20220912 evening

工具/讲义生成.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {

工具/识别讲义是否有改动的题目.ipynb

@@ -0,0 +1,153 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "000436 True\n",
+      "007709 True\n",
+      "002746 True\n",
+      "000003 True\n",
+      "000986 True\n",
+      "000977 True\n",
+      "020079 True\n",
+      "002734 True\n",
+      "000978 True\n",
+      "020089 True\n",
+      "002733 True\n",
+      "000009 True\n",
+      "020081 True\n",
+      "004875 True\n",
+      "004854 True\n",
+      "004847 True\n",
+      "004894 True\n",
+      "004873 False\n",
+      "已知$\\triangle ABC$的三边为$a,b,c$求证: 关于$x$的方程$x^2+2ax+b^2=0$与$x^2+2cx-b^2=0$有公共根的一个充要条件是$A=90^\\circ$.\n",
+      "已知$\\triangle ABC$的三边为$a,b,c$求证: 关于$x$的方程$x^2+2ax+b^2=0$与$x^2+2cx-b^2=0$有公共根的充要条件是$A=90^\\circ$.\n",
+      "002747 False\n",
+      "已知$m$是实常数. 命题甲: 关于$x$的方程$x^2+x+m=0$有两个相异的负根; 命题乙: 关于$x$的方程$4x^2+x+m=0$无实根, 若这两个命题有且只有一个是真命题, 求实数$m$的取值范围.\n",
+      "*\n",
+      "已知$m$是实常数. 命题甲: 关于$x$的方程$x^2+x+m=0$有两个相异的负根; 命题乙: 关于$x$的方程$4x^2+x+m=0$无实根, 若这两个命题有且只有一个是真命题, 求实数$m$的取值范围.\n",
+      "000018 True\n",
+      "003708 True\n",
+      "000431 True\n",
+      "002737 True\n",
+      "004282 True\n",
+      "004876 True\n",
+      "004878 False\n",
+      "$a,b,c$三个数不全为零的一个充要条件是\\bracket{20}.\n",
+      "\\twoch{$a,b,c$三个数都不是零}{$a,b,c$三个数中至多有一个是零}{$a,b,c$三个数中只有一个是零}{$a,b,c$三个数中至少有一个不是零}\n",
+      "$a,b,c$三个数不全为零的充要条件是\\bracket{20}.\n",
+      "\\twoch{$a,b,c$三个数都不是零}{$a,b,c$三个数中至多有一个是零}{$a,b,c$三个数中只有一个是零}{$a,b,c$三个数中至少有一个不是零}\n",
+      "007736 True\n",
+      "010030 False\n",
+      "判断下列语句是否为命题:\\\\\n",
+      "(1) 有的正方形是三角形;\\\\\n",
+      "(2) 任意一个三角形的内角和都为$180^\\circ$;\\\\\n",
+      "(3) $1$是自然数吗?\\\\\n",
+      "(4) $3>\\pi$;\\\\\n",
+      "(5) $2\\in (0, 5)$, 且$2\\in \\mathbf{Z}$.\n",
+      "判断下列语句是否为命题:\\\\\n",
+      "(1) 有的正方形是三角形;\\blank{50}; (2) 任意一个三角形的内角和都为$180^\\circ$;\\blank{50}; (3) $1$是自然数吗?\\blank{50}; (4) $3>\\pi$;\\blank{50}; (5) $2\\in (0, 5)$, 且$2\\in \\mathbf{Z}$;\\blank{50}.\n",
+      "020072 False\n",
+      "在下列各题中, 用符号``$\\Rightarrow$''``$\\Leftarrow$''``$\\Leftrightarrow$''把$\\alpha$和$\\beta$联系起来:\\\\\n",
+      "(1) $\\alpha:a=0$, $\\beta:ab=0$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(2) $\\alpha:x^2=4$, $\\beta:x=2$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(3) $\\alpha:$实数$x$适合$x^2-5x+6=0$, $\\beta:x=2$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(4) $\\alpha:\\sqrt {x^2}=x$, $\\beta:x>0$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(5) $\\alpha:$实数$x$适合$\\dfrac{x-3}{x+1}=-1$, $\\beta:x=1$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(6) $\\alpha:k$除以$4$余$1$, $\\beta:k$除以$2$余$1$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(7) $\\alpha: \\{2\\}\\subset B\\subseteq \\{2, 3, 5\\}$, $\\beta:B=\\{2, 5\\}$; $\\alpha$\\blank{20}$\\beta$.\n",
+      "在下列各题中, 用符号``$\\Rightarrow$''``$\\Leftarrow$''``$\\Leftrightarrow$''把$\\alpha$和$\\beta$联系起来:\\\\\n",
+      "(1) $\\alpha:a=0$, $\\beta:ab=0$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(2) $\\alpha:x^2=4$, $\\beta:x=2$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(3) $\\alpha:$实数$x$适合$x^2-5x+6=0$, $\\beta:x=2$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(4) $\\alpha:\\sqrt {x^2}=x$, $\\beta:x>0$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(5) $\\alpha:$实数$x$适合$\\dfrac{x-3}{x+1}=-1$, $\\beta:x=1$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(6) $\\alpha:k$除以$4$余$1$, $\\beta:k$除以$2$余$1$; $\\alpha$\\blank{20}$\\beta$;\\\\\n",
+      "(7)$\\alpha: \\{2\\}\\subset B\\subseteq \\{2, 3, 5\\}$, $\\beta:B=\\{2, 5\\}$; $\\alpha$\\blank{20}$\\beta$.\n",
+      "002740 True\n",
+      "004886 True\n",
+      "007719 False\n",
+      "判断下列命题的真假, 并在相应的横线上填入``真命题''或``假命题''.\\\\\n",
+      "(1) 若$A\\cap B\\ne \\varnothing$, $B\\subset C$, 则$A\\cap C\\ne \\varnothing$\\blank{20};\\\\\n",
+      "(2) 方程$(a+1)x+b=0$($a$、$b\\in \\mathbf{R}$)的解为$x=-\\dfrac b{a+1}$\\blank{20};\\\\\n",
+      "(3) 若命题$\\alpha$、$\\beta$、$\\gamma$满足$\\alpha \\Rightarrow \\beta$, $\\beta \\Rightarrow \\gamma$, $\\gamma \\Rightarrow \\alpha$, 则$\\alpha \\Leftrightarrow \\gamma$\\blank{20}.\n",
+      "判断下列命题的真假, 并在相应的横线上填入``真命题''或``假命题''.\\\\\n",
+      "(1) 若$A\\cap B\\ne \\varnothing$, $B\\subset C$, 则$A\\cap C\\ne \\varnothing$\\blank{20};\\\\\n",
+      "(2) 方程$(a+1)x+b=0$($a$、$b\\in \\mathbf{R}$)的解为$x=-\\dfrac b{a+1}$\\blank{20};\\\\\n",
+      "(3)若命题$\\alpha$、$\\beta$、$\\gamma$满足$\\alpha \\Rightarrow \\beta$, $\\beta \\Rightarrow \\gamma$, $\\gamma \\Rightarrow \\alpha$, 则$\\alpha \\Leftrightarrow \\gamma$\\blank{20}.\n",
+      "002731 True\n",
+      "000981 True\n",
+      "004864 False\n",
+      "已知命题$p$: 如果$a^2+2ab+b^2+a+b-2\\ne 0$, 那么$a+b\\ne 1$, 求证: 命题$p$是真命题.\n",
+      "已知命题$p$: 如果$a^2+2ab+b^2+a+b-2\\ne 0$, 那么$a+b\\ne 1$, 求证: 命题$p$是真命题.\n",
+      "\\end{enumerate}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os,re,json\n",
+    "\n",
+    "#读取题库json文件并转化为字典\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\"C:\\Users\\weiye\\Documents\\wwy sync\\23届\\第一轮复习讲义\\02_常用逻辑用语.tex\",\"r\",encoding = \"u8\") as f:\n",
+    "    data = f.read()\n",
+    "problems_raw = re.findall(r\"\\(([\\d]{6})\\)\\}([\\s\\S]*?)\\n\\n\",data)\n",
+    "problems_list = []\n",
+    "for p in problems_raw:\n",
+    "    if \"vspace\" in p[1]:\n",
+    "        problems_list.append((p[0],p[1][:p[1].index(r\"\\vspace\")]))\n",
+    "    else:\n",
+    "        problems_list.append(p)\n",
+    "        \n",
+    "for p in problems_list:\n",
+    "    print(p[0],pro_dict[p[0]][\"content\"].strip() == p[1].strip())\n",
+    "    if not pro_dict[p[0]][\"content\"].strip() == p[1].strip():\n",
+    "        print(pro_dict[p[0]][\"content\"].strip())\n",
+    "        print(p[1].strip())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.8 ('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": "3.8.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

文本处理工具/剪贴板文本整理_word文件.ipynb

@@ -0,0 +1,508 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os,re\n",
+    "import win32clipboard as wc\n",
+    "import win32con\n",
+    "\n",
+    "# 获取剪切板内容\n",
+    "def getCopy():\n",
+    "    wc.OpenClipboard()\n",
+    "    t = wc.GetClipboardData(win32con.CF_UNICODETEXT)\n",
+    "    wc.CloseClipboard()\n",
+    "    return t\n",
+    "\n",
+    "# 写入剪切板内容\n",
+    "def setCopy(str):\n",
+    "    wc.OpenClipboard()\n",
+    "    wc.EmptyClipboard()\n",
+    "    wc.SetClipboardData(win32con.CF_UNICODETEXT, str)\n",
+    "    wc.CloseClipboard()\n",
+    "\n",
+    "def full_stop(matchobj):\n",
+    "    if matchobj.group(1) == \"。\" or matchobj.group(1) == \"．\":\n",
+    "        return \". \"\n",
+    "    else:\n",
+    "        return \".\\n\"\n",
+    "def refine_brackets(matchobj):\n",
+    "    return matchobj.group(1)[1:-1]\n",
+    "def insert_a_blank(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\" \"+matchobj.group(1)[-1]\n",
+    "def multiple_choice(matchobj):\n",
+    "    string = \"\\\\fourch\" + \"{\" + matchobj.group(1) + \"}{\" + matchobj.group(2) + \"}{\" + matchobj.group(3) + \"}{\" + matchobj.group(4) + \"}\\n\"\n",
+    "    return string\n",
+    "def boldsymbols(matchobj):\n",
+    "    return \"\\\\i\"+matchobj.group(1)[:-1]+\"\\\\mathbf{\"+matchobj.group(1)[-1]+\"}\"\n",
+    "def boldsymbols_star(matchobj):\n",
+    "    return \"\\\\in \\\\mathbf{\"+matchobj.group(1)+\"}^*\"\n",
+    "def singleboldsymbols(matchobj):\n",
+    "    return \"$\\\\mathbf{\" + matchobj.group(1) + \"}$\"\n",
+    "def blackboardbold(matchobj):\n",
+    "    string = \"\\\\mathbf\" + \"{\" + matchobj.group(1) + \"}\"\n",
+    "    return string\n",
+    "def limit(matchobj):\n",
+    "    return \"\\\\displaystyle\\\\lim_{\"+matchobj.group(1)+\"}\"\n",
+    "def replace_i(matchobj):\n",
+    "    string = matchobj.group(1)\n",
+    "    length = len(string)\n",
+    "    for i in range(length-1,-1,-1):\n",
+    "        if string[i] == \"i\" and not \"item\" in string[i:] and not \"overline\" in string[i:]:\n",
+    "            string = string[:i] + \"\\\\mathrm{i}\" + string[i+1:]\n",
+    "    return string\n",
+    "def refine_log(matchobj):\n",
+    "    return r\"\\log_\"+matchobj.group(1)\n",
+    "def refine_powers(matchobj):\n",
+    "    base = matchobj.group(1)\n",
+    "    power = matchobj.group(2)\n",
+    "    return base + \"^\" + power\n",
+    "def refine_sequences(matchobj):\n",
+    "    return \"\\{\" + matchobj.group(1) + \"\\}\"\n",
+    "def refine_starting_brackets(matchobj):\n",
+    "    return \"$\" + matchobj.group(1)\n",
+    "def refine_left_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(2)\n",
+    "    return matchobj.group(1)+obj\n",
+    "def refine_right_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(1)\n",
+    "    return obj + matchobj.group(2)\n",
+    "def refine_brackets_in_brackets(matchobj):\n",
+    "    return matchobj.group(1) + matchobj.group(2) + matchobj.group(3)\n",
+    "def mathbf(matchobj):\n",
+    "    return \"\\\\mathbf{\" + matchobj.group(1) + \"}^\" + matchobj.group(2)\n",
+    "#以上是202207之前的文本处理机制\n",
+    "global layer\n",
+    "def rename_bracket(matchobj):\n",
+    "    return \"leftbracket\" + str(layer) + matchobj.group(1) + \"rightbracket\" + str(layer)\n",
+    "def frac_brackets(matchobj):\n",
+    "    return \"frac{\"+matchobj.group(1)+\"}{\"+matchobj.group(2)+\"}\"\n",
