From f348a87a0b4a1716de19da67324e61294ecaca96 Mon Sep 17 00:00:00 2001
From: Xor290 <free6nk33@gmail.com>
Date: Tue, 21 Apr 2026 09:23:43 +0200
Subject: [PATCH] chore: add scripts

---
 scripts/import_adresse_correction.py | 197 +++++++++++++++++++++++++++
 scripts/import_clients.py            | 179 ++++++++++++++++++++++++
 scripts/import_users.py              | 162 ++++++++++++++++++++++
 3 files changed, 538 insertions(+)
 create mode 100644 scripts/import_adresse_correction.py
 create mode 100644 scripts/import_clients.py
 create mode 100644 scripts/import_users.py

diff --git a/scripts/import_adresse_correction.py b/scripts/import_adresse_correction.py
new file mode 100644
index 00000000..b8de9f72
--- /dev/null
+++ b/scripts/import_adresse_correction.py
@@ -0,0 +1,197 @@
+#!/usr/bin/env python3
+"""
+Import adresse_correction depuis data2.txt (format psql pipe-séparé, avec
+gestion des valeurs multi-lignes et des lignes fusionnées sans newline).
+Usage : python3 import_adresse_correction.py [--dry-run]
+"""
+
+import os
+import re
+import sys
+
+import psycopg2
+
+DB_CONFIG = {
+    "host": "localhost",
+    "port": 5432,
+    "user": "",
+    "password": "",
+    "dbname": "",
+}
+
+DATA_FILE = os.path.join(os.path.dirname(__file__), "data2.txt")
+DRY_RUN = "--dry-run" in sys.argv
+
+SOURCE_COLUMNS = [
+    "id",
+    "invalid_address",
+    "correct_address",
+    "created_at",
+    "updated_at",
+]
+
+
+def preprocess(content: str) -> list[str]:
+    """
+    Sépare les lignes physiquement fusionnées :
+    ex: "...2026-03-13 22:33:10.353601  79 | 55 Quai..." → deux lignes.
+    Pattern : timestamp immédiatement suivi (sans \n) d'un entier + '|'.
+    """
+    content = re.sub(
+        r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d+)\s{2,}(\d+\s*\|)",
+        r"\1\n \2",
+        content,
+    )
+    return content.splitlines()
+
+
+def parse_psql_rows(path: str) -> list[list[str]]:
+    """
+    Parse le format aligné psql :
+    - Lignes de continuation (sans id, commençant par '    |') : valeur multi-ligne.
+    - Champ se terminant par '+' avant '|' : continuation sur la ligne suivante.
+    """
+    with open(path, encoding="utf-8") as f:
+        raw = f.read()
+
+    lines = preprocess(raw)
+    rows: list[list[str]] = []
+    current: list[str] | None = None
+
+    for line in lines:
+        line = line.rstrip("\n")
+        stripped = line.strip()
+
+        # Ligne vide
+        if not stripped:
+            continue
+
+        # Ligne séparateur psql  (----+----)
+        if (
+            set(
+                stripped.replace("|", "")
+                .replace("+", "")
+                .replace("-", "")
+                .replace(" ", "")
+            )
+            == set()
+        ):
+            continue
+
+        parts = line.split("|")
+        if len(parts) < 2:
+            continue
+
+        first = parts[0].strip()
+        is_continuation = current is not None and (first == "" or not first.isdigit())
+
+        if is_continuation:
+            # Fusionner avec la ligne en cours
+            cont = parts[:-1] if parts[-1].strip() == "" else parts
+            for i, cf in enumerate(cont):
+                if i < len(current):
+                    prev = current[i].rstrip("+").rstrip()
+                    add = cf.strip()
+                    current[i] = (prev + (" " if prev and add else "") + add).strip()
+            continue
+
+        # Sauvegarder la ligne précédente
+        if current is not None:
+            rows.append(current)
+
+        # Nouvelle ligne de données : nettoyer le '+' de continuation
+        raw_fields = parts[:-1] if parts[-1].strip() == "" else parts
+        current = [f.strip().rstrip("+").strip() for f in raw_fields]
+
+    if current is not None:
+        rows.append(current)
+
+    return rows
+
+
+def parse_value(v: str):
+    v = v.strip()
+    if v == "" or v.lower() == "null":
+        return None
