Add new Binance API endpoint 'binanceru.net' (#3210)

* Refactor: improve deduplicate

* Feat: support to export all lists to a plain yml

use: `--exportlists=_all_`

* Docs: add links for dlc plain yml

[skip ci]

.github/workflows/build.yml

@@ -33,15 +33,16 @@ jobs:
           echo "TAG_NAME=$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
         shell: bash
 
-      - name: Build dlc.dat file
+      - name: Build dlc.dat and plain lists
         run: |
           cd code || exit 1
-          go run ./ --outputdir=../ --exportlists=category-ads-all,tld-cn,cn,tld-\!cn,geolocation-\!cn,apple,icloud
+          go run ./ --outputdir=../ --exportlists=_all_,category-ads-all,tld-cn,cn,tld-\!cn,geolocation-\!cn,apple,icloud
           cd ../ && rm -rf code
 
       - name: Generate dlc.dat sha256 hash
         run: |
           sha256sum dlc.dat > dlc.dat.sha256sum
+          sha256sum dlc.dat_plain.yml > dlc.dat_plain.yml.sha256sum
 
       - name: Generate Zip
         run: |
@@ -66,6 +67,6 @@ jobs:
 
       - name: Release and upload assets
         run: |
-          gh release create ${{ env.TAG_NAME }} --generate-notes --latest --title ${{ env.RELEASE_NAME }} ./dlc.dat ./dlc.dat.*
+          gh release create ${{ env.TAG_NAME }} --generate-notes --latest --title ${{ env.RELEASE_NAME }} ./dlc.dat ./dlc.dat.* ./dlc.dat_plain.yml ./dlc.dat_plain.yml.*
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -8,4 +8,5 @@
 dlc.dat
 
 # Exported plaintext lists.
+dlc.dat_plain.yml
 /*.txt

README.md

@@ -10,12 +10,12 @@ This project is not opinionated. In other words, it does NOT endorse, claim or i
 
 - **dlc.dat**：[https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat](https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat)
 - **dlc.dat.sha256sum**：[https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat.sha256sum](https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat.sha256sum)
+- **dlc.dat_plain.yml**：[https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat_plain.yml](https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat_plain.yml)
+- **dlc.dat_plain.yml.sha256sum**：[https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat_plain.yml.sha256sum](https://github.com/v2fly/domain-list-community/releases/latest/download/dlc.dat_plain.yml.sha256sum)
 
 ## Notice
 
-Rules with `@!cn` attribute has been cast out from cn lists. `geosite:geolocation-cn@!cn` is no longer available.
-
-Check [#390](https://github.com/v2fly/domain-list-community/issues/390), [#3119](https://github.com/v2fly/domain-list-community/pull/3119) and [#3198](https://github.com/v2fly/domain-list-community/pull/3198) for more information.
+Rules with `@!cn` attribute has been cast out from cn lists. `geosite:geolocation-cn@!cn` is no longer available. Check [#390](https://github.com/v2fly/domain-list-community/issues/390), [#3119](https://github.com/v2fly/domain-list-community/pull/3119) and [#3198](https://github.com/v2fly/domain-list-community/pull/3198) for more information.
 
 Please report if you have any problems or questions.
 
