climbing the abstract syntax tree (bulgaria php 2016)
TRANSCRIPT
@asgrim
Climbing theAbstract Syntax Tree
James TitcumbBulgaria PHP Conference 2016
Who is this guy?James Titcumb
www.jamestitcumb.com
www.roave.com
www.phphants.co.uk
www.phpsouthcoast.co.uk
@asgrim
@asgrim
How PHP works
PHP code
OpCacheExecute (VM)
Lexer + Parser
Compiler
@asgrim
The PHP Lexer
zend_language_scanner.l
@asgrim
zend_language_scanner.l<ST_IN_SCRIPTING>"exit" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"die" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"function" {
RETURN_TOKEN(T_FUNCTION);
}
@asgrim
zend_language_scanner.l<ST_IN_SCRIPTING>"exit" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"die" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"function" {
RETURN_TOKEN(T_FUNCTION);
}
@asgrim
zend_language_scanner.l<ST_IN_SCRIPTING>"exit" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"die" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"function" {
RETURN_TOKEN(T_FUNCTION);
}
@asgrim
zend_language_scanner.l<ST_IN_SCRIPTING>"exit" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"die" {
RETURN_TOKEN(T_EXIT);
}
<ST_IN_SCRIPTING>"function" {
RETURN_TOKEN(T_FUNCTION);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
zend_language_scanner.l<ST_DOUBLE_QUOTES,ST_BACKQUOTE,ST_HEREDOC>"${" {
yy_push_state(ST_LOOKING_FOR_VARNAME);
RETURN_TOKEN(T_DOLLAR_OPEN_CURLY_BRACES);
}
<ST_LOOKING_FOR_VARNAME>{LABEL}[[}] {
yyless(yyleng - 1);
zend_copy_value(zendlval, yytext, yyleng);
yy_pop_state();
yy_push_state(ST_IN_SCRIPTING);
RETURN_TOKEN(T_STRING_VARNAME);
}
@asgrim
The PHP Lexer
zend_language_scanner.l
@asgrim
The PHP Lexer
zend_language_scanner.l
re2c
@asgrim
The PHP Lexer
zend_language_scanner.l
re2c
zend_language_scanner.c
@asgrim
The PHP Parser
zend_language_parser.y
@asgrim
zend_language_parser.yif_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
zend_language_parser.y
@asgrim
if ($a == 1)
{
a();
}
else if ($b == 1)
{
b();
}
else
{
c();
}
Using the rules to parse
@asgrim
if ($a == 1)
{
a();
}
else if ($b == 1)
{
b();
}
else
{
c();
}
Using the rules to parse
if_stmt_without_else (A)
@asgrim
if ($a == 1)
{
a();
}
else if ($b == 1)
{
b();
}
else
{
c();
}
Using the rules to parse
if_stmt_without_else (A)
if_stmt_without_else (B)
@asgrim
if ($a == 1)
{
a();
}
else if ($b == 1)
{
b();
}
else
{
c();
}
Using the rules to parse
if_stmt_without_else (A)
if_stmt_without_else (B)
if_stmt
@asgrim
Zend_language_parser.y (PHP 7.0.10)if_stmt:
if_stmt_without_else %prec T_NOELSE { $$ = $1; }
| if_stmt_without_else T_ELSE statement
{ $$ = zend_ast_list_add($1, zend_ast_create(ZEND_AST_IF_ELEM, NULL, $3)); }
;
if_stmt_without_else:
T_IF '(' expr ')' statement
{ $$ = zend_ast_create_list(1, ZEND_AST_IF,
zend_ast_create(ZEND_AST_IF_ELEM, $3, $5)); }
| if_stmt_without_else T_ELSEIF '(' expr ')' statement
{ $$ = zend_ast_list_add($1,
zend_ast_create(ZEND_AST_IF_ELEM, $4, $6)); }
;
@asgrim
zend_language_parser.y (PHP 5.6.26)T_IF parenthesis_expr { zend_do_if_cond(&$2, &$1 TSRMLS_CC); }
statement { zend_do_if_after_statement(&$1, 1 TSRMLS_CC); }
void zend_do_if_cond(const znode *cond, znode *closing_bracket_token TSRMLS_DC)
{
int if_cond_op_number = get_next_op_number(CG(active_op_array));
zend_op *opline = get_next_op(CG(active_op_array) TSRMLS_CC);
opline->opcode = ZEND_JMPZ;
SET_NODE(opline->op1, cond);
closing_bracket_token->u.op.opline_num = if_cond_op_number;
SET_UNUSED(opline->op2);
INC_BPC(CG(active_op_array));
}
@asgrim
AST is new in PHP 7+
@asgrim
How PHP works
PHP code
OpCacheExecute (VM)
Lexer + Parser
Compiler
@asgrim
Let’s simplify!
