blob: aca299325af40e862c6b5e287f837b3c077d0f13 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
#!/usr/bin/env python3
"""Add ids to all rules based on their headline"""
# TODO: support nested lists
import sys
import re
HEADER_RE = re.compile(r'<h\d')
DATA_NUMBER_RE = re.compile(r'data\-number="([^"]*)"')
def add_ids(ol):
"""add ids to all li"""
_id = ""
for s in ol.previous_siblings:
if not s.name:
continue
if s.name.startswith("h"):
_id = s.attrs["data-number"]
break
for i, li in enumerate(ol.find_all("li")):
li["id"] = f"{_id}-{i+1}"
li["class"] = "rule"
def extract_headline_nr(line: str) -> str:
"""Extract the headline's number from it's data-number attribute"""
m = DATA_NUMBER_RE.search(line)
if m:
return m.group(1)
return ""
def main():
"""Add ids to all ordered lists in the input"""
headline = ""
i = 0
for line in sys.stdin.readlines():
if HEADER_RE.match(line):
headline = extract_headline_nr(line)
h_idx = line.find('<h') + 3
line = line[:h_idx] + ' class="rule"' + line[h_idx:]
if '<ol' in line and headline:
i = 1
if '<li' in line and i:
line = line.replace('<li', f'<li id="{headline}-{i}" class="rule"')
i = i + 1
if '</ol' in line:
i = 0
print(line, end="")
if __name__ == "__main__":
main()
|
