From 18fa4b29cd78742dbee90606a7e2397bb6d42354 Mon Sep 17 00:00:00 2001
From: laubonghaudoi <laubonghaudoi@icloud.com>
Date: Tue, 15 Feb 2022 14:04:43 -0500
Subject: [PATCH] fix: add sentence validator for Cantonese (#605)

---
 server/lib/validation/index.js         |  2 ++
 server/lib/validation/languages/yue.js | 34 ++++++++++++++++++++++++++
 2 files changed, 36 insertions(+)
 create mode 100644 server/lib/validation/languages/yue.js

diff --git a/server/lib/validation/index.js b/server/lib/validation/index.js
index d2157581..ddadfbd8 100644
--- a/server/lib/validation/index.js
+++ b/server/lib/validation/index.js
@@ -12,6 +12,7 @@ const ru = require('./languages/ru');
 const th = require('./languages/th');
 const ur = require('./languages/ur');
 const uz = require('./languages/uz');
+const yue = require('./languages/yue');
 
 const VALIDATORS = {
   bas,
@@ -27,6 +28,7 @@ const VALIDATORS = {
   th,
   ur,
   uz,
+  yue,
 };
 
 module.exports = {
diff --git a/server/lib/validation/languages/yue.js b/server/lib/validation/languages/yue.js
new file mode 100644
index 00000000..617d325d
--- /dev/null
+++ b/server/lib/validation/languages/yue.js
@@ -0,0 +1,34 @@
+// Minimum of characters that qualify as a sentence.
+const MIN_LENGTH = 3;
+
+// Maximum of characters allowed per sentence to keep recordings in a manageable duration.
+const MAX_LENGTH = 50;
+
+const INVALIDATIONS = [{
+  fn: (sentence) => {
+    return sentence.length < MIN_LENGTH || sentence.length > MAX_LENGTH;
+  },
+  error: `字數必須要喺 ${MIN_LENGTH} 同  ${MAX_LENGTH} 之間`,
+}, {
+  regex: /[0-9]+/,
+  error: "句子唔可以包含阿拉伯數字",
+}, {
+  regex: /[<>+*#@%^[\]()/]/,
+  error: "句子唔可以有特殊符號",
+}, {
+  // 7 or more repeating characters in a row is likely a non-formal spelling or difficult to read.
+  regex: /(.)\1{6}/,
+  error: "唔可以有連續 7 個或以上重複字元",
+}, {
+  // Emoji range from https://www.regextester.com/106421 and
+  // https://stackoverflow.com/questions/10992921/how-to-remove-emoji-code-using-javascript
+  regex: /(\u00a9|\u00ae|[\u2000-\u3300]|[\u2580-\u27bf]|\ud83c[\ud000-\udfff]|\ud83d[\ud000-\udfff]|\ud83e[\ud000-\udfff]|[\ue000-\uf8ff])/,
+  error: "句子唔可以含有 emoji 或者其他特殊 Unicode 符號",
+}, {
+  regex: /[\u5427\u5504\u5436](\s|\u3002|\u002E|\uFF0C|\u002C|$)/,
+  error: '句子唔可以有官話語氣詞（例如吧、唄、吶）',
+}];
+
+module.exports = {
+  INVALIDATIONS,
+};