From 1793138b57b6192041b09088c8c0e12ed2c0a33f Mon Sep 17 00:00:00 2001
From: "weiye.wang" <kj_wangweiye@126.com>
Date: Thu, 29 Jun 2023 21:31:25 +0800
Subject: [PATCH] =?UTF-8?q?=E5=B7=A5=E5=85=B7v2=E4=B8=AD=E5=A2=9E=E5=8A=A0?=
 =?UTF-8?q?=E5=88=86=E7=B1=BB=E9=A2=98=E5=8F=B7=E5=AD=97=E5=85=B8=E7=94=9F?=
 =?UTF-8?q?=E6=88=90.py=E5=8A=9F=E8=83=BD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 工具v2/database_tools.py   | 13 +++++++++++++
 工具v2/分类题号字典生成.py | 25 +++++++++++++++++++++++++
 2 files changed, 38 insertions(+)
 create mode 100644 工具v2/分类题号字典生成.py

diff --git a/工具v2/database_tools.py b/工具v2/database_tools.py
index 66e21a4d..bb8279d5 100644
--- a/工具v2/database_tools.py
+++ b/工具v2/database_tools.py
@@ -626,7 +626,20 @@ def SortUsages(prodict):
     return 0 #返回0
 
 
+def SortUsagesbyAverage(theusages): #根据使用记录每一条的平均值进行排序, 越高的在越前面
+    glossdifflist = []
+    for i in range(len(theusages)):
+        glossdifflist = glossdifflist + [(i,parseUsage(theusages[i])["glossdiff"])]
+    sortedglossdifflist = sorted(glossdifflist, key = lambda x:x[1], reverse = True)
+    newusages = [theusages[i[0]] for i in sortedglossdifflist]
+    return(newusages) # 返回排序后的list
 
 
+def StripSuffix(string, suf_words): #除去字符串前后的空格及suf_words中每一个符合regex的字符串及其之后的部分
+    string = string.strip()
+    for sw in suf_words:
+        string = re.sub(sw+r"[\S]*$","",string)
+    return(string) # 返回处理以后的字符串
+
 if __name__ == "__main__":
     print("数据库工具, import用.")
\ No newline at end of file
diff --git a/工具v2/分类题号字典生成.py b/工具v2/分类题号字典生成.py
new file mode 100644
index 00000000..cd957801
--- /dev/null
+++ b/工具v2/分类题号字典生成.py
@@ -0,0 +1,25 @@
+original_id_list = "1:50000"
+suffix_words = ["试题",r"第[\d]*题"]
+outputfilepath = "临时文件/分类题号列表.json"
+
+from database_tools import *
+
+pro_dict = load_dict("../题库0.3/problems.json")
+idlist =  generate_number_set(original_id_list,pro_dict)
+
+#记录每一个出处对应的题号列表
+setlist = {}
+for id in idlist:
+    p = pro_dict[id]["origin"]
+    origin = StripSuffix(p,suffix_words)
+    if not origin in setlist:
+        setlist[origin] = [id]
+    else:
+        setlist[origin].append(id)
+
+outputdict = {}
+for origin in setlist:
+    outputdict[origin] = generate_exp(setlist[origin])
+
+save_dict(outputdict,outputfilepath)
+print("已将结果输出至 %s"%outputfilepath)
\ No newline at end of file