import os
import re

SRC_DIR = "src"

def minify_html(html: str) -> str:
    # Tags where whitespace should be preserved
    preserve_tags = ['pre', 'code', 'textarea']
    preserve_regex = '|'.join(preserve_tags)

    # Protect preserve blocks with placeholders
    preserve_blocks = []
    def preserve(match):
        preserve_blocks.append(match.group(0))
        return f"__PRESERVE_BLOCK_{len(preserve_blocks)-1}__"

    html = re.sub(rf'<({preserve_regex})[\s\S]*?</\1>', preserve, html, flags=re.IGNORECASE)

    # Remove HTML comments
    html = re.sub(r'<!--.*?-->', '', html, flags=re.DOTALL)

    # Collapse all whitespace between tags
    html = re.sub(r'>\s+<', '><', html)

    # Collapse multiple spaces inside tags
    html = re.sub(r'\s+', ' ', html)

    # Restore preserved blocks
    for i, block in enumerate(preserve_blocks):
        html = html.replace(f"__PRESERVE_BLOCK_{i}__", block)

    return html.strip()

for root, _, files in os.walk(SRC_DIR):
    for file in files:
        if file.endswith(".html"):
            html_path = os.path.join(root, file)
            with open(html_path, "r", encoding="utf-8") as f:
                html_content = f.read()

            # minified = regex.sub("\g<1>", html_content)
            minified = minify_html(html_content)
            base_name = f"{os.path.splitext(file)[0]}Html"
            header_path = os.path.join(root, f"{base_name}.generated.h")

            with open(header_path, "w", encoding="utf-8") as h:
                h.write(f"// THIS FILE IS AUTOGENERATED, DO NOT EDIT MANUALLY\n\n")
                h.write(f"#pragma once\n")
                h.write(f'constexpr char {base_name}[] PROGMEM = R"rawliteral({minified})rawliteral";\n')

            print(f"Generated: {header_path}")