policy-nexus/tools/render.py

462 lines
17 KiB
Python

#!/usr/bin/env python3
"""Render a canon markdown document into a styled, self-contained artifact page.
Single source of truth: the markdown. The page is generated, never hand-edited,
so the two cannot diverge.
Design devices are recognised from conventions already present in the markdown
rather than from extra markup, so the source stays a readable document:
* a table whose first column is `**X0**`/`**X1**`... renders as a level ladder
* a table whose first header cell is `Threat` renders as a threat matrix
* a table with a `Kind` column renders with mechanical/adversarial chips
* a table whose first header cell is `E \\ P` renders as the E x P matrix
* a blockquote renders as a pull quote
* `**Decision N.N...**` at the start of a paragraph renders as a decision
* `## N. Title` headings build the section rail
Stdlib only, per the estate's structure-not-tooling stance: a publishing step
that needs its own toolchain is a publishing step that stops being run.
Usage:
python3 tools/render.py <source.md> --output <page.html> \\
[--title "Name"] [--subtitle "..."]
"""
from __future__ import annotations
import argparse
import html
import pathlib
import re
import sys
STYLE = pathlib.Path(__file__).parent / "style.css"
INLINE_CODE = re.compile(r"`([^`]+)`")
BOLD = re.compile(r"\*\*([^*]+)\*\*")
EM = re.compile(r"(?<![*\w])\*([^*]+)\*(?!\*)")
LINK = re.compile(r"\[([^\]]+)\]\(([^)]+)\)")
HEADING = re.compile(r"^(#{1,4})\s+(.*)$")
SECTION_NO = re.compile(r"^(\d+)\.\s+(.*)$")
LEVEL_CELL = re.compile(r"^\*\*([IAEPRV])(\d)\*\*$")
DECISION = re.compile(r"^\*\*(Decision [\d.]+[^*]*)\*\*(.*)$", re.S)
def inline(text: str) -> str:
"""Escape, then apply inline markdown. Order matters: code first."""
slots: list[str] = []
def stash(rendered: str) -> str:
slots.append(rendered)
return f"\x00{len(slots) - 1}\x00"
text = INLINE_CODE.sub(lambda m: stash(f"<code>{html.escape(m.group(1))}</code>"), text)
text = html.escape(text, quote=False)
text = LINK.sub(
lambda m: f'<a href="{html.escape(m.group(2), quote=True)}">{m.group(1)}</a>', text
)
text = BOLD.sub(r"<strong>\1</strong>", text)
text = EM.sub(r"<em>\1</em>", text)
for i, rendered in enumerate(slots):
text = text.replace(f"\x00{i}\x00", rendered)
return text
def split_frontmatter(source: str) -> tuple[dict, str]:
if not source.startswith("---\n"):
return {}, source
end = source.index("\n---\n", 4)
meta = {}
for line in source[4:end].splitlines():
if ":" in line and not line.startswith((" ", "-")):
key, _, value = line.partition(":")
meta[key.strip()] = value.strip().strip('"')
return meta, source[end + 5 :]
def parse_table(lines: list[str], start: int) -> tuple[list[list[str]], int]:
rows, i = [], start
while i < len(lines) and lines[i].lstrip().startswith("|"):
cells = [c.strip() for c in lines[i].strip().strip("|").split("|")]
if not all(set(c) <= set("-: ") for c in cells):
rows.append(cells)
i += 1
return rows, i
# --- table renderers -------------------------------------------------------
def render_ladder(rows: list[list[str]]) -> str:
"""A level table becomes a stepped scale. Colour depth encodes strength."""
