import os
import re
import shutil

SOURCE_DIR = "docs"
ENGLISH_DIR = "docs/en"

if os.path.exists(ENGLISH_DIR):
    shutil.rmtree(ENGLISH_DIR)
shutil.copytree(SOURCE_DIR, ENGLISH_DIR)

# Hantera block i formatet:
# :sv
# text...
# :::
def remove_other_language_blocks(content, keep_lang):
    block_pattern = re.compile(r":(sv|en)\n(.*?)\n:::", re.DOTALL)

    result = []
    pos = 0
    for match in block_pattern.finditer(content):
        start, end = match.span()
        lang, block = match.groups()

        # Behåll neutral text mellan block
        result.append(content[pos:start])
        if lang == keep_lang:
            result.append(block.strip() + "\n\n")
        pos = end
    result.append(content[pos:])
    return ''.join(result)

# Inline-taggar, t.ex. [:sv]text
def remove_other_language_inline(content, keep_lang):
    def replacer(match):
        lang, text = match.groups()
        return text if lang == keep_lang else ""
    return re.sub(r"\[:(sv|en)](.*?)(?=(\[:|$))", replacer, content)

def clean_file(path, keep_lang):
    with open(path, "r", encoding="utf-8") as f:
        content = f.read()

    content = remove_other_language_blocks(content, keep_lang)
    content = remove_other_language_inline(content, keep_lang)

    with open(path, "w", encoding="utf-8") as f:
        f.write(content.strip() + "\n")

# Rensa svenska filer
for filename in os.listdir(SOURCE_DIR):
    if filename.endswith(".md"):
        clean_file(os.path.join(SOURCE_DIR, filename), keep_lang="sv")

# Rensa engelska filer
for filename in os.listdir(ENGLISH_DIR):
    if filename.endswith(".md"):
        clean_file(os.path.join(ENGLISH_DIR, filename), keep_lang="en")