sa6anw.se/clean_language_blocks.py

64 lines
2.0 KiB
Python

import os
import re
import shutil
import yaml
SOURCE_DIR = "docs"
ENGLISH_DIR = os.path.join(SOURCE_DIR, "en")
MKDOCS_YML = "mkdocs.yml"
# 1. Kopiera alla filer från docs/ till docs/en/
if os.path.exists(ENGLISH_DIR):
shutil.rmtree(ENGLISH_DIR)
shutil.copytree(SOURCE_DIR, ENGLISH_DIR)
def clean_file(path, keep_lang):
with open(path, "r", encoding="utf-8") as f:
content = f.read()
# 2. Rensa block: :sv ... ::: eller :en ... :::
if keep_lang == "sv":
content = re.sub(r":en\n.*?\n:::", "", content, flags=re.DOTALL)
elif keep_lang == "en":
content = re.sub(r":sv\n.*?\n:::", "", content, flags=re.DOTALL)
# 3. Ta bort alla språk-taggar som :sv, :en och :::
content = re.sub(r":(sv|en)", "", content)
content = re.sub(r":::", "", content)
# 4. Rensa inline-översättningar
def remove_other_language_inline(text, keep_lang):
def replacer(match):
lang = match.group(1)
txt = match.group(2)
return txt if lang == keep_lang else ""
return re.sub(r"\[:(sv|en)](.*?)(?=\[:|$)", replacer, text)
content = remove_other_language_inline(content, keep_lang)
with open(path, "w", encoding="utf-8") as f:
f.write(content.strip() + "\n")
# 5. Rensa svenska versioner
for filename in os.listdir(SOURCE_DIR):
if filename.endswith(".md"):
clean_file(os.path.join(SOURCE_DIR, filename), keep_lang="sv")
# 6. Rensa engelska versioner
for filename in os.listdir(ENGLISH_DIR):
if filename.endswith(".md"):
clean_file(os.path.join(ENGLISH_DIR, filename), keep_lang="en")
# 7. Skapa .pages i docs/en/ från mkdocs.yml
def extract_nav_from_mkdocs_yml(path):
with open(path, "r", encoding="utf-8") as f:
data = yaml.safe_load(f)
return {
"title": data.get("site_name", "SA6ANW"),
"nav": data.get("nav", [])
}
english_pages = extract_nav_from_mkdocs_yml(MKDOCS_YML)
with open(os.path.join(ENGLISH_DIR, ".pages"), "w", encoding="utf-8") as f:
yaml.dump(english_pages, f, allow_unicode=True)