database_tools中新增字符串与数据库中已有题目匹配功能

工具v2/database_tools.py

@@ -69,6 +69,25 @@ def detectmaxsim(currentid,excludelist,adict): #检测与已知题目关联程
                 argmaxsim = id
     return (maxsim,argmaxsim) #返回最大关联系数与关联程度最大的题号
 
+def stringmaxsim(string,adict,listlength): 
+    # maxsim = -1
+    # argmaxsim = "000000"
+    maxsimlist = []
+    string = pre_treating(string)
+    for id in adict:
+        if not "OBSOLETE" in adict[id]["content"]:
+            simrate = Levenshtein.jaro(adict[id]["content"],string)
+            # if simrate > maxsim:
+            #     maxsim = simrate
+            #     argmaxsim = id
+            if len(maxsimlist) < listlength:
+                maxsimlist.append((id,simrate))
+            elif simrate > maxsimlist[-1][1]:
+                maxsimlist = maxsimlist[:-1]
+                maxsimlist.append((id,simrate))
+                maxsimlist = sorted(maxsimlist,key = lambda x: x[1], reverse = True)
+    return maxsimlist #返回最大关联的listlength个题号及关联系数
+
 def generate_sim_group(startingids,prodict,max_size,threshold): #生成与已知题块startingids(冒号和逗号连接的字符串)关联程度超过threshold的题目组, 超过max_size即停止
     id_list = generate_number_set(startingids)
     output_list = []