C#基础-第14章：字符、字符串和文本处理

* 说明:第2部分：第14章：字符、字符串和文本处理(P280)
    * 14.1 本章内容：
        · 字符
        · System.String类型
        · 高效率构造字符串
        · 获取对象的字符串表示：ToString
        · 解析字符串来获取对象：Parse
        · 编码：字符和字节的相互转换
        · 安全字符串

using System;
using System.Globalization;
using System.IO;
using System.Runtime.InteropServices;
using System.Security;
using System.Text;
using System.Threading;
using System.Windows.Forms;

public static class Program
{
    public static void Main(String[] args)
    {
        GetNumericValue.Go();
        CharConvert.Go();
        ComparingStringForEquality.Go();
        ComparingStringsForSorting.Go();
        Interning.Go();
        UsingStringInfo.Go();
        UsingStringBuilder.Go();
        Formatting.Go();
        CustomFormatter.Go();
        Encodings.Go();
        EncodingProperties.Go();
        CodePageConverter.Go(args);
        Base64Encoding.Go();
        UsingSecureString.Go();
    }
}

/// <summary>
/// 
/// </summary>
internal static class GetNumericValue //P280
{
    public static void Go()
    {
        Double d;

        // ‘\u0033’ 是“数字 3”
        d = Char.GetNumericValue('\u0033'); //  也可以直接使用‘3’
        Console.WriteLine(d.ToString());       // 显示 "3"

        // ‘\u00bc’ 是普通分数四分值一“('¼')”
        d = Char.GetNumericValue('\u00bc');
        Console.WriteLine(d.ToString());       // Displays "0.25"

        // ‘A’是 “大写拉丁字母 A”
        d = Char.GetNumericValue('A');
        Console.WriteLine(d.ToString());      // Displays "-1"
    }
}

/// <summary>
/// 字符转换 P281
/// </summary>
internal static class CharConvert
{
    public static void Go()
    {
        Char c;
        Int32 n;

        // 通过
        c = (Char)65;
        Console.WriteLine(c);                  // 显示 "A"

        n = (Int32)c;
        Console.WriteLine(n);                  // 显示 "65"

        c = unchecked((Char)(65536 + 65));      //unchecked 允许发生溢出
        Console.WriteLine(c);                  // 显示 "A"



        // Convert 数字 <-> 字符的相互转换 
        c = Convert.ToChar(65);
        Console.WriteLine(c);                  // Displays "A"

        n = Convert.ToInt32(c);
        Console.WriteLine(n);                  // Displays "65" 


        // 演示Convert的范围检查
        try
        {
            c = Convert.ToChar(70000);          // 对16位来说过大
            Console.WriteLine(c);               // 不执行
        }
        catch (OverflowException)
        {
            Console.WriteLine("Can't convert 70000 to a Char.");
        }


        // IConvertible 数字 <-> 字符的转化
        c = ((IConvertible)65).ToChar(null);
        Console.WriteLine(c);                  // Displays "A"

        n = ((IConvertible)c).ToInt32(null);
        Console.WriteLine(n);                  // Displays "65"
    }
}

/// <summary>
/// 演示了了序号比较和对语言文化敏感的比较的区别 P288
/// </summary>
internal static class ComparingStringForEquality
{
    public static void Go()
    {
        String s1 = "Strasse";
        String s2 = "Straße";
        Boolean eq;

        // 比较返回非零值 
        eq = String.Compare(s1, s2, StringComparison.Ordinal) == 0;
        Console.WriteLine("Ordinal  comparison: '{0}' {2} '{1}'", s1, s2,
           eq ? "==" : "!=");

        // 面向在德国（de）说德语（de）的人群
        //正确的比较字符串
        CultureInfo ci = new CultureInfo("de-DE");

        // Compare 返回零值，表示相等
        eq = String.Compare(s1, s2, true, ci) == 0;
        Console.WriteLine("Cultural comparison: '{0}' {2} '{1}'", s1, s2,
           eq ? "==" : "!=");
    }
}

/// <summary>
/// 演示语言文化对字符串排序的重要性，并展示了执行字符串比较的各种方式
/// </summary>
internal static class ComparingStringsForSorting
{
    public static void Go()
    {
        String output = String.Empty;
        String[] symbol = new String[] { "<", "=", ">" };
        Int32 x;
        CultureInfo ci;

        // 以下代码演示了在不同语言文化中
        // 字符串的比较方式也有所不同
        String s1 = "coté";
        String s2 = "côte";

