egutierrez
cce7764510
Extractores nuevos en python/functions/cybersecurity/: - extract_ip_addresses (IPv4 + IPv6 con validacion ipaddress) - extract_emails (RFC 5322 simplificado) - extract_domains (FQDNs con TLD valido, lista estatica) - extract_file_hashes (MD5/SHA1/SHA256/SHA512, algoritmo por longitud) - extract_crypto_wallets (BTC legacy + bech32, ETH 0x+40hex) - extract_cve_ids (CVE-YYYY-NNNN+) - extract_mac_addresses (xx:xx:xx + xx-xx-xx, separador uniforme) - extract_phone_numbers (E.164 + ES local 9 digitos) Pipeline: - extract_iocs corre todos, deduplica spans contenidos. Mantiene purity:pure (kind:function con uses_functions no vacio) porque la regla del registry exige que los pipelines sean impuros. Todas devuelven list[dict] con value/start/end/type para que el caller (issues 0038-0040) pueda reconciliar offsets con spans NER sin reparsing. Refs #0037 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
54 lines
1.4 KiB
Python
54 lines
1.4 KiB
Python
"""Extrae IPv4 + IPv6 validas de un texto, con offsets."""
|
|
|
|
import ipaddress
|
|
import re
|
|
|
|
_IPV4_CANDIDATE = re.compile(r"\b\d{1,3}(?:\.\d{1,3}){3}\b")
|
|
_IPV6_CANDIDATE = re.compile(
|
|
r"(?<![0-9A-Fa-f:])"
|
|
r"(?:[0-9A-Fa-f]{0,4}:){2,7}[0-9A-Fa-f]{0,4}"
|
|
r"(?:%[0-9A-Za-z]+)?"
|
|
r"(?![0-9A-Fa-f:])"
|
|
)
|
|
|
|
|
|
def extract_ip_addresses(text: str) -> list[dict]:
|
|
"""Extrae IPv4 e IPv6 validas con offsets.
|
|
|
|
Filtra candidatos que no parsean como IP valida con `ipaddress`. No
|
|
distingue IP privadas (10.x, 192.168.x) de publicas — el filtrado de
|
|
relevancia es responsabilidad del caller.
|
|
"""
|
|
results: list[dict] = []
|
|
|
|
for m in _IPV4_CANDIDATE.finditer(text):
|
|
candidate = m.group(0)
|
|
try:
|
|
ipaddress.IPv4Address(candidate)
|
|
except ValueError:
|
|
continue
|
|
results.append({
|
|
"value": candidate,
|
|
"start": m.start(),
|
|
"end": m.end(),
|
|
"type": "ip_address",
|
|
})
|
|
|
|
for m in _IPV6_CANDIDATE.finditer(text):
|
|
candidate = m.group(0).split("%", 1)[0]
|
|
if candidate.count(":") < 2:
|
|
continue
|
|
try:
|
|
ipaddress.IPv6Address(candidate)
|
|
except ValueError:
|
|
continue
|
|
results.append({
|
|
"value": m.group(0),
|
|
"start": m.start(),
|
|
"end": m.end(),
|
|
"type": "ip_address",
|
|
})
|
|
|
|
results.sort(key=lambda r: r["start"])
|
|
return results
|