672 lines
27 KiB
C#
672 lines
27 KiB
C#
using Adaptation.Shared;
|
|
using Adaptation.Shared.Methods;
|
|
using log4net;
|
|
using System;
|
|
using System.Collections.Generic;
|
|
using System.Data;
|
|
using System.Diagnostics;
|
|
using System.Globalization;
|
|
using System.IO;
|
|
using System.Linq;
|
|
using System.Text;
|
|
using System.Text.Json;
|
|
using System.Text.RegularExpressions;
|
|
|
|
namespace Adaptation.FileHandlers.pcl;
|
|
|
|
public class ProcessData : IProcessData
|
|
{
|
|
|
|
private int _I;
|
|
private string _Data;
|
|
|
|
private readonly ILog _Log;
|
|
private readonly List<object> _Details;
|
|
|
|
public string JobID { get; set; }
|
|
public string MesEntity { get; set; }
|
|
public string AreaCountAvg { get; set; }
|
|
public string AreaCountMax { get; set; }
|
|
public string AreaCountMin { get; set; }
|
|
public string AreaCountStdDev { get; set; }
|
|
public string AreaTotalAvg { get; set; }
|
|
public string AreaTotalMax { get; set; }
|
|
public string AreaTotalMin { get; set; }
|
|
public string AreaTotalStdDev { get; set; }
|
|
public string Date { get; set; }
|
|
public string HazeAverageAvg { get; set; }
|
|
public string HazeAverageMax { get; set; }
|
|
public string HazeAverageMin { get; set; }
|
|
public string HazeAverageStdDev { get; set; }
|
|
public string HazeRegionAvg { get; set; }
|
|
public string HazeRegionMax { get; set; }
|
|
public string HazeRegionMin { get; set; }
|
|
public string HazeRegionStdDev { get; set; }
|
|
public string LPDCM2Avg { get; set; }
|
|
public string LPDCM2Max { get; set; }
|
|
public string LPDCM2Min { get; set; }
|
|
public string LPDCM2StdDev { get; set; }
|
|
public string LPDCountAvg { get; set; }
|
|
public string LPDCountMax { get; set; }
|
|
public string LPDCountMin { get; set; }
|
|
public string LPDCountStdDev { get; set; }
|
|
public string Lot { get; set; }
|
|
public string ParseErrorText { get; set; }
|
|
public string PSN { get; set; }
|
|
public string RDS { get; set; }
|
|
public string Reactor { get; set; }
|
|
public string Recipe { get; set; }
|
|
public string ScratchCountAvg { get; set; }
|
|
public string ScratchCountMax { get; set; }
|
|
public string ScratchCountMin { get; set; }
|
|
public string ScratchCountStdDev { get; set; }
|
|
public string ScratchTotalAvg { get; set; }
|
|
public string ScratchTotalMax { get; set; }
|
|
public string ScratchTotalMin { get; set; }
|
|
public string ScratchTotalStdDev { get; set; }
|
|
public string SumOfDefectsAvg { get; set; }
|
|
public string SumOfDefectsMax { get; set; }
|
|
public string SumOfDefectsMin { get; set; }
|
|
public string SumOfDefectsStdDev { get; set; }
|
|
public string UniqueId { get; set; }
|
|
|
|
List<object> Shared.Properties.IProcessData.Details => _Details;
|
|
|
|
public ProcessData(IFileRead fileRead, Logistics logistics, List<FileInfo> fileInfoCollection, string ghostPCLFileName)
|
|
{
|
|
fileInfoCollection.Clear();
|
|
_Details = new List<object>();
|
|
_I = 0;
|
|
_Data = string.Empty;
|
|
JobID = logistics.JobID;
|
|
MesEntity = logistics.MesEntity;
|
|
_Log = LogManager.GetLogger(typeof(ProcessData));
|
|
Parse(fileRead, logistics, fileInfoCollection, ghostPCLFileName);
|
|
}
|
|
|
|
string IProcessData.GetCurrentReactor(IFileRead fileRead, Logistics logistics, Dictionary<string, string> reactors) => throw new Exception(string.Concat("See ", nameof(Parse)));
|
|
|
|
Tuple<string, Test[], JsonElement[], List<FileInfo>> IProcessData.GetResults(IFileRead fileRead, Logistics logistics, List<FileInfo> fileInfoCollection)
|
|
{
|
|
Tuple<string, Test[], JsonElement[], List<FileInfo>> results;
|
|
List<Test> tests = new();
|
|
foreach (object item in _Details)
|
|
tests.Add(Test.Tencor);
|
|
List<IDescription> descriptions = fileRead.GetDescriptions(fileRead, tests, this);
|
|
if (tests.Count != descriptions.Count)
|
|
throw new Exception();
|
|
for (int i = 0; i < tests.Count; i++)
|
|
{
|
|
if (descriptions[i] is not Description description)
|
|
throw new Exception();
|
|
if (description.Test != (int)tests[i])
|
|
throw new Exception();
|
|
}
|
|
List<Description> fileReadDescriptions = (from l in descriptions select (Description)l).ToList();
|
|
string json = JsonSerializer.Serialize(fileReadDescriptions, fileReadDescriptions.GetType());
|
|
JsonElement[] jsonElements = JsonSerializer.Deserialize<JsonElement[]>(json);
|
|
results = new Tuple<string, Test[], JsonElement[], List<FileInfo>>(logistics.Logistics1[0], tests.ToArray(), jsonElements, fileInfoCollection);
|
|
return results;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Test and fix a data line from the Lot Summary page if there are two values that are merged.
