0

示例输入是（注意这是一个单行字符串，我在此处使用了引号以使其更具可读性）：

1/129/1 楼 Murray Ave & 15A&B ERICA AVENUE & 12 HARVEY STREET & 34 VICTORIA STREET & 3/56 ST LEONARDS ST, MOSMAN PARK (John)。78/10 WELLINGTON ST MOSMAN PARK (兰博)

我目前的输出是：

1/129/1 - Murray - Ave - 
15A -  -  - 
B - ERICA - AVENUE - 
12 - HARVEY - STREET - 
34 - VICTORIA - STREET - 
3/56 - ST LEONARDS - ST - MOSMAN PARK
78/10 - WELLINGTON - ST - MOSMAN PARK

期望的输出是：

1/129/1 - Murray - Ave - 
15A - ERICA - AVENUE - 
15B - ERICA - AVENUE - 
12 - HARVEY - STREET - 
34 - VICTORIA - STREET - 
3/56 - ST LEONARDS - ST - MOSMAN PARK
78/10 - WELLINGTON - ST - MOSMAN PARK

如果第一个属性只包含数字，它应该继承下一条记录的信息，如果下一条记录号只包含一个字母，则它向后显示继承上一条记录的编号，例如：

    15A - Erica - Avenue
    15B - Erica - Avenue

这给了我想要的上述输出，我该如何存档？

这是我的代码（注意：后缀是 a List<string>）：

static void Main(string[] args)
{
    List<ResultData> result = new List<ResultData>();
    string myColumn = "Level 1/129/1 Murray Ave & 15A&B ERICA AVENUE & 12 HARVEY STREET & 34 VICTORIA STREET & 3/56 ST LEONARDS ST, MOSMAN PARK ( John).  78/10 WELLINGTON ST MOSMAN PARK (Rambo)";
    // dot replaced with & as they are to be split
    myColumn = myColumn.Replace('.', '&');
    // I don't need the Level word which means 
    // each property starts with numbers now
    myColumn = myColumn.Replace("Level", "");
    // Removes anything in between parentheses and the parentheses
    myColumn = RemoveBetween(myColumn, '(', ')');

    string[] splitResult = myColumn.Split('&');    
    foreach (string item in splitResult)
    {
        string property = item.Trim();
        if (property.IndexOf(' ') > 0)
        {
            string area = string.Empty;
            string locationType = string.Empty;
            string number = property.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).First();
            property = property.Replace(number, "").Trim();

            // When comma is present, area is always the last
            // and locationType always before it
            if (property.IndexOf(',') > 0)
            {
                area = property.Split(new[] { ',' }, StringSplitOptions.RemoveEmptyEntries).Last().Trim();
                property = property.Replace(area, "").Replace(",", "").Trim();

                locationType = property.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).Last().Trim();
                property = property.Replace(" " + locationType, "").Trim();
            }
            else
            {
                // When comma is not present I have to check
                // if the string contains a given street suffix
                // and pick up from there
                string found = suffixes.Find(x => property.Trim().Contains(" " + x, StringComparison.OrdinalIgnoreCase));
                if (!string.IsNullOrEmpty(found))
                    found = " " + found; 
                    // need the space otherwise it will delete 
                    // places like ST LEONARD.

                locationType = property.Substring(property.ToLower().IndexOf(found.ToLower()), found.Length).Trim();

                int total = property.ToLower().IndexOf(found.ToLower()) + found.Length;
                if (property.ToLower().IndexOf(found.ToLower()) > 0 && total < property.Length)
                    area = property.Substring(total, property.Length - total).Trim();

                property = property.Replace(",", "").Trim().Replace(locationType, "").Trim();
                if (!string.IsNullOrEmpty(area))
                    property = property.Replace(area, "").Trim();
            }

            string name = property;
            result.Add(new ResultData() { Number = number, Name = name, LocationType = locationType, Area = area });
        }
        else
        {
            result.Add(new ResultData() { Number = property });
        }
    }

    string save = string.Empty;
    foreach (ResultData item in result)
    {
        Console.WriteLine(item.Number + " - " + item.Name + " - " + item.LocationType + " - " + item.Area);
        save += item.Number + " - " + item.Name + " - " + item.LocationType + " - " + item.Area + Environment.NewLine;
    }
    System.IO.File.WriteAllLines(@"save.txt", save.Split(new string[] { Environment.NewLine }, StringSplitOptions.RemoveEmptyEntries));

