丰富database tools

工具/database_tools.py

@@ -101,5 +101,45 @@ def parsePDF(filePath): #提取pdf文件中的字符
             text += page.get_text() + "\n"
     return text
 
+def extractIDs(filePath): #提取.txt,.tex或.pdf文件中的题号, 返回含有":"或","的题号字符串
+    if filePath[-4:] == ".txt" or filePath[-4:] == ".tex":
+        with open(filePath,"r",encoding = "u8") as f:
+            data = f.read()
+    elif filePath[-4:] == ".pdf":
+        data = parsePDF(filePath)
+    else:
+        return "格式不正确"
+    ids = re.findall(r"\((\d{6})\)",data)
+    return generate_exp(ids)
+
+
+def spareIDs(filename): #返回空闲题号
+    pro_dict = load_dict(filename)
+    idlist = list(pro_dict.keys())
+    used_str = generate_exp(idlist)
+    used_list = used_str.split(",")
+    output = ""
+    for group in range(len(used_list)-1):
+        output += "首个空闲id: %s, 直至: %s"%(str(int(used_list[group][-6:])+1).zfill(6),str(int(used_list[group+1][:6])-1).zfill(6)) + "\n"
+    output += "首个空闲id: %s, 直至: %s"%(str(int(used_list[-1][-6:])+1).zfill(6),"999999")
+    return output #返回的是一个多行的字符串, 每一行中含有一个空闲题号的闭区间
+
+def parse_usage(datastring): #对单个usages中的项的结果进行分词
+    datastring = re.sub(r"\s+","\t",datastring.strip())
+    datalist = datastring.split("\t")
+    date = ""
+    classname = ""
+    diff = []
+    for item in datalist:
+        if not "." in item and not "高" in item and not "班" in item:
+            date = item
+        elif "高" in item or "班" in item:
+            classname = item
+        else:
+            diff.append(item)
+    return({"date":date,"classname":classname,"difficulty":diff}) #返回一个字典, "date"表示日期, "classname"表示班级, "difficultiy"表示难度列表
+
+
+
 if __name__ == "__main__":
     print("数据库工具, import用.")