{ "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.811\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.946\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.811\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.946\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.595\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.757\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.216\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.676\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.919\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.973\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.755\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三10班\t0.946\t0.324\t0.600\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.652\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.913\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.565\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.957\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.783\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.913\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.304\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.522\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.739\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.957\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.514\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三11班\t0.884\t0.353\t0.270\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.692\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.962\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.769\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.923\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.577\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.885\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.308\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.808\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.692\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.962\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.423\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三12班\t0.827\t0.721\t0.358\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.970\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.939\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.879\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.970\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三1班\t1.000\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.909\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.667\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.939\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.970\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.970\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.496\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三1班\t0.950\t0.932\t0.827\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.839\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.903\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.903\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.839\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.806\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.774\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.452\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.871\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.806\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.903\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.760\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三2班\t0.909\t0.754\t0.784\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.935\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.935\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.806\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三3班\t1.000\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.806\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.839\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.452\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.935\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.935\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.968\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.835\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三3班\t0.979\t0.613\t0.703\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.906\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.969\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.875\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.938\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.844\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.875\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.625\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.750\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.844\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.969\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.584\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三4班\t0.969\t0.785\t0.600\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.846\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.949\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.846\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.923\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.872\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.795\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.436\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.846\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.846\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.974\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.468\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三5班\t0.949\t0.744\t0.585\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.829\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.951\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.829\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.780\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.829\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.780\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.439\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.878\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.902\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三6班\t1.000\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.688\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三6班\t0.882\t0.631\t0.573\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.879\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.939\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.879\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.970\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.849\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.909\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.273\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.818\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.758\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.939\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.795\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三7班\t0.889\t0.542\t0.394\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.875\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.938\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.781\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.844\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.812\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.781\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.469\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.844\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.750\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三8班\t1.000\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.797\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三8班\t0.932\t0.695\t0.578\n", "题号: 004810 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.706\n", "题号: 005230 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.882\n", "题号: 004108 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.824\n", "题号: 004106 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.882\n", "题号: 004949 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.824\n", "题号: 007809 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.765\n", "题号: 001339 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.265\n", "题号: 020068 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.735\n", "题号: 020081 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.618\n", "题号: 007959 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.971\n", "题号: 002859 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.388\n", "题号: 011131 , 字段: usages 中已添加数据: 20220914\t高三9班\t0.926\t0.607\t0.368\n" ] } ], "source": [ "import os,re,json\n", "\n", "\"\"\"---明确数据文件位置---\"\"\"\n", "datafile = \"临时文件/字段数据.txt\"\n", "# 双回车分隔，记录内单回车分隔列表，首行为字段名\n", "\"\"\"---文件位置结束---\"\"\"\n", "\n", "def trim(string):\n", " string = re.sub(r\"^[ \\t\\n]*\",\"\",string)\n", " string = re.sub(r\"[ \\t\\n]*$\",\"\",string)\n", " return string\n", "def FloatToInt(string):\n", " f = float(string)\n", " if abs(f-round(f))<0.01:\n", " f = round(f)\n", " return f\n", "\n", "with open(datafile,\"r\",encoding=\"utf8\") as f:\n", " data = f.read()\n", "pos = data.index(\"\\n\")\n", "field = data[:pos].strip()\n", "appending_data = data[pos:]\n", "\n", "with open(r\"../题库0.3/Problems.json\",\"r\",encoding = \"utf8\") as f:\n", " database = f.read()\n", "pro_dict = json.loads(database)\n", "with open(r\"../题库0.3/LessonObj.json\",\"r\",encoding = \"utf8\") as f:\n", " database = f.read()\n", "obj_dict = json.loads(database)\n", "\n", "#该字段列表可能需要更新\n", "fields = [\"content\",\"objs\",\"tags\",\"genre\",\"ans\",\"solution\",\"duration\",\"usages\",\"origin\",\"edit\",\"same\",\"related\",\"remark\",\"space\"]\n", "\n", "if field in fields:\n", " field_type = type(pro_dict[\"000001\"][field])\n", " datalist = [record.strip() for record in appending_data.split(\"\\n\\n\") if len(trim(record)) > 0]\n", " for record in datalist:\n", " id = re.findall(r\"^[\\d]{1,}\",record)[0]\n", " data = record[len(id):].strip()\n", " id = id.zfill(6)\n", " if not id in pro_dict:\n", " print(\"题号:\",id,\"不在数据库中.\")\n", " break\n", " \n", " #字符串类型字段添加数据\n", " elif field_type == str and data in pro_dict[id][field]:\n", " print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",data)\n", " elif field_type == str and not data in pro_dict[id][field] and not field == \"ans\" and not field == \"space\":\n", " origin_data = pro_dict[id][field]\n", " new_data = trim(origin_data + \"\\n\" + data)\n", " pro_dict[id][field] = new_data\n", " print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",data)\n", " elif field_type == str and not data in pro_dict[id][field] and field == \"ans\" or field == \"space\":\n", " pro_dict[id][field] = data\n", " print(\"题号:\",id,\", 字段:\",field,\"中已修改数据:\",data)\n", " \n", " #数值类型字段添加数据\n", " elif (field_type == int or field_type == float) and abs(float(data) - pro_dict[id][field])<0.01:\n", " print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",FloatToInt(data))\n", " elif (field_type == int or field_type == float) and abs(float(data) - pro_dict[id][field])>=0.01:\n", " pro_dict[id][field] = FloatToInt(data)\n", " print(\"题号:\",id,\", 字段:\",field,\"中已修改数据:\",FloatToInt(data))\n", " \n", " #列表类型字段添加数据\n", " elif field_type == list:\n", " cell_data_list = [d.strip() for d in data.split(\"\\n\")]\n", " for cell_data in cell_data_list:\n", " if cell_data in pro_dict[id][field]:\n", " print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",cell_data)\n", " elif not field == \"objs\":\n", " pro_dict[id][field].append(cell_data)\n", " print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",cell_data)\n", " else:\n", " if not cell_data in obj_dict and not cell_data.upper() == \"KNONE\":\n", " print(\"题号:\",id,\", 字段:\",field,\"目标编号有误:\",cell_data)\n", " else:\n", " pro_dict[id][field].append(cell_data.upper())\n", " print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",cell_data.upper())\n", "\n", "with open(r\"../题库0.3/Problems.json\",\"w\",encoding = \"utf8\") as f:\n", " f.write(json.dumps(pro_dict,indent=4,ensure_ascii=False))" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3.9.7 ('base')", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.7" }, "orig_nbformat": 4, "vscode": { "interpreter": { "hash": "e4cce46d6be9934fbd27f9ca0432556941ea5bdf741d4f4d64c6cd7f8dfa8fba" } } }, "nbformat": 4, "nbformat_minor": 2 }