Updated bug

Reviewed-on: #21

.gitea/workflows/build.yaml

@@ -1,19 +1,28 @@
 name: Build
-on: push
+on:
+  push:
+    tags:
+    - '*'
 
 jobs:
-  # build-linux-binary:
-  #   runs-on: ubuntu-latest
-  #   steps:
-  #   - uses: actions/checkout@v4
-  #   - uses: actions/setup-python@v5
-  #     with:
-  #       python-version: '3.12.4'
-  #       cache: 'pip' # caching pip dependencies
-  #   - run: apt-get update
-  #   - run: apt-get install unixodbc -y
-  #   - run: pip install -r requirements.txt
-  #   - run: pyinstaller --noconfirm --onefile --console ${{ gitea.workspace }}/inex.py
+  build-linux-binary:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write # release changes require contents write
+    steps:
+    - uses: actions/checkout@v4
+    - uses: actions/setup-python@v5
+      with:
+        python-version: '3.12.4'
+        cache: 'pip' # caching pip dependencies
+    - run: lsb_release -a
+    - run: apt-get update
+    - run: apt-get install unixodbc -y
+    - run: pip install -r requirements.txt
+    - run: pyinstaller --noconfirm --onefile --console ${{ gitea.workspace }}/inex.py
+    - uses: softprops/action-gh-release@v2
+      with:
+        files: ${{ gitea.workspace }}/dist/inex
 
   build-windows-binary:
     runs-on: windows
@@ -28,6 +37,7 @@ jobs:
       - run: python -m pip install -r requirements.txt
       - run: pyinstaller --noconfirm --onefile --console ${{ gitea.workspace }}/inex.py
       - uses: softprops/action-gh-release@v2
-        if: startsWith(gitea.ref, 'refs/tags/')
         with:
-          files: ${{ gitea.workspace }}/dist/inex.exe
+          files: |
+            ${{ gitea.workspace }}/dist/inex.exe
+            ${{ gitea.workspace }}/config.toml.example

LICENSE

@@ -209,7 +209,7 @@ If you develop a new program, and you want it to be of the greatest possible use
 To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the “copyright” line and a pointer to where the full notice is found.
 
      Inex
-     Copyright (C) 2024  jblu
+     Copyright (C) 2024  Jonathan Branan
 
      This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
 
@@ -221,7 +221,7 @@ Also add information on how to contact you by electronic and paper mail.
 
 If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode:
 
-     Inex  Copyright (C) 2024  jblu
+     Inex  Copyright (C) 2024  Jonathan Branan
      This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
      This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details.
 

README.md

@@ -1,34 +1,93 @@
 # Inex
 
-Information Exchange - Pull data from EFT ARM then dump it to a json file
+### Information Exchange - Ingest ARM data into EFC
+This application is designed to pull data from an Microsoft SQL database, reformat it, and then send that data via the web to the Event Fusion Center. It's designed to be performant. The embedded query doesn't return unneccesary data and data is written to memory before being pushed into EFC. Initially you may have to pull a large amount of days so the system is caught up but the sweet spot would be to pull a set of data every day. 
 
-# Data Map:
-## tbl_ProtocolCommands
-- ProtocolCommandID
-- Time_stamp
-- RemoteIP
-- RemotePort
-- LocalIP
-- LocalPort
-- Protocol
-- SiteName
-- Command
-- CommandParameters
-- FileName
-- VirtualFolderName
-- PhysicalFolderName
-- IsInternal
-- FileSize
-- TransferTime
-- BytesTransferred
-- ResultID
-- TransactionID
-- Description
-- Actor
-## tbl_Transactions
-- TransactionID
-- ParentTransactionID
-- TransactionObject
-- TransactionGUID
-- NodeName
-- time_stamp
+## Build from source
+You will need to install git and clone the repository:
+
+`git clone https://git.jonb.io/jblu/Inex.git`
+
+Alternitively you can download the files from [the releases page](https://git.jonb.io/jblu/Inex/releases).
+
+Then follow OS specific instructions. These are taken directly from the steps used in automation to build the executables found in the releases page.
+##### Windows
+
+You can find the requirements.txt in the repository.
+
+`python -m pip install -r requirements.txt`
+
+`pyinstaller --noconfirm --onefile --console path/to/inex.py`
+
+##### Linux
+Update Linux Distro. This is Ubuntu specific. Please check the package management tool in your specific version.
+
+`apt-get update`
+
+You need unixodbc or else pyodbc cannot install.
+
+`apt-get install unixodbc -y`
+
+You can find the requirements.txt in the repository.
+
+`pip install -r requirements.txt`
+
+`pyinstaller --noconfirm --onefile --console path/to/inex.py`
+
+## Setup
+You will need a *config.toml* file in the same directory where *inex.py* or inex executable is. It's recommended to rename the existing config.toml.example file to save sometime and avoid omitting any data.
+
+> If the application doesn't find the *config.toml* at the time of execution, it will not continue.
+
+#### Config.toml
+| Table | Purpose |
+|-|-|
+| fortraPlatform | Fortra Specific data |
+| database | MSSQL Configuration |
+| immutables | Data that must be included but is not provided by the source database |
+| output | If and where to write files|
+| logging | Set if, where and level of logging |
+
+The following settings are not obvious as to how they affect the application.
+> Note the #comments
+```
+[fortraPlatform]
+selectedPlatform = "dev" # This will modify which environment the data is pushed to. The tenant_id and secret must be manually modified.
+
+[database]
+overrideEmbeddedquery = true # Choose if embedded query should be overridden.
+daysTopull = 30 # This setting is only related to the embedded query. Please note this will not affect query provided in config.toml
+driver = "ODBC Driver 18 for SQL Server" # Select which windows driver should be used. This one is recommended.
+
+[output]
+pushToplatform = false # if true, send data to fortraPlatform setting to false is useful in dry-runs.
+dumpTojson = true # if true, write data to json file
+token = "./.token" # Recommended to leave as-is
+
+```
+
+## Usage
+
+### Windows
+##### Run inex.py 
+1. Download [source](https://git.jonb.io/jblu/Inex/releases)
+2. `cd C:\path\to\Inex`
+3. `python inex.py`
+
+OR
+
+##### Run inex.exe
+1. Download [source](https://git.jonb.io/jblu/Inex/releases)
+2. `cd C:\path\to\Inex.exe`
+3. CMD `.\inex.exe`
+
+### Linux
+##### Run inex.py
+1. Download [source](https://git.jonb.io/jblu/Inex/releases)
+2. `cd /path/to/Inex`
+3. `python ./inex.py`
+
+OR
+1. Download [source](https://git.jonb.io/jblu/Inex/releases)
+2. `cd /path/to/Inex`
+3. RUN `./inex`

