Today, we’ll be discussing a new cross-over between API, JSON, Encryption along with data distribution through Queue.
The primary objective here is to distribute one csv file through API service & access our previously deployed Encryption/Decryption methods by accessing the parallel call through Queue. In this case, our primary objective is to allow asynchronous calls to Queue for data distributions & at this point we’re not really looking for performance improvement. Instead, our goal to achieve the target.
My upcoming posts will discuss the improvement of performance using Parallel calls.
Let’s discuss it now.
Please find the structure of our Windows & MAC directory are as follows –
We’re not going to discuss any scripts, which we’ve already discussed in my previous posts. Please refer the relevant earlier posts from my blogs.
1. clsL.py (This script will create the split csv files or final merge file after the corresponding process. However, this can be used as usual verbose debug logging as well. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 |
########################################### #### Written By: SATYAKI DE ######## #### Written On: 25-Jan-2019 ######## #### ######## #### Objective: Log File ######## ########################################### import pandas as p import platform as pl from clsParam import clsParam as cf class clsL(object): def __init__(self): self.path = cf.config['PATH'] def logr(self, Filename, Ind, df, subdir=None): try: x = p.DataFrame() x = df sd = subdir os_det = pl.system() if sd == None: if os_det == "Windows": fullFileName = self.path + '\\' + Filename else: fullFileName = self.path + '/' + Filename else: if os_det == "Windows": fullFileName = self.path + '\\' + sd + "\\" + Filename else: fullFileName = self.path + '/' + sd + "/" + Filename if Ind == 'Y': x.to_csv(fullFileName, index=False) return 0 except Exception as e: y = str(e) print(y) return 3 |
2. callRunServer.py (This script will create an instance of a server. Once, it is running – it will emulate the Server API functionalities. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
############################################ #### Written By: SATYAKI DE #### #### Written On: 10-Feb-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### initiate the encrypt/decrypt class #### #### based on client supplied data. #### #### Also, this will create an instance #### #### of the server & create an endpoint #### #### or API using flask framework. #### ############################################ from flask import Flask from flask import jsonify from flask import request from flask import abort from clsConfigServer import clsConfigServer as csf import clsFlask as clf app = Flask(__name__) @app.route('/process/getEncrypt', methods=['POST']) def getEncrypt(): try: # If the server application doesn't have # valid json, it will throw 400 error if not request.get_json: abort(400) # Capturing the individual element content = request.get_json() dGroup = content['dataGroup'] input_data = content['data'] dTemplate = content['dataTemplate'] # For debug purpose only print("-" * 157) print("Group: ", dGroup) print("Data: ", input_data) print("Template: ", dTemplate) print("-" * 157) ret_val = '' if ((dGroup != '') & (dTemplate != '')): y = clf.clsFlask() ret_val = y.getEncryptProcess(dGroup, input_data, dTemplate) else: abort(500) return jsonify({'status': 'success', 'encrypt_val': ret_val}) except Exception as e: x = str(e) return jsonify({'status': 'error', 'detail': x}) @app.route('/process/getDecrypt', methods=['POST']) def getDecrypt(): try: # If the server application doesn't have # valid json, it will throw 400 error if not request.get_json: abort(400) # Capturing the individual element content = request.get_json() dGroup = content['dataGroup'] input_data = content['data'] dTemplate = content['dataTemplate'] # For debug purpose only print("-" * 157) print("Group: ", dGroup) print("Data: ", input_data) print("Template: ", dTemplate) print("-" * 157) ret_val = '' if ((dGroup != '') & (dTemplate != '')): y = clf.clsFlask() ret_val = y.getDecryptProcess(dGroup, input_data, dTemplate) else: abort(500) return jsonify({'status': 'success', 'decrypt_val': ret_val}) except Exception as e: x = str(e) return jsonify({'status': 'error', 'detail': x}) def main(): try: print('Starting Encrypt/Decrypt Application!') # Calling Server Start-Up Script app.run(debug=True, host=str(csf.config['HOST_IP_ADDR'])) ret_val = 0 if ret_val == 0: print("Finished Returning Message!") else: raise IOError except Exception as e: print("Server Failed To Start!") if __name__ == '__main__': main() |
3. clsFlask.py (This script is part of the server process, which will categorize the encryption logic based on different groups. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
########################################### #### Written By: SATYAKI DE #### #### Written On: 25-Jan-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### encrypt/decrypt based on the #### #### supplied salt value. Also, #### #### this will capture the individual #### #### element & stored them into JSON #### #### variables using flask framework. #### ########################################### from clsConfigServer import clsConfigServer as csf import clsEnDecAuth as cen class clsFlask(object): def __init__(self): self.xtoken = str(csf.config['DEF_SALT']) def getEncryptProcess(self, dGroup, input_data, dTemplate): try: # It is sending default salt value xtoken = self.xtoken # Capturing the individual element dGroup = dGroup input_data = input_data dTemplate = dTemplate # This will check the mandatory json elements if ((dGroup != '') & (dTemplate != '')): # Based on the Group & Element it will fetch the salt # Based on the specific salt it will encrypt the data if ((dGroup == 'GrDet') & (dTemplate == 'subGrAcct_Nbr')): xtoken = str(csf.config['ACCT_NBR_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.encrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrName')): xtoken = str(csf.config['NAME_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.encrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrPhone')): xtoken = str(csf.config['PHONE_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.encrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrEmail')): xtoken = str(csf.config['EMAIL_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.encrypt_str(input_data) else: ret_val = '' else: ret_val = '' # Return value return ret_val except Exception as e: ret_val = '' # Return the valid json Error Response return ret_val def getDecryptProcess(self, dGroup, input_data, dTemplate): try: xtoken = self.xtoken # Capturing the individual element dGroup = dGroup input_data = input_data dTemplate = dTemplate # This will check the mandatory json elements if ((dGroup != '') & (dTemplate != '')): # Based on the Group & Element it will fetch the salt # Based on the specific salt it will decrypt the data if ((dGroup == 'GrDet') & (dTemplate == 'subGrAcct_Nbr')): xtoken = str(csf.config['ACCT_NBR_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.decrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrName')): xtoken = str(csf.config['NAME_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.decrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrPhone')): xtoken = str(csf.config['PHONE_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.decrypt_str(input_data) elif ((dGroup == 'GrDet') & (dTemplate == 'subGrEmail')): xtoken = str(csf.config['EMAIL_SALT']) print("xtoken: ", xtoken) print("Flask Input Data: ", input_data) x = cen.clsEnDec(xtoken) ret_val = x.decrypt_str(input_data) else: ret_val = '' else: ret_val = '' # Return value return ret_val except Exception as e: ret_val = '' # Return the valid Error Response return ret_val |