@@ -93,38 +93,45 @@ All data are under `data` directory. Each file in the directory represents a sub
 # comments
 include:another-file
 domain:google.com @attr1 @attr2
+full:analytics.google.com @ads
 keyword:google
-regexp:www\.google\.com$
-full:www.google.com
+regexp:^odd[1-7]\.example\.org(\.[a-z]{2})?$
 ```
 
 **Syntax:**
 
+> [!NOTE]
+> Adding new `regexp` and `keyword` rules is discouraged because it is easy to use them incorrectly, and proxy software cannot efficiently match these types of rules.
+
+> [!NOTE]
 > The following types of rules are **NOT** fully compatible with the ones that defined by user in V2Ray config file. Do **Not** copy and paste directly.
 
 - Comment begins with `#`. It may begin anywhere in the file. The content in the line after `#` is treated as comment and ignored in production.
-- Inclusion begins with `include:`, followed by the file name of an existing file in the same directory.
 - Subdomain begins with `domain:`, followed by a valid domain name. The prefix `domain:` may be omitted.
-- Keyword begins with `keyword:`, followed by a string.
-- Regular expression begins with `regexp:`, followed by a valid regular expression (per Golang's standard).
 - Full domain begins with `full:`, followed by a complete and valid domain name.
-- Domains (including `domain`, `keyword`, `regexp` and `full`) may have one or more attributes. Each attribute begins with `@` and followed by the name of the attribute.
-
-> **Note:** Adding new `regexp` and `keyword` rules is discouraged because it is easy to use them incorrectly, and proxy software cannot efficiently match these types of rules.
+- Keyword begins with `keyword:`, followed by a substring of a valid domain name.
+- Regular expression begins with `regexp:`, followed by a valid regular expression (per Golang's standard).
+- Domain rules (including `domain`, `full`, `keyword`, and `regexp`) may have none, one or more attributes. Each attribute begins with `@` and followed by the name of the attribute. Attributes will remain available in final lists and `dlc.dat`.
+- Domain rules may have none, one or more affiliations, which additionally adds the domain rule into the affiliated target list. Each affiliation begins with `&` and followed by the name of the target list (nomatter whether the target has a dedicated file in data path). This is a method for data management, and will not remain in the final lists or `dlc.dat`.
+- Inclusion begins with `include:`, followed by the name of another valid domain list. A simple `include:listb` in file `lista` means adding all domain rules of `listb` into `lista`. Inclusions with attributes stands for selective inclusion. `include:listb @attr1 @-attr2` means only adding those domain rules *with* `@attr1` **and** *without* `@attr2`. This is a special type for data management, and will not remain in the final lists or `dlc.dat`.
 
 ## How it works
 
 The entire `data` directory will be built into an external `geosite` file for Project V. Each file in the directory represents a section in the generated file.
 
-To generate a section:
+**General steps:**
 
-1. Remove all the comments in the file.
-2. Replace `include:` lines with the actual content of the file.
-3. Omit all empty lines.
-4. Generate each `domain:` line into a [sub-domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L21).
-5. Generate each `full:` line into a [full domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L23).
-6. Generate each `keyword:` line into a [plain domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L17).
-7. Generate each `regexp:` line into a [regex domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L19).
+1. Read files in the data path (ignore all comments and empty lines).
+2. Parse and resolve source data, turn affiliations and inclusions into actual domain rules in proper lists.