body = rows[1:]
axis = LEVEL_CELL.match(body[0][0]).group(1)
names = {
"I": "Identity", "A": "Authorization", "E": "Enforcement",
"P": "Placement", "R": "Retention", "V": "Availability",
}
rungs = []
for cells in body:
match = LEVEL_CELL.match(cells[0])
if not match:
continue
n = int(match.group(2))
text = cells[1] if len(cells) > 1 else ""
rungs.append(
f'<div class="rung r{n}"><span class="code">{axis}{n}</span>'
f'<span class="txt">{inline(text)}</span></div>'
)
while len(rungs) < 5:
rungs.append('<div class="rung na"><span class="code">—</span>'
f'<span class="txt">Ladder ends at {axis}{len(rungs) - 1}.</span></div>')
return (
'<div class="ladder"><div class="pname">'
f'{names.get(axis, axis)}<span>axis {axis}</span></div>'
f'<div class="rungs">{"".join(rungs)}</div></div>'
)
def render_threat(rows: list[list[str]]) -> str:
head = "".join(f"<th>{inline(c)}</th>" for c in rows[0])
body = []
for cells in rows[1:]:
tds = [f"<td>{inline(cells[0])}</td>"]
for c in cells[1:]:
cls = "yes" if "" in c else "no" if "" in c else ""
tds.append(f'<td class="{cls}">{inline(c)}</td>')
body.append(f"<tr>{''.join(tds)}</tr>")
return (f'<div class="scroll"><table class="tm"><thead><tr>{head}</tr></thead>'
f'<tbody>{"".join(body)}</tbody></table></div>')
def render_matrix(rows: list[list[str]]) -> str:
"""`E \\ P` table becomes the two-axis grid. Cells hold pins or markers."""
cols = rows[0][1:]
cells = ['<div class="mgrid">']
for cells_row in rows[1:]:
e = cells_row[0].strip("*")
level = int(e[1]) if len(e) > 1 and e[1].isdigit() else 0
cells.append(f'<div class="rlab">{html.escape(e)}</div>')
for value in cells_row[1:]:
v = value.strip()
if v == "":
cells.append('<div class="mcell void"></div>')
continue
tint = f" tint{level}" if level else ""
pins = ""
for entry in (p.strip() for p in v.split("<br>") if p.strip()):
ghost = " ghost" if entry.startswith("(") else ""
pins += f'<span class="pin{ghost}">{inline(entry.strip("()"))}</span>'
cells.append(f'<div class="mcell{tint}">{pins}</div>')
cells.append('<div class="rlab"></div>')
cells.extend(f'<div class="clab">{html.escape(c)}</div>' for c in cols)
cells.append("</div>")
return (
'<div class="matrix-shell"><div class="ylab">Enforcement →</div>'
+ "".join(cells)
+ "</div>"
'<div class="mnote">'
'<span class="k"><span class="sw"></span>Where a service sits today</span>'
'<span class="k"><span class="sw g"></span>Target or default</span>'
'<span class="k"><span class="sw v"></span>Unreachable at this placement</span>'
"</div>"
)
def render_table(rows: list[list[str]]) -> str:
if not rows:
return ""
header = [c.strip() for c in rows[0]]
first = header[0].lower()
if first.replace(" ", "") in {"e\\p", "e\\p"}:
return render_matrix(rows)
if first == "threat":
return render_threat(rows)
