diff --git a/文本处理工具/剪贴板文本整理_mathpix.ipynb b/文本处理工具/剪贴板文本整理_mathpix.ipynb index efcf8624..2ff64bfb 100644 --- a/文本处理工具/剪贴板文本整理_mathpix.ipynb +++ b/文本处理工具/剪贴板文本整理_mathpix.ipynb @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 15, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -235,6 +235,9 @@ "#删除\\quad\n", "data = re.sub(r\"\\\\q+uad\",\"\",data)\n", "\n", + "#删除~\n", + "data = re.sub(r\"~\",\"\",data)\n", + "\n", "\n", "\n", "data1 = data #替换后暂存data1\n", @@ -287,7 +290,8 @@ " equation1 = re.sub(r\"([0-9A-Z])\\s+([0-9A-Z])\",lambda x:x.group(1)+x.group(2),equation1)\n", " #改变组合数和排列数\n", " equation1 = re.sub(r\"([CP])(_[^_\\^]{,5}\\^)\",lambda x:r\"\\mathrm{\"+x.group(1)+\"}\"+x.group(2),equation1)\n", - " \n", + " #改单位\n", + " equation1 = re.sub(r\"mathrm\\{cm\\}\",\"text{cm}\",equation1)\n", " modified_equations.append(equation1)\n", "\n", "\n", @@ -315,8 +319,10 @@ " modified_data = re.sub(r\" \\$\",\"$\",modified_data)\n", "#mathpix的错别字修改\n", "modified_data = modified_data.replace(\"雉\",\"锥\")\n", - "modified_data = modified_data.replace(\"粗圆\",\"椭圆\")\n", + "modified_data = re.sub(\"[粗秿]圆\",\"椭圆\",modified_data)\n", "modified_data = modified_data.replace(\"针角\",\"钝角\")\n", + "modified_data = re.sub(\"投郑\",\"投掷\",modified_data)\n", + "modified_data = re.sub(\"抛郑\",\"抛掷\",modified_data)\n", "#mathpix的自由向量修改\n", "modified_data = modified_data.replace(r\"\\vec\",r\"\\overrightarrow \")\n", "modified_data = modified_data.replace(r\"\\bar\",r\"\\overline \")\n", @@ -341,6 +347,9 @@ "modified_data = re.sub(r\"\\\\{\\\\begin\\{array\\}\\{[rcl]*\\}\",r\"\\\\begin{cases}\",modified_data)\n", "modified_data = re.sub(r\"\\\\end{array}\",r\"\\\\end{cases}\",modified_data)\n", "\n", + "#冒号后加空格\n", + "modified_data = re.sub(r\":([\\S])\", lambda x:\": \"+x.group(1),modified_data)\n", + "\n", "#识别填空题加空格\n", "modified_data = re.sub(r\"([\\u4e00-\\u9fa5\\$])[\\s]*\\n\\\\item\",lambda x: x.group(1)+\"\\\\blank{50}.\\n\\\\item\",modified_data)\n", "\n", @@ -378,12 +387,12 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.15" + "version": "3.8.15" }, "orig_nbformat": 4, "vscode": { "interpreter": { - "hash": "ff3c292c316ba85de6f1ad75f19c731e79d694e741b6f515ec18f14996fe48dc" + "hash": "42dd566da87765ddbe9b5c5b483063747fec4aacc5469ad554706e4b742e67b2" } } },