ietf-draft-analyzer/scripts/build-site.py

#!/usr/bin/env python3
"""Build static HTML blog site from markdown posts in data/reports/blog-series/."""

import re
from pathlib import Path

import markdown

ROOT = Path(__file__).resolve().parent.parent
POSTS_DIR = ROOT / "data" / "reports" / "blog-series"
OUT_DIR = ROOT / "docs" / "blog"
CSS_DIR = OUT_DIR / "css"
POSTS_OUT = OUT_DIR / "posts"

# Ordered list of posts to include
POSTS = [
    ("00-series-overview.md", "Series Overview"),
    ("01-gold-rush.md", "The Gold Rush"),
    ("02-who-writes-the-rules.md", "Who Writes the Rules"),
    ("03-oauth-wars.md", "The OAuth Wars"),
    ("04-what-nobody-builds.md", "What Nobody Builds"),
    ("05-1262-ideas.md", "Where Drafts Converge"),
    ("06-big-picture.md", "The Big Picture"),
    ("07-how-we-built-this.md", "How We Built This"),
    ("08-agents-building-the-analysis.md", "Agents Building the Agent Analysis"),
]

CSS = """\
:root {
    --bg: #ffffff;
    --text: #1a1a1a;
    --muted: #6b7280;
    --border: #e5e7eb;
    --accent: #2563eb;
    --code-bg: #f3f4f6;
}

@media (prefers-color-scheme: dark) {
    :root {
        --bg: #111827;
        --text: #e5e7eb;
        --muted: #9ca3af;
        --border: #374151;
        --accent: #60a5fa;
        --code-bg: #1f2937;
    }
}

* { margin: 0; padding: 0; box-sizing: border-box; }

body {
    font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
    color: var(--text);
    background: var(--bg);
    line-height: 1.7;
    font-size: 17px;
}

.container {
    max-width: 720px;
    margin: 0 auto;
    padding: 2rem 1.5rem;
}

nav {
    border-bottom: 1px solid var(--border);
    padding: 1rem 0;
    margin-bottom: 2rem;
}

nav a {
    color: var(--accent);
    text-decoration: none;
    margin-right: 1.5rem;
    font-size: 0.9rem;
}

nav a:hover { text-decoration: underline; }
nav .site-title { font-weight: 700; font-size: 1.1rem; }

h1 { font-size: 2rem; margin: 1.5rem 0 1rem; line-height: 1.2; }
h2 { font-size: 1.5rem; margin: 2rem 0 0.75rem; }
h3 { font-size: 1.2rem; margin: 1.5rem 0 0.5rem; }

p { margin: 0.75rem 0; }

a { color: var(--accent); }

blockquote {
    border-left: 3px solid var(--accent);
    padding-left: 1rem;
    color: var(--muted);
    margin: 1rem 0;
}

code {
    background: var(--code-bg);
    padding: 0.15rem 0.4rem;
    border-radius: 3px;
    font-size: 0.9em;
}

pre {
    background: var(--code-bg);
    padding: 1rem;
    border-radius: 6px;
    overflow-x: auto;
    margin: 1rem 0;
}

pre code { background: none; padding: 0; }

table {
    width: 100%;
    border-collapse: collapse;
    margin: 1rem 0;
    font-size: 0.95rem;
}

th, td {
    padding: 0.5rem 0.75rem;
    border: 1px solid var(--border);
    text-align: left;
}

th { background: var(--code-bg); font-weight: 600; }

ul, ol { padding-left: 1.5rem; margin: 0.75rem 0; }
li { margin: 0.25rem 0; }

.post-nav {
    display: flex;
    justify-content: space-between;
    margin-top: 3rem;
    padding-top: 1rem;
    border-top: 1px solid var(--border);
    font-size: 0.9rem;
}

.post-list { list-style: none; padding: 0; }
.post-list li { margin: 1rem 0; }
.post-list a { font-size: 1.1rem; font-weight: 500; }
.post-list .desc { color: var(--muted); font-size: 0.9rem; }

footer {
    margin-top: 3rem;
    padding-top: 1rem;
    border-top: 1px solid var(--border);
    color: var(--muted);
    font-size: 0.85rem;
}
"""


def slug(filename: str) -> str:
    return filename.replace(".md", ".html")


