"""Live-preview rendering for smolbuilder.

Turns the agent's workspace (a `path -> content` dict of a small static web app)
into a single self-contained HTML document, then into a sandboxed iframe that
Gradio can drop straight into a `gr.HTML`. This is the "Replit/Lovable" preview:
what the tiny model just built, running live in the browser.

Deliberately dependency-free (stdlib only) so it can be unit-tested without
Gradio or the Rust engine, and so the rendering logic stays trivially auditable.

Design choices:
- We inline locally-referenced `<link rel=stylesheet>` and `<script src=...>`
  from sibling files, so a model that splits style.css / script.js out of
  index.html still previews correctly — but we never touch absolute/CDN URLs.
- The iframe is loaded via `srcdoc=` (not a `data:` URI). A `data:` URL has an
  *opaque origin*, where `localStorage`/`sessionStorage` throw `SecurityError` —
  so any app that persists state (a notepad, a to-do list) dies on load before it
  can wire up its buttons. A `srcdoc` frame inherits the embedder's (Gradio's)
  origin, so storage and scripts work the way the model expects.
- SECURITY TRADE-OFF: `sandbox="allow-scripts allow-same-origin ..."` is required
  for storage to work, but that combination also lets the framed (model-written)
  code reach the parent page. This is acceptable for a *local, single-user*
  builder — the framed code is the same user's own request, on a page holding no
  one else's secrets. Do NOT reuse this wrapper to embed untrusted third-party
  apps on an origin that holds other users' data; the isolation-preserving fix is
  to serve the preview from a separate origin (out of scope here).
- The same wrapper (`PREVIEW_SANDBOX`/`_escape_srcdoc`) is reused by the headless
  verification check (engine/browsercheck.py) so the agent tests *exactly* what
  the user sees.
"""
from __future__ import annotations

import html
import re

# Sandbox flags shared by the live preview and the verification check.
# allow-same-origin is required so srcdoc inherits the parent origin and web
# storage works; combined with allow-scripts it weakens isolation (see docstring).
PREVIEW_SANDBOX = "allow-scripts allow-same-origin allow-modals allow-popups allow-forms"

# Files we know how to treat as the app entrypoint, best first.
_ENTRY_CANDIDATES = ("index.html", "main.html", "app.html")

_LINK_RE = re.compile(
    r"""<link\b[^>]*?\brel\s*=\s*['"]?stylesheet['"]?[^>]*?>""", re.I | re.S)
_SCRIPT_SRC_RE = re.compile(
    r"""<script\b[^>]*?\bsrc\s*=\s*['"]([^'"]+)['"][^>]*?>\s*</script>""", re.I | re.S)
_HREF_RE = re.compile(r"""\bhref\s*=\s*['"]([^'"]+)['"]""", re.I)


def find_entry(files: dict[str, str]) -> str | None:
    """Pick the HTML entrypoint to preview, or None if there's nothing webby."""
    lower = {p.lower(): p for p in files}
    for cand in _ENTRY_CANDIDATES:
        if cand in lower:
            return lower[cand]
    # Fall back to any .html file (shallowest path wins for determinism).
    htmls = sorted((p for p in files if p.lower().endswith(".html")),
                   key=lambda p: (p.count("/"), p))
    return htmls[0] if htmls else None


def _is_local(url: str) -> bool:
    """True for a same-app relative reference we can inline (not a CDN/data URI)."""
    u = url.strip()
    if not u:
        return False
    return not re.match(r"^(?:[a-z]+:)?//|^https?:|^data:|^mailto:|^#", u, re.I)


def _lookup(files: dict[str, str], ref: str) -> str | None:
    """Resolve a relative href/src against the workspace file map."""
    ref = ref.split("?", 1)[0].split("#", 1)[0].lstrip("./").lstrip("/")
    if ref in files:
        return files[ref]
    # Case-insensitive / basename fallback so '/style.css' finds 'style.css'.
    base = ref.rsplit("/", 1)[-1].lower()
    for path, content in files.items():
        if path.lower() == ref.lower() or path.rsplit("/", 1)[-1].lower() == base:
            return content
    return None


def inline_app(files: dict[str, str]) -> str:
    """Return one self-contained HTML document for the app in `files`.

    If there's no HTML entrypoint, render a friendly placeholder (e.g. the model
    has only written notes or a not-yet-web file).
    """
    entry = find_entry(files)
    if entry is None:
        return _placeholder(files)

    doc = files[entry]

    def _inline_css(match: re.Match) -> str:
        tag = match.group(0)
        href_m = _HREF_RE.search(tag)
        if not href_m or not _is_local(href_m.group(1)):
            return tag
        css = _lookup(files, href_m.group(1))
        if css is None:
            return tag
        return f"<style>\n{css}\n</style>"

    def _inline_js(match: re.Match) -> str:
        src = match.group(1)
        if not _is_local(src):
            return match.group(0)
        js = _lookup(files, src)
        if js is None:
            return match.group(0)
        # Guard against the inlined body prematurely closing the script element.
        safe = js.replace("</script>", "<\\/script>")
        return f"<script>\n{safe}\n</script>"

    doc = _LINK_RE.sub(_inline_css, doc)
    doc = _SCRIPT_SRC_RE.sub(_inline_js, doc)
    return doc


def _escape_srcdoc(doc: str) -> str:
    """Escape an HTML document for a double-quoted `srcdoc="..."` attribute.

    Only `&` and `"` are significant inside a double-quoted attribute value, and
    `&` must go first (so the `&` we introduce for `"` isn't re-escaped). `<`,
    `>` and even a literal `</script>` are FINE here — the parser is in
    attribute-value state, not script-data state — so we must NOT touch them
    (html.escape would corrupt the rendered document).
    """
    return doc.replace("&", "&amp;").replace('"', "&quot;")


def preview_iframe(files: dict[str, str], *, height: int = 540) -> str:
    """Render the app as a sandboxed `srcdoc` iframe ready for `gr.HTML`."""
    srcdoc = _escape_srcdoc(inline_app(files))
    return (
        f'<iframe title="smolbuilder preview" '
        f'style="width:100%;height:{height}px;border:0;border-radius:12px;'
        f'background:#fff;box-shadow:0 1px 0 rgba(0,0,0,.06)" '
        f'sandbox="{PREVIEW_SANDBOX}" '
        f'srcdoc="{srcdoc}"></iframe>'
    )


def _placeholder(files: dict[str, str]) -> str:
    listing = "".join(
        f"<li><code>{html.escape(p)}</code></li>" for p in sorted(files)
    ) or "<li><em>workspace is empty</em></li>"
    return (
        "<!doctype html><html><head><meta charset='utf-8'>"
        "<style>body{font:15px/1.5 system-ui,sans-serif;color:#475569;"
        "background:#f8fafc;padding:2rem}h2{color:#7c3aed;margin:.2rem 0 1rem}"
        "code{background:#ede9fe;color:#5b21b6;padding:1px 6px;border-radius:6px}"
        "</style></head><body>"
        "<h2>No preview yet</h2>"
        "<p>smolbuilder previews the app's <code>index.html</code>. "
        "Describe a web app on the left and it'll appear here, live.</p>"
        f"<p>Files in the workspace:</p><ul>{listing}</ul>"
        "</body></html>"
    )