From f8723ed4d21f3276cb659dbaac164ee4d6a2e53a Mon Sep 17 00:00:00 2001
From: sinksank <1007286821@qq.com>
Date: Wed, 28 May 2025 12:28:08 +0800
Subject: [PATCH] =?UTF-8?q?=E7=AC=AC=E4=BA=8C=E6=AC=A1=E4=BF=AE=E6=94=B9?=
 =?UTF-8?q?=20vocabulary.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/vocabulary.py | 41 +++++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/app/vocabulary.py b/app/vocabulary.py
index 17e4386..0ef490c 100644
--- a/app/vocabulary.py
+++ b/app/vocabulary.py
@@ -6,25 +6,24 @@
    Hui, 2024-09-23
    Last upated: 2024-09-25, 2024-09-30
 '''
+import os
 import pickle
+import random
 import re
-
+from collections import defaultdict
+from datetime import datetime, timedelta
+import heapq
+import snowballstemmer
+from flask import session
+import enchant
 
 
 # word_lst = 词汇表
 
 def load_record(pickle_fname):
-    try:
-        with open(pickle_fname, 'rb') as f:
-            d = pickle.load(f)
-        return d
-    except FileNotFoundError:
-        print("未发现文件")
-    except pickle.UnpicklingError:
-        print("无法打开文件")
-    except Exception as e:
-        print("文件处理异常")
-    return None
+    with open(pickle_fname, 'rb') as f:
+        d = pickle.load(f)
+    return d
 
 
 
@@ -34,7 +33,7 @@ def is_english_word(word):
     if word == 'xyz':
         return False
     return bool(pattern.match(word))
-
+t
 def is_valid_datetime_string(date_string, format='%Y%m%d%H%M'):
     try:
         datetime.strptime(date_string, format)
@@ -44,7 +43,10 @@ def is_valid_datetime_string(date_string, format='%Y%m%d%H%M'):
 
 def remove_non_words(input_string):
     cleaned_string = re.sub(r'[^a-zA-Z\s]', '', input_string)
-    return cleaned_string.strip()
+    words = cleaned_string.split()
+    result = ' '.join(words)
+    return result
+
 
 
 class VocabularyLevelEstimator:
@@ -104,11 +106,8 @@ class UserVocabularyLevel(VocabularyLevelEstimator):
             return  # 如果词库为空，直接返回
 
         stemmer = snowballstemmer.stemmer('english')
-        #硬编码情况
         # date_str = "20240805"
-        # 实际时间
-        now = datetime.now()
-        date_str = now.strftime('%Y%m%d')
+        date_str = datetime.now().strftime('%Y%m%d')
         dt = datetime.strptime(date_str, "%Y%m%d")
         range_datetime = dt.strftime("%Y%m%d%H%M")  # 设定筛选时间范围
 
@@ -216,10 +215,8 @@ class ArticleVocabularyLevel(VocabularyLevelEstimator):
 
 
 if __name__ == '__main__':
-    now = datetime.now()
-    print(now.strftime("%Y%m%d"))
-# user = UserVocabularyLevel({})
-# print(user.level)
+    user = UserVocabularyLevel({})
+    print(user.level)
 #     _test = load_record('static/words_and_tests.p')
 #     print(_test)
 #