From 541f78c7eabcaade6f6393ab584dd30f1f1b0833 Mon Sep 17 00:00:00 2001
From: PlutoCtx <chentingxian195467@163.com>
Date: Mon, 15 May 2023 09:58:32 +0800
Subject: [PATCH] =?UTF-8?q?=E8=AF=84=E5=AE=A1=E5=90=8E=E7=9A=84=E4=BF=AE?=
 =?UTF-8?q?=E6=94=B9=EF=BC=88words=5Fand=5Ftests.p=E6=96=87=E4=BB=B6?=
 =?UTF-8?q?=E6=B2=A1=E6=9C=89=E6=8F=90=E4=BA=A4=EF=BC=8C=E4=B8=BA=E9=98=B2?=
 =?UTF-8?q?=E6=AD=A2=E7=89=88=E6=9C=AC=E7=9A=84=E6=8E=A7=E5=88=B6=EF=BC=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/difficulty.py | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/app/difficulty.py b/app/difficulty.py
index 2570f77..3e6007b 100644
--- a/app/difficulty.py
+++ b/app/difficulty.py
@@ -37,26 +37,28 @@ def difficulty_level_from_frequency(word, d):
     return level
 
 
-def get_difficulty_level_for_words_and_tests(d_in):
+def get_difficulty_level_for_words_and_tests(d):
     """
     对原本的单词库中的单词进行难度评级
-    :param d_in: 存储了单词库pickle文件中的单词的字典
+    :param d: 存储了单词库pickle文件中的单词的字典
     :return:
     """
-    d = {}
-    L = list(d_in.keys())  # in dic, we have test types (e.g., CET4,CET6,BBC) for each word
+    result = {}
+    L = list(d.keys())  # in dic, we have test types (e.g., CET4,CET6,BBC) for each word
 
     for k in L:
-        if 'CET4' in d_in[k]:
-            d[k] = 4  # CET4 word has level 4
-        elif 'CET6' in d_in[k]:
-            d[k] = 6
-        elif 'IELTS' in d_in[k] or 'GRADUATE' in d_in[k]:   # 雅思或研究生英语
-            d[k] = 8
-        elif 'EnWords' in d_in[k]:      # 除基础词汇外的绝大多数词，包括一些犄角旮旯的专业词汇，近九万个，绝大多数我是真不认识
-            d[k] = 7
+        if 'CET4' in d[k]:
+            result[k] = 4  # CET4 word has level 4
+        elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
+            result[k] = 6
+        elif 'IELTS' in d[k]:   # 雅思或研究生英语
+            result[k] = 7
+        elif 'BBC' in d[k]:
+            result[k] = 8
+        # elif 'EnWords' in d[k]:      # 除基础词汇外的绝大多数词，包括一些犄角旮旯的专业词汇，近九万个，定级不太好处理，绝大多数我是真不认识
+        #     result[k] = 7
 
-    return d  # {'apple': 4, ...}
+    return result  # {'apple': 4, ...}
 
 def simplify_the_words_dict(d):
     """
@@ -65,13 +67,13 @@ def simplify_the_words_dict(d):
     stem = snowballstemmer.stemmer('english')
 
     result = {}
-    for j in d:   # j 在字典中
-        temp = stem.stemWord(j)     # 提取j得词根
-        if not temp in result:         # 如果这个词根不在结果字典中，则以词根为键、以dic中的等级作为值添加
-            result[temp] = d[j]
+    for k in d:   # j 在字典中
+        temp = stem.stemWord(k)     # 提取j得词根
+        if temp not in result:         # 如果这个词根不在结果字典中，则以词根为键、以dic中的等级作为值添加
+            result[temp] = d[k]
         else:                   # 如果这个词在结果词典中，则比较一下单词的难度等级是否最小
-            if result[temp] > d[j]:
-                result[temp] = d[j]
+            if result[temp] > d[k]:
+                result[temp] = d[k]
 
     return result