Bump goldmark 1.6.0 and go 1.21

.github/workflows/ci.yml

@@ -11,7 +11,7 @@ on:
     - master
 
 env:
-  GO_VERSION: "~1.20.5"
+  GO_VERSION: "~1.21.6"
 
 jobs:
   # Runs Golangci-lint on the source code

.github/workflows/goreleaser.yml

@@ -16,7 +16,7 @@ jobs:
     - name: Set Up Go
       uses: actions/setup-go@v5
       with:
-        go-version: "1.20"
+        go-version: "1.21"
     - name: Run GoReleaser
       uses: goreleaser/goreleaser-action@v5
       with:

go.mod

@@ -1,6 +1,8 @@
 module github.com/kovetskiy/mark
 
-go 1.19
+go 1.21
+
+toolchain go1.21.6
 
 require (
 	github.com/bmatcuk/doublestar/v4 v4.6.1
@@ -12,7 +14,7 @@ require (
 	github.com/reconquest/regexputil-go v0.0.0-20160905154124-38573e70c1f4
 	github.com/stretchr/testify v1.8.4
 	github.com/urfave/cli/v2 v2.27.1
-	github.com/yuin/goldmark v1.5.6
+	github.com/yuin/goldmark v1.6.0
 	golang.org/x/tools v0.17.0
 	gopkg.in/yaml.v3 v3.0.1
 )

go.sum

@@ -59,8 +59,8 @@ github.com/urfave/cli/v2 v2.27.1 h1:8xSQ6szndafKVRmfyeUMxkNUJQMjL1F2zmsZ+qHpfho=
 github.com/urfave/cli/v2 v2.27.1/go.mod h1:8qnjx1vcq5s2/wpsqoZFndg2CE5tNFyrTvS6SinrnYQ=
 github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 h1:bAn7/zixMGCfxrRTfdpNzjtPYqr8smhKouy9mxVdGPU=
 github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673/go.mod h1:N3UwUGtsrSj3ccvlPHLoLsHnpR27oXr4ZE984MbSER8=
-github.com/yuin/goldmark v1.5.6 h1:COmQAWTCcGetChm3Ig7G/t8AFAN00t+o8Mt4cf7JpwA=
+github.com/yuin/goldmark v1.6.0 h1:boZcn2GTjpsynOsC0iJHnBWa4Bi0qzfJjthwauItG68=
-github.com/yuin/goldmark v1.5.6/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
+github.com/yuin/goldmark v1.6.0/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 github.com/zazab/zhash v0.0.0-20210630080733-6e809466f8d3 h1:BhVaeQJc3xalHGONn215FylzuxdQBIT3d/aRjDg4nXQ=
 github.com/zazab/zhash v0.0.0-20210630080733-6e809466f8d3/go.mod h1:NtepZ8TEXErPsmQDMUoN72f8aIy4+xNinSJ3f1giess=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -72,5 +72,6 @@ gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15 h1:YR8cESwS4TdDjEe65xsg0ogRM/Nc3DYOhEAlW+xobZo=
 gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
+gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

pkg/mark/renderer/text.go

@@ -1,6 +1,7 @@
 package renderer
 
 import (
+	"unicode"
 	"unicode/utf8"
 
 	"github.com/yuin/goldmark/ast"
@@ -39,7 +40,7 @@ func (r *ConfluenceTextRenderer) RegisterFuncs(reg renderer.NodeRendererFuncRegi
 	reg.Register(ast.KindText, r.renderText)
 }
 
