documents: the drawing's reading rules are public, for exports to share

Shortcodes, inline_tag, html_block_text, alert, is_toc and headings are what
the drawing itself calls, so an export that calls them shows the same.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

src/documents/mod.rs

@@ -57,6 +57,10 @@ pub use templates::{Template, TemplatePicker};
 pub use thumbs::PageThumbnailList;
 pub use todo::{Checklist, TodoItem};
 pub use toolbar::FixedFormatToolbar;
+pub use tree::{
+    AlertKind, Inline, InlineTag, Shortcodes, Style, alert, headings, html_block_text, inline_tag,
+    is_toc,
+};
 pub(crate) use viewer::step as zoom_step;
 pub use viewer::{DocPage, DocumentViewer, PageHit, PageNote};
 

src/documents/tree/blocks.rs

@@ -1,7 +1,7 @@
 use markdown::mdast;
 
-use super::{Node, Reader, Run, html, text_block};
+use super::{Inline, Node, Reader, Run, html};
-use crate::documents::markdown::span;
+use crate::documents::markdown::{file_tree, span};
 
 /// A heading anywhere in the file.
 #[derive(Clone, Debug, PartialEq)]
@@ -58,9 +58,7 @@ impl Reader<'_> {
         if let Some(alert) = self.alert(node) {
             return out.push(alert);
         }
-        let toc = matches!(node, mdast::Node::Paragraph(_))
+        match is_toc(node, self.source) {
-            && self.source[span(node)].trim().eq_ignore_ascii_case("[toc]");
-        match toc {
             true => out.push(Node::Toc(self.headings.clone())),
             false => self.block(node, out),
         }
@@ -71,87 +69,74 @@ impl Reader<'_> {
         let mdast::Node::Blockquote(quote) = node else {
             return None;
         };
-        let [mdast::Node::Paragraph(paragraph), rest @ ..] = &quote.children[..] else {
+        let (kind, parts) = alert(quote)?;
-            return None;
-        };
-        let (kind, after) = marker(&paragraph.children)?;
-        if after.is_empty() && rest.is_empty() {
-            return None;
-        }
         let mut body = Vec::new();
-        if !after.is_empty() {
+        self.blocks(&parts, &mut body);
-            let kept = mdast::Paragraph {
-                children: after,
-                position: paragraph.position.clone(),
-            };
-            self.block(&mdast::Node::Paragraph(kept), &mut body);
-        }
-        self.blocks(rest, &mut body);
         Some(Node::Alert { kind, body })
     }
+}
 
