Changeset 9652

Timestamp:

06/24/13 13:32:12 (11 years ago)

Author:

sforsten

Message:

#2047: TableFileParser can now handle white spaces (currently the character '\0' symbolizes white spaces in the TableFileParser)

Location:

trunk/sources

Files:

• HeuristicLab.Problems.Instances.DataAnalysis.Views/3.3/DataAnalysisImportTypeDialog.cs (modified) (1 diff)
• HeuristicLab.Problems.Instances.DataAnalysis/3.3/TableFileParser.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis.Views/3.3/DataAnalysisImportTypeDialog.cs

@@ -42 +42 @@
       new KeyValuePair<char, string>(';', "; (Semicolon)" ),
       new KeyValuePair<char, string>(',', ", (Comma)" ),    
-      new KeyValuePair<char, string>('\t', "\\t (Tab)")
+      new KeyValuePair<char, string>('\t', "\\t (Tab)"),
+      new KeyValuePair<char, string>((char)0, "all whitespaces (including tabs and spaces)")
     };
 

trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/TableFileParser.cs

@@ -28 +28 @@
 using System.Linq;
 using System.Runtime.Serialization;
-using System.Text;
 
 namespace HeuristicLab.Problems.Instances.DataAnalysis {
   public class TableFileParser {
     private const int BUFFER_SIZE = 65536;
-    private static readonly char[] POSSIBLE_SEPARATORS = new char[] { ',', ';', '\t' };
+    // char used to symbolize whitespaces (no missing values can be handled with whitespaces)
+    private const char WHITESPACECHAR = (char)0;
+    private static readonly char[] POSSIBLE_SEPARATORS = new char[] { ',', ';', '\t', WHITESPACECHAR };
     private Tokenizer tokenizer;
     private List<List<object>> rowValues;
@@ -360 +361 @@
 
       private IEnumerable<string> Split(string line) {
-        StringBuilder subStr = new StringBuilder();
-        foreach (char c in line) {
-          if (c == separator) {
-            yield return subStr.ToString();
-            subStr = new StringBuilder();
-            // all separator characters are transformed to the internally used separator character
+        IEnumerable<string> splitString;
+        if (separator == WHITESPACECHAR) {
+          //separate whitespaces
+          splitString = line.Split(new char[0], StringSplitOptions.RemoveEmptyEntries);
+        } else {
+          splitString = line.Split(separator);
+        }
+        int cur = splitString.Count();
+        foreach (var str in splitString) {
+          yield return str;
+          cur--;
+          // do not return the INTERNAL_SEPARATOR after the last string
+          if (cur != 0) {
             yield return INTERNAL_SEPARATOR;
-          } else {
-            subStr.Append(c);
           }
         }
-        yield return subStr.ToString();
       }