regexp/syntax

.              any character, possibly including newline (flag s=true)
[xyz]          character class
[^xyz]         negated character class
\d             Perl character class
\D             negated Perl character class
[[:alpha:]]    ASCII character class
[[:^alpha:]]   negated ASCII character class
\pN            Unicode character class (one-letter name)
\p{Greek}      Unicode character class
\PN            negated Unicode character class (one-letter name)
\P{Greek}      negated Unicode character class

xy             x followed by y
x|y            x or y (prefer x)

x*             zero or more x, prefer more
x+             one or more x, prefer more
x?             zero or one x, prefer one
x{n,m}         n or n+1 or ... or m x, prefer more
x{n,}          n or more x, prefer more
x{n}           exactly n x
x*?            zero or more x, prefer fewer
x+?            one or more x, prefer fewer
x??            zero or one x, prefer zero
x{n,m}?        n or n+1 or ... or m x, prefer fewer
x{n,}?         n or more x, prefer fewer
x{n}?          exactly n x

(re)           numbered capturing group (submatch)
(?P<name>re)   named & numbered capturing group (submatch)
(?:re)         non-capturing group
(?flags)       set flags within current group; non-capturing
(?flags:re)    set flags during re; non-capturing

Flag syntax is xyz (set) or -xyz (clear) or xy-z (set xy, clear z). The flags are:

i              case-insensitive (default false)
m              multi-line mode: ^ and $ match begin/end line in addition to begin/end text (default false)
s              let . match \n (default false)
U              ungreedy: swap meaning of x* and x*?, x+ and x+?, etc (default false)

^              at beginning of text or line (flag m=true)
$              at end of text (like \z not Perl's \Z) or line (flag m=true)
\A             at beginning of text
\b             at ASCII word boundary (\w on one side and \W, \A, or \z on the other)
\B             not at ASCII word boundary
\z             at end of text

\a             bell (== \007)
\f             form feed (== \014)
\t             horizontal tab (== \011)
\n             newline (== \012)
\r             carriage return (== \015)
\v             vertical tab character (== \013)
\*             literal *, for any punctuation character *
\123           octal character code (up to three digits)
\x7F           hex character code (exactly two digits)
\x{10FFFF}     hex character code
\Q...\E        literal text ... even if ... has punctuation

x              single character
A-Z            character range (inclusive)
\d             Perl character class
[:foo:]        ASCII character class foo
\p{Foo}        Unicode character class Foo
\pF            Unicode character class F (one-letter name)

[\d]           digits (== \d)
[^\d]          not digits (== \D)
[\D]           not digits (== \D)
[^\D]          not not digits (== \d)
[[:name:]]     named ASCII class inside character class (== [:name:])
[^[:name:]]    named ASCII class inside negated character class (== [:^name:])
[\p{Name}]     named Unicode property inside character class (== \p{Name})
[^\p{Name}]    named Unicode property inside negated character class (== \P{Name})

\d             digits (== [0-9])
\D             not digits (== [^0-9])
\s             whitespace (== [\t\n\f\r ])
\S             not whitespace (== [^\t\n\f\r ])
\w             word characters (== [0-9A-Za-z_])
\W             not word characters (== [^0-9A-Za-z_])

[[:alnum:]]    alphanumeric (== [0-9A-Za-z])
[[:alpha:]]    alphabetic (== [A-Za-z])
[[:ascii:]]    ASCII (== [\x00-\x7F])
[[:blank:]]    blank (== [\t ])
[[:cntrl:]]    control (== [\x00-\x1F\x7F])
[[:digit:]]    digits (== [0-9])
[[:graph:]]    graphical (== [!-~] == [A-Za-z0-9!"#$%&'()*+,\-./:;<=>?@[\\\]^_`{|}~])
[[:lower:]]    lower case (== [a-z])
[[:print:]]    printable (== [ -~] == [ [:graph:]])
[[:punct:]]    punctuation (== [!-/:-@[-`{-~])
[[:space:]]    whitespace (== [\t\n\v\f\r ])
[[:upper:]]    upper case (== [A-Z])
[[:word:]]     word characters (== [0-9A-Za-z_])
[[:xdigit:]]   hex digit (== [0-9A-Fa-f])

func IsWordChar(r rune) bool

type EmptyOp uint8

const (
        EmptyBeginLine EmptyOp = 1 << iota
        EmptyEndLine
        EmptyBeginText
        EmptyEndText
        EmptyWordBoundary
        EmptyNoWordBoundary
)

func EmptyOpContext(r1, r2 rune) EmptyOp

type Error struct {
        Code ErrorCode
        Expr string
}

func (e *Error) Error() string

type ErrorCode string

const (
        // Unexpected error
        ErrInternalError ErrorCode = "regexp/syntax: internal error"

