I have an input file of the following format
CC -----------------------------------------------------------------------
CC
CC hgfsdh kjhsdt kjshdk
CC
CC -----------------------------------------------------------------------
CC Release of 18-Sep-2019
CC -----------------------------------------------------------------------
CC
CC Alex
CC -----------------------------------------------------------------------
CC Copyrighted vvvncbm License
CC -----------------------------------------------------------------------
//
ID 1.1
ED text1
AN text2.
CA text3
CF text4.
CC -!- Some members
CC also on .
CC -!- May be
CC -!- Re
PR PRTSF; C000AS61;
DQ Q6, AZW2_DANRE; Q7, AZW2_DANRE; Q97, AZW2_DONT;
DQ Q8, AZW2_DONT; Q9, AZW2_AZW2_DONT; Q10, AZW2_CAFT;
//
ID 1.2
ED text1
AN text2.
CA text3
CF text4.
CC -!- Some members
CC also on .
CC -!- May be
CC second line
PR PRTSF; DOC00;
DQ Q6, AZW2_DANRE; Q7, AZW2_DANRE; Q97, AZW2_DONT;
DQ Q8, AZW2_DONT; Q9, AZW2_AZW2_DONT; Q10, AZW2_CAFT;
DQ Q15, AZW2_DANRE; Q43, AZW2_DANRE; Q049, AZW2_DONT;
//
I would like to group the data in this text file and store it in a json
I've tried the following,
import os
import json
from pprint import pprint
def text_to_json(f_input):
location_data = []
if os.path.exists(f_input):
with open(f_input, 'r') as f:
for line in f.readlines()[12:]:
if line.strip() != '//' and line.strip() != '//' and line.strip():
print(line[:-1])
pass
# return json.dumps(data)
if __name__ == '__main__':
f_input = 'input.txt'
text_to_json(f_input)
I have skipped the first few lines with comments. if line.strip() != 'DELIMITER' and line.strip() != 'DELIMITER' and line.strip(): , the delimiter is //. However, I am not sure how to use \\ and group the data corresponding to each id.
I would like to group the data using delimiter and store the data of each id in json format.
{
'1.1' :
{'DQ': {'Q6': AZW2_DANRE, 'Q7': 'AZW2_DANRE', 'Q97': 'AZW2_DONT'
'Q8': 'AZW2_DONT', 'Q9': 'AZW2_AZW2_DONT'; 'Q10': 'AZW2_CAFT'},
'ED': 'text1',
'AN': 'text2.',
'CA': 'text3',
'CF': 'text4.',
'PR': 'PRTSF; C000AS61;',
'CC': ['Some members also on .', 'May be', 'Re']
}
'1.2' :
{'DQ': {'Q6': AZW2_DANRE, 'Q7': 'AZW2_DANRE', 'Q97': 'AZW2_DONT'
'Q8': 'AZW2_DONT', 'Q9': 'AZW2_AZW2_DONT'; 'Q10': 'AZW2_CAFT',
'Q15': 'AZW2_DANRE', 'Q43': 'AZW2_DANRE', 'Q049': 'AZW2_DONT'},
'ED': 'text1',
'AN': 'text2.',
'CA': 'text3',
'CF': 'text4.',
'PR': 'PRTSF; DOC00;',
'CC': ['Some members also on .', 'May be second line']
}
}
I could create the above json by storing based on line numbers. However, the line number of each dataset keeps varying. For instance, the data stored against DQ has 2 lines in the first dataset and 3 in second. Any suggestions on how to proceed?
I would suggest taking the approach of constructing everything in memory, in dictionaries and arrays. In the code below everything is being accumulated into the d dictionary. And then dump the data from memory as a JSON object. It looks like you want to treat different types of lines differently ('CC' lines become an array, 'DQ' lines become a dictionary, and other lines just stored). So, here's how I would approach the code:
import os
import json
from pprint import pprint
def text_to_json(f_input):
location_data = []
if os.path.exists(f_input):
with open(f_input, 'r') as f:
# Accumulate all of the line data in this dictionary
d = {}
# This keeps track of the current ID, like 1.1 or 1.2
current_line_id = ''
for line in f.readlines()[12:]:
if line.strip() != '//' and line.strip() != '//' and line.strip():
# print(line[:-1])
line_type = line[0:2]
line_data = line[5:-1]
if line_type == 'ID':
d[line_data] = dict()
current_line_id = line_data
elif line_type == 'CC':
if line_type not in d[current_line_id]:
d[current_line_id][line_type] = []
d[current_line_id][line_type].append(line_data)
elif line_type == 'DQ':
if line_type not in d[current_line_id]:
d[current_line_id][line_type] = {}
for dq in line_data.split(';'):
dq = dq.strip()
dq_key = dq[0:2]
dq_val = dq[4:]
if dq_key != '':
d[current_line_id][line_type][dq_key] = dq_val
else:
d[current_line_id][line_type] = line_data
pass
print(json.dumps(d, indent=2))
# return json.dumps(data)
if __name__ == '__main__':
f_input = 'input.txt'
text_to_json(f_input)