catcrafts.net/shared/interfaces/Catcrafts.Shared-Markdown.cppm

/*
catcrafts.net
Copyright (C) 2026 Catcrafts

The source code of this website is made available for viewing purposes only.
No permission is granted to copy, modify, distribute, or create derivative works.
*/

// A deliberately small Markdown renderer, for fediverse post bodies only.
//
// The site used to have no markdown pipeline at all, on the grounds that the
// posts page only ever showed a 280-character preview and the body stayed on
// the instance. Hosting the full body changes that calculation: a post IS
// prose with headings, quotes, code blocks and screenshots, and rendering it
// as one flat paragraph of literal `**asterisks**` would be worse than not
// hosting it. So: a parser, but only as much of one as these bodies use.
//
// WHAT IT SUPPORTS — everything observed in the real bodies, and nothing else:
//
//   blocks   ATX headings, fenced code, blockquotes (nested), ordered and
//            unordered lists, thematic breaks, paragraphs
//   inline   links, images, code spans, ** strong **, * emphasis *, and bare
//            URLs via Html::Autolink
//
// WHAT IT DELIBERATELY DOES NOT SUPPORT:
//
//   * Raw HTML. Never. A post body is text fetched from someone else's server,
//     so the ONE thing this renderer must guarantee is that no byte of it can
//     become markup. Every character of body text leaves here through
//     Html::Escape or Html::Autolink, and the only SafeHtml built from a raw
//     string is the fixed structural markup written in this file. That is why
//     `<` in a body renders as a less-than sign rather than opening a tag.
//   * Underscore emphasis. `_` is common inside identifiers that appear in
//     these posts unquoted (kworker/u16:8-qc_ufs_qos_swq), and mangling half a
//     symbol name into italics is a worse failure than not italicising a word
//     that used the underscore form. Asterisks are unambiguous here.
//   * Setext headings, reference links, tables, footnotes, HTML entities.
//     None appear; adding them speculatively is parser surface with no reader.
//   * Trailing-double-space hard breaks. An invisible two-character difference
//     is not something a reader can see in the source or a writer can rely on
//     having typed; the lines of a paragraph join with a space, and a break
//     that was meant is written as a blank line.
//
// Anything unrecognised degrades to text rather than being dropped, so a
// construct this parser does not know shows up as visibly odd prose instead of
// silently vanishing from the page.

export module Catcrafts.Shared:Markdown;
import std;
import :Html;
import :Media;
import :Model;

namespace Catcrafts::Markdown {

using Html::SafeHtml;
using Html::Escape;
using Html::Autolink;
using Html::Attr;
using Html::Format;
using Html::Join;
using Html::Raw;
using Html::Url;

// Blockquotes recurse, and a body is untrusted input, so the recursion needs a
// bound that does not depend on the input being sane. Four is past anything
// these posts do (a quote inside a list item inside a quote) and far short of
// anything that could trouble the stack.
constexpr int kMaxDepth = 4;

// ── small string helpers ──────────────────────────────────────────────

bool IsSpace(char c) { return c == ' ' || c == '\t'; }

std::string_view TrimRight(std::string_view s) {
    while (!s.empty() && (IsSpace(s.back()) || s.back() == '\r')) s.remove_suffix(1);
    return s;
}

std::string_view TrimLeft(std::string_view s) {
    while (!s.empty() && IsSpace(s.front())) s.remove_prefix(1);
    return s;
}

std::string_view Trim(std::string_view s) { return TrimLeft(TrimRight(s)); }

bool Blank(std::string_view line) { return Trim(line).empty(); }

// Up to three leading spaces are indentation a block marker is still allowed
// to carry; four or more would be a code block in real Markdown, which these
// bodies never use (they fence instead).
std::string_view Undent(std::string_view line) {
    std::size_t n = 0;
    while (n < line.size() && n < 3 && line[n] == ' ') ++n;
    return line.substr(n);
}

// ── media ─────────────────────────────────────────────────────────────

// One embedded file, in the same shape (and CSS) the posts page uses for a
// post's headline media — an inline screenshot and a post's headline recording
// are the same kind of thing to a reader, so they should not look like two
// different components. :Media is what guarantees that: both go through it.
//
// A src with no mirrored record (its download failed, so the body still points
// at the original URL) still renders, just without dimensions or format tiers.
SafeHtml MediaTag(std::string_view src, std::string_view alt,
                  std::span<const PostMedia> media) {
    return Media::Tag(Media::Describe(media, src), alt);
}