+    "def frac_single_second_bracket(matchobj):\n",
+    "    return \"frac \"+matchobj.group(1)+\"{\"+matchobj.group(2)+\"}\"\n",
+    "def recall_vital_bracket(matchobj):\n",
+    "    return matchobj.group(1) + \"{\" + matchobj.group(2) + \"}\"\n",
+    "def sqrt_brackets(matchobj):\n",
+    "    if matchobj.group(1) == None:\n",
+    "        first_group = \"\"\n",
+    "    else:\n",
+    "        first_group = matchobj.group(1)\n",
+    "    return \"sqrt \"+ first_group +\"{\" + matchobj.group(2) + \"}\"\n",
+    "#def refine_frac(string):\n",
+    "#    for s in range(7):\n",
+    "#        for t in range(7):\n",
+    "#            string = re.sub(r\"frac[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s)+\"[\\s]*\"+r\"leftbracket\"+str(t)+\"(.*?)\"+r\"rightbracket\"+str(t),frac_brackets,string)\n",
+    "#    return string\n",
+    "def refine_single_second_frac(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"frac[\\s]*(\\w)[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s),frac_single_second_bracket,string)\n",
+    "    return string\n",
+    "def refine_vital_bracket(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"(frac)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(line)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(arrow)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(_)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(\\^)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathrm)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathbf)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(begin)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(end)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "    return string\n",
+    "def refine_sqrt(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"sqrt[\\s]*(\\[\\w*\\])*[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),sqrt_brackets,string)\n",
+    "    return string\n",
+    "def give_blanks(string):\n",
+    "    string = re.sub(r\"(sqrt[\\w])\",insert_a_blank,string)\n",
+    "    string = re.sub(r\"(frac[\\w])\",insert_a_blank,string)\n",
+    "    return string\n",
+    "def give_brackets(string):\n",
+    "    string = re.sub(r\"leftbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"rightbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"leftset\",r\"\\{\",string)\n",
+    "    string = re.sub(r\"rightset\",r\"\\}\",string)\n",
+    "    return string\n",
+    "#以上是20220715新加的文本处理机制\n",
+    "def initial_bracket_search(string):\n",
+    "    t = re.search(r\"^[\\s]*?leftbracket(\\d)\",string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def initial_brackets_pair_search(string,d):\n",
+    "    t = re.search(\"rightbracket\"+d,string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def refine_frac(string):\n",
+    "    eq_left = \"\"\n",
+    "    eq_right = string\n",
+    "    while re.search(\"frac\",eq_right) != None:\n",
+    "        pos = re.search(\"frac\",eq_right)\n",
+    "        eq_left += eq_right[:pos.span()[1]]\n",
+    "        eq_right = eq_right[pos.span()[1]:]\n",
+    "        if initial_bracket_search(eq_right)>0:\n",
+    "            pos = initial_brackets_pair_search(eq_right,eq_right[initial_bracket_search(eq_right)-1])\n",
+    "            first_bracket = eq_right[:pos]\n",
+    "            first_layer = first_bracket[-1]\n",
+    "            eq_remain = eq_right[pos:]\n",
+    "            if initial_bracket_search(eq_remain)>0:\n",
+    "                pos = initial_brackets_pair_search(eq_remain,eq_remain[initial_bracket_search(eq_remain)-1])\n",
+    "                second_bracket = eq_remain[:pos]\n",
+    "                second_layer = second_bracket[-1]\n",
+    "                first_bracket = re.sub(r\"leftbracket\"+first_layer,\"{\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"leftbracket\"+second_layer,\"{\",second_bracket)\n",
+    "                first_bracket = re.sub(r\"rightbracket\"+first_layer,\"}\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"rightbracket\"+second_layer,\"}\",second_bracket)\n",
+    "                eq_right = first_bracket+second_bracket+eq_remain[pos:]\n",
+    "    return eq_left+eq_right\n",
+    "#以上是20220718修改的大括号处理机制, 修复了一个bug\n",
+    "def reduce_blank(matchobj):\n",
+    "    return matchobj.group(1).replace(\" \",\"\")\n",
+    "def add_dollars(matchobj):\n",
+    "    return matchobj.group(1)[0] + r\"$\" + matchobj.group(1)[1:-1] + r\"$\" + matchobj.group(1)[-1]\n",
+    "def del_first_char(matchobj):\n",
+    "    return matchobj.group(1)[1:]\n",
+    "def add_underline(matchobj):\n",
+    "    return matchobj.group(1)[0] + \"_\" + matchobj.group(1)[-1]\n",
+    "def brackets_to_cwords(matchobj):\n",
+    "    return \"左括号\"+matchobj.group(1)+\"右括号\"\n",
+    "def cwords_to_brackets(matchobj):\n",
+    "    return \"(\"+matchobj.group(1)+\")\"\n",
+    "def circled_brackets(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\"{\"+matchobj.group(1)[-1] + \"}\"\n",
+    "\n",
+    "# try:\n",
+    "#     os.chdir(r\"D:\\mathdept\\mathdept\\文本处理程序等\")\n",
+    "# except:\n",
+    "#     os.chdir(r\"D:\\mathdept\\文本处理程序等\")\n",
+    "# with open(\"textfile.txt\", \"r\", encoding = \"utf8\") as textfile:\n",
+    "#     data = textfile.read()\n",
+    "\n",
+    "data = getCopy()\n",
+    "\n",
+    "\n",
+    "#去除左右括号的前缀\n",
+    "data = data.replace(r\"\\left.\",\"\").replace(r\"\\left\",\"\").replace(r\"\\right.\",\"\").replace(r\"\\right\",\"\")\n",
+    "\n",
+    "#全角半角符号替换\n",
+    "data = re.sub(\"　\",\"  \",data)\n",
+    "data = re.sub(\"(。[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"(．[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"，\",\", \",data)\n",
+    "data = re.sub(\"：\",\": \",data)\n",
+    "data = re.sub(\"；\",\"; \",data)\n",
+    "data = re.sub(\"（\",\"(\",data)\n",
+    "data = re.sub(\"）\",\")\",data)\n",
+    "data = re.sub(\"？\",\"? \",data)\n",
+    "data = re.sub(\"“\",\"``\",data)\n",
+    "data = re.sub(\"”\",\"''\",data)\n",
+    "\n",
+    "#替换全角数字等\n",
+    "data = re.sub(\"α\",r\"\\\\alpha\",data)\n",
+    "data = re.sub(\"β\",r\"\\\\beta\",data)\n",
+    "data = re.sub(\"｛\",\"\\{\",data)\n",
+    "data = re.sub(\"｝\",\"\\}\",data)\n",
+    "data = re.sub(\"∪\",r\"\\\\cup \",data)\n",
+    "data = re.sub(\"∩\",r\"\\\\cap \",data)\n",
+    "data = re.sub(\"∞\",r\"\\\\infty\",data)\n",
+    "data = re.sub(\"γ\",r\"\\\\gamma\",data)\n",
+    "data = re.sub(\"δ\",r\"\\\\delta\",data)\n",
+    "data = re.sub(\"≤\",r\"\\\\le \",data)\n",
+    "data = re.sub(\"≥\",r\"\\\\ge \",data)\n",
+    "data = re.sub(\"槡\",r\"\\\\sqrt \",data)\n",
+    "data = re.sub(\"ｌｏｇ\",r\"\\\\log \",data)\n",
+    "data = re.sub(\"ｌｇ\",r\"\\\\lg \",data)\n",
+    "data = re.sub(\"ｌｎ\",r\"\\\\ln \",data)\n",
+    "data = re.sub(\"≠\",r\"\\\\ne \",data)\n",
+    "data = re.sub(\"π\",r\"\\\\pi \",data)\n",
+    "data = re.sub(\"θ\",r\"\\\\theta \",data)\n",
+    "data = re.sub(\"ｓｉｎ\",r\"\\\\sin \",data)\n",
+    "data = re.sub(\"ｃｏｓ\",r\"\\\\cos \",data)\n",
+    "data = re.sub(\"ｔａｎ\",r\"\\\\tan \",data)\n",
+    "data = re.sub(\"ｃｏｔ\",r\"\\\\cot \",data)\n",
+    "data = re.sub(\"△\",r\"\\\\triangle \",data)\n",
+    "data = re.sub(\"φ\",r\"\\\\varphi \",data)\n",
+    "data = re.sub(\"ω\",r\"\\\\omega \",data)\n",
+    "data = re.sub(\"珗\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珝\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤犲\",r\"\\\\overrightarrow e_ \",data)\n",
+    "data = re.sub(\"λ\",r\"\\\\lambda \",data)\n",
+    "data = re.sub(\"ｉ\",r\"\\\\mathrm{i}\",data)\n",
+    "data = re.sub(\"∈\",r\"\\\\in \",data)\n",
+    "data = re.sub(\"⊥\",r\"\\\\perp \",data)\n",
+    "data = re.sub(\"∥\",r\"\\\\parallel \",data)\n",
+    "data = re.sub(\"①\",r\"\\\\textcircled{1} \",data)\n",
+    "data = re.sub(\"②\",r\"\\\\textcircled{2} \",data)\n",
+    "data = re.sub(\"③\",r\"\\\\textcircled{3} \",data)\n",
+    "data = re.sub(\"④\",r\"\\\\textcircled{4} \",data)\n",
+    "data = re.sub(\"⑤\",r\"\\\\textcircled{5} \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subseteq \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\supset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\Rightarrow \",data)\n",
+    "data = re.sub(\"\",r\"\\\\varnothing \",data)\n",
+    "data = re.sub(\"×\",r\"\\\\times \",data)\n",
+    "data = re.sub(\"·\",r\"\\\\cdot \",data)\n",
+    "data = re.sub(\"％\",r\"\\\\%\",data)\n",
+    "data = re.sub(\"ｃｍ\",r\"\\\\text{cm}\",data)\n",
+    "data = re.sub(\"°\",r\"^\\\\circ \",data)\n",
+    "data = re.sub(\"∶\",r\": \",data)\n",
+    "data = re.sub(\"ｍ\",r\"\\\\text{m}\",data)\n",
+    "data = re.sub(\"∠\",r\"\\\\angle \",data)\n",
+    "data = re.sub(r\"→\\n \",r\"\",data)\n",
+    "data = re.sub(\"〈\",r\"\\\\langle \",data)\n",
+    "data = re.sub(\"〉\",r\"\\\\rangle \",data)\n",
+    "data = re.sub(\"…\",r\"\\\\cdots\",data)\n",
+    "data = re.sub(\"Ｐ\",r\"\\\\mathrm{P}^\",data)\n",
+    "data = re.sub(\"\",r\"\\\\supseteq\",data)\n",
+    "data = re.sub(\"ｅ\",r\"\\\\mathrm{e}\",data)\n",
+    "data = re.sub(\"μ\",r\"\\\\mu\",data)\n",
+    "data = re.sub(\"ρ\",r\"\\\\rho\",data)\n",
+    "\n",
+    "\n",
+    "#修改一些常用的错误latex命令\n",
+    "data = re.sub(\"centerdot\",\"cdot\",data)\n",
+    "data = re.sub(\"cancel\",\"not\",data)\n",
+    "\n",
