bench-forgejo/modules/charset/ambiguous.go
zeripath a08584ee36
Ensure that Chinese punctuation is not ambiguous when locale is Chinese (#22019)
Although there are per-locale fallbacks for ambiguity the locale names
for Chinese do not quite match our locales. This PR simply maps zh-CN on
to zh-hans and other zh variants on to zh-hant.

Ref #20999

Signed-off-by: Andrew Thornton <art27@cantab.net>
2022-12-04 17:57:30 +00:00

59 lines
1.4 KiB
Go

// This file is generated by modules/charset/ambiguous/generate.go DO NOT EDIT
// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package charset
import (
"sort"
"strings"
"unicode"
"code.gitea.io/gitea/modules/translation"
)
// AmbiguousTablesForLocale provides the table of ambiguous characters for this locale.
func AmbiguousTablesForLocale(locale translation.Locale) []*AmbiguousTable {
key := locale.Language()
var table *AmbiguousTable
var ok bool
for len(key) > 0 {
if table, ok = AmbiguousCharacters[key]; ok {
break
}
idx := strings.LastIndexAny(key, "-_")
if idx < 0 {
key = ""
} else {
key = key[:idx]
}
}
if table == nil && (locale.Language() == "zh-CN" || locale.Language() == "zh_CN") {
table = AmbiguousCharacters["zh-hans"]
}
if table == nil && strings.HasPrefix(locale.Language(), "zh") {
table = AmbiguousCharacters["zh-hant"]
}
if table == nil {
table = AmbiguousCharacters["_default"]
}
return []*AmbiguousTable{
table,
AmbiguousCharacters["_common"],
}
}
func isAmbiguous(r rune, confusableTo *rune, tables ...*AmbiguousTable) bool {
for _, table := range tables {
if !unicode.Is(table.RangeTable, r) {
continue
}
i := sort.Search(len(table.Confusable), func(i int) bool {
return table.Confusable[i] >= r
})
(*confusableTo) = table.With[i]
return true
}
return false
}