+3. Deduplicate and sort rules in every list.
+4. Export desired plain text lists.
+5. Generate `dlc.dat`:
+   - turn each `domain:` line into a [sub-domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L21).
+   - turn each `full:` line into a [full domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L23).
+   - turn each `keyword:` line into a [plain domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L17).
+   - turn each `regexp:` line into a [regex domain routing rule](https://github.com/v2fly/v2ray-core/blob/master/app/router/routercommon/common.proto#L19).
+
+Read [main.go](./main.go) for details.
 
 ## How to organize domains
 

data/binance

@@ -28,6 +28,7 @@ binancezh.top
 
 # API
 binanceapi.com
+binanceru.net
 bnbstatic.com
 bntrace.com
 nftstatic.com

data/category-games-!cn

@@ -5,6 +5,7 @@ include:curseforge
 include:cygames
 include:ea
 include:embark
+include:eneba
 include:epicgames
 include:escapefromtarkov
 include:faceit

data/category-games-cn

@@ -16,6 +16,8 @@ include:yokaverse
 7k7k.com
 # 刀锋盒子 皖B2-20190103-4
 9xgame.com
+# 韵律谱面研究站 桂ICP备20001846号-3
+arcaea.cn
 # 《异象回声》游戏官网 沪ICP备2023010411号-1
 astral-vector.com
 # 九九互动 粤ICP备19068416号

data/category-hospital-cn

@@ -10,3 +10,6 @@ yctdyy.com
 
 # 南方医科大学深圳医院
 smuszh.com
+
+# 四川大学华西医院
+cd120.com

data/eneba

@@ -0,0 +1,2 @@
+eneba.com
+eneba.games

data/geolocation-!cn

@@ -102,6 +102,8 @@ include:w3schools
 include:zotero
 
 chemequations.com # 线上化学方程式！
+geogebra.org
+wolframalpha.com
 
 # Entertainment & Games & Music & Podcasts & Videos
 include:category-entertainment
@@ -300,6 +302,7 @@ include:wikimedia
 
 atwiki.jp
 touhouwiki.net
+wiki.gg
 
 # Others
 include:avaxhome

data/geolocation-cn

@@ -488,6 +488,12 @@ include:chinaunicom @-!cn
 ## IPIP ip地理位置数据库
 include:ipip @-!cn
 
+## 白描
+baimiao.tech
+baimiaoapp.com
+shinescan.tech
+uzero.cn
+
 chaziyu.com # 滇ICP备2024035496号
 fofa.info # Fofa网站测绘（华顺信安）
 icplishi.com # 粤ICP备20009057号

data/okx

@@ -1,8 +1,9 @@
 okex.com
-okx.com
 okx-dns.com
 okx-dns1.com
 okx-dns2.com
+okx.cab
+okx.com
 
 # OKC Browser
 oklink.com @cn

data/xiaohongshu

@@ -1,5 +1,6 @@
 include:askdiandian
 
+rednotecdn.com
 xhscdn.com
 xhscdn.net
 xhslink.com

main.go

@@ -30,10 +30,10 @@ const (
 )
 
 var (
-	TypeChecker  = regexp.MustCompile(`^(domain|full|keyword|regexp|include)$`)
-	ValueChecker = regexp.MustCompile(`^[a-z0-9!\.-]+$`)
-	AttrChecker  = regexp.MustCompile(`^[a-z0-9!-]+$`)
-	SiteChecker  = regexp.MustCompile(`^[A-Z0-9!-]+$`)
+	TypeChecker   = regexp.MustCompile(`^(domain|full|keyword|regexp|include)$`)
+	DomainChecker = regexp.MustCompile(`^[a-z0-9\.-]+$`)
+	AttrChecker   = regexp.MustCompile(`^[a-z0-9!-]+$`)
+	SiteChecker   = regexp.MustCompile(`^[A-Z0-9!-]+$`)
 )
 
 var (
@@ -92,6 +92,25 @@ func makeProtoList(listName string, entries []*Entry) (*router.GeoSite, error) {
 	return site, nil
 }
 
+func writePlainAll(siteList *[]string) error {
+	file, err := os.Create(filepath.Join(*outputDir, *outputName + "_plain.yml"))
+	if err != nil {
+		return err
+	}
+	defer file.Close()
+	w := bufio.NewWriter(file)
+	w.WriteString("lists:\n")
+	for _, site := range *siteList {
+		fmt.Fprintf(w, "  - name: %s\n", strings.ToLower(site))
+		fmt.Fprintf(w, "    length: %d\n", len(finalMap[site]))
+		w.WriteString("    rules:\n")
+		for _, entry := range finalMap[site] {
+			fmt.Fprintf(w, "      - %s\n", entry.Plain)
+		}
+	}
+	return w.Flush()
+}
+
 func writePlainList(exportedName string) error {
 	targetList, exist := finalMap[strings.ToUpper(exportedName)]
 	if !exist || len(targetList) == 0 {
@@ -123,6 +142,8 @@ func parseEntry(line string) (Entry, error) {
 		entry.Type = strings.ToLower(kv[0])
 		if entry.Type == RuleTypeRegexp {
 			entry.Value = kv[1]
+		} else if entry.Type == RuleTypeInclude {
+			entry.Value = strings.ToUpper(kv[1])
