成语接龙

scripts/idiom_cli.py

@@ -0,0 +1,151 @@
+"""
+命令行交互脚本：根据用户输入的开头（1个汉字 / 2个汉字 / 单字拼音）
+从 data/idiom.json 中查找匹配成语，随机返回最多 5 条。
+
+该脚本不依赖第三方库，使用条目中的 `pinyin` 字段进行拼音匹配。
+"""
+
+import json
+import os
+import random
+import re
+import unicodedata
+
+ROOT = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+IDIOM_PATH = os.path.join(ROOT, "data", "idiom.json")
+
+
+def normalize_str(s):
+    if s is None:
+        return ""
+    if not isinstance(s, str):
+        s = str(s)
+    # NFKD 分解，再去掉重音符号
+    s = unicodedata.normalize('NFKD', s)
+    s = ''.join(ch for ch in s if not unicodedata.category(ch).startswith('M'))
+    # 去掉非字母/汉字/空格的字符
+    s = re.sub(r'[^0-9A-Za-z\u4e00-\u9fff\s]', '', s)
+    return s.strip()
+
+
+def extract_pinyin_tokens(raw_pinyin):
+    """把原始 pinyin 字段规范化并按空白分词，返回 token 列表（小写，去掉数字/声调符号）"""
+    if not raw_pinyin:
+        return []
+    s = normalize_str(raw_pinyin)
+    s = re.sub(r'\d', '', s)
+    tokens = [t.lower() for t in re.split(r'\s+', s) if t]
+    return tokens
+
+
+def load_idioms(path):
+    if not os.path.exists(path):
+        print(f"找不到文件: {path}")
+        return []
+    try:
+        with open(path, 'r', encoding='utf-8') as f:
+            data = json.load(f)
+    except Exception as e:
+        print(f"读取 JSON 出错: {e}")
+        return []
+
+    items = []
+    if isinstance(data, list):
+        for entry in data:
+            if isinstance(entry, str):
+                items.append({'word': entry, 'pinyin': None})
+            elif isinstance(entry, dict):
+                word = None
+                for key in ('word', 'idiom', 'name', 'chengyu', 'text'):
+                    if key in entry and isinstance(entry[key], str):
+                        word = entry[key]
+                        break
+                if not word:
+                    for v in entry.values():
+                        if isinstance(v, str):
+                            word = v
+                            break
+                pinyin = None
+                for key in entry.keys():
+                    if 'pin' in key.lower() or key.lower() in ('py', 'pinyin'):
+                        val = entry.get(key)
+                        if isinstance(val, str) and val.strip():
+                            pinyin = val
+                            break
+                items.append({'word': word or '', 'pinyin': pinyin})
+    elif isinstance(data, dict):
+        for k, v in data.items():
+            word = k
+            pinyin = None
+            if isinstance(v, str):
+                pinyin = v
+            elif isinstance(v, dict):
+                for key in v.keys():
+                    if 'pin' in key.lower() or key.lower() in ('py', 'pinyin'):
+                        val = v.get(key)
+                        if isinstance(val, str) and val.strip():
+                            pinyin = val
+                            break
+            items.append({'word': word, 'pinyin': pinyin})
+
+    items = [it for it in items if it.get('word')]
+    return items
+
+
+def is_ascii_letters(s):
+    return bool(re.fullmatch(r'[A-Za-z]+', s))
+
+
+def find_matches(items, q):
+    q = q.strip()
+    if not q:
+        return []
+
+    q_norm = normalize_str(q).lower()
+
+    if is_ascii_letters(q_norm):
+        matches = []
+        for it in items:
+            p = it.get('pinyin')
+            if not p:
+                continue
+            tokens = extract_pinyin_tokens(p)
+            if not tokens:
+                continue
+            first = tokens[0]
+            if first == q_norm:
+                matches.append(it['word'])
+        return matches
+
+    matches = [it['word'] for it in items if it['word'].startswith(q)]
+    return matches
+
+
+def main():
+    items = load_idioms(IDIOM_PATH)
+    if not items:
+        print("未从 data/idiom.json 中读取到可用成语（请确认文件存在且条目内包含成语文本）")
+        return
+
+    try:
+        while True:
+            q = input('请输入开头（1汉字/2汉字 或 单字拼音），回车退出: ').strip()
+            if q == '':
+                print('退出。')
+                break
+            matches = find_matches(items, q)
+            if not matches:
+                print('未找到匹配的成语。')
+            else:
+                count = min(5, len(matches))
+                sample = random.sample(matches, count)
+                print(f'共找到 {len(matches)} 条，随机返回 {len(sample)} 条：')
+                for i, w in enumerate(sample, 1):
+                    print(f'{i}. {w}')
+            print()
+    except (KeyboardInterrupt, EOFError):
+        print('\n退出。')
+
+
+if __name__ == '__main__':
+    main()