-    /// An HTML block's text, as a browser shows it.
+/// An HTML block's text, as a browser shows it.
-    pub(super) fn html_block(&self, written: &str, out: &mut Vec<Node>) {
+pub fn html_block_text(written: &str) -> Inline {
-        let mut run = Run::default();
+    let mut run = Run::default();
-        let mut rest = written;
+    let mut rest = written;
-        while let Some(at) = rest.find('<') {
+    while let Some(at) = rest.find('<') {
-            run.words(&rest[..at]);
+        run.words(&rest[..at]);
-            rest = &rest[at..];
+        rest = &rest[at..];
-            if let Some(comment) = rest.strip_prefix("<!--") {
+        if let Some(comment) = rest.strip_prefix("<!--") {
-                rest = comment.split_once("-->").map_or("", |(_, after)| after);
+            rest = comment.split_once("-->").map_or("", |(_, after)| after);
-                run.shortcodes.split();
+            run.shortcodes.split();
-                continue;
+            continue;
-            }
+        }
-            let opens =
+        let opens =
-                rest[1..].starts_with(|ch: char| ch.is_ascii_alphabetic() || "/!?".contains(ch));
+            rest[1..].starts_with(|ch: char| ch.is_ascii_alphabetic() || "/!?".contains(ch));
-            if !opens {
+        if !opens {
-                run.words("<");
+            run.words("<");
-                rest = &rest[1..];
+            rest = &rest[1..];
-                continue;
+            continue;
-            }
+        }
-            // An unclosed tag drops the rest, as HTML5 does.
+        // An unclosed tag drops the rest, as HTML5 does.
-            let Some(end) = html::tag_end(rest) else {
+        let Some(end) = html::tag_end(rest) else {
-                rest = "";
+            rest = "";
-                break;
+            break;
-            };
+        };
-            let (written, after) = rest.split_at(end);
+        let (written, after) = rest.split_at(end);
-            rest = after;
+        rest = after;
-            match html::tag(written) {
+        match html::tag(written) {
-                Some(tag) if html::filtered(&tag.name) => run.words(written),
+            Some(tag) if html::filtered(&tag.name) => run.words(written),
-                // A block closes what opened inside it.
+            // A block closes what opened inside it.
-                Some(tag) if html::breaks(&tag.name) => {
+            Some(tag) if html::breaks(&tag.name) => {
-                    run.line();
+                run.line();
-                    match tag.closing {
+                match tag.closing {
-                        true => run.end(&tag.name),
+                    true => run.end(&tag.name),
-                        false => {
+                    false => {
-                            run.implied(&tag.name);
+                        run.implied(&tag.name);
-                            match tag.name == "hr" {
+                        match tag.name == "hr" {
-                                true => run.shortcodes.split(),
+                            true => run.shortcodes.split(),
-                                false => run.start(&tag.name, None, None),
+                            false => run.start(&tag.name, None, None),
-                            }
                         }
                     }
                 }
-                // It ends a `p` but lays no block.
-                Some(tag) if !tag.closing && html::closes_p(&tag.name) => {
-                    run.implied(&tag.name);
-                    run.html(written);
-                }
-                // A line's end drops its space.
-                Some(tag) if tag.closing || tag.name == "br" => {
-                    run.owed = run.owed.filter(|_| tag.name != "br");
-                    run.html(written);
-                }
-                Some(_) => {
-                    run.pay();
-                    run.html(written);
-                }
-                None => run.shortcodes.split(),
             }
+            // It ends a `p` but lays no block.
+            Some(tag) if !tag.closing && html::closes_p(&tag.name) => {
+                run.implied(&tag.name);
+                run.html(written);
+            }
+            // A line's end drops its space.
+            Some(tag) if tag.closing || tag.name == "br" => {
+                run.owed = run.owed.filter(|_| tag.name != "br");
+                run.html(written);
+            }
+            Some(_) => {
+                run.pay();
+                run.html(written);
+            }
+            None => run.shortcodes.split(),
         }
-        run.words(rest);
-        text_block(run.cut(), out);
     }
+    run.words(rest);
+    run.cut()
 }
 
 impl Run {
@@ -223,6 +208,35 @@ impl Run {
     }
 }
 
+/// A quote's alert kind and its blocks after the marker.
+pub fn alert(quote: &mdast::Blockquote) -> Option<(AlertKind, Vec<mdast::Node>)> {
+    let [mdast::Node::Paragraph(paragraph), rest @ ..] = &quote.children[..] else {
+        return None;
+    };
+    let (kind, after) = marker(&paragraph.children)?;
+    if after.is_empty() && rest.is_empty() {
+        return None;
+    }
+    let head = (!after.is_empty()).then(|| {
+        mdast::Node::Paragraph(mdast::Paragraph {
+            children: after,
+            position: paragraph.position.clone(),
+        })
+    });
+    Some((kind, head.into_iter().chain(rest.iter().cloned()).collect()))
+}
+
+/// A paragraph that is `[toc]` alone, as Typora reads it.
+pub fn is_toc(node: &mdast::Node, source: &str) -> bool {
+    matches!(node, mdast::Node::Paragraph(_))
+        && source[span(node)].trim().eq_ignore_ascii_case("[toc]")
+}
+
+/// Every heading in `text`, as `[toc]` lists them.
+pub fn headings(text: &str) -> Vec<DocumentHeading> {
+    Reader::new(text, &file_tree(text)).headings
+}
+
 /// A plain first line naming a kind, and what follows.
 fn marker(children: &[mdast::Node]) -> Option<(AlertKind, Vec<mdast::Node>)> {
     let mut line = String::new();

src/documents/tree/emoji.rs

@@ -49,7 +49,7 @@ fn candidate(text: &str) -> Option<usize> {
 
 /// One DOM text node's shortcodes, as GitHub reads them.
 #[derive(Default)]
-pub(crate) struct Shortcodes {
+pub struct Shortcodes {
     /// Settled by the node's first `:name:`.
     reads: Option<bool>,
     /// Text before it held more than white space.
@@ -59,12 +59,12 @@ pub(crate) struct Shortcodes {
 
 impl Shortcodes {
     /// A new DOM text node starts.
-    pub(crate) fn split(&mut self) {
+    pub fn split(&mut self) {
         *self = Self::default();
     }
 