4. clsEnDec.py (This script will convert the string to encryption or decryption from its previous states based on the supplied group. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
########################################### #### Written By: SATYAKI DE ######## #### Written On: 25-Jan-2019 ######## #### Package Cryptography needs to ######## #### install in order to run this ######## #### script. ######## #### ######## #### Objective: This script will ######## #### encrypt/decrypt based on the ######## #### hidden supplied salt value. ######## ########################################### from cryptography.fernet import Fernet class clsEnDec(object): def __init__(self, token): # Calculating Key self.token = token def encrypt_str(self, data): try: # Capturing the Salt Information salt = self.token # Checking Individual Types inside the Dataframe cipher = Fernet(salt) encr_val = str(cipher.encrypt(bytes(data,'utf8'))).replace("b'","").replace("'","") return encr_val except Exception as e: x = str(e) print(x) encr_val = '' return encr_val def decrypt_str(self, data): try: # Capturing the Salt Information salt = self.token # Checking Individual Types inside the Dataframe cipher = Fernet(salt) decr_val = str(cipher.decrypt(bytes(data,'utf8'))).replace("b'","").replace("'","") return decr_val except Exception as e: x = str(e) print(x) decr_val = '' return decr_val |
5. clsConfigServer.py (This script contains all the main parameter details of your emulated API server. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
########################################### #### Written By: SATYAKI DE ######## #### Written On: 10-Feb-2019 ######## #### ######## #### Objective: Parameter File ######## ########################################### import os import platform as pl # Checking with O/S system os_det = pl.system() class clsConfigServer(object): Curr_Path = os.path.dirname(os.path.realpath(__file__)) if os_det == "Windows": config = { 'FILE': 'acct_addr_20180112.csv', 'SRC_FILE_PATH': Curr_Path + '\\' + 'src_file\\', 'PROFILE_FILE_PATH': Curr_Path + '\\' + 'profile\\', 'HOST_IP_ADDR': '0.0.0.0', 'DEF_SALT': 'iooquzKtqLwUwXG3rModqj_fIl409vemWg9PekcKh2o=', 'ACCT_NBR_SALT': 'iooquzKtqLwUwXG3rModqj_fIlpp1vemWg9PekcKh2o=', 'NAME_SALT': 'iooquzKtqLwUwXG3rModqj_fIlpp1026Wg9PekcKh2o=', 'PHONE_SALT': 'iooquzKtqLwUwXG3rMM0F5_fIlpp1026Wg9PekcKh2o=', 'EMAIL_SALT': 'iooquzKtqLwU0653rMM0F5_fIlpp1026Wg9PekcKh2o=' } else: config = { 'FILE': 'acct_addr_20180112.csv', 'SRC_FILE_PATH': Curr_Path + '/' + 'src_file/', 'PROFILE_FILE_PATH': Curr_Path + '/' + 'profile/', 'HOST_IP_ADDR': '0.0.0.0', 'DEF_SALT': 'iooquzKtqLwUwXG3rModqj_fIl409vemWg9PekcKh2o=', 'ACCT_NBR_SALT': 'iooquzKtqLwUwXG3rModqj_fIlpp1vemWg9PekcKh2o=', 'NAME_SALT': 'iooquzKtqLwUwXG3rModqj_fIlpp1026Wg9PekcKh2o=', 'PHONE_SALT': 'iooquzKtqLwUwXG3rMM0F5_fIlpp1026Wg9PekcKh2o=', 'EMAIL_SALT': 'iooquzKtqLwU0653rMM0F5_fIlpp1026Wg9PekcKh2o=' } |
6. clsWeb.py (This script will receive the input Pandas dataframe & then convert it to JSON & then send it back to our Flask API Server for encryption/decryption. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
############################################ #### Written By: SATYAKI DE #### #### Written On: 09-Mar-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### initiate API based JSON requests #### #### at the server & receive the #### #### response from it & transform it #### #### back to the data-frame. #### ############################################ import json import requests import datetime import time import ssl import os from clsParam import clsParam as cf class clsWeb(object): def __init__(self, payload): self.payload = payload self.path = str(cf.config['PATH']) self.max_retries = int(cf.config['MAX_RETRY']) self.encrypt_ulr = str(cf.config['ENCRYPT_URL']) self.decrypt_ulr = str(cf.config['DECRYPT_URL']) def getResponse(self, mode): # Assigning Logging Info max_retries = self.max_retries encrypt_ulr = self.encrypt_ulr decrypt_ulr = self.decrypt_ulr En_Dec_Mode = mode try: # Bypassing SSL Authentication try: _create_unverified_https_context = ssl._create_unverified_context except AttributeError: # Legacy python that doesn't verify HTTPS certificates by default pass else: # Handle target environment that doesn't support HTTPS verification ssl._create_default_https_context = _create_unverified_https_context # Providing the url if En_Dec_Mode == 'En': url = encrypt_ulr else: url = decrypt_ulr print("URL::", url) # Capturing the payload data = self.payload # Converting String to Json # json_data = json.loads(data) json_data = json.loads(data) print("JSON:::::::", str(json_data)) headers = {"Content-type": "application/json"} param = headers var1 = datetime.datetime.now().strftime("%H:%M:%S") print('Json Fetch Start Time:', var1) retries = 1 success = False while not success: # Getting response from web service # response = requests.post(url, params=param, json=data, auth=(login, password), verify=False) response = requests.post(url, params=param, json=json_data, verify=False) print("Complete Return Code:: ", str(response.status_code)) print("Return Code Initial::", str(response.status_code)[:1]) if str(response.status_code)[:1] == '2': # response = s.post(url, params=param, json=json_data, verify=False) success = True else: wait = retries * 2 print("Retry fails! Waiting " + str(wait) + " seconds and retrying.") time.sleep(wait) retries += 1 # print('Return Service::') # Checking Maximum Retries if retries == max_retries: success = True raise ValueError print("JSON RESPONSE:::", response.text) var2 = datetime.datetime.now().strftime("%H:%M:%S") print('Json Fetch End Time:', var2) # Capturing the response json from Web Service response_json = response.text load_val = json.loads(response_json) # Based on the mode application will send the return value if En_Dec_Mode == 'En': encrypt_ele = str(load_val['encrypt_val']) return_ele = encrypt_ele else: decrypt_ele = str(load_val['decrypt_val']) return_ele = decrypt_ele return return_ele except ValueError as v: raise ValueError except Exception as e: x = str(e) print(x) return 'Error' |
Let’s discuss the key lines –
try: _create_unverified_https_context = ssl._create_unverified_context except AttributeError: # Legacy python that doesn't verify HTTPS certificates by default pass else: # Handle target environment that doesn't support HTTPS verification ssl._create_default_https_context = _create_unverified_https_context
If you are running in a secure environment. Sometimes, your proxy or firewall blocks you from accessing the API server – if they are using different networks. Hence, we need to bypass that. However, it is advisable not to use this in Prod environment for obvious reasons.