@asgrim
First… WTF is AST?
@asgrim
AST is just a data structure
@asgrim
PHP code
<?php
echo "Hello world";
@asgrim
An AST representation
Echo statement
`-- String, value "Hello world"
@asgrim
PHP code
<?php
echo "Hello " . "world";
@asgrim
An AST representation
Echo statement
`-- Concat
|-- Left
| `-- String, value "Hello "
`-- Right
`-- String, value "world"
@asgrim
PHP code
<?php
$a = 5;
$b = 3;
echo $a + ($b * 2);
@asgrim
An AST representationAssign statement
|-- Variable $a
`-- Integer, value 5
Assign statement
|-- Variable $b
`-- Integer, value 3
Echo statement
`-- Add operation
|-- Left
| `-- Variable $a
`-- Right
`-- Multiply operation
|-- Left
| `-- Variable $b
`-- Right
`-- Integer, value 2
@asgrim
AST compilationStatements
EchoAssign
Scalarvalue: (int)5
Variablename: $a
Assign
Scalarvalue: (int)3
Variablename: $b Add op
Right operandLeft operand
Variablename: $a
Multiply op
Right operandLeft operand
Variablename: $b
Scalarvalue: (int)2
@asgrim
AST compilation: pre-order traversalStatements
EchoAssign
Scalarvalue: (int)5
Variablename: $a
Assign
Scalarvalue: (int)3
Variablename: $b Add op
Right operandLeft operand
Variablename: $a
Multiply op
Right operandLeft operand
Variablename: $b
Scalarvalue: (int)2
@asgrim
Pre-order traversal: Polish notationAssign(Variable $a, Scalar 5)
Assign(Variable $b, Scalar 3)
Echo (
Add(
Variable $a,
Multiply( $b, 2 )
)
)
@asgrim
Order of precedence
1 + 2 * 3
= 1 + (2 * 3) = 7?
= (1 + 2) * 3 = 9?
@asgrim
Order of precedence
1 + 2 * 3
= 1 + (2 * 3) = 7?
= (1 + 2) * 3 = 9?
+ 1 * 2 3
@asgrim
Order of precedence
1 + 2 * 3
= 1 + (2 * 3) = 7?
= (1 + 2) * 3 = 9?
+ 1 * 2 3
Operator Left operand Right operand
@asgrim
Order of precedence
1 + 2 * 3
= 1 + (2 * 3) = 7?
= (1 + 2) * 3 = 9?
+ 1 * 2 3
Operator Left operand Right operand
Operator Left operand Right operand
@asgrim
Reverse Polish Notation
1 2 3 * +
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
2
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
2
3
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
2
3
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
2
3
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
6
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
1
6
@asgrim
Reverse Polish Notation
1 2 3 * + The stack
7
@asgrim
Let’s write a compiler (!!!)In three easy steps…
@asgrim
Warning: do not use in production
@asgrim
View > Sourcehttps://github.com/asgrim/basic-maths-compiler
@asgrim
Define the languageTokens
● T_ADD (+)
● T_SUBTRACT (-)
● T_MULTIPLY (/)
● T_DIVIDE (*)
● T_INTEGER (\d)
● T_WHITESPACE (\s+)
@asgrim
Step 1: Writing a simple lexer
@asgrim
Using regular expressionsprivate static $matches = [
'/^(\+)/' => Token::T_ADD,
'/^(-)/' => Token::T_SUBTRACT,
'/^(\*)/' => Token::T_MULTIPLY,
'/^(\/)/' => Token::T_DIVIDE,
'/^(\d+)/' => Token::T_INTEGER,
'/^(\s+)/' => Token::T_WHITESPACE,
];
@asgrim
Step through the input stringpublic function __invoke(string $input) : array
{
$tokens = [];
$offset = 0;
while ($offset < strlen($input)) {
$focus = substr($input, $offset);
$result = $this->match($focus);
$tokens[] = $result;
$offset += strlen($result->getLexeme());
}
return $tokens;
}
@asgrim
The matching methodprivate function match(string $input) : Token
{
foreach (self::$matches as $pattern => $token) {
if (preg_match($pattern, $input, $matches)) {
return new Token($token, $matches[1]);
}
}
throw new \RuntimeException(sprintf(
'Unmatched token, next 15 chars were: %s', substr($input, 0, 15)
));
}
@asgrim
Step 2: Parsing the tokens
@asgrim
Order tokens by operator precedence/**
* Higher number is higher precedence.
