OneStream XF Business Rule Source Code Extractor

business-rule-code-extractor.py

#!/usr/bin/python
#Python 3.7 <=
# Comments and improvements welcome on GitHub! <https://gist.github.com/kzaremski/4d7c02d7fecb0212c0373abc13cb2a47>
'''
    Copyright 2022 Konstantin Zaremski
    
      Permission is hereby granted, free of charge, to any person obtaining a copy 
      of this software and associated documentation files (the "Software"), to deal
      in the Software without restriction, including without limitation the rights
      to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 
      copies of the Software, and to permit persons to whom the Software is
      furnished to do so, subject to the following conditions:
    
      The above copyright notice and this permission notice shall be included in
      all copies or substantial portions of the Software.
    
      THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
      IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
      FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
      AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
      LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
      OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
      THE SOFTWARE.

    OneStream XF Business Rule Source Code Extractor
      Konstantin Zaremski - 26 December 2021

      The purpose of this software is to extract OneStream business rule source
      code from OneStreamXF xml files exported from the platform.

    Usage:
      The script accepts two arguments: the input path followed by the output path.
      -- If the input path is a directory, all files within that directory will be
         parsed.
      -- By default the input and output are the present working directory.

    Usage Examples (unix/linux style paths, windows works too):
        $ python business-rule-code-extractor.py ~/input ~/Documents/businessrules      
            Takes files from ~/input and outputs to ~/Documents/businessrules
        $ python business-rule-code-extractor.py . ~/Documents/businessrules
            Takes files from the current working directory and outputs to 
            ~/Documents/businessrules
        $ python business-rule-code-extractor.py ~/input 
            Takes files from ~/input and outputs to the current working directory
        $ python business-rule-code-extractor.py ~/input.xml ~/Documents
            Takes the single ~/input.xml file as an input and outputs all business
            rules to ~/Documents/input.businessRuleType.businessRuleName.vb                    
'''

# Import dependencies
import os
from xml.etree import ElementTree
import sys

# Main program loop
def main(inputpath, outputpath):
    # If the output path does not exist, exit and do nothing
    if not os.path.exists(inputpath):
        print(f'The input path {inputpath} does not exist.')
        return False
    
    # If the input path resolves to a file and not a directory, then the input is a single file
    inputIsSingleFile = os.path.isfile(inputpath)

    # Use OS listdir to get a list of folder icons
    try:
        # Only get a list of files within './input'
        inputItems = [f for f in os.listdir(inputpath) if os.path.isfile(os.path.join(inputpath, f))] if not inputIsSingleFile else [inputpath]

        # Iterate through the input items and remove all items that do not end in .xml or .XML
        validInputItems = []
        for item in inputItems:
            if item.lower().split('.').pop() == 'xml' and item[0] != '.': validInputItems.append(item) 
        inputItems = validInputItems

        # If there are no leftover XML files, we have nothing to do
        if len(inputItems) == 0 and not inputIsSingleFile:
            print('There are no valid input XML files in the input directory, exiting.')
            return False
        elif inputIsSingleFile:
            print('The input file is not an XML but was explicitly provied so continuing.')
            inputItems = [inputpath]

        print(f'Loaded {str(len(inputItems))} input file{"s" if len(inputItems) > 1 else ""} for processing.')
    except Exception as e:
        print(e)
        # If the directory does not exist we have nothing to do
        print(f'The input path {inputpath} does not exist.')
        return False
    
    # If the output path does not exist, exit and do nothing
    if not os.path.exists(outputpath):
        print(f'The output path {outputpath} does not exist.')
        return False
    
    # If the output path is a file and not a folder
    elif os.path.isfile(outputpath):
        print(f'The output path {outputpath} is a file. It needs to be a directory to accomodate multiple business rules.')
        return False

    # Extractor method
    def extractFromFile(filepath):
        try:
            # Find all business rules according to the known OneStreamXF file structure
            inputXML = ElementTree.parse(filepath)
            businessRuleIterator = inputXML.getroot().iter('businessRule')
            # Convert iterator to standard array
            businessRules = []
            for businessRule in businessRuleIterator:
                businessRules.append(businessRule)
        except Exception as e:
            print(f'There was an issue parsing the business rules from {filepath}, perhaps the file is malformed?')
            return False

        # If there are no business rules in this file, we have nothing to do
        if len(businessRules) == 0:
            print(f'No business rules detected in {filepath}')
            return False

        # Business rule parsing function
        def parseBusinessRule(businessRule):
            # Business rule contents object
            businessRuleContents = {
                'type': businessRule.attrib['businessRuleType'],
                'name': businessRule.attrib['name'],
                'encrypted': str(businessRule.find('isEncrypted').text),
                'sourceCode': str(businessRule.find('sourceCode').text)
            }
            
            # Write the sourcecode to a file
            # Create a filename based on the location of the business rule, and if it is encrypted
            filename = f'{filepath.split("/").pop().split(".").pop(-2)}.{businessRuleContents["type"]}.{businessRuleContents["name"]}.{"encrypted" if businessRuleContents["encrypted"] == "true" else "vb"}'
            # Output file object
            outputFile = open(os.path.join(outputpath, filename), 'w')
            # Write lines
            outputFile.writelines(businessRuleContents['sourceCode'])
            # Close file
            outputFile.close()
            print(f'  Finished extracting {businessRuleContents["type"]}.{businessRuleContents["name"]}{" (encrypted)" if businessRuleContents["encrypted"] == "true" else ""} from {filepath}')

        # Iterate through the business rules
        for businessRule in businessRules:
            try:
                parseBusinessRule(businessRule)
            except Exception as e:
                print(str(e))
        
        print(f'Finished extracting rules from {filepath}')

    # Parse each remaining item as XML and search for the sorucecode tag within each business rule
    for inputFileName in inputItems:
        extractFromFile(os.path.join(inputpath, inputFileName) if not inputIsSingleFile else inputFileName)
        
    print('* * * * * FINISHED * * * * *')
    return True

# Entry point
if __name__ == '__main__':
    runtimeArguments = sys.argv.pop(0)
    inputpath = sys.argv[0] if (len(sys.argv) > 0) else '.'
    outputpath = sys.argv[1] if (len(sys.argv) > 1) else '.'
    main(inputpath, outputpath)

Hi, I don't know if it's my version of python that is causing this (v3.10.6) but when I run the script, it says local variable 'inputIsSingleFile' referenced before assignment and the process stops with an exception thrown. Simply adding inputIsSingleFile = False at the beginning of the main func did the trick

Hi, I don't know if it's my version of python that is causing this (v3.10.6) but when I run the script, it says local variable 'inputIsSingleFile' referenced before assignment and the process stops with an exception thrown. Simply adding inputIsSingleFile = False at the beginning of the main func did the trick

Hi. Yeah you're right.

I wrote this towards the end of last year and I must have been testing with a single file only then.

I have changed line 62 from if os.path.isfile(inputpath): inputIsSingleFile = True to inputIsSingleFile = os.path.isfile(inputpath). Looking back it wasn't good practice anyways to define a boolean variable using an if statement when I could just set it to the condition itself anyways; I don't know why I made that decision, but this change rectifies the problem.

Thanks for catching this and letting me know!