narty-2027/gen_pages.py

#!/usr/bin/env python3
"""Renderuje karty HTML konceptów bundle'a do katalogu pages/.

Graf (viz.html) pokazuje strukturę; karty pokazują treść — ceny, dostępność,
plusy/minusy, listy do zrobienia. Węzeł w grafie linkuje do karty przez pole
`resource` (patrz gen_viz.py).

Renderer markdown: używa `python-markdown`, jeśli jest zainstalowany
(rozszerzenia tables + fenced_code + sane_lists); w przeciwnym razie własnego
renderera na samej bibliotece standardowej — obsługuje nagłówki, akapity,
tabele GFM, listy (w tym `- [ ]`), cytaty, bloki kodu, linie poziome oraz
inline: **bold**, *kursywa*, `kod`, [linki](...). Który tor zadziałał, skrypt
wypisuje przy uruchomieniu.

Pliki .md NIE są modyfikowane — to czysty generator, tak samo jak gen_viz.py.
Pliki zarezerwowane (index.md, log.md) nie są konceptami (§3.1) i nie
dostają kart; linki do nich prowadzą do pages/index.html.

Uruchomienie: python3 gen_pages.py
"""

from __future__ import annotations

import html
import posixpath
import re
import shutil
import sys
from dataclasses import dataclass
from pathlib import Path

import yaml

BUNDLE_ROOT = Path(__file__).resolve().parent
PAGES_DIRNAME = "pages"
PAGES_DIR = BUNDLE_ROOT / PAGES_DIRNAME
BUNDLE_NAME = "Ski 2027 — Skicircus Saalbach"
RESERVED = {"index.md", "log.md"}

try:  # renderer preferowany, jeśli dostępny w systemie
    import markdown as _markdown_lib
except ModuleNotFoundError:
    _markdown_lib = None

RENDERER = "python-markdown" if _markdown_lib else "fallback (biblioteka standardowa)"


# --- model ------------------------------------------------------------


@dataclass
class Concept:
    id: str            # np. "oferty/glemm-lodge"
    path: Path
    frontmatter: dict
    body: str

    @property
    def page(self) -> str:
        """Ścieżka karty względem katalogu pages/."""
        return f"{self.id}.html"

    @property
    def title(self) -> str:
        return str(self.frontmatter.get("title") or self.id)


def load_concepts() -> list[Concept]:
    concepts: list[Concept] = []
    for path in sorted(BUNDLE_ROOT.rglob("*.md")):
        if ".git" in path.parts or path.name in RESERVED:
            continue
        text = path.read_text(encoding="utf-8")
        frontmatter: dict = {}
        body = text
        if text.startswith("---\n"):
            end = text.find("\n---", 3)
            if end != -1:
                frontmatter = yaml.safe_load(text[4:end]) or {}
                body = text[end + 4 :]
        concepts.append(
            Concept(
                id=path.relative_to(BUNDLE_ROOT).with_suffix("").as_posix(),
                path=path,
                frontmatter=frontmatter,
                body=body.lstrip("\n"),
            )
        )
    return concepts


# --- linki ------------------------------------------------------------

_LINK_TARGET_RE = re.compile(r"\]\(([^)\s]+\.md)((?:#[^)\s]*)?)\)")


def rewrite_links(body: str, source: Concept, pages: dict[str, str]) -> str:
    """Linki do plików .md → względne ścieżki do kart. External bez zmian."""
    here = posixpath.dirname(source.page)

    def repl(match: re.Match) -> str:
        target, fragment = match.group(1), match.group(2)
        if "://" in target:
            return match.group(0)
        if target.startswith("/"):
            rel = target[1:]
        else:
            rel = posixpath.normpath(posixpath.join(posixpath.dirname(source.id), target))
        concept_id = rel[:-3] if rel.endswith(".md") else rel
        if concept_id in pages:
            dest = pages[concept_id]
        elif posixpath.basename(rel) in RESERVED:
            dest = "index.html"  # index.md / log.md nie mają kart
        else:
            return match.group(0)
        return "](" + posixpath.relpath(dest, here or ".") + fragment + ")"

    return _LINK_TARGET_RE.sub(repl, body)