+    "whole_numbers = \"０１２３４５６７８９＋－＝犞犎犲狆狇狉犕犖＞＜犃犅犆犇狓犝［］｜犪狔犙犽犘犚犫犛犮犈犗犿犣狀犳犵犺狋犻犼狕犉犾′犱狊犌犡犢狘\"\n",
+    "correct_numbers = \"0123456789+-=VHepqrMN><ABCDxU[]|ayQkPRbScEOmZnfghtijzFl'dsGXY|\"\n",
+    "\n",
+    "\n",
+    "\n",
+    "for i in range(len(whole_numbers)):\n",
+    "    data = re.sub(whole_numbers[i],correct_numbers[i],data)\n",
+    "\n",
+    "data = re.sub(\"A1\",r\"A_1\",data)\n",
+    "data = re.sub(\"B1\",r\"B_1\",data)\n",
+    "data = re.sub(\"C1\",r\"C_1\",data)\n",
+    "data = re.sub(\"D1\",r\"D_1\",data)\n",
+    "#替换题号\n",
+    "data = re.sub(\"(\\\\n[例]*[0-9]+\\.[\\s]+)\",\"\\\\n\\\\\\\\item \",data)\n",
+    "\n",
+    "#公式标志换成$符号\n",
+    "data = re.sub(\"\\\\\\\\\\[\",r\"$\",data)\n",
+    "data = re.sub(\"\\\\\\\\\\]\",r\"$\",data)\n",
+    "data = re.sub(\"\\$\\$\",\"\",data)\n",
+    "\n",
+    "#选择题替换成标准格式\n",
+    "data = re.sub(\"A\\.([\\s\\S]*?)B\\.([\\s\\S]*?)C\\.([\\s\\S]*?)D\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(A\\)([\\s\\S]*?)\\(B\\)([\\s\\S]*?)\\(C\\)([\\s\\S]*?)\\(D\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"Ａ\\.([\\s\\S]*?)Ｂ\\.([\\s\\S]*?)Ｃ\\.([\\s\\S]*?)Ｄ\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(Ａ\\)([\\s\\S]*?)\\(Ｂ\\)([\\s\\S]*?)\\(Ｃ\\)([\\s\\S]*?)\\(Ｄ\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\$[ ]+\\}\",\"$}\",data)\n",
+    "data = re.sub(\"\\{[ ]+\\$\",\"{$\",data)\n",
+    "#data = re.sub(\"Ｃ\",r\"\\\\mathrm{C}^\",data)\n",
+    "#替换多余的空行\n",
+    "for i in range(20):\n",
+    "    data = re.sub(\"\\n[\\t ]*\\n\",\"\\n\",data)\n",
+    "#复数变成正体i\n",
+    "data = re.sub(\"(\\\\n.*?复数.*?\\\\n)\",replace_i,data)\n",
+    "\n",
+    "data1 = data #替换后暂存data1\n",
+    "\n",
+    "\n",
+    "#针对从教材里扒下来的文字\n",
+    "if 1 == 0:\n",
+    "    data = re.sub(r\"\\((\\d{1,2})\\)\",brackets_to_cwords,data)\n",
+    "    data = re.sub(r\"([A-Z][0-9])\",add_underline,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、\\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z]{1}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"左括号\\$(\\d{1,2})\\$右括号\",cwords_to_brackets,data)\n",
+    "    data = re.sub(r\"\\$\\,[\\s]*\\$\",\", \",data)\n",
+    "    data = re.sub(r\"(\\n[^(\\\\])\",del_first_char,data)\n",
+    "\n",
+    "\n",
+    "\n",
+    "#分离文字和公式\n",
+    "raw_texts = [] #文字数组\n",
+    "raw_equations = [] #公式数组\n",
+    "d = data\n",
+    "while len(d) > 0:\n",
+    "    interval = re.search(r\"\\$[\\s\\S]*?\\$\",d)\n",
+    "    if not interval == None:\n",
+    "        (start, end) = interval.span()\n",
+    "        raw_texts.append(d[:start])\n",
+    "        raw_equations.append(d[start:end])\n",
+    "        d = d[end:]\n",
+    "    else:\n",
+    "        raw_texts.append(d)\n",
+    "        d = \"\"\n",
+    "#至此已经分离了文字和公式，公式在两个$之内，包含两个$\n",
+    "\n",
+    "modified_texts = []\n",
+    "modified_equations = []\n",
+    "\n",
+    "for text in raw_texts:\n",
+    "    text1 = text\n",
+    "    #删除选项中无用的空格\n",
+    "    text1 = re.sub(\"\\{[\\s]+?\",\"{\",text1)\n",
+    "    text1 = re.sub(\"[\\s]+?\\}\",\"}\",text1)\n",
+    "    #填空题的处理\n",
+    "    text1 = re.sub(\"[ _]{5,}\",r\"\\\\blank{50}\",text1)\n",
+    "    #选择题的处理\n",
+    "    text1 = re.sub(r\"\\(\\\\blank\\{50\\}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    text1 = re.sub(r\"\\([\\s]{1,10}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    #逗号后面加空格\n",
+    "    text1 = re.sub(\",[ ]*\",\", \",text1)\n",
+    "    text1 = re.sub(r\"\\.\\}\",\"}\",text1)\n",
+    "    text1 = re.sub(r\"\\n\\d{1,3}\\.\",r\"\\n\\\\item \",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\.\",r\"\\\\blank{50}.\",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\,\",r\"\\\\blank{50},\",text1)\n",
+    "    text1 = re.sub(r\"\\\\bracket\\{20\\}\\n\",r\"\\\\bracket{20}.\\n\",text1)\n",
+    "    text1 = re.sub(r\"\\\\mathrm{\\\\mathrm{i}}\",r\"\\\\mathrm{i}\",text1)\n",
+    "    text1 = re.sub(r\"\\\\\\\\mathrm{i}n\",r\"\\\\in \",text1)\n",
+    "    modified_texts.append(text1)\n",
+    "\n",
+    "for equation in raw_equations:\n",
+    "    equation1 = equation\n",
+    "    # 去除单个字周围的大括号和去除双重无意义的大括号\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{[\\w\\+\\-\\*]?\\})\",refine_brackets,equation1)\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{\\{[^\\{\\}]*?\\}\\})\",refine_brackets,equation1)\n",
+    "    #去除公式中的无意义的空格\n",
+    "    equation1 = re.sub(\"\\\\\\\\[!,]|\\\\\\\\quad|\\\\\\\\qquad\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\{ *\\}\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\( *\",\"(\",equation1)\n",
+    "    equation1 = re.sub(\" *\\)\",\")\",equation1)\n",
+    "    equation1 = re.sub(\"\\$ *\",\"$\",equation1)\n",
+    "    equation1 = re.sub(\" *\\$\",\"$\",equation1)\n",
+    "    #改善大括号20220715\n",
+    "    layer = 0\n",
+    "    equation1 = re.sub(r\"\\\\\\{\",\"leftset\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\}\",\"rightset\",equation1)\n",
+    "    for layer in range(7):\n",
+    "        equation1 = re.sub(r\"\\{([^\\{\\}]*)\\}\",rename_bracket,equation1)\n",
+    "    equation1 = refine_sqrt(equation1)\n",
+    "    equation1 = refine_vital_bracket(refine_single_second_frac(refine_frac(equation1)))\n",
+    "    equation1 = give_blanks(equation1)\n",
+    "    equation1 = give_brackets(equation1)\n",
+    "    \n",
+    "    #改善交集和并集\n",
+    "    equation1 = equation1.replace(\"\\\\bigc\",\"\\\\c\")\n",
+    "    #在数集中的数集改为粗黑体\n",
+    "    equation1 = re.sub(\"\\\\\\i(n[ ]*[R|Q|Z|N|C])\",boldsymbols,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\in[\\s]*?\\{([NZQRC])\\^\\*\\}\",boldsymbols_star,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathbf([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\text([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(\"operatorname\",\"mathbf \",equation1)\n",
+    "    #equation1 = re.sub(\"\\$([R|Q|Z|N|C])\\$\",singleboldsymbols,equation1)\n",
+    "    #有关数列极限\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop\\\\lim }\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{lim}}\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\\\\,\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }\",limit,equation1)\n",
+    "    #修改centerdot\n",
+    "    equation1 = re.sub(r\"centerdot\",r\"cdot\",equation1)\n",
+    "    #分情况和方程组的处理\n",
+    "    equation1 = re.sub(\"align\\}[\\s]*\",\"cases}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\[\\s]*\",\"\\\\\\\\\\\\\\\\\",equation1)\n",
+    "    equation1 = re.sub(r\"&\",r\"\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{[\\s]*\\\\begin\",r\"\\\\begin\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\\\\\end\",r\"\\\\end\",equation1)\n",
+    "    #分式变displaystyle\n",
+    "    equation1 = re.sub(r\"\\\\frac\",r\"\\\\dfrac\",equation1)\n",
+    "    #处理多余的斜杠空格\n",
+    "    equation1 = re.sub(r\"\\\\[\\s]*?,[\\s]*?\\\\\",\",\",equation1)\n",
+    "    #处理三个点的写法\n",
+    "    equation1 = re.sub(r\"\\\\cdot[\\s]*?\\\\cdot[\\s]*?\\\\cdot\",r\"\\\\cdots\",equation1)\n",
+    "    #\\bot改为\\perp\n",
+    "    equation1 = re.sub(r\"\\\\bot\",r\"\\\\perp\",equation1)\n",
+    "    #\\texti等改为\\mathrm{i}\n",
+    "    equation1 = re.sub(r\"\\\\texti\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathrmi\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    #处理矩阵与行列式\n",
+    "    equation1 = re.sub(r\"\\([\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\)\",r\"\\\\end{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\|[\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\|\",r\"\\\\end{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\Delta\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\vartriangle\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\\.\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\|\\s*\",\"|\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\\\\\}\",r\"\\\\}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\{ *([ZRNQC])\\^([\\+\\-*]) *\\}\",mathbf,equation1)\n",
+    "    equation1 = re.sub(r\"\\{\\\\log *\\}_\",r\"\\\\log_\",equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\])\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\))\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\(\\s+?)\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\[\\s+?)\",reduce_blank,equation1)\n",
+    "    modified_equations.append(equation1)\n",
+    "\n",
+    "\n",
+    "#整合修改过的文本和公式    \n",
+    "modified_data = \"\"\n",
+    "for i in range(len(modified_texts)):\n",
+    "    try:\n",
+    "        modified_data += modified_texts[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "    try:\n",
+    "        modified_data += modified_equations[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "modified_data = re.sub(r\"[ ]+\\n\",\"\\n\",modified_data)\n",
+    "modified_data = re.sub(r\"\\$[\\s]*?\\\\parallel[\\s]*?\\$\",r\"\\\\parallel\",modified_data)\n",
+    "modified_data = re.sub(r\"\\n例\\s*?\\d{1,3}\\s*\",r\"\\n\\\\item \",modified_data)\n",
+    "modified_data = re.sub(r\"ABCDA_1B_1C_1D_1\",r\"$ABCD-A_1B_1C_1D_1$\",modified_data)\n",
+    "modified_data = re.sub(r\"(\\$[\\,\\.:;]\\$)\",refine_brackets,modified_data)\n",
+    "\n",
+    "\n",
+    "#以下是扒上教社教材题目时作的改动\n",
+    "#modified_data = re.sub(r\"log[\\s]\",r\"log_\",modified_data)\n",
+    "modified_data = re.sub(r\"(textcircled[\\d])\",circled_brackets,modified_data)\n",
+    "\n",
