工具v2中增加分类题号字典生成.py功能

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.")

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)