config.toml.example

@@ -1,6 +1,33 @@
 [fortraPlatform]
 selectedPlatform = "dev"
 
+[output]
+pushToplatform = false
+dumpTojson = true
+filename ="./data.json"
+token = "./.token"
+
+[logging]
+useLog = true
+logLevel = "debug"
+logPath = "./inex.log"
+
+[database]
+overrideEmbeddedquery = false
+daysTopull = 20
+driver = "ODBC Driver 18 for SQL Server"
+server = "192.168.x.x"
+database = "EFTDB"
+user = "a"
+password = "a"
+query = """DECLARE @stopTime DATETIME2
+SET @stopTime=DATEADD(DAY, -30, GETDATE())
+SELECT p.ProtocolCommandID, t.Time_stamp, p.RemoteIP, p.RemotePort, p.LocalIP, p.LocalPort, p.Protocol, p.SiteName, p.Command, p.FileName, p.PhysicalFolderName, p.VirtualFolderName, p.FileSize, p.TransferTime, p.BytesTransferred, p.Description, p.ResultID, t.TransactionID, p.Actor, t.TransactionObject, t.NodeName, t.TransactionGUID, a.Protocol user_type
+FROM tbl_Transactions t
+     Full JOIN tbl_ProtocolCommands p ON(t.TransactionID=p.TransactionID)
+     Full JOIN tbl_Authentications a ON(t.TransactionID=a.TransactionID)
+WHERE p.Time_stamp>@stopTime AND p.Command IS NOT NULL"""
+
 [fortraPlatform.dev]
 idp = "https://foundation.foundation-dev.cloudops.fortradev.com/idp/realms/products/protocol/openid-connect/token"
 efc_url = "https://efc.efc-dev.cloudops.fortradev.com"
@@ -22,56 +49,6 @@ tenant_id = ""
 client_id = "eft-event-generator-confidential"
 secret = ""
 
-[database]
-driver = "ODBC Driver 18 for SQL Server"
-server = "192.168.x.x"
-database = "EFTDB"
-user = "a"
-password = "a"
-query = """DECLARE	@stopTime DATETIME2
-SET @stopTime = DATEADD(DAY, -30, GETDATE())
-SELECT p.[ProtocolCommandID]
-      ,t.[Time_stamp]
-      ,p.[RemoteIP]
-      ,p.[RemotePort]
-      ,p.[LocalIP]
-      ,p.[LocalPort]
-      ,p.[Protocol]
-      ,p.[SiteName]
-      ,p.[Command]
-      ,p.[CommandParameters]
-      ,p.[FileName]
-      ,p.[VirtualFolderName]
-      ,p.[PhysicalFolderName]
-      ,p.[IsInternal]
-      ,p.[FileSize]
-      ,p.[TransferTime]
-      ,p.[BytesTransferred]
-      ,p.[ResultID]
-      ,t.[TransactionID]
-      ,p.[Description]
-      ,p.[Actor]
-	  ,t.ParentTransactionID
-	  ,t.TransactionObject
-	  ,t.NodeName
-	  ,t.TransactionGUID
-	  ,a.Protocol user_type
-  FROM [EFTDB].[dbo].[tbl_Transactions] t Full JOIN tbl_ProtocolCommands p ON (t.TransactionID = p.TransactionID) Full join tbl_Authentications a ON (t.TransactionID = a.TransactionID)
-  WHERE p.Time_stamp > @stopTime"""
-
 [immutables] 
-prd_instance_id = 1
-product_guid = "asdf"
-product_name = "EFT"
-product_version ="8.1.0.9"
-
-[output]
-pushToplatform = true
-dumpTojson = true
-filename ="./data.json"
-token = "./.token"
-
-[logging]
-use_log = true
-logLevel = "debug"
-logPath = "./inex.log"
+product_name = "GlobalScape EFT"
+prd_ext_tenant_name = "GlobalScape EFT"