+    "#以下是为\\log_瘦身\n",
+    "modified_data = re.sub(r\"log[\\s]+_\",r\"log_\",modified_data)\n",
+    "\n",
+    "setCopy(modified_data)\n",
+    "\n",
+    "with open(\"临时文件/outputfile.txt\",\"w\",encoding = \"utf8\") as f:\n",
+    "    f.write(modified_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.8 ('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": "3.8.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

文本处理工具/文本整理_word文件.ipynb

@@ -0,0 +1,483 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os,re\n",
+    "\n",
+    "def full_stop(matchobj):\n",
+    "    if matchobj.group(1) == \"。\" or matchobj.group(1) == \"．\":\n",
+    "        return \". \"\n",
+    "    else:\n",
+    "        return \".\\n\"\n",
+    "def refine_brackets(matchobj):\n",
+    "    return matchobj.group(1)[1:-1]\n",
+    "def insert_a_blank(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\" \"+matchobj.group(1)[-1]\n",
+    "def multiple_choice(matchobj):\n",
+    "    string = \"\\\\fourch\" + \"{\" + matchobj.group(1) + \"}{\" + matchobj.group(2) + \"}{\" + matchobj.group(3) + \"}{\" + matchobj.group(4) + \"}\\n\"\n",
+    "    return string\n",
+    "def boldsymbols(matchobj):\n",
+    "    return \"\\\\i\"+matchobj.group(1)[:-1]+\"\\\\mathbf{\"+matchobj.group(1)[-1]+\"}\"\n",
+    "def boldsymbols_star(matchobj):\n",
+    "    return \"\\\\in \\\\mathbf{\"+matchobj.group(1)+\"}^*\"\n",
+    "def singleboldsymbols(matchobj):\n",
+    "    return \"$\\\\mathbf{\" + matchobj.group(1) + \"}$\"\n",
+    "def blackboardbold(matchobj):\n",
+    "    string = \"\\\\mathbf\" + \"{\" + matchobj.group(1) + \"}\"\n",
+    "    return string\n",
+    "def limit(matchobj):\n",
+    "    return \"\\\\displaystyle\\\\lim_{\"+matchobj.group(1)+\"}\"\n",
+    "def replace_i(matchobj):\n",
+    "    string = matchobj.group(1)\n",
+    "    length = len(string)\n",
+    "    for i in range(length-1,-1,-1):\n",
+    "        if string[i] == \"i\" and not \"item\" in string[i:] and not \"overline\" in string[i:]:\n",
+    "            string = string[:i] + \"\\\\mathrm{i}\" + string[i+1:]\n",
+    "    return string\n",
+    "def refine_log(matchobj):\n",
+    "    return r\"\\log_\"+matchobj.group(1)\n",
+    "def refine_powers(matchobj):\n",
+    "    base = matchobj.group(1)\n",
+    "    power = matchobj.group(2)\n",
+    "    return base + \"^\" + power\n",
+    "def refine_sequences(matchobj):\n",
+    "    return \"\\{\" + matchobj.group(1) + \"\\}\"\n",
+    "def refine_starting_brackets(matchobj):\n",
+    "    return \"$\" + matchobj.group(1)\n",
+    "def refine_left_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(2)\n",
+    "    return matchobj.group(1)+obj\n",
+    "def refine_right_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(1)\n",
+    "    return obj + matchobj.group(2)\n",
+    "def refine_brackets_in_brackets(matchobj):\n",
+    "    return matchobj.group(1) + matchobj.group(2) + matchobj.group(3)\n",
+    "def mathbf(matchobj):\n",
+    "    return \"\\\\mathbf{\" + matchobj.group(1) + \"}^\" + matchobj.group(2)\n",
+    "#以上是202207之前的文本处理机制\n",
+    "global layer\n",
+    "def rename_bracket(matchobj):\n",
+    "    return \"leftbracket\" + str(layer) + matchobj.group(1) + \"rightbracket\" + str(layer)\n",
+    "def frac_brackets(matchobj):\n",
+    "    return \"frac{\"+matchobj.group(1)+\"}{\"+matchobj.group(2)+\"}\"\n",
+    "def frac_single_second_bracket(matchobj):\n",
+    "    return \"frac \"+matchobj.group(1)+\"{\"+matchobj.group(2)+\"}\"\n",
+    "def recall_vital_bracket(matchobj):\n",
+    "    return matchobj.group(1) + \"{\" + matchobj.group(2) + \"}\"\n",
+    "def sqrt_brackets(matchobj):\n",
+    "    if matchobj.group(1) == None:\n",
+    "        first_group = \"\"\n",
+    "    else:\n",
+    "        first_group = matchobj.group(1)\n",
+    "    return \"sqrt \"+ first_group +\"{\" + matchobj.group(2) + \"}\"\n",
+    "#def refine_frac(string):\n",
+    "#    for s in range(7):\n",
+    "#        for t in range(7):\n",
+    "#            string = re.sub(r\"frac[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s)+\"[\\s]*\"+r\"leftbracket\"+str(t)+\"(.*?)\"+r\"rightbracket\"+str(t),frac_brackets,string)\n",
+    "#    return string\n",
+    "def refine_single_second_frac(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"frac[\\s]*(\\w)[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s),frac_single_second_bracket,string)\n",
+    "    return string\n",
+    "def refine_vital_bracket(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"(frac)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(line)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(arrow)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(_)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(\\^)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathrm)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathbf)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(begin)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(end)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "    return string\n",
+    "def refine_sqrt(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"sqrt[\\s]*(\\[\\w*\\])*[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),sqrt_brackets,string)\n",
+    "    return string\n",
+    "def give_blanks(string):\n",
+    "    string = re.sub(r\"(sqrt[\\w])\",insert_a_blank,string)\n",
+    "    string = re.sub(r\"(frac[\\w])\",insert_a_blank,string)\n",
+    "    return string\n",
+    "def give_brackets(string):\n",
+    "    string = re.sub(r\"leftbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"rightbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"leftset\",r\"\\{\",string)\n",
+    "    string = re.sub(r\"rightset\",r\"\\}\",string)\n",
+    "    return string\n",
+    "#以上是20220715新加的文本处理机制\n",
+    "def initial_bracket_search(string):\n",
+    "    t = re.search(r\"^[\\s]*?leftbracket(\\d)\",string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def initial_brackets_pair_search(string,d):\n",
+    "    t = re.search(\"rightbracket\"+d,string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def refine_frac(string):\n",
+    "    eq_left = \"\"\n",
+    "    eq_right = string\n",
+    "    while re.search(\"frac\",eq_right) != None:\n",
+    "        pos = re.search(\"frac\",eq_right)\n",
+    "        eq_left += eq_right[:pos.span()[1]]\n",
+    "        eq_right = eq_right[pos.span()[1]:]\n",
+    "        if initial_bracket_search(eq_right)>0:\n",
+    "            pos = initial_brackets_pair_search(eq_right,eq_right[initial_bracket_search(eq_right)-1])\n",
+    "            first_bracket = eq_right[:pos]\n",
+    "            first_layer = first_bracket[-1]\n",
+    "            eq_remain = eq_right[pos:]\n",
+    "            if initial_bracket_search(eq_remain)>0:\n",
+    "                pos = initial_brackets_pair_search(eq_remain,eq_remain[initial_bracket_search(eq_remain)-1])\n",
+    "                second_bracket = eq_remain[:pos]\n",
+    "                second_layer = second_bracket[-1]\n",
+    "                first_bracket = re.sub(r\"leftbracket\"+first_layer,\"{\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"leftbracket\"+second_layer,\"{\",second_bracket)\n",
+    "                first_bracket = re.sub(r\"rightbracket\"+first_layer,\"}\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"rightbracket\"+second_layer,\"}\",second_bracket)\n",
+    "                eq_right = first_bracket+second_bracket+eq_remain[pos:]\n",
+    "    return eq_left+eq_right\n",
+    "#以上是20220718修改的大括号处理机制, 修复了一个bug\n",
+    "def reduce_blank(matchobj):\n",
+    "    return matchobj.group(1).replace(\" \",\"\")\n",
+    "def add_dollars(matchobj):\n",
+    "    return matchobj.group(1)[0] + r\"$\" + matchobj.group(1)[1:-1] + r\"$\" + matchobj.group(1)[-1]\n",
+    "def del_first_char(matchobj):\n",
+    "    return matchobj.group(1)[1:]\n",
+    "def add_underline(matchobj):\n",
+    "    return matchobj.group(1)[0] + \"_\" + matchobj.group(1)[-1]\n",
+    "def brackets_to_cwords(matchobj):\n",
+    "    return \"左括号\"+matchobj.group(1)+\"右括号\"\n",
+    "def cwords_to_brackets(matchobj):\n",
+    "    return \"(\"+matchobj.group(1)+\")\"\n",
+    "def circled_brackets(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\"{\"+matchobj.group(1)[-1] + \"}\"\n",
+    "\n",
+    "with open(\"临时文件/textfile.txt\", \"r\", encoding = \"utf8\") as textfile:\n",
+    "    data = textfile.read()\n",
+    "\n",
+    "\n",
+    "\n",
+    "#去除左右括号的前缀\n",
+    "data = data.replace(r\"\\left.\",\"\").replace(r\"\\left\",\"\").replace(r\"\\right.\",\"\").replace(r\"\\right\",\"\")\n",
+    "\n",
+    "#全角半角符号替换\n",
+    "data = re.sub(\"　\",\"  \",data)\n",
+    "data = re.sub(\"(。[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"(．[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"，\",\", \",data)\n",
+    "data = re.sub(\"：\",\": \",data)\n",
+    "data = re.sub(\"；\",\"; \",data)\n",
+    "data = re.sub(\"（\",\"(\",data)\n",
+    "data = re.sub(\"）\",\")\",data)\n",
+    "data = re.sub(\"？\",\"? \",data)\n",
+    "data = re.sub(\"“\",\"``\",data)\n",
+    "data = re.sub(\"”\",\"''\",data)\n",
+    "\n",
+    "#替换全角数字等\n",
+    "data = re.sub(\"α\",r\"\\\\alpha\",data)\n",
+    "data = re.sub(\"β\",r\"\\\\beta\",data)\n",
+    "data = re.sub(\"｛\",\"\\{\",data)\n",
