-
Notifications
You must be signed in to change notification settings - Fork 1
/
gen_docsite.py
119 lines (99 loc) · 3.72 KB
/
gen_docsite.py
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
import os
import re
docsite_url = "https://open-prophetdb.github.io/biomedgps-data/"
domain = "https://github.com/open-prophetdb/biomedgps-data/blob/main"
path_name_map = {
"README.md": "index.md",
"DEPENDENCIES.md": "installation_index.md",
"graph_data/README.md": "graph_data_index.md",
"graph_data/KG_README.md": "graph_data_kg.md",
"wandb/README.md": "wandb_index.md",
"graph_analysis/README.md": "graph_analysis_index.md",
"examples/README.md": "examples_index.md",
"embeddings/README.md": "embeddings_index.md",
"embedding_analysis/README.md": "embedding_analysis_index.md",
"benchmarks/README.md": "benchmarks_index.md",
"prediction/README.md": "prediction_index.md",
"FAQs.md": "faqs.md",
}
no_navigations = [
"index.md",
"installation_index.md",
"graph_analysis_index.md",
"prediction_index.md",
"faqs.md",
]
def is_valid(filepath):
return not (
filepath.startswith("http")
or filepath.startswith("https")
or filepath.startswith("www")
or filepath.startswith("ftp")
or filepath.startswith("sftp")
or filepath.startswith("ssh")
or filepath.startswith("#")
)
def is_doc(filepath):
paths = path_name_map.keys()
for path in paths:
if filepath.endswith(path):
return True
return False
def normalize_path(filepath):
relative_path = os.path.relpath(filepath, os.getcwd())
url_path = path_name_map.get(relative_path)
if url_path:
return os.path.join(docsite_url, url_path.replace(".md", ""))
else:
return filepath
# Copy files and rename
def copy_files():
if os.path.exists("docs"):
# Remove all markdown files in docs
for file in os.listdir("docs"):
if file.endswith(".md"):
os.remove(os.path.join("docs", file))
for path, name in path_name_map.items():
if not os.path.exists(path):
continue
destpath = os.path.join("docs", name)
# Replace all relative links to absolute links in the markdown file
with open(path, "r") as f:
content = f.readlines()
for i in range(len(content)):
# Extract the relative file path using regex
line = content[i]
filepaths = re.findall(r"\]\((?!http)([^)]+)\)", line)
dirpath = os.path.dirname(os.path.abspath(path))
fixed_filepaths = [
os.path.normpath(os.path.join(dirpath, filepath))
if is_valid(filepath)
else filepath
for filepath in filepaths
]
urls = [
filepath.replace(os.getcwd(), domain)
if is_valid(filepath) and not is_doc(filepath)
else normalize_path(filepath)
for filepath in fixed_filepaths
]
zipped = list(zip(filepaths, fixed_filepaths, urls))
if len(zipped) > 0:
print(f"Replace {zipped} in {path}")
for j in range(len(filepaths)):
# line = line.replace(filepaths[j], urls[j])
# Replace only the perfect match
line = re.sub(
r"\]\({}\)".format(re.escape(filepaths[j])),
"]({})".format(urls[j]),
line,
)
content[i] = line
header = ""
if name in no_navigations:
header = """---\nhide:\n - navigation\n---\n\n"""
content = header + "".join(content)
with open(destpath, "w") as f:
f.writelines(content)
if __name__ == "__main__":
copy_files()