executable/config.toml.example

@@ -1,35 +0,0 @@
-[database]
-driver = "ODBC Driver 18 for SQL Server"
-server = "192.168.x.x"
-database = "EFTDB"
-user = "a"
-password = "a"
-query = """SELECT TOP (1) [ProtocolCommandID]
-      ,[Time_stamp]
-      ,[RemoteIP]
-      ,[RemotePort]
-      ,[LocalIP]
-      ,[LocalPort]
-      ,[Protocol]
-      ,[SiteName]
-      ,[Command]
-      ,[CommandParameters]
-      ,[FileName]
-      ,[VirtualFolderName]
-      ,[PhysicalFolderName]
-      ,[IsInternal]
-      ,[FileSize]
-      ,[TransferTime]
-      ,[BytesTransferred]
-      ,[ResultID]
-      ,[TransactionID]
-      ,[Description]
-      ,[Actor]
-  FROM [EFTDB].[dbo].[tbl_ProtocolCommands]"""
-[output]
-filename ="./data.json"
-
-[logging]
-use_log = true
-logLevel = "debug"
-logPath = "./inex.log"

inex.py

@@ -1,23 +1,24 @@
 import pyodbc
 import os
 import logging
-import datetime
 import tomllib
 from inexLogging import inexLog
 import inexConnect
 from inexDataModel import dataTemplate
 from inexDataProcessing import processData
 import json
-import decimal
 import requests
 import inexEncoder
+import inexSqlquery
 
 class Inex:
     def __init__(self):
-        """Initilize config, calls functions from inex-connect.py and inex-logging.py"""
+        """Initilize config, calls functions from inexConnect.py, inexLogging.py 
+        inexDataModel.py, inexDataProcessing.py, inexEncoder.py and inexSqlquery.py
+        Main logic of the program. Requires a config.toml in the same directory it's
+        being run from."""
         # assign libraries
         self.db = pyodbc
-        self.tm = datetime
         self.il = logging
         self.ic = inexConnect
         self.r = requests
@@ -25,13 +26,17 @@ class Inex:
         self.os = os
         self.j = json
         self.e = inexEncoder.Encoder
+        self.sq = inexSqlquery
 
+        # Check if local config file exists.
         if self.os.path.exists('./config.toml'):
             config_file_path = './config.toml'
             with open(config_file_path, 'rb') as c:
                 self.config = self.tl.load(c)
         
         # set config
+        try:
+            if self.config:
                 self.dbDriver = self.config["database"]["driver"]
                 self.dbServer = self.config["database"]["server"]
                 self.dbDatabase = self.config["database"]["database"]
@@ -42,14 +47,20 @@ class Inex:
                 self.useLog = self.config["logging"]["useLog"]
                 self.logPath = self.config["logging"]["logPath"]
                 self.logLevel = self.config["logging"]["logLevel"]
-        self.prdInstanceID = self.config["immutables"]["prd_instance_id"]
-        self.productGUID = self.config["immutables"]["product_guid"]
+                self.prdExttenantname = self.config["immutables"]["prd_ext_tenant_name"]
                 self.productName = self.config["immutables"]["product_name"]
-        self.productVersion = self.config["immutables"]["product_version"]
                 self.tokenFilepath = self.config["output"]["token"]
                 self.selectedPlatform = self.config["fortraPlatform"]["selectedPlatform"]
                 self.writeJsonfile = self.config["output"]["dumpTojson"]
                 self.pushToplatform = self.config["output"]["pushToplatform"]
+                self.queryOverride = self.config["database"]["overrideEmbeddedquery"]
+                self.queryDaystopull = self.config["database"]["daysTopull"]
+        except Exception as e:
+            print("No config.toml or possibly missing settings in the file. Please use config.toml.example file and configure appropriately")
+            self.il.error(e)
+            print(e)
+
+            exit(1)
 
         if "dev" in self.selectedPlatform.lower():
             self.platformConfig = self.config["fortraPlatform"]["dev"]
@@ -57,25 +68,27 @@ class Inex:
             self.platformConfig = self.config["fortraPlatform"]["stage"]
         if "prod" in self.selectedPlatform.lower():
             self.platformConfig = self.config["fortraPlatform"]["prod"]
-        # print(self.platformConfig)
 
         #Setup logging
         inexLog(self)
 
         # create the connection to the database
-        self.cursor = self.ic.connectDatabase(self, self.db, self.dbDriver, self.dbServer, self.dbDatabase, self.dbUser, self.dbPassword)
+        self.cursor = self.ic.inexSql.connectDatabase(self, self.db, self.dbDriver, self.dbServer, self.dbDatabase, self.dbUser, self.dbPassword)
 