|
|
/// </summary>
|
|
/// <param name="toEol">data line from Lot Summary</param>
|
|
private void FixToEolArray(ref string[] toEol)
|
|
{
|
|
const int MAX_COLUMNS = 9;
|
|
int[] mColumnWidths = new int[MAX_COLUMNS] { 8, 6, 6, 6, 6, 7, 7, 5, 7 };
|
|
// is it short at least one data point
|
|
if (toEol.Length < MAX_COLUMNS)
|
|
{
|
|
_Log.Debug($"****FixToEolArray - Starting array:");
|
|
_Log.Debug(toEol);
|
|
_Log.Debug($"****FixToEolArray - Column widths:");
|
|
_Log.Debug(mColumnWidths);
|
|
string leftVal, rightVal;
|
|
|
|
// size up and assign a working list
|
|
List<string> toEolList = new(toEol);
|
|
if (string.IsNullOrEmpty(toEolList[toEolList.Count - 1]))
|
|
toEolList.RemoveAt(toEolList.Count - 1); // removes a null element at end
|
|
_Log.Debug($"****FixToEolArray - New toEolList:");
|
|
_Log.Debug(toEolList);
|
|
for (int i = toEolList.Count; i < MAX_COLUMNS; i++)
|
|
toEolList.Insert(0, ""); // insert to top of list
|
|
_Log.Debug(toEolList);
|
|
|
|
// start at the end
|
|
for (int i = MAX_COLUMNS - 1; i >= 0; i--)
|
|
{
|
|
// test for a bad value - does it have too many characters
|
|
_Log.Debug($"****FixToEolArray - toEolList[i].Length: {toEolList[i].Length}, mColumnWidths[i]: {mColumnWidths[i]}");
|
|
if (toEolList[i].Length > mColumnWidths[i])
|
|
{
|
|
// split it up into its two parts
|
|
leftVal = toEolList[i].Substring(0, toEolList[i].Length - mColumnWidths[i]);
|
|
rightVal = toEolList[i].Substring(leftVal.Length);
|
|
_Log.Debug($"****FixToEolArray - Split leftVal: {leftVal}");
|
|
_Log.Debug($"****FixToEolArray - Split rightVal: {rightVal}");
|
|
|
|
// insert new value
|
|
toEolList[i] = rightVal;
|
|
toEolList.Insert(i, leftVal);
|
|
if (string.IsNullOrEmpty(toEolList[0]))
|
|
toEolList.RemoveAt(0); // removes a null element at end
|
|
_Log.Debug($"****FixToEolArray - Fixed toEolList:");
|
|
_Log.Debug(toEolList);
|
|
}
|
|
}
|
|
toEol = toEolList.ToArray();
|
|
_Log.Debug($"****FixToEolArray - Ending array:");
|
|
_Log.Debug(toEol);
|
|
}
|
|
}
|
|
|
|
private void ScanPast(string text)
|
|
{
|
|
int num = _Data.IndexOf(text, _I);
|
|
if (num > -1)
|
|
_I = num + text.Length;
|
|
else
|
|
_I = _Data.Length;
|
|
}
|
|
|
|
private string GetBefore(string text)
|
|
{
|
|
int num = _Data.IndexOf(text, _I);
|
|
if (num > -1)
|
|
{
|
|
string str = _Data.Substring(_I, num - _I);
|
|
_I = num + text.Length;
|
|
return str.Trim();
|
|
}
|
|
string str1 = _Data.Substring(_I);
|
|
_I = _Data.Length;
|
|
return str1.Trim();
|
|
}
|
|
|
|
private string GetBefore(string text, bool trim)
|
|
{
|
|
if (trim)
|
|
return GetBefore(text);
|
|
int num = _Data.IndexOf(text, _I);
|
|
if (num > -1)
|
|
{
|
|
string str = _Data.Substring(_I, num - _I);
|
|
