Comparar commits

...

5 Commits

Autor SHA1 Mensaje Fecha
ale
b91d19dc0b fix memory remove dup
Signed-off-by: ale <ale@manalejandro.com>
2025-12-21 22:36:31 +01:00
ale
da89037125 out useRouter
Signed-off-by: ale <ale@manalejandro.com>
2025-12-11 00:46:59 +01:00
ale
20f0503134 fix share link
Signed-off-by: ale <ale@manalejandro.com>
2025-12-08 23:11:25 +01:00
ale
42bc5a15d0 sanitize nosql
Signed-off-by: ale <ale@manalejandro.com>
2025-12-08 23:08:38 +01:00
ale
2de78b7461 share link
Signed-off-by: ale <ale@manalejandro.com>
2025-12-08 23:08:24 +01:00
Se han modificado 3 ficheros con 363 adiciones y 118 borrados

Ver fichero

@@ -11,13 +11,101 @@ interface HashDocument {
created_at?: string;
}
// Maximum allowed query length
const MAX_QUERY_LENGTH = 1000;
// Characters that could be used in NoSQL/Elasticsearch injection attacks
const DANGEROUS_PATTERNS = [
/[{}\[\]]/g, // JSON structure characters
/\$[a-zA-Z]/g, // MongoDB-style operators
/\\u[0-9a-fA-F]{4}/g, // Unicode escapes
/<script/gi, // XSS attempts
/javascript:/gi, // XSS attempts
];
/**
* Sanitize input to prevent NoSQL injection attacks
* For hash lookups, we only need alphanumeric characters and $
* For plaintext, we allow more characters but sanitize dangerous patterns
*/
function sanitizeInput(input: string): string {
// Trim and take first word only
let sanitized = input.trim().split(/\s+/)[0] || '';
// Limit length
if (sanitized.length > MAX_QUERY_LENGTH) {
sanitized = sanitized.substring(0, MAX_QUERY_LENGTH);
}
// Remove null bytes
sanitized = sanitized.replace(/\0/g, '');
// Check for dangerous patterns
for (const pattern of DANGEROUS_PATTERNS) {
sanitized = sanitized.replace(pattern, '');
}
return sanitized;
}
/**
* Validate that the input is safe for use in Elasticsearch queries
*/
function isValidInput(input: string): boolean {
// Check for empty input
if (!input || input.length === 0) {
return false;
}
// Check for excessively long input
if (input.length > MAX_QUERY_LENGTH) {
return false;
}
// Check for control characters (except normal whitespace)
if (/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]/.test(input)) {
return false;
}
return true;
}
export async function POST(request: NextRequest) {
try {
const { query } = await request.json();
const body = await request.json();
// Validate request body structure
if (!body || typeof body !== 'object') {
return NextResponse.json(
{ error: 'Invalid request body' },
{ status: 400 }
);
}
const { query } = body;
// Validate query type
if (!query || typeof query !== 'string') {
return NextResponse.json(
{ error: 'Query parameter is required' },
{ error: 'Query parameter is required and must be a string' },
{ status: 400 }
);
}
// Validate input before processing
if (!isValidInput(query)) {
return NextResponse.json(
{ error: 'Invalid query: contains forbidden characters or is too long' },
{ status: 400 }
);
}
// Sanitize input
const cleanQuery = sanitizeInput(query);
if (!cleanQuery) {
return NextResponse.json(
{ error: 'Invalid query: only whitespace or invalid characters provided' },
{ status: 400 }
);
}
@@ -25,15 +113,6 @@ export async function POST(request: NextRequest) {
// Ensure index exists
await initializeIndex();
const cleanQuery = query.trim().split(/\s+/)[0];
if (!cleanQuery) {
return NextResponse.json(
{ error: 'Invalid query: only whitespace provided' },
{ status: 400 }
);
}
const cleanQueryLower = cleanQuery.toLowerCase();
const hashType = detectHashType(cleanQueryLower);