        // Parse errors
        ErrInvalidCharClass      ErrorCode = "invalid character class"
        ErrInvalidCharRange      ErrorCode = "invalid character class range"
        ErrInvalidEscape         ErrorCode = "invalid escape sequence"
        ErrInvalidNamedCapture   ErrorCode = "invalid named capture"
        ErrInvalidPerlOp         ErrorCode = "invalid or unsupported Perl syntax"
        ErrInvalidRepeatOp       ErrorCode = "invalid nested repetition operator"
        ErrInvalidRepeatSize     ErrorCode = "invalid repeat count"
        ErrInvalidUTF8           ErrorCode = "invalid UTF-8"
        ErrMissingBracket        ErrorCode = "missing closing ]"
        ErrMissingParen          ErrorCode = "missing closing )"
        ErrMissingRepeatArgument ErrorCode = "missing argument to repetition operator"
        ErrTrailingBackslash     ErrorCode = "trailing backslash at end of expression"
        ErrUnexpectedParen       ErrorCode = "unexpected )"
)

func (e ErrorCode) String() string

type Flags uint16

const (
        FoldCase      Flags = 1 << iota // case-insensitive match
        Literal                         // treat pattern as literal string
        ClassNL                         // allow character classes like [^a-z] and [[:space:]] to match newline
        DotNL                           // allow . to match newline
        OneLine                         // treat ^ and $ as only matching at beginning and end of text
        NonGreedy                       // make repetition operators default to non-greedy
        PerlX                           // allow Perl extensions
        UnicodeGroups                   // allow \p{Han}, \P{Han} for Unicode group and negation
        WasDollar                       // regexp OpEndText was $, not \z
        Simple                          // regexp contains no counted repetition

        MatchNL = ClassNL | DotNL

        Perl        = ClassNL | OneLine | PerlX | UnicodeGroups // as close to Perl as possible
        POSIX Flags = 0                                         // POSIX syntax
)

type Inst struct {
        Op   InstOp
        Out  uint32 // all but InstMatch, InstFail
        Arg  uint32 // InstAlt, InstAltMatch, InstCapture, InstEmptyWidth
        Rune []rune
}

func (i *Inst) MatchEmptyWidth(before rune, after rune) bool

func (i *Inst) MatchRune(r rune) bool

func (i *Inst) MatchRunePos(r rune) int

func (i *Inst) String() string

type InstOp uint8

const (
        InstAlt InstOp = iota
        InstAltMatch
        InstCapture
        InstEmptyWidth
        InstMatch
        InstFail
        InstNop
        InstRune
        InstRune1
        InstRuneAny
        InstRuneAnyNotNL
)

func (i InstOp) String() string

type Op uint8

const (
        OpNoMatch        Op = 1 + iota // matches no strings
        OpEmptyMatch                   // matches empty string
        OpLiteral                      // matches Runes sequence
        OpCharClass                    // matches Runes interpreted as range pair list
        OpAnyCharNotNL                 // matches any character except newline
        OpAnyChar                      // matches any character
        OpBeginLine                    // matches empty string at beginning of line
        OpEndLine                      // matches empty string at end of line
        OpBeginText                    // matches empty string at beginning of text
        OpEndText                      // matches empty string at end of text
        OpWordBoundary                 // matches word boundary `\b`
        OpNoWordBoundary               // matches word non-boundary `\B`
        OpCapture                      // capturing subexpression with index Cap, optional name Name
        OpStar                         // matches Sub[0] zero or more times
        OpPlus                         // matches Sub[0] one or more times
        OpQuest                        // matches Sub[0] zero or one times
        OpRepeat                       // matches Sub[0] at least Min times, at most Max (Max == -1 is no limit)
        OpConcat                       // matches concatenation of Subs
        OpAlternate                    // matches alternation of Subs
)

type Prog struct {
        Inst   []Inst
        Start  int // index of start instruction
        NumCap int // number of InstCapture insts in re
}

func Compile(re *Regexp) (*Prog, error)

func (p *Prog) Prefix() (prefix string, complete bool)

func (p *Prog) StartCond() EmptyOp

func (p *Prog) String() string

type Regexp struct {
        Op       Op // operator
        Flags    Flags
        Sub      []*Regexp  // subexpressions, if any
        Sub0     [1]*Regexp // storage for short Sub
        Rune     []rune     // matched runes, for OpLiteral, OpCharClass
        Rune0    [2]rune    // storage for short Rune
        Min, Max int        // min, max for OpRepeat
        Cap      int        // capturing index, for OpCapture
        Name     string     // capturing name, for OpCapture
}

func Parse(s string, flags Flags) (*Regexp, error)

func (re *Regexp) CapNames() []string

func (x *Regexp) Equal(y *Regexp) bool

func (re *Regexp) MaxCap() int

func (re *Regexp) Simplify() *Regexp

func (re *Regexp) String() string