新增ExtractIDList功能

工具v2/database_tools.py

@@ -1975,5 +1975,28 @@ def MultiplechoicetoBlankFilling(string_raw): #把多选题的题干和选项转
     output = headstring + output[:-2]+"."
     return output
 
+def ExtractIDList(filepath): #从文件获取题目序号和ID的对应, 返回一个列表, 列表中的每个tuple都是(文件中的题目序号,六位题号)
+    if filepath[-4:] == ".pdf":
+        data = parsePDF(filepath)
+        idlist = re.findall(r"(\d+)\.[\s\n]*\((\d{6})\)",data)
+    else:
+        data = ReadTextFile(filepath)
+        enumerateBlocks = [item.strip() for item in re.findall(r"\\begin\{enumerate\}([\s\S]*?)\\end\{enumerate\}",data)]
+        for i in range(len(enumerateBlocks)):
+            if not enumerateBlocks[i].startswith("\\setcounter"):
+                enumerateBlocks[i] = "\\setcounter{enumi}{0}\n\n" + enumerateBlocks[i]
+        idlist = []
+        for item in enumerateBlocks:
+            enumilist = [i.span() for i in re.finditer(r"\\setcounter\{enumi\}\{(\d+)\}",item)]
+            enumilist.append((len(item),len(item)))
+            for i in range(len(enumilist)-1):
+                indstring = item[enumilist[i][0]:enumilist[i][1]]
+                ind = int(re.findall(r"\d+",indstring)[0])
+                bodylist = re.findall(r"\((\d{6})\)",item[enumilist[i][1]:enumilist[i+1][0]])
+                for id in bodylist:
+                    ind += 1
+                    idlist.append((str(ind),id))
+    return idlist
+
 if __name__ == "__main__":
     print("数据库工具, import用.")