        // 为法国法语排序字符串
        ci = new CultureInfo("fr-FR");
        x = Math.Sign(ci.CompareInfo.Compare(s1, s2));
        output += String.Format("{0} Compare: {1} {3} {2}",
           ci.Name, s1, s2, symbol[x + 1]);
        output += Environment.NewLine;

        // 为日本日语排序字符串
        ci = new CultureInfo("ja-JP");
        x = Math.Sign(ci.CompareInfo.Compare(s1, s2));
        output += String.Format("{0} Compare: {1} {3} {2}",
           ci.Name, s1, s2, symbol[x + 1]);
        output += Environment.NewLine;

        // 为当前线程的当前语言文化排序字符串
        ci = Thread.CurrentThread.CurrentCulture;
        x = Math.Sign(ci.CompareInfo.Compare(s1, s2));
        output += String.Format("{0} Compare: {1} {3} {2}",
           ci.Name, s1, s2, symbol[x + 1]);
        output += Environment.NewLine + Environment.NewLine;

        // 以下代码演示了如果将CompareInfo.Compare的
        // 高级选项应用于两个日语字符串
       // 一个字符串代表用平假名写成的同一个单词“shikansen”（新干线）
       // 另一个字符串代表用片假名写成的同一个单词
        s1 = "しんかんせん";  // ("\u3057\u3093\u304B\u3093\u305b\u3093")
        s2 = "シンカンセン";  // ("\u30b7\u30f3\u30ab\u30f3\u30bb\u30f3")

        // H以下是默认比较结果
        ci = new CultureInfo("ja-JP");
        x = Math.Sign(String.Compare(s1, s2, true, ci));
        output += String.Format("Simple {0} Compare: {1} {3} {2}",
           ci.Name, s1, s2, symbol[x + 1]);
        output += Environment.NewLine;

        // 以下是忽略日语假名的比较结果
        CompareInfo compareInfo = CompareInfo.GetCompareInfo("ja-JP");
        x = Math.Sign(compareInfo.Compare(s1, s2, CompareOptions.IgnoreKanaType));
        output += String.Format("Advanced {0} Compare: {1} {3} {2}",
           ci.Name, s1, s2, symbol[x + 1]);

        MessageBox.Show(output, "Comparing Strings For Sorting");
    }
}

/// <summary>
/// 字符串留用,
/// </summary>
internal static class Interning//P292
{
    public static void Go()
    {
        String s1 = "Hello";
        String s2 = "Hello";
        Console.WriteLine(Object.ReferenceEquals(s1, s2));  // 显示 be 'False'

        //显示调用Intern，
        s1 = String.Intern(s1); 
        s2 = String.Intern(s2);
        Console.WriteLine(Object.ReferenceEquals(s1, s2));  // 'True'
    }

    private static Int32 NumTimesWordAppearsIntern(String word, String[] wordlist)
    {
        // 这个方法假定wordlist中的所有数组元素都引用已留用的字符串
        //但是要谨慎使用。虽然能局部的提升性能，但有可能会带来整体性能降低。
        word = String.Intern(word);
        Int32 count = 0;
        for (Int32 wordnum = 0; wordnum < wordlist.Length; wordnum++)
        {
            if (Object.ReferenceEquals(word, wordlist[wordnum]))
                count++;
        }
        return count;
    }

    private static Int32 NumTimesWordAppearsEquals(String word, String[] wordlist)
    {
        Int32 count = 0;
        for (Int32 wordnum = 0; wordnum < wordlist.Length; wordnum++)
        {
            if (word.Equals(wordlist[wordnum], StringComparison.Ordinal))
                count++;
        }
        return count;
    }
}

/// <summary>
/// StringInfo类来处理字符串的文本元素的各种方式
/// </summary>
internal static class UsingStringInfo
{
    public static void Go()
    {
        // 以下字符串包含组合字符
        String s = "a\u0304\u0308bc\u0327";
        SubstringByTextElements(s);
        EnumTextElements(s);
        EnumTextElementIndexes(s);
    }

    private static void SubstringByTextElements(String s)
    {
        String output = String.Empty;

        StringInfo si = new StringInfo(s);
        for (Int32 element = 0; element < si.LengthInTextElements; element++)
        {
            output += String.Format(
               "Text element {0} is '{1}'{2}",
               element, si.SubstringByTextElements(element, 1),
               Environment.NewLine);
        }
        MessageBox.Show(output, "Result of SubstringByTextElements");
    }

    private static void EnumTextElements(String s)
    {
        String output = String.Empty;

