484 lines
25 KiB
Plaintext
484 lines
25 KiB
Plaintext
{
|
||
"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
|
||
}
|