File: suburl.py

package info (click to toggle)
python-skbio 0.6.3-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 11,924 kB
  • sloc: python: 67,527; ansic: 672; makefile: 225
file content (52 lines) | stat: -rw-r--r-- 1,629 bytes parent folder | download | duplicates (2)
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
# ----------------------------------------------------------------------------
# Copyright (c) 2013--, scikit-bio development team.
#
# Distributed under the terms of the Modified BSD License.
#
# The full license is in the file LICENSE.txt, distributed with this software.
# ----------------------------------------------------------------------------

# Script to substitute domain names with relative paths in hyperlinks in the
# built html files, such as to avoid unnecessary domain resolutions when the
# visitor navigates the website. It may be executed only when "doc" and "web"
# are hosted at the same web server.

import os
import re
import glob
from functools import partial


# -- Configuration -----------------------------------------------------------

rootdir = "_build/html"
source = "https://scikit.bio/docs/latest"
target = "docs/latest"


# -- Workflow ----------------------------------------------------------------

pattern = re.compile(f'href="{re.escape(source)}/([^"]+)"')


def substitute(match, prefix):
    return f'href="{prefix}{target}/{match.group(1)}"'


cwd = os.getcwd()
os.chdir(os.path.join(os.path.dirname(__file__), rootdir))

for file in glob.glob("**/*.html", recursive=True):
    depth = len(os.path.normpath(file).split(os.sep))
    prefix = "../" * (depth - 1)
    with open(file, "r") as fh:
        content = fh.read()
    content = content.replace(
        f'href="{source}"', f'href="{prefix}{target}/index.html"'
    )
    repl = partial(substitute, prefix=prefix)
    content = pattern.sub(repl, content)
    with open(file, "w") as fh:
        fh.write(content)

os.chdir(cwd)