        TextElementEnumerator charEnum =
           StringInfo.GetTextElementEnumerator(s);
        while (charEnum.MoveNext())
        {
            output += String.Format(
               "Text element at index {0} is '{1}'{2}",
               charEnum.ElementIndex, charEnum.GetTextElement(),
               Environment.NewLine);
        }
        MessageBox.Show(output, "Result of GetTextElementEnumerator");
    }

    private static void EnumTextElementIndexes(String s)
    {
        String output = String.Empty;

        Int32[] textElemIndex = StringInfo.ParseCombiningCharacters(s);
        for (Int32 i = 0; i < textElemIndex.Length; i++)
        {
            output += String.Format(
               "Text element {0} starts at index {1}{2}",
               i, textElemIndex[i], Environment.NewLine);
        }
        MessageBox.Show(output, "Result of ParseCombiningCharacters");
    }
}

/// <summary>
/// 高效率的构造字符串
/// </summary>
internal static class UsingStringBuilder
{
    public static void Go()
    {
        // 构造一个StringBuilder来执行字符串操作
        StringBuilder sb = new StringBuilder();

        // 使用StringBuiler来执行一些字符串的操作
        sb.AppendFormat("{0} {1}", "Jeffrey", "Richter").Replace(" ", "-");

        //将 StringBuilder转化为 String 以便将所以字符串转化为大写
        String s = sb.ToString().ToUpper();

        //清除StringBuilder（分配新的char数组）
        sb.Length = 0;

        // 将全部字符大写的String加载到StringBuilder中，执行其他操作 
        sb.Append(s).Insert(8, "Marc-");

        // 将StringBuilder 转化回 String. 
        s = sb.ToString();

        //向用户显示String
        Console.WriteLine(s);  // "JEFFREY-Marc-RICHTER"
    }
}

/// <summary>
/// 格式化字符串
/// </summary>
internal static class Formatting
{
    public static void Go()
    {
        Decimal price = 123.54M;
        String s = price.ToString("C", new CultureInfo("vi-VN"));
        MessageBox.Show(s);

        s = price.ToString("C", CultureInfo.InvariantCulture);
        MessageBox.Show(s);
    }
}

/// <summary>
/// 提供定制格式化器 P304
/// </summary>
internal static class CustomFormatter
{
    public static void Go()
    {
        StringBuilder sb = new StringBuilder();
        sb.AppendFormat(new BoldInt32s(), "{0} {1} {2:M}", "Jeff", 123, DateTime.Now);
        Console.WriteLine(sb);
    }

    private sealed class BoldInt32s : IFormatProvider, ICustomFormatter
    {
        public Object GetFormat(Type formatType)
        {
            if (formatType == typeof(ICustomFormatter)) return this;
            return Thread.CurrentThread.CurrentCulture.GetFormat(formatType);
        }

        public String Format(String format, Object arg, IFormatProvider formatProvider)
        {
            String s;

            IFormattable formattable = arg as IFormattable;

            if (formattable == null) s = arg.ToString();
            else s = formattable.ToString(format, formatProvider);

            if (arg.GetType() == typeof(Int32))
                return "<B>" + s + "</B>";
            return s;
        }
    }
}

/// <summary>
/// 编码：字符和字节的相互转化P310
/// </summary>
internal static class Encodings
{
    public static void Go()
    {
        // 准备编码的字符串
        String s = "Hi there.";

        // 获取从Endoing派生的一个对象
        // to encode/decode using UTF8
        Encoding encodingUTF8 = Encoding.UTF8;

        //将字符串编码成字节数组
        Byte[] encodedBytes = encodingUTF8.GetBytes(s);

        // 显示编好码的字节值
        Console.WriteLine("Encoded bytes: " +
           BitConverter.ToString(encodedBytes));

        // 将字节数组解码回字符串
        String decodedString = encodingUTF8.GetString(encodedBytes);

        // 显示解码的字符串.
        Console.WriteLine("Decoded string: " + decodedString);
    }
}