kind_col = header.index("Kind") if "Kind" in header else None
# A level table is a ladder. The evidence table also leads with `Level` but
# carries a `Kind` column, and is a table of artifacts, not of rungs.
if first == "level" and kind_col is None and len(rows) > 1 and LEVEL_CELL.match(rows[1][0]):
return render_ladder(rows)
head = "".join(f"<th>{inline(c)}</th>" for c in header)
body = []
for cells in rows[1:]:
tds = []
for i, c in enumerate(cells):
if i == kind_col:
adv = "adv" if "adversarial" in c.lower() else ""
label = re.sub(r"[*_]", "", c).strip()
tds.append(f'<td><span class="kind {adv}">{html.escape(label)}</span></td>')
else:
tds.append(f"<td>{inline(c)}</td>")
body.append(f"<tr>{''.join(tds)}</tr>")
return (f'<div class="scroll"><table><thead><tr>{head}</tr></thead>'
f'<tbody>{"".join(body)}</tbody></table></div>')
# --- document ---------------------------------------------------------------
def render_body(markdown: str) -> tuple[str, list[tuple[str, str, str]]]:
lines = markdown.splitlines()
out: list[str] = []
rail: list[tuple[str, str, str]] = []
open_section = False
ladders_open = False
i = 0
def close_ladders() -> None:
nonlocal ladders_open
if ladders_open:
out.append("</div></div>")
ladders_open = False
while i < len(lines):
line = lines[i]
stripped = line.strip()
if not stripped:
i += 1
continue
heading = HEADING.match(stripped)
if heading:
level, text = len(heading.group(1)), heading.group(2)
if level == 1:
i += 1
continue
if level == 2:
close_ladders()
if open_section:
out.append("</section>")
match = SECTION_NO.match(text)
if match:
num, title = match.group(1), match.group(2)
anchor = f"s{num}"
rail.append((anchor, num, title))
out.append(
f'<section id="{anchor}"><h2>'
f'<span class="sn">{int(num):02d}</span>{inline(title)}</h2>'
)
else:
anchor = re.sub(r"[^a-z0-9]+", "-", text.lower()).strip("-")
rail.append((anchor, "·", text))
out.append(f'<section id="{anchor}"><h2>{inline(text)}</h2>')
open_section = True
else:
close_ladders()
out.append(f"<h3>{inline(text)}</h3>")
i += 1
continue
if stripped.startswith("|"):
rows, i = parse_table(lines, i)
rendered = render_table(rows)
if 'class="ladder"' in rendered:
if not ladders_open:
out.append('<div class="breakout"><div class="ladders">')
ladders_open = True
out.append(rendered)
else:
close_ladders()
out.append(rendered)
continue
close_ladders()
if stripped.startswith("```"):
block = []
i += 1
while i < len(lines) and not lines[i].strip().startswith("```"):
block.append(lines[i])
i += 1
out.append(f"<pre>{html.escape(chr(10).join(block))}</pre>")
i += 1
continue
if stripped.startswith(">"):
quote = []
while i < len(lines) and lines[i].strip().startswith(">"):
quote.append(lines[i].strip().lstrip(">").strip())
i += 1
out.append(f'<div class="rule-quote"><p>{inline(" ".join(quote))}</p></div>')
continue
if re.match(r"^[-*]\s+", stripped) or re.match(r"^\d+\.\s+", stripped):
ordered = bool(re.match(r"^\d+\.\s+", stripped))
items = []
while i < len(lines):
s = lines[i].strip()
if re.match(r"^[-*]\s+", s) or re.match(r"^\d+\.\s+", s):
items.append(re.sub(r"^([-*]|\d+\.)\s+", "", s))
elif s and lines[i].startswith((" ", "\t")) and items:
items[-1] += " " + s
else:
break
i += 1
tag = "ol" if ordered else "ul"
body = "".join(f"<li>{inline(t)}</li>" for t in items)
out.append(f"<{tag}>{body}</{tag}>")
continue
if set(stripped) <= set("-") and len(stripped) >= 3:
i += 1
continue
para = [stripped]
i += 1
while i < len(lines) and lines[i].strip() and not re.match(
r"^(\||>|```|#{1,4}\s|[-*]\s|\d+\.\s|---)", lines[i].strip()
):
para.append(lines[i].strip())
i += 1
text = " ".join(para)
decision = DECISION.match(text)
if decision:
out.append(
f'<p><span class="dec">{inline(decision.group(1))}</span>'
f"{inline(decision.group(2))}</p>"
)
else:
out.append(f"<p>{inline(text)}</p>")
close_ladders()
if open_section:
out.append("</section>")
return "\n".join(out), rail
def render_page(
source: pathlib.Path,
*,
title: str | None = None,