    Console.WriteLine(Environment.NewLine + "Press any key to leave...");
    Console.ReadKey();
}

/// <summary>
/// Remove from the string the pattern and what is in between it 
/// more format double space to single
/// </summary>
static string RemoveBetween(string s, char begin, char end)
{
    Regex regex = new Regex(string.Format("\\{0}.*?\\{1}", begin, end));
    return new Regex(" +").Replace(regex.Replace(s, string.Empty), " ");
}

public static bool Contains(this string source, string toCheck, StringComparison comp)
{
    return source.IndexOf(toCheck, comp) >= 0;
}

如果你知道我可以做些什么来改进上面的代码也很想知道，给我写评论。

4

2 回答 2

0

这段代码应该可以完成这项工作：

  string prevString = "";
  string[] splitResult = myColumn.Split('&');    
  foreach (string item in splitResult)
    {
        string property = item.Trim();
        if (property.IndexOf(' ') > 0)
        {
            string area = string.Empty;
            string locationType = string.Empty;
            string number = property.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).First();
            property = property.Replace(number, "").Trim();

            // When comma is present, area is always the last
            // and locationType always before it
            if (property.IndexOf(',') > 0)
            {
                area = property.Split(new[] { ',' }, StringSplitOptions.RemoveEmptyEntries).Last().Trim();
                property = property.Replace(area, "").Replace(",", "").Trim();

                locationType = property.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries).Last().Trim();
                property = property.Replace(" " + locationType, "").Trim();
            }
            else
            {
                // When comma is not present I have to check
                // if the string contains a given street suffix
                // and pick up from there
                string found = suffixes.Find(x => property.Trim().Contains(" " + x, StringComparison.OrdinalIgnoreCase));
                if (!string.IsNullOrEmpty(found))
                    found = " " + found; 
                    // need the space otherwise it will delete 
                    // places like ST LEONARD.

                locationType = property.Substring(property.ToLower().IndexOf(found.ToLower()), found.Length).Trim();

                int total = property.ToLower().IndexOf(found.ToLower()) + found.Length;
                if (property.ToLower().IndexOf(found.ToLower()) > 0 && total < property.Length)
                    area = property.Substring(total, property.Length - total).Trim();

                property = property.Replace(",", "").Trim().Replace(locationType, "").Trim();
                if (!string.IsNullOrEmpty(area))
                    property = property.Replace(area, "").Trim();
            }

                string name = property;
                if (prevString != "")
                {
                    result.Add(new ResultData() { Number = prevString, Name = name, LocationType = locationType, Area = area });
                    string numbersFromString = new String(number.Where(x => x >= '0' && x <= '9').ToArray());
                    if (numbersFromString == "")
                    {
                        string numbersFromString2 = new String(prevString.Where(x => x >= '0' && x <= '9').ToArray());
                        result.Add(new ResultData() { Number = (int)numbersFromString2 + number, Name = name, LocationType = locationType, Area = area });
                    }
                    else
                    {
                        result.Add(new ResultData() { Number = number, Name = name, LocationType = locationType, Area = area });
                    }

                }
                else
                {
                    result.Add(new ResultData() { Number = number, Name = name, LocationType = locationType, Area = area });
                }


                prevString = "";
        }
        else
        {
            prevString = property;
        }
    }
于 2013-06-19T13:30:39.110 回答
-1

看起来每行都以空格开头，然后是数字。

因此，在您进行任何其他处理之前，这可能是一个更简单的第一次清理。

       var myString = "Line: 12 this way 23 that way 34 no way".ToCharArray();
        var firstDigitFound = false;
        for (int i = 0; i < myString.Length; i++)
        {                
            var isNumber = char.IsNumber(myString[i]);
            if (isNumber && i > 0 && !firstDigitFound)
            {
                firstDigitFound = true;
                myString[i - 1] = '|';
            }
            else { firstDigitFound = false; }
        }

        var myNewArray = new string(myString).Split('|');
于 2013-06-19T13:15:41.693 回答