小幅优化收录新题的方式

工具v2/database_tools.py

@@ -128,7 +128,9 @@ def generate_problem_series(startingid,length,adict): #在adict字典里返回
 
 def generate_number_set(string,*thedict): #根据可能含有":"和","的题号字符串生成一个用逗号分隔的六位题号列表, 例如"1:3,5"会生成["000001","000002","000003","000005"]
 #可变参数*dict如果存在, 将只生成dict的keys中包含的题号列表
-    string = re.sub(r"[\n\s]","",string)
+    string = re.sub(r"[\n\s]","",string).strip()
+    while not string[-1] in "0123456789":
+        string = string[:-1]
     string_list = string.split(",")
     numbers_list = []
     for s in string_list:

工具v2/新题比对.py

@@ -10,11 +10,20 @@ pro_dict = load_dict("../题库0.3/problems.json")
 treated_dict = treat_dict(pro_dict)
 data = getCopy()
 problems = [(d.strip()) for d in data.split("\\item") if not d.strip() == ""]
-output = "\\begin{enumerate}\n\n"
+output = "使用说明: repxxxxxx表示使用已有题号xxxxxx, sxxxxxx,yyyyyy,...表示和xxxxxx,yyyyyy,...相同, rxxxxxx,yyyyyy,...表示和xxxxxx,yyyyyy,...相关\n\n\\begin{enumerate}\n\n"
 for p in problems:
     p_treated = pre_treating(p)
-    output += f"\\item {p}\n\n"
     t = stringmaxsim(p_treated,treated_dict,3)
+    psrstring = ""
+    for id,simrate in t:
+        if simrate == 1:
+            psrstring = "rep"+id
+            break
+        else:
+            psrstring += id + ","
+    if psrstring[-1] == ",":
+        psrstring = psrstring[:-1]
+    output += f"\\item [{psrstring}] {p}\n\n"
     count = 0
     for id,simrate in t:
         output += "\n\\begin{tcolorbox}"+f"[colback = {colors[count]}!10!white, colframe = orange!10!white, breakable]\n"