99efa02edf
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>
33 lines
1,005 B
Go
33 lines
1,005 B
Go
// 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 (
|
|
"sort"
|
|
"testing"
|
|
"unicode"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
)
|
|
|
|
func TestAmbiguousCharacters(t *testing.T) {
|
|
for locale, ambiguous := range AmbiguousCharacters {
|
|
assert.Equal(t, locale, ambiguous.Locale)
|
|
assert.Equal(t, len(ambiguous.Confusable), len(ambiguous.With))
|
|
assert.True(t, sort.SliceIsSorted(ambiguous.Confusable, func(i, j int) bool {
|
|
return ambiguous.Confusable[i] < ambiguous.Confusable[j]
|
|
}))
|
|
|
|
for _, confusable := range ambiguous.Confusable {
|
|
assert.True(t, unicode.Is(ambiguous.RangeTable, confusable))
|
|
i := sort.Search(len(ambiguous.Confusable), func(j int) bool {
|
|
return ambiguous.Confusable[j] >= confusable
|
|
})
|
|
found := i < len(ambiguous.Confusable) && ambiguous.Confusable[i] == confusable
|
|
assert.True(t, found, "%c is not in %d", confusable, i)
|
|
}
|
|
}
|
|
}
|