// ── inline ────────────────────────────────────────────────────────────

SafeHtml RenderInline(std::string_view text, std::span<const PostMedia> media, int depth);

// The span between `open` and its matching close delimiter, honouring nesting,
// or npos when it never closes. Used for [link text] and (link target), both of
// which can legitimately contain their own brackets — the Fairphone manual link
// in one of these posts has a parenthesised sentence as its text.
std::size_t MatchingDelimiter(std::string_view s, std::size_t from, char open, char close) {
    int depth = 0;
    for (std::size_t i = from; i < s.size(); ++i) {
        if (s[i] == '\\') { ++i; continue; }
        if (s[i] == open) { ++depth; continue; }
        if (s[i] == close) {
            if (depth == 0) return i;
            --depth;
        }
    }
    return std::string_view::npos;
}

// A run of ordinary prose, escaped and with bare URLs linked.
//
// Autolink rather than Escape because these bodies paste addresses constantly —
// mailing-list archives, merge requests, the shop — as bare text with no
// Markdown link syntax around them. Rendering those inert would strip most of
// the outbound value out of the post. Autolink escapes everything itself and
// puts each address through Html::Url, so this adds no new trusted path.
SafeHtml PlainRun(std::string_view text) {
    return text.empty() ? SafeHtml{} : Autolink(text);
}

// True when the delimiter at `i` opens (rather than closes) an emphasis run:
// it must be followed by something that is not whitespace. Combined with the
// closing test below this is what keeps a lone asterisk — a multiplication
// sign, a footnote marker, a shell glob — from swallowing the rest of a
// paragraph into italics.
bool OpensEmphasis(std::string_view s, std::size_t after) {
    return after < s.size() && !IsSpace(s[after]) && s[after] != '\n';
}

// The closing delimiter for an emphasis run opened at `from`, or npos. The
// character before it must not be whitespace, so "a * b * c" stays literal.
std::size_t FindEmphasisClose(std::string_view s, std::size_t from, std::string_view delim) {
    std::size_t i = from;
    while (i < s.size()) {
        const std::size_t at = s.find(delim, i);
        if (at == std::string_view::npos) return std::string_view::npos;
        if (at > from && !IsSpace(s[at - 1])) return at;
        i = at + delim.size();
    }
    return std::string_view::npos;
}

SafeHtml RenderInline(std::string_view text, std::span<const PostMedia> media, int depth) {
    std::vector<SafeHtml> out;
    std::size_t run = 0;   // start of the pending plain-text run

    auto flush = [&](std::size_t upto) {
        if (upto > run) out.push_back(PlainRun(text.substr(run, upto - run)));
    };

    std::size_t i = 0;
    while (i < text.size()) {
        const char c = text[i];

        // A backslash escape hides the next character from this parser. The
        // pair is emitted as the second character alone, which is what lets a
        // post write a literal asterisk.
        if (c == '\\' && i + 1 < text.size()) {
            flush(i);
            out.push_back(Escape(text.substr(i + 1, 1)));
            i += 2;
            run = i;
            continue;
        }

        // `code` — highest precedence, so an asterisk inside a code span is a
        // literal asterisk and not an emphasis delimiter.
        if (c == '`') {
            const std::size_t close = text.find('`', i + 1);
            if (close != std::string_view::npos) {
                flush(i);
                out.push_back(Format(R"(<code>{}</code>)",
                                     Escape(text.substr(i + 1, close - i - 1))));
                i = close + 1;
                run = i;
                continue;
            }
        }

        // ![alt](src) — an image. Checked before the link case, since the
        // bracket that follows would otherwise parse as one.
        if (c == '!' && i + 1 < text.size() && text[i + 1] == '[' && depth < kMaxDepth) {
            const std::size_t altEnd = MatchingDelimiter(text, i + 2, '[', ']');
            if (altEnd != std::string_view::npos && altEnd + 1 < text.size()
                && text[altEnd + 1] == '(') {
                const std::size_t srcEnd = MatchingDelimiter(text, altEnd + 2, '(', ')');
                if (srcEnd != std::string_view::npos) {
                    flush(i);
                    out.push_back(MediaTag(Trim(text.substr(altEnd + 2, srcEnd - altEnd - 2)),
                                           text.substr(i + 2, altEnd - i - 2),
                                           media));
                    i = srcEnd + 1;
                    run = i;
                    continue;
                }
            }
        }