-        self.data = self.ic.databaseQuery(self, self.cursor, self.dbQuery)
+        # Query the database
+        self.data = self.ic.inexSql.databaseQuery(self, self.cursor, self.sq.sqlQuerymodel.queryData(self.queryOverride,self.dbQuery, self.queryDaystopull))
 
-        self.modifiedData = processData(self.data, dataTemplate, prd_instance_id=self.prdInstanceID,\
-                                         product_guid=self.productGUID,product_name=self.productName,product_version=self.productVersion)
+        # Modify the data to meet EFC requirements
+        self.modifiedData = processData(self.data, dataTemplate, prd_ext_tenant_name=self.prdExttenantname,product_name=self.productName,\
+                                        prd_ext_tenant_id=self.platformConfig["tenant_id"])
 
+        # Push data to EFC. Check for local Auth token -> Authenticate if needed -> push data
         if self.pushToplatform:
-            inexConnect.fortraEFC.pushPayload(self)
+            inexConnect.fortraEFC.__init__(self)
 
-        # TODO: move this to its own function
         if self.useLog:
             self.il.warning(f"Writing to '{self.outputFile}'.")
+        # Write data to json
         if self.writeJsonfile:
             with open(self.outputFile, "w") as f:
                 self.j.dump(self.modifiedData, f, indent = 2, cls=self.e)

inexConnect.py

@@ -1,3 +1,4 @@
+class inexSql:
     def connectDatabase(self, lib, driver, server, database, user, password):
         """Connects to the database. Requires a windows driver to do so.
         Typically there is one installed by default"""
@@ -19,6 +20,7 @@ def connectDatabase(self, lib, driver, server, database, user, password):
         return  cursor
 
     def databaseQuery(self, cursor, query, args=()):
+        """Use the database connection to send a query."""
         if self.useLog:
             self.il.debug(f"Query:")
             self.il.debug(query)
@@ -42,32 +44,54 @@ def databaseQuery(self, cursor, query, args=()):
         return r
 
 class fortraEFC:
-    def getToken(self):
-        self.tokenData = self.r.post(self.platformConfig["idp"], data={"grant_type":"client_credentials",\
-                                                                              "client_id": self.platformConfig["client_id"],\
-                                                                              "client_secret": self.platformConfig["secret"],})
-    def writeToken(self):
+    """Class to connect to fortra EFC. It will authenticate and push rest payloads. 
+    Writes a .token file to the same directory script was run in."""
+    def __init__(self):
+        """This is the logic for how authentication is handled"""
+        # Check if .token file is present
+        if fortraEFC.readToken(self) == 1:
+            # Get fresh token. First run.
             fortraEFC.getToken(self)
-        with open(self.tokenFilepath, "w") as f:
-            self.j.dump(self.tokenData.json(), f, indent = 2)
+            fortraEFC.writeToken(self)
+        # Push data with token
+        self.pushPayloadresponse = fortraEFC.pushPayload(self)
+        if self.pushPayloadresponse == 401:
+            fortraEFC.getToken(self)
+            fortraEFC.writeToken(self)
+            fortraEFC.pushPayload(self)
 
     def readToken(self):
+        """Looks locally for a .token file. Returns a numeral code
+        for logic in the init method."""
         if self.os.path.exists(self.tokenFilepath):
             with open(self.tokenFilepath, 'rb') as t:
                 self.tokenData = self.j.load(t)
-                # print(self.tokenData["access_token"])
+                self.il.debug(f'readToken {self.tokenData["access_token"]}')
+            return 0
         else:
-            fortraEFC.writeToken(self)
+            return 1
+    
+    def getToken(self):
+        """Gets a token from fortra idp."""
+        self.tokenData = self.r.post(self.platformConfig["idp"], data={"grant_type":"client_credentials",\
+                                                                              "client_id": self.platformConfig["client_id"],\
+                                                                              "client_secret": self.platformConfig["secret"],})
+        self.tokenData = self.tokenData.json()
+        self.il.debug(f'getToken {self.tokenData["access_token"]}')
+
+    def writeToken(self):
+        """Writes a token to a local file named '.token'."""
+        fortraEFC.getToken(self)
+        with open(self.tokenFilepath, "w") as f:
+            self.j.dump(self.tokenData, f, indent = 2)
+            self.il.debug(f'writeToken {self.tokenData["access_token"]}')
 