_I = num + text.Length;
|
|
return str;
|
|
}
|
|
string str1 = _Data.Substring(_I);
|
|
_I = _Data.Length;
|
|
return str1;
|
|
}
|
|
|
|
private static bool IsNullOrWhiteSpace(string text)
|
|
{
|
|
for (int index = 0; index < text.Length; ++index)
|
|
{
|
|
if (!char.IsWhiteSpace(text[index]))
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
private bool IsBlankLine()
|
|
{
|
|
int num = _Data.IndexOf("\n", _I);
|
|
return IsNullOrWhiteSpace(num > -1 ? _Data.Substring(_I, num - _I) : _Data.Substring(_I));
|
|
}
|
|
|
|
private string GetToEOL() => GetBefore("\n");
|
|
|
|
private string GetToEOL(bool trim)
|
|
{
|
|
if (trim)
|
|
return GetToEOL();
|
|
return GetBefore("\n", false);
|
|
}
|
|
|
|
private string GetToText(string text) => _Data.Substring(_I, _Data.IndexOf(text, _I) - _I).Trim();
|
|
|
|
private string GetToken()
|
|
{
|
|
while (_I < _Data.Length && IsNullOrWhiteSpace(_Data.Substring(_I, 1)))
|
|
++_I;
|
|
int j = _I;
|
|
while (j < _Data.Length && !IsNullOrWhiteSpace(_Data.Substring(j, 1)))
|
|
++j;
|
|
string str = _Data.Substring(_I, j - _I);
|
|
_I = j;
|
|
return str.Trim();
|
|
}
|
|
|
|
private string PeekNextLine()
|
|
{
|
|
int j = _I;
|
|
string toEol = GetToEOL();
|
|
_I = j;
|
|
return toEol;
|
|
}
|
|
|
|
private void ParseLotSummary(IFileRead fileRead, ILogistics logistics, string headerFileName, Dictionary<string, string> pages, Dictionary<string, List<Detail>> slots)
|
|
{
|
|
if (fileRead is null)
|
|
{ }
|
|
_I = 0;
|
|
//string headerText;
|
|
//string altHeaderFileName = Path.ChangeExtension(headerFileName, ".txt");
|
|
//if (File.Exists(altHeaderFileName))
|
|
// headerText = File.ReadAllText(altHeaderFileName);
|
|
//else
|
|
//{
|
|
// //Pdfbox, IKVM.AWT.WinForms
|
|
// org.apache.pdfbox.pdmodel.PDDocument pdfDocument = org.apache.pdfbox.pdmodel.PDDocument.load(headerFileName);
|
|
// org.apache.pdfbox.util.PDFTextStripper stripper = new org.apache.pdfbox.util.PDFTextStripper();
|
|
// headerText = stripper.getText(pdfDocument);
|
|
// pdfDocument.close();
|
|
// File.AppendAllText(altHeaderFileName, headerText);
|
|
//}
|
|
//result.Id = h;
|
|
//result.Title = h;
|
|
//result.Zone = h;
|
|
//result.PSN = h;
|
|
//result.Layer = h;
|
|
ParseErrorText = string.Empty;
|
|
if (!pages.ContainsKey(headerFileName))
|
|
throw new Exception();
|
|
_I = 0;
|
|
_Data = pages[headerFileName];
|
|
ScanPast("Date:");
|
|
Date = GetToEOL();
|
|
ScanPast("Recipe ID:");
|
|
Recipe = GetBefore("LotID:");
|
|
Recipe = Recipe.Replace(";", "");
|
|
if (_Data.Contains("[]"))
|
|
Lot = GetBefore("[]");
|
|
else if (_Data.Contains("[7]"))
|
|
Lot = GetBefore("[7]");
|
|
else
|
|
Lot = GetBefore("[");
|
|
|
|
// Remove illegal characters \/:*?"<>| found in the Lot.
