regex

README

Go Regex RE2

A performance improvement to the builtin RE2 module.

This method adds a cache, and some better functions, and uses RE2 for compatability.

If you need more speed, checkout my other PCRE based module go-regex.

Installation

  go get github.com/AspieSoft/go-regex-re2/v2

Usage

import (
  "github.com/AspieSoft/go-regex-re2/v2"

  // or for verbose function names
  "github.com/AspieSoft/go-regex-re2/v2/verbose"
)

// this example will use verbose mode to make function names more clear

// pre compile a regex into the cache
// this method also returns the compiled pcre.Regexp struct
regex.Compile(`re`)

// compile a regex and safely escape user input
regex.Compile(`re %1`, `this will be escaped .*`); // output: this will be escaped \.\*
regex.Compile(`re %1`, `hello \n world`); // output: hello \\n world (note: the \ was escaped, and the n is literal)
tree/v4.0.0
// use %n to reference a param
// use %{n} for param indexes with more than 1 digit
regex.Compile(`re %1 and %2 ... %{12}`, `param 1`, `param 2` ..., `param 12`);

// manually escape a string
// note: the compile methods params are automatically escaped
regex.Escape(`(.*)? \$ \\$ \\\$ regex hack blocked`)

// determine if a regex is valid, and can be compiled by this module
regex.IsValid(`re`)

// determine if a regex is valid, and can be compiled by the builtin RE2 module
regex.IsValidRE2(`re`)

// run a replace function (most advanced feature)
regex.Compile(`(?flags)re(capture group)`).ReplaceFunc(myByteArray, func(data func(int) []byte) []byte {
  data(0) // get the string
  data(1) // get the first capture group

  return []byte("")

  // if the last option is true, returning nil will stop the loop early
  return nil
}, true /* optional: if true, will not process a return output */)

// run a replace function
regex.Compile(`re (capture)`).ReplaceString(myByteArray, []byte("test $1"))

// run a simple light replace function
regex.Compile(`re`).ReplaceStringLiteral(myByteArray, []byte("all capture groups ignored (ie: $1)"))

// return a bool if a regex matches a byte array
regex.Compile(`re`).Match(myByteArray)

// split a byte array in a similar way to JavaScript
regex.Compile(`re|(keep this and split like in JavaScript)`).Split(myByteArray)

// a regex string is modified before compiling, to add a few other features
`use \' in place of ` + "`" + ` to make things easier`
`(?#This is a comment in regex)`

// an alias of *regexp.Regexp
regex.RE2

// direct access to compiled *regexp.Regexp
regex.Compile("re").RE


// another helpful function
// this method makes it easier to return results to a regex function
regex.JoinBytes("string", []byte("byte array"), 10, 'c', data(2))

// the above method can be used in place of this one
append(append(append(append([]byte("string"), []byte("byte array")...), []byte(strconv.Itoa(10))...), 'c'), data(2)...)

Documentation

Index

• func Escape(re string) string
• func IsValid(re string) bool
• func IsValidRE2(re string) bool
• func JoinBytes(bytes ...interface{}) []byte
• type RE2
• type Regexp
  • func Comp(re string, params ...string) *Regexp
  • func CompTry(re string, params ...string) (*Regexp, error)
  • func (reg *Regexp) Match(str []byte) bool
  • func (reg *Regexp) RepFileFunc(name string, rep func(data func(int) []byte) []byte, all bool, ...) error
  • func (reg *Regexp) RepFileStr(name string, rep []byte, all bool, maxReSize ...int64) error
  • func (reg *Regexp) RepFunc(str []byte, rep func(data func(int) []byte) []byte, blank ...bool) []byte
  • func (reg *Regexp) RepStr(str []byte, rep []byte) []byte
  • func (reg *Regexp) RepStrLit(str []byte, rep []byte) []byte
  • func (reg *Regexp) Split(str []byte) [][]byte

Functions

func Escape

func Escape(re string) string

Escape will escape regex special chars

func IsValid

func IsValid(re string) bool

IsValid will return true if a regex is valid and can be compiled by this module

func IsValidRE2

func IsValidRE2(re string) bool

IsValidRE2 will return true if a regex is valid and can be compiled by the builtin RE2 module

func JoinBytes

func JoinBytes(bytes ...interface{}) []byte

JoinBytes is an easy way to join multiple values into a single []byte

Types

type RE2

type RE2 *regexp.Regexp

type Regexp

type Regexp struct {
	RE *regexp.Regexp
	// contains filtered or unexported fields
}

func Comp

func Comp(re string, params ...string) *Regexp

Comp compiles a regular expression and store it in the cache

func CompTry

func CompTry(re string, params ...string) (*Regexp, error)

CompTry tries to compile or returns an error

func (*Regexp) Match

func (reg *Regexp) Match(str []byte) bool

Match returns true if a []byte matches a regex

func (*Regexp) RepFileFunc

func (reg *Regexp) RepFileFunc(name string, rep func(data func(int) []byte) []byte, all bool, maxReSize ...int64) error

RepFileFunc replaces a regex match with the result of a callback function in a file

@all: if true, will replace all text matching @re, if false, will only replace the first occurrence

func (*Regexp) RepFileStr

func (reg *Regexp) RepFileStr(name string, rep []byte, all bool, maxReSize ...int64) error

RepFileStr replaces a regex match with a new []byte in a file

@all: if true, will replace all text matching @re, if false, will only replace the first occurrence

func (*Regexp) RepFunc

func (reg *Regexp) RepFunc(str []byte, rep func(data func(int) []byte) []byte, blank ...bool) []byte

RepFunc replaces a string with the result of a function

similar to JavaScript .replace(/re/, function(data){})

func (*Regexp) RepStr

func (reg *Regexp) RepStr(str []byte, rep []byte) []byte

RepStr is a more complex version of the RepStrLit method

this function will replace things in the result like $1 with your capture groups

use $0 to use the full regex capture group

use ${123} to use numbers with more than one digit

func (*Regexp) RepStrLit

func (reg *Regexp) RepStrLit(str []byte, rep []byte) []byte

RepStrLit replaces a string with another string

@rep uses the literal string, and does Not use args like $1

func (*Regexp) Split

func (reg *Regexp) Split(str []byte) [][]byte

Split splits a string, and keeps capture groups

Similar to JavaScript .split(/re/)