        // [text](href)
        if (c == '[' && depth < kMaxDepth) {
            const std::size_t textEnd = MatchingDelimiter(text, i + 1, '[', ']');
            if (textEnd != std::string_view::npos && textEnd + 1 < text.size()
                && text[textEnd + 1] == '(') {
                const std::size_t hrefEnd = MatchingDelimiter(text, textEnd + 2, '(', ')');
                if (hrefEnd != std::string_view::npos) {
                    const std::string_view href =
                        Trim(text.substr(textEnd + 2, hrefEnd - textEnd - 2));
                    flush(i);
                    // The label is rendered rather than escaped flat, because
                    // these posts bold inside link text. Depth-guarded, so a
                    // link whose label contains a link cannot recurse forever.
                    out.push_back(Format(
                        R"(<a{} rel="noopener">{}</a>)",
                        Url("href", href),
                        RenderInline(text.substr(i + 1, textEnd - i - 1), media, depth + 1)));
                    i = hrefEnd + 1;
                    run = i;
                    continue;
                }
            }
        }

        // **strong** before *emphasis*: the longer delimiter has to win, or
        // every bold run parses as an empty italic followed by loose text.
        if (c == '*') {
            const bool doubled = i + 1 < text.size() && text[i + 1] == '*';
            const std::string_view delim = doubled ? "**" : "*";
            const std::size_t inner = i + delim.size();
            if (depth < kMaxDepth && OpensEmphasis(text, inner)) {
                const std::size_t close = FindEmphasisClose(text, inner, delim);
                if (close != std::string_view::npos) {
                    flush(i);
                    const SafeHtml body =
                        RenderInline(text.substr(inner, close - inner), media, depth + 1);
                    out.push_back(doubled ? Format(R"(<strong>{}</strong>)", body)
                                          : Format(R"(<em>{}</em>)", body));
                    i = close + delim.size();
                    run = i;
                    continue;
                }
            }
        }

        ++i;
    }

    flush(text.size());
    return Join(out);
}

// ── blocks ────────────────────────────────────────────────────────────

// A line's leading run of '#', when it is an ATX heading marker.
// Returns 0 when the line is not a heading.
int HeadingLevel(std::string_view line) {
    std::size_t n = 0;
    while (n < line.size() && line[n] == '#') ++n;
    if (n == 0 || n > 6) return 0;
    // "#tag" is not a heading; a marker has to be followed by space or be the
    // whole line.
    if (n < line.size() && !IsSpace(line[n])) return 0;
    return static_cast<int>(n);
}

bool IsFence(std::string_view line) { return TrimLeft(line).starts_with("```"); }

// `---`, `***`, `___`: three or more of one character, nothing else but spaces.
bool IsThematicBreak(std::string_view line) {
    const std::string_view s = Trim(line);
    if (s.size() < 3) return false;
    const char c = s.front();
    if (c != '-' && c != '*' && c != '_') return false;
    int count = 0;
    for (const char ch : s) {
        if (ch == c) { ++count; continue; }
        if (!IsSpace(ch)) return false;
    }
    return count >= 3;
}

struct ListMarker {
    bool ok = false;
    bool ordered = false;
    std::int64_t start = 1;      // the number an ordered item announced
    std::size_t contentAt = 0;   // offset of the item's text within the line
};

ListMarker ParseListMarker(std::string_view line) {
    ListMarker m;
    const std::string_view s = Undent(line);
    const std::size_t indent = line.size() - s.size();
    if (s.empty()) return m;

    if ((s[0] == '-' || s[0] == '*' || s[0] == '+') && s.size() > 1 && IsSpace(s[1])) {
        // A thematic break is also a run of dashes; it wins, because "- - -"
        // is a rule everywhere and a three-item list nowhere.
        if (IsThematicBreak(line)) return m;
        m.ok = true;
        m.contentAt = indent + 2;
        return m;
    }

    std::size_t n = 0;
    while (n < s.size() && s[n] >= '0' && s[n] <= '9') ++n;
    // Bounded so a line starting with a long number is not mistaken for a list.
    if (n == 0 || n > 9) return m;
    if (n + 1 >= s.size() || (s[n] != '.' && s[n] != ')') || !IsSpace(s[n + 1])) return m;

    std::int64_t value = 0;
    std::from_chars(s.data(), s.data() + n, value);
    m.ok = true;
    m.ordered = true;
    m.start = value;
    m.contentAt = indent + n + 2;
    return m;
}

bool StartsBlock(std::string_view line) {
    return HeadingLevel(Undent(line)) > 0 || IsFence(line) || IsThematicBreak(line)
        || Undent(line).starts_with('>') || ParseListMarker(line).ok;
}