|
|
Lot = Regex.Replace(Lot, @"[\\,\/,\:,\*,\?,\"",\<,\>,\|]", "_").Split('\r')[0].Split('\n')[0];
|
|
|
|
// determine number of wafers and their slot numbers
|
|
_Log.Debug(_Data.Substring(_I));
|
|
string slot;
|
|
string toEOL;
|
|
int slotCount = _Data.Substring(_I).Split('*').Length - 1;
|
|
_Log.Debug($"****HeaderFile - Slot Count: {slotCount}.");
|
|
for (int i = 0; i < slotCount; i++)
|
|
{
|
|
ScanPast("*");
|
|
toEOL = GetToEOL(false);
|
|
slot = string.Concat("*", toEOL.Substring(0, 2));
|
|
if (!slots.ContainsKey(slot))
|
|
slots.Add(slot, new List<Detail>());
|
|
}
|
|
_Log.Debug($"****HeaderFile - Slots:");
|
|
_Log.Debug(slots);
|
|
|
|
ScanPast("Min:");
|
|
|
|
string[] toEol1 = GetToEOL(false).Trim().Split(' ');
|
|
_Log.Debug($"****HeaderFile - toEol1 Count: {toEol1.Length}.");
|
|
FixToEolArray(ref toEol1);
|
|
LPDCountMin = toEol1[0].Trim();
|
|
LPDCM2Min = toEol1[1].Trim();
|
|
AreaCountMin = toEol1[2].Trim();
|
|
AreaTotalMin = toEol1[3].Trim();
|
|
ScratchCountMin = toEol1[4].Trim();
|
|
ScratchTotalMin = toEol1[5].Trim();
|
|
SumOfDefectsMin = toEol1[6].Trim();
|
|
HazeRegionMin = toEol1[7].Trim();
|
|
HazeAverageMin = toEol1[8].Trim();
|
|
ScanPast("Max:");
|
|
|
|
string[] toEol2 = GetToEOL(false).Trim().Split(' ');
|
|
_Log.Debug($"****HeaderFile - toEol2 Count: {toEol2.Length}.");
|
|
FixToEolArray(ref toEol2);
|
|
LPDCountMax = toEol2[0].Trim();
|
|
LPDCM2Max = toEol2[1].Trim();
|
|
AreaCountMax = toEol2[2].Trim();
|
|
AreaTotalMax = toEol2[3].Trim();
|
|
ScratchCountMax = toEol2[4].Trim();
|
|
ScratchTotalMax = toEol2[5].Trim();
|
|
SumOfDefectsMax = toEol2[6].Trim();
|
|
HazeRegionMax = toEol2[7].Trim();
|
|
HazeAverageMax = toEol2[8].Trim();
|
|
ScanPast("Average:");
|
|
|
|
string[] toEol3 = GetToEOL(false).Trim().Split(' ');
|
|
_Log.Debug($"****HeaderFile - toEol3 Count: {toEol3.Length}.");
|
|
FixToEolArray(ref toEol3);
|
|
LPDCountAvg = toEol3[0].Trim();
|
|
LPDCM2Avg = toEol3[1].Trim();
|
|
AreaCountAvg = toEol3[2].Trim();
|
|
AreaTotalAvg = toEol3[3].Trim();
|
|
ScratchCountAvg = toEol3[4].Trim();
|
|
ScratchTotalAvg = toEol3[5].Trim();
|
|
SumOfDefectsAvg = toEol3[6].Trim();
|
|
HazeRegionAvg = toEol3[7].Trim();
|
|
HazeAverageAvg = toEol3[8].Trim();
|
|
ScanPast("Std Dev:");
|
|
|
|
string[] toEol4 = GetToEOL(false).Trim().Split(' ');
|
|
_Log.Debug($"****HeaderFile - toEol4 Count: {toEol4.Length}.");
|
|
FixToEolArray(ref toEol4);
|
|
LPDCountStdDev = toEol4[0].Trim();
|
|
LPDCM2StdDev = toEol4[1].Trim();
|
|
AreaCountStdDev = toEol4[2].Trim();
|
|
AreaTotalStdDev = toEol4[3].Trim();
|
|
ScratchCountStdDev = toEol4[4].Trim();
|
|
ScratchTotalStdDev = toEol4[5].Trim();
|
|
SumOfDefectsStdDev = toEol4[6].Trim();
|
|
HazeRegionStdDev = toEol4[7].Trim();
|
|
HazeAverageStdDev = toEol4[8].Trim();
|
|
|
|
string[] segments = Lot.Split('-');
|
|
if (segments.Length > 0)
|
|