Ver fichero

@@ -1,7 +1,8 @@
'use client';
import { useState, useEffect } from 'react';
import { Search, Copy, Check, Hash, Key, AlertCircle, Loader2, Database } from 'lucide-react';
import { useState, useEffect, useCallback, Suspense } from 'react';
import { useSearchParams } from 'next/navigation';
import { Search, Copy, Check, Hash, Key, AlertCircle, Loader2, Database, Link } from 'lucide-react';
interface SearchResult {
found: boolean;
@@ -45,13 +46,62 @@ function formatNumber(num: number): string {
return num.toLocaleString();
}
export default function Home() {
function HasherContent() {
const searchParams = useSearchParams();
const [query, setQuery] = useState('');
const [result, setResult] = useState<SearchResult | null>(null);
const [loading, setLoading] = useState(false);
const [error, setError] = useState('');
const [copiedField, setCopiedField] = useState<string | null>(null);
const [stats, setStats] = useState<IndexStats | null>(null);
const [copiedLink, setCopiedLink] = useState(false);
const [initialLoadDone, setInitialLoadDone] = useState(false);
const performSearch = useCallback(async (searchQuery: string, updateUrl: boolean = true) => {
if (!searchQuery.trim()) return;
setLoading(true);
setError('');
setResult(null);
try {
const response = await fetch('/api/search', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ query: searchQuery.trim() })
});
if (!response.ok) {
throw new Error('Search failed');
}
const data = await response.json();
setResult(data);
// Update URL with search query (using history API to avoid re-triggering effects)
if (updateUrl) {
const newUrl = new URL(window.location.href);
newUrl.searchParams.set('q', searchQuery.trim());
window.history.replaceState(null, '', newUrl.pathname + newUrl.search);
}
} catch (_err) {
setError('Failed to perform search. Please check your connection.');
} finally {
setLoading(false);
}
}, []);
// Load query from URL on mount (only once)
useEffect(() => {
if (initialLoadDone) return;
const urlQuery = searchParams.get('q');
if (urlQuery) {
setQuery(urlQuery);
performSearch(urlQuery, false);
}
setInitialLoadDone(true);
}, [searchParams, performSearch, initialLoadDone]);
useEffect(() => {
const fetchStats = async () => {
@@ -73,30 +123,7 @@ export default function Home() {
const handleSearch = async (e: React.FormEvent) => {
e.preventDefault();
if (!query.trim()) return;
setLoading(true);
setError('');
setResult(null);
try {
const response = await fetch('/api/search', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ query: query.trim() })
});
if (!response.ok) {
throw new Error('Search failed');
}
const data = await response.json();
setResult(data);
} catch (_err) {
setError('Failed to perform search. Please check your connection.');
} finally {
setLoading(false);
}
performSearch(query);
};
const copyToClipboard = (text: string, field: string) => {
@@ -105,6 +132,14 @@ export default function Home() {
setTimeout(() => setCopiedField(null), 2000);
};
const copyShareLink = () => {
const url = new URL(window.location.href);
url.searchParams.set('q', query.trim());
navigator.clipboard.writeText(url.toString());
setCopiedLink(true);
setTimeout(() => setCopiedLink(false), 2000);
};
const HashDisplay = ({ label, value, field }: { label: string; value: string; field: string }) => (
<div className="bg-gray-50 rounded-lg p-4 border border-gray-200">
<div className="flex items-center justify-between mb-2">
@@ -166,19 +201,35 @@ export default function Home() {
value={query}
onChange={(e) => setQuery(e.target.value)}
placeholder="Enter a hash or plaintext..."
className="w-full px-6 py-4 pr-14 text-lg rounded-2xl border-2 border-gray-200 focus:border-blue-500 focus:ring-4 focus:ring-blue-100 outline-none transition-all shadow-sm"
className="w-full px-6 py-4 pr-28 text-lg rounded-2xl border-2 border-gray-200 focus:border-blue-500 focus:ring-4 focus:ring-blue-100 outline-none transition-all shadow-sm"
/>
<button
type="submit"
disabled={loading || !query.trim()}
className="absolute right-2 top-1/2 -translate-y-1/2 bg-gradient-to-r from-blue-600 to-purple-600 text-white p-3 rounded-xl hover:shadow-lg disabled:opacity-50 disabled:cursor-not-allowed transition-all"
>
{loading ? (
<Loader2 className="w-6 h-6 animate-spin" />
) : (
<Search className="w-6 h-6" />
<div className="absolute right-2 top-1/2 -translate-y-1/2 flex gap-1">
{query.trim() && (
<button
type="button"
onClick={copyShareLink}
className="bg-gray-100 text-gray-600 p-3 rounded-xl hover:bg-gray-200 transition-all"
title="Copy share link"
>
{copiedLink ? (
<Check className="w-6 h-6 text-green-600" />
) : (
<Link className="w-6 h-6" />
)}
</button>
)}
</button>
<button
type="submit"
disabled={loading || !query.trim()}
className="bg-gradient-to-r from-blue-600 to-purple-600 text-white p-3 rounded-xl hover:shadow-lg disabled:opacity-50 disabled:cursor-not-allowed transition-all"
>
{loading ? (
<Loader2 className="w-6 h-6 animate-spin" />
) : (
<Search className="w-6 h-6" />
)}
</button>
</div>
</div>
</form>
@@ -315,3 +366,19 @@ export default function Home() {
);
}
function LoadingFallback() {
return (
<div className="min-h-screen bg-gradient-to-br from-blue-50 via-white to-purple-50 flex items-center justify-center">
<Loader2 className="w-12 h-12 text-blue-600 animate-spin" />
</div>
);
}
export default function Home() {
return (
<Suspense fallback={<LoadingFallback />}>
<HasherContent />
</Suspense>
);
}

