[DatFile] Modularize and rename code

RombaSharp/Partials/RombaSharp_Helpers.cs

@@ -402,7 +402,7 @@ namespace SabreTools
 
 			// First get a list of SHA-1's from the input DATs
 			DatFile datroot = new DatFile { Type = "SuperDAT", };
-			datroot.PopulateDatFromDir(_dats, false, false, false, false, false, false, false, _tmpdir, false, null, 4, _logger);
+			datroot.PopulateFromDir(_dats, false, false, false, false, false, false, false, _tmpdir, false, null, 4, _logger);
 			datroot.BucketBySHA1(false, _logger, false);
 
 			// Create a List of dat hashes in the database (SHA-1)
@@ -616,7 +616,7 @@ namespace SabreTools
 
 			// Now rescan the depot itself
 			DatFile depot = new DatFile();
-			depot.PopulateDatFromDir(depotname, false, false, false, false, true, false, false, _tmpdir, false, null, _workers, _logger);
+			depot.PopulateFromDir(depotname, false, false, false, false, true, false, false, _tmpdir, false, null, _workers, _logger);
 			depot.BucketBySHA1(false, _logger, false);
 
 			// Set the base queries to use

RombaSharp/Partials/RombaSharp_Inits.cs

@@ -41,12 +41,12 @@ namespace SabreTools
 			DatFile df = new DatFile();
 			foreach (string dir in onlyDirs)
 			{
-				df.PopulateDatFromDir(dir, false, false, false, false, true, false, false, _tmpdir, false, null, _workers, _logger);
+				df.PopulateFromDir(dir, false, false, false, false, true, false, false, _tmpdir, false, null, _workers, _logger);
 
 				// If we're looking for only needed, consider the zipfiles themselves too
 				if (onlyNeeded)
 				{
-					df.PopulateDatFromDir(dir, false, false, false, true, true, false, false, _tmpdir, false, null, _workers, _logger);
+					df.PopulateFromDir(dir, false, false, false, true, true, false, false, _tmpdir, false, null, _workers, _logger);
 				}
 			}
 
@@ -266,7 +266,7 @@ namespace SabreTools
 			Logger logger = new Logger();
 			foreach (string input in inputs)
 			{
-				datdata.PopulateDatFromDir(input, false /* noMD5 */, false /* noSHA1 */, true /* bare */, false /* archivesAsFiles */,
+				datdata.PopulateFromDir(input, false /* noMD5 */, false /* noSHA1 */, true /* bare */, false /* archivesAsFiles */,
 					true /* enableGzip */, false /* addBlanks */, false /* addDate */, _tmpdir /* tempDir */, false /* copyFiles */,
 					null /* headerToCheckAgainst */, _workers /* maxDegreeOfParallelism */, _logger);
 				datdata.WriteToFile("", logger);

SabreTools.Helper/Tools/FileTools.cs

@@ -3,6 +3,7 @@ using System;
 using System.Collections.Generic;
 using System.Linq;
 using System.Security.Cryptography;
+using System.Threading.Tasks;
 using System.Xml;
 using System.Xml.Schema;
 
@@ -20,6 +21,7 @@ using BinaryWriter = System.IO.BinaryWriter;
 using FileStream = System.IO.FileStream;
 using IOException = System.IO.IOException;
 using MemoryStream = System.IO.MemoryStream;
+using PathTooLongException = System.IO.PathTooLongException;
 using SearchOption = System.IO.SearchOption;
 using SeekOrigin = System.IO.SeekOrigin;
 using Stream = System.IO.Stream;
@@ -79,7 +81,7 @@ namespace SabreTools.Helper.Tools
 			}
 
 			// Read the input file, if possible
-			logger.Verbose("Attempting to read file: \"" + filename + "\"");
+			logger.Verbose("Attempting to read file to get format: \"" + filename + "\"");
 
 			// Check if file exists
 			if (!File.Exists(filename))
@@ -446,6 +448,66 @@ namespace SabreTools.Helper.Tools
 			}
 		}
 