# Capturing the payload data = self.payload # Converting String to Json json_data = json.loads(data)
This snippet will convert your data frame into a JSON object.
response = requests.post(url, params=param, json=json_data, verify=False) print("Complete Return Code:: ", str(response.status_code)) print("Return Code Initial::", str(response.status_code)[:1]) if str(response.status_code)[:1] == '2': # response = s.post(url, params=param, json=json_data, verify=False) success = True else: wait = retries * 2 print("Retry fails! Waiting " + str(wait) + " seconds and retrying.") time.sleep(wait) retries += 1 # print('Return Service::') # Checking Maximum Retries if retries == max_retries: success = True raise ValueError
In the first 3 lines, the application is building a JSON response, which will be sent to the API Server. And, it will capture the response from the server.
Next 8 lines will check the status code. And, based on the status code, it will continue or retry the requests in case if there is any failure or lousy response from the server.
Last 3 lines say if the application crosses the maximum allowable error limit, it will terminate the process by raising it as an error.
# Capturing the response json from Web Service response_json = response.text load_val = json.loads(response_json)
Once, it receives the valid response, the application will convert it back to the dataframe & send it to the calling methods.
7. clsParam.py (This script contains the fundamental parameter values to run your client application. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
########################################### #### Written By: SATYAKI DE ######## #### Written On: 20-Jan-2019 ######## ########################################### import os class clsParam(object): config = { 'MAX_RETRY' : 5, 'ENCRYPT_MODE' : 'En', 'DECRYPT_MODE': 'De', 'PATH' : os.path.dirname(os.path.realpath(__file__)), 'SRC_DIR' : os.path.dirname(os.path.realpath(__file__)) + '/' + 'src_files/', 'FIN_DIR': os.path.dirname(os.path.realpath(__file__)) + '/' + 'finished/', 'ENCRYPT_URL': "http://192.168.0.13:5000/process/getEncrypt", 'DECRYPT_URL': "http://192.168.0.13:5000/process/getDecrypt", 'NUM_OF_THREAD': 20 } |
8. clsSerial.py (This script will show the usual or serial way to convert your data into encryption & then to decrypts & store the result into two separate csv files. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 |
############################################ #### Written By: SATYAKI DE #### #### Written On: 10-Feb-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### initiate the encrypt/decrypt class #### #### based on client supplied data #### #### using serial mode operation. #### ############################################ import pandas as p import clsWeb as cw import datetime from clsParam import clsParam as cf # Disbling Warnings def warn(*args, **kwargs): pass import warnings warnings.warn = warn class clsSerial(object): def __init__(self): self.path = cf.config['PATH'] self.EncryptMode = str(cf.config['ENCRYPT_MODE']) self.DecryptMode = str(cf.config['DECRYPT_MODE']) # Lookup Methods for Encryption def encrypt_acctNbr(self, row): # Declaring Local Variable en_AcctNbr = '' json_source_str = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_acctNbr = row['Acct_Nbr'] str_acct_nbr = str(lkp_acctNbr) fil_acct_nbr = str_acct_nbr.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_nbr + '","dataTemplate":"subGrAcct_Nbr"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_nbr) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_AcctNbr = x.getResponse(EncryptMode) else: en_AcctNbr = '' fil_acct_nbr = '' fil_acct_nbr = '' return en_AcctNbr def encrypt_Name(self, row): # Declaring Local Variable en_AcctName = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_acctName = row['Name'] str_acct_name = str(lkp_acctName) fil_acct_name = str_acct_name.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_name + '","dataTemplate":"subGrName"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_name) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_AcctName = x.getResponse(EncryptMode) else: en_AcctName = '' return en_AcctName def encrypt_Phone(self, row): # Declaring Local Variable en_Phone = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_phone = row['Phone'] str_phone = str(lkp_phone) fil_phone = str_phone.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_phone + '","dataTemplate":"subGrPhone"}' # Identifying Length of the field len_acct_nbr = len(fil_phone) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_Phone = x.getResponse(EncryptMode) else: en_Phone = '' return en_Phone def encrypt_Email(self, row): # Declaring Local Variable en_Email = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_email = row['Email'] str_email = str(lkp_email) fil_email = str_email.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_email + '","dataTemplate":"subGrEmail"}' # Identifying Length of the field len_acct_nbr = len(fil_email) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_Email = x.getResponse(EncryptMode) else: en_Email = '' return en_Email # Lookup Methods for Decryption def decrypt_acctNbr(self, row): # Declaring Local Variable de_AcctNbr = '' json_source_str = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_acctNbr = row['Acct_Nbr'] str_acct_nbr = str(lkp_acctNbr) fil_acct_nbr = str_acct_nbr.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_nbr + '","dataTemplate":"subGrAcct_Nbr"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_nbr) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_AcctNbr = x.getResponse(EncryptMode) else: de_AcctNbr = '' return de_AcctNbr def decrypt_Name(self, row): # Declaring Local Variable de_AcctName = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_acctName = row['Name'] str_acct_name = str(lkp_acctName) fil_acct_name = str_acct_name.