     def pushPayload(self):
-        fortraEFC.readToken(self)
-        try:
+        """Sends data to fortra EFC. Requires a token from the idp."""
+        self.il.debug(f'pushPayload {self.tokenData["access_token"]}')
         url = f'{self.platformConfig["efc_url"]}/api/v1/unity/data/{self.platformConfig["tenant_id"]}/machine_event'
-            pushPayloadResponse = self.r.post(url, headers={'Authorization': f'bearer {self.tokenData["access_token"]}'},\
-                                               json=self.j.dumps(self.modifiedData,indent = 2, cls=self.e))
+        pushPayloadResponse = self.r.post(url, headers={'Authorization': f'Bearer {self.tokenData["access_token"]}'},\
+                                           data=self.j.dumps(self.modifiedData, cls=self.e))
+        self.il.debug(pushPayloadResponse.status_code)
+        self.il.debug(pushPayloadResponse.text)
         return pushPayloadResponse.status_code
-        except self.r.exceptions.HTTPError as errh:
-            print ("Http Error:",errh)
-            if "401" in errh:
-                fortraEFC.writeToken(self)
-                fortraEFC.pushPayload(self)

inexDataModel.py

@@ -1,48 +1,195 @@
-def dataTemplate(**kwargs):
-    """Expects the following keyword arguments:
-    status,status_detail,status_code,file_size,file_path,file_virtual_path,file_name,
-    guid,ref_id,prd_instance_id,product_guid,product_name,product_version,node_name,
-    src_endpoint_port,src_endpoint_ip,dst_endpoint_port,dst_endpoint_ip,dst_endpoint_type,
-    session_uid,bytes_out,transfer_time,time,user_type,user_domain,user_name and utype.
-    """
-    template ={
-    "status": kwargs.get('status'),
-    "status_detail": kwargs.get('status_detail'),
-	"status_code": kwargs.get('status_code'),
-    "file": {
-        "size": kwargs.get('file_size'),
-        "path": kwargs.get('file_path'),
-        "virtual_path": kwargs.get('file_virtual_path'),
-        "name": kwargs.get('file_name')
-    },
-    "guid": kwargs.get('guid'),
-    "ref_id": kwargs.get('ref_id'),
-    "prd_instance_id": kwargs.get('prd_instance_id'),
-    "product_guid": kwargs.get('product_guid'),
-    "product_name": kwargs.get('product_name'),
-    "product_version": kwargs.get('product_version'),
-    "node_name":kwargs.get('node_name'),
-    "src_endpoint": {
-        "port": kwargs.get('src_endpoint_port'),
-        "ip": kwargs.get('src_endpoint_ip')
-    },
+def dataTemplate(transactionType,**kwargs):
+    """Created templates for use. This function forms json data into an
+    appropriate model for EFC. It returnes the appropriate template based
+    on the transaction type passed into the function. The logic to process
+    this is at the bottom of the function."""
+    upload = {
+        "bytes" : kwargs.get('bytes'),
         "dst_endpoint": { 
             "port": kwargs.get('dst_endpoint_port'),
             "ip": kwargs.get('dst_endpoint_ip'),
             "type": kwargs.get('dst_endpoint_type')
         },
+        "duration": kwargs.get('duration'),
+        "file": {
+            "created_time": kwargs.get('file_created_time'),
+            "uid": kwargs.get('file_uid'),
+            "size": kwargs.get('file_size'),
+            "name": kwargs.get('file_name'),
+            "path": kwargs.get('file_path')
+        },
+        "guid": kwargs.get('file_uid'),
+        "node_name": kwargs.get('node_name'),
+        "prd_ext_tenant_id": kwargs.get('prd_ext_tenant_id'),
+        "product_name": kwargs.get('product_name'),
+        "prd_ext_tenant_name": kwargs.get('prd_ext_tenant_name'),
+        "classifications": [{
+            "ref_id": f"globalscape:{kwargs.get('guid')}",
+            "time": kwargs.get('time'),
+        }],
         "session": {
+           "created_time": kwargs.get('time'),
            "uid": kwargs.get('session_uid')
         },
-	"bytes_out" : kwargs.get('bytes_out'),
-	"transfer_time" : kwargs.get('transfer_time'),
+        "src_endpoint": {
+            "port": kwargs.get('src_endpoint_port'),
+            "ip": kwargs.get('src_endpoint_ip'),
+            "type": kwargs.get('src_endpoint_type')
+        },
+        "tenant": kwargs.get('prd_ext_tenant_id'),
+        "tenant_name":"GlobalScape",
         "time": kwargs.get('time'),
+        "status_code": kwargs.get('status_code'),
+        "status_detail": kwargs.get('status_detail'),
         "user": {
+            "home_directory": kwargs.get('user_home_directory'),
+            "uuid": kwargs.get('guid'),
+            "uid": kwargs.get('user_uid'),
+            "type": kwargs.get('user_type'),
+            "name": kwargs.get('user_name')
+        },
+        "utype": kwargs.get('utype')
+    }
+    download = {
+        "bytes" : kwargs.get('bytes'),
+        "dst_endpoint": { 
+            "port": kwargs.get('dst_endpoint_port'),
+            "ip": kwargs.get('dst_endpoint_ip'),
+            "type": kwargs.get('dst_endpoint_type')
+        },
+        "duration": kwargs.get('duration'),
+        "file": {
+            "uid": kwargs.get('file_uid'),
+            "size": kwargs.get('file_size'),
+            "name": kwargs.get('file_name'),
+            "path": kwargs.get('file_path')
+        },
+        "guid": kwargs.get('file_uid'),
+        "node_name": kwargs.get('node_name'),
+        "prd_ext_tenant_id": kwargs.get('prd_ext_tenant_id'),
+        "product_name": kwargs.get('product_name'),
+        "prd_ext_tenant_name": kwargs.get('prd_ext_tenant_name'),
+        "classifications": [{
+            "ref_id": f"globalscape:{kwargs.get('guid')}",
+            "time": kwargs.get('time'),
+        }],
+        "session": {
+           "created_time": kwargs.get('time'),
+           "uid": kwargs.get('session_uid')
+        },
+        "src_endpoint": {
+            "port": kwargs.get('src_endpoint_port'),
+            "ip": kwargs.get('src_endpoint_ip'),
+            "type": kwargs.get('src_endpoint_type')
+        },
+        "tenant": kwargs.get('prd_ext_tenant_id'),
+        "tenant_name":"GlobalScape",
+        "time": kwargs.get('time'),
+        "status_code": kwargs.get('status_code'),
+        "status_detail": kwargs.get('status_detail'),
+        "user": {
+            "home_directory": kwargs.get('user_home_directory'),
+            "uuid": kwargs.get('guid'),
+            "uid": kwargs.get('user_uid'),
             "type": kwargs.get('user_type'),
-        "domain": kwargs.get('user_domain'),
             "name": kwargs.get('user_name')
         },
         "utype": kwargs.get('utype')
     }
    