Reactor = segments[0];
|
|
if (segments.Length > 1)
|
|
RDS = segments[1];
|
|
if (segments.Length > 2)
|
|
PSN = segments[2];
|
|
// Example of header.UniqueId is TENCOR1_33-289217-4693_201901300556533336
|
|
UniqueId = string.Format("{0}_{1}_{2}", logistics.JobID, Lot, Path.GetFileNameWithoutExtension(logistics.ReportFullPath));
|
|
}
|
|
|
|
private Detail ParseWaferSummary(string waferFileName, Dictionary<string, string> pages)
|
|
{
|
|
Detail result = new() { Data = "*Data*", i = -1, };
|
|
_I = 0;
|
|
//string waferText;
|
|
//string altWaferFileName = Path.ChangeExtension(waferFileName, ".txt");
|
|
//if (File.Exists(altWaferFileName))
|
|
// waferText = File.ReadAllText(altWaferFileName);
|
|
//else
|
|
//{
|
|
// //Pdfbox, IKVM.AWT.WinForms
|
|
// org.apache.pdfbox.pdmodel.PDDocument pdfDocument = org.apache.pdfbox.pdmodel.PDDocument.load(waferFileName);
|
|
// org.apache.pdfbox.util.PDFTextStripper dataStripper = new org.apache.pdfbox.util.PDFTextStripper();
|
|
// waferText = dataStripper.getText(pdfDocument);
|
|
// pdfDocument.close();
|
|
// File.AppendAllText(altWaferFileName, waferText);
|
|
//}
|
|
List<string> stringList = new();
|
|
result.HeaderUniqueId = UniqueId;
|
|
result.Id = 0;
|
|
result.Title = null;
|
|
if (!pages.ContainsKey(waferFileName))
|
|
throw new Exception();
|
|
_I = 0;
|
|
_Data = pages[waferFileName];
|
|
ScanPast("Date:");
|
|
result.Date = GetToEOL();
|
|
ScanPast("ID#");
|
|
result.Slot = GetToEOL();
|
|
if (result.Slot.Length > 5)
|
|
result.Slot = string.Concat(result.Slot.Substring(0, 5), "... - ***");
|
|
//result.Slot = result.Slot.Replace("*", "");
|
|
ScanPast("Comments:");
|
|
result.Comments = GetToEOL();
|
|
ScanPast("Sort:");
|
|
result.Sort = GetToEOL();
|
|
ScanPast("LPD Count:");
|
|
result.LPDCount = GetToEOL();
|
|
ScanPast("LPD / cm2:");
|
|
result.LPDCM2 = GetToEOL();
|
|
while (GetBefore(":").Contains("Bin"))
|
|
stringList.Add(GetToEOL());
|
|
if (stringList.Count >= 1)
|
|
result.Bin1 = stringList[0];
|
|
if (stringList.Count >= 2)
|
|
result.Bin2 = stringList[1];
|
|
if (stringList.Count >= 3)
|
|
result.Bin3 = stringList[2];
|
|
if (stringList.Count >= 4)
|
|
result.Bin4 = stringList[3];
|
|
if (stringList.Count >= 5)
|
|
result.Bin5 = stringList[4];
|
|
if (stringList.Count >= 6)
|
|
result.Bin6 = stringList[5];
|
|
if (stringList.Count >= 7)
|
|
result.Bin7 = stringList[6];
|
|
if (stringList.Count >= 8)
|
|
result.Bin8 = stringList[7];
|
|
result.Mean = GetToEOL();
|
|
ScanPast("Std Dev:");
|
|
result.StdDev = GetToEOL();
|
|
ScanPast("Area Count:");
|
|
result.AreaCount = GetToEOL();
|
|
ScanPast("Area Total:");
|
|
result.AreaTotal = GetToEOL();
|
|
ScanPast("Scratch Count:");
|
|
result.ScratchCount = GetToEOL();
|
|
ScanPast("Scratch Total:");
|
|
result.ScratchTotal = GetToEOL();
|
|
ScanPast("Sum of All Defects:");
|
|
result.SumOfDefects = GetToEOL();