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_name + '","dataTemplate":"subGrName"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_name) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_AcctName = x.getResponse(EncryptMode) else: de_AcctName = '' return de_AcctName def decrypt_Phone(self, row): # Declaring Local Variable de_Phone = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_phone = row['Phone'] str_phone = str(lkp_phone) fil_phone = str_phone.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_phone + '","dataTemplate":"subGrPhone"}' # Identifying Length of the field len_acct_nbr = len(fil_phone) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_Phone = x.getResponse(EncryptMode) else: de_Phone = '' return de_Phone def decrypt_Email(self, row): # Declaring Local Variable de_Email = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_email = row['Email'] str_email = str(lkp_email) fil_email = str_email.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_email + '","dataTemplate":"subGrEmail"}' # Identifying Length of the field len_acct_nbr = len(fil_email) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_Email = x.getResponse(EncryptMode) else: de_Email = '' return de_Email def getEncrypt(self, df_payload): try: df_input = p.DataFrame() df_fin = p.DataFrame() # Assigning Target File Basic Name df_input = df_payload # Checking total count of rows count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) # Deriving rows df_input['Encrypt_Acct_Nbr'] = df_input.apply(lambda row: self.encrypt_acctNbr(row), axis=1) df_input['Encrypt_Name'] = df_input.apply(lambda row: self.encrypt_Name(row), axis=1) df_input['Encrypt_Phone'] = df_input.apply(lambda row: self.encrypt_Phone(row), axis=1) df_input['Encrypt_Email'] = df_input.apply(lambda row: self.encrypt_Email(row), axis=1) # Dropping original columns df_input.drop(['Acct_Nbr', 'Name', 'Phone', 'Email'], axis=1, inplace=True) # Renaming new columns with the old column names df_input.rename(columns={'Encrypt_Acct_Nbr':'Acct_Nbr'}, inplace=True) df_input.rename(columns={'Encrypt_Name': 'Name'}, inplace=True) df_input.rename(columns={'Encrypt_Phone': 'Phone'}, inplace=True) df_input.rename(columns={'Encrypt_Email': 'Email'}, inplace=True) # New Column List Orders column_order = ['Acct_Nbr', 'Name', 'Acct_Addr_1', 'Acct_Addr_2', 'Phone', 'Email', 'Serial_No'] df_fin = df_input.reindex(column_order, axis=1) return df_fin except Exception as e: df_error = p.DataFrame({'Acct_Nbr':str(e), 'Name':'', 'Acct_Addr_1':'', 'Acct_Addr_2':'', 'Phone':'', 'Email':'', 'Serial_No':''}) return df_error def getDecrypt(self, df_encrypted_payload): try: df_input = p.DataFrame() df_fin = p.DataFrame() # Assigning Target File Basic Name df_input = df_encrypted_payload # Checking total count of rows count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) # Deriving rows df_input['Decrypt_Acct_Nbr'] = df_input.apply(lambda row: self.decrypt_acctNbr(row), axis=1) df_input['Decrypt_Name'] = df_input.apply(lambda row: self.decrypt_Name(row), axis=1) df_input['Decrypt_Phone'] = df_input.apply(lambda row: self.decrypt_Phone(row), axis=1) df_input['Decrypt_Email'] = df_input.apply(lambda row: self.decrypt_Email(row), axis=1) # Dropping original columns df_input.drop(['Acct_Nbr', 'Name', 'Phone', 'Email'], axis=1, inplace=True) # Renaming new columns with the old column names df_input.rename(columns={'Decrypt_Acct_Nbr':'Acct_Nbr'}, inplace=True) df_input.rename(columns={'Decrypt_Name': 'Name'}, inplace=True) df_input.rename(columns={'Decrypt_Phone': 'Phone'}, inplace=True) df_input.rename(columns={'Decrypt_Email': 'Email'}, inplace=True) # New Column List Orders column_order = ['Acct_Nbr', 'Name', 'Acct_Addr_1', 'Acct_Addr_2', 'Phone', 'Email'] df_fin = df_input.reindex(column_order, axis=1) return df_fin except Exception as e: df_error = p.DataFrame({'Acct_Nbr':str(e), 'Name':'', 'Acct_Addr_1':'', 'Acct_Addr_2':'', 'Phone':'', 'Email':''}) return df_error |
Key lines to discuss –
Main two methods, we’ll be looking into & they are –
a. getEncrypt
b. getDecrypt
However, these two functions constructions are identical in nature. One is for encryption & the other one is decryption.
# Deriving rows df_input['Encrypt_Acct_Nbr'] = df_input.apply(lambda row: self.encrypt_acctNbr(row), axis=1) df_input['Encrypt_Name'] = df_input.apply(lambda row: self.encrypt_Name(row), axis=1) df_input['Encrypt_Phone'] = df_input.apply(lambda row: self.encrypt_Phone(row), axis=1) df_input['Encrypt_Email'] = df_input.apply(lambda row: self.encrypt_Email(row), axis=1)
As you can see, the application is processing row-by-row & column-by-column data transformations using look-up functions.
# Dropping original columns df_input.drop(['Acct_Nbr', 'Name', 'Phone', 'Email'], axis=1, inplace=True)
As the comment suggested, the application is dropping all the unencrypted source columns.
# Renaming new columns with the old column names df_input.rename(columns={'Encrypt_Acct_Nbr':'Acct_Nbr'}, inplace=True) df_input.rename(columns={'Encrypt_Name': 'Name'}, inplace=True) df_input.rename(columns={'Encrypt_Phone': 'Phone'}, inplace=True) df_input.rename(columns={'Encrypt_Email': 'Email'}, inplace=True)
Once, the application drops all the source columns, it will rename the new column names back to old columns & based on this data will be merged with the rest of the data from the source csv.