/// <summary>
///  演示大多数属性及其含义P311
/// </summary>
internal static class EncodingProperties
{
    public static void Go()
    {
        foreach (EncodingInfo ei in Encoding.GetEncodings())
        {
            Encoding e = ei.GetEncoding();
            Console.WriteLine("{1}{0}" +
               "\tCodePage={2}, WindowsCodePage={3}{0}" +
               "\tWebName={4}, HeaderName={5}, BodyName={6}{0}" +
               "\tIsBrowserDisplay={7}, IsBrowserSave={8}{0}" +
               "\tIsMailNewsDisplay={9}, IsMailNewsSave={10}{0}",

               Environment.NewLine,
               e.EncodingName, e.CodePage, e.WindowsCodePage,
               e.WebName, e.HeaderName, e.BodyName,
               e.IsBrowserDisplay, e.IsBrowserSave,
               e.IsMailNewsDisplay, e.IsMailNewsSave);
        }
    }
}

internal static class CodePageConverter
{
    public static void Go(String[] args)
    {
        if (args.Length != 4)
        {
            Console.WriteLine(
               "CodePageConverter <SrcFile> <SrcCodePage> <DstFile> <DstCodePage>{0}{0}" +
               "Examples:{0}" +
               "   CodePageConverter InFile.txt 65001 OutFile.txt 1200{0}" +
               "      => Converts from UTF-8 (codepage 65001) to UTF-16 (Little Endian){0}{0}" +
               "   CodePageConverter InFile.txt 932 OutFile.txt UTF-8{0}" +
               "      => Converts from shift-jis (codepage 932) to UTF-8",
               Environment.NewLine);
            return;
        }

        // Open the source stream using the specified encoding
        // Create the destination stream using the specified encoding
        using (StreamReader srcText = new StreamReader(args[0], GetEncoding(args[1])))
        using (StreamWriter dstText = new StreamWriter(args[2], false, GetEncoding(args[3])))
        {
            // Read from the source stream and write to the destination stream
            dstText.Write(srcText.ReadToEnd());
        }  // Close both streams
    }

    private static Encoding GetEncoding(String s)
    {
        try
        {
            // Assume the user passed an integer identifying a code page
            return Encoding.GetEncoding(Int32.Parse(s));
        }
        catch (FormatException)
        {
            // The user didn't pass an integer code page value
        }

        // Assume the user passed a string identifying a code page
        return Encoding.GetEncoding(s);
    }
}

/// <summary>
/// Base64 编码和解码
/// </summary>
internal static class Base64Encoding
{
    public static void Go()
    {
        // 获取一组10个随机生成的字节
        Byte[] bytes = new Byte[10];
        new Random().NextBytes(bytes);

        // 显示字节
        Console.WriteLine(BitConverter.ToString(bytes));

        // 将字节解码成Base-64字节串，并显示字符串
        String s = Convert.ToBase64String(bytes);
        Console.WriteLine(s);

        // 讲Base-64字符串编码回字节，变显示字节
        bytes = Convert.FromBase64String(s);
        Console.WriteLine(BitConverter.ToString(bytes));
    }
}

/// <summary>
/// 安全字符串，主要防止 机密数据在内存中被破解！
/// </summary>
internal static class UsingSecureString
{
    public static void Go()
    {
        using (SecureString ss = new SecureString())
        {
            Console.Write("Please enter password: ");
            while (true)
            {
                ConsoleKeyInfo cki = Console.ReadKey(true);
                if (cki.Key == ConsoleKey.Enter) break;

                // 将密码字符附加到SecureString中
                ss.AppendChar(cki.KeyChar);
                Console.Write("*");
            }
            Console.WriteLine();

            // 密码已输入，处于演示的目的显示它
            //DisplaySecureString(ss);
        }
        //  'using'之后,  SecureString 被 Disposed; 内存中无敏感数据
    }

    // 这个方法是不安全的，因为它要访问非托管存存
    // private unsafe static void DisplaySecureString(SecureString ss)
    //{
    //    Char* pc = null;
    //    try
    //    {
    //        // 将  SecureString 解密到一个非托管内存缓冲区中
    //        pc = (Char*)Marshal.SecureStringToCoTaskMemUnicode(ss);

    //        // 访问包含已解密的SecureString的非托管内存缓冲区
    //        // 
    //        for (Int32 index = 0; pc[index] != 0; index++)
    //            Console.Write(pc[index]);
    //    }
    //    finally
    //    {
    //        // 确保清零变释放包含已解密SecureString字符的非托管内存缓冲区
    //        if (pc != null)
    //            Marshal.ZeroFreeCoTaskMemUnicode((IntPtr)pc);
    //    }
    // }
}