在 C# 中比较文本文件并删除重复行
Compare text files in C# and remove duplicate lines
1.txt:
始发地、目的地、日期时间、价格
YYZ,YTC,2016-04-01 12:30,0
YYZ,YTC,2016-04-01 12:30,0
LKC,LKP,2016-04-01 12:30,0
2.txt:
始发地|目的地|日期时间|价格
YYZ|YTC|2016-04-01 12:30|0
AMV|YRk|2016-06-01 12:30|0
LKC|LKP|2016-12-01 12:30|0
我有两个带有“,”和“|”的文本文件作为分隔符,我想在 C# 中创建一个控制台应用程序,它在我从命令提示符传递起始位置和目标位置时读取这两个文件。
搜索时,我想忽略重复行,我想按价格顺序显示结果。
输出应该是{ origination } -> { destination } -> datetime -> price
需要帮助如何执行。
我不是 100% 清楚你的程序的输出应该是什么,所以我将把这部分实现留给你。我的策略是使用一个构造函数方法,该方法接受一个字符串(您将从文件中读取)和一个定界符(因为它会变化)并使用它来创建您可以操作的对象(例如添加到哈希集等)。
PriceObject.cs
using System;
using System.Globalization;
namespace ConsoleApplication1
{
class PriceObject
{
public string origination { get; set; }
public string destination { get; set; }
public DateTime time { get; set; }
public decimal price { get; set; }
public PriceObject(string inputLine, char delimiter)
{
string[] parsed = inputLine.Split(new char[] { delimiter }, 4);
origination = parsed[0];
destination = parsed[1];
time = DateTime.ParseExact(parsed[2], "yyyy-MM-dd HH:mm", CultureInfo.InvariantCulture);
price = Decimal.Parse(parsed[3], NumberStyles.Currency, new CultureInfo("en-US"));
}
public override bool Equals(object obj)
{
var item = obj as PriceObject;
return origination.Equals(item.origination) &&
destination.Equals(item.destination) &&
time.Equals(item.time) &&
price.Equals(item.price);
}
public override int GetHashCode()
{
unchecked
{
var result = 17;
result = (result * 23) + origination.GetHashCode();
result = (result * 23) + destination.GetHashCode();
result = (result * 23) + time.GetHashCode();
result = (result * 23) + price.GetHashCode();
return result;
}
}
}
}
Program.cs
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
namespace ConsoleApplication1
{
class Program
{
static void Main(string[] args)
{
HashSet<PriceObject> list1 = new HashSet<PriceObject>();
HashSet<PriceObject> list2 = new HashSet<PriceObject>();
using (StreamReader reader = File.OpenText(args[0]))
{
string line = reader.ReadLine(); // this will remove the header row
while (!reader.EndOfStream)
{
line = reader.ReadLine();
if (String.IsNullOrEmpty(line))
continue;
// add each line to our list
list1.Add(new PriceObject(line, ','));
}
}
using (StreamReader reader = File.OpenText(args[1]))
{
string line = reader.ReadLine(); // this will remove the header row
while (!reader.EndOfStream)
{
line = reader.ReadLine();
if (String.IsNullOrEmpty(line))
continue;
// add each line to our list
list2.Add(new PriceObject(line, '|'));
}
}
// merge the two hash sets, order by price
list1.UnionWith(list2);
List<PriceObject> output = list1.ToList();
output.OrderByDescending(x => x.price).ToList();
// display output here, e.g. define your own ToString method, etc
foreach (var item in output)
{
Console.WriteLine(item.ToString());
}
Console.ReadLine();
}
}
}
这是一个适用于您的示例文件的简单解决方案。它不会检查文件格式是否错误。
using System;
using System.Collections.Generic;
class Program
{
class entry
{
public string origin;
public string destination;
public DateTime time;
public double price;
}
static void Main(string[] args)
{
List<entry> data = new List<entry>();
//parse the input files and add the data to a list
ParseFile(data, args[0], ',');
ParseFile(data, args[1], '|');
//sort the list (by price first)
data.Sort((a, b) =>
{
if (a.price != b.price)
return a.price > b.price ? 1 : -1;
else if (a.origin != b.origin)
return string.Compare(a.origin, b.origin);
else if (a.destination != b.destination)
return string.Compare(a.destination, b.destination);
else
return DateTime.Compare(a.time, b.time);
});
//remove duplicates (list must be sorted for this to work)
int i = 1;
while (i < data.Count)
{
if (data[i].origin == data[i - 1].origin
&& data[i].destination == data[i - 1].destination
&& data[i].time == data[i - 1].time
&& data[i].price == data[i - 1].price)
data.RemoveAt(i);
else
i++;
}
//print the results
for (i = 0; i < data.Count; i++)
Console.WriteLine("{0}->{1}->{2:yyyy-MM-dd HH:mm}->",
data[i].origin, data[i].destination, data[i].time, data[i].price);
Console.ReadLine();
}
private static void ParseFile(List<entry> data, string filename, char separator)
{
using (System.IO.FileStream fs = System.IO.File.Open(filename, System.IO.FileMode.Open))
using (System.IO.StreamReader reader = new System.IO.StreamReader(fs))
while (!reader.EndOfStream)
{
string[] line = reader.ReadLine().Split(separator);
if (line.Length == 4)
{
entry newitem = new entry();
newitem.origin = line[0];
newitem.destination = line[1];
newitem.time = DateTime.Parse(line[2]);
newitem.price = double.Parse(line[3].Substring(line[3].IndexOf('$') + 1));