# New Column List Orders column_order = ['Acct_Nbr', 'Name', 'Acct_Addr_1', 'Acct_Addr_2', 'Phone', 'Email', 'Serial_No'] df_fin = df_input.reindex(column_order, axis=1)
Once, the application finished doing all these transformations, it will now re-sequence the order of the columns, which will create the same column order as it’s source csv files.
Similar logic is applicable for the decryption as well.
As we know, there are many look-up methods take part as part of this drive.
encrypt_acctNbr, encrypt_Name, encrypt_Phone, encrypt_Email
decrypt_acctNbr, decrypt_Name, decrypt_Phone, decrypt_Email
We’ll discuss only one method as these are completely identical.
# Capturing essential values EncryptMode = self.EncryptMode lkp_acctNbr = row['Acct_Nbr'] str_acct_nbr = str(lkp_acctNbr) fil_acct_nbr = str_acct_nbr.strip()
From the row, our application is extracting the relevant column. In this case, it is Acct_Nbr. And, then converts it to string & remove any unnecessary white space from it.
# Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_nbr + '","dataTemplate":"subGrAcct_Nbr"}'
Once extracted, the application will build the target JON string as per column data.
# Identifying Length of the field len_acct_nbr = len(fil_acct_nbr) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_AcctNbr = x.getResponse(EncryptMode) else: en_AcctNbr = ''
Based on the length of the extracted value, our application will trigger the individual JSON requests & will receive the data frame in response.
9. clsParallel.py (This script will use the queue to make asynchronous calls & perform the same encryption & decryption. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 |
############################################ #### Written By: SATYAKI DE #### #### Written On: 10-Feb-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### initiate the encrypt/decrypt class #### #### based on client supplied data. #### #### This script will use the advance #### #### queue & asynchronus calls to the #### #### API Server to process Encryption & #### #### Decryption on our csv files. #### ############################################ import pandas as p import clsWebService as cw import datetime from clsParam import clsParam as cf from multiprocessing import Lock, Process, Queue, freeze_support, JoinableQueue import gc import signal import time import os import queue import asyncio # Declaring Global Variable q = Queue() lock = Lock() finished_task = JoinableQueue() pending_task = JoinableQueue() sp_fin_dict = {} dp_fin_dict = {} # Disbling Warnings def warn(*args, **kwargs): pass import warnings warnings.warn = warn class clsParallel(object): def __init__(self): self.path = cf.config['PATH'] self.EncryptMode = str(cf.config['ENCRYPT_MODE']) self.DecryptMode = str(cf.config['DECRYPT_MODE']) self.num_worker_process = int(cf.config['NUM_OF_THREAD']) self.lock = Lock() # Lookup Methods for Encryption def encrypt_acctNbr(self, row): # Declaring Local Variable en_AcctNbr = '' json_source_str = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_acctNbr = row['Acct_Nbr'] str_acct_nbr = str(lkp_acctNbr) fil_acct_nbr = str_acct_nbr.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_nbr + '","dataTemplate":"subGrAcct_Nbr"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_nbr) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_AcctNbr = x.getResponse(EncryptMode) else: en_AcctNbr = '' fil_acct_nbr = '' return en_AcctNbr def encrypt_Name(self, row): # Declaring Local Variable en_AcctName = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_acctName = row['Name'] str_acct_name = str(lkp_acctName) fil_acct_name = str_acct_name.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_name + '","dataTemplate":"subGrName"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_name) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_AcctName = x.getResponse(EncryptMode) else: en_AcctName = '' return en_AcctName def encrypt_Phone(self, row): # Declaring Local Variable en_Phone = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_phone = row['Phone'] str_phone = str(lkp_phone) fil_phone = str_phone.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_phone + '","dataTemplate":"subGrPhone"}' # Identifying Length of the field len_acct_nbr = len(fil_phone) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_Phone = x.getResponse(EncryptMode) else: en_Phone = '' return en_Phone def encrypt_Email(self, row): # Declaring Local Variable en_Email = '' # Capturing essential values EncryptMode = self.EncryptMode lkp_email = row['Email'] str_email = str(lkp_email) fil_email = str_email.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_email + '","dataTemplate":"subGrEmail"}' # Identifying Length of the field len_acct_nbr = len(fil_email) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) en_Email = x.getResponse(EncryptMode) else: en_Email = '' return en_Email # Lookup Methods for Decryption def decrypt_acctNbr(self, row): # Declaring Local Variable de_AcctNbr = '' json_source_str = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_acctNbr = row['Acct_Nbr'] str_acct_nbr = str(lkp_acctNbr) fil_acct_nbr = str_acct_nbr.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_nbr + '","dataTemplate":"subGrAcct_Nbr"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_nbr) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_AcctNbr = x.getResponse(EncryptMode) else: de_AcctNbr = '' return de_AcctNbr def decrypt_Name(self, row): # Declaring Local Variable de_AcctName = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_acctName = row['Name'] str_acct_name = str(lkp_acctName) fil_acct_name = str_acct_name.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_acct_name + '","dataTemplate":"subGrName"}' # Identifying Length of the field len_acct_nbr = len(fil_acct_name) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_AcctName = x.getResponse(EncryptMode) else: de_AcctName = '' return de_AcctName def decrypt_Phone(self, row): # Declaring Local Variable de_Phone = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_phone = row['Phone'] str_phone = str(lkp_phone) fil_phone = str_phone.