# --- renderer markdown: fallback na stdlib -----------------------------

_CODE_RE = re.compile(r"`([^`]+)`")
_LINK_RE = re.compile(r"\[([^\]]*)\]\(([^)\s]+)\)")
_BOLD_RE = re.compile(r"\*\*(.+?)\*\*", re.S)
_ITALIC_STAR_RE = re.compile(r"(?<!\*)\*(?!\s)([^*]+?)(?<!\s)\*(?!\*)")
_ITALIC_UNDER_RE = re.compile(r"(?<![\w\\])_(?!\s)([^_]+?)(?<!\s)_(?![\w])")
_HEADING_RE = re.compile(r"^(#{1,6})\s+(.*)$")
_HR_RE = re.compile(r"^(-{3,}|\*{3,}|_{3,})$")
_LIST_RE = re.compile(r"^\s*([-*+]|\d+[.)])\s+(.*)$")
_TASK_RE = re.compile(r"^\[([ xX])\]\s+(.*)$")
_TABLE_SEP_RE = re.compile(r"^\s*\|?\s*:?-{2,}:?\s*(\|\s*:?-{2,}:?\s*)*\|?\s*$")


def render_inline(text: str) -> str:
    codes: list[str] = []

    def stash(match: re.Match) -> str:
        codes.append(match.group(1))
        return f"\x00c{len(codes) - 1}\x00"

    text = _CODE_RE.sub(stash, text)
    text = html.escape(text, quote=False)

    def link(match: re.Match) -> str:
        label, href = match.group(1), match.group(2)
        attrs = ""
        if "://" in href or href.startswith("mailto:"):
            attrs = ' target="_blank" rel="noopener" class="ext"'
        return f'<a href="{html.escape(href, quote=True)}"{attrs}>{label}</a>'

    text = _LINK_RE.sub(link, text)
    text = _BOLD_RE.sub(r"<strong>\1</strong>", text)
    text = _ITALIC_STAR_RE.sub(r"<em>\1</em>", text)
    text = _ITALIC_UNDER_RE.sub(r"<em>\1</em>", text)

    for i, code in enumerate(codes):
        text = text.replace(f"\x00c{i}\x00", f"<code>{html.escape(code, quote=False)}</code>")
    return text


def _alignments(sep: str) -> list[str]:
    out = []
    for cell in _cells(sep):
        left, right = cell.startswith(":"), cell.endswith(":")
        out.append("center" if left and right else "right" if right else "left")
    return out


def _cells(row: str) -> list[str]:
    return [c.strip() for c in row.strip().strip("|").split("|")]


def _starts_block(line: str) -> bool:
    s = line.strip()
    return (
        not s
        or bool(_HEADING_RE.match(s))
        or bool(_HR_RE.match(s))
        or s.startswith(("```", ">"))
        or bool(_LIST_RE.match(line))
    )


def render_blocks(text: str) -> str:
    lines = text.split("\n")
    out: list[str] = []
    i = 0
    while i < len(lines):
        line = lines[i]
        stripped = line.strip()

        if not stripped:
            i += 1
            continue

        if stripped.startswith("```"):
            i += 1
            code: list[str] = []
            while i < len(lines) and not lines[i].strip().startswith("```"):
                code.append(lines[i])
                i += 1
            i += 1
            out.append(f"<pre><code>{html.escape(chr(10).join(code), quote=False)}</code></pre>")
            continue

        heading = _HEADING_RE.match(stripped)
        if heading:
            level = len(heading.group(1))
            out.append(f"<h{level}>{render_inline(heading.group(2))}</h{level}>")
            i += 1
            continue

        if _HR_RE.match(stripped):
            out.append("<hr>")
            i += 1
            continue

        if "|" in stripped and i + 1 < len(lines) and _TABLE_SEP_RE.match(lines[i + 1]):
            header = _cells(stripped)
            align = _alignments(lines[i + 1])
            i += 2
            rows = []
            while i < len(lines) and "|" in lines[i] and lines[i].strip():
                rows.append(_cells(lines[i]))
                i += 1
            head = "".join(
                f'<th style="text-align:{align[n] if n < len(align) else "left"}">'
                f"{render_inline(c)}</th>"
                for n, c in enumerate(header)
            )
            body = "".join(
                "<tr>"
                + "".join(
                    f'<td style="text-align:{align[n] if n < len(align) else "left"}">'
                    f"{render_inline(c)}</td>"
                    for n, c in enumerate(row)
                )
                + "</tr>"
                for row in rows
            )
            out.append(
                f'<div class="table-wrap"><table><thead><tr>{head}</tr></thead>'
                f"<tbody>{body}</tbody></table></div>"
            )
            continue

        if stripped.startswith(">"):
            quoted = []
            while i < len(lines) and lines[i].strip().startswith(">"):
                quoted.append(lines[i].strip()[1:].lstrip())
                i += 1
            out.append(f"<blockquote>{render_blocks(chr(10).join(quoted))}</blockquote>")
            continue