+    fileDeleted = {
+        "file": {
+                "size": kwargs.get('file_size'),
+                "name": kwargs.get('file_name'),
+                "path": kwargs.get('file_path'),
+                "uid": kwargs.get('file_uid'),
+        },
+        "guid": f'deleted:{kwargs.get("guid")}',
+        "node_name": kwargs.get('node_name'),
+        "classifications": [{
+            "ref_id": f"globalscape:{kwargs.get('guid')}",
+            "time": kwargs.get('time'),
+        }],
+        "prd_ext_tenant_name": kwargs.get("prd_ext_tenant_name"),
+        "prd_ext_tenant_id": kwargs.get('prd_ext_tenant_id'),
+        "product_name": kwargs.get("product_name"),
+        "session": {
+            "created_time": kwargs.get('time'),
+            "uid": kwargs.get('session_uid')
+        },
+        "src_endpoint": {
+            "port": kwargs.get('src_endpoint_port'),
+            "ip": kwargs.get('src_endpoint_ip'),
+            "type": kwargs.get('src_endpoint_type')
+        },
+        "tenant": kwargs.get('prd_ext_tenant_id'),
+        "tenant_name":"GlobalScape",
+        "dst_endpoint": {
+            "port": kwargs.get('dst_endpoint_port'),
+            "ip": kwargs.get('dst_endpoint_ip'),
+            "type": kwargs.get('dst_endpoint_type')
+        },
+        "time": kwargs.get('time'),
+        "status_code": kwargs.get('status_code'),
+        "status_detail": kwargs.get('status_detail'),
+        "user": {
+            "home_directory": kwargs.get('user_home_directory'),
+            "uuid": kwargs.get('user_session_uid'),
+            "uid": kwargs.get('user_uid'),
+            "type": kwargs.get('user_type'),
+            "name": kwargs.get('user_name')
+        },
+        "utype": kwargs.get('utype')
+    }
+    
+    logon ={
+    "classifications": [{
+        "ref_id": f"globalscape:{kwargs.get('guid')}",
+        "time": kwargs.get('time'),
+    }],
+    "dst_endpoint": {
+        "port": kwargs.get('dst_endpoint_port'),
+        "ip": kwargs.get('dst_endpoint_ip'),
+        "type": kwargs.get('dst_endpoint_type')
+    },
+    "guid": kwargs.get('guid'),
+    "node_name": kwargs.get('node_name'),
+    "tenant": kwargs.get('prd_ext_tenant_id'),
+    "tenant_name":"GlobalScape",
+    "prd_ext_tenant_id": kwargs.get('prd_ext_tenant_id'),
+    "product_name": kwargs.get("product_name"),
+    "prd_ext_tenant_name": kwargs.get('prd_ext_tenant_name'),
+    "status_code": kwargs.get('status_code'),
+    "status_detail": kwargs.get('status_detail'),
+    "src_endpoint": {
+        "port": kwargs.get('src_endpoint_port'),
+        "ip": kwargs.get('src_endpoint_ip'),
+        "type": kwargs.get('src_endpoint_type')
+    },
+    "time": kwargs.get('time'),
+    "user": {
+        "home_directory": kwargs.get('user_home_directory'),
+        "uuid": kwargs.get('user_session_uid'),
+        "uid": kwargs.get('user_uid'),
+        "type": kwargs.get('user_type'),
+        "name": kwargs.get('user_name')
+    },
+    "session": {
+        "created_time": kwargs.get('time'),
+        "uid": kwargs.get('session_uid')
+    },
+    "utype": kwargs.get('utype')
+    }
+
+    if transactionType == "file_uploaded":
+        template = upload
+    if transactionType == "file_downloaded":
+        template = download
+    if transactionType == "file_deleted":
+        template = fileDeleted
+    if transactionType == "user_logged_on":
+        template = logon
+    if transactionType == "other":
+        template = {}
+    
     return template

