Improvement/more fields refractor some fields

src/main/conf/import.json

@@ -12,21 +12,23 @@
     {
       "key": "delim",
       "title": "Delimiter Character",
+      "default": ",",
+      "maximum": 1,
       "type": "string",
       "description": "Single character used to separate fields within a record. Leave blank to read whitespace-separated columns."
     },
     {
-      "key": "col_types",
-      "title": "Column Types",
+      "key": "na",
       "type": "string",
-      "format": "textarea",
-      "default": ".default=\"?\"",
-      "description": "A compact string representation where each character represents one column: c = character, i = integer, n = number, d = double, l = logical, D = date, T = date time, t = time, ? = guess, or _/- to skip the column."
+      "title": "Missing Values",
+      "description": "A comma separated list of values to be considered as missing."
     },
     {
-      "key": "is_col_types_subset",
-      "type": "boolean",
-      "title": "Subset of Columns"
+      "key": "skip",
+      "type": "integer",
+      "default": 0,
+      "title": "Skip",
+      "description": "Number of lines to skip before reading data."
     },
     {
       "key": "locale",

src/main/java/org/obiba/datasource/opal/readr/DataReadROperation.java

@@ -11,16 +11,20 @@ public class DataReadROperation extends AbstractROperation {
 
   private final String delimiter;
 
-  private final String columnSpecification;
+  private final String missingValuesCharacters;
 
-  private final boolean columnSpecificationForSubset;
+  private final int numberOfRecordsToSkip;
 
-  public DataReadROperation(String symbol, String source, String delimiter, String columnSpecification, boolean columnSpecificationForSubset) {
+  private final String locale;
+
+  public DataReadROperation(String symbol,
+  String source, String delimiter, String missingValuesCharacters, int numberOfRecordsToSkip, String locale) {
     this.symbol = symbol;
     this.source = source;
     this.delimiter = delimiter;
-    this.columnSpecification = columnSpecification;
-    this.columnSpecificationForSubset = columnSpecificationForSubset;
+    this.missingValuesCharacters = missingValuesCharacters;
+    this.numberOfRecordsToSkip = numberOfRecordsToSkip;
+    this.locale = locale;
   }
 
   @Override
@@ -38,18 +42,23 @@ private String getCommand() {
   }
 
   private String readWithDelimiter() {
-    return String.format("read_delim('%s', delim = '%s'%s)", source, delimiter, columnTypes());
+    return String.format("read_delim('%s', delim = '%s'%s%s%s)", source, delimiter, missingValues(), numberOfRecordsToSkipValue(), localeValue());
   }
 
   private String readWithTable() {
-    return String.format("read_table('%s'%s)", source, columnTypes());
+    return String.format("read_table('%s'%s%s%s)", source, missingValues(), numberOfRecordsToSkipValue(), localeValue());
+  }
+
+  private String missingValues() {
+    return Strings.isNullOrEmpty(missingValuesCharacters) ? ", na = c(\"\", \"NA\")" : String.format(", na = c(%s)", missingValuesCharacters);
+  }
+
+  private String numberOfRecordsToSkipValue() {
+    return ", skip = " + numberOfRecordsToSkip;
   }
 
-  private String columnTypes() {
-    if (Strings.isNullOrEmpty(columnSpecification)) {
-      return "";
-    }
-    return ", col_types = " + String.format(columnSpecificationForSubset ? "cols_only(%s)" : "cols(%s)", columnSpecification);
+  private String localeValue() {
+    return String.format(", locale = locale(\"%s\")", locale);
   }
 
   @Override

src/main/java/org/obiba/datasource/opal/readr/ReadRDatasourceService.java

@@ -4,6 +4,8 @@
 
 import javax.validation.constraints.NotNull;
 
+import com.google.common.base.Strings;
+
 import org.json.JSONObject;
 import org.obiba.magma.Datasource;
 import org.obiba.magma.DatasourceFactory;
@@ -33,14 +35,16 @@ protected Datasource internalCreate() {
         File file = resolvePath(parameters.optString("file"));
 
         String delimiter = parameters.optString("delim");
-        String columnTypes = parameters.optString("col_types");
-        boolean columnSpecificationForSubset = parameters.optBoolean("is_col_types_subset");
+        String missingValuesCharacters = parameters.optString("na");
+        String locale = parameters.optString("locale");
+        int skip = parameters.optInt("skip");
 
         String symbol = getSymbol(file);
         // copy file to the R session
         prepareFile(file);
-        execute(new DataReadROperation(symbol, file.getName(), delimiter, columnTypes, columnSpecificationForSubset));
-        return new RDatasource(getName(), getRSessionHandler(), symbol, parameters.optString("entity_type"), parameters.optString("id"));
+        execute(new DataReadROperation(symbol, file.getName(), delimiter, missingValuesCharacters, skip, Strings.isNullOrEmpty(locale) ? "en" : locale));
+        return new RDatasource(getName(), getRSessionHandler(), symbol, parameters.optString("entity_type"),
+            parameters.optString("id"));
       }
     };
     factory.setRSessionHandler(getRSessionHandler());