002

脚本/count_zh.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+"""统计文本文件的中文字符数、总字符数、非空白字符数。"""
+import argparse
+import re
+from pathlib import Path
+
+
+def stats(text: str) -> dict:
+    return {
+        "chars": len(text),
+        "nonspace": len(re.sub(r"\s", "", text)),
+        "zh": len(re.findall(r"[\u4e00-\u9fff]", text)),
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Count Chinese characters in text files.")
+    parser.add_argument("paths", nargs="+", help="Files to count.")
+    args = parser.parse_args()
+
+    for path_str in args.paths:
+        path = Path(path_str)
+        text = path.read_text(encoding="utf-8")
+        s = stats(text)
+        print(f"{path}: 中文字符={s['zh']}, 总字符={s['chars']}, 非空白字符={s['nonspace']}")
+
+
+if __name__ == "__main__":
+    main()