Skip single character & too long pages (closes #1 & felixonmars#2)

jactry · May 24, 2020 · d7384c0 · d7384c0
1 parent 16400de
commit d7384c0
Showing 1 changed file with 5 additions and 1 deletion.
diff --git a/convert.py b/convert.py
@@ -18,7 +18,11 @@
         if not HANZI_RE.match(line):
             continue
 
-        # Skip list page.
+        # Skip single character & too long pages
+        if not 1 < len(line) < 9:
+            continue
+
+        # Skip list pages
         if line.endswith('\u5217\u8868'):
             continue