获取带有特殊大小写的字符串的前 140 个字符

这样的事情可能会起作用：

string result;
if (input.Length > 140)
{
    result = new string(input.Take(140).ToArray());
    if (input[140] != ',') // will ensure that we don´t omit the last complete word if the 140eth character is a comma
        result = result.Substring(0, result.LastIndexOf(','));
} 
else result = input;

如果总长度更大，则只需前 140 个字符。然后，它搜索逗号的最后一个索引，并获取所有字符，直到此逗号。

最好的办法是将字符串拆分为"单词"，然后使用字符串生成器重新组合它们。 未经测试的原始代码如下所示;

public IEnumerable<string> SplitSettlementStrings(string settlementsString) 
{
    var sb = new StringBuilder();
    foreach(var word in WordsFrom(settlementsString))
    {
        var extraFragment = $"{word}, ";
        if (sb.Length + extraFragment < 140) {
        sb.Append(extraFragment);
    }
    else
    {
        // we'd overflow the 140 char limit, so return this fragment and continue;
        yield return sb.ToString();
        sb = new StringBuilder();
    }
    if (sb.Length > 0) {
        // we may have content left in the string builder
        yield return sb.ToString();
    }
}

您需要使用这样的东西拆分单词;

 public IEnumerable<string> WordsFrom(string settlementsString) 
 {
    // split on commas, then trim to remove whitespace;
    return settlementsString.split(',').Select(x => x.Trim()).Where(x => x.Length > 0);
 }

你会像这样使用整体;

 var settlementStringsIn140CharLenghts = SplitSettlementStrings("M234, M456, M452 ...").ToArray()

编辑

旧的 skool .net 版本看起来像这样;

public ICollection<string> SplitSettlementStrings(string settlementsString) 
{
    List<string> results = new List<string>();
    StringBuilder sb = new StringBuilder();
    foreach(string word in WordsFrom(settlementsString))
    {
        string extraFragment = word + ", ";
        if (sb.Length + extraFragment < 140) {
           sb.Append(extraFragment);
        }
    }
    else
    {
        // we'd overflow the 140 char limit, so return this fragment and continue;
        results.Add(sb.ToString());
        sb = new StringBuilder();
    }
    if (sb.Length > 0) {
        // we may have content left in the string builder
        resuls.Add(sb.ToString());
    }
}
 public ICollection<string> WordsFrom(string settlementsString) 
 {
    // split on commas, then trim to remove whitespace;
    string[] fragments = settlementsString.split(',');
    List<string> result = new List<string>();
    foreach(string fragment in fragments) 
    {
        var candidate = fragment.Trim();
        if (candidate.Length > 0) 
        {
            result.Add(candidate);
        }
    } 
    return result;
 }

如果您不想将字符串拆分为列表，我会执行以下操作：

string myString = "M19, M42........";
string result;
int index = 141;
do
{
    //Decrement index to reduce the substring size
    index--;
    //Make the result the new length substring
    result = myString.Substring(0, index);
}while (myString[index] != ','); //Check if our result contains a comma as the next char to check if we're at the end of an entry

因此，您基本上只是将原始字符串子串到 140，检查位置 141 处的字符是否是表示"干净"剪切的逗号。如果没有，它将在 139 处子字符串，检查 140 是否有逗号，等等。

这样的事情应该可以工作：

string test = "M5903, M6169, M6753, M619, M6169, M6753, M6919, M6169, M6753, M919, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M919, M6169, M6753, M6919, M669, M6753, M6919, M69, M6753, M6919, M6169, M63, M6919, M6169, M6753, M6919, M619, M653, M6919, M66, M6753, M19, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M619";
if (test.Length > 140)
    if (test[140] != ',' && test[140] != ' ') // Last entry was split?
        test = test.Substring(0, test.LastIndexOf(',', 139)); // Take up to but not including the last ','
    else
        test = test.Substring(0, 139);
Console.WriteLine(test);

