😫 🦓 🤚🏿 Cara meningkatkan keterbacaan ekspresi reguler di PHP 🙍🏽 👵 👩🏻

Ekspresi reguler adalah alat yang sangat kuat, tetapi kebijaksanaan konvensional adalah bahwa sekali ditulis, mereka sangat sulit untuk dipahami, jadi mempertahankannya bukanlah pengalaman yang menyenangkan. Dikumpulkan di sini adalah tips untuk membantu membuat mereka lebih mudah dibaca.

PHP PCRE — PHP 7.3, PCRE2 — . PHP , , . PHP , ctype*, URL-, — . IDE , , , .

, , . . , - PHP ( PHP 7.3). , . , PHP, JavaScript , ES2018.

-;
;
;
;
;
.

-

— . -, — . :

/(foo|bar)/i

(foo|bar)

— , i

— , , /

— . /

, . , ~, !, @, #, $

. , , \

— . : {}, (), [], <>

, . , , , . - , . , , . (, ^, $,

, ), . , , , . , /

, — , , URL-. :

preg_match('/^https:\/\/example.com\/path/i', $uri);

“#”, , :

preg_match('#^https://example.com/path#i', $uri);

- . . , .

, *

, +

, $

. , /Username: @[a-z\.0-9]/

“.” , .

, , . , -

. , , , , .

, /[A-Z]/

, A Z. (/[A\-Z]/)

, — , A, Z . , , , . , /[AZ-]/

, /[A\-Z]/

, .

( , ), . , :

/Price: [0-9\-\$\.\+]+/

/Price: [0-9$.+-]+/

X

, , , . , , , , . — :

preg_match('/x\yz/X', ''); //  "y" — ,   —

Warning: preg_match(): Compilation failed: unrecognized character follows \ at offset 2 in ... on line ...

, ()

, , , , , , .

, “Price: €24

”.

$pattern = '/Price: (£|€)(\d+)/';
$text    = 'Price: €24';
preg_match($pattern, $text, $matches);

2 , , ((£|€))

, — . , $matches

, , :

var_dump($matches);

array(3) {
  [0]=> string(12) "Price: €24"
  [1]=> string(3) "€"
  [2]=> string(2) "24"
}

, . , , ?:

. , , . , , (£|€)

, , : (?:£|€)

.

$pattern = '/Price: (?:£|€)(\d+)/';
$text    = 'Price: €24';
preg_match($pattern, $text, $matches);
var_dump($matches);

$matches

1 — :

array(2) {
  [0]=> string(12) "Price: €24"
  [1]=> string(2) "24"
}

, , , , , .

, . , , ,

, , :

/Price: (?<currency>£|€)(?<price>\d+)/

, (?

, , . , (?<currency>£|€)

— currency, (?<price>\d+)

— price. , , — . , :

$pattern = '/Price: (?<currency>£|€)(?<price>\d+)/';
$text    = 'Price: €24';
preg_match($pattern, $text, $matches);
var_dump($matches);

array(5) {
 [0]=> string(12) "Price: €24"
["currency"]=> string(3) "€"
[1]=> string(3) "€"
["price"]=> string(2) "24"
[2]=> string(2) "24"
}

, $matches

, , .

, , ["currency"]=> "€"

, [1]=> "€"

.

PHP , :

Warning: preg_match(): Compilation failed: two named subpatterns have the same name (PCRE2_DUPNAMES not set) at offset ... in ... on line ....

, J

(UPD: , PHP 7.2.0, ?J

):

/Price: (?<currency>£|€)?(?<price>\d+)(?<currency>£|€)?/J

2 currency, , J

. , currency , . , , :

$pattern = '/Price: (?<currency>£|€)?(?<price>\d+)(?<currency>£|€)?/J';
$text    = 'Price: €24£';
preg_match($pattern, $text, $matches);
var_dump($matches);

array(6) {
  [0]=> string(14) "Price: €24£"
  ["currency"]=> string(2) "£"
  [1]=> string(3) "€"
  ["price"]=> string(2) "24"
  [2]=> string(2) "24"
  [3]=> string(2) "£"
}

, . , , PHP-, , . — . .

, :

$pattern  = '/Price: (?<currency>£|€)(?<price>\d+)/i';

$pattern  = '/Price: ';
$pattern .= '(?<currency>£|€)'; // Capture currency symbols £ or €
$pattern .= '(?<price>\d+)'; // Capture price without decimals.
$pattern .= '/i'; // Flags: Case-insensitive

. x

, , . , . :

/Price: (?<currency>£|€)(?<price>\d+)/i

/Price:  \s  (?<currency>£|€)  (?<price>\d+)  /ix

, , x

. , , , . , , \s

.

x

, #

, PHP . , . , :

/Price: (?<currency>£|€)(?<price>\d+)/i

/Price:           # Check for the label "Price:"
\s                # Ensure a white-space after.
(?<currency>£|€)  # Capture currency symbols £ or €
(?<price>\d+)     # Capture price without decimals.
/ix

PHP, Heredoc Nowdoc . , :

$pattern = <<<PATTERN
  /Price:           # Check for the label "Price:"
  \s                # Ensure a white-space after.
  (?<currency>£|€)  # Capture currency symbols £ or €
  (?<price>\d+)     # Capture price without decimals.
  /ix               # Flags: Case-insensitive
PATTERN;

preg_match($pattern, 'Price: £42', $matches);

, , , . , — \d

, , [0-9]

. \D

, — , [^0-9]

. , , , , , :

/Number: [0-9][^0-9]/

/Number: \d\D/

, . :

\w

— , , [A-Za-z0-9_]

,

/[A-Za-z0-9_]/

/\w/

[:xdigit:]

— , [A-Fa-f0-9]

,

/[a-zA-F0-9]/

/[[:xdigit:]]/

\s

— , [ \t\r\n\v\f]

,

/ \t\r\n\v\f/

/\s/

/u

, , . \p{_}

, _

— . \p

"p" , \P{FOO}

, — , . , , , \p{Sc}

, , , , , . , : \p{Currency_Symbol}

, PHP.

$pattern = '/Price: \p{Sc}\d+/u';

$text = 'Price: ¥42';

, . , , , . , . , \p{Sinhala}

, \x{0D80}-\x{0DFF

}. , :

$pattern = '/[\x{0D80}-\x{0DFF}]/u';

, :

$pattern = '/\p{Sinhala}/u';

$text = 'පීඑච්පී.වොච්`;
$contains_sinhala = preg_match($pattern, $text);

, , , !

P.S. — - . , .

Cara meningkatkan keterbacaan ekspresi reguler di PHP

-

More articles: