Switch Unicode Escaping to a VSCode-like system (#19990)

This PR rewrites the invisible unicode detection algorithm to more
closely match that of the Monaco editor on the system. It provides a
technique for detecting ambiguous characters and relaxes the detection
of combining marks.

Control characters are in addition detected as invisible in this
implementation whereas they are not on monaco but this is related to
font issues.

Close #19913

Signed-off-by: Andrew Thornton <art27@cantab.net>

1 files changed, 69 insertions, 0 deletions

diff --git a/modules/charset/breakwriter_test.go b/modules/charset/breakwriter_test.go
new file mode 100644
index 0000000000..6bbed42ea5
--- /dev/null
+++ b/modules/charset/breakwriter_test.go
@@ -0,0 +1,69 @@
+// Copyright 2022 The Gitea Authors. All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package charset
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestBreakWriter_Write(t *testing.T) {
+	tests := []struct {
+		name    string
+		kase    string
+		expect  string
+		wantErr bool
+	}{
+		{
+			name:   "noline",
+			kase:   "abcdefghijklmnopqrstuvwxyz",
+			expect: "abcdefghijklmnopqrstuvwxyz",
+		},
+		{
+			name:   "endline",
+			kase:   "abcdefghijklmnopqrstuvwxyz\n",
+			expect: "abcdefghijklmnopqrstuvwxyz<br>",
+		},
+		{
+			name:   "startline",
+			kase:   "\nabcdefghijklmnopqrstuvwxyz",
+			expect: "<br>abcdefghijklmnopqrstuvwxyz",
+		},
+		{
+			name:   "onlyline",
+			kase:   "\n\n\n",
+			expect: "<br><br><br>",
+		},
+		{
+			name:   "empty",
+			kase:   "",
+			expect: "",
+		},
+		{
+			name:   "midline",
+			kase:   "\nabc\ndefghijkl\nmnopqrstuvwxy\nz",
+			expect: "<br>abc<br>defghijkl<br>mnopqrstuvwxy<br>z",
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			buf := &strings.Builder{}
+			b := &BreakWriter{
+				Writer: buf,
+			}
+			n, err := b.Write([]byte(tt.kase))
+			if (err != nil) != tt.wantErr {
+				t.Errorf("BreakWriter.Write() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if n != len(tt.kase) {
+				t.Errorf("BreakWriter.Write() = %v, want %v", n, len(tt.kase))
+			}
+			if buf.String() != tt.expect {
+				t.Errorf("BreakWriter.Write() wrote %q, want %v", buf.String(), tt.expect)
+			}
+		})
+	}
+}