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_phone + '","dataTemplate":"subGrPhone"}' # Identifying Length of the field len_acct_nbr = len(fil_phone) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_Phone = x.getResponse(EncryptMode) else: de_Phone = '' return de_Phone def decrypt_Email(self, row): # Declaring Local Variable de_Email = '' # Capturing essential values EncryptMode = self.DecryptMode lkp_email = row['Email'] str_email = str(lkp_email) fil_email = str_email.strip() # Forming JSON String for this field json_source_str = '{"dataGroup":"GrDet","data":"' + fil_email + '","dataTemplate":"subGrEmail"}' # Identifying Length of the field len_acct_nbr = len(fil_email) # This will trigger the service if it has valid data if len_acct_nbr > 0: x = cw.clsWeb(json_source_str) de_Email = x.getResponse(EncryptMode) else: de_Email = '' return de_Email def getEncrypt(self, df_dict): try: en_fin_dict = {} df_input = p.DataFrame() df_fin = p.DataFrame() # Assigning Target File Basic Name for k, v in df_dict.items(): Process_Name = k df_input = v # Checking total count of rows count_row = int(df_input.shape[0]) print('Part number of records to process:: ', count_row) if count_row > 0: # Deriving rows df_input['Encrypt_Acct_Nbr'] = df_input.apply(lambda row: self.encrypt_acctNbr(row), axis=1) df_input['Encrypt_Name'] = df_input.apply(lambda row: self.encrypt_Name(row), axis=1) df_input['Encrypt_Phone'] = df_input.apply(lambda row: self.encrypt_Phone(row), axis=1) df_input['Encrypt_Email'] = df_input.apply(lambda row: self.encrypt_Email(row), axis=1) # Dropping original columns df_input.drop(['Acct_Nbr', 'Name', 'Phone', 'Email'], axis=1, inplace=True) # Renaming new columns with the old column names df_input.rename(columns={'Encrypt_Acct_Nbr':'Acct_Nbr'}, inplace=True) df_input.rename(columns={'Encrypt_Name': 'Name'}, inplace=True) df_input.rename(columns={'Encrypt_Phone': 'Phone'}, inplace=True) df_input.rename(columns={'Encrypt_Email': 'Email'}, inplace=True) # New Column List Orders column_order = ['Acct_Nbr', 'Name', 'Acct_Addr_1', 'Acct_Addr_2', 'Phone', 'Email', 'Serial_No'] df_fin = df_input.reindex(column_order, axis=1) sp_fin_dict[Process_Name] = df_fin return sp_fin_dict except Exception as e: df_error = p.DataFrame({'Acct_Nbr':str(e), 'Name':'', 'Acct_Addr_1':'', 'Acct_Addr_2':'', 'Phone':'', 'Email':'', 'Serial_No':''}) sp_fin_dict[Process_Name] = df_error return sp_fin_dict async def produceEncr(self, queue, l_dict): m_dict = {} m_dict = self.getEncrypt(l_dict) for k, v in m_dict.items(): item = k print('producing {}...'.format(item)) await queue.put(m_dict) async def consumeEncr(self, queue): result_dict = {} while True: # wait for an item from the producer sp_fin_dict.update(await queue.get()) # process the item for k, v in sp_fin_dict.items(): item = k print('consuming {}...'.format(item)) # Notify the queue that the item has been processed queue.task_done() async def runEncrypt(self, n, df_input): l_dict = {} queue = asyncio.Queue() # schedule the consumer consumer = asyncio.ensure_future(self.consumeEncr(queue)) start_pos = 0 end_pos = 0 num_worker_process = n count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) interval = int(count_row / num_worker_process) + 1 actual_worker_task = int(count_row / interval) + 1 for i in range(actual_worker_task): name = 'Task-' + str(i) if ((start_pos + interval) < count_row): end_pos = start_pos + interval else: end_pos = start_pos + (count_row - start_pos) print("start_pos: ", start_pos) print("end_pos: ", end_pos) split_df = df_input.iloc[start_pos:end_pos] l_dict[name] = split_df if ((start_pos > count_row) | (start_pos == count_row)): break else: start_pos = start_pos + interval # run the producer and wait for completion await self.produceEncr(queue, l_dict) # wait until the consumer has processed all items await queue.join() # the consumer is still awaiting for an item, cancel it consumer.cancel() return sp_fin_dict def getEncryptParallel(self, df_payload): l_dict = {} data_dict = {} min_val_list = {} cnt = 1 num_worker_process = self.num_worker_process actual_worker_task = 0 number_of_processes = 4 processes = [] split_df = p.DataFrame() df_ret = p.DataFrame() dummy_df = p.DataFrame() # Assigning Target File Basic Name df_input = df_payload # Checking total count of rows count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) interval = int(count_row / num_worker_process) + 1 actual_worker_task = int(count_row/interval) + 1 loop = asyncio.get_event_loop() loop.run_until_complete(self.runEncrypt(actual_worker_task, df_input)) loop.close() for k, v in sp_fin_dict.items(): min_val_list[int(k.replace('Task-', ''))] = v min_val = min(min_val_list, key=int) print("Minimum Index Value: ", min_val) for k, v in sorted(sp_fin_dict.items(), key=lambda k: int(k[0].replace('Task-', ''))): if int(k.replace('Task-', '')) == min_val: df_ret = sp_fin_dict[k] else: d_frames = [df_ret, sp_fin_dict[k]] df_ret = p.concat(d_frames) return df_ret def getDecrypt(self, df_encrypted_dict): try: de_fin_dict = {} df_input = p.DataFrame() df_fin = p.DataFrame() # Assigning Target File Basic Name for k, v in df_encrypted_dict.items(): Process_Name = k df_input = v # Checking total count of rows count_row = int(df_input.shape[0]) print('Part number of records to process:: ', count_row) if count_row > 0: # Deriving rows df_input['Decrypt_Acct_Nbr'] = df_input.apply(lambda row: self.decrypt_acctNbr(row), axis=1) df_input['Decrypt_Name'] = df_input.apply(lambda row: self.decrypt_Name(row), axis=1) df_input['Decrypt_Phone'] = df_input.apply(lambda row: self.decrypt_Phone(row), axis=1) df_input['Decrypt_Email'] = df_input.apply(lambda row: self.decrypt_Email(row), axis=1) # Dropping original columns df_input.drop(['Acct_Nbr', 'Name', 'Phone', 'Email'], axis=1, inplace=True) # Renaming