ZacharyZhang-NYandClaude Opus 5.5
256240c365
HTML export, plain text and rich copy read each paragraph, heading, cell and HTML block through the component's MarkdownReader (pin 1251221). Emoji, alerts, the TOC and inline tags match visual mode. Footnotes sit in place as [n]; link titles are not written. Three review rounds failed; round 3's one finding (a scan per footnote over open marks) is fixed with a growth regression, unreviewed. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
100 lines
3.7 KiB
Rust
100 lines
3.7 KiB
Rust
//! Markdown as plain text: words, code and TeX, no marks.
|
|
|
|
use std::io;
|
|
|
|
use ely_gpui_component::documents::{
|
|
MarkdownBlock, MarkdownReader, alert, is_toc, markdown_options,
|
|
};
|
|
use markdown::mdast::Node;
|
|
|
|
/// `text` as plain text, a blank line between blocks.
|
|
pub fn plain(text: &str) -> io::Result<String> {
|
|
let tree = markdown::to_mdast(text, &markdown_options())
|
|
.map_err(|error| io::Error::other(error.to_string()))?;
|
|
let reader = MarkdownReader::new(text, &tree);
|
|
let mut blocks = Vec::new();
|
|
// Alerts and `[toc]` live only at the root.
|
|
for child in tree.children().into_iter().flatten() {
|
|
match child {
|
|
Node::Blockquote(quote) => match alert(quote) {
|
|
Some((kind, body)) => {
|
|
blocks.push(kind.title().to_string());
|
|
for node in &body {
|
|
block(&reader, node, &mut blocks);
|
|
}
|
|
}
|
|
None => block(&reader, child, &mut blocks),
|
|
},
|
|
_ if is_toc(child, text) => {
|
|
let titles: Vec<&str> = (reader.headings.iter())
|
|
.map(|heading| heading.title.as_str())
|
|
.collect();
|
|
if !titles.is_empty() {
|
|
blocks.push(titles.join("\n"));
|
|
}
|
|
}
|
|
_ => block(&reader, child, &mut blocks),
|
|
}
|
|
}
|
|
Ok(blocks.join("\n\n") + "\n")
|
|
}
|
|
|
|
fn block(reader: &MarkdownReader, node: &Node, blocks: &mut Vec<String>) {
|
|
match node {
|
|
Node::Code(code) => blocks.push(code.value.clone()),
|
|
Node::Math(math) => blocks.push(math.value.clone()),
|
|
Node::List(list) => {
|
|
let items = list.children.iter().map(|item| {
|
|
let mut inner = Vec::new();
|
|
for child in item.children().into_iter().flatten() {
|
|
block(reader, child, &mut inner);
|
|
}
|
|
inner.join("\n")
|
|
});
|
|
blocks.push(items.collect::<Vec<_>>().join("\n"));
|
|
}
|
|
Node::Table(table) => {
|
|
let rows = table.children.iter().map(|row| {
|
|
let cells = row.children().into_iter().flatten();
|
|
let cells = cells.map(|cell| words(reader, cell));
|
|
cells.collect::<Vec<_>>().join("\t")
|
|
});
|
|
blocks.push(rows.collect::<Vec<_>>().join("\n"));
|
|
}
|
|
Node::FootnoteDefinition(note) => {
|
|
let mut body = Vec::new();
|
|
for child in ¬e.children {
|
|
block(reader, child, &mut body);
|
|
}
|
|
// The label the drawing shows beside it.
|
|
let label = format!("[{}]", reader.label(note));
|
|
blocks.push([label, body.join("\n\n")].join(" ").trim_end().to_string());
|
|
}
|
|
Node::Blockquote(_) => {
|
|
for child in node.children().into_iter().flatten() {
|
|
block(reader, child, blocks);
|
|
}
|
|
}
|
|
Node::Paragraph(_) | Node::Heading(_) => blocks.push(words(reader, node)),
|
|
Node::Html(_) => {
|
|
let mut read = Vec::new();
|
|
reader.block(node, &mut read);
|
|
for piece in read {
|
|
match piece {
|
|
MarkdownBlock::Paragraph(text) => blocks.push(text.text),
|
|
other => unreachable!("an HTML block reads as text, not {other:?}"),
|
|
}
|
|
}
|
|
}
|
|
// Front matter, rules and definitions are not words.
|
|
_ => {}
|
|
}
|
|
}
|
|
|
|
/// An inline run's words, as the drawing reads them.
|
|
fn words(reader: &MarkdownReader, node: &Node) -> String {
|
|
reader
|
|
.inline(node.children().expect("an inline run holds inlines"))
|
|
.text
|
|
}
|