        item = _LIST_RE.match(line)
        if item:
            ordered = item.group(1)[0].isdigit()
            items: list[str] = []
            while i < len(lines):
                current = lines[i]
                match = _LIST_RE.match(current)
                if match:
                    items.append(match.group(2))
                    i += 1
                elif current.startswith((" ", "\t")) and current.strip() and items:
                    items[-1] += " " + current.strip()
                    i += 1
                else:
                    break
            rendered = []
            for raw in items:
                task = _TASK_RE.match(raw)
                if task:
                    checked = " checked" if task.group(1).lower() == "x" else ""
                    rendered.append(
                        f'<li class="task"><input type="checkbox" disabled{checked}> '
                        f"{render_inline(task.group(2))}</li>"
                    )
                else:
                    rendered.append(f"<li>{render_inline(raw)}</li>")
            tag = "ol" if ordered else "ul"
            out.append(f"<{tag}>{''.join(rendered)}</{tag}>")
            continue

        paragraph = [stripped]
        i += 1
        while i < len(lines) and not _starts_block(lines[i]):
            if "|" in lines[i] and i + 1 < len(lines) and _TABLE_SEP_RE.match(lines[i + 1]):
                break
            paragraph.append(lines[i].strip())
            i += 1
        out.append(f"<p>{render_inline(' '.join(paragraph))}</p>")

    return "\n".join(out)


def md_to_html(text: str) -> str:
    if _markdown_lib:
        return _markdown_lib.markdown(
            text, extensions=["tables", "fenced_code", "sane_lists"]
        )
    return render_blocks(text)


# --- szablon ----------------------------------------------------------

CSS = """
:root { color-scheme: light dark; --fg:#0f172a; --muted:#64748b; --bg:#ffffff;
        --line:#e2e8f0; --accent:#0d9488; --chip:#f1f5f9; --quote:#f8fafc; }
@media (prefers-color-scheme: dark) {
  :root { --fg:#e2e8f0; --muted:#94a3b8; --bg:#0f172a; --line:#334155;
          --accent:#2dd4bf; --chip:#1e293b; --quote:#1e293b; }
}
* { box-sizing: border-box; }
body { margin: 0 auto; padding: 1.25rem 1rem 4rem; max-width: 46rem;
       font-family: system-ui, -apple-system, "Segoe UI", Roboto, sans-serif;
       font-size: 17px; line-height: 1.55; color: var(--fg); background: var(--bg);
       -webkit-text-size-adjust: 100%; }
nav { font-size: .85rem; margin-bottom: 1.25rem; }
nav a { color: var(--muted); }
h1 { font-size: 1.55rem; line-height: 1.25; margin: 0 0 .35rem; }
h2 { font-size: 1.2rem; margin: 2rem 0 .5rem; padding-top: .5rem;
     border-top: 1px solid var(--line); }
h3 { font-size: 1.02rem; margin: 1.4rem 0 .4rem; }
p, ul, ol { margin: .6rem 0; }
ul, ol { padding-left: 1.3rem; }
li { margin: .25rem 0; }
li.task { list-style: none; margin-left: -1.3rem; }
li.task input { margin-right: .45rem; }
a { color: var(--accent); }
a.ext::after { content: " ↗"; font-size: .8em; color: var(--muted); }
code { font-family: ui-monospace, SFMono-Regular, Menlo, monospace; font-size: .88em;
       background: var(--chip); padding: .1em .35em; border-radius: 4px; }
pre { background: var(--chip); padding: .75rem; border-radius: 6px; overflow-x: auto; }
pre code { background: none; padding: 0; }
blockquote { margin: .9rem 0; padding: .6rem .9rem; background: var(--quote);
             border-left: 3px solid var(--accent); border-radius: 0 6px 6px 0; }
blockquote p { margin: .2rem 0; }
hr { border: 0; border-top: 1px solid var(--line); margin: 1.5rem 0; }
.table-wrap { overflow-x: auto; margin: .8rem 0; -webkit-overflow-scrolling: touch; }
table { border-collapse: collapse; width: 100%; font-size: .92rem; }
th, td { border: 1px solid var(--line); padding: .4rem .55rem; vertical-align: top; }
th { background: var(--chip); font-weight: 600; }
.chip { display: inline-block; background: var(--chip); color: var(--muted);
        font-size: .72rem; text-transform: uppercase; letter-spacing: .04em;
        padding: .15rem .5rem; border-radius: 999px; }
.lead { color: var(--muted); margin: .35rem 0 1.25rem; }
.meta { margin: 0 0 1.5rem; }
.meta summary { cursor: pointer; font-size: .85rem; color: var(--muted);
                padding: .3rem 0; }
.meta table { font-size: .85rem; }
.meta th { width: 38%; text-align: left; font-weight: 500; word-break: break-word; }
.cards { list-style: none; padding: 0; margin: 0; }
.cards li { border: 1px solid var(--line); border-radius: 8px; padding: .8rem .9rem;
            margin: .6rem 0; }
.cards a { font-weight: 600; text-decoration: none; }
.cards p { margin: .3rem 0 0; font-size: .9rem; color: var(--muted); }
footer { margin-top: 3rem; padding-top: 1rem; border-top: 1px solid var(--line);
         font-size: .78rem; color: var(--muted); }
"""