|
|
ScanPast("Haze Region:");
|
|
result.HazeRegion = GetToEOL();
|
|
ScanPast("Haze Average:");
|
|
result.HazeAverage = GetToEOL();
|
|
ScanPast("Haze Peak:");
|
|
result.HazePeak = GetToEOL();
|
|
ScanPast("Laser:");
|
|
result.Laser = GetBefore("Gain:");
|
|
result.Gain = GetBefore("Diameter:");
|
|
result.Diameter = GetToEOL();
|
|
ScanPast("Thresh:");
|
|
result.Thresh = GetBefore("Exclusion:");
|
|
result.Exclusion = GetToEOL();
|
|
ScanPast("Haze Rng:");
|
|
result.HazeRng = GetBefore("Thruput:");
|
|
result.Thruput = GetToEOL();
|
|
ScanPast("Recipe ID:");
|
|
result.Recipe = GetToEOL();
|
|
result.UniqueId = string.Format("{0}_{1}", UniqueId, result.Slot.Replace("*", string.Empty).TrimStart('0'));
|
|
return result;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Convert the raw data file to parsable file format - in this case from PCL to PDF
|
|
/// </summary>
|
|
/// <param name="sourceFile">source file to be converted to PDF</param>
|
|
/// <returns></returns>
|
|
private static string ConvertSourceFileToPdf(string ghostPCLFileName, Logistics logistics)
|
|
{
|
|
string result = Path.ChangeExtension(logistics.ReportFullPath, ".pdf");
|
|
if (!File.Exists(result))
|
|
{
|
|
//string arguments = string.Concat("-i \"", sourceFile, "\" -o \"", result, "\"");
|
|
string arguments = string.Concat("-dSAFER -dBATCH -dNOPAUSE -sOutputFile=\"", result, "\" -sDEVICE=pdfwrite \"", logistics.ReportFullPath, "\"");
|
|
//Process process = Process.Start(configData.LincPDFCFileName, arguments);
|
|
Process process = Process.Start(ghostPCLFileName, arguments);
|
|
_ = process.WaitForExit(30000);
|
|
if (!File.Exists(result))
|
|
throw new Exception("PDF file wasn't created");
|
|
}
|
|
return result;
|
|
}
|
|
|
|
private void Parse(IFileRead fileRead, Logistics logistics, List<FileInfo> fileInfoCollection, string ghostPCLFileName)
|
|
{
|
|
object item;
|
|
string pageText;
|
|
string pagePDFFile;
|
|
string pageTextFile;
|
|
List<string> sourceFiles = new();
|
|
List<string> missingSlots = new();
|
|
List<Detail> dataFiles = new();
|
|
Dictionary<string, string> pages = new();
|
|
string sourcePath = Path.GetDirectoryName(logistics.ReportFullPath);
|
|
Dictionary<string, List<Detail>> slots = new();
|
|
string sourceFileNamePdf = ConvertSourceFileToPdf(ghostPCLFileName, logistics);
|
|
sourceFiles.Add(sourceFileNamePdf);
|
|
string sourceFileNameNoExt = Path.GetFileNameWithoutExtension(logistics.ReportFullPath);
|
|
////PdfSharp open pdf
|
|
//using (PdfSharp.Pdf.PdfDocument sourceDocument = PdfSharp.Pdf.IO.PdfReader.Open(sourceFileNamePdf, PdfSharp.Pdf.IO.PdfDocumentOpenMode.Import))
|
|
//{
|
|
// for (int idxPage = 0; idxPage < sourceDocument.PageCount; idxPage++)
|
|
// {
|
|
// // split the pdf into separate pages. Odd pages are wafer image, even are wafer summary. Last page is Lot Summary.
