khosra/internal/ext/notation/notation_test.go

package notation

import (
	"bytes"
	"strings"
	"testing"

	"github.com/yuin/goldmark"
)

func html(t *testing.T, markdown string) string {
	t.Helper()
	md := goldmark.New(goldmark.WithExtensions(New()))
	var out bytes.Buffer
	if err := md.Convert([]byte(markdown), &out); err != nil {
		t.Fatal(err)
	}
	return out.String()
}

func TestEachMarkBecomesItsElement(t *testing.T) {
	for _, c := range []struct{ in, want string }{
		{"H~2~O", "H<sub>2</sub>O"},
		{"10^6^ of them", "10<sup>6</sup> of them"},
		{"==marked==", "<mark>marked</mark>"},
		{"~~struck~~", "<del>struck</del>"},
		// Nested and adjacent marks are ordinary inline text, so emphasis still works around them.
		{"*a ~1~ b*", "<em>a <sub>1</sub> b</em>"},
		{"CO~2~ and H~2~O", "CO<sub>2</sub> and H<sub>2</sub>O"},
	} {
		if got := html(t, c.in); !strings.Contains(got, c.want) {
			t.Errorf("%q rendered %s, want it to contain %q", c.in, strings.TrimSpace(got), c.want)
		}
	}
}

// The reason this package owns the tilde. goldmark's own strikethrough treats one tilde as a strike, which
// turns a chemical formula into struck text — measured on the real binary before ADR-0061.
func TestOneTildeIsSubscriptAndTwoIsStrikethrough(t *testing.T) {
	got := html(t, "H~2~O is not ~~struck~~")
	if !strings.Contains(got, "H<sub>2</sub>O") {
		t.Errorf("a single tilde must subscript, not strike:\n%s", got)
	}
	if !strings.Contains(got, "<del>struck</del>") {
		t.Errorf("a double tilde must still strike:\n%s", got)
	}
	if strings.Contains(got, "<del>2</del>") {
		t.Errorf("the formula was struck instead of subscripted:\n%s", got)
	}
}

// Prose is full of these bytes. An unpaired or meaningless run has to stay exactly as typed.
func TestProseKeepsItsPunctuation(t *testing.T) {
	for _, c := range []struct{ in, keep string }{
		{"a = b and c == d", "=="},       // `==` needs no space to open; `c == d` has one either side
		{"x^2 + y^2 = z^2", "x^2 + y^2"}, // unpaired carets
		{"the range 10~20 is wide", "10~20"},
		{"a ~ b", "~"},
	} {
		got := html(t, c.in)
		if !strings.Contains(got, c.keep) {
			t.Errorf("%q lost its punctuation: %s", c.in, strings.TrimSpace(got))
		}
		for _, tag := range []string{"<sub>", "<sup>", "<mark>", "<del>"} {
			if strings.Contains(got, tag) {
				t.Errorf("%q produced %s: %s", c.in, tag, strings.TrimSpace(got))
			}
		}
	}
}

// A run length the table has no meaning for must not match at a shorter one.
func TestAnUndefinedRunLengthDoesNotMatch(t *testing.T) {
	if got := html(t, "=marked="); strings.Contains(got, "<mark>") {
		t.Errorf("a single = is not a highlight: %s", strings.TrimSpace(got))
	}
	if got := html(t, "^^up^^"); strings.Contains(got, "<sup>") {
		t.Errorf("a double ^ is not a superscript: %s", strings.TrimSpace(got))
	}
}

// Code spans are the author's literal text, whatever bytes are in them.
func TestCodeSpansAreUntouched(t *testing.T) {
	got := html(t, "`H~2~O` and `a==b`")
	if strings.Contains(got, "<sub>") || strings.Contains(got, "<mark>") {
		t.Errorf("a code span must survive verbatim:\n%s", got)
	}
}

func TestAbbreviationsExpandWhereverTheyAppear(t *testing.T) {
	got := html(t, "The HTML spec.\n\n*[HTML]: HyperText Markup Language\n\nHTML again.\n")
	if n := strings.Count(got, `<abbr title="HyperText Markup Language">HTML</abbr>`); n != 2 {
		t.Errorf("both uses should expand, got %d:\n%s", n, got)
	}
	// A definition may follow the use it explains, which is why this is a transformer and not a parser.
	if strings.Contains(got, "*[HTML]") || strings.Contains(got, "HyperText Markup Language<") {
		t.Errorf("the definition line is a note to the parser, not content:\n%s", got)
	}
}

func TestAnAbbreviationIsAWholeWord(t *testing.T) {
	got := html(t, "HTML and HTMLish and xHTML.\n\n*[HTML]: HyperText Markup Language\n")
	if strings.Count(got, "<abbr") != 1 {
		t.Errorf("only the standalone use should expand:\n%s", got)
	}
	for _, keep := range []string{"HTMLish", "xHTML"} {
		if !strings.Contains(got, keep) {
			t.Errorf("%q should survive untouched:\n%s", keep, got)
		}
	}
}

func TestTheLongestDefinitionWins(t *testing.T) {
	got := html(t, "HTML5 and HTML.\n\n*[HTML]: Markup\n*[HTML5]: The fifth one\n")
	if !strings.Contains(got, `<abbr title="The fifth one">HTML5</abbr>`) {
		t.Errorf("HTML5 should not be shadowed by HTML:\n%s", got)
	}
	if !strings.Contains(got, `<abbr title="Markup">HTML</abbr>`) {
		t.Errorf("the shorter term should still expand on its own:\n%s", got)
	}
}

func TestCodeAndUrlsAreNotExpanded(t *testing.T) {
	got := html(t, "Use `HTML` here and <https://HTML.example/> there, but HTML in prose.\n\n*[HTML]: Markup\n")
	if strings.Count(got, "<abbr") != 1 {
		t.Errorf("only the prose use should expand:\n%s", got)
	}
	if !strings.Contains(got, "<code>HTML</code>") {
		t.Errorf("a code span is literal text:\n%s", got)
	}
}

func TestAnExpansionCannotBreakItsAttribute(t *testing.T) {
	got := html(t, `Term T here.`+"\n\n"+`*[T]: a "quoted" thing`+"\n")
	if strings.Contains(got, `title="a "quoted" thing"`) {
		t.Errorf("the attribute was broken by the expansion:\n%s", got)
	}
	if !strings.Contains(got, "&quot;quoted&quot;") {
		t.Errorf("the expansion should be escaped into the attribute:\n%s", got)
	}
}

// A list item starts with an asterisk too, so the definition form must not eat one.
func TestAListItemIsNotADefinition(t *testing.T) {
	got := html(t, "* [a link](/x/): still a list\n")
	if !strings.Contains(got, "<li>") {
		t.Errorf("a list item must survive:\n%s", got)
	}
}