정규표현식 치트시트

h.t  →  "hat", "hit", "hot"

\d  →  0-9
\w  →  a-z, A-Z, 0-9, _
\s  →  space, tab, newline

[aeiou]    →  any vowel
[0-9a-f]   →  hex digit
[A-Za-z]   →  any letter

[^0-9]     →  any non-digit
[^\s]      →  any non-whitespace

^Hello     →  starts with "Hello"
world$     →  ends with "world"
^exact$    →  matches only "exact"

cat|dog       →  "cat" or "dog"
(Mon|Fri)day  →  "Monday" or "Friday"

\.   →  literal dot
\$   →  literal dollar sign
\(   →  literal parenthesis
\\   →  literal backslash

colou*r  →  "color", "colour", "colouur"

\d+  →  "1", "42", "3000" (at least one digit)

https?://  →  "http://" or "https://"

\d{4}      →  exactly 4 digits ("2024")
\d{2,}     →  2 or more digits
\w{3,8}    →  3 to 8 word characters

Greedy:  <.+>   on "<b>bold</b>"  →  "<b>bold</b>"
Lazy:   <.+?>  on "<b>bold</b>"  →  "<b>"

\d++\.\d++  →  matches "3.14" without backtracking
(only supported in Java, PCRE — not JavaScript)

(\d{3})-(\d{4})
on "555-1234"  →  group 1: "555", group 2: "1234"

(?:https?|ftp)://
Groups the protocol but does not capture it

(?<year>\d{4})-(?<month>\d{2})-(?<day>\d{2})
match.groups.year  →  "2024"

(\w+)\s\1    →  "hello hello" (repeated word)
(['"]).*?\1  →  matches quoted strings

(cat|dog|bird) food  →  "cat food", "dog food", "bird food"

// Reformat date: MM/DD/YYYY → YYYY-MM-DD
str.replace(
  /(?<m>\d{2})\/(?<d>\d{2})\/(?<y>\d{4})/,
  '$<y>-$<m>-$<d>'
)

\d+(?= dollars)
"100 dollars"  →  matches "100"
"100 euros"    →  no match

\d+(?! dollars)
"100 euros"    →  matches "100"
"100 dollars"  →  no match on "100"

(?<=\$)\d+
"$50"   →  matches "50"
"€50"   →  no match

(?<!\d)px
"16px"   →  no match
"top px" →  matches "px"

// At least 8 chars, 1 upper, 1 lower, 1 digit
^(?=.*[A-Z])(?=.*[a-z])(?=.*\d).{8,}$

\d   →  [0-9]
\D   →  [^0-9]

\w   →  [A-Za-z0-9_]
\W   →  [^A-Za-z0-9_]

\s   →  [ \t\n\r\f\v]
\S   →  [^ \t\n\r\f\v]

\bcat\b    →  "cat" but not "catch" or "bobcat"
\Bcat\B    →  "concatenate" but not "cat"

[a-z]     →  lowercase letter
[A-Z]     →  uppercase letter
[0-9]     →  same as \d
[a-f0-9]  →  hex digit (lowercase)

\p{L}   →  any Unicode letter (한글, 日本語, etc.)
\p{N}   →  any Unicode number
\p{Sc}  →  currency symbols ($, €, ¥)

^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$

https?:\/\/[\w\-]+(\.[\w\-]+)+[\/\w\-._~:?#\[\]@!$&'()*+,;=]*

^\+?[1-9]\d{1,14}$

// US format
^\(?\d{3}\)?[-.\s]?\d{3}[-.\s]?\d{4}$

^((25[0-5]|2[0-4]\d|[01]?\d\d?)\.){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)$

^\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12]\d|3[01])$

^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[@$!%*?&])[A-Za-z\d@$!%*?&]{8,}$

^[a-z0-9]+(?:-[a-z0-9]+)*$

"my-cool-slug"  →  match
"My Slug!"      →  no match

<([a-z][a-z0-9]*)\[^>]*>(.*?)<\/\1>

"banana".match(/a/g)   →  ["a", "a", "a"]
"banana".match(/a/)    →  ["a"] (first only)

/hello/i.test("Hello")  →  true
/hello/.test("Hello")   →  false

const text = "line1\nline2"
/^line2$/m.test(text)  →  true
/^line2$/.test(text)   →  false

/a.b/s.test("a\nb")  →  true
/a.b/.test("a\nb")   →  false

/^\p{L}+$/u.test("café")  →  true
/^\p{L}+$/.test("café")   →  SyntaxError

const re = /\d+/y
re.lastIndex = 4
re.exec("abc 123")  →  "123"

const word = "hello"
const re = new RegExp(word, 'gi')
re.test("Hello World")  →  true

/^\d+$/.test("123")  →  true
/^\d+$/.test("abc")  →  false

"2024-01-15".match(/(\d{4})-(\d{2})-(\d{2})/)
→  ["2024-01-15", "2024", "01", "15"]

const text = "a1 b2 c3"
for (const m of text.matchAll(/([a-z])(\d)/g)) {
  console.log(m[1], m[2])
}
// a 1,  b 2,  c 3

"foo bar foo".replace(/foo/g, "baz")
→  "baz bar baz"

// With capture group
"John Smith".replace(/(\w+) (\w+)/, "$2, $1")
→  "Smith, John"

"one, two;  three".split(/[,;]\s*/)
→  ["one", "two", "three"]

"camelCase".split(/(?=[A-Z])/)
→  ["camel", "Case"]

"Hello World".search(/world/i)  →  6
"Hello World".search(/xyz/)     →  -1