|
|
// _Log.Debug($"****ParseData - Splitting page: {idxPage}, sourceDocument: {sourceDocument.FullPath}, sourcePathFileNoExt: {sourcePathFileNoExt}");
|
|
// //SplitPage(sourceDocument, sourcePathFileNoExt, idxPage);
|
|
// pageNum = idxPage + 1;
|
|
// pageFile = string.Format("{0}_{1}.pdf", sourcePathFileNoExt, pageNum);
|
|
// _Log.Debug($"****SplitPage - Page {pageNum} Source file: {sourceDocument.FullPath}");
|
|
// _Log.Debug($"****SplitPage - Page {pageNum} Output file: {pageFile}");
|
|
// //PdfSharp Create new document
|
|
// PdfSharp.Pdf.PdfDocument outputDocument = new PdfSharp.Pdf.PdfDocument { Version = sourceDocument.Version };
|
|
// outputDocument.Info.Title = string.Format("Page {0} of {1}", pageNum, sourceDocument.Info.Title);
|
|
// outputDocument.Info.Creator = sourceDocument.Info.Creator;
|
|
// outputDocument.AddPage(sourceDocument.Pages[idxPage]);
|
|
// outputDocument.Pages[0].CropBox = new PdfSharp.Pdf.PdfRectangle(new PdfSharp.Drawing.XRect(0, 100, 700, 700));
|
|
// outputDocument.Save(pageFile);
|
|
// }
|
|
// sourceDocumentPageCount = sourceDocument.PageCount;
|
|
// sourceDocument.Close();
|
|
//}
|
|
java.io.File file = new(sourceFileNamePdf);
|
|
org.apache.pdfbox.util.Splitter splitter = new();
|
|
org.apache.pdfbox.pdmodel.PDDocument pdDocument = org.apache.pdfbox.pdmodel.PDDocument.load(file);
|
|
java.util.List list = splitter.split(pdDocument);
|
|
java.util.ListIterator iterator = list.listIterator();
|
|
org.apache.pdfbox.util.PDFTextStripper dataStripper = new();
|
|
for (short i = 1; i < short.MaxValue; i++)
|
|
{
|
|
if (!iterator.hasNext())
|
|
break;
|
|
item = iterator.next();
|
|
pagePDFFile = string.Concat(sourcePath, @"\", sourceFileNameNoExt, "_", i, ".pdf");
|
|
pageTextFile = Path.ChangeExtension(pagePDFFile, ".txt");
|
|
if (File.Exists(pageTextFile))
|
|
{
|
|
pageText = File.ReadAllText(pageTextFile);
|
|
sourceFiles.Add(pageTextFile);
|
|
if (item is not org.apache.pdfbox.pdmodel.PDDocument pd)
|
|
continue;
|
|
pd.close();
|
|
}
|
|
else if (File.Exists(pagePDFFile))
|
|
{
|
|
org.apache.pdfbox.pdmodel.PDDocument document = org.apache.pdfbox.pdmodel.PDDocument.load(pagePDFFile);
|
|
pageText = dataStripper.getText(document);
|
|
document.close();
|
|
sourceFiles.Add(pagePDFFile);
|
|
if (item is not org.apache.pdfbox.pdmodel.PDDocument pd)
|
|
continue;
|
|
pd.close();
|
|
}
|
|
else
|
|
{
|
|
if (item is not org.apache.pdfbox.pdmodel.PDDocument pd)
|
|
continue;
|
|
pageText = dataStripper.getText(pd);
|
|
pd.save(pagePDFFile);
|
|
sourceFiles.Add(pagePDFFile);
|
|
pd.close();
|
|
File.WriteAllText(pageTextFile, pageText);
|
|
sourceFiles.Add(pageTextFile);
|
|
}
|
|
pages.Add(pagePDFFile, pageText);
|
|
}
|
|
pdDocument.close();
|
|
// parse lot summary
|
|
_Log.Debug($"****ParseData - Parsing lot summary");
|
|
List<Tuple<string, string>> pageMapping = new();
|
|
string headerFileName = string.Concat(sourcePath, @"\", sourceFileNameNoExt, "_", pages.Count, ".pdf");
|
|
ParseLotSummary(fileRead, logistics, headerFileName, pages, slots);
|
|
foreach (KeyValuePair<string, string> keyValuePair in pages)