+    return v
+
+
+def main():
+    raw_rows = parse_psql_rows(DATA_FILE)
+    if not raw_rows:
+        print("❌ Aucune ligne trouvée dans data2.txt")
+        sys.exit(1)
+
+    # Filtrer l'en-tête éventuel
+    rows = [[parse_value(v) for v in r] for r in raw_rows if r[0].strip() != "id"]
+
+    print(f"📂 {len(rows)} lignes de données à importer depuis {DATA_FILE}")
+
+    insert_cols = [c for c in SOURCE_COLUMNS if c != "id"]
+    insert_cols_all = ["id"] + insert_cols
+    placeholders = ", ".join(["%s"] * len(insert_cols_all))
+    col_names = ", ".join(insert_cols_all)
+    update_expr = ", ".join(f"{c} = EXCLUDED.{c}" for c in insert_cols)
+
+    sql = f"""
+        INSERT INTO adresse_correction ({col_names})
+        VALUES ({placeholders})
+        ON CONFLICT (invalid_address) DO UPDATE SET {update_expr}
+    """
+
+    conn = psycopg2.connect(**DB_CONFIG)
+    conn.autocommit = False
+    cur = conn.cursor()
+
+    inserted = updated = errors = 0
+
+    for i, row in enumerate(rows, 1):
+        if len(row) < len(SOURCE_COLUMNS):
+            print(f"  ⚠️  Ligne {i} ignorée ({len(row)} champs) : {row}")
+            continue
+
+        row_dict = {SOURCE_COLUMNS[j]: row[j] for j in range(len(SOURCE_COLUMNS))}
+        values = [row_dict[c] for c in insert_cols_all]
+        inv_addr = row_dict.get("invalid_address", "?")
+
+        if DRY_RUN:
+            print(
+                f"  [DRY-RUN] {i:3}. {inv_addr!r} → {row_dict.get('correct_address')!r}"
+            )
+            inserted += 1
+            continue
+
+        try:
+            cur.execute(
+                "SELECT 1 FROM adresse_correction WHERE invalid_address = %s",
+                (inv_addr,),
+            )
+            exists = cur.fetchone() is not None
+            cur.execute(sql, values)
+            if exists:
+                updated += 1
+            else:
+                inserted += 1
+
+        except Exception as e:
+            print(f"  ❌ Erreur ligne {i} ({inv_addr!r}) : {e}")
+            conn.rollback()
+            errors += 1
+
+    if not DRY_RUN:
+        cur.execute(
+            "SELECT setval('adresse_correction_id_seq', COALESCE((SELECT MAX(id) FROM adresse_correction), 1))"
+        )
+        conn.commit()
+
+    cur.close()
+    conn.close()
+
+    print(f"\n{'🔍 DRY-RUN — ' if DRY_RUN else ''}✅ Terminé")
+    print(f"   Insérés    : {inserted}")
+    print(f"   Mis à jour : {updated}")
+    print(f"   Erreurs    : {errors}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/import_clients.py b/scripts/import_clients.py
new file mode 100644
index 00000000..eea7e5e5
--- /dev/null
+++ b/scripts/import_clients.py
@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+"""
+Import clients depuis data.txt (format psql pipe-séparé) vers PostgreSQL.
+Usage : python3 import_clients.py [--dry-run]
+"""
+
+import os
+import sys
+
+import psycopg2
+
+# ── Connexion ──────────────────────────────────────────────────────────────────
+DB_CONFIG = {
+    "host": "localhost",
+    "port": 5432,
+    "user": "",
+    "password": "",
+    "dbname": "",
+}
+
+DATA_FILE = os.path.join(os.path.dirname(__file__), "data.txt")
+DRY_RUN = "--dry-run" in sys.argv
+
+# ── Ordre des colonnes dans data.txt (DB production, construite incrémentalement)
+# None = colonne inconnue/obsolète à ignorer
+SOURCE_COLUMNS = [
+    "id",
+    "username",
+    "password",
+    "nom",
+    "prenom",
+    "telephone",
+    "command",
+    "amende",
+    "cancel_commande",
+    "referral_balance",  # position 9  : NUMERIC(10,2) → "0.00"
+    "cancellations_count",  # position 10 : INTEGER       → "0"
+    None,  # position 11 : colonne obsolète/inconnue, ignorée
+    "last_penalty_reason",  # position 12 : TEXT
+    "updated_at",
+    "created_at",
+    "must_change_password",  # position 15 : BOOLEAN → "f"/"t"
+]
+
+
+def parse_value(v: str):
+    """Convertit une valeur brute psql en type Python (None si vide)."""