new columns with the old column names df_input.rename(columns={'Decrypt_Acct_Nbr':'Acct_Nbr'}, inplace=True) df_input.rename(columns={'Decrypt_Name': 'Name'}, inplace=True) df_input.rename(columns={'Decrypt_Phone': 'Phone'}, inplace=True) df_input.rename(columns={'Decrypt_Email': 'Email'}, inplace=True) # New Column List Orders column_order = ['Acct_Nbr', 'Name', 'Acct_Addr_1', 'Acct_Addr_2', 'Phone', 'Email', 'Serial_No'] df_fin = df_input.reindex(column_order, axis=1) de_fin_dict[Process_Name] = df_fin return de_fin_dict except Exception as e: df_error = p.DataFrame({'Acct_Nbr': str(e), 'Name': '', 'Acct_Addr_1': '', 'Acct_Addr_2': '', 'Phone': '', 'Email': '', 'Serial_No': ''}) de_fin_dict[Process_Name] = df_error return de_fin_dict async def produceDecr(self, queue, l_dict): m_dict = {} m_dict = self.getDecrypt(l_dict) for k, v in m_dict.items(): item = k print('producing {}...'.format(item)) await queue.put(m_dict) async def consumeDecr(self, queue): result_dict = {} while True: # wait for an item from the producer dp_fin_dict.update(await queue.get()) # process the item for k, v in dp_fin_dict.items(): item = k print('consuming {}...'.format(item)) # Notify the queue that the item has been processed queue.task_done() async def runDecrypt(self, n, df_input): l_dict = {} queue = asyncio.Queue() # schedule the consumer consumerDe = asyncio.ensure_future(self.consumeDecr(queue)) start_pos = 0 end_pos = 0 num_worker_process = n count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) interval = int(count_row / num_worker_process) + 1 actual_worker_task = int(count_row / interval) + 1 for i in range(actual_worker_task): name = 'Task-' + str(i) if ((start_pos + interval) < count_row): end_pos = start_pos + interval else: end_pos = start_pos + (count_row - start_pos) print("start_pos: ", start_pos) print("end_pos: ", end_pos) split_df = df_input.iloc[start_pos:end_pos] l_dict[name] = split_df if ((start_pos > count_row) | (start_pos == count_row)): break else: start_pos = start_pos + interval # run the producer and wait for completion await self.produceDecr(queue, l_dict) # wait until the consumer has processed all items await queue.join() # the consumer is still awaiting for an item, cancel it consumerDe.cancel() return dp_fin_dict def getDecryptParallel(self, df_payload): l_dict = {} data_dict = {} min_val_list = {} cnt = 1 num_worker_process = self.num_worker_process actual_worker_task = 0 number_of_processes = 4 processes = [] split_df = p.DataFrame() df_ret_1 = p.DataFrame() dummy_df = p.DataFrame() # Assigning Target File Basic Name df_input = df_payload # Checking total count of rows count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) interval = int(count_row / num_worker_process) + 1 actual_worker_task = int(count_row/interval) + 1 loop_1 = asyncio.new_event_loop() asyncio.set_event_loop(asyncio.new_event_loop()) loop_2 = asyncio.get_event_loop() loop_2.run_until_complete(self.runDecrypt(actual_worker_task, df_input)) loop_2.close() for k, v in dp_fin_dict.items(): min_val_list[int(k.replace('Task-', ''))] = v min_val = min(min_val_list, key=int) print("Minimum Index Value: ", min_val) for k, v in sorted(dp_fin_dict.items(), key=lambda k: int(k[0].replace('Task-', ''))): if int(k.replace('Task-', '')) == min_val: df_ret_1 = dp_fin_dict[k] else: d_frames = [df_ret_1, dp_fin_dict[k]] df_ret_1 = p.concat(d_frames) return df_ret_1 |
I don’t want to discuss any more look-up methods as the post is already pretty big. Only address a few critical lines
Under getEncryptParallel, the following lines are essential –
# Checking total count of rows count_row = df_input.shape[0] print('Total number of records to process:: ', count_row) interval = int(count_row / num_worker_process) + 1 actual_worker_task = int(count_row/interval) + 1
Based on the dataframe total number of records, our application will split that main dataframe into parts of sub dataframe & then pass them using queue by asynchronous queue calls.
loop = asyncio.get_event_loop() loop.run_until_complete(self.runEncrypt(actual_worker_task, df_input)) loop.close()
Initiating our queue methods & passing our dataframe to it.
for k, v in sorted(sp_fin_dict.items(), key=lambda k: int(k[0].replace('Task-', ''))): if int(k.replace('Task-', '')) == min_val: df_ret = sp_fin_dict[k] else: d_frames = [df_ret, sp_fin_dict[k]] df_ret = p.concat(d_frames)
Our application is sending & receiving data using the dictionary. The reason is – we’re not expecting data that we may get it from our server in sequence. Instead, we’re hoping the data will be random. Hence, using keys, we’re maintaining our final sequence & that will ensure our application to joining back to the correct sets of source data, which won’t be the candidate for any encryption/decryption.
Let’s discuss runEncrypt method.
for i in range(actual_worker_task): name = 'Task-' + str(i) if ((start_pos + interval) < count_row): end_pos = start_pos + interval else: end_pos = start_pos + (count_row - start_pos) print("start_pos: ", start_pos) print("end_pos: ", end_pos) split_df = df_input.iloc[start_pos:end_pos] l_dict[name] = split_df if ((start_pos > count_row) | (start_pos == count_row)): break else: start_pos = start_pos + interval
Here, our application is splitting our source data frame into multiple sub dataframe & then it can be processed in parallel using queues.
# run the producer and wait for completion await self.produceEncr(queue, l_dict) # wait until the consumer has processed all items await queue.join()
Invoking the encryption-decryption process using queues. The last line is significant. The queue will not destroy until all the item produced/place into the queue are not consumed. Hence, your main program will wait until it processes all the records of your dataframe.
Two methods named produceEncr & consumeEncr mainly used for placing an item inside the queue & then after encryption/decryption it will retrieve it from the queue.
