itsybitsy/wap/src/xhtmlmp.rs

//! XHTML Mobile Profile markup, and the `text/html` body derived from it.
//!
//! One document serves both: a WAP 2.0 client needs well-formed XML with the
//! prolog and the Mobile Profile doctype, while a browser parsing the same bytes
//! as `text/html` tolerates the leading `<?xml ...?>` as a bogus comment but
//! logs a warning for it. So the HTML form is the same markup with that one line
//! removed.

use itsybitsy_core::ir::{Block, Doc, Inline};

use crate::escape;

/// The XML declaration, which only the XHTML-MP form carries.
const PROLOG: &str = "<?xml version=\"1.0\" encoding=\"utf-8\"?>\n";

const DOCTYPE: &str = "<!DOCTYPE html PUBLIC \"-//WAPFORUM//DTD XHTML Mobile 1.0//EN\" \
                       \"http://www.wapforum.org/DTD/xhtml-mobile10.dtd\">\n";

/// Build the whole document. `prolog` distinguishes the two media types.
pub fn document(doc: &Doc, title: &str, prolog: bool) -> String {
    let mut out = String::new();
    if prolog {
        out.push_str(PROLOG);
    }
    out.push_str(DOCTYPE);
    out.push_str("<html xmlns=\"http://www.w3.org/1999/xhtml\">\n");
    out.push_str(&format!("<head><title>{}</title></head>\n", escape::text(title)));
    out.push_str("<body>\n");
    blocks(&doc.blocks, &mut out);
    out.push_str("</body>\n</html>\n");
    out
}

fn blocks(blocks: &[Block], out: &mut String) {
    for block in blocks {
        self_block(block, out);
    }
}

fn self_block(block: &Block, out: &mut String) {
    match block {
        Block::Heading { level, inline } => {
            let level = (*level).clamp(1, 6);
            out.push_str(&format!("<h{level}>{}</h{level}>\n", inlines(inline)));
        }
        Block::Paragraph(inline) => out.push_str(&format!("<p>{}</p>\n", inlines(inline))),
        Block::CodeBlock { lines, .. } => {
            out.push_str("<pre>");
            out.push_str(&escape::text(&lines.join("\n")));
            out.push_str("</pre>\n");
        }
        Block::Art { alt, lines } => {
            // The label is the only description a client that cannot show the
            // art would have, so it is kept as the title attribute.
            out.push_str(&format!("<pre title=\"{}\">", escape::attr(alt)));
            out.push_str(&escape::text(&lines.join("\n")));
            out.push_str("</pre>\n");
        }
        Block::BlockQuote(inner) => {
            out.push_str("<blockquote>\n");
            blocks(inner, out);
            out.push_str("</blockquote>\n");
        }
        Block::List { ordered, start, items } => {
            if *ordered {
                // XHTML-MP has no `start` attribute, so a list beginning
                // elsewhere than 1 cannot be expressed; the numbers restart.
                out.push_str("<ol>\n");
            } else {
                out.push_str("<ul>\n");
            }
            let _ = start;
            for item in items {
                out.push_str("<li>");
                // A single paragraph needs no block wrapper inside the item.
                match item.as_slice() {
                    [Block::Paragraph(inline)] => out.push_str(&inlines(inline)),
                    blocks_in_item => {
                        out.push('\n');
                        blocks(blocks_in_item, out);
                    }
                }
                out.push_str("</li>\n");
            }
            out.push_str(if *ordered { "</ol>\n" } else { "</ul>\n" });
        }
        Block::Table { head, rows, .. } => {
            out.push_str("<table>\n");
            if !head.is_empty() {
                out.push_str("<tr>");
                for cell in head {
                    out.push_str(&format!("<th>{}</th>", inlines(cell)));
                }
                out.push_str("</tr>\n");
            }
            for row in rows {
                out.push_str("<tr>");
                for cell in row {
                    out.push_str(&format!("<td>{}</td>", inlines(cell)));
                }
                out.push_str("</tr>\n");
            }
            out.push_str("</table>\n");
        }
        Block::Rule => out.push_str("<hr/>\n"),
        // Raw HTML is passed through: this is the one family of formats where it
        // is already in the right language.
        Block::Html(html) => {
            out.push_str(html.trim_end());
            out.push('\n');
        }
        // Alignment reaches only the fixed-width text formats. Pagination is a
        // WML concern; a browser scrolls one document.
        Block::Aligned { block, .. } => self_block(block, out),
        // Gates are filtered out before rendering; keeping the content is the
        // harmless reading if one ever arrives here.
        Block::Gated { block, .. } => self_block(block, out),
        Block::CardBreak { .. } => {}
    }
}

fn inlines(inline: &[Inline]) -> String {
    let mut out = String::new();
    for item in inline {
        match item {
            Inline::Text(text) => out.push_str(&escape::text(text)),
            Inline::Code(code) => out.push_str(&format!("<code>{}</code>", escape::text(code))),
            Inline::Emph(inner) => out.push_str(&format!("<em>{}</em>", inlines(inner))),
            Inline::Strong(inner) => out.push_str(&format!("<strong>{}</strong>", inlines(inner))),
            // XHTML-MP 1.0 has no <del>, and <strike> is not in the profile, so
            // the text survives without its markup rather than being dropped.
            Inline::Strike(inner) => out.push_str(&inlines(inner)),
            Inline::Link { href, title, label } => {
                let title = title
                    .as_deref()
                    .map(|t| format!(" title=\"{}\"", escape::attr(t)))
                    .unwrap_or_default();
                out.push_str(&format!(
                    "<a href=\"{}\"{title}>{}</a>",
                    escape::attr(href),
                    inlines(label)
                ));
            }
            Inline::Image { src, title, alt } => {
                let title = title
                    .as_deref()
                    .map(|t| format!(" title=\"{}\"", escape::attr(t)))
                    .unwrap_or_default();
                out.push_str(&format!(
                    "<img src=\"{}\" alt=\"{}\"{title}/>",
                    escape::attr(src),
                    escape::attr(&Doc::plain_text(alt))
                ));
            }
            Inline::SoftBreak => out.push('\n'),
            Inline::HardBreak => out.push_str("<br/>\n"),
            Inline::Html(html) => out.push_str(html),
        }
    }
    out
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn the_prolog_is_present_only_when_asked_for() {
        let doc = Doc { blocks: Vec::new(), first_h1: None };
        assert!(document(&doc, "T", true).starts_with("<?xml"));
        assert!(document(&doc, "T", false).starts_with("<!DOCTYPE html"));
    }
}