def _page_shell(title: str, depth: int, content: str) -> str:
    up = "../" * depth
    return f"""<!doctype html>
<html lang="pl">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>{html.escape(title)} — {html.escape(BUNDLE_NAME)}</title>
<style>{CSS}</style>
</head>
<body>
<nav><a href="{up}index.html">← Wszystkie karty</a> · <a href="{up}../viz.html">Graf</a></nav>
{content}
<footer>Wygenerowane z bundle'a OKF przez <code>gen_pages.py</code> — nie edytuj
tych plików, edytuj <code>.md</code> i przegeneruj.</footer>
</body>
</html>
"""


def _meta_table(frontmatter: dict) -> str:
    rows = []
    for key, value in frontmatter.items():
        if isinstance(value, list):
            shown = ", ".join(_link_value(str(v)) for v in value)
        else:
            shown = _link_value(str(value))
        rows.append(
            f"<tr><th>{html.escape(str(key))}</th><td>{shown}</td></tr>"
        )
    return (
        '<details class="meta" open><summary>Metadane (frontmatter)</summary>'
        f'<div class="table-wrap"><table><tbody>{"".join(rows)}</tbody></table></div>'
        "</details>"
    )


_URLISH_RE = re.compile(
    r"^(https?://\S+|(?:[a-z0-9][a-z0-9-]*\.)+(?:at|com|pl|de|eu|net|org|io|info))$"
)


def _link_value(value: str) -> str:
    """Wartość frontmattera; adresy robi klikalnymi, resztę tylko escape'uje."""
    escaped = html.escape(value, quote=False)
    if _URLISH_RE.match(value.strip()):
        href = value.strip()
        if "://" not in href:
            href = "https://" + href
        return f'<a href="{html.escape(href, quote=True)}" target="_blank" rel="noopener" class="ext">{escaped}</a>'
    if value.strip().startswith("mailto:") or "@" in value and " " not in value.strip():
        return f'<a href="mailto:{html.escape(value.strip(), quote=True)}">{escaped}</a>'
    return escaped


def render_page(concept: Concept, pages: dict[str, str]) -> str:
    body = rewrite_links(concept.body, concept, pages)
    rendered = md_to_html(body)

    # Pierwszy nagłówek H1 body dubluje tytuł karty — awansujemy go na <h1>
    # strony zamiast dokładać drugi. Sam `title` i tak jest w tabelce metadanych.
    match = re.match(r"\s*<h1>(.*?)</h1>", rendered, re.S)
    if match:
        headline = match.group(1)
        rendered = rendered[match.end() :]
    else:
        headline = html.escape(concept.title)

    frontmatter = concept.frontmatter
    chip = html.escape(str(frontmatter.get("type") or "—"))
    description = str(frontmatter.get("description") or "")
    lead = f'<p class="lead">{html.escape(description)}</p>' if description else ""

    content = (
        f'<span class="chip">{chip}</span>\n'
        f"<h1>{headline}</h1>\n{lead}\n"
        f"{_meta_table(frontmatter)}\n{rendered}"
    )
    return _page_shell(concept.title, concept.id.count("/"), content)


_INDEX_HEADING_RE = re.compile(r"^#\s+(.+)$", re.M)


def group_heading(dirname: str) -> str:
    """Nagłówek grupy = pierwszy nagłówek `index.md` katalogu (§8).