 		} else {
 			entry.Value = strings.ToLower(kv[1])
 		}
@@ -133,12 +154,19 @@ func parseEntry(line string) (Entry, error) {
 	if !TypeChecker.MatchString(entry.Type) {
 		return entry, fmt.Errorf("invalid type: %s", entry.Type)
 	}
-	if entry.Type == RuleTypeRegexp {
+	switch entry.Type {
+	case RuleTypeRegexp:
 		if _, err := regexp.Compile(entry.Value); err != nil {
 			return entry, fmt.Errorf("invalid regexp: %s", entry.Value)
 		}
-	} else if !ValueChecker.MatchString(entry.Value) {
-		return entry, fmt.Errorf("invalid value: %s", entry.Value)
+	case RuleTypeInclude:
+		if !SiteChecker.MatchString(entry.Value) {
+			return entry, fmt.Errorf("invalid included list name: %s", entry.Value)
+		}
+	default: // `full`, `domain` and `keyword` are all (parts of) domains
+		if !DomainChecker.MatchString(entry.Value) {
+			return entry, fmt.Errorf("invalid domain: %s", entry.Value)
+		}
 	}
 
 	// Parse/Check attributes and affiliations
@@ -214,7 +242,7 @@ func parseList(refName string, refList []*Entry) error {
 			if len(entry.Affs) != 0 {
 				return fmt.Errorf("affiliation is not allowed for include:%s", entry.Value)
 			}
-			inc := &Inclusion{Source: strings.ToUpper(entry.Value)}
+			inc := &Inclusion{Source: entry.Value}
 			for _, attr := range entry.Attrs {
 				if strings.HasPrefix(attr, "-") {
 					inc.BanAttrs = append(inc.BanAttrs, attr[1:]) // Trim attribute prefix `-` character
@@ -266,7 +294,10 @@ func polishList(roughMap *map[string]*Entry) []*Entry {
 	// Remove redundant subdomains for full/domain without attr
 	for _, qentry := range queuingList {
 		isRedundant := false
-		pd := qentry.Value // Parent domain
+		pd := qentry.Value // To be parent domain
+		if qentry.Type == RuleTypeFullDomain {
+			pd = "." + pd // So that `domain:example.org` overrides `full:example.org`
+		}
 		for {
 			idx := strings.Index(pd, ".")
 			if idx == -1 { break }
@@ -364,13 +395,16 @@ func main() {
 		}
 	}
 
-	// Generate finalMap
+	// Generate finalMap and sorted list of site names
+	siteList := make([]string, 0 ,len(plMap))
 	for _, pl := range plMap {
+		siteList = append(siteList, pl.Name)
 		if err := resolveList(pl); err != nil {
 			fmt.Println("Failed to resolveList:", err)
 			os.Exit(1)
 		}
 	}
+	slices.Sort(siteList)
 
 	// Create output directory if not exist
 	if _, err := os.Stat(*outputDir); os.IsNotExist(err) {
@@ -384,9 +418,16 @@ func main() {
 	if *exportLists != "" {
 		exportedListSlice := strings.Split(*exportLists, ",")
 		for _, exportedList := range exportedListSlice {
-			if err := writePlainList(exportedList); err != nil {
-				fmt.Println("Failed to write list:", err)
-				continue
+			if exportedList == "_all_" {
+				if err := writePlainAll(&siteList); err != nil {
+					fmt.Println("Failed to writePlainAll:", err)
+					continue
+				}
+			} else {
+				if err := writePlainList(exportedList); err != nil {
+					fmt.Println("Failed to write list:", err)
+					continue
+				}
 			}
 			fmt.Printf("list: '%s' has been generated successfully.\n", exportedList)
 		}
@@ -394,18 +435,14 @@ func main() {
 
 	// Generate dat file
 	protoList := new(router.GeoSiteList)
-	for siteName, siteEntries := range finalMap {
-		site, err := makeProtoList(siteName, siteEntries)
+	for _, siteName := range siteList { // So that protoList.Entry is sorted
+		site, err := makeProtoList(siteName, finalMap[siteName])
 		if err != nil {
-			fmt.Println("Failed:", err)
+			fmt.Println("Failed to makeProtoList:", err)
 			os.Exit(1)
 		}
 		protoList.Entry = append(protoList.Entry, site)
 	}
-	// Sort protoList so the marshaled list is reproducible
-	slices.SortFunc(protoList.Entry, func(a, b *router.GeoSite) int {
-		return strings.Compare(a.CountryCode, b.CountryCode)
-	})
 
 	protoBytes, err := proto.Marshal(protoList)
 	if err != nil {