From 2796a2e82f16ade9872008878cf88299bd66b4e7 Mon Sep 17 00:00:00 2001
From: tobi <31960611+tsmethurst@users.noreply.github.com>
Date: Mon, 31 Jul 2023 15:47:35 +0200
Subject: [feature] Hashtag federation (in/out), hashtag client API endpoints
 (#2032)

* update go-fed

* do the things

* remove unused columns from tags

* update to latest lingo from main

* further tag shenanigans

* serve stub page at tag endpoint

* we did it lads

* tests, oh tests, ohhh tests, oh tests (doo doo doo doo)

* swagger docs

* document hashtag usage + federation

* instanceGet

* don't bother parsing tag href

* rename whereStartsWith -> whereStartsLike

* remove GetOrCreateTag

* dont cache status tag timelineability
---
 internal/text/normalize.go | 60 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 internal/text/normalize.go

(limited to 'internal/text/normalize.go')

diff --git a/internal/text/normalize.go b/internal/text/normalize.go
new file mode 100644
index 000000000..14caf6311
--- /dev/null
+++ b/internal/text/normalize.go
@@ -0,0 +1,60 @@
+// 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 (
+	"strings"
+
+	"github.com/superseriousbusiness/gotosocial/internal/util"
+	"golang.org/x/text/unicode/norm"
+)
+
+const (
+	maximumHashtagLength = 100
+)
+
+// NormalizeHashtag normalizes the given hashtag text by
+// removing the initial '#' symbol, and then decomposing
+// and canonically recomposing chars + combining diacritics
+// in the text to single unicode characters, following
+// Normalization Form C (https://unicode.org/reports/tr15/).
+//
+// Finally, it will do a check on the normalized string to
+// ensure that it's below maximumHashtagLength chars, and
+// contains only unicode letters and numbers. If this passes,
+// returned bool will be true.
+func NormalizeHashtag(text string) (string, bool) {
+	// This normalization is specifically to avoid cases
+	// where visually-identical hashtags are stored with
+	// different unicode representations (e.g. with combining
+	// diacritics). It allows a tasteful number of combining
+	// diacritics to be used, as long as they can be combined
+	// with parent characters to form regular letter symbols.
+	normalized := norm.NFC.String(strings.TrimPrefix(text, "#"))
+
+	// Validate normalized.
+	ok := true
+	for i, r := range normalized {
+		if i >= maximumHashtagLength || !util.IsPermittedInHashtag(r) {
+			ok = false
+			break
+		}
+	}
+
+	return normalized, ok
+}
-- 
cgit v1.2.3