我的看法，只是为了好玩：

var ssplit = theString.Replace(", ", "#").Split('#');       
var sb = new StringBuilder();
for(int i = 0; i < ssplit.Length; i++)
{
    if(sb.Length + ssplit[i].Length > 138) // 140 minus the ", "
        break;
    if(sb.Length > 0) sb.Append(", ");
    sb.Append(ssplit[i]);
}

在这里，我将字符串分成Mxxx部分。然后我遍历这些部分，直到下一部分溢出 140（或 138，因为它需要在计数中包含", "分隔符）

查看实际效果

由于新字符串的持续内存分配，它可能不是对性能最敏感的解决方案，但它听起来确实像某种一次性原始数据输入。我们可以选择在输入中移除"令牌"，而我们有超过 140 个字符：

const string separator = ", ";
while (input.Length > 140)
{
     int delStartIndex = input.LastIndexOf(separator);
     int delLength = input.Length - delStartIndex;
     input = input.Remove(delStartIndex, delLength);
}

更注重性能的方法是为子字符串创建一种IEnumerable<string>或string[]的形式，并在连接它们之前计算它们的总长度。大致如下：

const string separator = ", ";
var splitInput = input.Split(separator.ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
var length = splitInput[0].Length;
var targetIndex = 1;
for (targetIndex = 1; length <= 140; targetIndex++)
    length += separator.Length + splitInput[targetIndex].Length;
if (length > 140)
    targetIndex--;
var splitOutput = new string[targetIndex];
Array.Copy(splitInput, 0, splitOutput, 0, targetIndex);
var output = string.Join(separator, splitOutput);

我们甚至可以制作一个不错的扩展方法，如下所示：

public static class StringUtils
{
    public static string TrimToLength(this string input, string separator, int targetLength)
    {
        var splitInput = input.Split(separator.ToCharArray(), StringSplitOptions.RemoveEmptyEntries);
        var length = splitInput[0].Length;
        var targetIndex = 1;
        for (targetIndex = 1; length <= targetLength; targetIndex++)
            length += separator.Length + splitInput[targetIndex].Length;
        if (length > targetLength)
            targetIndex--;
        var splitOutput = new string[targetIndex];
        Array.Copy(splitInput, 0, splitOutput, 0, targetIndex);
        return string.Join(separator, splitOutput);
    }
}

并像这样称呼它：

input.TrimToLength(", ", 140);

或：

input.TrimToLength(separator: ", ", targetLength:140);

这是一个解决方案。它从第 141 个字符向后处理字符串。

public static string Normalize(string input, int length)
{
    var terminators = new[] { ',', ' ' };
    if (input.Length <= length + 1)
        return input;
    int i = length + 1;
    while (!terminators.Contains(input[i]) && i > 0)
        i = i - 1;
    return input.Substring(0, i).TrimEnd(' ', ',');
}
Normalize(settlementsString, 140);

我使用这个：

static string FirstN(string s, int n = 140)
{
    if (string.IsNullOrEmpty(s) || s.Length <= n) return s;
    while (n > 0 && s[n] != ' ' && s[n] != ',') n--;
    return s.Substring(0, n);
}

工作测试示例代码（带有注释输出）：

using System;
namespace ConsoleApplication1
{
    class Program
    {
        static string FirstN(string s, int n = 140)
        {
            if (string.IsNullOrEmpty(s) || s.Length <= n) return s;
            while (n > 0 && s[n] != ' ' && s[n] != ',') n--;
            return s.Substring(0, n);
        }
        static void Main(string[] args)
        {
            var s = FirstN("M5903, M6169, M6753, M619, M6169, M6753, M6919, M6169, M6753, M919, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M919, M6169, M6753, M6919, M669, M6753, M6919, M69, M6753, M6919, M6169, M63, M6919, M6169, M6753, M6919, M619, M653, M6919, M66, M6753, M19, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M619");
            Console.WriteLine(s.Length); // 136
            Console.WriteLine(s);  //M5903, M6169, M6753, M619, M6169, M6753, M6919, M6169, M6753, M919, M6169, M6753, M6919, M6169, M6753, M6919, M6169, M6753, M919, M6169,
        }
    }
}

我希望这有所帮助。