-1)], $this->getAttributes($this->tokenStartStack[$stackPos-(1-1)], $this->tokenEndStack[$stackPos]), $this->phpVersion->allowsInvalidOctals());

9
lib/PhpParser/PhpVersion.php
View File

@ -149,9 +149,16 @@ class PhpVersion {
} }
/** /**
* Whether this version support yield in expression context without parentheses. * Whether this version supports yield in expression context without parentheses.
*/ */
public function supportsYieldWithoutParentheses(): bool { public function supportsYieldWithoutParentheses(): bool {
return $this->id >= 70000; return $this->id >= 70000;
} }
/**
* Whether this version supports unicode escape sequences in strings.
*/
public function supportsUnicodeEscapes(): bool {
return $this->id >= 70000;
}
} }

63
test/code/parser/scalar/unicodeEscape.test
View File

@ -3,8 +3,8 @@ Unicode escape sequence
<?php <?php
"\u{0}"; "\u{0}";
"\u{114}"; "\u{114}$foo";
"\u{1F602}"; `\u{1F602}$bar`;
----- -----
array( array(
0: Stmt_Expression( 0: Stmt_Expression(
@ -13,13 +13,66 @@ array(
) )
) )
1: Stmt_Expression( 1: Stmt_Expression(
expr: Scalar_String( expr: Scalar_InterpolatedString(
value: Ĕ parts: array(
0: InterpolatedStringPart(
value: Ĕ
)
1: Expr_Variable(
name: foo
)
)
) )
) )
2: Stmt_Expression( 2: Stmt_Expression(
expr: Expr_ShellExec(
parts: array(
0: InterpolatedStringPart(
value: @@{"\xF0\x9F\x98\x82"}@@
)
1: Expr_Variable(
name: bar
)
)
)
)
)
-----
<?php
"\u{0}";
"\u{114}$foo";
`\u{1F602}$bar`;
-----
!!version=5.6
array(
0: Stmt_Expression(
expr: Scalar_String( expr: Scalar_String(
value: @@{"\xF0\x9F\x98\x82"}@@ value: \u{0}
)
)
1: Stmt_Expression(
expr: Scalar_InterpolatedString(
parts: array(
0: InterpolatedStringPart(
value: \u{114}
)
1: Expr_Variable(
name: foo
)
)
)
)
2: Stmt_Expression(
expr: Expr_ShellExec(
parts: array(
0: InterpolatedStringPart(
value: \u{1F602}
)
1: Expr_Variable(
name: bar
)
)
) )
) )
) )