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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
|
#!/usr/bin/env python3
import json
import os
import re
import sys
from dataclasses import dataclass
from pathlib import Path
__all__ = ["get_docs_section"]
DOCS_ROOT = "https://gnome.pages.gitlab.gnome.org/blueprint-compiler"
sections: dict[str, "Section"] = {}
@dataclass
class Section:
link: str
lines: str
def to_json(self):
return {
"content": rst_to_md(self.lines),
"link": self.link,
}
def load_reference_docs():
for filename in Path(os.path.dirname(__file__), "reference").glob("*.rst"):
with open(filename) as f:
section_name = None
lines = []
def close_section():
if section_name:
html_file = re.sub(r"\.rst$", ".html", filename.name)
anchor = re.sub(r"[^a-z0-9]+", "-", section_name.lower())
link = f"{DOCS_ROOT}/reference/{html_file}#{anchor}"
sections[section_name] = Section(link, lines)
for line in f:
if m := re.match(r"\.\.\s+_(.*):", line):
close_section()
section_name = m.group(1)
lines = []
else:
lines.append(line)
close_section()
# This isn't a comprehensive rST to markdown converter, it just needs to handle the
# small subset of rST used in the reference docs.
def rst_to_md(lines: list[str]) -> str:
result = ""
def rst_to_md_inline(line):
line = re.sub(r"``(.*?)``", r"`\1`", line)
line = re.sub(
r":ref:`(.*?)<(.*?)>`",
lambda m: f"[{m.group(1)}]({sections[m.group(2)].link})",
line,
)
line = re.sub(r"`([^`]*?) <([^`>]*?)>`_", r"[\1](\2)", line)
return line
i = 0
n = len(lines)
heading_levels = {}
def print_block(lang: str = "", code: bool = True, strip_links: bool = False):
nonlocal result, i
block = ""
while i < n:
line = lines[i].rstrip()
if line.startswith(" "):
line = line[3:]
elif line != "":
break
if strip_links:
line = re.sub(r":ref:`(.*?)<(.*?)>`", r"\1", line)
if not code:
line = rst_to_md_inline(line)
block += line + "\n"
i += 1
if code:
result += f"```{lang}\n{block.strip()}\n```\n\n"
else:
result += block
while i < n:
line = lines[i].rstrip()
i += 1
if line == ".. rst-class:: grammar-block":
print_block("text", strip_links=True)
elif line == ".. code-block:: blueprint":
print_block("blueprint")
elif line == ".. note::":
result += "#### Note\n"
print_block(code=False)
elif m := re.match(r"\.\. image:: (.*)", line):
result += f"})\n"
elif i < n and re.match(r"^((-+)|(~+)|(\++))$", lines[i]):
level_char = lines[i][0]
if level_char not in heading_levels:
heading_levels[level_char] = max(heading_levels.values(), default=1) + 1
result += (
"#" * heading_levels[level_char] + " " + rst_to_md_inline(line) + "\n"
)
i += 1
else:
result += rst_to_md_inline(line) + "\n"
return result
if __name__ == "__main__":
if len(sys.argv) != 2:
print("Usage: collect_sections.py <output_file>")
sys.exit(1)
outfile = sys.argv[1]
load_reference_docs()
# print the sections to a json file
with open(outfile, "w") as f:
json.dump(
{name: section.to_json() for name, section in sections.items()},
f,
indent=2,
sort_keys=True,
)
|