subtitle: str = "",
publication: dict[str, str] | None = None,
) -> tuple[str, dict, int]:
meta, markdown = split_frontmatter(source.read_text(encoding="utf-8"))
body, rail = render_body(markdown)
resolved_title = title or meta.get("title", source.stem)
display = resolved_title.split(":")[0].strip()
eyebrow = " ".join(
f"<span{' class=\"stat\"' if k == 'status' else ''}>{html.escape(v)}</span>"
for k, v in (
("id", meta.get("id", "")),
("status", f"{meta.get('status', '')} · {meta.get('revision', '')}".strip(" ·")),
("owner", meta.get("owner", "")),
(
"review",
f"reviewed {meta.get('last_reviewed', '')}"
if meta.get("last_reviewed")
else "",
),
)
if v
)
rail_html = "".join(
f'<li><a href="#{a}"><span class="n">{n}</span>{html.escape(t)}</a></li>'
for a, n, t in rail
)
publication = publication or {}
source_note = " · ".join(
item
for item in (
publication.get("source_repo", ""),
publication.get("source_path", ""),
publication.get("source_revision", ""),
)
if item
)
source_line = (
f'<p class="sub">Source: <code>{html.escape(source_note)}</code></p>'
if source_note
else ""
)
review_due = publication.get("review_due", "")
review_line = (
f'<p class="sub">Review due: {html.escape(review_due)}</p>'
if review_due
else ""
)
lifecycle = publication.get("lifecycle", "active")
successor = publication.get("successor", "")
lifecycle_notice = ""
if lifecycle == "superseded":
successor_link = (
f' <a href="{html.escape(successor, quote=True)}">Read its successor.</a>'
if successor
else ""
)
lifecycle_notice = (
'<div class="rule-quote"><p><strong>Superseded.</strong>'
f" This address is retained as part of the policy record.{successor_link}</p></div>"
)
elif lifecycle == "withdrawn":
lifecycle_notice = (
'<div class="rule-quote"><p><strong>Withdrawn.</strong> '
"This document is retained for historical reference and is not current policy."
"</p></div>"
)
currency_notice = (
'<div class="rule-quote"><p><strong>Review overdue.</strong> '
f"This document was due for review on {html.escape(review_due)}.</p></div>"
if review_due and publication.get("stale") == "true"
else ""
)
source_revision_meta = (
f'<meta name="policy-source-revision" content="'
f'{html.escape(publication.get("source_revision", ""), quote=True)}">\n'
if publication.get("source_revision")
else ""
)
source_digest_meta = (
f'<meta name="policy-source-digest" content="'
f'{html.escape(publication.get("source_digest", ""), quote=True)}">\n'
if publication.get("source_digest")
else ""
)
page = (
"<!doctype html>\n<html lang=\"en\"><meta charset=\"utf-8\">\n"
+ source_revision_meta
+ source_digest_meta
+ f"<title>{html.escape(display)}</title>\n"
f"<style>\n{STYLE.read_text()}\n</style>\n"
'<div class="wrap"><header>'
f'<div class="eyebrow">{eyebrow}<span>generated from canonical source — do not edit</span></div>'
f"<h1>{html.escape(display)}</h1>"
+ (f'<p class="sub">{html.escape(subtitle)}</p>' if subtitle else "")
+ source_line
+ review_line
+ '</header><div class="layout">'
f'<nav class="rail" aria-label="Sections"><ol>{rail_html}</ol></nav>'
f"<main>{lifecycle_notice}{currency_notice}{body}"
f'<footer><span>{html.escape(meta.get("id", ""))} · '
f'{html.escape(meta.get("revision", ""))} · {html.escape(meta.get("status", ""))}</span>'
f"<span>{html.escape(source_note or 'generated from canonical source')}</span></footer>"
"</main></div></div></html>\n"
)
return page, meta, len(rail)
def main() -> int:
ap = argparse.ArgumentParser()
ap.add_argument("source", type=pathlib.Path)
ap.add_argument("--output", required=True, type=pathlib.Path)
ap.add_argument("--title", default=None)
ap.add_argument("--subtitle", default="")
args = ap.parse_args()
page, _meta, section_count = render_page(
args.source,
title=args.title,
subtitle=args.subtitle,
)
args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(page, encoding="utf-8")
print(f"{args.output}: {section_count} sections, {len(page)} bytes")
return 0
if __name__ == "__main__":
raise SystemExit(main())