* @var int[]
*/
private static $operatorPrecedence = [
Token::T_SUBTRACT => 0,
Token::T_ADD => 1,
Token::T_DIVIDE => 2,
Token::T_MULTIPLY => 3,
];
@asgrim
Order tokens by operator precedence/** @var Token[] $stack */
$stack = [];
/** @var Token[] $operators */
$operators = [];
while (false !== ($token = current($tokens))) {
if ($token->isOperator()) {
// ...
}
$stack[] = $token;
next($tokens);
}
@asgrim
Order tokens by operator precedence/** @var Token[] $stack */
$stack = [];
/** @var Token[] $operators */
$operators = [];
while (false !== ($token = current($tokens))) {
if ($token->isOperator()) {
// ...
}
$stack[] = $token;
next($tokens);
}
@asgrim
Order tokens by operator precedence/** @var Token[] $stack */
$stack = [];
/** @var Token[] $operators */
$operators = [];
while (false !== ($token = current($tokens))) {
if ($token->isOperator()) {
// ...
}
$stack[] = $token;
next($tokens);
}
@asgrim
Order tokens by operator precedence/** @var Token[] $stack */
$stack = [];
/** @var Token[] $operators */
$operators = [];
while (false !== ($token = current($tokens))) {
if ($token->isOperator()) {
// ...
}
$stack[] = $token;
next($tokens);
}
@asgrim
Order tokens by operator precedenceif ($token->isOperator()) {
$tokenPrecedence = self::$operatorPrecedence[$token->getToken()];
while (
count($operators)
&& self::$operatorPrecedence[$operators[count($operators) - 1]->getToken()]
> $tokenPrecedence
) {
$higherOp = array_pop($operators);
$stack[] = $higherOp;
}
$operators[] = $token;
next($tokens);
continue;
}
@asgrim
Order tokens by operator precedenceif ($token->isOperator()) {
$tokenPrecedence = self::$operatorPrecedence[$token->getToken()];
while (
count($operators)
&& self::$operatorPrecedence[$operators[count($operators) - 1]->getToken()]
> $tokenPrecedence
) {
$higherOp = array_pop($operators);
$stack[] = $higherOp;
}
$operators[] = $token;
next($tokens);
continue;
}
@asgrim
Order tokens by operator precedenceif ($token->isOperator()) {
$tokenPrecedence = self::$operatorPrecedence[$token->getToken()];
while (
count($operators)
&& self::$operatorPrecedence[$operators[count($operators) - 1]->getToken()]
> $tokenPrecedence
) {
$higherOp = array_pop($operators);
$stack[] = $higherOp;
}
$operators[] = $token;
next($tokens);
continue;
}
@asgrim
Order tokens by operator precedenceif ($token->isOperator()) {
$tokenPrecedence = self::$operatorPrecedence[$token->getToken()];
while (
count($operators)
&& self::$operatorPrecedence[$operators[count($operators) - 1]->getToken()]
> $tokenPrecedence
) {
$higherOp = array_pop($operators);
$stack[] = $higherOp;
}
$operators[] = $token;
next($tokens);
continue;
}
@asgrim
Order tokens by operator precedence// Clean up by moving any remaining operators onto the token stack
while (count($operators)) {
$stack[] = array_pop($operators);
}
return $stack;
@asgrim
Order tokens by operator precedence
1 + 2 * 3
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1
+
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1 2
+
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1 2
+ *
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1 2 3
+ *
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1 2 3 *
+ *
Output stack
Operator stack
@asgrim
Order tokens by operator precedence
1 + 2 * 3
1 2 3 * +
+
Output stack
Operator stack
@asgrim
Create ASTwhile ($ip < count($tokenStack)) {
$token = $tokenStack[$ip++];
if ($token->isOperator()) {
// (figure out $nodeType)
$right = array_pop($astStack);
$left = array_pop($astStack);
$astStack[] = new $nodeType($left, $right);
continue;
}
$astStack[] = new Node\Scalar\IntegerValue((int)$token->getLexeme());
}
@asgrim
Create ASTwhile ($ip < count($tokenStack)) {
$token = $tokenStack[$ip++];
if ($token->isOperator()) {
// (figure out $nodeType)
$right = array_pop($astStack);
$left = array_pop($astStack);
$astStack[] = new $nodeType($left, $right);
continue;
}
$astStack[] = new Node\Scalar\IntegerValue((int)$token->getLexeme());
}
@asgrim
