z230

50 MD5calculate.py

@@ -0,0 +1,192 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import os
+import hashlib
+from datetime import datetime
+import mysql.connector
+from dotenv import load_dotenv
+from pathlib import Path
+
+
+# ======================================================
+# Load environment
+# ======================================================
+env_path = Path(__file__).resolve().parent / ".env"
+load_dotenv(env_path)
+
+
+# ======================================================
+# MySQL connection
+# ======================================================
+def get_db_connection():
+    conn = mysql.connector.connect(
+        host=os.getenv("DB_MYSQL_HOST"),
+        user=os.getenv("DB_MYSQL_ROOT"),
+        password=os.getenv("DB_MYSQL_ROOT_PASS"),
+        port=int(os.getenv("DB_MYSQL_PORT")),
+        database="walkfiles",
+        auth_plugin="mysql_native_password"
+    )
+    c = conn.cursor()
+    c.execute("SET NAMES utf8mb4 COLLATE utf8mb4_general_ci")
+    c.close()
+    return conn
+
+
+# ======================================================
+# Helpers
+# ======================================================
+def file_md5(path, chunk_size=1024 * 1024):
+    """Compute content MD5 of a file in chunks."""
+    md5 = hashlib.md5()
+    with open(path, "rb") as f:
+        while chunk := f.read(chunk_size):
+            md5.update(chunk)
+    return md5.hexdigest()
+
+
+def parse_size(size_str: str) -> int:
+    """
+    Convert human input like:
+        10MB, 500kB, 2GB
+    into bytes. If already numeric, return as-is.
+    """
+    s = size_str.strip().upper()
+    if s.endswith("KB"):
+        return int(float(s[:-2]) * 1024)
+    if s.endswith("MB"):
+        return int(float(s[:-2]) * 1024 * 1024)
+    if s.endswith("GB"):
+        return int(float(s[:-2]) * 1024 * 1024 * 1024)
+    return int(s)  # assume raw bytes
+
+
+# ======================================================
+# MAIN LOGIC
+# ======================================================
+def run_md5_calculator(device_name=None,
+                       device_id=None,
+                       extension=".pdf",
+                       max_size="50MB"):
+    """
+    device_name OR device_id must be provided.
+    extension: ".pdf", ".jpg", etc.
+    max_size: "10MB", "500KB", "1GB" or number of bytes
+    """
+
+    max_bytes = parse_size(max_size)
+
+    conn, cursor = None, None
+
+    try:
+        conn = get_db_connection()
+        cursor = conn.cursor(dictionary=True)
+
+        # ------------------------------------------
+        # Resolve device_id if only device_name given
+        # ------------------------------------------
+        if device_id is None:
+            if device_name is None:
+                raise RuntimeError("You must provide device_name or device_id")
+            cursor.execute("SELECT id FROM devices WHERE name=%s", (device_name,))
+            row = cursor.fetchone()
+            if not row:
+                raise RuntimeError(f"Device '{device_name}' not found")
+            device_id = row["id"]
+
+        print(f"\n🔍 Filtering: device={device_id}, ext={extension}, max_size={max_bytes} bytes\n")
+
+        # ------------------------------------------
+        # SELECT only files that need MD5 calculation
+        # ------------------------------------------
+        cursor.execute("""
+            SELECT id, path, size, modified, content_md5, md5_calculated
+            FROM files
+            WHERE device_id=%s
+              AND deleted = 0
+              AND path LIKE %s
+              AND size <= %s
+        """, (device_id, "%" + extension, max_bytes))
+
+        rows = cursor.fetchall()
+        total = len(rows)
+        print(f"📁 Files matching criteria: {total}")
+
+        updates = 0
+
+        for row in rows:
+
+            file_id = row["id"]
+            path = row["path"]
+            size = row["size"]
+            modified = row["modified"]
+            prev_md5 = row["content_md5"]
+            prev_calc = row["md5_calculated"]
+
+            # -------------------------------
+            # Skip missing files on disk
+            # -------------------------------
+            if not os.path.isfile(path):
+                print(f"⚠️ Missing on disk, skipping: {path}")
+                continue
+
+            # -------------------------------
+            # Check conditions for recalculation
+            # -------------------------------
+            need_md5 = False
+
+            if prev_md5 is None:
+                need_md5 = True
+            else:
+                if prev_calc is None or prev_calc < modified:
+                    need_md5 = True
+
+            if not need_md5:
+                continue
+
+            # -------------------------------
+            # Compute MD5
+            # -------------------------------
+            print(f"🔄 Calculating MD5: {path}")
+            new_md5 = file_md5(path)
+            now = datetime.now().replace(microsecond=0)
+
+            cursor.execute("""
+                UPDATE files
+                SET content_md5=%s,
+                    md5_calculated=%s
+                WHERE id=%s
+            """, (new_md5, now, file_id))
+
+            updates += 1
+
+            # optional commit per-file:
+            # conn.commit()
+
+        conn.commit()
+
+        print("\n✅ MD5 calculation finished.")
+        print(f"   Updated files: {updates}")
+        print(f"   Skipped files: {total - updates}\n")
+
+    except Error as e:
+        print("MySQL Error:", e)
+
+    finally:
+        if cursor:
+            cursor.close()
+        if conn:
+            conn.close()
+
+
+# ======================================================
+# RUN EXAMPLE
+# ======================================================
+if __name__ == "__main__":
+    # Example usage:
+    run_md5_calculator(
+        device_name="Z230",
+        extension=".pdf",
+        max_size="100MB"
+    )