+    "data = re.sub(\"｝\",\"\\}\",data)\n",
+    "data = re.sub(\"∪\",r\"\\\\cup \",data)\n",
+    "data = re.sub(\"∩\",r\"\\\\cap \",data)\n",
+    "data = re.sub(\"∞\",r\"\\\\infty\",data)\n",
+    "data = re.sub(\"γ\",r\"\\\\gamma\",data)\n",
+    "data = re.sub(\"δ\",r\"\\\\delta\",data)\n",
+    "data = re.sub(\"≤\",r\"\\\\le \",data)\n",
+    "data = re.sub(\"≥\",r\"\\\\ge \",data)\n",
+    "data = re.sub(\"槡\",r\"\\\\sqrt \",data)\n",
+    "data = re.sub(\"ｌｏｇ\",r\"\\\\log \",data)\n",
+    "data = re.sub(\"ｌｇ\",r\"\\\\lg \",data)\n",
+    "data = re.sub(\"ｌｎ\",r\"\\\\ln \",data)\n",
+    "data = re.sub(\"≠\",r\"\\\\ne \",data)\n",
+    "data = re.sub(\"π\",r\"\\\\pi \",data)\n",
+    "data = re.sub(\"θ\",r\"\\\\theta \",data)\n",
+    "data = re.sub(\"ｓｉｎ\",r\"\\\\sin \",data)\n",
+    "data = re.sub(\"ｃｏｓ\",r\"\\\\cos \",data)\n",
+    "data = re.sub(\"ｔａｎ\",r\"\\\\tan \",data)\n",
+    "data = re.sub(\"ｃｏｔ\",r\"\\\\cot \",data)\n",
+    "data = re.sub(\"△\",r\"\\\\triangle \",data)\n",
+    "data = re.sub(\"φ\",r\"\\\\varphi \",data)\n",
+    "data = re.sub(\"ω\",r\"\\\\omega \",data)\n",
+    "data = re.sub(\"珗\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珝\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤犲\",r\"\\\\overrightarrow e_ \",data)\n",
+    "data = re.sub(\"λ\",r\"\\\\lambda \",data)\n",
+    "data = re.sub(\"ｉ\",r\"\\\\mathrm{i}\",data)\n",
+    "data = re.sub(\"∈\",r\"\\\\in \",data)\n",
+    "data = re.sub(\"⊥\",r\"\\\\perp \",data)\n",
+    "data = re.sub(\"∥\",r\"\\\\parallel \",data)\n",
+    "data = re.sub(\"①\",r\"\\\\textcircled{1} \",data)\n",
+    "data = re.sub(\"②\",r\"\\\\textcircled{2} \",data)\n",
+    "data = re.sub(\"③\",r\"\\\\textcircled{3} \",data)\n",
+    "data = re.sub(\"④\",r\"\\\\textcircled{4} \",data)\n",
+    "data = re.sub(\"⑤\",r\"\\\\textcircled{5} \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subseteq \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\supset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\Rightarrow \",data)\n",
+    "data = re.sub(\"\",r\"\\\\varnothing \",data)\n",
+    "data = re.sub(\"×\",r\"\\\\times \",data)\n",
+    "data = re.sub(\"·\",r\"\\\\cdot \",data)\n",
+    "data = re.sub(\"％\",r\"\\\\%\",data)\n",
+    "data = re.sub(\"ｃｍ\",r\"\\\\text{cm}\",data)\n",
+    "data = re.sub(\"°\",r\"^\\\\circ \",data)\n",
+    "data = re.sub(\"∶\",r\": \",data)\n",
+    "data = re.sub(\"ｍ\",r\"\\\\text{m}\",data)\n",
+    "data = re.sub(\"∠\",r\"\\\\angle \",data)\n",
+    "data = re.sub(r\"→\\n \",r\"\",data)\n",
+    "data = re.sub(\"〈\",r\"\\\\langle \",data)\n",
+    "data = re.sub(\"〉\",r\"\\\\rangle \",data)\n",
+    "data = re.sub(\"…\",r\"\\\\cdots\",data)\n",
+    "data = re.sub(\"Ｐ\",r\"\\\\mathrm{P}^\",data)\n",
+    "data = re.sub(\"\",r\"\\\\supseteq\",data)\n",
+    "data = re.sub(\"ｅ\",r\"\\\\mathrm{e}\",data)\n",
+    "data = re.sub(\"μ\",r\"\\\\mu\",data)\n",
+    "data = re.sub(\"ρ\",r\"\\\\rho\",data)\n",
+    "\n",
+    "\n",
+    "#修改一些常用的错误latex命令\n",
+    "data = re.sub(\"centerdot\",\"cdot\",data)\n",
+    "data = re.sub(\"cancel\",\"not\",data)\n",
+    "\n",
+    "whole_numbers = \"０１２３４５６７８９＋－＝犞犎犲狆狇狉犕犖＞＜犃犅犆犇狓犝［］｜犪狔犙犽犘犚犫犛犮犈犗犿犣狀犳犵犺狋犻犼狕犉犾′犱狊犌犡犢狘\"\n",
+    "correct_numbers = \"0123456789+-=VHepqrMN><ABCDxU[]|ayQkPRbScEOmZnfghtijzFl'dsGXY|\"\n",
+    "\n",
+    "\n",
+    "\n",
+    "for i in range(len(whole_numbers)):\n",
+    "    data = re.sub(whole_numbers[i],correct_numbers[i],data)\n",
+    "\n",
+    "data = re.sub(\"A1\",r\"A_1\",data)\n",
+    "data = re.sub(\"B1\",r\"B_1\",data)\n",
+    "data = re.sub(\"C1\",r\"C_1\",data)\n",
+    "data = re.sub(\"D1\",r\"D_1\",data)\n",
+    "#替换题号\n",
+    "data = re.sub(\"(\\\\n[例]*[0-9]+\\.[\\s]+)\",\"\\\\n\\\\\\\\item \",data)\n",
+    "\n",
+    "#公式标志换成$符号\n",
+    "data = re.sub(\"\\\\\\\\\\[\",r\"$\",data)\n",
+    "data = re.sub(\"\\\\\\\\\\]\",r\"$\",data)\n",
+    "data = re.sub(\"\\$\\$\",\"\",data)\n",
+    "\n",
+    "#选择题替换成标准格式\n",
+    "data = re.sub(\"A\\.([\\s\\S]*?)B\\.([\\s\\S]*?)C\\.([\\s\\S]*?)D\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(A\\)([\\s\\S]*?)\\(B\\)([\\s\\S]*?)\\(C\\)([\\s\\S]*?)\\(D\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"Ａ\\.([\\s\\S]*?)Ｂ\\.([\\s\\S]*?)Ｃ\\.([\\s\\S]*?)Ｄ\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(Ａ\\)([\\s\\S]*?)\\(Ｂ\\)([\\s\\S]*?)\\(Ｃ\\)([\\s\\S]*?)\\(Ｄ\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\$[ ]+\\}\",\"$}\",data)\n",
+    "data = re.sub(\"\\{[ ]+\\$\",\"{$\",data)\n",
+    "#data = re.sub(\"Ｃ\",r\"\\\\mathrm{C}^\",data)\n",
+    "#替换多余的空行\n",
+    "for i in range(20):\n",
+    "    data = re.sub(\"\\n[\\t ]*\\n\",\"\\n\",data)\n",
+    "#复数变成正体i\n",
+    "data = re.sub(\"(\\\\n.*?复数.*?\\\\n)\",replace_i,data)\n",
+    "\n",
+    "data1 = data #替换后暂存data1\n",
+    "\n",
+    "\n",
+    "#针对从教材里扒下来的文字\n",
+    "if 1 == 0:\n",
+    "    data = re.sub(r\"\\((\\d{1,2})\\)\",brackets_to_cwords,data)\n",
+    "    data = re.sub(r\"([A-Z][0-9])\",add_underline,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、\\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z]{1}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "    data = re.sub(r\"左括号\\$(\\d{1,2})\\$右括号\",cwords_to_brackets,data)\n",
+    "    data = re.sub(r\"\\$\\,[\\s]*\\$\",\", \",data)\n",
+    "    data = re.sub(r\"(\\n[^(\\\\])\",del_first_char,data)\n",
+    "\n",
+    "\n",
+    "\n",
+    "#分离文字和公式\n",
+    "raw_texts = [] #文字数组\n",
+    "raw_equations = [] #公式数组\n",
+    "d = data\n",
+    "while len(d) > 0:\n",
+    "    interval = re.search(r\"\\$[\\s\\S]*?\\$\",d)\n",
+    "    if not interval == None:\n",
+    "        (start, end) = interval.span()\n",
+    "        raw_texts.append(d[:start])\n",
+    "        raw_equations.append(d[start:end])\n",
+    "        d = d[end:]\n",
+    "    else:\n",
+    "        raw_texts.append(d)\n",
+    "        d = \"\"\n",
+    "#至此已经分离了文字和公式，公式在两个$之内，包含两个$\n",
+    "\n",
+    "modified_texts = []\n",
+    "modified_equations = []\n",
+    "\n",
+    "for text in raw_texts:\n",
+    "    text1 = text\n",
+    "    #删除选项中无用的空格\n",
+    "    text1 = re.sub(\"\\{[\\s]+?\",\"{\",text1)\n",
+    "    text1 = re.sub(\"[\\s]+?\\}\",\"}\",text1)\n",
+    "    #填空题的处理\n",
+    "    text1 = re.sub(\"[ _]{5,}\",r\"\\\\blank{50}\",text1)\n",
+    "    #选择题的处理\n",
+    "    text1 = re.sub(r\"\\(\\\\blank\\{50\\}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    text1 = re.sub(r\"\\([\\s]{1,10}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    #逗号后面加空格\n",
+    "    text1 = re.sub(\",[ ]*\",\", \",text1)\n",
+    "    text1 = re.sub(r\"\\.\\}\",\"}\",text1)\n",
+    "    text1 = re.sub(r\"\\n\\d{1,3}\\.\",r\"\\n\\\\item \",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\.\",r\"\\\\blank{50}.\",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\,\",r\"\\\\blank{50},\",text1)\n",
+    "    text1 = re.sub(r\"\\\\bracket\\{20\\}\\n\",r\"\\\\bracket{20}.\\n\",text1)\n",
+    "    text1 = re.sub(r\"\\\\mathrm{\\\\mathrm{i}}\",r\"\\\\mathrm{i}\",text1)\n",
+    "    text1 = re.sub(r\"\\\\\\\\mathrm{i}n\",r\"\\\\in \",text1)\n",
+    "    modified_texts.append(text1)\n",
+    "\n",
+    "for equation in raw_equations:\n",
+    "    equation1 = equation\n",
+    "    # 去除单个字周围的大括号和去除双重无意义的大括号\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{[\\w\\+\\-\\*]?\\})\",refine_brackets,equation1)\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{\\{[^\\{\\}]*?\\}\\})\",refine_brackets,equation1)\n",
+    "    #去除公式中的无意义的空格\n",
+    "    equation1 = re.sub(\"\\\\\\\\[!,]|\\\\\\\\quad|\\\\\\\\qquad\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\{ *\\}\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\( *\",\"(\",equation1)\n",
+    "    equation1 = re.sub(\" *\\)\",\")\",equation1)\n",
+    "    equation1 = re.sub(\"\\$ *\",\"$\",equation1)\n",
+    "    equation1 = re.sub(\" *\\$\",\"$\",equation1)\n",
+    "    #改善大括号20220715\n",
+    "    layer = 0\n",
+    "    equation1 = re.sub(r\"\\\\\\{\",\"leftset\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\}\",\"rightset\",equation1)\n",
+    "    for layer in range(7):\n",
+    "        equation1 = re.sub(r\"\\{([^\\{\\}]*)\\}\",rename_bracket,equation1)\n",
+    "    equation1 = refine_sqrt(equation1)\n",
+    "    equation1 = refine_vital_bracket(refine_single_second_frac(refine_frac(equation1)))\n",
+    "    equation1 = give_blanks(equation1)\n",
+    "    equation1 = give_brackets(equation1)\n",
+    "    \n",
+    "    #改善交集和并集\n",
+    "    equation1 = equation1.replace(\"\\\\bigc\",\"\\\\c\")\n",
+    "    #在数集中的数集改为粗黑体\n",
+    "    equation1 = re.sub(\"\\\\\\i(n[ ]*[R|Q|Z|N|C])\",boldsymbols,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\in[\\s]*?\\{([NZQRC])\\^\\*\\}\",boldsymbols_star,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathbf([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\text([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(\"operatorname\",\"mathbf \",equation1)\n",
+    "    #equation1 = re.sub(\"\\$([R|Q|Z|N|C])\\$\",singleboldsymbols,equation1)\n",
+    "    #有关数列极限\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop\\\\lim }\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{lim}}\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\\\\,\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }\",limit,equation1)\n",
