From 6462ef87ccf8c02bc4c58693ca6de385efb2bc01 Mon Sep 17 00:00:00 2001
From: AsWhitale <1838528479@qq.com>
Date: Thu, 29 May 2025 14:16:44 +0800
Subject: [PATCH] vocabulary

---
 app/static/wordfreqapp.db | Bin 0 -> 20480 bytes
 app/vocabulary.py         |  61 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)
 create mode 100644 app/static/wordfreqapp.db
 create mode 100644 app/vocabulary.py

diff --git a/app/static/wordfreqapp.db b/app/static/wordfreqapp.db
new file mode 100644
index 0000000000000000000000000000000000000000..943d6432c08d6911012a9fb19d0d8ab83a62ca8c
GIT binary patch
literal 20480
zcmeI&L2KJE6u@yQ&Ds)3)=S8s7tNO?v<ya%yDS}Mgr#Yhxv-p!muO&c<JMNX?AYzN
z^S(}x{V@F$m5fVQlhMO&;V+PF=~)lIpH2dQ{xpn@R^QU>EHdgq><B5vJEepW()MSz
z-?y55sNWCl-Nm13QoO$W-E3Wpdh=F1f6=;W-nRZcwTL(Z2q1s}0tg_000IagfWZF<
zTy;0LI_<Xnd0?WiiC*M7bG`n4?Dqp-1^vUJuRJ&9scu6lZyud#PX+#$K#h)VKOGL$
z$#`(oA5YXrf3ol1Igj%Edz#HE?-jA!M41U^k*Q`WqI!8AXFpbj8@*Tc&Cc7l6!Cnf
zm-$6vPpDzEFljLk-6w``+|`{<x1GsJZL_ntCnrT^<$_#aEcAS;E5nUP^;UviSM$DI
z*}KwmtFyZ+f4wYn+DhVSqRU(DQ4X)1E!oOZ7+aLVDDXe{<G<Nd|1>xrjBJJ@e-soH
zMla1uz;uyKSK|E(HPM$kS(VCC<R(t%l~|+KbbLGRLPG!n1Q0*~0R#|0009ILKmdVt
z72y28t~*Oz2q1s}0tg_000IagfB*srJP2_9f3V;Q0R#|0009ILKmY**5I_Kdbrop1
f!ubDxUALFI5I_I{1Q0*~0R#|0009ILC<N{R&%US2

literal 0
HcmV?d00001

diff --git a/app/vocabulary.py b/app/vocabulary.py
new file mode 100644
index 0000000..2098d1c
--- /dev/null
+++ b/app/vocabulary.py
@@ -0,0 +1,61 @@
+import re
+import pickle
+
+def load_record(pickle_fname):
+    with open(pickle_fname, 'rb') as f:
+        d = pickle.load(f)
+    return d
+
+def convert_test_type_to_difficulty_level(d):
+    result = {}
+    for word, test_types in d.items():
+        if 'CET4' in test_types:
+            result[word] = 4
+        elif 'OXFORD3000' in test_types:
+            result[word] = 5
+        elif 'CET6' in test_types or 'GRADUATE' in test_types:
+            result[word] = 6
+        elif 'IELTS' in test_types:
+            result[word] = 7
+        elif 'OXFORD5000' in test_types:
+            result[word] = 7
+        elif 'BBC' in test_types:
+            result[word] = 8
+        else:
+            result[word] = 0
+    return result
+
+class VocabularyLevelEstimator:
+    _test_raw = load_record('words_and_tests.p')
+    _difficulty_dict = convert_test_type_to_difficulty_level(_test_raw)
+
+    @classmethod
+    def get_word_level(cls, word):
+        return cls._difficulty_dict.get(word, 0)
+
+class UserVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, d):
+        self.d = d
+        word_time = [(word, max(times)) for word, times in d.items() if times]
+        sorted_words = sorted(word_time, key=lambda x: x[1], reverse=True)
+        self.recent_words = [word for word, _ in sorted_words[:3]]
+
+    @property
+    def level(self):
+        levels = [self.get_word_level(word) for word in self.recent_words]
+        valid_levels = [lvl for lvl in levels if lvl > 0]
+        return sum(valid_levels) / len(valid_levels) if valid_levels else 0
+
+class ArticleVocabularyLevel(VocabularyLevelEstimator):
+    def __init__(self, content):
+        self.content = content
+        words = re.findall(r'\b[\w-]+\b', content.lower())
+        word_levels = [self.get_word_level(word) for word in words]
+        valid_levels = sorted([lvl for lvl in word_levels if lvl > 0], reverse=True)
+        self.top_levels = valid_levels[:5]  # 取前5个最高难度单词
+
+    @property
+    def level(self):
+        if not self.top_levels:
+            return 0
+        return sum(self.top_levels) / len(self.top_levels)
\ No newline at end of file