Go back to old data format names for metadata

Going back to old values for data format where applicable, otherwise it could cause confusion when comparing old and new processed data.
madprime · Aug 31, 2012 · 5728317 · 5728317
1 parent 1aee93a
commit 5728317
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 11 deletions.
diff --git a/server/conversion/convert_to_gff.py b/server/conversion/convert_to_gff.py
@@ -18,9 +18,9 @@ def convert(input_file, options=None):
     input_type = detect_format.detect_format(input_file)
     if input_type == 'GFF':
         input_data = autozip.file_open(input_file)
-    elif input_type == 'CGIvar':
+    elif input_type == 'CGIVAR':
         input_data = cgivar_to_gff.convert(input_file, options)
-    elif input_type == '23andme':
+    elif input_type == '23ANDME':
         input_data = gff_from_23andme.convert(input_file)
     elif input_type == 'VCF':
         input_data = vcf_to_gff.convert(input_file, options)

diff --git a/server/conversion/detect_format.py b/server/conversion/detect_format.py
@@ -21,8 +21,9 @@ def detect_format(file_input):
 
     Takes a path to a file, or a string generator (e.g. a filehandle).
     Tries to match one of the following:
-      23andme: 23andme (microarray genotyping)
-      CGIvar: Complete Genomics var file
+      23ANDME: 23andme (microarray genotyping)
+      CGIVAR: Complete Genomics var file
+      deCODEme: deCODEme (microarray genotyping)
       GFF: General Feature Format
       VCF: Variant Call Format (only tested for 23andme exome data)
     """
@@ -48,14 +49,14 @@ def detect_format(file_input):
         # Check comment lines, if they exist, for information on file type.
         if re.match('#', line):
             if re.match(r'#TYPE.*VAR-ANNOTATION', line):
-                print "Complete Genomics var file format (CGIvar) detected"
-                looks_like['CGIvar'] = True
+                print "Complete Genomics var file format (CGIVAR) detected"
+                looks_like['CGIVAR'] = True
             if re.match(r'##gff-version', line):
                 print "General Feature Format (GFF) detected"
                 looks_like['GFF'] = True
             if re.match(r'# This data file generated by 23andMe', line):
-                print "23andme microarray genotyping data (23andme) detected"
-                looks_like['23andme'] = True
+                print "23andme microarray genotyping data (23ANDME) detected"
+                looks_like['23ANDME'] = True
             if re.match(r'##fileformat=VCFv4', line):
                 print "Variant Call Format (VCF) detected"
                 looks_like['VCF'] = True
@@ -76,15 +77,15 @@ def detect_format(file_input):
              re.match(r'rs', tsv_data[0]) and 
              re.match(r'[0-9]', tsv_data[2]) and
              re.match(r'[ACGT][ACGT]', tsv_data[3]) ):
-            print "23andme microarray genotyping data (23andme) guessed"
-            looks_like['23andme'] = True
+            print "23andme microarray genotyping data (23ANDME) guessed"
+            looks_like['23ANDME'] = True
         if ( len(tsv_data) > 6 and
              re.match(r'chr', tsv_data[3]) and 
              re.match(r'[0-9]', tsv_data[4]) and 
              re.match(r'[0-9]', tsv_data[5]) and
              (tsv_data[6] == "no-call" or tsv_data[6] == "ref") ):
             print "Complete Genomics var file format (CGIvar) guessed"
-            looks_like['CGIvar'] = True
+            looks_like['CGIVAR'] = True
         if ( len(tsv_data) > 6 and
              re.match(r'[0-9]', tsv_data[3]) and
              re.match(r'[0-9]', tsv_data[4]) and