data.Add(newitem);
}
}
}
}
1.txt:
始发地、目的地、日期时间、价格
YYZ,YTC,2016-04-01 12:30,0
YYZ,YTC,2016-04-01 12:30,0
LKC,LKP,2016-04-01 12:30,0
2.txt:
始发地|目的地|日期时间|价格
YYZ|YTC|2016-04-01 12:30|0
AMV|YRk|2016-06-01 12:30|0
LKC|LKP|2016-12-01 12:30|0
我有两个带有“,”和“|”的文本文件作为分隔符,我想在 C# 中创建一个控制台应用程序,它在我从命令提示符传递起始位置和目标位置时读取这两个文件。
搜索时,我想忽略重复行,我想按价格顺序显示结果。
输出应该是{ origination } -> { destination } -> datetime -> price
需要帮助如何执行。
我不是 100% 清楚你的程序的输出应该是什么,所以我将把这部分实现留给你。我的策略是使用一个构造函数方法,该方法接受一个字符串(您将从文件中读取)和一个定界符(因为它会变化)并使用它来创建您可以操作的对象(例如添加到哈希集等)。
PriceObject.cs
using System;
using System.Globalization;
namespace ConsoleApplication1
{
class PriceObject
{
public string origination { get; set; }
public string destination { get; set; }
public DateTime time { get; set; }
public decimal price { get; set; }
public PriceObject(string inputLine, char delimiter)
{
string[] parsed = inputLine.Split(new char[] { delimiter }, 4);
origination = parsed[0];
destination = parsed[1];
time = DateTime.ParseExact(parsed[2], "yyyy-MM-dd HH:mm", CultureInfo.InvariantCulture);
price = Decimal.Parse(parsed[3], NumberStyles.Currency, new CultureInfo("en-US"));
}
public override bool Equals(object obj)
{
var item = obj as PriceObject;
return origination.Equals(item.origination) &&
destination.Equals(item.destination) &&
time.Equals(item.time) &&
price.Equals(item.price);
}
public override int GetHashCode()
{
unchecked
{
var result = 17;
result = (result * 23) + origination.GetHashCode();
result = (result * 23) + destination.GetHashCode();
result = (result * 23) + time.GetHashCode();
result = (result * 23) + price.GetHashCode();
return result;
}
}
}
}
Program.cs
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
namespace ConsoleApplication1
{
class Program
{
static void Main(string[] args)
{
HashSet<PriceObject> list1 = new HashSet<PriceObject>();
HashSet<PriceObject> list2 = new HashSet<PriceObject>();
using (StreamReader reader = File.OpenText(args[0]))
{
string line = reader.ReadLine(); // this will remove the header row
while (!reader.EndOfStream)
{
line = reader.ReadLine();
if (String.IsNullOrEmpty(line))
continue;
// add each line to our list
list1.Add(new PriceObject(line, ','));
}
}
using (StreamReader reader = File.OpenText(args[1]))
{
string line = reader.ReadLine(); // this will remove the header row
while (!reader.EndOfStream)
{
line = reader.ReadLine();
if (String.IsNullOrEmpty(line))
continue;
// add each line to our list
list2.Add(new PriceObject(line, '|'));
}
}
// merge the two hash sets, order by price
list1.UnionWith(list2);
List<PriceObject> output = list1.ToList();
output.OrderByDescending(x => x.price).ToList();
// display output here, e.g. define your own ToString method, etc
foreach (var item in output)
{
Console.WriteLine(item.ToString());
}
Console.ReadLine();
}
}
}
这是一个适用于您的示例文件的简单解决方案。它不会检查文件格式是否错误。
using System;
using System.Collections.Generic;
class Program
{
class entry
{
public string origin;
public string destination;
public DateTime time;
public double price;
}
static void Main(string[] args)
{
List<entry> data = new List<entry>();
//parse the input files and add the data to a list
ParseFile(data, args[0], ',');
ParseFile(data, args[1], '|');
//sort the list (by price first)
data.Sort((a, b) =>
{
if (a.price != b.price)
return a.price > b.price ? 1 : -1;
else if (a.origin != b.origin)
return string.Compare(a.origin, b.origin);
else if (a.destination != b.destination)
return string.Compare(a.destination, b.destination);
else
return DateTime.Compare(a.time, b.time);
});
//remove duplicates (list must be sorted for this to work)
int i = 1;
while (i < data.Count)
{
if (data[i].origin == data[i - 1].origin
&& data[i].destination == data[i - 1].destination
&& data[i].time == data[i - 1].time
&& data[i].price == data[i - 1].price)
data.RemoveAt(i);
else
i++;
}
//print the results
for (i = 0; i < data.Count; i++)
Console.WriteLine("{0}->{1}->{2:yyyy-MM-dd HH:mm}->",
data[i].origin, data[i].destination, data[i].time, data[i].price);
Console.ReadLine();
}
private static void ParseFile(List<entry> data, string filename, char separator)
{
using (System.IO.FileStream fs = System.IO.File.Open(filename, System.IO.FileMode.Open))
using (System.IO.StreamReader reader = new System.IO.StreamReader(fs))
while (!reader.EndOfStream)
{
string[] line = reader.ReadLine().Split(separator);
if (line.Length == 4)
{
entry newitem = new entry();
newitem.origin = line[0];
newitem.destination = line[1];
newitem.time = DateTime.Parse(line[2]);
newitem.price = double.Parse(line[3].Substring(line[3].IndexOf('$') + 1));
data.Add(newitem);
}
}
}
}