当前位置：网站首页>Go language foundation ----- 11 ----- regular expression

Go language foundation ----- 11 ----- regular expression

2022-07-03 07:37:00 【Mango sauce】

1 Regular expression Introduction

Regular expression is a complex and powerful tool for pattern matching and text manipulation . Although regular expressions are less efficient than pure text matching , But it's more flexible . According to its grammatical rules , The matching pattern constructed on demand can filter almost any character combination you want from the original text .

Go Language passing regexp The standard package provides official support for regular expressions , If you've used the regular features of other programming languages , So you should be right Go The language version is not too strange , But there are also some small differences between them , because Go What we achieve is RE2 standard , except \C, Detailed syntax description reference ：http://code.google.com/p/re2/wiki/Syntax.

In fact, string processing we can use strings Package to search (Contains、Index)、 Replace (Replace) And analysis (Split、Join) Wait for the operation , But these are simple string operations , Their search is case sensitive , And fixed strings , If we need to match the variable one, we can't do it , Of course, if strings Bag can solve your problem , Then try to use it to solve . Because they're simple enough 、 And the performance and readability will be better than regular .

2 Regular matching rule graph

Refer to the official website ： https://studygolang.com/pkgdoc.
Insert picture description here

2.1 Example 1： Order number (.) Match any type .

package main

import (
	"fmt"
	"regexp"
)

func main(){
    
	buf := "abc azc a7c aac 888 a9c tac"

	//1)  Interpretation rules ,  It parses regular expressions , If successful, return to the interpreter 
	reg1 := regexp.MustCompile(`a.c`)
	if reg1 == nil {
    
		fmt.Println("regexp err")
		return
	}

	//2)  Extract key information according to rules 
	result1 := reg1.FindAllStringSubmatch(buf, -1)
	fmt.Println("result1 = ", result1)

}

Insert picture description here

2.2 Example 2： matching a[0-9]c Value between .

package main

import (
	"fmt"
	"regexp"
)

func main(){
    

	buf := "abc azc a7c aac 888 a9c tac"

	//1)  Interpretation rules ,  It parses regular expressions , If successful, return to the interpreter 
	reg1 := regexp.MustCompile(`a[0-9]c`)

	if reg1 == nil {
     // Explanation failed , return nil
		fmt.Println("regexp err")
		return
	}

	//2)  Extract key information according to rules 
	result1 := reg1.FindAllStringSubmatch(buf, -1)
	fmt.Println("result1 = ", result1)

}

Insert picture description here

2.3 Example 3：\d matching a[0-9]c Value between .

package main

import (
	"fmt"
	"regexp"
)

func main(){
    

	buf := "abc azc a7c aac 888 a9c tac"

	//1)  Interpretation rules ,  It parses regular expressions , If successful, return to the interpreter 
	reg1 := regexp.MustCompile(`a\dc`)
	if reg1 == nil {
     // Explanation failed , return nil
		fmt.Println("regexp err")
		return
	}

	//2)  Extract key information according to rules 
	result1 := reg1.FindAllStringSubmatch(buf, -1)
	fmt.Println("result1 = ", result1)
}

Results and examples 2 equally .

Insert picture description here

2.4 Example 4：+ Matches the previous character 1 Times or times .

package main

import (
	"fmt"
	"regexp"
)

func main(){
    

	buf := "43.14 567 agsdg 1.23 7. 8.9 1sdljgl 6.66 7.8 "

	// Explain regular expressions , + Matches the previous character 1 Times or times 
	reg := regexp.MustCompile(`\d+\.\d+`)
	if reg == nil {
    
		fmt.Println("MustCompile err")
		return
	}

	// Extract key information 
	//result := reg.FindAllString(buf, -1)
	result := reg.FindAllStringSubmatch(buf, -1)
	fmt.Println("result = ", result)
}

Insert picture description here

2.5 Example 5： Filter labeled or unlabeled .

package main

import (
	"fmt"
	"regexp"
)

func main(){
    

	//``  Native string 
	buf := ` <!DOCTYPE html> <html lang="zh-CN"> <head> <title>Go Language standard library document Chinese version  | Go Chinese language network  | Golang The Chinese community  | Golang China </title> <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=1.0, user-scalable=no"> <meta http-equiv="X-UA-Compatible" content="IE=edge, chrome=1"> <meta charset="utf-8"> <link rel="shortcut icon" href="/static/img/go.ico"> <link rel="apple-touch-icon" type="image/png" href="/static/img/logo2.png"> <meta name="author" content="polaris <[email protected]>"> <meta name="keywords" content=" chinese ,  file ,  Standard library , Go Language ,Golang,Go Community ,Go The Chinese community ,Golang The Chinese community ,Go Language community ,Go Language learning , Study Go Language ,Go Language learning garden ,Golang  China ,Golang China ,Golang China, Go Language Forum , Go Chinese language network "> <meta name="description" content="Go Language document Chinese version ,Go Chinese language network , China  Golang  Community ,Go Language learning garden , Committed to building a perfect  Golang  The Chinese community ,Go Learning home for language lovers . Share  Go  language knowledge , Exchange experience "> </head> <div> And hobbies </div> <div> ha-ha   Are you there   be not in  </div> <div> test </div> <div> Come here </div> <frameset cols="15,85"> <frame src="/static/pkgdoc/i.html"> <frame name="main" src="/static/pkgdoc/main.html" tppabs="main.html" > <noframes> </noframes> </frameset> </html> `

	// Explain regular expressions , + Matches the previous character 1 Times or times 
	//reg := regexp.MustCompile(`<div>(.*)</div>`)
	//.* Indicates that all current contents are matched . At this point, the current is <div></div> The content of both .* Followed by ? after , namely *? Indicates matching duplicate items , That is, if there is a repetition, it will only be displayed once , The less, the better. .
	//?s:： Indicates that line breaks are also matched .
	reg := regexp.MustCompile(`<div>(?s:(.*?))</div>`)
	if reg == nil {
    
		fmt.Println("MustCompile err")
		return
	}

	// Extract key information 
	result := reg.FindAllStringSubmatch(buf, -1)
	//fmt.Println("result = ", result)

	// Filter <></>
	for _, text := range result {
    
		// Filter tagged 
		//fmt.Println("text[0] = ", text[0]) // belt <></>
		// Filter unlabeled 
		fmt.Println("text[1] = ", text[1]) // No <></>
	}
}