Ver fichero

@@ -225,50 +225,166 @@ async function findDuplicatesForField(
return duplicates;
}
async function removeDuplicates(parsedArgs: ParsedArgs) {
/**
* Phase 1: Initialize and connect to Elasticsearch
*/
async function phase1_InitAndConnect() {
console.log(`🔍 Hasher Duplicate Remover - Phase 1: Initialization`);
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Elasticsearch: ${ELASTICSEARCH_NODE}`);
console.log(`Index: ${INDEX_NAME}`);
console.log('');
const client = new Client({ node: ELASTICSEARCH_NODE });
console.log('🔗 Connecting to Elasticsearch...');
await client.cluster.health({});
console.log('✅ Connected successfully\n');
const countResponse = await client.count({ index: INDEX_NAME });
console.log(`📊 Total documents in index: ${countResponse.count}\n`);
return { client, totalDocuments: countResponse.count };
}
/**
* Phase 2: Find duplicates for a specific field
*/
async function phase2_FindDuplicatesForField(
client: Client,
field: string,
batchSize: number,
seenDeleteIds: Set<string>
): Promise<{ duplicates: DuplicateGroup[], totalFound: number }> {
console.log(`\n🔍 Phase 2: Checking duplicates for field: ${field}...`);
const fieldDuplicates = await findDuplicatesForField(client, field, batchSize);
const duplicates: DuplicateGroup[] = [];
// Filter out already seen delete IDs to avoid counting the same document multiple times
for (const dup of fieldDuplicates) {
const newDeleteIds = dup.deleteIds.filter(id => !seenDeleteIds.has(id));
if (newDeleteIds.length > 0) {
dup.deleteIds = newDeleteIds;
newDeleteIds.forEach(id => seenDeleteIds.add(id));
duplicates.push(dup);
}
}
console.log(` Found ${fieldDuplicates.length} duplicate groups for ${field}`);
console.log(` New unique documents to delete: ${duplicates.reduce((sum, dup) => sum + dup.deleteIds.length, 0)}`);
// Force garbage collection if available
if (global.gc) {
global.gc();
console.log(` ♻️ Memory freed after processing ${field}`);
}
return { duplicates, totalFound: fieldDuplicates.length };
}
/**
* Phase 3: Process deletion for a batch of duplicates
*/
async function phase3_DeleteBatch(
client: Client,
deleteIds: string[],
batchSize: number,
startIndex: number
): Promise<{ deleted: number, errors: number }> {
const batch = deleteIds.slice(startIndex, startIndex + batchSize);
let deleted = 0;
let errors = 0;
try {
const bulkOperations = batch.flatMap(id => [
{ delete: { _index: INDEX_NAME, _id: id } }
]);
const bulkResponse = await client.bulk({
operations: bulkOperations,
refresh: false
});
if (bulkResponse.errors) {
const errorCount = bulkResponse.items.filter((item: any) => item.delete?.error).length;
errors += errorCount;
deleted += batch.length - errorCount;
} else {
deleted += batch.length;
}
} catch (error) {
console.error(`\n❌ Error deleting batch:`, error);
errors += batch.length;
}
// Force garbage collection if available
if (global.gc) {
global.gc();
}
return { deleted, errors };
}
/**
* Phase 4: Finalize and report results
*/
async function phase4_Finalize(
client: Client,
totalDeleted: number,
totalErrors: number,
initialDocumentCount: number
) {
console.log('\n\n🔄 Phase 4: Refreshing index...');
await client.indices.refresh({ index: INDEX_NAME });
const newCountResponse = await client.count({ index: INDEX_NAME });
console.log('\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
console.log('✅ Duplicate removal complete!');
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Documents deleted: ${totalDeleted}`);
console.log(`Errors: ${totalErrors}`);
console.log(`Previous document count: ${initialDocumentCount}`);
console.log(`New document count: ${newCountResponse.count}`);
console.log('');
}
async function removeDuplicates(parsedArgs: ParsedArgs) {
const fields = parsedArgs.field
? [parsedArgs.field]
: ['plaintext', 'md5', 'sha1', 'sha256', 'sha512'];
console.log(`🔍 Hasher Duplicate Remover`);
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Elasticsearch: ${ELASTICSEARCH_NODE}`);
console.log(`Index: ${INDEX_NAME}`);
console.log(`Mode: ${parsedArgs.dryRun ? '🔎 DRY RUN (no changes)' : '⚠️ EXECUTE (will delete)'}`);
console.log(`Batch size: ${parsedArgs.batchSize}`);
console.log(`Fields to check: ${fields.join(', ')}`);
