diff options
Diffstat (limited to 'content/en/blog/2025/01-sitegen.md')
| -rw-r--r-- | content/en/blog/2025/01-sitegen.md | 135 |
1 files changed, 135 insertions, 0 deletions
diff --git a/content/en/blog/2025/01-sitegen.md b/content/en/blog/2025/01-sitegen.md new file mode 100644 index 0000000..99fb97f --- /dev/null +++ b/content/en/blog/2025/01-sitegen.md @@ -0,0 +1,135 @@ +# Static site generator in 90 lines of Python code + +Created: Apr 16, 2025 + +[На русском](/ru/blog/2025/01-sitegen) + +A long time ago, I made a small business card website. It consisted of three +simple HTML pages, one CSS file (which I generated from SCSS), several fonts +and images. That was more than enough to get a link to my website featured +in a resume or social media profile. + + + + +I recently decided to continue working <a href="https://github.com/blankhex/bhlib" target="_blank">on my pet-project</a> +and would like to publish all sorts of notes and articles on this topic on my +website. I didn't want to manually mess with HTML files, so I decided to look +for an alternative in the form of some kind of static website generator. +Ideally, I would like it to be: + +- Small and simple +- Able to work with Markdown +- Able syntax-highlight blocks of code + +Unfortunately, I couldn't find any suitable solutions for myself, so I decided +to build my own using Python, <a href="https://mistune.lepture.com/en/latest/" target="_blank">mistune</a> +Markdown parser, <a href="https://jinja.palletsprojects.com/en/stable/" target="_blank">Jinja2</a> +template engine, and <a href="https://pygments.org" target="_blank">Pygments</a>. +The whole generation process boils down to the following: + +1. For every file in the input directory check whether it is Markdown + - If yes - convert it to HTML (with highlighting) and write to output directory + - If no - copy as is to output directory +2. Compress content of the output directory + +This generation process has a rather major drawback - due to the fact that +there is no post-processing of HTML, any links to other Markdown pages must +end with a `.html` extension[^1]. + +[^1]: This can be mitigated by special web-server configuration, that replaces + `.md` extension with `.html` or by omitting `.md` extension entirely and + using something like `try_files $uri $uri.html` + +Here is the code: + +```python +import re, jinja2, mistune, shutil, os, pathlib, tarfile +from pygments.lexers import get_lexer_by_name +from pygments.formatters import HtmlFormatter +from pygments import highlight + + +class PygmentsHTMLRenderer(mistune.HTMLRenderer): + def block_code(self, code: str, info = None): + if not info: + return '\n<pre><code>%s</code></pre>\n' % mistune.escape(code) + lexer = get_lexer_by_name(info, stripall=True) + formatter = HtmlFormatter(lineseparator='<br>') + return highlight(code, lexer, formatter) + + +def convert_markdown(page: str): + plugins = ['footnotes', 'table', 'strikethrough', 'url'] + renderer = PygmentsHTMLRenderer(escape=False) + return mistune.create_markdown(plugins=plugins, renderer=renderer)(page) + + +def extract_title(page: str): + matches = re.match('<h1>(.*?)</h1>', page) + if matches: + return matches.group(1) + return 'BlankHex' + + +def handle_file(path: str, input_dir: str, output_dir: str, template_name: str): + # Calculate input and output paths + relpath = os.path.relpath(path, input_dir) + input_path = path + output_path = os.path.join(output_dir, relpath) + if input_path.endswith('.md'): + output_path = output_path.replace('.md', '.html') + + # Don't convert if output path exists + if os.path.exists(output_path): + return + + # Run conversion + pathlib.Path(os.path.dirname(output_path)).mkdir(parents=True, exist_ok=True) + if input_path.endswith('.md'): + # Read Markdown document + with open(input_path, 'r') as handle: + markdown_page = handle.read() + + # Get Pygments styles for light and dark themes + light_style = HtmlFormatter(style='default').get_style_defs() + dark_style = HtmlFormatter(style='monokai').get_style_defs() + + # Convert Markdown document to HTML document + html_page = convert_markdown(markdown_page) + html_header = extract_title(html_page) + environment = jinja2.Environment(loader=jinja2.FileSystemLoader('template/')) + template = environment.get_template(template_name) + output_page = template.render(title=html_header, + body=html_page, + light_style=light_style, + dark_style=dark_style) + + # Write HTML document + with open(output_path, 'w') as handle: + handle.write(output_page) + else: + # Copy file as is + shutil.copy(path, output_path) + + +def convert_dir(input_dir: str, output_dir: str, template_name: str): + # Convert or copy every file from the input directory to the output directory + for subdir, dirs, files in os.walk(input_dir): + for file in files: + handle_file(os.path.join(subdir, file), input_dir, output_dir, template_name) + + +# Remove output from previous run +if os.path.isdir('public'): + shutil.rmtree('public') +if os.path.isfile('public.tgz'): + os.remove('public.tgz') + +# Run conversion +convert_dir('content', 'public', 'template.html') +with tarfile.open('public.tgz', 'w:gz') as tar: + for file in os.listdir('public'): + tar.add(os.path.join('public', file), file) +``` + |