SafeHtml RenderBlocks(std::span<const std::string_view> lines,
                      std::span<const PostMedia> media, int depth);

// A paragraph's lines, joined and rendered.
//
// A paragraph whose entire content is embedded files becomes the same
// .post-media block the cards use rather than a <p> of images: that is what
// gives a run of screenshots the two-up grid instead of a column of full-width
// pictures with paragraph spacing between them.
SafeHtml RenderParagraph(std::span<const std::string_view> lines,
                         std::span<const PostMedia> media, int depth) {
    // Lines join with a space: a body wraps its prose at whatever width the
    // author's editor used, and those wraps are not meaningful.
    std::string joined;
    for (std::size_t i = 0; i < lines.size(); ++i) {
        joined += Trim(lines[i]);
        if (i + 1 < lines.size()) joined += ' ';
    }

    // Only-images test: strip every ![](...) span and see whether anything but
    // whitespace is left.
    bool onlyMedia = false;
    {
        std::string rest;
        std::size_t i = 0;
        std::size_t found = 0;
        const std::string_view s = joined;
        while (i < s.size()) {
            if (s[i] == '!' && i + 1 < s.size() && s[i + 1] == '[') {
                const std::size_t altEnd = MatchingDelimiter(s, i + 2, '[', ']');
                if (altEnd != std::string_view::npos && altEnd + 1 < s.size()
                    && s[altEnd + 1] == '(') {
                    const std::size_t srcEnd = MatchingDelimiter(s, altEnd + 2, '(', ')');
                    if (srcEnd != std::string_view::npos) {
                        ++found;
                        i = srcEnd + 1;
                        continue;
                    }
                }
            }
            rest += s[i];
            ++i;
        }
        onlyMedia = found > 0 && Trim(rest).empty();
    }

    const SafeHtml inner = RenderInline(joined, media, depth);
    if (inner.Empty()) return SafeHtml{};
    if (onlyMedia) return Format(R"(<div class="post-media">{}</div>)", inner);
    return Format(R"(<p>{}</p>)", inner);
}

SafeHtml RenderBlocks(std::span<const std::string_view> lines,
                      std::span<const PostMedia> media, int depth) {
    std::vector<SafeHtml> out;
    std::size_t i = 0;

    while (i < lines.size()) {
        if (Blank(lines[i])) { ++i; continue; }

        const std::string_view line = lines[i];
        const std::string_view body = Undent(line);

        // ── fenced code ───────────────────────────────────────────────
        //
        // Taken verbatim and escaped: the battery-measurement tables and the
        // android top output in these posts are the one place where every
        // space matters and nothing inside should be interpreted at all.
        if (IsFence(line)) {
            std::size_t j = i + 1;
            std::string code;
            while (j < lines.size() && !IsFence(lines[j])) {
                code += TrimRight(lines[j]);
                code += '\n';
                ++j;
            }
            out.push_back(Format(R"(<pre class="post-body__code"><code>{}</code></pre>)",
                                 Escape(code)));
            // Past the closing fence, or to the end when it never closed —
            // an unterminated fence renders as code rather than swallowing
            // the rest of the post into a parse failure.
            i = (j < lines.size()) ? j + 1 : j;
            continue;
        }

        // ── heading ───────────────────────────────────────────────────
        //
        // Demoted by one: the page's <h1> is the post title, so a body's own
        // top-level heading is a section inside it. Without the shift every
        // post would carry two h1s and the document outline would be wrong on
        // exactly the pages this whole change exists to make indexable.
        if (const int level = HeadingLevel(body); level > 0) {
            std::string_view textPart = body.substr(static_cast<std::size_t>(level));
            // A closing run of #s is decoration, not content.
            textPart = TrimRight(textPart);
            while (!textPart.empty() && textPart.back() == '#') textPart.remove_suffix(1);
            const int tag = std::min(level + 1, 6);
            out.push_back(Format("<h{}>{}</h{}>",
                                 Html::Num(tag),
                                 RenderInline(Trim(textPart), media, depth),
                                 Html::Num(tag)));
            ++i;
            continue;
        }

        if (IsThematicBreak(line)) {
            out.push_back(Raw("<hr>"));
            ++i;
            continue;
        }