console.log('');
try {
// Test connection
console.log('🔗 Connecting to Elasticsearch...');
await client.cluster.health({});
console.log('✅ Connected successfully\n');
// Get index stats
const countResponse = await client.count({ index: INDEX_NAME });
console.log(`📊 Total documents in index: ${countResponse.count}\n`);
// === PHASE 1: Initialize ===
const { client, totalDocuments } = await phase1_InitAndConnect();
// Force garbage collection after phase 1
if (global.gc) {
global.gc();
console.log('♻️ Memory freed after initialization\n');
}
// === PHASE 2: Find duplicates field by field ===
const allDuplicates: DuplicateGroup[] = [];
const seenDeleteIds = new Set<string>();
// Find duplicates for each field
for (const field of fields) {
console.log(`🔍 Checking duplicates for field: ${field}...`);
const fieldDuplicates = await findDuplicatesForField(client, field, parsedArgs.batchSize);
const { duplicates } = await phase2_FindDuplicatesForField(
client,
field,
parsedArgs.batchSize,
seenDeleteIds
);
allDuplicates.push(...duplicates);
// Filter out already seen delete IDs to avoid counting the same document multiple times
for (const dup of fieldDuplicates) {
const newDeleteIds = dup.deleteIds.filter(id => !seenDeleteIds.has(id));
if (newDeleteIds.length > 0) {
dup.deleteIds = newDeleteIds;
newDeleteIds.forEach(id => seenDeleteIds.add(id));
allDuplicates.push(dup);
}
}
console.log(` Found ${fieldDuplicates.length} duplicate groups for ${field}`);
// Clear field duplicates to free memory
duplicates.length = 0;
}
const totalToDelete = allDuplicates.reduce((sum, dup) => sum + dup.deleteIds.length, 0);
@@ -310,57 +426,40 @@ async function removeDuplicates(parsedArgs: ParsedArgs) {
return;
}
// Execute deletion
console.log(`\n🗑 Removing ${totalToDelete} duplicate documents...\n`);
// === PHASE 3: Execute deletion in batches ===
console.log(`\n🗑 Phase 3: Removing ${totalToDelete} duplicate documents...\n`);
let deleted = 0;
let errors = 0;
let totalDeleted = 0;
let totalErrors = 0;
const deleteIds = allDuplicates.flatMap(dup => dup.deleteIds);
// Delete in batches
// Clear allDuplicates to free memory
allDuplicates.length = 0;
// Delete in batches with memory management
for (let i = 0; i < deleteIds.length; i += parsedArgs.batchSize) {
const batch = deleteIds.slice(i, i + parsedArgs.batchSize);
const { deleted, errors } = await phase3_DeleteBatch(
client,
deleteIds,
parsedArgs.batchSize,
i
);
try {
const bulkOperations = batch.flatMap(id => [
{ delete: { _index: INDEX_NAME, _id: id } }
]);
totalDeleted += deleted;
totalErrors += errors;
const bulkResponse = await client.bulk({
operations: bulkOperations,
refresh: false
});
if (bulkResponse.errors) {
const errorCount = bulkResponse.items.filter((item: any) => item.delete?.error).length;
errors += errorCount;
deleted += batch.length - errorCount;
} else {
deleted += batch.length;
}
process.stdout.write(`\r⏳ Progress: ${Math.min(i + parsedArgs.batchSize, deleteIds.length)}/${deleteIds.length} - Deleted: ${deleted}, Errors: ${errors}`);
} catch (error) {
console.error(`\n❌ Error deleting batch:`, error);
errors += batch.length;
}
process.stdout.write(
`\r⏳ Progress: ${Math.min(i + parsedArgs.batchSize, deleteIds.length)}/${deleteIds.length} - ` +
`Deleted: ${totalDeleted}, Errors: ${totalErrors}`
);
}
// Refresh index
console.log('\n\n🔄 Refreshing index...');
await client.indices.refresh({ index: INDEX_NAME });
// Clear deleteIds to free memory
deleteIds.length = 0;
seenDeleteIds.clear();
// Get new count
const newCountResponse = await client.count({ index: INDEX_NAME });
console.log('\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
console.log('✅ Duplicate removal complete!');
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
console.log(`Documents deleted: ${deleted}`);
console.log(`Errors: ${errors}`);
console.log(`Previous document count: ${countResponse.count}`);
console.log(`New document count: ${newCountResponse.count}`);
console.log('');
// === PHASE 4: Finalize ===
await phase4_Finalize(client, totalDeleted, totalErrors, totalDocuments);
} catch (error) {
console.error('\n❌ Error:', error instanceof Error ? error.message : error);