inexDataProcessing.py

@@ -1,37 +1,99 @@
 def processData(data, template, **kwargs):
+    """Translates data from sql query to the appropriate place in the respective template.
+    Accepts data, which is the sql query output, the template function, and finally
+    additional data to insert into the template. Uses other functions to further 
+    process row data."""
     processedData = []
+    transactionLoginid = []
+    
     for row in data:
         # print(f'Row: {row}')
-        processedData.append(template(status=row.get(''),\
-                            status_detail=row.get(''),\
+        # must set variables for the different templates and do logic based on that. Do not call identifyUtype many times
+        identifyUtypecommand = identifyUtype(row.get('Command'))
+
+        if identifyUtypecommand == "other":
+            continue
+
+        if row.get('Command') == None:
+            continue
+
+        userType = identifyUserType(row.get('user_type'))
+        userHome = parseHomefolder(row.get('Actor'),row.get('VirtualFolderName'))
+        try:
+            processedData.append(template(identifyUtypecommand,\
+                prd_ext_tenant_name=kwargs.get('prd_ext_tenant_name'),\
+                user_uid=row.get('TransactionID'),\
+                status_detail=row.get('Description'),\
+                prd_ext_tenant_id=kwargs.get('prd_ext_tenant_id'),\
                 status_code=row.get('ResultID'),\
+                file_created_time=row.get('Time_stamp'),\
                 file_size=row.get('FileSize'),\
+                file_uid=row.get('ProtocolCommandID'),\
                 file_path=row.get('PhysicalFolderName'),\
-                            file_virtual_path=row.get('VirtualFolderName'),\
                 file_name=row.get('FileName'),\
                 guid=row.get('TransactionGUID'),\
-                            ref_id=row.get('ProtocolCommandID'),\
-                            prd_instance_id=kwargs.get('prd_instance_id'),\
-                            product_guid=kwargs.get('product_guid'),\
                 product_name=kwargs.get('product_name'),\
-                            product_version=kwargs.get('product_version'),\
                 node_name=row.get('NodeName'),\
+                session_uid=row.get('TransactionID'),\
+                src_endpoint_type=row.get('Protocol'),\
+                src_endpoint_port=row.get('RemotePort'),\
+                src_endpoint_ip=row.get('RemoteIP'),\
+                dst_endpoint_port=row.get('LocalPort'),\
+                dst_endpoint_ip=row.get('LocalIP'),\
+                dst_endpoint_type=row.get('Protocol'),\
+                user_session_uid=row.get('TransactionID'),\
+                bytes=row.get('BytesTransferred'),\
+                time=row.get('Time_stamp'),\
+                duration=row.get('TransferTime'),\
+                user_type=userType,\
+                user_name=row.get('Actor'),\
+                user_home_directory=userHome,\
+                utype=identifyUtypecommand))
+        except UnboundLocalError:
+            print(f'Problem row GUID:{row.get("TransactionGUID")} ::: TransactionObject:{row.get("TransactionObject")} Command: {row.get("Command")}')
+            continue
+
+        identifyUtypetransactionObject = identifyUtype(row.get('TransactionObject'))
+
+        if identifyUtypetransactionObject == "other":
+            continue
+
+        if row.get('TransactionGUID') not in transactionLoginid:
+            try:
+                processedData.append(template(identifyUtypetransactionObject,\
+                    prd_ext_tenant_id=kwargs.get('prd_ext_tenant_id'),\
+                    prd_ext_tenant_name=kwargs.get('prd_ext_tenant_name'),\
+                    status_detail=row.get('Description'),\
+                    guid=row.get('TransactionGUID'),\
+                    status_code=row.get('ResultID'),\
+                    node_name=row.get('NodeName'),\
+                    prd_instance_id=kwargs.get('prd_instance_id'),\
+                    product_name=kwargs.get('product_name'),\
+                    src_endpoint_type=row.get('Protocol'),\
                     src_endpoint_port=row.get('RemotePort'),\
                     src_endpoint_ip=row.get('RemoteIP'),\
                     dst_endpoint_port=row.get('LocalPort'),\
                     dst_endpoint_ip=row.get('LocalIP'),\
                     dst_endpoint_type=row.get('Protocol'),\
                     session_uid=row.get('TransactionID'),\
-                            bytes_out=row.get('BytesTransferred'),\
                     transfer_time=row.get('TransferTime'),\
                     time=row.get('Time_stamp'),\
-                            user_type=identifyUserType(row.get('user_type')),\
-                            user_domain=row.get('SiteName'),\
+                    user_session_uid=row.get('TransactionID'),\
+                    user_uid=row.get('TransactionID'),\
+                    user_type=userType,\
                     user_name=row.get('Actor'),\
-                            utype=identifyUtype(row.get('TransactionObject'))))
+                    user_home_directory=userHome,\
+                    utype=identifyUtypetransactionObject\
+                    ))
+                transactionLoginid.append(row.get('TransactionGUID'))
+            except UnboundLocalError:
+                print(f'Problem row GUID:{row.get("TransactionGUID")} ::: TransactionObject:{row.get("TransactionObject")} Command: {row.get("Command")}')
+                continue
+
     return processedData
 
