Skip to content

Commit

Permalink
Chore: merge reject ruleset and domainset during build
Browse files Browse the repository at this point in the history
  • Loading branch information
SukkaW committed May 18, 2024
1 parent 70bbf9c commit 6380d0b
Showing 1 changed file with 10 additions and 14 deletions.
24 changes: 10 additions & 14 deletions Build/build-reject-domainset.ts
Original file line number Diff line number Diff line change
Expand Up @@ -78,9 +78,7 @@ export const buildRejectDomainSet = task(import.meta.path, async (span) => {
console.log(`Import ${previousSize} rules from Hosts / AdBlock Filter Rules & reject_sukka.conf!`);

// Dedupe domainSets
await span.traceChildAsync('dedupe from black keywords/suffixes', async (childSpan) => {
/** Collect DOMAIN-SUFFIX from non_ip/reject.conf for deduplication */
const domainSuffixSet = new Set<string>();
await span.traceChildAsync('dedupe from black keywords', async (childSpan) => {
/** Collect DOMAIN-KEYWORD from non_ip/reject.conf for deduplication */
const domainKeywordsSet = new Set<string>();

Expand All @@ -91,28 +89,26 @@ export const buildRejectDomainSet = task(import.meta.path, async (span) => {
if (type === 'DOMAIN-KEYWORD') {
domainKeywordsSet.add(value.trim());
} else if (type === 'DOMAIN-SUFFIX') {
domainSuffixSet.add(value.trim());
domainSets.add(`.${value.trim()}`); // Add to domainSets for later deduplication
}
}
});

// Remove as many domains as possible from domainSets before creating trie
SetHelpers.subtract(domainSets, domainSuffixSet);
SetHelpers.subtract(domainSets, filterRuleWhitelistDomainSets);

childSpan.traceChildSync('dedupe from white/suffixes', () => {
childSpan.traceChildSync('dedupe from white suffixes', () => {
const trie = createTrie(domainSets);

domainSuffixSet.forEach(suffix => {
trie.substractSetInPlaceFromFound(suffix, domainSets);
});
filterRuleWhitelistDomainSets.forEach(suffix => {
trie.substractSetInPlaceFromFound(suffix, domainSets);
domainSets.delete(
suffix[0] === '.'
? suffix.slice(1) // handle case like removing `g.msn.com` due to white `.g.msn.com` (`@@||g.msn.com`)
: `.${suffix}` // If `g.msn.com` is whitelisted, then `.g.msn.com` should be removed from domain set
);
if (suffix[0] === '.') {
domainSets.delete(suffix.slice(1));
domainSets.delete(suffix);
} else {
domainSets.delete(`.${suffix}`);
domainSets.delete(suffix);
}
});
});

Expand Down

0 comments on commit 6380d0b

Please sign in to comment.