properly working refactor of markdown

This commit is contained in:
Xevion
2019-07-14 00:13:30 -05:00
parent a3ef604afa
commit 6cfda7de65

View File

@@ -2,52 +2,63 @@ import re
def parse(markdown):
lines = markdown.split('\n')
res = ''
in_list = False
in_list_append = False
result, in_list, finish_list = '', False, False
for line in lines:
# Heading formatting
if re.match('###### (.*)', line) is not None:
line = '<h6>' + line[7:] + '</h6>'
elif re.match('## (.*)', line) is not None:
line = '<h2>' + line[3:] + '</h2>'
elif re.match('# (.*)', line) is not None:
line = '<h1>' + line[2:] + '</h1>'
m = re.match(r'\* (.*)', line)
if m:
in_list, is_bold, is_italic = True, False, False
current_line = m.group(1)
# Bold
strongmatch = re.match('(.*)__(.*)__(.*)', current_line)
if strongmatch:
current_line = strongmatch.group(1) + '<strong>' + \
strongmatch.group(2) + '</strong>' + strongmatch.group(3)
is_bold = True
# Italics
italicmatch = re.match('(.*)_(.*)_(.*)', current_line)
if italicmatch:
current_line = italicmatch.group(1) + '<em>' + italicmatch.group(2) + \
'</em>' + italicmatch.group(3)
is_italic = True
line = '<ul><li>' + current_line + '</li></ul>' if not in_list else '<li>' + current_line + '</li>'
# List detection
is_list = re.match(r'\* (.*)', line) or False
line = is_list.group(1) if is_list else line
# Bold
strongmatch = re.match('(.*)__(.*)__(.*)', line)
if strongmatch:
line = strongmatch.group(1) + '<strong>' + \
strongmatch.group(2) + '</strong>' + strongmatch.group(3)
# Italics
italicmatch = re.match('(.*)_(.*)_(.*)', line)
if italicmatch:
line = italicmatch.group(1) + '<em>' + italicmatch.group(2) + \
'</em>' + italicmatch.group(3)
# If a list has been detected
if is_list:
if not in_list:
line = '<ul><li>' + line + '</li>'
in_list = True
else:
line = '<li>' + line + '</li>'
else:
# If a list wasn't detected, but it's supposedly trying to continue a list
if in_list:
in_list_append = True
finish_list = True
in_list = False
m = re.match('<h|<ul|<p|<li', line)
if not m:
# Detect whether a heading, list or text paragraph has already been started
# This is just to ensure it's wrapped in something at the very least, and follows HTML sytnax.
occupied = re.match('<h|<ul|<p|<li', line)
if not occupied:
line = '<p>' + line + '</p>'
m = re.match('(.*)__(.*)__(.*)', line)
if m:
line = m.group(1) + '<strong>' + m.group(2) + '</strong>' + m.group(3)
m = re.match('(.*)_(.*)_(.*)', line)
if m:
line = m.group(1) + '<em>' + m.group(2) + '</em>' + m.group(3)
if in_list_append:
# If a list has ended and it needs to be formally ended
if finish_list:
line = '</ul>' + line
in_list_append = False
res += line
is_list = False
finish_list = False
# Finish this line and add it to the result.
result += line
# If we have somehow not ended a list yet, complete it now.
if in_list:
res += '</ul>'
return res
result += '</ul>'
return result