From a39b0bb8e5c0914f289c6ebe4118e7efb1203d11 Mon Sep 17 00:00:00 2001
From: PlutoCtx <chentingxian195467@163.com>
Date: Wed, 10 May 2023 13:35:44 +0800
Subject: [PATCH] =?UTF-8?q?=E6=96=B0=E5=BB=BA=E4=BA=86simplify=5Fthe=5Fwor?=
 =?UTF-8?q?ds=5Fdict=E5=87=BD=E6=95=B0=E4=B8=93=E9=97=A8=E7=94=A8=E4=BA=8E?=
 =?UTF-8?q?=E7=BB=99=E8=AF=84=E7=BA=A7=E5=90=8E=E7=9A=84=E8=AF=8D=E5=BA=93?=
 =?UTF-8?q?=E5=8D=95=E8=AF=8D=E6=B8=85=E6=B4=97=E8=AF=8D=E6=A0=B9=EF=BC=8C?=
 =?UTF-8?q?=E8=AF=8D=E6=A0=B9=E7=9A=84=E9=9A=BE=E5=BA=A6=E6=8C=89=E7=85=A7?=
 =?UTF-8?q?=E5=85=B6=E5=8F=98=E5=BC=8F=E7=9A=84=E6=9C=80=E4=BD=8E=E7=AD=89?=
 =?UTF-8?q?=E7=BA=A7=E5=86=B3=E5=AE=9A=EF=BC=8C?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 app/difficulty.py | 37 +++++++++++++++++++++++++++----------
 1 file changed, 27 insertions(+), 10 deletions(-)

diff --git a/app/difficulty.py b/app/difficulty.py
index 34e7717..8e2d84b 100644
--- a/app/difficulty.py
+++ b/app/difficulty.py
@@ -53,29 +53,46 @@ def get_difficulty_level_for_words_and_tests(dic):
             d[k] = 6
         elif 'BBC' in dic[k]:
             d[k] = 8
-        print(k, d[k])
+        # print(k, d[k])
 
     return d  # {'apple': 4, ...}
 
+def simplify_the_words_dict(dic):
+    """
+    用于把保存了词库中评级后的词新建一个以词根为键、以同词根的最低等级为值
+    """
+    stem = snowballstemmer.stemmer('english')
+
+    res = {}
+    for j in dic:   # j 在字典中
+        temp = stem.stemWord(j)     # 提取j得词根
+        if not temp in res:         # 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
+            res[temp] = dic[j]
+        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 res[temp] > dic[j]:
+                res[temp] = dic[j]
+
+    return res
+
+
 def get_difficulty_level(d1, d2):
     """
     d2 来自于词库的27000个已标记单词
     d1 你个老六不会的词
+    在d2的后面添加单词，没有新建一个新的字典
     """
-    d2 = get_difficulty_level_for_words_and_tests(d2)  # 根据标记评级，仅适用于词库中的词
+    d2 = get_difficulty_level_for_words_and_tests(d2)   # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
+    d2_sim = simplify_the_words_dict(d2)                # 提取d2的词根   {'appl': 4, 'abandon': 4, ...}
     stem = snowballstemmer.stemmer('english')
 
-    for k in d1:        # k是用户不会的词
-        for l in d2:     # l是已经完成评级的词库的词
-            if k == l:  # k == l，这个用户也不会的词刚好以原型的形式出现在词库中，因为词库已经评过难度了，所以啥也不用干
+    for k in d1:        # 用户的词
+        for l in d2_sim:        # l是词库的某个单词的词根
+            if stem.stemWord(k) == l:   # 两者相等则视为同一难度的词
+                d2[k] = d2_sim[l]       # 给d2定级
                 break
-            elif stem.stemWord(k) in l:     # 这个词的词根与词库中的某个词一样，我们认为是同一难度的词
-                d1[k] = d2[l]
-            else:   # 这个词不在词库中，按频率来评定难度
+            else:       # 不相等则表明词库中没这词，按照单词的频率定级
                 d2[k] = difficulty_level_from_frequency(k, d1)
-
     return d2
-
         
 
 def revert_dict(d):