|
|
using System;
|
|
|
using System.Collections.Generic;
|
|
|
using System.Data;
|
|
|
using System.IO;
|
|
|
using System.IO.MemoryMappedFiles;
|
|
|
using System.Linq;
|
|
|
using System.Text;
|
|
|
using System.Threading.Tasks;
|
|
|
using WorkData.Entity;
|
|
|
|
|
|
#region 文件说明
|
|
|
/*-----------------------------------------------------
|
|
|
* 版权所有 （c） 2024 jdfcd
|
|
|
* CLR版本 4.0.30319.42000
|
|
|
* 命名空间 DQ.Construction.NewLook.Utility
|
|
|
*
|
|
|
* 创建者：pnpe
|
|
|
* 电子邮件：pnpe@qq.com
|
|
|
* 创建时间：2024/12/31 10:38:45
|
|
|
*/
|
|
|
#endregion 文件说明
|
|
|
namespace InterfaceWorkAreaData.LoadCurveData
|
|
|
{
|
|
|
public class LasHelper
|
|
|
{
|
|
|
//读取las
|
|
|
public static ResultDataInfo LasFileToDataTable(ref DataTable table, string filename, string charset, int rowindex)
|
|
|
{
|
|
|
ResultDataInfo result = new ResultDataInfo();
|
|
|
List<string> columnNames = new List<string>();
|
|
|
try
|
|
|
{
|
|
|
long length = new FileInfo(filename).Length;
|
|
|
using (MemoryMappedFile mmf = MemoryMappedFile.CreateFromFile(filename, FileMode.Open, Guid.NewGuid().ToString()))
|
|
|
using (MemoryMappedViewStream stream = mmf.CreateViewStream(0, length))
|
|
|
using (StreamReader reader = new StreamReader(stream, Encoding.GetEncoding(charset)))
|
|
|
{
|
|
|
int lineindex = 0;
|
|
|
bool isReadHeader = false;
|
|
|
bool isReadBody = false;
|
|
|
string strLine = string.Empty;
|
|
|
while (!reader.EndOfStream)
|
|
|
{
|
|
|
string str = reader.ReadLine();
|
|
|
if (string.IsNullOrWhiteSpace(str))
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
else if (str.StartsWith("~C") || str.StartsWith("~Curve"))
|
|
|
{
|
|
|
isReadHeader = true;
|
|
|
continue;
|
|
|
}
|
|
|
else if (!isReadHeader)
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
else if (str.StartsWith("~A") || str.StartsWith("~Ascii"))
|
|
|
{
|
|
|
isReadBody = true;
|
|
|
table.Columns.Clear();
|
|
|
if (columnNames.Count == 0)
|
|
|
{
|
|
|
result.Code = 0;
|
|
|
result.Msg = $"文件{filename}列读取失败,已跳过文件,{Environment.NewLine}";
|
|
|
return result;
|
|
|
}
|
|
|
//说明表头写完了
|
|
|
for (int i = 0; i < columnNames.Count; i++)
|
|
|
{
|
|
|
table.Columns.Add(columnNames[i]);
|
|
|
}
|
|
|
continue;
|
|
|
}
|
|
|
if (isReadHeader && !isReadBody)
|
|
|
{
|
|
|
//判断表头，对于小数点处理和冒号处理
|
|
|
string colName = str.Replace(":", string.Empty);
|
|
|
colName = colName.Split('.')[0];
|
|
|
if (colName.StartsWith("#"))
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
colName = colName.Trim().ToUpper();
|
|
|
if (!columnNames.Contains(colName))
|
|
|
{
|
|
|
columnNames.Add(colName);
|
|
|
}
|
|
|
else
|
|
|
{
|
|
|
//存在重复列名
|
|
|
table.Columns.Clear();
|
|
|
result.Code = 0;
|
|
|
result.Msg = $"文件{filename}存在重复列名{colName},已跳过文件,{Environment.NewLine}";
|
|
|
return result;
|
|
|
}
|
|
|
continue;
|
|
|
}
|
|
|
strLine = str;
|
|
|
string trimString = string.Join(",", strLine.Split(new[] { "\r", "\t", "\0", " " }, StringSplitOptions.RemoveEmptyEntries));
