Files
hasher/scripts/index-file.ts
2025-12-04 01:30:37 +01:00

261 líneas
8.3 KiB
JavaScript

#!/usr/bin/env node
/**
* Hasher Indexer Script
*
* This script reads a text file with one word/phrase per line and indexes
* all the generated hashes into Elasticsearch.
*
* Usage:
* npm run index-file <path-to-file.txt>
* or
* node scripts/index-file.js <path-to-file.txt>
*
* Options:
* --batch-size <number> Number of items to process in each batch (default: 100)
* --help Show this help message
*/
import { Client } from '@elastic/elasticsearch';
import { createReadStream } from 'fs';
import { resolve } from 'path';
import { createInterface } from 'readline';
import crypto from 'crypto';
const ELASTICSEARCH_NODE = process.env.ELASTICSEARCH_NODE || 'http://localhost:9200';
const INDEX_NAME = 'hasher';
const DEFAULT_BATCH_SIZE = 100;
interface HashDocument {
plaintext: string;
md5: string;
sha1: string;
sha256: string;
sha512: string;
bcrypt: string;
created_at: string;
}
async function generateHashes(plaintext: string): Promise<HashDocument> {
const bcrypt = await import('bcrypt');
const bcryptHash = await bcrypt.default.hash(plaintext, 10);
return {
plaintext,
md5: crypto.createHash('md5').update(plaintext).digest('hex'),
sha1: crypto.createHash('sha1').update(plaintext).digest('hex'),
sha256: crypto.createHash('sha256').update(plaintext).digest('hex'),
sha512: crypto.createHash('sha512').update(plaintext).digest('hex'),
bcrypt: bcryptHash,
created_at: new Date().toISOString()
};
}
function showHelp() {
console.log(`
Hasher Indexer Script
Usage:
npm run index-file <path-to-file.txt>
node scripts/index-file.js <path-to-file.txt>
Options:
--batch-size <number> Number of items to process in each batch (default: 100)
--help Show this help message
Environment Variables:
ELASTICSEARCH_NODE Elasticsearch node URL (default: http://localhost:9200)
Example:
npm run index-file wordlist.txt
npm run index-file wordlist.txt -- --batch-size 500
`);
process.exit(0);
}
async function indexFile(filePath: string, batchSize: number = DEFAULT_BATCH_SIZE) {
const client = new Client({ node: ELASTICSEARCH_NODE });
console.log(`📚 Hasher Indexer`);
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Elasticsearch: ${ELASTICSEARCH_NODE}`);
console.log(`Index: ${INDEX_NAME}`);
console.log(`File: ${filePath}`);
console.log(`Batch size: ${batchSize}`);
console.log('');
try {
// Test connection
console.log('🔗 Connecting to Elasticsearch...');
await client.cluster.health({});
console.log('✅ Connected successfully\n');
// Process file line by line using streams
console.log('📖 Processing file...\n');
const absolutePath = resolve(filePath);
let totalLines = 0;
let indexed = 0;
let skipped = 0;
let errors = 0;
const startTime = Date.now();
let currentBatch: string[] = [];
const fileStream = createReadStream(absolutePath, { encoding: 'utf-8' });
const rl = createInterface({
input: fileStream,
crlfDelay: Infinity
});
const processBatch = async (batch: string[]) => {
if (batch.length === 0) return;
const bulkOperations: any[] = [];
// Generate hashes for all items in batch first
const batchWithHashes = await Promise.all(
batch.map(async (plaintext: string) => ({
plaintext,
hashes: await generateHashes(plaintext)
}))
);
// Check which items already exist (by plaintext or any hash)
const md5List = batchWithHashes.map((item: any) => item.hashes.md5);
const sha1List = batchWithHashes.map((item: any) => item.hashes.sha1);
const sha256List = batchWithHashes.map((item: any) => item.hashes.sha256);
