check for new filenames before merge/subset

python logic written in separate library
- looks for any filenames present in the current datatype sheet (embedded in script)
- excludes any filenames which were in use before the introduction of updated filenames
- ignore normal sample files (which are ignored by importer)
- determines cancer study id for proper handling of <CANCER_STUDY> placeholder
- matches filenames in directory against wildcard patterns (up to a single asterisk)
perform check from subset-impact-data.sh and merge.py and exit on noticing new filename patterns.

import-scripts/merge.py

@@ -7,6 +7,7 @@
 import shutil
 import re
 import csv
+import study_directory_uses_updated_filenames
 
 # ------------------------------------------------------------------------------
 # globals
@@ -103,7 +104,6 @@
     'HYBRIDIZATION REF',
 ]
 
-
 # only files fitting patterns placed in these two lists will be merged
 NORMAL_MERGE_PATTERNS = [MUTATION_META_PATTERN,
     FUSION_META_PATTERN,
@@ -814,6 +814,15 @@ def organize_files(studies, file_types, merge_clinical):
             else:
                 file_types[SUPP_DATA].append(study_file)
 
+def exit_if_unsupported_filenames_detected(study_paths):
+    unsupported_filenames_detected = False
+    for study_path in study_paths:
+        if study_directory_uses_updated_filenames.study_directory_uses_updated_filenames(study_path):
+            print("unsupported filenames present in study directory '%s' - unable to merge" % study_path)
+            unsupported_filenames_detected = True
+    if unsupported_filenames_detected:
+        sys.exit(2)
+
 def usage():
     print >> OUTPUT_FILE, 'merge.py --subset [/path/to/subset] --output-directory [/path/to/output] --study-id [study id] --cancer-type [cancer type] --merge-clinical [true/false] --exclude-supplemental-data [true/false] --excluded-samples [/path/to/exclude_list] <path/to/study path/to/study ...>'
 
@@ -919,6 +928,9 @@ def main():
     else:
         exclude_supp_data = True
 
+    # test input study paths for new filenames
+    exit_if_unsupported_filenames_detected(args)
+
     # get all the filenames
     organize_files(args, file_types, merge_clinical)