mirror of
https://github.com/v2fly/domain-list-community.git
synced 2026-03-06 19:50:43 +07:00
Improve value checkers and docs (#3208)
* Refactor: improve value checkers * Docs: small improvements [skip ci]
This commit is contained in:
10
README.md
10
README.md
@@ -91,9 +91,9 @@ All data are under `data` directory. Each file in the directory represents a sub
|
|||||||
# comments
|
# comments
|
||||||
include:another-file
|
include:another-file
|
||||||
domain:google.com @attr1 @attr2
|
domain:google.com @attr1 @attr2
|
||||||
|
full:analytics.google.com @ads
|
||||||
keyword:google
|
keyword:google
|
||||||
regexp:www\.google\.com$
|
regexp:^odd[1-7]\.example\.org(\.[a-z]{2})?$
|
||||||
full:www.google.com
|
|
||||||
```
|
```
|
||||||
|
|
||||||
**Syntax:**
|
**Syntax:**
|
||||||
@@ -106,10 +106,10 @@ full:www.google.com
|
|||||||
|
|
||||||
- Comment begins with `#`. It may begin anywhere in the file. The content in the line after `#` is treated as comment and ignored in production.
|
- Comment begins with `#`. It may begin anywhere in the file. The content in the line after `#` is treated as comment and ignored in production.
|
||||||
- Subdomain begins with `domain:`, followed by a valid domain name. The prefix `domain:` may be omitted.
|
- 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.
|
- Full domain begins with `full:`, followed by a complete and valid domain name.
|
||||||
- Domain rules (including `domain`, `keyword`, `regexp` and `full`) 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`.
|
- 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`.
|
- 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`.
|
- 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`.
|
||||||
|
|
||||||
|
|||||||
25
main.go
25
main.go
@@ -30,10 +30,10 @@ const (
|
|||||||
)
|
)
|
||||||
|
|
||||||
var (
|
var (
|
||||||
TypeChecker = regexp.MustCompile(`^(domain|full|keyword|regexp|include)$`)
|
TypeChecker = regexp.MustCompile(`^(domain|full|keyword|regexp|include)$`)
|
||||||
ValueChecker = regexp.MustCompile(`^[a-z0-9!\.-]+$`)
|
DomainChecker = regexp.MustCompile(`^[a-z0-9\.-]+$`)
|
||||||
AttrChecker = regexp.MustCompile(`^[a-z0-9!-]+$`)
|
AttrChecker = regexp.MustCompile(`^[a-z0-9!-]+$`)
|
||||||
SiteChecker = regexp.MustCompile(`^[A-Z0-9!-]+$`)
|
SiteChecker = regexp.MustCompile(`^[A-Z0-9!-]+$`)
|
||||||
)
|
)
|
||||||
|
|
||||||
var (
|
var (
|
||||||
@@ -123,6 +123,8 @@ func parseEntry(line string) (Entry, error) {
|
|||||||
entry.Type = strings.ToLower(kv[0])
|
entry.Type = strings.ToLower(kv[0])
|
||||||
if entry.Type == RuleTypeRegexp {
|
if entry.Type == RuleTypeRegexp {
|
||||||
entry.Value = kv[1]
|
entry.Value = kv[1]
|
||||||
|
} else if entry.Type == RuleTypeInclude {
|
||||||
|
entry.Value = strings.ToUpper(kv[1])
|
||||||
} else {
|
} else {
|
||||||
entry.Value = strings.ToLower(kv[1])
|
entry.Value = strings.ToLower(kv[1])
|
||||||
}
|
}
|
||||||
@@ -133,12 +135,19 @@ func parseEntry(line string) (Entry, error) {
|
|||||||
if !TypeChecker.MatchString(entry.Type) {
|
if !TypeChecker.MatchString(entry.Type) {
|
||||||
return entry, fmt.Errorf("invalid type: %s", 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 {
|
if _, err := regexp.Compile(entry.Value); err != nil {
|
||||||
return entry, fmt.Errorf("invalid regexp: %s", entry.Value)
|
return entry, fmt.Errorf("invalid regexp: %s", entry.Value)
|
||||||
}
|
}
|
||||||
} else if !ValueChecker.MatchString(entry.Value) {
|
case RuleTypeInclude:
|
||||||
return entry, fmt.Errorf("invalid value: %s", entry.Value)
|
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
|
// Parse/Check attributes and affiliations
|
||||||
@@ -214,7 +223,7 @@ func parseList(refName string, refList []*Entry) error {
|
|||||||
if len(entry.Affs) != 0 {
|
if len(entry.Affs) != 0 {
|
||||||
return fmt.Errorf("affiliation is not allowed for include:%s", entry.Value)
|
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 {
|
for _, attr := range entry.Attrs {
|
||||||
if strings.HasPrefix(attr, "-") {
|
if strings.HasPrefix(attr, "-") {
|
||||||
inc.BanAttrs = append(inc.BanAttrs, attr[1:]) // Trim attribute prefix `-` character
|
inc.BanAttrs = append(inc.BanAttrs, attr[1:]) // Trim attribute prefix `-` character
|
||||||
|
|||||||
Reference in New Issue
Block a user