From c64943eb7dbcf7e0d03654f20c1dc2ec3849dd4c Mon Sep 17 00:00:00 2001
From: Dnomd343 <i@343.re>
Date: Tue, 13 Dec 2022 16:21:33 +0800
Subject: [PATCH] feat: traditional chinese convert demo

---
 src/chinese/convert.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100755 src/chinese/convert.py

diff --git a/src/chinese/convert.py b/src/chinese/convert.py
new file mode 100755
index 0000000..bd0b296
--- /dev/null
+++ b/src/chinese/convert.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+from snownlp import SnowNLP
+
+
+def traditionalCheck(sentence: str) -> None:
+    simplified = SnowNLP(sentence).han  # convert into simplified chinese
+    if simplified == sentence:  # simplified chinese already
+        return
+    sentence = list(sentence)
+    simplified = list(simplified)
+    for i in range(0, min(len(sentence), len(simplified))):  # traverse each character
+        if sentence[i] != simplified[i]:  # found different character
+            sentence[i] = '\033[0;33m%s\033[0;39m' % sentence[i]  # set colorful flag
+            simplified[i] = '\033[0;32m%s\033[0;39m' % simplified[i]
+    print('%s\n> %s\n> %s\n%s' % (
+        '-' * 128, ''.join(sentence), ''.join(simplified), '-' * 128
+    ))
+
+
+traditionalCheck('繁體中文的叫法在臺灣亦很常見')
+