-// This is taken from https://github.com/yuin/goldmark/blob/v1.5.6/renderer/html/html.go#L648
+// This is taken from https://github.com/yuin/goldmark/blob/v1.6.0/renderer/html/html.go#L719
 // with the hardcoded '\n' for soft breaks swapped for the configurable r.softBreak
 func (r *ConfluenceTextRenderer) renderText(w util.BufWriter, source []byte, node ast.Node, entering bool) (ast.WalkStatus, error) {
 	if !entering {
@@ -59,14 +60,24 @@ func (r *ConfluenceTextRenderer) renderText(w util.BufWriter, source []byte, nod
 				_, _ = w.WriteString("<br>\n")
 			}
 		} else if n.SoftLineBreak() {
-			if r.EastAsianLineBreaks && len(value) != 0 {
+			if r.EastAsianLineBreaks != html.EastAsianLineBreaksNone && len(value) != 0 {
 				sibling := node.NextSibling()
 				if sibling != nil && sibling.Kind() == ast.KindText {
 					if siblingText := sibling.(*ast.Text).Text(source); len(siblingText) != 0 {
 						thisLastRune := util.ToRune(value, len(value)-1)
 						siblingFirstRune, _ := utf8.DecodeRune(siblingText)
-						if !(util.IsEastAsianWideRune(thisLastRune) &&
+						// Inline the softLineBreak function as it's not public
-							util.IsEastAsianWideRune(siblingFirstRune)) {
+						writeLineBreak := false
+						switch r.EastAsianLineBreaks {
+						case html.EastAsianLineBreaksNone:
+							writeLineBreak = false
+						case html.EastAsianLineBreaksSimple:
+							writeLineBreak = !(util.IsEastAsianWideRune(thisLastRune) && util.IsEastAsianWideRune(siblingFirstRune))
+						case html.EastAsianLineBreaksCSS3Draft:
+							writeLineBreak = eastAsianLineBreaksCSS3DraftSoftLineBreak(thisLastRune, siblingFirstRune)
+						}
+
+						if writeLineBreak {
 							_ = w.WriteByte(byte(r.softBreak))
 						}
 					}
@@ -78,3 +89,48 @@ func (r *ConfluenceTextRenderer) renderText(w util.BufWriter, source []byte, nod
 	}
 	return ast.WalkContinue, nil
 }
+
+func eastAsianLineBreaksCSS3DraftSoftLineBreak(thisLastRune rune, siblingFirstRune rune) bool {
+	// Implements CSS text level3 Segment Break Transformation Rules with some enhancements.
+	// References:
+	//   - https://www.w3.org/TR/2020/WD-css-text-3-20200429/#line-break-transform
+	//   - https://github.com/w3c/csswg-drafts/issues/5086
+
+	// Rule1:
+	//   If the character immediately before or immediately after the segment break is
+	//   the zero-width space character (U+200B), then the break is removed, leaving behind the zero-width space.
+	if thisLastRune == '\u200B' || siblingFirstRune == '\u200B' {
+		return false
+	}
+
+	// Rule2:
+	//   Otherwise, if the East Asian Width property of both the character before and after the segment break is
+	//   F, W, or H (not A), and neither side is Hangul, then the segment break is removed.
+	thisLastRuneEastAsianWidth := util.EastAsianWidth(thisLastRune)
+	siblingFirstRuneEastAsianWidth := util.EastAsianWidth(siblingFirstRune)
+	if (thisLastRuneEastAsianWidth == "F" ||
+		thisLastRuneEastAsianWidth == "W" ||
+		thisLastRuneEastAsianWidth == "H") &&
+		(siblingFirstRuneEastAsianWidth == "F" ||
+			siblingFirstRuneEastAsianWidth == "W" ||
+			siblingFirstRuneEastAsianWidth == "H") {
+		return unicode.Is(unicode.Hangul, thisLastRune) || unicode.Is(unicode.Hangul, siblingFirstRune)
+	}
+
+	// Rule3:
+	//   Otherwise, if either the character before or after the segment break belongs to
+	//   the space-discarding character set and it is a Unicode Punctuation (P*) or U+3000,
+	//   then the segment break is removed.
+	if util.IsSpaceDiscardingUnicodeRune(thisLastRune) ||
+		unicode.IsPunct(thisLastRune) ||
+		thisLastRune == '\u3000' ||
+		util.IsSpaceDiscardingUnicodeRune(siblingFirstRune) ||
+		unicode.IsPunct(siblingFirstRune) ||
+		siblingFirstRune == '\u3000' {
+		return false
+	}
+
+	// Rule4:
+	//   Otherwise, the segment break is converted to a space (U+0020).
+	return true
+}