internal/frontend: limit heading ids to ASCII characters

It seems like bluemonday intended to only allow ascii IDs. Limit the heading ids produced to ASCII characters to keep with what we think the intended behavior is. Change-Id: Ifa9aaad5fcc5308d9efcaa75fafb65547839fde2 Reviewed-on: https://go-review.googlesource.com/c/pkgsite/+/544356 LUCI-TryBot-Result: Go LUCI <[email protected]> kokoro-CI: kokoro <[email protected]> Reviewed-by: Jonathan Amsterdam <[email protected]>
golang · Nov 30, 2023 · 044caf5 · 044caf5
1 parent e743b59
commit 044caf5
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 3 deletions.
diff --git a/internal/frontend/goldmark.go b/internal/frontend/goldmark.go
@@ -12,7 +12,6 @@ import (
 	"fmt"
 	"regexp"
 	"strings"
-	"unicode"
 
 	"github.com/yuin/goldmark/ast"
 	"github.com/yuin/goldmark/parser"
@@ -180,7 +179,7 @@ func newIDs() parser.IDs {
 }
 
 // Generate turns heading content from a markdown document into a heading id.
-// First HTML markup and markdown images are stripped then unicode letters
+// First HTML markup and markdown images are stripped then ASCII letters
 // and numbers are used to generate the final result. Finally, all heading ids
 // are prefixed with "readme-" to avoid name collisions with other ids on the
 // unit page. Duplicated heading ids are given an incremental suffix. See
@@ -190,7 +189,7 @@ func (s *ids) Generate(value []byte, kind ast.NodeKind) []byte {
 	r := regexp.MustCompile(`(<[^<>]+>|\[\!\[[^\]]+]\([^\)]+\)\]\([^\)]+\))`)
 	str := r.ReplaceAllString(string(value), "")
 	f := func(c rune) bool {
-		return !unicode.IsLetter(c) && !unicode.IsNumber(c)
+		return !('a' <= c && c <= 'z') && !('A' <= c && c <= 'Z') && !('0' <= c && c <= '9')
 	}
 	str = strings.Join(strings.FieldsFunc(str, f), "-")
 	str = strings.ToLower(str)

diff --git a/internal/frontend/readme_test.go b/internal/frontend/readme_test.go
@@ -144,6 +144,16 @@ func TestReadme(t *testing.T) {
 				{Level: 1, Text: "One", ID: "readme-one-1"},
 			},
 		},
+		{
+			name: "Non-ASCII Heading",
+			unit: unit,
+			readme: &internal.Readme{
+				Filepath: sample.ReadmeFilePath,
+				Contents: "# 中文¹",
+			},
+			wantHTML:    "<h3 class=\"h1\" id=\"readme-heading\">中文¹</h3>",
+			wantOutline: []*Heading{{Level: 1, Text: "中文¹", ID: "readme-heading"}},
+		},
 		{
 			name: "Github markdown emoji markup is properly rendered",
 			unit: unit,