Pull request 2243: AG-33443-upd-vetted-script

Squashed commit of the following:

commit 85ce53f0fc53c5422d49dc50d9017a7dd009f7ba
Author: Ainar Garipov <A.Garipov@AdGuard.COM>
Date:   Thu Jun 27 20:11:01 2024 +0300

    client: upd

commit 2588807dfdf4e7e0159ada57d6973194eaf3e286
Merge: c5fc7fbf4 a1a31cd91
Author: Ainar Garipov <A.Garipov@AdGuard.COM>
Date:   Thu Jun 27 20:10:34 2024 +0300

    Merge branch 'master' into AG-33443-upd-vetted-script

commit c5fc7fbf4f85cb7e123a58f42c1ee83b1b369013
Author: Ainar Garipov <A.Garipov@AdGuard.COM>
Date:   Mon Jun 24 13:39:46 2024 +0300

    scripts: imp log

commit af420878b4f5753187b7afa6c2c3f3db54cf7711
Author: Ainar Garipov <A.Garipov@AdGuard.COM>
Date:   Mon Jun 24 13:12:12 2024 +0300

    scripts: upd vetter-filters
This commit is contained in:
Ainar Garipov 2024-06-27 20:18:17 +03:00
parent a1a31cd916
commit 3993f4c476
2 changed files with 30 additions and 17 deletions

View file

@ -295,7 +295,7 @@ export default {
"phishing_army": {
"name": "Phishing Army",
"categoryId": "security",
"homepage": "https://gitlab.com/malware-filter/phishing-filter",
"homepage": "https://phishing.army/",
"source": "https://adguardteam.github.io/HostlistsRegistry/assets/filter_18.txt"
},
"scam_blocklist_by_durablenapkin": {

View file

@ -4,18 +4,23 @@ package main
import (
"bytes"
"context"
"encoding/json"
"fmt"
"log/slog"
"net/http"
"net/url"
"os"
"time"
"github.com/AdguardTeam/golibs/log"
"github.com/AdguardTeam/golibs/logutil/slogutil"
"github.com/google/renameio/v2/maybe"
)
func main() {
ctx := context.Background()
l := slogutil.New(nil)
urlStr := "https://adguardteam.github.io/HostlistsRegistry/assets/filters.json"
if v, ok := os.LookupEnv("URL"); ok {
urlStr = v
@ -31,7 +36,7 @@ func main() {
resp, err := c.Get(urlStr)
check(err)
defer log.OnCloserError(resp.Body, log.ERROR)
defer slogutil.CloseAndLog(ctx, l, resp.Body, slog.LevelError)
if resp.StatusCode != http.StatusOK {
panic(fmt.Errorf("expected code %d, got %d", http.StatusOK, resp.StatusCode))
@ -64,13 +69,13 @@ func main() {
}
for i, f := range hlFlt.Filters {
id := f.FilterID
key := f.FilterKey
cat := f.category()
if cat == "" {
log.Info("warning: filter %s at index %d does not have a fitting category", id, i)
l.WarnContext(ctx, "no fitting category for filter", "key", key, "idx", i)
}
aghFlt.Filters[id] = &aghFiltersFilter{
aghFlt.Filters[key] = &aghFiltersFilter{
Name: f.Name,
CategoryID: cat,
Homepage: f.Homepage,
@ -118,26 +123,34 @@ type hlFilters struct {
// hlFiltersFilter is the JSON structure for a filter in the Hostlists Registry.
type hlFiltersFilter struct {
DownloadURL string `json:"downloadUrl"`
FilterID string `json:"filterId"`
Homepage string `json:"homepage"`
Name string `json:"name"`
Tags []string `json:"tags"`
DownloadURL string `json:"downloadUrl"`
FilterKey string `json:"filterKey"`
Homepage string `json:"homepage"`
Name string `json:"name"`
Tags []int `json:"tags"`
}
// Known tag IDs. Keep in sync with tags/metadata.json in the source repo.
const (
tagIDGeneral = 1
tagIDSecurity = 2
tagIDRegional = 3
tagIDOther = 4
)
// category returns the AdGuard Home category for this filter. If there is no
// fitting category, cat is empty.
func (f *hlFiltersFilter) category() (cat string) {
for _, t := range f.Tags {
switch t {
case "purpose:general":
case tagIDGeneral:
return "general"
case "purpose:other":
return "other"
case "purpose:regional":
return "regional"
case "purpose:security":
case tagIDSecurity:
return "security"
case tagIDRegional:
return "regional"
case tagIDOther:
return "other"
}
}