parser

Documentation

Index

• Constants
• Variables
• func TypeWeight(t string) int
• type Segment
• type SorterSegment
  • func (s SorterSegment) Len() int
  • func (s SorterSegment) Less(i, j int) bool
  • func (s SorterSegment) Swap(i, j int)
• type TextParser
  • func NewTextParser(text string) *TextParser
  • func (t *TextParser) Distinct() *TextParser
  • func (t *TextParser) Parse() *TextParser
  • func (t *TextParser) ParseIPv4() *TextParser
  • func (t *TextParser) ParseIPv6() *TextParser

Constants

const (
	// TextTypeIPv4 represents the IPv4 type in the text.
	TextTypeIPv4 = "ipv4"

	// TextTypeIPv6 represents the IPv6 type in the text.
	TextTypeIPv6 = "ipv6"

	// TextTypeDomain represents the domain type in the text.
	TextTypeDomain = "domain"

	// TextTypeText represents any other text type.
	TextTypeText = "text"
)

Variables

var (
	// IPv4Regexp IPv4 正则表达式
	IPv4Regexp = regexp.MustCompile(`(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)(\.(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)){3}`)

	// IPv6Regexp IPv6 正则表达式
	// [fF][eE]80:(:[0-9a-fA-F]{1,4}){0,4}(%\w+)?| # IPv6 Link-local
	// ([0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}| # IPv6
	// ::([fF]{4}){1}:(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)(\.(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)){3}| # IPv4-mapped IPv6 address
	// (([0-9a-fA-F]{1,4}:){0,6}[0-9a-fA-F]{1,4})?::(([0-9a-fA-F]{1,4}:){0,6}[0-9a-fA-F]{1,4})? # IPv6 with two colons
	IPv6Regexp = regexp.MustCompile(`[fF][eE]80:(:[0-9a-fA-F]{1,4}){0,4}(%\w+)?|([0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}|::([fF]{4}){1}:(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)(\.(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)){3}|(([0-9a-fA-F]{1,4}:){0,6}[0-9a-fA-F]{1,4})?::(([0-9a-fA-F]{1,4}:){0,6}[0-9a-fA-F]{1,4})?`)
)

Functions

func TypeWeight

func TypeWeight(t string) int

TypeWeight provides a weight for segment types to help in sorting. IPv4 segments have the highest weight, followed by IPv6, then Domain, and then any other type.

Types

type Segment

type Segment struct {
	Start   int    // Start position of the segment
	End     int    // End position of the segment
	Type    string // Type of the segment (IPv4, IPv6, Domain, or Text)
	Content string // Actual content of the segment
}

Segment represents a section or segment of the text.

type SorterSegment

type SorterSegment []Segment

SorterSegment is a type to help in sorting a slice of Segments based on their Start position.

func (SorterSegment) Len

func (s SorterSegment) Len() int

func (SorterSegment) Less

func (s SorterSegment) Less(i, j int) bool

func (SorterSegment) Swap

func (s SorterSegment) Swap(i, j int)

type TextParser

type TextParser struct {
	Text     string    // Text to be parsed
	Segments []Segment // Parsed segments from the text
}

TextParser is a parser designed to extract IPv4, IPv6, and other text segments from a given text.

func NewTextParser

func NewTextParser(text string) *TextParser

NewTextParser initializes and returns a new TextParser.

func (*TextParser) Distinct

func (t *TextParser) Distinct() *TextParser

Distinct removes duplicate segments and completes the text slices.

func (*TextParser) Parse

func (t *TextParser) Parse() *TextParser

Parse parses the text to extract IPv4, IPv6, and other segments.

func (*TextParser) ParseIPv4

func (t *TextParser) ParseIPv4() *TextParser

ParseIPv4 extracts IPv4 segments from the text.

func (*TextParser) ParseIPv6

func (t *TextParser) ParseIPv6() *TextParser

ParseIPv6 extracts IPv6 segments from the text.