1  import os
 2  import re
 3  
 4  SRC_DIR = "src"
 5  
 6  def minify_html(html: str) -> str:
 7      # Tags where whitespace should be preserved
 8      preserve_tags = ['pre', 'code', 'textarea', 'script', 'style']
 9      preserve_regex = '|'.join(preserve_tags)
10  
11      # Protect preserve blocks with placeholders
12      preserve_blocks = []
13      def preserve(match):
14          preserve_blocks.append(match.group(0))
15          return f"__PRESERVE_BLOCK_{len(preserve_blocks)-1}__"
16  
17      html = re.sub(rf'<({preserve_regex})[\s\S]*?</\1>', preserve, html, flags=re.IGNORECASE)
18  
19      # Remove HTML comments
20      html = re.sub(r'<!--.*?-->', '', html, flags=re.DOTALL)
21  
22      # Collapse all whitespace between tags
23      html = re.sub(r'>\s+<', '><', html)
24  
25      # Collapse multiple spaces inside tags
26      html = re.sub(r'\s+', ' ', html)
27  
28      # Restore preserved blocks
29      for i, block in enumerate(preserve_blocks):
30          html = html.replace(f"__PRESERVE_BLOCK_{i}__", block)
31  
32      return html.strip()
33  
34  for root, _, files in os.walk(SRC_DIR):
35      for file in files:
36          if file.endswith(".html"):
37              html_path = os.path.join(root, file)
38              with open(html_path, "r", encoding="utf-8") as f:
39                  html_content = f.read()
40  
41              # minified = regex.sub("\g<1>", html_content)
42              minified = minify_html(html_content)
43              base_name = f"{os.path.splitext(file)[0]}Html"
44              header_path = os.path.join(root, f"{base_name}.generated.h")
45  
46              with open(header_path, "w", encoding="utf-8") as h:
47                  h.write(f"// THIS FILE IS AUTOGENERATED, DO NOT EDIT MANUALLY\n\n")
48                  h.write(f"#pragma once\n")
49                  h.write(f'constexpr char {base_name}[] PROGMEM = R"rawliteral({minified})rawliteral";\n')
50  
51              print(f"Generated: {header_path}")