|
|
|
string[] array = trimString.Split(new[] { "\r", "\t", "\0", ",", ";", " " }, StringSplitOptions.None);
|
|
|
if (array.Length != columnNames.Count)
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
if (array.Length > 0)
|
|
|
{
|
|
|
table.Rows.Add(array);
|
|
|
}
|
|
|
lineindex++;
|
|
|
}
|
|
|
}
|
|
|
}
|
|
|
catch (Exception e)
|
|
|
{
|
|
|
result.Code = 0;
|
|
|
result.Msg = e.Message;
|
|
|
Console.WriteLine(e.ToString());
|
|
|
}
|
|
|
result.Code = 1;
|
|
|
return result;
|
|
|
}
|
|
|
|
|
|
/// <summary>
|
|
|
/// las文件转List<WellCurve>
|
|
|
/// </summary>
|
|
|
public static IEnumerable<WellCurve> LasFileToList(string jh, string filename, string charset)
|
|
|
{
|
|
|
if (!File.Exists(filename))
|
|
|
{
|
|
|
yield break;
|
|
|
}
|
|
|
|
|
|
using (MemoryMappedFile mmf = MemoryMappedFile.CreateFromFile(filename, FileMode.Open, Guid.NewGuid().ToString()))
|
|
|
using (MemoryMappedViewStream stream = mmf.CreateViewStream(0, new FileInfo(filename).Length))
|
|
|
using (StreamReader reader = new StreamReader(stream, Encoding.GetEncoding(charset)))
|
|
|
{
|
|
|
List<string> columnNames = new List<string>();
|
|
|
bool isReadHeader = false;
|
|
|
bool isReadBody = false;
|
|
|
|
|
|
while (!reader.EndOfStream)
|
|
|
{
|
|
|
string str = reader.ReadLine();
|
|
|
if (string.IsNullOrWhiteSpace(str))
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
if (str.StartsWith("~C") || str.StartsWith("~Curve"))
|
|
|
{
|
|
|
isReadHeader = true;
|
|
|
continue;
|
|
|
}
|
|
|
else if (!isReadHeader)
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
else if (str.StartsWith("~A") || str.StartsWith("~Ascii"))
|
|
|
{
|
|
|
isReadBody = true;
|
|
|
if (columnNames.Count == 0)
|
|
|
{
|
|
|
throw new Exception($"文件{filename} 列名为空！");
|
|
|
}
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
if (isReadHeader && !isReadBody)
|
|
|
{
|
|
|
string colName = str.Replace(":", string.Empty);
|
|
|
colName = colName.Split('.')[0];
|
|
|
if (colName.StartsWith("#"))
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
colName = colName.Trim().ToUpper();
|
|
|
|
|
|
if (!columnNames.Contains(colName))
|
|
|
{
|
|
|
columnNames.Add(colName);
|
|
|
}
|
|
|
else
|
|
|
{
|
|
|
throw new Exception($"文件{filename} 存在重复列名：{colName}");
|
|
|
}
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
// 数据体
|
|
|
string trimString = string.Join(",", str.Split(new[] { "\r", "\t", "\0", " " }, StringSplitOptions.RemoveEmptyEntries));
|
|
|
string[] array = trimString.Split(new[] { "\r", "\t", "\0", ",", ";", " " }, StringSplitOptions.None);
|
|
|
|
|
|
if (array.Length != columnNames.Count)
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
if (!double.TryParse(array[0], out double depth))
|
|
|
{
|
|
|
continue;
|
|
|
}
|
|
|
|
|
|
var dic = new Dictionary<string, string>();
|
|
|
for (int i = 1; i < array.Length; i++)
|
|
|
{
|
|
|
