Odtnhj

I have a text file that is formatted like the following, with each hyphen representing a hierarchy for the list item.

category1 : 0120391123123
- subcategory : 0120391123123
-- subsubcategory : 019301948109
--- subsubsubcategory : 013904123908
---- subsubsubsubcategory : 019341823908
- subcategory2 : 0934810923801
-- subsubcategory2 : 09341829308123
category2: 1309183912309
- subcategory : 10293182094
...

How can I programmatically get a list like this into a json format like the following?

[
 
 "category1":"0120391123123"
 ,
 [
 
 "subcategory":"0120391123123"
 ,
 [
 
 "subsubcategory":"019301948109"
 ,
 [
 
 "subsubsubcategory":"013904123908"
 ,
 [
 
 "subsubsubsubcategory":"019341823908"
 
 ]
 ]
 ]
 ],
 [
 
 "subcategory2":"0934810923801"
 ,
 [
 
 "subsubcategory2":"09341829308123"
 
 ]
 ],
 [
 
 "category2":"1309183912309"
 ,
 [
 
 "subcategory":"10293182094"
 
 ]
 ]
]

You can use recursion with itertools.groupby:

s = """
category1 : 0120391123123
- subcategory : 0120391123123
-- subsubcategory : 019301948109
--- subsubsubcategory : 013904123908
---- subsubsubsubcategory : 019341823908
- subcategory2 : 0934810923801
-- subsubcategory2 : 09341829308123
category2: 1309183912309
- subcategory : 10293182094
"""

import re, itertools
data = list(filter(None, s.split('n')))
def group_data(d):
 if len(d) == 1:
 return [dict([re.split('s*:s*', d[0])])]
 grouped = [[a, list(b)] for a, b in itertools.groupby(d, key=lambda x:not x.startswith('-'))]
 _group = [[grouped[i][-1], grouped[i+1][-1]] for i in range(0, len(grouped), 2)]
 _c = [[dict([re.split('s*:s*', i) for i in a]), group_data([c[1:] for c in b])] for a, b in _group]
 return [i for b in _c for i in b]


print(json.dumps(group_data(data), indent=4))

Output:

[
 
 "category1": "0120391123123"
 ,
 [
 
 " subcategory": "0120391123123"
 ,
 [
 
 " subsubcategory": "019301948109"
 ,
 [
 
 " subsubsubcategory": "013904123908"
 ,
 [
 
 " subsubsubsubcategory": "019341823908"
 
 ]
 ]
 ],
 
 " subcategory2": "0934810923801"
 ,
 [
 
 " subsubcategory2": "09341829308123"
 
 ]
 ],
 
 "category2": "1309183912309"
 ,
 [
 
 " subcategory": "10293182094"
 
 ]
]

Note: this answer assumes that your final output should have "category2" be at the same level as "category1", since both do not contain a "-" in the front.

use a recursive function to split the content of the file to chunks and use divide and conquer

from pprint import pprint
req=
startingindex=-1

with open('temp.txt' ,'r') as f:

 content=f.read().split('n') 



def foo(splitcontent):
 index=0
 reqlist=
 while(index<len(splitcontent)):

 if (splitcontent[index][0]!='-'):
 key,value=splitcontent[index].split(':')
 reqlist.append(key.strip():value.strip())
 index+=1
 templist=

 while(index<len(splitcontent) and splitcontent[index][0]=='-'):
 templist.append(splitcontent[index][1:])
 index+=1

 intermediatelist=foo(templist)
 if(intermediatelist):
 reqlist.append(intermediatelist)
 return reqlist
pprint(foo(content))

OUTPUT

['category1': '0120391123123',
 ['subcategory': '0120391123123',
 ['subsubcategory': '019301948109',
 ['subsubsubcategory': '013904123908',
 ['subsubsubsubcategory': '019341823908']]],
 'subcategory2': '0934810923801',
 ['subsubcategory2': '09341829308123']],
 'category2': '1309183912309',
 ['subcategory': '10293182094']]