 def identifyUserType(obj):
+    """Check string if it has Admin-> return Administrator else return User."""
     if obj:
         if "Admin" in obj:
             return "Administrator"
@@ -39,19 +101,36 @@ def identifyUserType(obj):
             return "User"
     else:
         return None
+
+def parseHomefolder(user, virtualfolder):
+    """Extract users home folder using the username. Will not work on edge cases
+    such as when a users home folder does not have the user name. When that occurs
+    it is impossible to know based on the arm data what the home folder is.
+    This function is an assumption so it may return the incorrect home folder. 
+    This function finds the user name and takes the path from the left of the folder
+    as the home folder. There are cases where this may not be accurate."""
+    if user:
+        userSplit = f'/{user}/'
+    if virtualfolder:
+        if userSplit in virtualfolder:
+            home = virtualfolder.split(userSplit)[0] + userSplit
+            return home if home else None
+
 def identifyUtype(obj):
-    user_logged_on = []
-    file_deleted = []
-    file_uploaded = []
-    file_downloaded = []
+    """Process Type of transaction based on string that passed in.
+    Return transaction type."""
+    user_logged_on = ['AUTH']
+    file_deleted = ["dele"]
+    file_uploaded = ["created"]
+    file_downloaded = ["sent"]
 
     if obj in user_logged_on:
         return "user_logged_on"
-    if obj in file_deleted:
+    elif obj in file_deleted:
         return "file_deleted"
-    if obj in file_uploaded:
+    elif obj in file_uploaded:
         return "file_uploaded"
-    if obj in file_downloaded:
+    elif obj in file_downloaded:
         return "file_downloaded"
     else:
-        return None
+        return "other"

inexEncoder.py

@@ -3,6 +3,8 @@ import decimal
 import datetime
 
 class Encoder(json.JSONEncoder):
+    """Encoder uses json.JSONEncoder and checks for instances of decimal and datetime. 
+    Changes decimal.Decimal to int and datetime.datetime to unix timestamp with miliseconds."""
     def default(self, o):
         if isinstance(o, decimal.Decimal):
             return int(o)

inexSqlquery.py

@@ -0,0 +1,11 @@
+class sqlQuerymodel:
+    def queryData(overRideflag, configQuery, daysTopull):
+        """Embedded query data. Data is slightly modified to change the amount of days to pull."""
+        q ="""DECLARE @stopTime DATETIME2
+        SET @stopTime=DATEADD(DAY, -30, GETDATE())
+        SELECT p.ProtocolCommandID, t.Time_stamp, p.RemoteIP, p.RemotePort, p.LocalIP, p.LocalPort, p.Protocol, p.SiteName, p.Command, p.FileName, p.PhysicalFolderName, p.VirtualFolderName, p.FileSize, p.TransferTime, p.BytesTransferred, p.Description, p.ResultID, t.TransactionID, p.Actor, t.TransactionObject, t.NodeName, t.TransactionGUID, a.Protocol user_type
+        FROM tbl_Transactions t
+             Full JOIN tbl_ProtocolCommands p ON(t.TransactionID=p.TransactionID)
+             Full join tbl_Authentications a ON(t.TransactionID=a.TransactionID)
+        WHERE p.Time_stamp>@stopTime AND p.Command IS NOT NULL""".replace("30", str(daysTopull))
+        return configQuery if overRideflag else q

test.py

@@ -9,4 +9,40 @@ def connectDatabase(driver, server, database, user, password):
 def converttimestamp(t):
     print(int(t.timestamp()* 1000))
 
-a = converttimestamp(datetime.datetime(2024, 7, 23, 14, 26, 38, 214000))
+def builddict(keys,*args,**kwargs):
+    dict = {}
+    for key in keys:
+        dict[key] = kwargs.get(key)
+    print(dict)
+
+
+def identifyUtype(obj):
+    """Process Type of transaction based on string that passed in.
+    Return transaction type."""
+    user_logged_on = ['AUTH']
+    file_deleted = ["dele"]
+    file_uploaded = ["created"]
+    file_downloaded = ["sent"]
+
+    if obj in user_logged_on:
+        return "user_logged_on"
+    if obj in file_deleted:
+        return "file_deleted"
+    if obj in file_uploaded:
+        return "file_uploaded"
+    if obj in file_downloaded:
+        return "file_downloaded"
+    else:
+        return "other"
+    
+
+testfolder = '/Usr/a/asdf/asf/asdfas/asdfasdf/'
+user = 'a'
+
+def parsehomefolder(user, virtualfolder):
+    userSplit = f'/{user}/'
+    home = virtualfolder.split(userSplit)[0] + userSplit
+    print(home)
+    return home
+
+a = parsehomefolder(user, testfolder)