Documentation
¶
Index ¶
Constants ¶
View Source
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 ¶
View Source
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 (`net.ParseIP` does not support this format) // ([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(`([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})?`) // DomainRegexp 域名正则表达式 // [a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,} // ([a-zA-Z0-9][-a-zA-Z0-9]{0,62}\.)+([a-zA-Z][-a-zA-Z]{0,62}) // ^(xn--|_)?[a-zA-Z0-9]([a-zA-Z0-9-_]{0,61}[a-zA-Z0-9])?(\.(xn--|_)?[a-zA-Z0-9]([a-zA-Z0-9-_]{0,61}[a-zA-Z0-9])?)*(\.[a-zA-Z]{2,})$ DomainRegexp = regexp.MustCompile(`(xn--|_)?[a-zA-Z0-9]([a-zA-Z0-9-_]{0,61}[a-zA-Z0-9])?(\.(xn--|_)?[a-zA-Z0-9]([a-zA-Z0-9-_]{0,61}[a-zA-Z0-9])?)*(\.[a-zA-Z]{2,})`) )
Functions ¶
func TypeWeight ¶
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) ParseDomain ¶ added in v0.2.8
func (t *TextParser) ParseDomain() *TextParser
ParseDomain extracts domain segments from the text.
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.
Source Files
Click to show internal directories.
Click to hide internal directories.