dic[columnNames[i]] = array[i];
|
|
|
}
|
|
|
|
|
|
yield return new WellCurve
|
|
|
{
|
|
|
JH = jh,
|
|
|
DEPTH = depth,
|
|
|
ColumnValues = dic,
|
|
|
};
|
|
|
}
|
|
|
}
|
|
|
}
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
/// 给定文件的路径，读取文件的二进制数据，判断文件的编码类型
|
|
|
/// </summary>
|
|
|
/// <param name="fileName">文件路径</param>
|
|
|
/// <returns>文件的编码类型</returns>
|
|
|
public static System.Text.Encoding GetType(string fileName)
|
|
|
{
|
|
|
FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read);
|
|
|
Encoding r = GetType(fs);
|
|
|
fs.Close();
|
|
|
return r;
|
|
|
}
|
|
|
|
|
|
public static System.Text.Encoding GetType(FileStream fs)
|
|
|
{
|
|
|
byte[] unicode = new byte[] { 0xFF, 0xFE, 0x41 };
|
|
|
byte[] unicodeBIG = new byte[] { 0xFE, 0xFF, 0x00 };
|
|
|
byte[] uTF8 = new byte[] { 0xEF, 0xBB, 0xBF }; // 带BOM
|
|
|
|
|
|
BinaryReader r = new BinaryReader(fs, System.Text.Encoding.Default);
|
|
|
int i;
|
|
|
int.TryParse(fs.Length.ToString(), out i);
|
|
|
byte[] ss = r.ReadBytes(i);
|
|
|
Encoding reVal = GetType(ss);
|
|
|
r.Close();
|
|
|
return reVal;
|
|
|
}
|
|
|
|
|
|
|
|
|
/// <summary>
|
|
|
/// 获得格式编码
|
|
|
/// </summary>
|
|
|
/// <param name="data">数据内容</param>
|
|
|
/// <returns>编码</returns>
|
|
|
public static System.Text.Encoding GetType(byte[] data)
|
|
|
{
|
|
|
Encoding reVal = Encoding.Default;
|
|
|
if (IsUTF8Bytes(data) || (data[0] == 0xEF && data[1] == 0xBB && data[2] == 0xBF))
|
|
|
{
|
|
|
reVal = Encoding.UTF8;
|
|
|
}
|
|
|
else if (data[0] == 0xFE && data[1] == 0xFF && data[2] == 0x00)
|
|
|
{
|
|
|
reVal = Encoding.BigEndianUnicode;
|
|
|
}
|
|
|
else if (data[0] == 0xFF && data[1] == 0xFE && data[2] == 0x41)
|
|
|
{
|
|
|
reVal = Encoding.Unicode;
|
|
|
}
|
|
|
return reVal;
|
|
|
}
|
|
|
/// <summary>
|
|
|
/// 判断是否是不带 BOM 的 UTF8 格式
|
|
|
/// </summary>
|
|
|
/// <param name="data">数据</param>
|
|
|
/// <returns>是否UTF8</returns>
|
|
|
private static bool IsUTF8Bytes(byte[] data)
|
|
|
{
|
|
|
int charByteCounter = 1;
|
|
|
// 计算当前正分析的字符应还有的字节数
|
|
|
byte curByte; // 当前分析的字节.
|
|
|
for (int i = 0; i < data.Length; i++)
|
|
|
{
|
|
|
curByte = data[i];
|
|
|
if (charByteCounter == 1)
|
|
|
{
|
|
|
if (curByte >= 0x80)
|
|
|
{
|
|
|
// 判断当前
|
|
|
while (((curByte <<= 1) & 0x80) != 0)
|
|
|
{
|
|
|
charByteCounter++;
|
|
|
}
|
|
|
// 标记位首位若为非0 则至少以2个1开始 如:110XXXXX...........1111110X
|
|
|
if (charByteCounter == 1 || charByteCounter > 6)
|
|
|
{
|
|
|
return false;
|
|
|
}
|
|
|
}
|
|
|
}
|
|
|
else
|
|
|
{
|
|
|
// 若是UTF-8 此时第一位必须为1
|
|
|
if ((curByte & 0xC0) != 0x80)
|
|
|
{
|
|
|
return false;
|
|
|
}
|
|
|
charByteCounter--;
|
|
|
}
|
|
|
}
|
|
|
if (charByteCounter > 1)
|
|
|
{
|
|
|
throw new Exception("非预期的byte格式");
|
|
|
}
|
|
|
return true;
|
|
|
}
|
|
|
}
|
|
|
|
|
|
public class ResultDataInfo
|
|
|
{
|
|
|
public int Code { get; set; }
|
|
|
public string Msg { get; set; }
|
|
|
public object Data { get; set; }
|
|
|
}
|
|
|
}
|