+    v = v.strip()
+    if v == "" or v.lower() == "null":
+        return None
+    if v.lower() == "t":
+        return True
+    if v.lower() == "f":
+        return False
+    return v
+
+
+def load_data(path: str) -> list[list]:
+    rows = []
+    with open(path, encoding="utf-8") as f:
+        for line in f:
+            line = line.rstrip("\n")
+            if not line.strip():
+                continue
+            # Lignes séparateur psql (ex: "----+----")
+            if (
+                set(
+                    line.replace("|", "")
+                    .replace("+", "")
+                    .replace("-", "")
+                    .replace(" ", "")
+                )
+                == set()
+            ):
+                continue
+            parts = line.split("|")
+            values = (
+                [parse_value(p) for p in parts[:-1]]
+                if parts[-1].strip() == ""
+                else [parse_value(p) for p in parts]
+            )
+            if values:
+                rows.append(values)
+    return rows
+
+
+def main():
+    rows = load_data(DATA_FILE)
+    if not rows:
+        print("❌ Aucune ligne trouvée dans data.txt")
+        sys.exit(1)
+
+    print(f"📂 {len(rows)} lignes lues depuis {DATA_FILE}")
+
+    data_col_count = len(rows[0])
+    print(
+        f"📋 Colonnes data.txt : {data_col_count}  |  SOURCE_COLUMNS définis : {len(SOURCE_COLUMNS)}"
+    )
+
+    if data_col_count != len(SOURCE_COLUMNS):
+        print(
+            f"⚠️  Ajuste SOURCE_COLUMNS dans le script ({len(SOURCE_COLUMNS)} définis, {data_col_count} dans le fichier)"
+        )
+        sys.exit(1)
+
+    # Colonnes à insérer (on filtre les None = colonnes ignorées)
+    insert_cols = [col for col in SOURCE_COLUMNS if col is not None and col != "id"]
+    # On conserve aussi l'id pour FORCE_ID
+    insert_cols_with_id = ["id"] + insert_cols
+
+    placeholders = ", ".join(["%s"] * len(insert_cols_with_id))
+    col_names = ", ".join(insert_cols_with_id)
+    update_expr = ", ".join(f"{c} = EXCLUDED.{c}" for c in insert_cols)
+
+    sql = f"""
+        INSERT INTO clients ({col_names})
+        VALUES ({placeholders})
+        ON CONFLICT (username) DO UPDATE SET {update_expr}
+    """
+
+    conn = psycopg2.connect(**DB_CONFIG)
+    conn.autocommit = False
+    cur = conn.cursor()
+
+    inserted = 0
+    updated = 0
+    errors = 0
+
+    for i, row in enumerate(rows, 1):
+        # Construire un dict {col_name: value} depuis SOURCE_COLUMNS
+        row_dict = {}
+        for pos, col in enumerate(SOURCE_COLUMNS):
+            if col is None:
+                continue
+            row_dict[col] = row[pos] if pos < len(row) else None
+
+        values = [row_dict.get(c) for c in insert_cols_with_id]
+        username = row_dict.get("username", "?")
+
+        try:
+            if DRY_RUN:
+                print(f"  [DRY-RUN] ligne {i} : {username} → {row_dict}")
+                inserted += 1
+                continue
+
+            cur.execute("SELECT 1 FROM clients WHERE username = %s", (username,))
+            exists = cur.fetchone() is not None
+
+            cur.execute(sql, values)
+
+            if exists:
+                updated += 1
+            else:
+                inserted += 1
+
+        except Exception as e:
+            print(f"  ❌ Erreur ligne {i} ({username}) : {e}")
+            conn.rollback()
+            errors += 1
+            continue
+
+    if not DRY_RUN:
+        cur.execute(
+            "SELECT setval('clients_id_seq', COALESCE((SELECT MAX(id) FROM clients), 1))"
+        )
+        conn.commit()
+
+    cur.close()
+    conn.close()
+
+    print(f"\n{'🔍 DRY-RUN — ' if DRY_RUN else ''}✅ Terminé")
+    print(f"   Insérés    : {inserted}")
+    print(f"   Mis à jour : {updated}")
+    print(f"   Erreurs    : {errors}")
+    print(f"   ℹ️  Séquence clients_id_seq resynchronisée sur MAX(id)")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/import_users.py b/scripts/import_users.py
new file mode 100644
index 00000000..7b509daf
--- /dev/null
+++ b/scripts/import_users.py
@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+"""
+Import users depuis data3.txt (format psql pipe-séparé) vers PostgreSQL.