     /// Blank or spaced text before the first reads them all.
-    pub(crate) fn read(&mut self, text: &str) -> String {
+    pub fn read(&mut self, text: &str) -> String {
         if self.reads.is_none() {
             let at = candidate(text);
             let lead = &text[..at.unwrap_or(text.len())];

src/documents/tree/html.rs

@@ -96,6 +96,52 @@ pub(crate) fn breaks(name: &str) -> bool {
     )
 }
 
+/// What one inline HTML tag does, as GitHub shows it.
+#[derive(Clone, Debug, PartialEq)]
+pub enum InlineTag {
+    /// Opens `name`; an anchor styles only with an address.
+    Open {
+        name: String,
+        style: Option<Style>,
+        href: Option<String>,
+    },
+    Close(String),
+    Break,
+    /// A filtered tag, shown as its text.
+    Text(String),
+    /// Gone; the text around it stays.
+    Gone,
+}
+
+/// What the inline HTML `written` does.
+pub fn inline_tag(written: &str) -> InlineTag {
+    let Some(tag) = tag(written) else {
+        return InlineTag::Gone;
+    };
+    if filtered(&tag.name) {
+        return InlineTag::Text(text(written));
+    }
+    if tag.name == "br" {
+        return InlineTag::Break;
+    }
+    let Some(style) = inline_style(&tag.name) else {
+        return InlineTag::Gone;
+    };
+    if tag.closing {
+        return InlineTag::Close(tag.name);
+    }
+    let href = match style {
+        Style::Link => tag.attribute("href").map(str::to_string),
+        _ => None,
+    };
+    let style = (style != Style::Link || href.is_some()).then_some(style);
+    InlineTag::Open {
+        name: tag.name,
+        style,
+        href,
+    }
+}
+
 /// Start tags that end an open `p`, as HTML5 lists them.
 pub(crate) fn closes_p(name: &str) -> bool {
     matches!(

src/documents/tree/mod.rs

@@ -8,7 +8,9 @@ mod blocks;
 mod emoji;
 mod html;
 
-pub use blocks::{AlertKind, DocumentHeading};
+pub use blocks::{AlertKind, DocumentHeading, alert, headings, html_block_text, is_toc};
+pub use emoji::Shortcodes;
+pub use html::{InlineTag, inline_tag};
 
 /// How a stretch of inline text prints.
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
@@ -156,28 +158,19 @@ impl Run {
 
     /// Opens or closes an element for an inline HTML tag.
     fn html(&mut self, written: &str) {
-        let Some(tag) = html::tag(written) else {
+        match html::inline_tag(written) {
-            return self.shortcodes.split();
+            InlineTag::Text(shown) => self.push_text(&shown),
-        };
+            InlineTag::Open { name, style, href } => self.start(&name, style, href),
-        if html::filtered(&tag.name) {
+            InlineTag::Close(name) => {
-            return self.push_text(&html::text(written));
+                self.shortcodes.split();
+                self.end(&name);
+            }
+            InlineTag::Break => {
+                self.shortcodes.split();
+                self.text.text.push('\n');
+            }
+            InlineTag::Gone => self.shortcodes.split(),
         }
-        self.shortcodes.split();
-        if tag.name == "br" {
-            return self.text.text.push('\n');
-        }
-        let Some(style) = html::inline_style(&tag.name) else {
-            return;
-        };
-        if tag.closing {
-            return self.end(&tag.name);
-        }
-        let url = match style {
-            Style::Link => tag.attribute("href").map(str::to_string),
-            _ => None,
-        };
-        let style = (style != Style::Link || url.is_some()).then_some(style);
-        self.start(&tag.name, style, url);
     }
 
     /// Opens `name`; a new `a` ends the open one.
@@ -366,7 +359,7 @@ impl<'a> Reader<'a> {
                 },
                 body: self.nested(&note.children),
             }),
-            mdast::Node::Html(html) => self.html_block(&html.value, out),
+            mdast::Node::Html(html) => text_block(html_block_text(&html.value), out),
             mdast::Node::Yaml(yaml) => out.push(Node::FrontMatter(yaml.value.clone())),
             mdast::Node::Toml(toml) => out.push(Node::FrontMatter(toml.value.clone())),
             mdast::Node::Definition(_) => {}