[chore/bugfix] Deinterface text.Formatter, allow underscores in hashtags (#2233)

internal/text/util.go

@@ -0,0 +1,51 @@
+// GoToSocial
+// Copyright (C) GoToSocial Authors admin@gotosocial.org
+// SPDX-License-Identifier: AGPL-3.0-or-later
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package text
+
+import "unicode"
+
+func isPlausiblyInHashtag(r rune) bool {
+	// Marks are allowed during parsing
+	// prior to normalization, but not after,
+	// since they may be combined into letters
+	// during normalization.
+	return unicode.IsMark(r) ||
+		isPermittedInHashtag(r)
+}
+
+func isPermittedInHashtag(r rune) bool {
+	return unicode.IsLetter(r) ||
+		unicode.IsNumber(r) ||
+		r == '_'
+}
+
+// isHashtagBoundary returns true if rune r
+// is a recognized break character for before
+// or after a #hashtag.
+func isHashtagBoundary(r rune) bool {
+	return unicode.IsSpace(r) ||
+		(unicode.IsPunct(r) && r != '_')
+}
+
+// isMentionBoundary returns true if rune r
+// is a recognized break character for before
+// or after a @mention.
+func isMentionBoundary(r rune) bool {
+	return unicode.IsSpace(r) ||
+		unicode.IsPunct(r)
+}