+Usage : python3 import_users.py [--dry-run]
+"""
+
+import os
+import sys
+
+import psycopg2
+
+DB_CONFIG = {
+    "host": "localhost",
+    "port": 5432,
+    "user": "",
+    "password": "",
+    "dbname": "",
+}
+
+DATA_FILE = os.path.join(os.path.dirname(__file__), "data3.txt")
+DRY_RUN = "--dry-run" in sys.argv
+
+# Colonnes dans data3.txt — None = ignoré (push_token supprimé)
+SOURCE_COLUMNS = [
+    "id",
+    "username",
+    "password",
+    "role",
+    "total",
+    "livraison",
+    "created_at",
+    "updated_at",
+]
+
+
+def parse_value(v: str):
+    v = v.strip()
+    if v == "" or v.lower() == "null":
+        return None
+    if v.lower() == "t":
+        return True
+    if v.lower() == "f":
+        return False
+    return v
+
+
+def load_data(path: str) -> list[list]:
+    rows = []
+    with open(path, encoding="utf-8") as f:
+        for line in f:
+            line = line.rstrip("\n")
+            if not line.strip():
+                continue
+            if (
+                set(
+                    line.replace("|", "")
+                    .replace("+", "")
+                    .replace("-", "")
+                    .replace(" ", "")
+                )
+                == set()
+            ):
+                continue
+            parts = line.split("|")
+            values = (
+                [parse_value(p) for p in parts[:-1]]
+                if parts[-1].strip() == ""
+                else [parse_value(p) for p in parts]
+            )
+            # Ignorer la ligne d'en-tête
+            if values and values[0] == "id":
+                continue
+            if values:
+                rows.append(values)
+    return rows
+
+
+def main():
+    rows = load_data(DATA_FILE)
+    if not rows:
+        print("❌ Aucune ligne trouvée dans data3.txt")
+        sys.exit(1)
+
+    print(f"📂 {len(rows)} lignes lues depuis {DATA_FILE}")
+
+    data_col_count = len(rows[0])
+    print(
+        f"📋 Colonnes data3.txt : {data_col_count}  |  SOURCE_COLUMNS définis : {len(SOURCE_COLUMNS)}"
+    )
+
+    if data_col_count != len(SOURCE_COLUMNS):
+        print(
+            f"⚠️  Ajuste SOURCE_COLUMNS ({len(SOURCE_COLUMNS)} définis, {data_col_count} dans le fichier)"
+        )
+        sys.exit(1)
+
+    insert_cols = [col for col in SOURCE_COLUMNS if col is not None and col != "id"]
+    insert_cols_with_id = ["id"] + insert_cols
+
+    placeholders = ", ".join(["%s"] * len(insert_cols_with_id))
+    col_names = ", ".join(insert_cols_with_id)
+    update_expr = ", ".join(f"{c} = EXCLUDED.{c}" for c in insert_cols)
+
+    sql = f"""
+        INSERT INTO users ({col_names})
+        VALUES ({placeholders})
+        ON CONFLICT (username) DO UPDATE SET {update_expr}
+    """
+
+    conn = psycopg2.connect(**DB_CONFIG)
+    conn.autocommit = False
+    cur = conn.cursor()
+
+    inserted = updated = errors = 0
+
+    for i, row in enumerate(rows, 1):
+        row_dict = {}
+        for pos, col in enumerate(SOURCE_COLUMNS):
+            if col is None:
+                continue
+            row_dict[col] = row[pos] if pos < len(row) else None
+
+        values = [row_dict.get(c) for c in insert_cols_with_id]
+        username = row_dict.get("username", "?")
+
+        try:
+            if DRY_RUN:
+                print(f"  [DRY-RUN] {i}. {username} → {row_dict}")
+                inserted += 1
+                continue
+
+            cur.execute("SELECT 1 FROM users WHERE username = %s", (username,))
+            exists = cur.fetchone() is not None
+            cur.execute(sql, values)
+            if exists:
+                updated += 1
+            else:
+                inserted += 1
+
+        except Exception as e:
+            print(f"  ❌ Erreur ligne {i} ({username}) : {e}")
+            conn.rollback()
+            errors += 1
+
+    if not DRY_RUN:
+        cur.execute(
+            "SELECT setval('users_id_seq', COALESCE((SELECT MAX(id) FROM users), 1))"
+        )
+        conn.commit()
+
+    cur.close()
+    conn.close()
+
+    print(f"\n{'🔍 DRY-RUN — ' if DRY_RUN else ''}✅ Terminé")
+    print(f"   Insérés    : {inserted}")
+    print(f"   Mis à jour : {updated}")
+    print(f"   Erreurs    : {errors}")
+    print("   ℹ️  Séquence users_id_seq resynchronisée sur MAX(id)")
+
+
+if __name__ == "__main__":
+    main()