cstdotnet/notebooks/cst.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Caret-Separated Text\n",
    "\n",
    "Caret-Separated Text (or CST) is a key-value pair format represented by numbers as keys and the value is the string enclosed between carets (^) that contains the translation. Any text which is not enclosed with carets is considered a comment and ignored.\n",
    "\n",
    "## CST.NET\n",
    "\n",
    "CST.NET uses .NET's built-in indexing extension function to accomplish locating of each respective key. As a consequence, it does not matter what you use for keys. I added an additional normalization to the pipeline that converts the document's line endings to the system's, in order to prevent crashes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "vscode": {
     "languageId": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "using System.IO;\n",
    "using System.Collections.Generic;\n",
    "using System.Text.RegularExpressions;"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "vscode": {
     "languageId": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "public static class CaretSeparatedText\n",
    "{\n",
    "    const char CARET = '^';\n",
    "    static readonly string _lf = \"\\u000A\";\n",
    "    static readonly string _cr = \"\\u000D\";\n",
    "    static readonly string _crlf = \"\\u000D\\u000A\";\n",
    "    static readonly string _ls = \"\\u2028\";\n",
    "\n",
    "    /// <summary>\n",
    "    /// Gets the value from the integer-based key.\n",
    "    /// </summary>\n",
    "    /// <returns>Returns the entry</returns>\n",
    "    public static string Parse(string content, int key)\n",
    "    {\n",
    "        var entries = NormalizeEntries(content);\n",
    "        return GetEntry(entries, key.ToString());\n",
    "    }\n",
    "\n",
    "    /// <summary>\n",
    "    /// Gets the value from the string-based key.\n",
    "    /// </summary>\n",
    "    /// <returns>Returns the entry</returns>\n",
    "    public static string Parse(string content, string key)\n",
    "    {\n",
    "        var entries = NormalizeEntries(content);\n",
    "        return GetEntry(entries, key);\n",
    "    }\n",
    "\n",
    "    /// <summary>\n",
    "    /// Replaces the document's line endings with the native system line endings.\n",
    "    /// </summary>\n",
    "    /// <remarks>This stage ensures there are no crashes during parsing.</remarks>\n",
    "    static IEnumerable<string> NormalizeEntries(string content)\n",
    "    {\n",
    "        if (!content.Contains(Environment.NewLine))\n",
    "        {\n",
    "            if (content.Contains(_lf))\n",
    "                content = content.Replace(_lf, Environment.NewLine);\n",
    "\n",
    "            if (content.Contains(_cr))\n",
    "                content = content.Replace(_cr, Environment.NewLine);\n",
    "\n",
    "            if (content.Contains(_crlf))\n",
    "                content = content.Replace(_crlf, Environment.NewLine);\n",
    "\n",
    "            if (content.Contains(_ls))\n",
    "                content = content.Replace(_ls, Environment.NewLine);\n",
    "        }\n",
    "\n",
    "        var lines = content.Split(new[] { $\"{CARET}{Environment.NewLine}\" },\n",
    "            StringSplitOptions.RemoveEmptyEntries);\n",
    "        var entries = new List<string>();\n",
    "\n",
    "        foreach (var line in lines)\n",
    "        {\n",
    "            // Skip comments\n",
    "            if (line.StartsWith(\"//\") || line.StartsWith(\"#\") ||\n",
    "                line.StartsWith(\"/*\") || line.EndsWith(\"*/\"))\n",
    "                continue;\n",
    "\n",
    "            entries.Add(line);\n",
    "        }\n",
    "\n",
    "        return entries;\n",
    "    }\n",
    "\n",
    "    static string GetEntry(IEnumerable<string> entries, string key)\n",
    "    {\n",
    "        // Search through list\n",
    "        foreach (var entry in entries)\n",
    "        {\n",
    "            // If the line doesn't start with the key, keep searching.\n",
    "            if (!entry.StartsWith(key))\n",
    "                continue;\n",
    "\n",
    "            // Locate index, trim carets and return translation.\n",
    "            var startIndex = entry.IndexOf(CARET);\n",
    "            var line = entry.Substring(startIndex);\n",
    "\n",
    "            return line.TrimStart(CARET).TrimEnd(CARET);\n",
    "        }\n",
    "\n",
    "        return \"***MISSING***\";\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "vscode": {
     "languageId": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "class ContentStrings\n",
    "{\n",
    "    string Language { get; set; } = \"english\";\n",
    "\n",
    "    public string GetText(string table, int key) => GetText(table, key.ToString());\n",
    "\n",
    "    public string GetText(string table, string key)\n",
    "    {\n",
    "        var baseDir = Path.Combine(Environment.CurrentDirectory, \"data\", \"uitext\", $\"{Language}.dir\");\n",
    "        var files = Directory.GetFiles(baseDir);\n",
    "\n",
    "        foreach (var file in files)\n",
    "        {\n",
    "            var id = Path.GetFileName(file);\n",
    "            var second = id.IndexOf(\"_\", 1);\n",
    "\n",
    "            if (second == -1)\n",
    "                continue;\n",
    "\n",
    "            id = id.Substring(1, second - 1);\n",
    "\n",
    "            if (id != table)\n",
    "                continue;\n",
    "\n",
    "            var content = File.ReadAllText(file);\n",
    "            return CaretSeparatedText.Parse(content, key);\n",
    "        }\n",
    "\n",
    "        return \"***MISSING***\";\n",
    "    }\n",
    "\n",
    "    public static string CSTFile(string cst, string key)\n",
    "    {\n",
    "        var path = Path.Combine(AppContext.BaseDirectory, cst);\n",
    "        var file = File.ReadAllText(path);\n",
    "\n",
    "        return CaretSeparatedText.Parse(file, key);\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "vscode": {
     "languageId": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "var english = new ContentStrings();\n",
    "var v1Path = Path.Combine(Environment.CurrentDirectory, \"data\", \"v1.cst\");\n",
    "var v1File = File.ReadAllText(v1Path);\n",
    "var one = english.GetText(\"102\", \"Singleline\");\n",
    "/*var three = CaretSeparatedText.Parse(v1File, 3);\n",
    "var four = CaretSeparatedText.Parse(v1File, 4); */\n",
    "Console.WriteLine($\"One:{Environment.NewLine}{one}\");\n",
    "/*Console.WriteLine($\"Three:{Environment.NewLine}{three}\");\n",
    "Console.WriteLine($\"Four:{Environment.NewLine}{four}\"); */"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "vscode": {
     "languageId": "csharp"
    }
   },
   "outputs": [],
   "source": [
    "var v2Path = Path.Combine(Environment.CurrentDirectory, \"data\", \"v2.cst\");\n",
    "var v2File = File.ReadAllText(v2Path);\n",
    "var singleLineV2 = CaretSeparatedText.Parse(v2File, \"Singleline\");\n",
    "var multiLineV2 = CaretSeparatedText.Parse(v2File, \"Multiline\");\n",
    "Console.WriteLine($\"Single line v2:{Environment.NewLine}{singleLineV2}\");\n",
    "Console.WriteLine($\"Multiline v2:{Environment.NewLine}{multiLineV2}\");"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".NET (C#)",
   "language": "C#",
   "name": ".net-csharp"
  },
  "language_info": {
   "file_extension": ".cs",
   "mimetype": "text/x-csharp",
   "name": "C#",
   "pygments_lexer": "csharp",
   "version": "8.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}