From 19e5a0be4110fa973f4d9c3b497a5ea0187a073e Mon Sep 17 00:00:00 2001
From: xfy <i@rua.plus>
Date: Wed, 3 Jun 2026 10:25:38 +0800
Subject: [PATCH] fix(api): correct count_words for CJK characters

Chinese characters (U+4E00-U+9FFF) also return true for is_alphabetic(),
so they were being counted as part of English words instead of individually.
Fix: check CJK range before is_alphabetic().
---
 src/api/posts.rs | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/src/api/posts.rs b/src/api/posts.rs
index 31d8f74..644989f 100644
--- a/src/api/posts.rs
+++ b/src/api/posts.rs
@@ -418,15 +418,14 @@ fn count_words(md: &str) -> u32 {
     let mut in_word = false;
 
     for c in plain.chars() {
-        if c.is_alphabetic() {
+        if c as u32 >= 0x4E00 && c as u32 <= 0x9FFF {
+            count += 1;
+            in_word = false;
+        } else if c.is_alphabetic() {
             if !in_word {
                 count += 1;
                 in_word = true;
             }
-        } else if c as u32 >= 0x4E00 && c as u32 <= 0x9FFF {
-            // Chinese character
-            count += 1;
-            in_word = false;
         } else {
             in_word = false;
         }