From 6c573c2d477cf3d45ed8629402c429a2352bca6b Mon Sep 17 00:00:00 2001
From: syimyuzya <syimyuzya@gmail.com>
Date: Thu, 26 Dec 2024 21:32:10 +0800
Subject: [PATCH] =?UTF-8?q?Check=20=E5=8F=8D=E5=88=87=20&=20=E9=87=8B?=
 =?UTF-8?q?=E7=BE=A9?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 check.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/check.py b/check.py
index facdb91..e678842 100644
--- a/check.py
+++ b/check.py
@@ -9,6 +9,12 @@
 PATTERN_描述 = re.compile(
     f'([{所有母}])([開合])?([{所有等}])([ABC])?([{所有韻}])([{所有聲}])'
 )
+PATTERN_反切 = re.compile(
+    r"""(?x)(
+        \[.\] |  # 脫字
+        . ( <.> | ⦉.⦊ | \(.\) | ⦅.⦆ )*  # 原貌及校正
+    ){2}"""
+)
 
 
 def contains_ascii(s: str):
@@ -35,12 +41,16 @@ def contains_ascii(s: str):
                 釋義,
                 釋義補充,
             ) = line.rstrip('\n').split(',')
+
             assert (
                 PATTERN_描述.fullmatch(音韻地位描述) is not None
             ), f'invalid 音韻地位: {音韻地位描述}'
-            # TODO 反切
+
+            if 反切:
+                assert PATTERN_反切.fullmatch(反切) is not None, f'invalid 反切: {反切}'
             assert len(字頭) == 1, 'The length of 字頭 should be 1'
+
+            assert 釋義 + 釋義補充, '釋義 and 釋義補充 should not be both empty'
             assert not contains_ascii(
                 釋義
             ), '釋義 should not contain any ASCII characters'
-            # TODO 釋義 should not be empty