const sha512List = batchWithHashes.map((item: any) => item.hashes.sha512);
const existingCheck = await client.search({
index: INDEX_NAME,
size: batchSize * 5,
query: {
bool: {
should: [
{ terms: { 'plaintext.keyword': batch } },
{ terms: { md5: md5List } },
{ terms: { sha1: sha1List } },
{ terms: { sha256: sha256List } },
{ terms: { sha512: sha512List } },
],
minimum_should_match: 1
}
},
_source: ['plaintext', 'md5', 'sha1', 'sha256', 'sha512']
});
// Create a set of existing hashes for quick lookup
const existingHashes = new Set<string>();
existingCheck.hits.hits.forEach((hit: any) => {
const src = hit._source;
existingHashes.add(src.plaintext);
existingHashes.add(src.md5);
existingHashes.add(src.sha1);
existingHashes.add(src.sha256);
existingHashes.add(src.sha512);
});
// Prepare bulk operations only for items that don't have any duplicate hash
for (const item of batchWithHashes) {
const isDuplicate =
existingHashes.has(item.plaintext) ||
existingHashes.has(item.hashes.md5) ||
existingHashes.has(item.hashes.sha1) ||
existingHashes.has(item.hashes.sha256) ||
existingHashes.has(item.hashes.sha512);
if (!isDuplicate) {
bulkOperations.push({ index: { _index: INDEX_NAME } });
bulkOperations.push(item.hashes);
} else {
skipped++;
}
}
// Execute bulk operation only if there are new items to insert
if (bulkOperations.length > 0) {
try {
const bulkResponse = await client.bulk({
operations: bulkOperations,
refresh: false
});
if (bulkResponse.errors) {
const errorCount = bulkResponse.items.filter((item: any) => item.index?.error).length;
errors += errorCount;
indexed += (bulkOperations.length / 2) - errorCount;
} else {
indexed += bulkOperations.length / 2;
}
} catch (error) {
console.error(`\n❌ Error processing batch:`, error);
errors += bulkOperations.length / 2;
}
}
// Progress indicator
process.stdout.write(`\r⏳ Processed: ${totalLines} - Indexed: ${indexed}, Skipped: ${skipped}, Errors: ${errors}`);
};
for await (const line of rl) {
const trimmedLine = line.trim();
if (trimmedLine.length > 0) {
// Only take first word (no spaces or separators)
const firstWord = trimmedLine.split(/\s+/)[0];
if (firstWord) {
totalLines++;
currentBatch.push(firstWord);
if (currentBatch.length >= batchSize) {
await processBatch(currentBatch);
currentBatch = [];
}
}
}
}
// Process remaining items in last batch
if (currentBatch.length > 0) {
await processBatch(currentBatch);
}
// Refresh index
console.log('\n\n🔄 Refreshing index...');
await client.indices.refresh({ index: INDEX_NAME });
const duration = ((Date.now() - startTime) / 1000).toFixed(2);
const rate = (indexed / parseFloat(duration)).toFixed(0);
console.log('\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
console.log('✅ Indexing complete!');
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Total processed: ${totalLines}`);
console.log(`Successfully indexed: ${indexed}`);
console.log(`Skipped (duplicates): ${skipped}`);
console.log(`Errors: ${errors}`);
console.log(`Duration: ${duration}s`);
console.log(`Rate: ${rate} docs/sec`);
console.log('');
} catch (error) {
console.error('\n❌ Error:', error instanceof Error ? error.message : error);
process.exit(1);
}
}
// Parse command line arguments
const args = process.argv.slice(2);
if (args.length === 0 || args.includes('--help') || args.includes('-h')) {
showHelp();
}
const filePath = args[0];
const batchSizeIndex = args.indexOf('--batch-size');
const batchSize = batchSizeIndex !== -1 && args[batchSizeIndex + 1]
? parseInt(args[batchSizeIndex + 1], 10)
: DEFAULT_BATCH_SIZE;
indexFile(filePath, batchSize).catch(console.error);