+		/// <summary>
+		/// Retrieve a list of just files from inputs
+		/// </summary>
+		/// <param name="inputs">List of strings representing directories and files</param>
+		/// <param name="maxDegreeOfParallelism">Integer representing the maximum amount of parallelization to be used</param>
+		/// <param name="logger">Logger object for file and console output</param>
+		/// <param name="appendparent">True if the parent name should be appended after the special character "¬", false otherwise</param>
+		/// <returns>List of strings representing just files from the inputs</returns>
+		public static List<string> GetOnlyFilesFromInputs(List<string> inputs, int maxDegreeOfParallelism, Logger logger, bool appendparent = false)
+		{
+			List<string> outputs = new List<string>();
+			Parallel.ForEach(inputs,
+				new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism, },
+				input =>
+			{
+				if (Directory.Exists(input))
+				{
+					List<string> files = FileTools.RetrieveFiles(input, new List<string>());
+					foreach (string file in files)
+					{
+						try
+						{
+							lock (outputs)
+							{
+								outputs.Add(Path.GetFullPath(file) + (appendparent ? "¬" + Path.GetFullPath(input) : ""));
+							}
+						}
+						catch (PathTooLongException)
+						{
+							logger.Warning("The path for " + file + " was too long");
+						}
+						catch (Exception ex)
+						{
+							logger.Error(ex.ToString());
+						}
+					}
+				}
+				else if (File.Exists(input))
+				{
+					try
+					{
+						lock (outputs)
+						{
+							outputs.Add(Path.GetFullPath(input) + (appendparent ? "¬" + Path.GetFullPath(input) : ""));
+						}
+					}
+					catch (PathTooLongException)
+					{
+						logger.Warning("The path for " + input + " was too long");
+					}
+					catch (Exception ex)
+					{
+						logger.Error(ex.ToString());
+					}
+				}
+			});
+
+			return outputs;
+		}
+
 		#endregion
 
 		#region Stream Information

SabreTools.Helper/Tools/Style.cs

@@ -396,6 +396,31 @@ namespace SabreTools.Helper.Tools
 				.ToArray());
 		}
 
+		/// <summary>
+		/// Split a line as if it were a CMP rom line
+		/// </summary>
+		/// <param name="s">Line to split</param>
+		/// <returns>Line split</returns>
+		/// <remarks>Uses code from http://stackoverflow.com/questions/554013/regular-expression-to-split-on-spaces-unless-in-quotes</remarks>
+		public static string[] SplitLineAsCMP(string s)
+		{
+			// Preprocess the string
+			s = Regex.Replace(s, @"^\S* \(", ""); // Remove item identifier and opening brace
+			s = Regex.Replace(s, @"#.*$", ""); // Remove trailing comments
+			s = s.TrimEnd(')'); // Remove closing brace
+			s = s.Trim(); // Remove leading and trailing whitespace
+
+			// Now we get each string, divided up as cleanly as possible
+			string[] matches = Regex
+				//.Matches(s, @"([^\s]*""[^""]+""[^\s]*)|[^""]?\w+[^""]?")
+				.Matches(s, @"[^\s""]+|""[^""]*""")
+				.Cast<Match>()
+				.Select(m => m.Groups[0].Value)
+				.ToArray();
+
+			return matches;
+		}
+
 		#endregion
 
 		#region System.IO.Path Replacements

SabreTools/Partials/SabreTools_Inits.cs

@@ -118,7 +118,7 @@ namespace SabreTools
 					datdata.Files = new SortedDictionary<string, List<DatItem>>();
 
 					string basePath = Path.GetFullPath(path);
-					bool success = datdata.PopulateDatFromDir(basePath, noMD5, noSHA1, removeDateFromAutomaticName, parseArchivesAsFiles, enableGzip,
+					bool success = datdata.PopulateFromDir(basePath, noMD5, noSHA1, removeDateFromAutomaticName, parseArchivesAsFiles, enableGzip,
 						addBlankFilesForEmptyFolder, addFileDates, tempDir, copyFiles, headerToCheckAgainst, maxDegreeOfParallelism, _logger);
 
 					// If it was a success, write the DAT out