+    "    #修改centerdot\n",
+    "    equation1 = re.sub(r\"centerdot\",r\"cdot\",equation1)\n",
+    "    #分情况和方程组的处理\n",
+    "    equation1 = re.sub(\"align\\}[\\s]*\",\"cases}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\[\\s]*\",\"\\\\\\\\\\\\\\\\\",equation1)\n",
+    "    equation1 = re.sub(r\"&\",r\"\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{[\\s]*\\\\begin\",r\"\\\\begin\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\\\\\end\",r\"\\\\end\",equation1)\n",
+    "    #分式变displaystyle\n",
+    "    equation1 = re.sub(r\"\\\\frac\",r\"\\\\dfrac\",equation1)\n",
+    "    #处理多余的斜杠空格\n",
+    "    equation1 = re.sub(r\"\\\\[\\s]*?,[\\s]*?\\\\\",\",\",equation1)\n",
+    "    #处理三个点的写法\n",
+    "    equation1 = re.sub(r\"\\\\cdot[\\s]*?\\\\cdot[\\s]*?\\\\cdot\",r\"\\\\cdots\",equation1)\n",
+    "    #\\bot改为\\perp\n",
+    "    equation1 = re.sub(r\"\\\\bot\",r\"\\\\perp\",equation1)\n",
+    "    #\\texti等改为\\mathrm{i}\n",
+    "    equation1 = re.sub(r\"\\\\texti\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathrmi\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    #处理矩阵与行列式\n",
+    "    equation1 = re.sub(r\"\\([\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\)\",r\"\\\\end{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\|[\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\|\",r\"\\\\end{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\Delta\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\vartriangle\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\\.\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\|\\s*\",\"|\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\\\\\}\",r\"\\\\}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\{ *([ZRNQC])\\^([\\+\\-*]) *\\}\",mathbf,equation1)\n",
+    "    equation1 = re.sub(r\"\\{\\\\log *\\}_\",r\"\\\\log_\",equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\])\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\))\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\(\\s+?)\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\[\\s+?)\",reduce_blank,equation1)\n",
+    "    modified_equations.append(equation1)\n",
+    "\n",
+    "\n",
+    "#整合修改过的文本和公式    \n",
+    "modified_data = \"\"\n",
+    "for i in range(len(modified_texts)):\n",
+    "    try:\n",
+    "        modified_data += modified_texts[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "    try:\n",
+    "        modified_data += modified_equations[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "modified_data = re.sub(r\"[ ]+\\n\",\"\\n\",modified_data)\n",
+    "modified_data = re.sub(r\"\\$[\\s]*?\\\\parallel[\\s]*?\\$\",r\"\\\\parallel\",modified_data)\n",
+    "modified_data = re.sub(r\"\\n例\\s*?\\d{1,3}\\s*\",r\"\\n\\\\item \",modified_data)\n",
+    "modified_data = re.sub(r\"ABCDA_1B_1C_1D_1\",r\"$ABCD-A_1B_1C_1D_1$\",modified_data)\n",
+    "modified_data = re.sub(r\"(\\$[\\,\\.:;]\\$)\",refine_brackets,modified_data)\n",
+    "\n",
+    "\n",
+    "\n",
+    "#以下是扒上教社教材题目时作的改动\n",
+    "modified_data = re.sub(r\"log[\\s]\",r\"log_\",modified_data)\n",
+    "modified_data = re.sub(r\"(textcircled[\\d])\",circled_brackets,modified_data)\n",
+    "\n",
+    "with open(\"临时文件/outputfile.txt\",\"w\",encoding = \"utf8\") as f:\n",
+    "    f.write(modified_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.8 ('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": "3.8.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

文本处理工具/文本整理_图片转文字后.ipynb

@@ -0,0 +1,484 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os,re\n",
+    "\n",
+    "def full_stop(matchobj):\n",
+    "    if matchobj.group(1) == \"。\" or matchobj.group(1) == \"．\":\n",
+    "        return \". \"\n",
+    "    else:\n",
+    "        return \".\\n\"\n",
+    "def refine_brackets(matchobj):\n",
+    "    return matchobj.group(1)[1:-1]\n",
+    "def insert_a_blank(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\" \"+matchobj.group(1)[-1]\n",
+    "def multiple_choice(matchobj):\n",
+    "    string = \"\\\\fourch\" + \"{\" + matchobj.group(1) + \"}{\" + matchobj.group(2) + \"}{\" + matchobj.group(3) + \"}{\" + matchobj.group(4) + \"}\\n\"\n",
+    "    return string\n",
+    "def boldsymbols(matchobj):\n",
+    "    return \"\\\\i\"+matchobj.group(1)[:-1]+\"\\\\mathbf{\"+matchobj.group(1)[-1]+\"}\"\n",
+    "def boldsymbols_star(matchobj):\n",
+    "    return \"\\\\in \\\\mathbf{\"+matchobj.group(1)+\"}^*\"\n",
+    "def singleboldsymbols(matchobj):\n",
+    "    return \"$\\\\mathbf{\" + matchobj.group(1) + \"}$\"\n",
+    "def blackboardbold(matchobj):\n",
+    "    string = \"\\\\mathbf\" + \"{\" + matchobj.group(1) + \"}\"\n",
+    "    return string\n",
+    "def limit(matchobj):\n",
+    "    return \"\\\\displaystyle\\\\lim_{\"+matchobj.group(1)+\"}\"\n",
+    "def replace_i(matchobj):\n",
+    "    string = matchobj.group(1)\n",
+    "    length = len(string)\n",
+    "    for i in range(length-1,-1,-1):\n",
+    "        if string[i] == \"i\" and not \"item\" in string[i:] and not \"overline\" in string[i:]:\n",
+    "            string = string[:i] + \"\\\\mathrm{i}\" + string[i+1:]\n",
+    "    return string\n",
+    "def refine_log(matchobj):\n",
+    "    return r\"\\log_\"+matchobj.group(1)\n",
+    "def refine_powers(matchobj):\n",
+    "    base = matchobj.group(1)\n",
+    "    power = matchobj.group(2)\n",
+    "    return base + \"^\" + power\n",
+    "def refine_sequences(matchobj):\n",
+    "    return \"\\{\" + matchobj.group(1) + \"\\}\"\n",
+    "def refine_starting_brackets(matchobj):\n",
+    "    return \"$\" + matchobj.group(1)\n",
+    "def refine_left_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(2)\n",
+    "    return matchobj.group(1)+obj\n",
+    "def refine_right_operating_brackets(matchobj):\n",
+    "    obj = matchobj.group(1)\n",
+    "    return obj + matchobj.group(2)\n",
+    "def refine_brackets_in_brackets(matchobj):\n",
+    "    return matchobj.group(1) + matchobj.group(2) + matchobj.group(3)\n",
+    "def mathbf(matchobj):\n",
+    "    return \"\\\\mathbf{\" + matchobj.group(1) + \"}^\" + matchobj.group(2)\n",
+    "#以上是202207之前的文本处理机制\n",
+    "global layer\n",
+    "def rename_bracket(matchobj):\n",
+    "    return \"leftbracket\" + str(layer) + matchobj.group(1) + \"rightbracket\" + str(layer)\n",
+    "def frac_brackets(matchobj):\n",
+    "    return \"frac{\"+matchobj.group(1)+\"}{\"+matchobj.group(2)+\"}\"\n",
+    "def frac_single_second_bracket(matchobj):\n",
+    "    return \"frac \"+matchobj.group(1)+\"{\"+matchobj.group(2)+\"}\"\n",
+    "def recall_vital_bracket(matchobj):\n",
+    "    return matchobj.group(1) + \"{\" + matchobj.group(2) + \"}\"\n",
+    "def sqrt_brackets(matchobj):\n",
+    "    if matchobj.group(1) == None:\n",
+    "        first_group = \"\"\n",
+    "    else:\n",
+    "        first_group = matchobj.group(1)\n",
+    "    return \"sqrt \"+ first_group +\"{\" + matchobj.group(2) + \"}\"\n",
+    "#def refine_frac(string):\n",
+    "#    for s in range(7):\n",
+    "#        for t in range(7):\n",
+    "#            string = re.sub(r\"frac[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s)+\"[\\s]*\"+r\"leftbracket\"+str(t)+\"(.*?)\"+r\"rightbracket\"+str(t),frac_brackets,string)\n",
+    "#    return string\n",
+    "def refine_single_second_frac(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"frac[\\s]*(\\w)[\\s]*leftbracket\"+str(s)+\"(.*?)\"+r\"rightbracket\"+str(s),frac_single_second_bracket,string)\n",
+    "    return string\n",
+    "def refine_vital_bracket(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"(frac)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(line)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(arrow)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(_)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(\\^)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathrm)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(mathbf)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(begin)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "        string = re.sub(r\"(end)[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),recall_vital_bracket,string)\n",
+    "    return string\n",
+    "def refine_sqrt(string):\n",
+    "    for s in range(7):\n",
+    "        string = re.sub(r\"sqrt[\\s]*(\\[\\w*\\])*[\\s]*leftbracket\"+str(s)+\"(.*?)rightbracket\"+str(s),sqrt_brackets,string)\n",
+    "    return string\n",
+    "def give_blanks(string):\n",
+    "    string = re.sub(r\"(sqrt[\\w])\",insert_a_blank,string)\n",
+    "    string = re.sub(r\"(frac[\\w])\",insert_a_blank,string)\n",
+    "    return string\n",
+    "def give_brackets(string):\n",
+    "    string = re.sub(r\"leftbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"rightbracket\\d\",\"\",string)\n",
+    "    string = re.sub(r\"leftset\",r\"\\{\",string)\n",
+    "    string = re.sub(r\"rightset\",r\"\\}\",string)\n",
+    "    return string\n",
+    "#以上是20220715新加的文本处理机制\n",
+    "def initial_bracket_search(string):\n",
+    "    t = re.search(r\"^[\\s]*?leftbracket(\\d)\",string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def initial_brackets_pair_search(string,d):\n",
+    "    t = re.search(\"rightbracket\"+d,string)\n",
+    "    if t == None:\n",
+    "        return -1\n",
+    "    else:\n",
+    "        return t.span()[1]\n",
