khosra/internal/ext/notation/notation.go

package notation

import (
	"github.com/yuin/goldmark"
	"github.com/yuin/goldmark/ast"
	"github.com/yuin/goldmark/parser"
	"github.com/yuin/goldmark/renderer"
	"github.com/yuin/goldmark/text"
	"github.com/yuin/goldmark/util"
)

// mark is one delimiter byte and what a single or doubled run of it means around some text.
//
// The tilde carries both, and that is the whole reason this package exists: goldmark's own strikethrough
// claims a single tilde as well as a double, which silently turns `H~2~O` into `H<del>2</del>O`. Owning the
// byte here is what lets subscript and strikethrough coexist (ADR-0061).
var marks = []mark{
	{char: '~', single: "sub", double: "del"},
	{char: '^', single: "sup"},
	{char: '=', double: "mark"},
}

// A single run is scanned to its closing byte and may not cross whitespace; a doubled run goes through
// goldmark's delimiter machinery and may. The split is not a preference: `x^2 + y^2 = z^2` pairs its carets
// across the whole expression under delimiter rules, which is prose silently becoming markup. Pandoc draws
// the same line, and it is why a subscript holds a formula rather than a phrase.
type mark struct {
	char           byte
	single, double string
}

// New returns the Markdown extension.
func New() goldmark.Extender { return extension{} }

type extension struct{}

// Extend registers one inline parser per mark, and the single renderer they share.
//
// Priority 500 is goldmark's own for delimiter-run inlines, so these resolve alongside emphasis rather than
// ahead of it: a mark is ordinary inline text, not a construct that outranks the language.
func (extension) Extend(md goldmark.Markdown) {
	inline := make([]util.PrioritizedValue, 0, len(marks))
	for _, m := range marks {
		inline = append(inline, util.Prioritized(inlineParser{m}, 500))
	}
	md.Parser().AddOptions(
		parser.WithInlineParsers(inline...),
		// Above the paragraph parser, so a definition line stops being content (ADR-0062).
		parser.WithBlockParsers(util.Prioritized(definitionParser{}, 99)),
		parser.WithASTTransformers(util.Prioritized(expand{}, 200)),
	)
	md.Renderer().AddOptions(renderer.WithNodeRenderers(util.Prioritized(nodeRenderer{}, 500)))
}

// kind identifies a parsed mark in the tree.
var kind = ast.NewNodeKind("Notation")

// node is one matched pair, carrying the element it becomes and nothing else.
type node struct {
	ast.BaseInline
	tag string
}

func (n *node) Kind() ast.NodeKind { return kind }

func (n *node) Dump(source []byte, level int) { ast.DumpHelper(n, source, level, nil, nil) }

// processor pairs doubled runs. A run of one is refused here, so `=marked=` stays prose and the single-run
// meaning — where a mark has one — is decided by the scan instead.
type processor struct{ tag string }

func (p processor) IsDelimiter(b byte) bool { return b == '~' || b == '=' }

func (p processor) CanOpenCloser(opener, closer *parser.Delimiter) bool {
	return opener.Char == closer.Char && opener.Length >= 2 && closer.Length >= 2
}

func (p processor) OnMatch(consumes int) ast.Node { return &node{tag: p.tag} }

// inlineParser handles one byte, both of its meanings.
type inlineParser struct{ m mark }

func (p inlineParser) Trigger() []byte { return []byte{p.m.char} }

func (p inlineParser) Parse(parent ast.Node, block text.Reader, pc parser.Context) ast.Node {
	line, segment := block.PeekLine()
	if len(line) > 1 && line[1] == p.m.char {
		return p.doubled(block, line, segment, pc)
	}
	return p.single(block, line, segment)
}

// doubled pushes a delimiter run, so the pair may hold spaces and nested markup: `~~a *b*~~`.
func (p inlineParser) doubled(block text.Reader, line []byte, segment text.Segment, pc parser.Context) ast.Node {
	if p.m.double == "" {
		return nil
	}
	before := block.PrecendingCharacter()
	d := parser.ScanDelimiter(line, before, 2, processor{p.m.double})
	if d == nil {
		return nil
	}
	d.Segment = segment.WithStop(segment.Start + d.OriginalLength)
	block.Advance(d.OriginalLength)
	pc.PushDelimiter(d)
	return d
}

// single scans to the closing byte on this line, refusing to cross whitespace.
//
// The content is taken as text rather than parsed for markup: a span that cannot hold a space has no room
// for emphasis either, and scanning is what keeps `x^2 + y^2` out of the parser's hands.
func (p inlineParser) single(block text.Reader, line []byte, segment text.Segment) ast.Node {
	// A run of the byte is not a single mark, so `^^up^^` stays prose rather than matching the pair inside
	// it. goldmark's own strikethrough guards the same way.
	if p.m.single == "" || block.PrecendingCharacter() == rune(p.m.char) {
		return nil
	}
	end := 0
	for i := 1; i < len(line); i++ {
		if line[i] == p.m.char {
			end = i
			break
		}
		if util.IsSpace(line[i]) {
			return nil
		}
	}
	if end < 2 {
		return nil
	}
	inner := segment
	inner.Start, inner.Stop = segment.Start+1, segment.Start+end
	n := &node{tag: p.m.single}
	n.AppendChild(n, ast.NewTextSegment(inner))
	block.Advance(end + 1)
	return n
}

// nodeRenderer writes the element a matched pair became. The tag is one of a fixed set in `marks`, never
// anything an author supplied, so it is written directly.
type nodeRenderer struct{}

func (r nodeRenderer) RegisterFuncs(reg renderer.NodeRendererFuncRegisterer) {
	reg.Register(kind, render)
	r.registerAbbr(reg)
}

func render(w util.BufWriter, source []byte, n ast.Node, entering bool) (ast.WalkStatus, error) {
	tag := n.(*node).tag
	if entering {
		_, _ = w.WriteString("<" + tag + ">")
	} else {
		_, _ = w.WriteString("</" + tag + ">")
	}
	return ast.WalkContinue, nil
}