from __future__ import annotations

import json
from html.parser import HTMLParser
from pathlib import Path
from urllib.parse import urlparse

SITE_ROOT = Path(__file__).parents[1] / "docs" / "site"
ALLOWED_STATUSES = {"baseline", "validated", "backlog"}


class SiteParser(HTMLParser):
    def __init__(self) -> None:
        super().__init__()
        self.ids: set[str] = set()
        self.references: list[str] = []

    def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
        values = dict(attrs)
        if values.get("id"):
            self.ids.add(values["id"])
        attribute = "href" if tag in {"a", "link"} else "src" if tag in {"script", "img"} else None
        if attribute and values.get(attribute):
            self.references.append(values[attribute])


def _parser() -> SiteParser:
    parser = SiteParser()
    parser.feed((SITE_ROOT / "index.html").read_text())
    return parser


def test_docs_site_required_files_are_present() -> None:
    for relative_path in ("index.html", "styles.css", "app.js", "experiments.json", "og.png"):
        path = SITE_ROOT / relative_path
        assert path.is_file(), relative_path
        assert path.stat().st_size > 0, relative_path
    assert (SITE_ROOT / "og.png").read_bytes().startswith(b"\x89PNG\r\n\x1a\n")


def test_docs_site_local_links_and_anchors_resolve() -> None:
    parser = _parser()
    for reference in parser.references:
        if reference.startswith("#"):
            assert reference[1:] in parser.ids, reference
            continue

        parsed = urlparse(reference)
        if parsed.scheme or parsed.netloc or reference.startswith("/"):
            continue
        if reference == "../static/favicon.svg":
            continue

        local_path = (SITE_ROOT / parsed.path).resolve()
        assert local_path.is_relative_to(SITE_ROOT.resolve()), reference
        assert local_path.is_file(), reference


def test_docs_site_navigation_targets_every_top_level_section() -> None:
    parser = _parser()
    html = (SITE_ROOT / "index.html").read_text()
    expected_sections = {
        "overview",
        "architecture",
        "agent-loop",
        "workspace",
        "models",
        "experiments",
        "operations",
        "timeline",
        "repository",
    }
    assert expected_sections <= parser.ids
    for section_id in expected_sections:
        assert f'href="#{section_id}"' in html


def test_experiment_ledger_has_unique_stable_records() -> None:
    experiments = json.loads((SITE_ROOT / "experiments.json").read_text())
    assert len(experiments) >= 5

    ids = [item["id"] for item in experiments]
    assert len(ids) == len(set(ids))
    for item in experiments:
        assert item["status"] in ALLOWED_STATUSES
        assert item["title"].strip()
        assert item["summary"].strip()
        assert item["area"].strip()
        assert item["version"].strip()
        assert isinstance(item["metrics"], list)