ActiveGo 1.8Package syntax
Overview ▹
Index ▹
func IsWordChar ¶
func IsWordChar(r rune) bool
IsWordChar reports whether r is consider a “word character” during the evaluation of the \b and \B zero-width assertions. These assertions are ASCII-only: the word characters are [A-Za-z0-9_].
type EmptyOp ¶
An EmptyOp specifies a kind or mixture of zero-width assertions.
type EmptyOp uint8
const (
EmptyBeginLine EmptyOp = 1 << iota
EmptyEndLine
EmptyBeginText
EmptyEndText
EmptyWordBoundary
EmptyNoWordBoundary
)
func EmptyOpContext ¶
func EmptyOpContext(r1, r2 rune) EmptyOp
EmptyOpContext returns the zero-width assertions satisfied at the position between the runes r1 and r2. Passing r1 == -1 indicates that the position is at the beginning of the text. Passing r2 == -1 indicates that the position is at the end of the text.
type Error ¶
An Error describes a failure to parse a regular expression and gives the offending expression.
type Error struct {
Code ErrorCode
Expr string
}
func (*Error) Error ¶
func (e *Error) Error() string
type ErrorCode ¶
An ErrorCode describes a failure to parse a regular expression.
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 (ErrorCode) String ¶
func (e ErrorCode) String() string
type Flags ¶
Flags control the behavior of the parser and record information about regexp context.
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 ¶
An Inst is a single instruction in a regular expression program.
type Inst struct {
Op InstOp
Out uint32 // all but InstMatch, InstFail
Arg uint32 // InstAlt, InstAltMatch, InstCapture, InstEmptyWidth
Rune []rune
}
func (*Inst) MatchEmptyWidth ¶
func (i *Inst) MatchEmptyWidth(before rune, after rune) bool
MatchEmptyWidth reports whether the instruction matches an empty string between the runes before and after. It should only be called when i.Op == InstEmptyWidth.
func (*Inst) MatchRune ¶
func (i *Inst) MatchRune(r rune) bool
MatchRune reports whether the instruction matches (and consumes) r. It should only be called when i.Op == InstRune.
func (*Inst) MatchRunePos ¶
func (i *Inst) MatchRunePos(r rune) int
MatchRunePos checks whether the instruction matches (and consumes) r. If so, MatchRunePos returns the index of the matching rune pair (or, when len(i.Rune) == 1, rune singleton). If not, MatchRunePos returns -1. MatchRunePos should only be called when i.Op == InstRune.
func (*Inst) String ¶
func (i *Inst) String() string
type InstOp ¶
An InstOp is an instruction opcode.
type InstOp uint8
const (
InstAlt InstOp = iota
InstAltMatch
InstCapture
InstEmptyWidth
InstMatch
InstFail
InstNop
InstRune
InstRune1
InstRuneAny
InstRuneAnyNotNL
)
func (InstOp) String ¶
func (i InstOp) String() string
type Op ¶
An Op is a single regular expression operator.
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 ¶
A Prog is a compiled regular expression program.
type Prog struct {
Inst []Inst
Start int // index of start instruction
NumCap int // number of InstCapture insts in re
}
func Compile ¶
func Compile(re *Regexp) (*Prog, error)
Compile compiles the regexp into a program to be executed. The regexp should have been simplified already (returned from re.Simplify).
func (*Prog) Prefix ¶
func (p *Prog) Prefix() (prefix string, complete bool)
Prefix returns a literal string that all matches for the regexp must start with. Complete is true if the prefix is the entire match.
func (*Prog) StartCond ¶
func (p *Prog) StartCond() EmptyOp
StartCond returns the leading empty-width conditions that must be true in any match. It returns ^EmptyOp(0) if no matches are possible.
func (*Prog) String ¶
func (p *Prog) String() string
type Regexp ¶
A Regexp is a node in a regular expression syntax tree.
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 ¶
func Parse(s string, flags Flags) (*Regexp, error)
Parse parses a regular expression string s, controlled by the specified Flags, and returns a regular expression parse tree. The syntax is described in the top-level comment.
func (*Regexp) CapNames ¶
func (re *Regexp) CapNames() []string
CapNames walks the regexp to find the names of capturing groups.
func (*Regexp) Equal ¶
func (x *Regexp) Equal(y *Regexp) bool
Equal returns true if x and y have identical structure.
func (*Regexp) MaxCap ¶
func (re *Regexp) MaxCap() int
MaxCap walks the regexp to find the maximum capture index.
func (*Regexp) Simplify ¶
func (re *Regexp) Simplify() *Regexp
Simplify returns a regexp equivalent to re but without counted repetitions and with various other simplifications, such as rewriting /(?:a+)+/ to /a+/. The resulting regexp will execute correctly but its string representation will not produce the same parse tree, because capturing parentheses may have been duplicated or removed. For example, the simplified form for /(x){1,2}/ is /(x)(x)?/ but both parentheses capture as $1. The returned regexp may share structure with or be the original.
func (*Regexp) String ¶
func (re *Regexp) String() string