egutierrez
6526da32dc
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>
64 lines
1.8 KiB
Python
64 lines
1.8 KiB
Python
"""Extrae numeros de telefono (E.164 + formatos comunes ES/EU) con offsets."""
|
|
|
|
import re
|
|
|
|
# E.164: + seguido de 8 a 15 digitos, opcionalmente con espacios/guiones internos.
|
|
_E164_REGEX = re.compile(
|
|
r"(?<![A-Za-z0-9])"
|
|
r"\+\d{1,3}[\s\-]?\d{1,4}(?:[\s\-]?\d{1,4}){1,4}"
|
|
r"(?![A-Za-z0-9])"
|
|
)
|
|
# ES: 9 digitos empezando por 6, 7, 8 o 9 (movil/fijo).
|
|
_ES_LOCAL_REGEX = re.compile(
|
|
r"(?<![A-Za-z0-9+])"
|
|
r"[6789]\d{2}[\s\-]?\d{3}[\s\-]?\d{3}"
|
|
r"(?![A-Za-z0-9])"
|
|
)
|
|
|
|
|
|
def extract_phone_numbers(text: str) -> list[dict]:
|
|
"""Extrae numeros de telefono E.164 y formato local ES de 9 digitos.
|
|
|
|
Acepta separadores `space`, `-` entre grupos. E.164 requiere `+` y
|
|
entre 8 y 15 digitos (ITU-T). Formato local ES son 9 digitos que
|
|
empiezan por 6/7/8/9. Tras quitar separadores se valida la longitud
|
|
minima.
|
|
"""
|
|
seen_spans = set()
|
|
results = []
|
|
|
|
for m in _E164_REGEX.finditer(text):
|
|
candidate = m.group(0)
|
|
digits = re.sub(r"[^0-9]", "", candidate)
|
|
if not (8 <= len(digits) <= 15):
|
|
continue
|
|
span = (m.start(), m.end())
|
|
if span in seen_spans:
|
|
continue
|
|
seen_spans.add(span)
|
|
results.append({
|
|
"value": candidate,
|
|
"start": m.start(),
|
|
"end": m.end(),
|
|
"type": "phone_number",
|
|
})
|
|
|
|
for m in _ES_LOCAL_REGEX.finditer(text):
|
|
candidate = m.group(0)
|
|
digits = re.sub(r"[^0-9]", "", candidate)
|
|
if len(digits) != 9:
|
|
continue
|
|
span = (m.start(), m.end())
|
|
if span in seen_spans:
|
|
continue
|
|
seen_spans.add(span)
|
|
results.append({
|
|
"value": candidate,
|
|
"start": m.start(),
|
|
"end": m.end(),
|
|
"type": "phone_number",
|
|
})
|
|
|
|
results.sort(key=lambda r: r["start"])
|
|
return results
|