def build_nav(current: str = "") -> str:
    links = ['<a href="/blog/" class="site-title">IETF AI Agent Analysis</a>']
    for fn, title in POSTS[1:]:  # skip overview in nav
        s = slug(fn)
        if fn == current:
            links.append(f"<strong>{title.split()[-1]}</strong>")
        else:
            links.append(f'<a href="/blog/posts/{s}">{title.split()[-1]}</a>')
    return "<nav>" + "\n".join(links) + "</nav>"


def build_post_nav(idx: int) -> str:
    parts = []
    if idx > 0:
        prev_fn, prev_title = POSTS[idx - 1]
        parts.append(f'<a href="/blog/posts/{slug(prev_fn)}">&larr; {prev_title}</a>')
    else:
        parts.append("<span></span>")
    if idx < len(POSTS) - 1:
        next_fn, next_title = POSTS[idx + 1]
        parts.append(f'<a href="/blog/posts/{slug(next_fn)}">{next_title} &rarr;</a>')
    else:
        parts.append("<span></span>")
    return f'<div class="post-nav">{parts[0]}{parts[1]}</div>'


def wrap_html(title: str, body: str, nav: str, post_nav: str = "") -> str:
    return f"""<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="utf-8">
    <meta name="viewport" content="width=device-width, initial-scale=1">
    <title>{title} — IETF AI Agent Analysis</title>
    <link rel="stylesheet" href="/blog/css/style.css">
</head>
<body>
<div class="container">
{nav}
{body}
{post_nav}
<footer>
    <p>IETF Draft Analyzer &mdash; Data collected through March 2026.
    <a href="https://github.com/cnennemann/ietf-draft-analyzer">Source on GitHub</a></p>
</footer>
</div>
</body>
</html>"""


def extract_title(md_text: str) -> str:
    """Extract first H1 from markdown."""
    m = re.search(r"^#\s+(.+)$", md_text, re.MULTILINE)
    return m.group(1) if m else "Untitled"


def main():
    md_ext = markdown.Markdown(extensions=["tables", "fenced_code", "toc"])

    # Create output dirs
    CSS_DIR.mkdir(parents=True, exist_ok=True)
    POSTS_OUT.mkdir(parents=True, exist_ok=True)

    # Write CSS
    (CSS_DIR / "style.css").write_text(CSS)

    # Write .nojekyll
    (OUT_DIR / ".nojekyll").write_text("")

    # Build each post
    for idx, (fn, fallback_title) in enumerate(POSTS):
        src = POSTS_DIR / fn
        if not src.exists():
            print(f"  SKIP {fn} (not found)")
            continue

        md_text = src.read_text()
        md_ext.reset()
        html_body = md_ext.convert(md_text)
        title = extract_title(md_text) or fallback_title

        nav = build_nav(fn)
        post_nav = build_post_nav(idx)
        full_html = wrap_html(title, html_body, nav, post_nav)

        out_path = POSTS_OUT / slug(fn)
        out_path.write_text(full_html)
        print(f"  BUILT {out_path.relative_to(ROOT)}")

    # Build index page
    post_links = []
    for i, (fn, title) in enumerate(POSTS):
        if i == 0:
            continue  # skip overview in index list
        post_links.append(
            f'<li><a href="/blog/posts/{slug(fn)}">Post {i}: {title}</a></li>'
        )

    index_body = f"""
<h1>The AI Agent Standards Gold Rush</h1>
<p><em>A data-driven analysis of {475} IETF Internet-Drafts on AI agents, autonomous systems, and machine learning protocols.</em></p>

<p>The IETF is experiencing an unprecedented surge in AI/agent standardization activity.
We built an automated analysis pipeline to make sense of it: {713} authors, {501} ideas,
{132} cross-organizational convergent ideas, and {12} identified gaps.</p>

<h2>The Series</h2>
<ul class="post-list">
{"".join(post_links)}
</ul>

<h2>About</h2>
<p>This analysis was produced using the <a href="https://github.com/cnennemann/ietf-draft-analyzer">IETF Draft Analyzer</a>,
an open-source Python tool that combines Claude for multi-dimensional rating and idea extraction
with Ollama for semantic embeddings. Total API cost: ~$9-15.</p>

<p><a href="/blog/posts/{slug(POSTS[0][0])}">Read the series overview &rarr;</a></p>
"""

    index_html = wrap_html("Home", index_body, build_nav())
    (OUT_DIR / "index.html").write_text(index_html)
    print(f"  BUILT docs/blog/index.html")

    print(f"\nDone. {len(POSTS) + 1} pages built in docs/blog/")


if __name__ == "__main__":
    main()