improved blacklist parsing

This commit is contained in:
Niklas 2020-12-29 22:34:30 +01:00
parent c995920b68
commit 4ddaa5a4c0

View File

@ -1,6 +1,7 @@
package main
import (
"errors"
"io/ioutil"
"log"
"net"
@ -26,12 +27,10 @@ func loadBlacklist(config []configBlacklist) map[string]bool {
}
domains := parseRawBlacklist(element, *raw)
log.Printf("Added %d blocked domains", len(domains))
list = append(list, domains...)
}
// list = removeDuplicates(list)
// sort.Strings(list)
domainMap := make(map[string]bool)
for _, e := range list {
domainMap[e] = true
@ -56,22 +55,46 @@ func removeDuplicates(elements []string) []string {
}
func requestBacklist(blacklist configBlacklist) (*string, error) {
if blacklist.URL != "" {
return getBlacklistFromURL(blacklist.URL)
}
return nil, errors.New("No blacklist provided")
}
func getBlacklistFromURL(url string) (*string, error) {
// Request list
resp, err := http.Get(blacklist.URL)
resp, err := http.Get(url)
if err != nil {
return nil, err
}
defer resp.Body.Close()
if resp.StatusCode != 200 {
log.Printf("Got %d status code. Continueing anyway.", resp.StatusCode)
}
body, err := ioutil.ReadAll(resp.Body)
bodyString := string(body)
log.Printf("Downloaded blacklist %s", blacklist.URL)
log.Printf("Downloaded blacklist %s", url)
return &bodyString, err
}
func parseRawBlacklist(blacklist configBlacklist, raw string) []string {
switch blacklist.Format {
case "host":
return parseHostFormat(raw)
default:
log.Printf("Failed to parse blacklist. Format not supported: %s", blacklist.Format)
log.Println("Supported types are: host")
return make([]string, 0)
}
}
func parseHostFormat(raw string) []string {
finalList := make([]string, 0)
reg := regexp.MustCompile(`(?mi)^\s*(#*)\s*(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\s+([a-zA-Z0-9\.\- ]+)$`)
matches := reg.FindAllStringSubmatch(raw, -1)