-- =============================================================================
-- 11_views.sql — Vues métier du dashboard
--
-- Ce fichier crée les vues référencées par le dashboard mais absentes du schéma
-- partagé. Ces vues agrègent les données de agg_host_ip_ja4_1h et http_logs
-- pour fournir des perspectives métier aux endpoints FastAPI.
--
-- Vues créées :
--   view_form_bruteforce_detected  — IPs/hôtes avec fort volume de requêtes POST
--   view_host_ip_ja4_rotation      — IPs changeant de fingerprint JA4 (évasion)
--   view_dashboard_entities        — Pivot IP/JA4/pays/ASN/host pour investigation
--   view_dashboard_user_agents     — User-Agents agrégés par IP/JA4/heure
--   view_dashboard_summary         — Métriques globales 24h (si pas déjà créée)
-- =============================================================================


-- -----------------------------------------------------------------------------
-- view_form_bruteforce_detected
--
-- Détecte les IPs effectuant des attaques par force brute sur des formulaires :
--   - Volume élevé de requêtes POST vers un hôte donné (≥ 10 POST/heure)
--   - Fenêtre glissante 24h depuis agg_host_ip_ja4_1h
--
-- Colonnes :
--   src_ip, host, ja4, hits, post_count, distinct_paths, first_seen, last_seen
-- -----------------------------------------------------------------------------
CREATE OR REPLACE VIEW ja4_processing.view_form_bruteforce_detected AS
SELECT
    src_ip,
    host,
    argMax(ja4, ja4_hits)  AS ja4,
    sum(ja4_hits)          AS hits,
    sum(ja4_posts)         AS post_count,
    sum(ja4_posts)         AS query_params_count,
    count()                AS distinct_paths,
    min(w_min)             AS first_seen,
    max(w_max)             AS last_seen
FROM (
    SELECT
        src_ip, host, ja4,
        sum(hits)         AS ja4_hits,
        sum(count_post)   AS ja4_posts,
        min(window_start) AS w_min,
        max(window_start) AS w_max
    FROM ja4_processing.agg_host_ip_ja4_1h
    WHERE window_start >= now() - INTERVAL 24 HOUR
    GROUP BY src_ip, host, ja4
) sub
GROUP BY src_ip, host
HAVING post_count >= 10;


-- -----------------------------------------------------------------------------
-- view_host_ip_ja4_rotation
--
-- Détecte les IPs qui changent de fingerprint JA4 (rotation de TLS ClientHello)
-- — indicateur d'évasion de détection par les outils de bot.
--
-- Colonnes :
--   src_ip, host, distinct_ja4, distinct_ja4_count, ja4_list,
--   total_hits, window_start, first_seen, last_seen
-- -----------------------------------------------------------------------------
CREATE OR REPLACE VIEW ja4_processing.view_host_ip_ja4_rotation AS
SELECT
    src_ip,
    argMax(host, ja4_hits)   AS host,
    count()                  AS distinct_ja4,
    count()                  AS distinct_ja4_count,
    groupArray(ja4)          AS ja4_list,
    sum(ja4_hits)            AS total_hits,
    max(w_max)               AS window_start,
    min(w_min)               AS first_seen,
    max(w_max)               AS last_seen
FROM (
    SELECT
        src_ip, host, ja4,
        sum(hits)         AS ja4_hits,
        min(window_start) AS w_min,
        max(window_start) AS w_max
    FROM ja4_processing.agg_host_ip_ja4_1h
    WHERE window_start >= now() - INTERVAL 24 HOUR
      AND ja4 != ''
    GROUP BY src_ip, host, ja4
) sub
GROUP BY src_ip
HAVING distinct_ja4 >= 2
ORDER BY distinct_ja4 DESC;


-- -----------------------------------------------------------------------------
-- view_dashboard_user_agents
--
-- Agrégation des User-Agents par IP, JA4 et heure.
-- Utilisée par variability.py et attributes.py avec ARRAY JOIN user_agents.
--
-- Colonnes :
--   src_ip       — IPv4 (sans préfixe ::ffff:)
--   ja4          — Fingerprint TLS
--   hour         — Début d'heure (toStartOfHour)
--   log_date     — Date (pour le TTL de la vue)
--   user_agents  — Array(String) des UAs distincts sur cette heure
--   requests     — Nombre total de requêtes sur cette heure
-- -----------------------------------------------------------------------------
CREATE OR REPLACE VIEW ja4_processing.view_dashboard_user_agents AS
SELECT
    -- Normalisation IPv4 : supprime le préfixe ::ffff: des IPs mappées IPv6→IPv4
    toIPv4OrZero(replaceRegexpAll(toString(src_ip), '^::ffff:', ''))   AS src_ip,
    ja4,
    toStartOfHour(time)                                                AS hour,
    log_date,
    -- Collecte les UAs distincts (max 100 pour éviter les tableaux géants)
    groupUniqArray(100)(header_user_agent)                             AS user_agents,
    count()                                                            AS requests
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY
  AND header_user_agent != ''
GROUP BY src_ip, ja4, toStartOfHour(time), log_date;