+    "def refine_frac(string):\n",
+    "    eq_left = \"\"\n",
+    "    eq_right = string\n",
+    "    while re.search(\"frac\",eq_right) != None:\n",
+    "        pos = re.search(\"frac\",eq_right)\n",
+    "        eq_left += eq_right[:pos.span()[1]]\n",
+    "        eq_right = eq_right[pos.span()[1]:]\n",
+    "        if initial_bracket_search(eq_right)>0:\n",
+    "            pos = initial_brackets_pair_search(eq_right,eq_right[initial_bracket_search(eq_right)-1])\n",
+    "            first_bracket = eq_right[:pos]\n",
+    "            first_layer = first_bracket[-1]\n",
+    "            eq_remain = eq_right[pos:]\n",
+    "            if initial_bracket_search(eq_remain)>0:\n",
+    "                pos = initial_brackets_pair_search(eq_remain,eq_remain[initial_bracket_search(eq_remain)-1])\n",
+    "                second_bracket = eq_remain[:pos]\n",
+    "                second_layer = second_bracket[-1]\n",
+    "                first_bracket = re.sub(r\"leftbracket\"+first_layer,\"{\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"leftbracket\"+second_layer,\"{\",second_bracket)\n",
+    "                first_bracket = re.sub(r\"rightbracket\"+first_layer,\"}\",first_bracket)\n",
+    "                second_bracket = re.sub(r\"rightbracket\"+second_layer,\"}\",second_bracket)\n",
+    "                eq_right = first_bracket+second_bracket+eq_remain[pos:]\n",
+    "    return eq_left+eq_right\n",
+    "#以上是20220718修改的大括号处理机制, 修复了一个bug\n",
+    "def reduce_blank(matchobj):\n",
+    "    return matchobj.group(1).replace(\" \",\"\")\n",
+    "def add_dollars(matchobj):\n",
+    "    return matchobj.group(1)[0] + r\"$\" + matchobj.group(1)[1:-1] + r\"$\" + matchobj.group(1)[-1]\n",
+    "def del_first_char(matchobj):\n",
+    "    return matchobj.group(1)[1:]\n",
+    "def add_underline(matchobj):\n",
+    "    return matchobj.group(1)[0] + \"_\" + matchobj.group(1)[-1]\n",
+    "def brackets_to_cwords(matchobj):\n",
+    "    return \"左括号\"+matchobj.group(1)+\"右括号\"\n",
+    "def cwords_to_brackets(matchobj):\n",
+    "    return \"(\"+matchobj.group(1)+\")\"\n",
+    "def circled_brackets(matchobj):\n",
+    "    return matchobj.group(1)[:-1]+\"{\"+matchobj.group(1)[-1] + \"}\"\n",
+    "\n",
+    "\n",
+    "with open(\"临时文件/textfile.txt\", \"r\", encoding = \"utf8\") as textfile:\n",
+    "    data = textfile.read()\n",
+    "\n",
+    "\n",
+    "\n",
+    "#去除左右括号的前缀\n",
+    "data = data.replace(r\"\\left.\",\"\").replace(r\"\\left\",\"\").replace(r\"\\right.\",\"\").replace(r\"\\right\",\"\")\n",
+    "\n",
+    "#全角半角符号替换\n",
+    "data = re.sub(\"　\",\"  \",data)\n",
+    "data = re.sub(\"(。[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"(．[\\n]*)\",full_stop,data)\n",
+    "data = re.sub(\"，\",\", \",data)\n",
+    "data = re.sub(\"：\",\": \",data)\n",
+    "data = re.sub(\"；\",\"; \",data)\n",
+    "data = re.sub(\"（\",\"(\",data)\n",
+    "data = re.sub(\"）\",\")\",data)\n",
+    "data = re.sub(\"？\",\"? \",data)\n",
+    "data = re.sub(\"“\",\"``\",data)\n",
+    "data = re.sub(\"”\",\"''\",data)\n",
+    "\n",
+    "#替换全角数字等\n",
+    "data = re.sub(\"α\",r\"\\\\alpha\",data)\n",
+    "data = re.sub(\"β\",r\"\\\\beta\",data)\n",
+    "data = re.sub(\"｛\",\"\\{\",data)\n",
+    "data = re.sub(\"｝\",\"\\}\",data)\n",
+    "data = re.sub(\"∪\",r\"\\\\cup \",data)\n",
+    "data = re.sub(\"∩\",r\"\\\\cap \",data)\n",
+    "data = re.sub(\"∞\",r\"\\\\infty\",data)\n",
+    "data = re.sub(\"γ\",r\"\\\\gamma\",data)\n",
+    "data = re.sub(\"δ\",r\"\\\\delta\",data)\n",
+    "data = re.sub(\"≤\",r\"\\\\le \",data)\n",
+    "data = re.sub(\"≥\",r\"\\\\ge \",data)\n",
+    "data = re.sub(\"槡\",r\"\\\\sqrt \",data)\n",
+    "data = re.sub(\"ｌｏｇ\",r\"\\\\log \",data)\n",
+    "data = re.sub(\"ｌｇ\",r\"\\\\lg \",data)\n",
+    "data = re.sub(\"ｌｎ\",r\"\\\\ln \",data)\n",
+    "data = re.sub(\"≠\",r\"\\\\ne \",data)\n",
+    "data = re.sub(\"π\",r\"\\\\pi \",data)\n",
+    "data = re.sub(\"θ\",r\"\\\\theta \",data)\n",
+    "data = re.sub(\"ｓｉｎ\",r\"\\\\sin \",data)\n",
+    "data = re.sub(\"ｃｏｓ\",r\"\\\\cos \",data)\n",
+    "data = re.sub(\"ｔａｎ\",r\"\\\\tan \",data)\n",
+    "data = re.sub(\"ｃｏｔ\",r\"\\\\cot \",data)\n",
+    "data = re.sub(\"△\",r\"\\\\triangle \",data)\n",
+    "data = re.sub(\"φ\",r\"\\\\varphi \",data)\n",
+    "data = re.sub(\"ω\",r\"\\\\omega \",data)\n",
+    "data = re.sub(\"珗\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珝\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤\",r\"\\\\overrightarrow \",data)\n",
+    "data = re.sub(\"珤犲\",r\"\\\\overrightarrow e_ \",data)\n",
+    "data = re.sub(\"λ\",r\"\\\\lambda \",data)\n",
+    "data = re.sub(\"ｉ\",r\"\\\\mathrm{i}\",data)\n",
+    "data = re.sub(\"∈\",r\"\\\\in \",data)\n",
+    "data = re.sub(\"⊥\",r\"\\\\perp \",data)\n",
+    "data = re.sub(\"∥\",r\"\\\\parallel \",data)\n",
+    "data = re.sub(\"①\",r\"\\\\textcircled{1} \",data)\n",
+    "data = re.sub(\"②\",r\"\\\\textcircled{2} \",data)\n",
+    "data = re.sub(\"③\",r\"\\\\textcircled{3} \",data)\n",
+    "data = re.sub(\"④\",r\"\\\\textcircled{4} \",data)\n",
+    "data = re.sub(\"⑤\",r\"\\\\textcircled{5} \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subseteq \",data)\n",
+    "data = re.sub(\"\",r\"\\\\subset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\supset \",data)\n",
+    "data = re.sub(\"\",r\"\\\\Rightarrow \",data)\n",
+    "data = re.sub(\"\",r\"\\\\varnothing \",data)\n",
+    "data = re.sub(\"×\",r\"\\\\times \",data)\n",
+    "data = re.sub(\"·\",r\"\\\\cdot \",data)\n",
+    "data = re.sub(\"％\",r\"\\\\%\",data)\n",
+    "data = re.sub(\"ｃｍ\",r\"\\\\text{cm}\",data)\n",
+    "data = re.sub(\"°\",r\"^\\\\circ \",data)\n",
+    "data = re.sub(\"∶\",r\": \",data)\n",
+    "data = re.sub(\"ｍ\",r\"\\\\text{m}\",data)\n",
+    "data = re.sub(\"∠\",r\"\\\\angle \",data)\n",
+    "data = re.sub(r\"→\\n \",r\"\",data)\n",
+    "data = re.sub(\"〈\",r\"\\\\langle \",data)\n",
+    "data = re.sub(\"〉\",r\"\\\\rangle \",data)\n",
+    "data = re.sub(\"…\",r\"\\\\cdots\",data)\n",
+    "data = re.sub(\"Ｐ\",r\"\\\\mathrm{P}^\",data)\n",
+    "data = re.sub(\"\",r\"\\\\supseteq\",data)\n",
+    "data = re.sub(\"ｅ\",r\"\\\\mathrm{e}\",data)\n",
+    "data = re.sub(\"μ\",r\"\\\\mu\",data)\n",
+    "data = re.sub(\"ρ\",r\"\\\\rho\",data)\n",
+    "\n",
+    "\n",
+    "#修改一些常用的错误latex命令\n",
+    "data = re.sub(\"centerdot\",\"cdot\",data)\n",
+    "data = re.sub(\"cancel\",\"not\",data)\n",
+    "\n",
+    "whole_numbers = \"０１２３４５６７８９＋－＝犞犎犲狆狇狉犕犖＞＜犃犅犆犇狓犝［］｜犪狔犙犽犘犚犫犛犮犈犗犿犣狀犳犵犺狋犻犼狕犉犾′犱狊犌犡犢狘\"\n",
+    "correct_numbers = \"0123456789+-=VHepqrMN><ABCDxU[]|ayQkPRbScEOmZnfghtijzFl'dsGXY|\"\n",
+    "\n",
+    "\n",
+    "\n",
+    "for i in range(len(whole_numbers)):\n",
+    "    data = re.sub(whole_numbers[i],correct_numbers[i],data)\n",
+    "\n",
+    "data = re.sub(\"A1\",r\"A_1\",data)\n",
+    "data = re.sub(\"B1\",r\"B_1\",data)\n",
+    "data = re.sub(\"C1\",r\"C_1\",data)\n",
+    "data = re.sub(\"D1\",r\"D_1\",data)\n",
+    "#替换题号\n",
+    "data = re.sub(\"(\\\\n[例]*[0-9]+\\.[\\s]+)\",\"\\\\n\\\\\\\\item \",data)\n",
+    "\n",
+    "#公式标志换成$符号\n",
+    "data = re.sub(\"\\\\\\\\\\[\",r\"$\",data)\n",
+    "data = re.sub(\"\\\\\\\\\\]\",r\"$\",data)\n",
+    "data = re.sub(\"\\$\\$\",\"\",data)\n",
+    "\n",
+    "#选择题替换成标准格式\n",
+    "data = re.sub(\"A\\.([\\s\\S]*?)B\\.([\\s\\S]*?)C\\.([\\s\\S]*?)D\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(A\\)([\\s\\S]*?)\\(B\\)([\\s\\S]*?)\\(C\\)([\\s\\S]*?)\\(D\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"Ａ\\.([\\s\\S]*?)Ｂ\\.([\\s\\S]*?)Ｃ\\.([\\s\\S]*?)Ｄ\\.([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\(Ａ\\)([\\s\\S]*?)\\(Ｂ\\)([\\s\\S]*?)\\(Ｃ\\)([\\s\\S]*?)\\(Ｄ\\)([\\s\\S]*?)\\\\n\",multiple_choice,data)\n",
+    "data = re.sub(\"\\$[ ]+\\}\",\"$}\",data)\n",
+    "data = re.sub(\"\\{[ ]+\\$\",\"{$\",data)\n",
+    "#data = re.sub(\"Ｃ\",r\"\\\\mathrm{C}^\",data)\n",
+    "#替换多余的空行\n",
+    "for i in range(20):\n",
+    "    data = re.sub(\"\\n[\\t ]*\\n\",\"\\n\",data)\n",
+    "#复数变成正体i\n",
+    "data = re.sub(\"(\\\\n.*?复数.*?\\\\n)\",replace_i,data)\n",
+    "\n",
+    "data1 = data #替换后暂存data1\n",
+    "\n",
+    "\n",
+    "#针对从教材里扒下来的文字\n",
+    "data = re.sub(r\"\\((\\d{1,2})\\)\",brackets_to_cwords,data)\n",
+    "data = re.sub(r\"([A-Z][0-9])\",add_underline,data)\n",
+    "data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "data = re.sub(r\"([\\u4e00-\\u9fa5、\\)][0-9a-zA-Z_\\^\\\\\\{\\}|=><\\s\\n'\\(\\)\\-\\+:±]{2,}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "data = re.sub(r\"([\\u4e00-\\u9fa5、 \\)][0-9a-zA-Z]{1}[\\u4e00-\\u9fa5、\\,\\.;\\( ])\",add_dollars,data)\n",
+    "data = re.sub(r\"左括号\\$(\\d{1,2})\\$右括号\",cwords_to_brackets,data)\n",
+    "data = re.sub(r\"\\$\\,[\\s]*\\$\",\", \",data)\n",
+    "data = re.sub(r\"(\\n[^(\\\\])\",del_first_char,data)\n",
+    "\n",
+    "\n",
+    "\n",
+    "#分离文字和公式\n",
+    "raw_texts = [] #文字数组\n",
+    "raw_equations = [] #公式数组\n",
+    "d = data\n",
+    "while len(d) > 0:\n",
+    "    interval = re.search(r\"\\$[\\s\\S]*?\\$\",d)\n",
+    "    if not interval == None:\n",
+    "        (start, end) = interval.span()\n",
+    "        raw_texts.append(d[:start])\n",
+    "        raw_equations.append(d[start:end])\n",
+    "        d = d[end:]\n",
+    "    else:\n",
+    "        raw_texts.append(d)\n",
