package main

import (
	"fmt"
	"golang.org/x/net/html"
	"io/ioutil"
	"log"
	"net/http"
	"sync"
	"time"
)

// 定义类型Memo
type Memo struct {
	f     Func
	mu    sync.Mutex
	cache map[string]*entry
}

type Func func(key string) (interface{}, error)

type result struct {
	value interface{}
	err   error
}
type entry struct {
	res   result
	ready chan struct{} // closed when res is ready
}

func main() {
	//res, _ := httpGetBody("http://www.baidu.com")
	//fmt.Println(string(res.([]byte))) //类型断言
	//初始化
	m := New(httpGetBody)
	urls, _ := Extract("http://www.baidu.com")
	var n sync.WaitGroup
	for _, url := range urls {
		n.Add(1)
		go func(url string) {
			fmt.Println(url)
			start := time.Now()
			value, err := m.Get(url)
			if err != nil {
				log.Print(err)
			}
			if value != nil {
				fmt.Printf("%s, %s, %d bytes\n",
					url, time.Since(start), len(value.([]byte)))
			}
			n.Done()
		}(url)
	}
	n.Wait()
}

//初始化Memo类型
func New(f Func) *Memo {
	return &Memo{f: f, cache: make(map[string]*entry)}
}

//获取数据放入缓存,如果缓存存在直接返回
func (memo *Memo) Get(key string) (interface{}, error) {
	memo.mu.Lock()
	e := memo.cache[key]
	if e == nil {
		e = &entry{ready: make(chan struct{})}
		memo.cache[key] = e
		memo.mu.Unlock()
		//最耗时的函数部分没有锁,性能会提升
		e.res.value, e.res.err = memo.f(key)
		close(e.ready)
	} else {
		memo.mu.Unlock()
		<-e.ready
	}
	return e.res.value, e.res.err
}

//获取http get数据
func httpGetBody(url string) (interface{}, error) {
	resp, err := http.Get(url)
	if err != nil {
		return nil, err
	}
	defer resp.Body.Close()
	return ioutil.ReadAll(resp.Body)
}

func Extract(url string) ([]string, error) {
	resp, err := http.Get(url)
	if err != nil {
		return nil, err
	}
	if resp.StatusCode != http.StatusOK {
		resp.Body.Close()
		return nil, fmt.Errorf("getting %s: %s", url, resp.Status)
	}

	doc, err := html.Parse(resp.Body)
	resp.Body.Close()
	if err != nil {
		return nil, fmt.Errorf("parsing %s as HTML: %v", url, err)
	}

	var links []string
	visitNode := func(n *html.Node) {
		if n.Type == html.ElementNode && n.Data == "a" {
			for _, a := range n.Attr {
				if a.Key != "href" {
					continue
				}
				link, err := resp.Request.URL.Parse(a.Val)
				if err != nil {
					continue // ignore bad URLs
				}
				links = append(links, link.String())
			}
		}
	}
	forEachNode(doc, visitNode, nil)
	return links, nil
}
func forEachNode(n *html.Node, pre, post func(n *html.Node)) {
	if pre != nil {
		pre(n)
	}
	for c := n.FirstChild; c != nil; c = c.NextSibling {
		forEachNode(c, pre, post)
	}
	if post != nil {
		post(n)
	}
}