-- -----------------------------------------------------------------------------
-- view_dashboard_entities
--
-- Vue pivot permettant de naviguer entre entités (IP ↔ JA4 ↔ pays ↔ ASN ↔ hôte).
-- Pour chaque entité (entity_type + entity_value), expose les données associées :
--   ips, ja4s, hosts (via GROUP BY en Python), asns, countries, user_agents,
--   client_headers (array pour clustering.py).
--
-- Structure UNION ALL : une branche par type d'entité.
-- ClickHouse optimise les requêtes WHERE entity_type = 'ip' en éliminant
-- les autres branches (condition constante sur colonne calculée).
--
-- Colonnes :
--   entity_type    — 'ip' | 'ja4' | 'country' | 'asn' | 'host'
--   entity_value   — Valeur de l'entité (ex: '1.2.3.4', 't13d...', 'FR', ...)
--   src_ip         — IPv6 (format natif ClickHouse)
--   ja4            — Fingerprint JA4
--   host           — Virtual host HTTP
--   log_date       — Date de la requête
--   client_headers — Array des noms de headers (splitByChar depuis http_logs)
--   asns           — Array(String) avec l'ASN source (pour groupUniqArrayArray)
--   countries      — Array(String) avec le code pays source
--   user_agents    — Array(String) avec le User-Agent
-- -----------------------------------------------------------------------------
CREATE OR REPLACE VIEW ja4_processing.view_dashboard_entities AS

-- Perspective IP : entity_value = adresse IPv4 de la source
SELECT
    'ip'                                                                     AS entity_type,
    replaceRegexpAll(toString(src_ip), '^::ffff:', '')                       AS entity_value,
    src_ip,
    ja4,
    host,
    log_date,
    splitByChar(',', client_headers)                                         AS client_headers,
    [toString(src_asn)]                                                      AS asns,
    [src_country_code]                                                       AS countries,
    [header_user_agent]                                                      AS user_agents
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY

UNION ALL

-- Perspective JA4 : entity_value = fingerprint TLS JA4
SELECT
    'ja4'                                                                    AS entity_type,
    ja4                                                                      AS entity_value,
    src_ip,
    ja4,
    host,
    log_date,
    splitByChar(',', client_headers)                                         AS client_headers,
    [toString(src_asn)]                                                      AS asns,
    [src_country_code]                                                       AS countries,
    [header_user_agent]                                                      AS user_agents
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY
  AND ja4 != ''

UNION ALL

-- Perspective pays : entity_value = code pays ISO-3166 (ex: 'FR', 'US')
SELECT
    'country'                                                                AS entity_type,
    src_country_code                                                         AS entity_value,
    src_ip,
    ja4,
    host,
    log_date,
    splitByChar(',', client_headers)                                         AS client_headers,
    [toString(src_asn)]                                                      AS asns,
    [src_country_code]                                                       AS countries,
    [header_user_agent]                                                      AS user_agents
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY
  AND src_country_code != ''

UNION ALL

-- Perspective ASN : entity_value = numéro ASN (ex: '15169' pour Google)
SELECT
    'asn'                                                                    AS entity_type,
    toString(src_asn)                                                        AS entity_value,
    src_ip,
    ja4,
    host,
    log_date,
    splitByChar(',', client_headers)                                         AS client_headers,
    [toString(src_asn)]                                                      AS asns,
    [src_country_code]                                                       AS countries,
    [header_user_agent]                                                      AS user_agents
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY
  AND src_asn > 0

UNION ALL

-- Perspective hôte : entity_value = virtual host HTTP (ex: 'api.example.com')
SELECT
    'host'                                                                   AS entity_type,
    host                                                                     AS entity_value,
    src_ip,
    ja4,
    host,
    log_date,
    splitByChar(',', client_headers)                                         AS client_headers,
    [toString(src_asn)]                                                      AS asns,
    [src_country_code]                                                       AS countries,
    [header_user_agent]                                                      AS user_agents
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 7 DAY
  AND host != '';