Perf: repalce aho-corasick w/ regexp

This commit is contained in:
SukkaW 2025-01-03 22:30:39 +08:00
parent 090f055677
commit ef1b80fb90
7 changed files with 14 additions and 14 deletions

View File

@ -7,7 +7,7 @@ import { appendArrayInPlaceCurried } from './append-array-in-place';
import { DEBUG_DOMAIN_TO_FIND, PHISHING_DOMAIN_LISTS_EXTRA, PHISHING_HOSTS_EXTRA } from '../constants/reject-data-source';
import { loosTldOptWithPrivateDomains } from '../constants/loose-tldts-opt';
import picocolors from 'picocolors';
import { createAhoCorasick as createKeywordFilter } from 'foxts/ahocorasick';
import { createRetrieKeywordFilter as createKeywordFilter } from 'foxts/retrie';
import { createCacheKey, deserializeArray, serializeArray } from './cache-filesystem';
import { cache } from './fs-memo';
import { isCI } from 'ci-info';

View File

@ -1,5 +1,5 @@
import { invariant } from 'foxts/guard';
import { createAhoCorasick as createKeywordFilter } from 'foxts/ahocorasick';
import { createRetrieKeywordFilter as createKeywordFilter } from 'foxts/retrie';
import { RuleOutput } from './base';
import type { SingboxSourceFormat } from '../singbox';
@ -17,7 +17,7 @@ export class DomainsetOutput extends RuleOutput<string[]> {
private $singbox_domains_suffixes: string[] = ['this_ruleset_is_made_by_sukkaw.ruleset.skk.moe'];
private $adguardhome: string[] = [];
preprocess() {
const kwfilter = createKeywordFilter(this.domainKeywords);
const kwfilter = createKeywordFilter(Array.from(this.domainKeywords));
this.domainTrie.dumpWithoutDot((domain, subdomain) => {
if (kwfilter(domain)) {

View File

@ -1,6 +1,6 @@
import { merge } from 'fast-cidr-tools';
import type { Span } from '../../trace';
import { createAhoCorasick as createKeywordFilter } from 'foxts/ahocorasick';
import { createRetrieKeywordFilter as createKeywordFilter } from 'foxts/retrie';
import { appendArrayInPlace } from '../append-array-in-place';
import { appendSetElementsToArray } from 'foxts/append-set-elements-to-array';
import type { SingboxSourceFormat } from '../singbox';
@ -17,7 +17,7 @@ export class RulesetOutput extends RuleOutput<Preprocessed> {
}
protected preprocess() {
const kwfilter = createKeywordFilter(this.domainKeywords);
const kwfilter = createKeywordFilter(Array.from(this.domainKeywords));
const domains: string[] = [];
const domainSuffixes: string[] = [];

View File

@ -10,7 +10,7 @@ import { newQueue } from '@henrygd/queue';
import asyncRetry from 'async-retry';
import * as whoiser from 'whoiser';
import picocolors from 'picocolors';
import { createAhoCorasick as createKeywordFilter } from 'foxts/ahocorasick';
import { createRetrieKeywordFilter as createKeywordFilter } from 'foxts/retrie';
import './lib/fetch-retry';
const dohServers: Array<[string, DNS2.DnsResolver]> = ([

View File

@ -7,7 +7,7 @@ import { readFileByLine } from './lib/fetch-text-by-line';
import path from 'node:path';
import { OUTPUT_SURGE_DIR } from './constants/dir';
import { $fetch } from './lib/make-fetch-happen';
import { createAhoCorasick as createKeywordFilter } from 'foxts/ahocorasick';
import { createRetrieKeywordFilter as createKeywordFilter } from 'foxts/retrie';
export async function parseGfwList() {
const whiteSet = new Set<string>();
@ -117,7 +117,7 @@ export async function parseGfwList() {
whiteSet.forEach(domain => trie.whitelist(domain));
const kwfilter = createKeywordFilter(keywordSet);
const kwfilter = createKeywordFilter([...keywordSet]);
const missingTop10000Gfwed = new Set<string>();

View File

@ -31,7 +31,7 @@
"fast-cidr-tools": "^0.3.1",
"fast-fifo": "^1.3.2",
"fdir": "^6.4.2",
"foxts": "^1.0.13",
"foxts": "^1.1.3",
"hash-wasm": "^4.12.0",
"json-stringify-pretty-compact": "^3.0.0",
"make-fetch-happen": "^14.0.3",

10
pnpm-lock.yaml generated
View File

@ -45,8 +45,8 @@ importers:
specifier: ^6.4.2
version: 6.4.2(picomatch@4.0.2)
foxts:
specifier: ^1.0.13
version: 1.0.13
specifier: ^1.1.3
version: 1.1.3
hash-wasm:
specifier: ^4.12.0
version: 4.12.0
@ -1145,8 +1145,8 @@ packages:
resolution: {integrity: sha512-tzN8e4TX8+kkxGPK8D5u0FNmjPUjw3lwC9lSLxxoB/+GtsJG91CO8bSWy73APlgAZzZbXEYZJuxjkHH2w+Ezhw==}
engines: {node: '>= 6'}
foxts@1.0.13:
resolution: {integrity: sha512-OTxteinRnc7hZ8NbcPH5gOji/D2JmSEoYEVzCZ08YEb1T7zudsK/+Kp4wUkBjBBvcjvWnxOv4EILBsbwnddMAg==}
foxts@1.1.3:
resolution: {integrity: sha512-xF599E5aoxmBBN1Q+CJjlJdQndkjcw2Drc59qfQmSWR/0mOVI2zK+zEIb1lvq6wdRZZHAdrI/x+kfRvjF+lpHQ==}
fs-constants@1.0.0:
resolution: {integrity: sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow==}
@ -3030,7 +3030,7 @@ snapshots:
combined-stream: 1.0.8
mime-types: 2.1.35
foxts@1.0.13: {}
foxts@1.1.3: {}
fs-constants@1.0.0: {}