Pfthb

Background

For some background, I'm trying to create a tool that converts worksheets into API calls using Python 3.5

For the conversion of the table cells to the schema needed for the API call, I've started down the path of using javascript like syntax for the headers used in the spreadsheet. e.g:

Worksheet Header (string)

dict.list[0].id

Python Dictionary

 "dict":
 "list": [
 "id": "my cell value"
 ]

It's also possible that the header schema could have nested arrays/dicts:

one.two[0].three[0].four.five[0].six

And I also need to append to the object after it has been created as I go through each header.

What I've tried

add_branch

Based on https://stackoverflow.com/a/47276490/2903486 I am able to get nested dictionaries setup using values like one.two.three.four and I'm able to append to the existing dictionary as I go through the rows but I've been unable to add in support for arrays:

def add_branch(tree, vector, value):
 key = vector[0]
 tree[key] = value 
 if len(vector) == 1 
 else add_branch(tree[key] if key in tree else ,
 vector[1:],
 value)
 return tree

file = Worksheet(filePath, sheet).readRow()
rowList = 
for row in file:
 rowObj = 
 for colName, rowValue in row.items():
 rowObj.update(add_branch(rowObj, colName.split("."), rowValue))
 rowList.append(rowObj)
return rowList

My own version of add_branch

import re, json
def branch(tree, vector, value):
 """
 Used to convert JS style notation (e.g dict.another.array[0].id) to a python object
 Originally based on https://stackoverflow.com/a/47276490/2903486
 """

 # Convert Boolean
 if isinstance(value, str):
 value = value.strip()

 if value.lower() in ['true', 'false']:
 value = True if value.lower() == "true" else False

 # Convert JSON
 try:
 value = json.loads(value)
 except:
 pass

 key = vector[0]
 arr = re.search('[([0-9]+)]', key)
 if arr:
 arr = arr.group(0)
 key = key.replace(arr, '')
 arr = arr.replace('[', '').replace(']', '')

 newArray = False
 if key not in tree:
 tree[key] = 
 tree[key].append(value 
 if len(vector) == 1 
 else branch( if key in tree else ,
 vector[1:],
 value))
 else:
 isInArray = False
 for x in tree[key]:
 if x.get(vector[1:][0], False):
 isInArray = x[vector[1:][0]]

 if isInArray:
 tree[key].append(value 
 if len(vector) == 1 
 else branch( if key in tree else ,
 vector[1:],
 value))
 else:

 tree[key].append(value 
 if len(vector) == 1 
 else branch( if key in tree else ,
 vector[1:],
 value))

 if len(vector) == 1 and len(tree[key]) == 1:
 tree[key] = value.split(",")
 else:
 tree[key] = value 
 if len(vector) == 1 
 else branch(tree[key] if key in tree else ,
 vector[1:],
 value)
 return tree

What still needs help

My branch solution works pretty well actually now after adding in some things but I'm wondering if I'm doing something wrong/messy here or if theres a better way to handle where I'm editing nested arrays (my attempt started in the if IsInArray section of the code)

I'd expect these two headers to edit the last array, but instead I end up creating a duplicate dictionary on the first array:

file = [
 "one.array[0].dict.arrOne[0]": "1,2,3",
 "one.array[0].dict.arrTwo[0]": "4,5,6"
]
rowList = 
for row in file:
 rowObj = 
 for colName, rowValue in row.items():
 rowObj.update(add_branch(rowObj, colName.split("."), rowValue))
 rowList.append(rowObj)
return rowList

Outputs:

[
 
 "one": 
 "array": [
 
 "dict": 
 "arrOne": [
 "1",
 "2",
 "3"
 ]
 
 ,
 
 "dict": 
 "arrTwo": [
 "4",
 "5",
 "6"
 ]
 
 
 ]
 
 
]

Instead of:

[
 
 "one": 
 "array": [
 
 "dict": 
 "arrOne": [
 "1",
 "2",
 "3"
 ],
 "arrTwo": [
 "4",
 "5",
 "6"
 ]
 
 
 ]
 
 
]

So I'm not sure if there are any caveats in this solution, but this appears to work for some of the use cases i'm throwing at it:

import json, re
def build_job():

 def branch(tree, vector, value):

 # Originally based on https://stackoverflow.com/a/47276490/2903486

 # Convert Boolean
 if isinstance(value, str):
 value = value.strip()

 if value.lower() in ['true', 'false']:
 value = True if value.lower() == "true" else False

 # Convert JSON
 try:
 value = json.loads(value)
 except:
 pass

 key = vector[0]
 arr = re.search('[([0-9]+)]', key)

 if arr:

 # Get the index of the array, and remove it from the key name
 arr = arr.group(0)
 key = key.replace(arr,'')
 arr = int(arr.replace('[','').replace(']',''))

 if key not in tree:

 # If we dont have an array already, turn the dict from the previous 
 # recursion into an array and append to it
 tree[key] = 
 tree[key].append(value 
 if len(vector) == 1 
 else branch( if key in tree else ,
 vector[1:],
 value))
 else:

 # Check to see if we are inside of an existing array here
 isInArray = False
 for i in range(len(tree[key])):
 if tree[key][i].get(vector[1:][0], False):
 isInArray = tree[key][i][vector[1:][0]]

 if isInArray:
 # Respond accordingly by appending or updating the value
 try:
 tree[key][arr].append(value 
 if len(vector) == 1 
 else branch(tree[key] if key in tree else ,
 vector[1:],
 value))
 except:
 # Make sure we have an index to attach the requested array to
 while arr >= len(tree[key]):
 tree[key].append()

 tree[key][arr].update(value 
 if len(vector) == 1 
 else branch(tree[key][arr] if key in tree else ,
 vector[1:],
 value))
 else:
 # Make sure we have an index to attach the requested array to
 while arr >= len(tree[key]):
 tree[key].append()

 # update the existing array with a dict
 tree[key][arr].update(value 
 if len(vector) == 1 
 else branch( if key in tree else ,
 vector[1:],
 value))

 # Turn comma deliminated values to lists
 if len(vector) == 1 and len(tree[key]) == 1:
 tree[key] = value.split(",")
 else:
 # Add dictionaries together
 tree.update(key: value 
 if len(vector) == 1 
 else branch(tree[key] if key in tree else ,
 vector[1:],
 value))
 return tree

 file = [
 "one.array[0].dict.dont-worry-about-me": "some value",
 "one.array[0].dict.arrOne[0]": "1,2,3",
 "one.array[0].dict.arrTwo[1]": "4,5,6",
 "one.array[1].x.y[0].z[0].id": "789"
 ]
 rowList = 
 for row in file:
 rowObj = 
 for colName, rowValue in row.items():
 rowObj.update(branch(rowObj, colName.split("."), rowValue))
 rowList.append(rowObj)
 return rowList
print(json.dumps(build_job(), indent=4))

Result:

[
 
 "one": 
 "array": [
 
 "dict": 
 "dont-worry-about-me": "some value",
 "arrOne": [
 "1",
 "2",
 "3"
 ],
 "arrTwo": [
 "4",
 "5",
 "6"
 ]
 
 ,
 
 "x": 
 "y": [
 
 "z": [
 
 "id": 789
 
 ]
 
 ]
 
 
 ]
 
 
]