c# - 从流式阅读器读取一行而不消耗？

Question

有没有办法提前读一行来测试下一行是否包含特定的标签数据？

我正在处理一种有开始标签但没有结束标签的格式。

我想阅读一行将其添加到结构中，然后测试下面的行以确保它不是新的“节点”，如果它关闭该结构并创建一个新的，则如果它没有继续添加

我能想到的唯一解决方案是让两个流阅读器同时进行锁定步骤，​​但这似乎很浪费（如果它甚至可以工作的话）

我需要像 peek 但 peekline 这样的东西

Answer 1

问题是底层流甚至可能不可搜索。如果您查看流读取器实现，它使用缓冲区，因此即使流不可搜索，它也可以实现 TextReader.Peek() 。

您可以编写一个简单的适配器来读取下一行并在内部对其进行缓冲，如下所示：

 public class PeekableStreamReaderAdapter
    {
        private StreamReader Underlying;
        private Queue<string> BufferedLines;

        public PeekableStreamReaderAdapter(StreamReader underlying)
        {
            Underlying = underlying;
            BufferedLines = new Queue<string>();
        }

        public string PeekLine()
        {
            string line = Underlying.ReadLine();
            if (line == null)
                return null;
            BufferedLines.Enqueue(line);
            return line;
        }


        public string ReadLine()
        {
            if (BufferedLines.Count > 0)
                return BufferedLines.Dequeue();
            return Underlying.ReadLine();
        }
    }

Answer 2

您可以存储访问 StreamReader.BaseStream.Position 的位置，然后读取下一行，进行测试，然后在读取该行之前找到该位置：

            // Peek at the next line
            long peekPos = reader.BaseStream.Position;
            string line = reader.ReadLine();

            if (line.StartsWith("<tag start>"))
            {
                // This is a new tag, so we reset the position
                reader.BaseStream.Seek(pos);    

            }
            else
            {
                // This is part of the same node.
            }

这是很多寻找和重新阅读相同的行。使用一些逻辑，您可以完全避免这种情况 - 例如，当您看到一个新标签开始时，关闭现有结构并开始一个新结构 - 这是一个基本算法：

        SomeStructure myStructure = null;
        while (!reader.EndOfStream)
        {
            string currentLine = reader.ReadLine();
            if (currentLine.StartsWith("<tag start>"))
            {
                // Close out existing structure.
                if (myStructure != null)
                {
                    // Close out the existing structure.
                }

                // Create a new structure and add this line.
                myStructure = new Structure();                   
                // Append to myStructure.
            }
            else
            {
                // Add to the existing structure.
                if (myStructure != null)
                {
                    // Append to existing myStructure
                }
                else
                {
                    // This means the first line was not part of a structure.
                    // Either handle this case, or throw an exception.
                }
            }
        }

Answer 3

为什么困难重重？无论如何都返回下一行。检查它是否是一个新节点，如果不是，将其添加到结构中。如果是，则创建一个新结构。

// Not exactly C# but close enough
Collection structs = new Collection();
Struct struct;
while ((line = readline()) != null)) {
    if (IsNode(line)) {
        if (struct != null) structs.add(struct);
        struct = new Struct();
        continue;
    }
    // Whatever processing you need to do
    struct.addLine(line);
}
structs.add(struct); // Add the last one to the collection

// Use your structures here
foreach s in structs {

}

Answer 4

这是我到目前为止所做的。我走的分割路线比逐行路线的流式阅读器要多。

我敢肯定，有一些地方正在变得更加优雅，但现在它似乎正在发挥作用。

请让我知道你在想什么

struct INDI
    {
        public string ID;
        public string Name;
        public string Sex;
        public string BirthDay;
        public bool Dead;


    }
    struct FAM
    {
        public string FamID;
        public string type;
        public string IndiID;
    }
    List<INDI> Individuals = new List<INDI>();
    List<FAM> Family = new List<FAM>();
    private void button1_Click(object sender, EventArgs e)
    {
        string path = @"C:\mostrecent.ged";
        ParseGedcom(path);
    }

    private void ParseGedcom(string path)
    {
        //Open path to GED file
        StreamReader SR = new StreamReader(path);

        //Read entire block and then plit on 0 @ for individuals and familys (no other info is needed for this instance)
        string[] Holder = SR.ReadToEnd().Replace("0 @", "\u0646").Split('\u0646');

        //For each new cell in the holder array look for Individuals and familys
        foreach (string Node in Holder)
        {

            //Sub Split the string on the returns to get a true block of info
            string[] SubNode = Node.Replace("\r\n", "\r").Split('\r');
            //If a individual is found
            if (SubNode[0].Contains("INDI"))
            {
                //Create new Structure
                INDI I = new INDI();
                //Add the ID number and remove extra formating
                I.ID = SubNode[0].Replace("@", "").Replace(" INDI", "").Trim();
                //Find the name remove extra formating for last name
                I.Name = SubNode[FindIndexinArray(SubNode, "NAME")].Replace("1 NAME", "").Replace("/", "").Trim(); 
                //Find Sex and remove extra formating
                I.Sex = SubNode[FindIndexinArray(SubNode, "SEX")].Replace("1 SEX ", "").Trim();

                //Deterine if there is a brithday -1 means no
                if (FindIndexinArray(SubNode, "1 BIRT ") != -1)
                {
                    // add birthday to Struct 
                    I.BirthDay = SubNode[FindIndexinArray(SubNode, "1 BIRT ") + 1].Replace("2 DATE ", "").Trim();
                }

                // deterimin if there is a death tag will return -1 if not found
                if (FindIndexinArray(SubNode, "1 DEAT ") != -1)
                {
                    //convert Y or N to true or false ( defaults to False so no need to change unless Y is found.
                    if (SubNode[FindIndexinArray(SubNode, "1 DEAT ")].Replace("1 DEAT ", "").Trim() == "Y")
                    {
                        //set death
                        I.Dead = true;
                    }
                }
                //add the Struct to the list for later use
                Individuals.Add(I);
            }

            // Start Family section
            else if (SubNode[0].Contains("FAM"))
            {
                //grab Fam id from node early on to keep from doing it over and over
                string FamID = SubNode[0].Replace("@ FAM", "");

                // Multiple children can exist for each family so this section had to be a bit more dynaimic

                // Look at each line of node
                foreach (string Line in SubNode)
                {
                    // If node is HUSB
                    if (Line.Contains("1 HUSB "))
                    {

                        FAM F = new FAM();
                        F.FamID = FamID;
                        F.type = "PAR";
                        F.IndiID = Line.Replace("1 HUSB ", "").Replace("@","").Trim();
                        Family.Add(F);
                    }
                        //If node for Wife
                    else if (Line.Contains("1 WIFE "))
                    {
                        FAM F = new FAM();
                        F.FamID = FamID;
                        F.type = "PAR";
                        F.IndiID = Line.Replace("1 WIFE ", "").Replace("@", "").Trim();
                        Family.Add(F);
                    }
                        //if node for multi children
                    else if (Line.Contains("1 CHIL "))
                    {
                        FAM F = new FAM();
                         F.FamID = FamID;
                        F.type = "CHIL";
                        F.IndiID = Line.Replace("1 CHIL ", "").Replace("@", "");
                        Family.Add(F);
                    }
                }
            }
        }
    }

    private int FindIndexinArray(string[] Arr, string search)
    {
        int Val = -1;
        for (int i = 0; i < Arr.Length; i++)
        {
            if (Arr[i].Contains(search))
            {
                Val = i;
            }
        }
        return Val;
    }