added ability to run in docker

src/DoresA/Dockerfile

@@ -0,0 +1,7 @@
+FROM python:3
+ENV PYTHONUNBUFFERED 1
+RUN mkdir /app
+WORKDIR /app
+ADD requirements.txt /app/
+RUN pip install -r requirements.txt
+ADD . /app/

src/DoresA/db.py

@@ -1,19 +1,46 @@
 import MySQLdb as mariadb
 import time
+import os
 from pymongo import MongoClient
 
 
-mongo_client = MongoClient('localhost', 27017)
+mongodb_host = 'localhost'
-mongo_db = mongo_client.doresa
+mongodb_db_name = 'doresa'
-pdns_logs_mongo = mongo_db.pdns_logs
+# mongodb_collection_name = 'pdns_logs'
+mongodb_collection_name = 'may'  # tmp TODO remove
+
+sql_host = 'localhost'
+sql_db_name = 'doresa'
+sql_user_name = 'doresa'
+sql_pw = '3qfACEZzbXY4b'
+# sql_table_name = 'pdns_logs'
+sql_table_name = 'pdns_logs_test'
 
 
-sql_connection = mariadb.connect(user='doresa', passwd='3qfACEZzbXY4b', db='doresa')
+if 'MYSQL_HOST' in os.environ:
+    sql_host = os.environ['MYSQL_HOST']
+
+if 'MYSQL_DATABASE' in os.environ:
+    sql_db_name = os.environ['MYSQL_DATABASE']
+
+if 'MYSQL_USER' in os.environ:
+    sql_user_name = os.environ['MYSQL_USER']
+
+if 'MYSQL_PASSWORD' in os.environ:
+    sql_pw = os.environ['MYSQL_PASSWORD']
+
+
+mongo_client = MongoClient(mongodb_host, 27017)
+mongo_db = mongo_client[mongodb_db_name]
+pdns_logs_mongo = mongo_db[mongodb_collection_name]
+
+
+sql_connection = mariadb.connect(host=sql_host, user=sql_user_name, passwd=sql_pw, db=sql_db_name)
 sql_cursor = sql_connection.cursor()
 
 
 def mariadb_insert_log(csv_entry):
-    insert_sql = 'INSERT INTO pdns_logs (timestamp, domain, type, record, ttl) VALUES (%s, %s, %s, %s, %s)'
+    insert_sql = 'INSERT INTO ' + sql_table_name + ' (timestamp, domain, type, record, ttl) VALUES (%s, %s, %s, %s, %s)'
 
     values = (convert_timestamp_to_sql_datetime(float(csv_entry[0])), csv_entry[1],
               csv_entry[2], csv_entry[3], csv_entry[4])
@@ -22,7 +49,7 @@ def mariadb_insert_log(csv_entry):
 
 
 def mariadb_insert_logs(csv_entries):
-    inserts_sql = 'INSERT INTO pdns_logs (timestamp, domain, type, record, ttl) VALUES '
+    inserts_sql = 'INSERT INTO ' + sql_table_name + ' (timestamp, domain, type, record, ttl) VALUES '
 
     for i in range(len(csv_entries) - 1):
         inserts_sql += '(%s, %s, %s, %s, %s), '
@@ -39,14 +66,13 @@ def mariadb_insert_logs(csv_entries):
 
 
 def mariadb_get_logs(from_time, to_time):
-    get_logs_from_to = 'SELECT * FROM pdns_logs WHERE timestamp BETWEEN \'{}\' and \'{}\';'.format(from_time, to_time)
+    get_logs_from_to = 'SELECT * FROM ' + sql_table_name + ' WHERE timestamp BETWEEN \'{}\' and \'{}\';'.format(from_time, to_time)
     sql_connection.query(get_logs_from_to)
     return sql_connection.use_result()
 
 
 def mariadb_create_table():
-    create_table = """
+    create_table = 'CREATE TABLE IF NOT EXISTS ' + sql_table_name + """ (
-        CREATE TABLE pdns_logs (
           id INTEGER AUTO_INCREMENT PRIMARY KEY,
           timestamp DATETIME,
           domain VARCHAR(255),
@@ -84,5 +110,7 @@ def close():
     mongo_client.close()
 
 
+mariadb_create_table()
+
 if __name__ == "__main__":
     exit()

src/DoresA/docker-compose.yml

@@ -0,0 +1,31 @@
+version: '3'
+
+services:
+  mariadb:
+    container_name: mariadb
+    image: mariadb
+    restart: unless-stopped
+    ports: 
+      - "3306:3306"
+    environment:
+      MYSQL_ROOT_PASSWORD: jDGb3CvbsmBSB
+      MYSQL_DATABASE: doresa
+      MYSQL_USER: doresa
+      MYSQL_PASSWORD: 3qfACEZzbXY4b
+  
+  app:
+    build: .
+    container_name: app
+    restart: unless-stopped
+    command: python3 serialize_logs_to_db.py
+    volumes:
+      - .:/app
+      - ./data:/data
+    environment:
+      MYSQL_HOST: mariadb
+      MYSQL_DATABASE: doresa
+      MYSQL_USER: doresa
+      MYSQL_PASSWORD: 3qfACEZzbXY4b
+      DATA_PATH: 
+    depends_on:
+      - mariadb

src/DoresA/iterate_db.py

@@ -0,0 +1,16 @@
+import db
+import datetime
+
+
+def test():
+    f = '%Y-%m-%d %H:%M:%S'
+    results = db.mariadb_get_logs(datetime.date(2017, 4, 7).strftime(f), datetime.date(2017, 4, 8).strftime(f))
+
+    row = results.fetch_row(how=1)
+    while row:
+        print(row[0]['domain'])
+        row = results.fetch_row(how=1)
+
+
+if __name__ == "__main__":
+    test()

src/DoresA/serialize_logs_to_db.py

@@ -4,25 +4,23 @@ import glob
 import time
 import datetime
 import pandas
+import os
 from progress.bar import Bar
 
 import db
 
-analysis_start_date = datetime.date(2017, 4, 7)
+analysis_start_date = datetime.date(2017, 5, 1)
-analysis_days_amount = 3
+analysis_days_amount = 31
+# pdns_logs_path = 'data/'
+pdns_logs_path = '/run/media/felix/ext/2017.05/'  # tmp TODO remove
 
 # e.g. analysis_days = ['2017-04-07', '2017-04-08', '2017-04-09']
 analysis_days = [(analysis_start_date + datetime.timedelta(days=x)).strftime('%Y-%m-%d') for x in
                  range(analysis_days_amount)]
 
 
-# mongodb
-
-# mariadb
-
-
 def main():
-    check_duplicates()
+    # check_duplicates() TODO readd
     start = time.time()
 
     distinct_ttl_count = {}
@@ -51,7 +49,7 @@ def main():
                     # batch mode (batches of 1000 entries)
                     for log_entries in batch(all_rows, 1000):
                         db.mariadb_insert_logs(log_entries)
-                        # db.mongodb_insert_logs(log_entries)
+                        db.mongodb_insert_logs(log_entries)
 
                         # single mode
                         # for log_entry in reader:
@@ -100,7 +98,7 @@ def get_log_files_for_hours_of_day(date):
     slots_amount = 24
 
     for slot in range(slots_amount):
-        slot_files[slot] = glob.glob('data/*' + date + '_' + ('%02d' % slot) + '*.csv.gz')
+        slot_files[slot] = glob.glob(pdns_logs_path + '*' + date + '_' + ('%02d' % slot) + '*.csv.gz')
 
     return slot_files