    Indexy podkatalogów same nazywają swoją zawartość, więc karta zbiorcza
    nie musi mieć zaszytej listy katalogów — dorzucenie nowego regionu do
    bundle'a wystarczy, żeby pojawił się tu z własną nazwą.
    """
    index = BUNDLE_ROOT / dirname / "index.md"
    if index.is_file():
        match = _INDEX_HEADING_RE.search(index.read_text(encoding="utf-8"))
        if match:
            return match.group(1).strip()
    return dirname


def render_index(concepts: list[Concept]) -> str:
    """Karta zbiorcza: koncepty z korzenia, potem grupa na katalog najwyższego
    poziomu. Każdy koncept bundle'a ląduje w dokładnie jednej grupie."""
    by_dir: dict[str, list[Concept]] = {}
    for concept in concepts:
        if "/" in concept.id:
            by_dir.setdefault(concept.id.split("/", 1)[0], []).append(concept)

    groups: list[tuple[str, list[Concept]]] = [
        ("Wyjazd i wiedza ogólna", [c for c in concepts if "/" not in c.id])
    ]
    for dirname in sorted(by_dir):
        # region.md przed oferty/* — płycej w drzewie znaczy ogólniej.
        items = sorted(by_dir[dirname], key=lambda c: (c.id.count("/"), c.id))
        groups.append((group_heading(dirname), items))
    sections = []
    for heading, items in groups:
        if not items:
            continue
        cards = []
        for concept in items:
            description = str(concept.frontmatter.get("description") or "")
            status = concept.frontmatter.get("status_ceny")
            badge = (
                f'<span class="chip">{html.escape(str(status).split("—")[0].strip())}</span> '
                if status
                else ""
            )
            cards.append(
                f'<li><a href="{html.escape(concept.page, quote=True)}">'
                f"{html.escape(concept.title)}</a> "
                f'{badge}<span class="chip">{html.escape(str(concept.frontmatter.get("type") or "—"))}</span>'
                f"<p>{html.escape(description)}</p></li>"
            )
        sections.append(f"<h2>{heading}</h2>\n<ul class=\"cards\">{''.join(cards)}</ul>")

    content = (
        f"<h1>{html.escape(BUNDLE_NAME)}</h1>\n"
        '<p class="lead">Karty konceptów bundle\'a — pełna treść każdego dokumentu '
        "(ceny, dostępność, plusy/minusy). Struktura powiązań: "
        '<a href="../viz.html">graf</a>.</p>\n' + "\n".join(sections)
    )
    return _page_shell("Karty", 0, content)


# --- raport braków ----------------------------------------------------


def missing_data(concepts: list[Concept]) -> list[tuple[str, list[str]]]:
    """Czego brakuje w ofertach — bez zgadywania, tylko z tego, co jest."""
    report = []
    for concept in concepts:
        if not str(concept.frontmatter.get("type", "")).startswith("oferta"):
            continue
        gaps = []
        status = str(concept.frontmatter.get("status_ceny") or "")
        if not status:
            gaps.append("brak pola `status_ceny`")
        elif "SZACUNEK" in status.upper():
            gaps.append(f"cena niepotwierdzona ({status})")
        # Danymi o dostępności jest osobna sekcja (jak w glemm-lodge), a nie
        # samo słowo w tekście — "duża dostępność" w opisie się nie liczy.
        if not re.search(r"^#+\s*.*dostępnoś", concept.body, re.IGNORECASE | re.M):
            gaps.append("brak danych o dostępności terminu 16–23.01.2027")
        open_todos = len(re.findall(r"^\s*[-*]\s+\[ \]", concept.body, re.M))
        if open_todos:
            gaps.append(f"otwartych pozycji „Do zrobienia”: {open_todos}")
        if gaps:
            report.append((concept.id, gaps))
    return report


# --- main -------------------------------------------------------------


def main() -> int:
    concepts = load_concepts()
    pages = {c.id: c.page for c in concepts}

    if PAGES_DIR.exists():
        shutil.rmtree(PAGES_DIR)
    PAGES_DIR.mkdir(parents=True)

    written = []
    for concept in concepts:
        out = PAGES_DIR / concept.page
        out.parent.mkdir(parents=True, exist_ok=True)
        out.write_text(render_page(concept, pages), encoding="utf-8")
        written.append(out)

    index = PAGES_DIR / "index.html"
    index.write_text(render_index(concepts), encoding="utf-8")
    written.append(index)

    print(f"Renderer markdown: {RENDERER}")
    print(f"Zapisano {len(written)} plików w {PAGES_DIR}:")
    for path in written:
        size = path.stat().st_size / 1024
        print(f"  {path.relative_to(BUNDLE_ROOT)}  ({size:.1f} KiB)")

    gaps = missing_data(concepts)
    print()
    if gaps:
        print(f"Oferty z brakami w danych ({len(gaps)}) — do uzupełnienia ręcznie:")
        for concept_id, items in gaps:
            print(f"  ! {concept_id}")
            for item in items:
                print(f"      – {item}")
    else:
        print("Braków w danych ofert nie wykryto.")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())