changeset 52:3a036a34c362

better handle of input file

--- a/seg2matrix/CGData/BaseTable.py	Thu Sep 17 14:33:21 2015 -0700
+++ b/seg2matrix/CGData/BaseTable.py	Thu Sep 17 15:00:45 2015 -0700
@@ -63,24 +63,31 @@
         linenum = 0
         for row in read:
             linenum += 1
+            if linenum ==1: #ignore header line
+                continue 
             r = self.__row_class__()
             if (comment is None or not row[0].startswith(comment)) and not row[0].startswith("#"):
                 for i, col in enumerate(cols):
+                    skip =0
                     isOptional = False
                     if 'columnDef' in self['cgformat'] and col in self['cgformat']['columnDef'] and 'optional' in self['cgformat']['columnDef'][col]:
                         isOptional = self['cgformat']['columnDef'][col]['optional']
                     if len(row) > i:
                         try:
                             setattr(r, col, colType[col](row[i]))
-                        except ValueError:
+                        except ValueError:  
                             raise ValueError( "col invalid type %s on line %d" % (row[i], linenum))
                     else:
                         if isOptional:
                             setattr(r, col, None)
                         else:
                             print row
+                            skip =1 # ignore bad lines
+                            break
                             raise InvalidFormat("missing colum " + col)
-                            
+                if skip:
+                    continue
+
                 if not self.groupKey:
                     if self.secondKey is not None:
                         key1 = getattr(r, self.firstKey )                    

--- a/segToMatrix.xml	Thu Sep 17 14:33:21 2015 -0700
+++ b/segToMatrix.xml	Thu Sep 17 15:00:45 2015 -0700
@@ -26,11 +26,23 @@
   </outputs>
   <help>
 
-    **Given a segmented copy number data file, convert it into xena ready matrix file.**
+**Given a segmented copy number data file, convert it into xena ready matrix file.**
+
+1. Input data file format: tab-deliminated
 
-    Output File no 1. matrix file
+   =======    =====  ======= ===== ====== ======
+   sanmple    chr    start   end   strand value
+   =======    =====  ======= ===== ====== ======
+   sample1    chr1   1       100   .      0.5
+   sample2    chr1   101     1000  .      1.5
+   sample3    chr1   1000    2000  .      -0.5
+   ...        ...    ...     ...   ...    ...
+   =======    =====  ======= ===== ====== ====== 
 
-    Output File no 2. probeMap file -- probe to gene mapping file  (is in the same genome assembly as the input segmented copy number data)
+
+2. Output File no 1. matrix file
+
+   Output File no 2. probeMap file -- probe to gene mapping file  (is in the same genome assembly as the input segmented copy number data)
   </help>
 </tool>