Parse md task list

tasker.py

#!/usr/bin/env python3

x="""
# header 1

textblock 1 line1
textblock 1 line2
textblock 1 line3

textblock 2 line 1

textblock 3 line 1
textblock 3 line 2
- p1
- p2
 - p2.1
\t- p2.2
\t- p2.3
\t - p2.3.1
  - p2.3.2
  [] t2.3.3
  [] @user1 task
  [] ! important task
  [] //25.01.2025 dated task
  [] !! //26.02.2024 @user1 @user2 full task
  
```language
code line1
    code line with spaces    
code line 3

code line 4
``` 

* p 3
""".splitlines()


text=" ! //25.10.2025 @user1 zrobić cos"

def lcount_chars(line, chars):
    for count, char in enumerate(line):
        if char not in chars:
            return count
    return 0
    

def parse_text(text):
    offset=0
    while True:
        offset += lcount_chars(text[offset:], " \t")
        t = text[offset:]
        if t.startswith('//') :
            start=2
            end = t.find(" ")
            yield ["Date", (offset + start,offset + end), t[start:end]]
            offset += end
        elif t.startswith("@"):
            start=1
            end = t.find(" ")
            yield ["User", (offset + start,offset + end), t[start:end]]
            offset += end
        elif t[0] == "!":
            priority = lcount_chars(t,"!")
            yield ["Priority", (offset, offset + priority), priority]
            offset += priority
        else:
            break

def _parse(lines):
    line_gen=enumerate(lines)

    for line_n, line in line_gen:
        stripped_line = line.strip()
        indentation=lcount_chars(line, " \t")
        if len(stripped_line) <= 0:
            yield [ "Empty", indentation, (line_n,1) ]
            continue
        first_char=stripped_line[0]
        if first_char == '#':
            level=lcount_chars(stripped_line, '#')
            yield [ "Header", indentation, (line_n,1), level, stripped_line[level:].strip()]
        elif first_char in '-*':
            yield [ "List", indentation, (line_n,1), stripped_line[1:].strip()]
        elif first_char == '[':
            bracket_end = stripped_line.find(']')
            status = stripped_line[1:bracket_end].strip()
            text = stripped_line[bracket_end+1:].strip()
            yield [ "Task", indentation, (line_n,1), status, text, list(parse_text(text))]
        elif stripped_line.startswith("```"):
            lang=stripped_line[3:].strip()
            start_line=line_n
            code=""
            for line_n, code_line in line_gen:
                if code_line.rstrip().endswith("```"):
                    code += code_line.rstrip()[:-3] + "\n"
                    break
                else:
                    code += code_line + "\n"
            yield [ "Code", indentation, (start_line, start_line-line_n), lang, code]
        else:
            yield [ "Text", indentation, (line_n,1), line]

def parse(lines):
    prev_node=None
    for node in _parse(lines):
        if prev_node and prev_node[0] == "Text" and node[0] == "Text":
                prev_node[2] = (prev_node[2][0], prev_node[2][0]+1)
                prev_node[3] += "\n" + node[3]
                continue
        if prev_node and prev_node[0] != "Empty":
            yield prev_node
        prev_node = node
    yield node

            

for n in parse(x):
    print(n)

for n in parse_text(text):
    print(n)