Parse txt to blocks

Question

i have a txt file, which has the following structure

start
id=1
date=21.05.2018
summ=500
end

start
id=7
date=23.05.2018
summ=500
owner=guest
end

Answer 1

You can simply parse the text file, provided you keep some context: start a new dictionnary on each start line and add it to the list on each end line.

Code could be:

def parse(fd):
    """Parse a file, fd is expected to be a file object"""
    resul = []     # the list of dictionaries to return
    d = None       # an individual dict initialized to None
    linenum = 0
    for line in fd:
        line = line.strip()
        linenum += 1
        if line.startswith('end'):
            if d is not None:
                resul.append(d)
                d = None
        elif line.startswith('start'):
            d = {}
        elif len(line) != 0:
            key, val = line.split('=', 1)
            d[key] = val
    return resul

Syntax errors in the file (missing start or end lines, other incorrect lines) are not handled here:

• a missing end line will cause the previous key=val lines to be discarded
• a missing start line will cause an exception because None is not subscriptable on next key=val line
• an other incorrect line (no = sign) should cause an exception ValueError: not enough values to unpack (expected 2, got 1)

Answer 2

Using Regex.

import re

with open(filename, "r") as infile:
    data = infile.read()
    data = re.findall("(?<=\\bstart\\b).*?(?=\\bend\\b)", data, flags=re.DOTALL)   #Find the required data from text

r = []
for i in data:
    val =  filter(None, i.split("\n"))
    d = {}
    for j in val:
        s = j.split("=")    #Split by "=" to form key-value pair
        d[s[0]] = s[1]
    r.append(d)             #Append to list
print(r)

Output:

[{'date': '21.05.2018', 'summ': '500', 'id': '1'}, {'date': '23.05.2018', 'owner': 'guest', 'summ': '500', 'id': '7'}]

Answer 3

Easiest algorithm I could think of, if I get your question right.

d ={}
arr = []

for line in plines:
  if line == 'start':
    continue
  elif line =='end':
    arr.append(d)
    continue
  else:
    list_key_value = line.split('=')    
    d[list_key_value[0]] = int(list_key_value[1]) if 
    type(list_key_value[1]) == 'int' else str(list_key_value[1])
print (arr)

Output: [{'id': '7', 'date': '23.05.2018', 'summ': '500', 'owner': 'guest'}, {'id': '7', 'date': '23.05.2018', 'summ': '500', 'owner': 'guest'}]

Answer 4

You could also try something like this:

from itertools import takewhile

with open('data.txt') as in_file:
    items = [line.strip() for line in in_file.read().split()]
    # ['start', 'id=1', 'date=21.05.2018', 'summ=500', 'end', 'start', 'id=7', 'date=23.05.2018', 'summ=500', 'owner=guest']

    pos = [i for i, item in enumerate(items) if item == 'start']
    # [0, 5]

    blocks = [list(takewhile(lambda x: x != 'end', items[i+1:])) for i in pos]
    # [['id=1', 'date=21.05.2018', 'summ=500'], ['id=7', 'date=23.05.2018', 'summ=500', 'owner=guest']]

    print([dict(x.split('=') for x in block) for block in blocks])

Which Outputs:

[{'id': '1', 'date': '21.05.2018', 'summ': '500'}, {'id': '7', 'date': '23.05.2018', 'summ': '500', 'owner': 'guest'}]

Answer 5

You can build a simple parser with recursion that attempts to find data between start and end blocks:

import re
class Parser:
  def __init__(self, source:str):
    self.source = iter(filter(None, source.split('\n')))
    self.results = []
    self.parse()
  @staticmethod
  def to_dict(between_blocks):
    return dict(re.split('\s*\=\s*', i) for i in between_blocks)
  def parse(self):
    _line = next(self.source, None)
    if _line is not None:
      if _line == 'start':
        scope = []
        while True:
         _temp = next(self.source, None)
         if _temp is None:
           raise Exception("Missing 'end' tag")
         if _temp != 'end':
           scope.append(_temp)
         else:
           break
        self.results.append(Parser.to_dict(filter(None, scope)))
      self.parse()
   def __repr__(self):
      return f'{Parsed}({self.results})'

print(Parser(open('filename.txt').read())).results)

Output:

[{'id': '1', 'date': '21.05.2018', 'summ': '500'}, {'id': '7', 'date': '23.05.2018', 'summ': '500', 'owner': 'guest'}]

---

Tests:

tests = [[
"""
start
id=1
date=21.05.2018
summ=500
""", Exception],
[
 """
 start
 name = someone
 age = 18
 id = 23
 end
 start
 name = someoneelse
 age = 45
 id = 55
 end
 start
 name = lastname
 age = 34
 id = 5
 end
""", None]
]
for text, is_error in tests:    
   try:
     _ = Parser(text)
   except:
     assert is_error == Exception
   else:
     assert is_error is None

print('all tests passed')

Output:

all tests passed