How to parse and group hierarchical list items from an unindented string in Python?

[Pedroski55]

Just using Input1 as text, I tried the code below. First I saved Input1 as input.txt

For better formatting maybe you should use the Python module docx, which has more options.

I doubt if all your text files have the same style, so you may need some more re expressions! That depends on what is in your other texts.

import re

# you can do the following with Python but do it like this for now for testing
# copy Input1 text from sample_data_strings.txt and paste it into a text editor
# remove " at both ends, just ' remains
# put [ at the beginning and ] at the end
# now you have a list.
# call the list l
# Paste the list into your Python IDE: l = ['Opening: ... players.']
# save the list l
# savepath = '/home/pedro/myPython/re/text_files/unformatted_text1.txt'
# with open(savepath, 'w') as output: output.writelines(l)
# now you have your text as lines of text, open with readlines()

# path to the unformatted lines of text from above
Input1 = '/home/pedro/myPython/re/text_files/unformatted_text1.txt'
# get the text as a list
with open(Input1, 'r') as infile:
    text_list = infile.readlines()

# have a look
for line in text_list:
    print(line)

# patterns to look for
p = re.compile(r'([A-Za-z]+:)') # get text followed by : like: Opening:
endline = re.compile(r'(:)$') # get end of line :
num = re.compile(r'(\d+\.)') # get a number or numbers followed by .
numsub = re.compile(r'(\w\.)') # get number subpoints \w followed by .
subsub = re.compile(r'(- )') # get the number subpoint marker -

if __name__ == "__main__":
    # match only looks at the beginning of each line
    # search looks through the whole line
    # re.compile(r'(:)$') finds : at the end of a line, if : is there
    for i in range(len(text_list)):
        res = p.match(text_list[i]) 
        end = endline.search(text_list[i])
        number = num.match(text_list[i])
        numsubp = numsub.match(text_list[i])
        subp = sub.match(text_list[i])    
        if res and end:
            text_list[i] = '  ' + text_list[i]
        elif res and not end:
            text_list[i] = '  ' + text_list[i]
        elif number:
            text_list[i] = '\t' + text_list[i]
        elif numsubp:
            text_list[i] = '\t  ' + text_list[i]
        elif subp:
            text_list[i] = '\t\t ' + text_list[i]
        elif i == len(text_list) - 1:
            text_list[i] = '\n\t' + text_list[i]

    savepath = '/home/pedro/myPython/re/text_files/formatted_text1.txt'       
    with open(savepath, 'w') as output:
        output.writelines(text_list)

You can tweak and change the elifs to get what you want. Add more re expressions for different text parts!