Create ASTwhile ($ip < count($tokenStack)) {
$token = $tokenStack[$ip++];
if ($token->isOperator()) {
// (figure out $nodeType)
$right = array_pop($astStack);
$left = array_pop($astStack);
$astStack[] = new $nodeType($left, $right);
continue;
}
$astStack[] = new Node\Scalar\IntegerValue((int)$token->getLexeme());
}
@asgrim
Create ASTwhile ($ip < count($tokenStack)) {
$token = $tokenStack[$ip++];
if ($token->isOperator()) {
// (figure out $nodeType)
$right = array_pop($astStack);
$left = array_pop($astStack);
$astStack[] = new $nodeType($left, $right);
continue;
}
$astStack[] = new Node\Scalar\IntegerValue((int)$token->getLexeme());
}
@asgrim
Create AST
Node\BinaryOp\Add (
Node\Scalar\IntegerValue(1),
Node\BinaryOp\Multiply (
Node\Scalar\IntegerValue(2),
Node\Scalar\IntegerValue(3)
)
)
@asgrim
Step 3: Executing the AST
@asgrim
Compile & execute ASTprivate function compileNode(NodeInterface $node)
{
if ($node instanceof Node\BinaryOp\AbstractBinaryOp) {
return $this->compileBinaryOp($node);
}
if ($node instanceof Node\Scalar\IntegerValue) {
return $node->getValue();
}
}
@asgrim
Compile & execute ASTprivate function compileBinaryOp(Node\BinaryOp\AbstractBinaryOp $node)
{
$left = $this->compileNode($node->getLeft());
$right = $this->compileNode($node->getRight());
switch (get_class($node)) {
case Node\BinaryOp\Add::class:
return $left + $right;
case Node\BinaryOp\Subtract::class:
return $left - $right;
case Node\BinaryOp\Multiply::class:
return $left * $right;
case Node\BinaryOp\Divide::class:
return $left / $right;
}
}
@asgrim
AST in userland
@asgrim
php-ast extensionhttps://github.com/nikic/php-ast
@asgrim
php-ast example usage<?php
require 'path/to/util.php';
$code = <<<'EOC'
<?php
$var = 42;
EOC;
echo ast_dump(ast\parse_code($code, $version=35)), "\n";
// Output:
AST_STMT_LIST
0: AST_ASSIGN
var: AST_VAR
name: "var"
expr: 42
@asgrim
astkithttps://github.com/sgolemon/astkit
@asgrim
astkit example usage$if = AstKit::parseString(<<<EOD
if (true) {
echo "This is a triumph.\n";
} else {
echo "The cake is a lie.\n";
}
EOD
);
$if->execute(); // First run, program is as-seen above
$const = $if->getChild(0)->getChild(0);
// Replace the "true" constant in the condition with false
$const->graft(0, false);
// Can also graft other AstKit nodes, instead of constants
$if->execute(); // Second run now takes the else path
@asgrim
PhpParserhttps://github.com/nikic/PHP-Parser
@asgrim
PHP Parser<?php
use PhpParser\ParserFactory;
$parser = (new ParserFactory)
->create(ParserFactory::PREFER_PHP7);
print_r($parser->parse(
file_get_contents('ast-demo-src.php')
));
@asgrim
Better Reflectionhttps://github.com/Roave/BetterReflection
@asgrim
Better Reflection workflow
Reflector
Source Locator
PhpParser
Reflection
@asgrim
PHP Reflection$reflection = new ReflectionClass(
\My\ExampleClass::class
);
$this->assertSame(
'ExampleClass',
$reflection->getShortName()
);
@asgrim
Better Reflection$reflection = ReflectionClass::createFromName(
\My\ExampleClass::class
);
$this->assertSame(
'ExampleClass',
$reflection->getShortName()
);
@asgrim
ReflectionClass::createFromName()// In ReflectionClass :
public static function createFromName($className)
{
return ClassReflector::buildDefaultReflector()->reflect($className);
}
@asgrim
ClassReflector::buildDefaultReflector()// In ClassReflector :
public static function buildDefaultReflector()
{
return new self(new AggregateSourceLocator([
new PhpInternalSourceLocator(),
new EvaledCodeSourceLocator(),
new AutoloadSourceLocator(),
]));
}
@asgrim
Given a class structure...<?php
class Foo
{
private $bar;
public function thing()
{
}
}
@asgrim
… we get the AST!Class, name Foo
|-- Statements
| |-- Property, name bar
| | |-- Type [private]
| | `-- Attributes [start line: 7, end line: 9]
| `-- Method, name thing
| |-- Type [public]
| |-- Parameters [...]
| |-- Statements [...]
| `-- Attributes [start line: 7, end line: 9]
`-- Attributes [start line: 3, end line: 10]
Any questions?
https://joind.in/talk/513ad
James Titcumb @asgrim