+    "        d = \"\"\n",
+    "#至此已经分离了文字和公式，公式在两个$之内，包含两个$\n",
+    "\n",
+    "modified_texts = []\n",
+    "modified_equations = []\n",
+    "\n",
+    "for text in raw_texts:\n",
+    "    text1 = text\n",
+    "    #删除选项中无用的空格\n",
+    "    text1 = re.sub(\"\\{[\\s]+?\",\"{\",text1)\n",
+    "    text1 = re.sub(\"[\\s]+?\\}\",\"}\",text1)\n",
+    "    #填空题的处理\n",
+    "    text1 = re.sub(\"[ _]{5,}\",r\"\\\\blank{50}\",text1)\n",
+    "    #选择题的处理\n",
+    "    text1 = re.sub(r\"\\(\\\\blank\\{50\\}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    text1 = re.sub(r\"\\([\\s]{1,10}\\)\",\"\\\\\\\\bracket{20}\",text1)\n",
+    "    #逗号后面加空格\n",
+    "    text1 = re.sub(\",[ ]*\",\", \",text1)\n",
+    "    text1 = re.sub(r\"\\.\\}\",\"}\",text1)\n",
+    "    text1 = re.sub(r\"\\n\\d{1,3}\\.\",r\"\\n\\\\item \",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\.\",r\"\\\\blank{50}.\",text1)\n",
+    "    text1 = re.sub(r\"\\s{3,}\\,\",r\"\\\\blank{50},\",text1)\n",
+    "    text1 = re.sub(r\"\\\\bracket\\{20\\}\\n\",r\"\\\\bracket{20}.\\n\",text1)\n",
+    "    text1 = re.sub(r\"\\\\mathrm{\\\\mathrm{i}}\",r\"\\\\mathrm{i}\",text1)\n",
+    "    text1 = re.sub(r\"\\\\\\\\mathrm{i}n\",r\"\\\\in \",text1)\n",
+    "    modified_texts.append(text1)\n",
+    "\n",
+    "for equation in raw_equations:\n",
+    "    equation1 = equation\n",
+    "    # 去除单个字周围的大括号和去除双重无意义的大括号\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{[\\w\\+\\-\\*]?\\})\",refine_brackets,equation1)\n",
+    "    for i in range(20):\n",
+    "        equation1 = re.sub(\"(\\{\\{[^\\{\\}]*?\\}\\})\",refine_brackets,equation1)\n",
+    "    #去除公式中的无意义的空格\n",
+    "    equation1 = re.sub(\"\\\\\\\\[!,]|\\\\\\\\quad|\\\\\\\\qquad\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\{ *\\}\",\"\",equation1)\n",
+    "    equation1 = re.sub(\"\\( *\",\"(\",equation1)\n",
+    "    equation1 = re.sub(\" *\\)\",\")\",equation1)\n",
+    "    equation1 = re.sub(\"\\$ *\",\"$\",equation1)\n",
+    "    equation1 = re.sub(\" *\\$\",\"$\",equation1)\n",
+    "    #改善大括号20220715\n",
+    "    layer = 0\n",
+    "    equation1 = re.sub(r\"\\\\\\{\",\"leftset\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\}\",\"rightset\",equation1)\n",
+    "    for layer in range(7):\n",
+    "        equation1 = re.sub(r\"\\{([^\\{\\}]*)\\}\",rename_bracket,equation1)\n",
+    "    equation1 = refine_sqrt(equation1)\n",
+    "    equation1 = refine_vital_bracket(refine_single_second_frac(refine_frac(equation1)))\n",
+    "    equation1 = give_blanks(equation1)\n",
+    "    equation1 = give_brackets(equation1)\n",
+    "    \n",
+    "    #改善交集和并集\n",
+    "    equation1 = equation1.replace(\"\\\\bigc\",\"\\\\c\")\n",
+    "    #在数集中的数集改为粗黑体\n",
+    "    equation1 = re.sub(\"\\\\\\i(n[ ]*[R|Q|Z|N|C])\",boldsymbols,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\in[\\s]*?\\{([NZQRC])\\^\\*\\}\",boldsymbols_star,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathbf([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\text([ZRNQC])\",blackboardbold,equation1)\n",
+    "    equation1 = re.sub(\"operatorname\",\"mathbf \",equation1)\n",
+    "    #equation1 = re.sub(\"\\$([R|Q|Z|N|C])\\$\",singleboldsymbols,equation1)\n",
+    "    #有关数列极限\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop\\\\lim }\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{lim}}\\\\,\",limit,equation1) \n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\\\\,\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }}\",limit,equation1)\n",
+    "    equation1 = re.sub(r\"\\\\underset{([\\w]\\\\to \\\\infty) }{\\\\mathop{\\\\lim }\",limit,equation1)\n",
+    "    #修改centerdot\n",
+    "    equation1 = re.sub(r\"centerdot\",r\"cdot\",equation1)\n",
+    "    #分情况和方程组的处理\n",
+    "    equation1 = re.sub(\"align\\}[\\s]*\",\"cases}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\[\\s]*\",\"\\\\\\\\\\\\\\\\\",equation1)\n",
+    "    equation1 = re.sub(r\"&\",r\"\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{[\\s]*\\\\begin\",r\"\\\\begin\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\\\\\\\end\",r\"\\\\end\",equation1)\n",
+    "    #分式变displaystyle\n",
+    "    equation1 = re.sub(r\"\\\\frac\",r\"\\\\dfrac\",equation1)\n",
+    "    #处理多余的斜杠空格\n",
+    "    equation1 = re.sub(r\"\\\\[\\s]*?,[\\s]*?\\\\\",\",\",equation1)\n",
+    "    #处理三个点的写法\n",
+    "    equation1 = re.sub(r\"\\\\cdot[\\s]*?\\\\cdot[\\s]*?\\\\cdot\",r\"\\\\cdots\",equation1)\n",
+    "    #\\bot改为\\perp\n",
+    "    equation1 = re.sub(r\"\\\\bot\",r\"\\\\perp\",equation1)\n",
+    "    #\\texti等改为\\mathrm{i}\n",
+    "    equation1 = re.sub(r\"\\\\texti\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\mathrmi\",r\"\\\\mathrm{i}\",equation1)\n",
+    "    #处理矩阵与行列式\n",
+    "    equation1 = re.sub(r\"\\([\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\)\",r\"\\\\end{pmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\|[\\s]*?\\\\begin\\{matrix\\}\",r\"\\\\begin{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\end\\{matrix\\}[\\s]*?\\|\",r\"\\\\end{vmatrix}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\Delta\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\vartriangle\",r\"\\\\triangle\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\\.\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\|\\s*\",\"|\",equation1)\n",
+    "    equation1 = re.sub(r\"\\s*\\\\\\}\",r\"\\\\}\",equation1)\n",
+    "    equation1 = re.sub(r\"\\\\\\{\\s*\",r\"\\\\{\",equation1)\n",
+    "    equation1 = re.sub(r\"\\{ *([ZRNQC])\\^([\\+\\-*]) *\\}\",mathbf,equation1)\n",
+    "    equation1 = re.sub(r\"\\{\\\\log *\\}_\",r\"\\\\log_\",equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\])\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"([^\\\\]\\s+?\\))\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\(\\s+?)\",reduce_blank,equation1)\n",
+    "    equation1 = re.sub(r\"(\\[\\s+?)\",reduce_blank,equation1)\n",
+    "    modified_equations.append(equation1)\n",
+    "\n",
+    "\n",
+    "#整合修改过的文本和公式    \n",
+    "modified_data = \"\"\n",
+    "for i in range(len(modified_texts)):\n",
+    "    try:\n",
+    "        modified_data += modified_texts[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "    try:\n",
+    "        modified_data += modified_equations[i]\n",
+    "    except:\n",
+    "        a = 1\n",
+    "modified_data = re.sub(r\"[ ]+\\n\",\"\\n\",modified_data)\n",
+    "modified_data = re.sub(r\"\\$[\\s]*?\\\\parallel[\\s]*?\\$\",r\"\\\\parallel\",modified_data)\n",
+    "modified_data = re.sub(r\"\\n例\\s*?\\d{1,3}\\s*\",r\"\\n\\\\item \",modified_data)\n",
+    "modified_data = re.sub(r\"ABCDA_1B_1C_1D_1\",r\"$ABCD-A_1B_1C_1D_1$\",modified_data)\n",
+    "modified_data = re.sub(r\"(\\$[\\,\\.:;]\\$)\",refine_brackets,modified_data)\n",
+    "modified_data = re.sub(r\"\\$\\$\",\"$\",modified_data)\n",
+    "\n",
+    "\n",
+    "\n",
+    "#以下是扒上教社教材题目时作的改动\n",
+    "modified_data = re.sub(r\"log[\\s]\",r\"log_\",modified_data)\n",
+    "modified_data = re.sub(r\"(textcircled[\\d])\",circled_brackets,modified_data)\n",
+    "\n",
+    "with open(\"临时文件/outputfile.txt\",\"w\",encoding = \"utf8\") as f:\n",
+    "    f.write(modified_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.8 ('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": "3.8.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

文本处理工具/表格整理.ipynb

@@ -0,0 +1,89 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def dollared(string):\n",
+    "    flag = True\n",
+    "    for c in string:\n",
+    "        if not c in \"1234567890.+-:[]()\":\n",
+    "            flag = False\n",
+    "            break\n",
+    "    if flag:\n",
+    "        string = \"$\" + string + \"$\"\n",
+    "    return string\n",
+    "\n",
+    "\n",
+    "with open(\"临时文件/textfile.txt\", \"r\", encoding = \"utf8\") as textfile:\n",
+    "    data = textfile.read()\n",
+    "\n",
+    "data1 = \"\"\n",
+    "for c in data:\n",
+    "    if 65296 <= ord(c) < 65306:\n",
+    "        data1 += str(ord(c)-65296)\n",
+    "    else:\n",
+    "        data1 += c\n",
+    "data = data1\n",
+    "data = data.replace(\"．\",\".\").replace(\"：\",\":\")\n",
+    "elements = data.split(\"\\n\")\n",
+    "elements_per_line = int(elements.pop(-1)) #这里需要修改\n",
+    "contents = \"\\\\begin{center}\\n\\\\begin{tabular}{|\"\n",
+    "for i in range(elements_per_line):\n",
+    "    contents += \"c|\"\n",
+    "contents += \"}\\n\"\n",
+    "contents += r\"\\hline\"+\"\\n\"\n",
+    "col = 1\n",
+    "for element in elements:\n",
+    "    if col != 1:\n",
+    "        contents += \" & \"\n",
+    "    contents += dollared(element)\n",
+    "    if col == elements_per_line:\n",
+    "        contents += r\" \\\\ \\hline\"+\"\\n\"\n",
+    "    col += 1\n",
+    "    if col > elements_per_line:\n",
+    "        col = 1\n",
+    "contents += \"\\\\end{tabular}\" + \"\\n\" + \"\\\\end{center}\"\n",
+    "\n",
+    "with open(\"临时文件/tablefile.txt\",\"w\",encoding = \"utf8\") as f:\n",
+    "    f.write(contents)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.8 ('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": "3.8.8"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "d311ffef239beb3b8f3764271728f3972d7b090c974f8e972fcdeedf230299ac"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}