okx: add okx.cab (#3209)

* Refactor: improve value checkers

* Docs: small improvements

[skip ci]

README.md

@@ -13,9 +13,7 @@ This project is not opinionated. In other words, it does NOT endorse, claim or i
 
 ## 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 +91,45 @@ 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/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 (
@@ -123,6 +123,8 @@ 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 +135,19 @@ 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 +223,7 @@ 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