Few important lines from both the methods are –
#produceEncr await queue.put(m_dict) #consumeEncr # wait for an item from the producer sp_fin_dict.update(await queue.get())# Notify the queue that the item has been processed queue.task_done()
From the first two lines, one can see that the application will place its item into the queue. Rests are the lines from the other methods. Our application is pouring the data into the dictionary, which will be returned to our calling methods. The last line is significantly essential. Without the task_done process, the queue will continue to wait for upcoming items. Hence, that will trigger infinite wait or sometimes deadlock.
10. callClient.py (This script will trigger both the serial & parallel process of encryption one by one & finally capture some statistics. Hence, the name comes into the picture.)
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 |
############################################ #### Written By: SATYAKI DE #### #### Written On: 10-Feb-2019 #### #### Package Flask package needs to #### #### install in order to run this #### #### script. #### #### #### #### Objective: This script will #### #### initiate the encrypt/decrypt class #### #### based on client supplied data. #### ############################################ import pandas as p import clsSerial as cs import time import datetime from clsParam import clsParam as cf import clsParallel as cp import sys def main(): source_df = p.DataFrame() encrypted_df = p.DataFrame() source_encrypted_df = p.DataFrame() decrypted_df = p.DataFrame() encrypted_parallel_df = p.DataFrame() source_encrypted_parallel_df = p.DataFrame() decrypted_parallel_df = p.DataFrame() ############################################################################### ##### Start Of Serial Encryption Methods ###### ############################################################################### print("-" * 157) startEnTime = time.time() srcFile = 'acct_addr_20180106' srcFileWithPath = str(cf.config['SRC_DIR']) + srcFile + '.csv' print("Calling Serial Process to Encrypt!") # Reading source file source_df = p.read_csv(srcFileWithPath, index_col=False) # Calling Encrypt Methods x = cs.clsSerial() encrypted_df = x.getEncrypt(source_df) # Handling Multiple source files var = datetime.datetime.now().strftime("%H.%M.%S") print('Target File Extension will contain the following:: ', var) targetFile = srcFile + '_Serial_' taregetFileWithPath = str(cf.config['FIN_DIR']) + targetFile + var + '.csv' # Finally Storing them into csv encrypted_df.to_csv(taregetFileWithPath, index=False) endEnTime = time.time() z1 = str(endEnTime - startEnTime) print("Over All Encrypt Process Time:", z1) time.sleep(20) ############################################################################### ##### Start Of Serial Decryption Methods ###### ############################################################################### print("-" * 157) startDeTime = time.time() srcFileWithPath = taregetFileWithPath print("Calling Serial Process to Decrypt!") # Reading source file source_encrypted_df = p.read_csv(srcFileWithPath, index_col=False) # Calling Encrypt Methods x = cs.clsSerial() decrypted_df = x.getDecrypt(source_encrypted_df) targetFile = srcFile + '_restored_' taregetFileWithPath = str(cf.config['FIN_DIR']) + targetFile + var + '.csv' # Finally Storing them into csv decrypted_df.to_csv(taregetFileWithPath, index=False) endDeTime = time.time() z2 = str(endDeTime - startDeTime) print("Over All Decrypt Process Time:", z2) print("-" * 157) ############################################################################### ##### End Of Serial Encryption/Decryption Methods ###### ############################################################################### time.sleep(20) ############################################################################### ##### Start Of Parallel Encryption Methods ###### ############################################################################### print("-" * 157) startEnTime = time.time() srcFileWithPath = str(cf.config['SRC_DIR']) + srcFile + '.csv' print("Calling Serial Process to Encrypt!") # Reading source file source_df = p.read_csv(srcFileWithPath, index_col=False) # Calling Encrypt Methods x = cp.clsParallel() encrypted_parallel_df = x.getEncryptParallel(source_df) # Handling Multiple source files var = datetime.datetime.now().strftime("%H.%M.%S") print('Target File Extension will contain the following:: ', var) targetFile = srcFile + '_Parallel_' taregetFileWithPath = str(cf.config['FIN_DIR']) + targetFile + var + '.csv' # Finally Storing them into csv encrypted_parallel_df.to_csv(taregetFileWithPath, index=False) endEnTime = time.time() z3 = str(endEnTime - startEnTime) print("Over All Encrypt Process Time:", z3) time.sleep(20) ############################################################################### ##### Start Of Serial Decryption Methods ###### ############################################################################### print("-" * 157) startDeTime = time.time() srcFileWithPath = taregetFileWithPath print("Calling Parallel Process to Decrypt!") # Reading source file source_encrypted_parallel_df = p.read_csv(srcFileWithPath, index_col=False) # Calling Encrypt Methods x = cp.clsParallel() decrypted_parallel_df = x.getDecryptParallel(source_encrypted_parallel_df) targetFile = srcFile + '_restored_' taregetFileWithPath = str(cf.config['FIN_DIR']) + targetFile + var + '.csv' # Finally Storing them into csv decrypted_parallel_df.to_csv(taregetFileWithPath, index=False) endDeTime = time.time() z4 = str(endDeTime - startDeTime) print("Over All Decrypt Process Time:", z4) print("-" * 157) ############################################################################### ##### End Of Parallel Encryption/Decryption Methods ###### ############################################################################### ############################################################################### ##### Final Statistics between Serial & Parallel loading. ###### ############################################################################### print("-" * 157) print("Serial Encryption:: ", z1) print("Serial Decryption:: ", z2) print("-" * 157) print("Parallel Encryption:: ", z3) print("Parallel Decryption:: ", z4) print("-" * 157) if __name__ == '__main__': main() |
As you can see, we’ve triggered both the application using the main callable scripts.
Let’s explore the output –
Windows:
Mac:
Note that you have to open two different windows or MAC terminal. One will trigger the server & others will trigger the client to simulate this.
Server:
Clients:
Win:
MAC:
So, finally, we’ve achieved our goal. So, today we’ve done a bit long but beneficial & advanced concepts of crossover stones from our python verse. 🙂
Lot more innovative posts are coming.
Till then – Happy Avenging!
You must be logged in to post a comment.