|
|
{
|
|
if (keyValuePair.Key == headerFileName)
|
|
continue;
|
|
if (string.IsNullOrEmpty(keyValuePair.Value.Trim()))
|
|
{
|
|
pageMapping.Add(new Tuple<string, string>(keyValuePair.Key, string.Empty));
|
|
continue;
|
|
}
|
|
if (!pages.ContainsKey(keyValuePair.Key))
|
|
throw new Exception();
|
|
Detail dataFile = ParseWaferSummary(keyValuePair.Key, pages);
|
|
if (string.IsNullOrEmpty(dataFile.Recipe) || dataFile.Recipe != Recipe)
|
|
{
|
|
missingSlots.Add(keyValuePair.Key);
|
|
pageMapping.Add(new Tuple<string, string>(keyValuePair.Key, string.Empty));
|
|
continue;
|
|
}
|
|
if (!slots.ContainsKey(dataFile.Slot))
|
|
{
|
|
missingSlots.Add(keyValuePair.Key);
|
|
pageMapping.Add(new Tuple<string, string>(keyValuePair.Key, string.Empty));
|
|
continue;
|
|
}
|
|
pageMapping.Add(new Tuple<string, string>(keyValuePair.Key, string.Concat(sourcePath, @"\", sourceFileNameNoExt, "_", dataFile.Slot.Replace('*', 's'), "_data.pdf")));
|
|
slots[dataFile.Slot].Add(dataFile);
|
|
}
|
|
string checkFileName = string.Concat(sourcePath, @"\", sourceFileNameNoExt, "_data.pdf");
|
|
if (!File.Exists(checkFileName))
|
|
{
|
|
File.Move(headerFileName, checkFileName);
|
|
_ = sourceFiles.Remove(headerFileName);
|
|
sourceFiles.Add(checkFileName);
|
|
}
|
|
checkFileName = string.Empty;
|
|
for (int i = pageMapping.Count - 1; i > -1; i--)
|
|
{
|
|
if (!string.IsNullOrEmpty(pageMapping[i].Item2))
|
|
{
|
|
checkFileName = pageMapping[i].Item2;
|
|
if (!File.Exists(checkFileName))
|
|
{
|
|
File.Move(pageMapping[i].Item1, checkFileName);
|
|
_ = sourceFiles.Remove(pageMapping[i].Item1);
|
|
sourceFiles.Add(checkFileName);
|
|
}
|
|
}
|
|
else if (!string.IsNullOrEmpty(checkFileName))
|
|
{
|
|
//if (i == 0 || !string.IsNullOrEmpty(pageMapping[i - 1].Item2))
|
|
//{
|
|
checkFileName = checkFileName.Replace("_data.pdf", "_image.pdf");
|
|
if (!File.Exists(checkFileName))
|
|
{
|
|
File.Move(pageMapping[i].Item1, checkFileName);
|
|
_ = sourceFiles.Remove(pageMapping[i].Item1);
|
|
sourceFiles.Add(checkFileName);
|
|
}
|
|
//}
|
|
checkFileName = string.Empty;
|
|
}
|
|
}
|
|
foreach (KeyValuePair<string, List<Detail>> keyValuePair in slots)
|
|
{
|
|
if (!keyValuePair.Value.Any() || keyValuePair.Value[0] is null)
|
|
missingSlots.Add(string.Concat("Slot ", keyValuePair.Key, ") is missing."));
|
|
else
|
|
{
|
|
foreach (Detail data in keyValuePair.Value)
|
|
dataFiles.Add(data);
|
|
}
|
|
}
|
|
if (missingSlots.Any())
|
|
{
|
|
string missingSlotsFile = string.Concat(sourcePath, @"\", sourceFileNameNoExt, "_MissingSlots.txt");
|
|
File.WriteAllLines(missingSlotsFile, missingSlots);
|
|
sourceFiles.Add(missingSlotsFile);
|
|
}
|
|
Date = DateTime.Parse(Date).ToString();
|
|
//Equipment data is wrong!!!
|
|
Date = DateTime.Now.ToString();
|
|
//Equipment data is wrong!!!
|
|
//for (int i = 0; i < dataFiles.Count; i++)
|
|
// dataFiles[i].Date = DateTime.Parse(dataFiles[i].Date).ToString();
|
|
foreach (string sourceFile in sourceFiles)
|
|
fileInfoCollection.Add(new FileInfo(sourceFile));
|
|
fileInfoCollection.Add(new FileInfo(logistics.ReportFullPath));
|
|
}
|
|
|
|
} |