        // ── blockquote ────────────────────────────────────────────────
        //
        // The quoted lines are re-parsed as blocks, so a quote keeps its own
        // paragraphs and headings — which matters here, because the longest
        // quotes in these posts are multi-paragraph company copy being taken
        // apart line by line.
        if (body.starts_with('>')) {
            std::vector<std::string_view> quoted;
            std::size_t j = i;
            while (j < lines.size() && Undent(lines[j]).starts_with('>')) {
                std::string_view q = Undent(lines[j]).substr(1);
                if (!q.empty() && q.front() == ' ') q.remove_prefix(1);
                quoted.push_back(q);
                ++j;
            }
            // At the depth limit the quote is still shown, just flattened —
            // dropping it would lose content, which is the worse failure.
            out.push_back(Format(
                R"(<blockquote class="post-body__quote">{}</blockquote>)",
                depth < kMaxDepth ? RenderBlocks(quoted, media, depth + 1)
                                  : RenderParagraph(quoted, media, depth)));
            i = j;
            continue;
        }

        // ── list ──────────────────────────────────────────────────────
        if (const ListMarker first = ParseListMarker(line); first.ok) {
            std::vector<SafeHtml> items;
            std::vector<std::string_view> current;
            std::size_t j = i;

            auto flushItem = [&] {
                if (current.empty()) return;
                items.push_back(Format(R"(<li>{}</li>)",
                                       RenderInline([&] {
                                           std::string joined;
                                           for (std::size_t k = 0; k < current.size(); ++k) {
                                               joined += Trim(current[k]);
                                               if (k + 1 < current.size()) joined += ' ';
                                           }
                                           return joined;
                                       }(), media, depth)));
                current.clear();
            };

            while (j < lines.size()) {
                if (Blank(lines[j])) {
                    // A blank line ends the list UNLESS the next non-blank line
                    // is another item of the same kind. These posts space their
                    // numbered steps apart, and treating that as seven separate
                    // one-item lists would restart the numbering at every gap.
                    std::size_t peek = j;
                    while (peek < lines.size() && Blank(lines[peek])) ++peek;
                    const ListMarker next =
                        peek < lines.size() ? ParseListMarker(lines[peek]) : ListMarker{};
                    if (!next.ok || next.ordered != first.ordered) break;
                    j = peek;
                    continue;
                }
                if (const ListMarker m = ParseListMarker(lines[j]); m.ok) {
                    if (m.ordered != first.ordered) break;
                    flushItem();
                    current.push_back(lines[j].substr(
                        std::min(m.contentAt, lines[j].size())));
                    ++j;
                    continue;
                }
                // A non-marker line that would start some other block ends the
                // list; anything else is this item's text continuing onto the
                // next line.
                if (StartsBlock(lines[j])) break;
                current.push_back(lines[j]);
                ++j;
            }
            flushItem();

            if (first.ordered) {
                // start= only when it is not 1, so the common case stays clean
                // markup — and so a list resumed after an interrupting
                // paragraph continues its numbering instead of starting over.
                out.push_back(Format(R"(<ol class="post-body__list"{}>{}</ol>)",
                                     first.start == 1 ? SafeHtml{}
                                                      : Attr("start", std::to_string(first.start)),
                                     Join(items)));
            } else {
                out.push_back(Format(R"(<ul class="post-body__list">{}</ul>)", Join(items)));
            }
            i = j;
            continue;
        }

        // ── paragraph ─────────────────────────────────────────────────
        {
            std::size_t j = i;
            while (j < lines.size() && !Blank(lines[j])) {
                // A block marker on a later line interrupts the paragraph
                // rather than being absorbed into it as text.
                if (j > i && StartsBlock(lines[j])) break;
                ++j;
            }
            out.push_back(RenderParagraph(lines.subspan(i, j - i), media, depth));
            i = j;
        }
    }

    return Join(out);
}

// ── entry point ───────────────────────────────────────────────────────

// Render a post body to the inner markup of the article element.
//
// `media` is the post's mirrored inline files, used to attach dimensions (and
// a poster, and the H.264 fallback) to whatever the body embeds. Passing an
// empty span is fine: the markup then simply carries no dimensions, exactly
// like a file whose mirror failed.
export SafeHtml Render(std::string_view text, std::span<const PostMedia> media = {}) {
    std::vector<std::string_view> lines;
    std::size_t start = 0;
    while (start <= text.size()) {
        const std::size_t nl = text.find('\n', start);
        if (nl == std::string_view::npos) {
            lines.push_back(text.substr(start));
            break;
        }
        lines.push_back(text.substr(start, nl - start));
        start = nl + 1;
    }
    return RenderBlocks(lines, media, 0);
}

} // namespace Catcrafts::Markdown