Revize 04a2b5a4

Re #7939
- pridana dokumentace metod a trid
- korekce chyb v jmenech promenych
- pridani informaci pro vygenerovane skripty

python-module/Utilities/Database/DatabaseLoader.py

@@ -1 +1 @@
 from Utilities.Database import DatabaseDataLine
 import pymongo
 
+# specify mongodb connection
+MONGODB_CONNECTION = "mongodb://localhost:27017/"
+# mongodb account name
+MONGODB_ACC_NAME = "root"
+# mongodb account password
+MONGODB_ACC_PASSWORD = "root"
+# mongodb data database
+MONGODB_DATA_DATABASE = "DATA"
+# mongodb collection with aviable datasets
+MONGODB_DATASET_COLLECTION = "DATASETS"
+
+# Path to processed data
+PROCESSED_DATA_PATH = "ProcessedData/"
+
+
+def create_database_connection():
+    """
+    Creates connection to mongoDB
+    
+    Returns:
+        Connection to mongoDB
+    """
+    client = pymongo.MongoClient(MONGODB_CONNECTION)
 
-def get_data_from_file(filename, devices):
-    f = open(filename, "r")
+    # Authenticating
+    client.admin.authenticate(MONGODB_ACC_NAME, MONGODB_ACC_PASSWORD)
+
+    database = client[MONGODB_DATA_DATABASE]
+
+    return database
+
+
+def get_data_from_file(filename, config):
+    """
+        Opens processed file, reads it line by line
+        name, ocurrence, date
+        searches name in config and adds device map coordinates
+        than creates a dictionary with date without hours as key
+        and list of data lines as value.
+    Args:
+        filename: name of processed file
+        config: loaded configuration file of dataset
+
+    Returns:
+        dictionary with date without hours as key
+        and list of Datalines as value
+    """
+    dataset_name = config["dataset-name"]
+    dataset_path = PROCESSED_DATA_PATH + dataset_name + '/'
 
+    f = open(dataset_path + filename, "r")
+
+    devices = config["devices"]
     date_dict = dict()
 
     for line in f:
-        # remove \n
         line = line[:-1]
-        # split by csv splitter ;
-
-        csv_collum = line.split(";")
 
-        name = csv_collum[0]
-        occurence = csv_collum[1]
-        date = csv_collum[2]
+        csv_column = line.split(";")
 
-        date_without_hours = date[:-2]
+        name = csv_column[0]
+        occurrence = csv_column[1]
+        date = csv_column[2]
 
         database_data_line = DatabaseDataLine.DatabaseDataLine(name, devices[name]["x"]
-                                                               , devices[name]["y"], date, occurence)
+                                                               , devices[name]["y"], date, occurrence)
 
+        # if you want to change table split by hours or months change this
+        date_without_hours = date[:-2]
         if date_without_hours not in date_dict:
             date_dict[date_without_hours] = list()
 
-        date_dict[date_without_hours].append(database_data_line.to_dictionary())
+        date_dict[date_without_hours].append(database_data_line.to_dictionary)
 
     return date_dict
 
 
 def load_data_to_database(dataset_name, data_dic):
-    myclient = pymongo.MongoClient("mongodb://localhost:27017/");
-
-    # Authenticating
-    myclient.admin.authenticate('root', 'root');
+    """
+    Takes data_dic created in method get_data_from_file
+    and loads into into database where collection name is dataset_name + data_dic key
+    and data lines are line in collection
 
-    # Database DATA
-    mydb = myclient["DATA"]
+    Args:
+        dataset_name: name of dataset that has existing configuration file
+        data_dic: dictionary of data lines created in get_data_from_file
+    """
+    database = create_database_connection()
 
-    # Collection Datasets
-    collection_datasets = mydb["DATASETS"]
+    # collection where are specified aviable datasets
+    collection_datasets = database[MONGODB_DATASET_COLLECTION]
 
+    # check if newly added data already have a dataset specified in collection
     dataset_present = collection_datasets.find_one({}, {'name': dataset_name})
 
     if dataset_present is None:
         collection_datasets.insert_one({'name': dataset_name})
 
     for date in data_dic:
-        dataset_collections = mydb[dataset_name]
+        dataset_collections = database[dataset_name]
         dataset_collections.insert_one({'name': dataset_name+date})
-        date_dataset = mydb[dataset_name + date]
+        date_dataset = database[dataset_name + date]
         date_dataset.insert_many(data_dic[date])