backport the new report file requirement

bin/anvi-rename-bins

@@ -9,6 +9,7 @@ import anvio
 import anvio.dbops as dbops
 import anvio.utils as utils
 import anvio.terminal as terminal
+import anvio.filesnpaths as filesnpaths
 import anvio.ccollections as ccollections
 
 from anvio.completeness import Completeness
@@ -36,12 +37,7 @@ def main(args):
     list_collections = A('list_collections')
     collection_name = A('collection_name')
     prefix = A('prefix')
-
-    if not prefix:
-        raise ConfigError, "Anvi'o is having hard time believing that you called this function without\
-                            a prefix to rename bins in collection '%s'." % collection_name
-
-    utils.is_this_name_OK_for_database('prefix', prefix)
+    report_file_path = A('report_file')
 
     dbops.is_profile_db_and_contigs_db_compatible(profile_db, contigs_db)
 
@@ -52,6 +48,19 @@ def main(args):
         collections.list_collections()
         sys.exit()
 
+    if not prefix:
+        raise ConfigError, "Anvi'o is having hard time believing that you called this function without\
+                            a prefix to rename bins in collection '%s'." % collection_name
+
+    utils.is_this_name_OK_for_database('prefix', prefix)
+
+    if not report_file_path:
+        raise ConfigError, "You must provide an output file name to report file changes. It may or may not\
+                            be useful to you, but let's don't take unnecessary risks, eh? (you can use the\
+                            `--report-file` parameter)"
+
+    filesnpaths.is_output_file_writable(report_file_path)
+
     if not collection_name:
         raise ConfigError, "You must provide a collection name."
 
@@ -76,19 +85,25 @@ def main(args):
         bins_sorted_by_completion.append((bin_name, d['percent_complete'] - d['percent_redundancy']),)
 
     bins_sorted_by_completion.sort(key=operator.itemgetter(1), reverse=True)
+    report = open(report_file_path, 'w')
+    report.write('old_bin_name\tnew_bin_name\n')
     counter = 1
     for bin_name, _ in bins_sorted_by_completion:
         new_bin_name = '%s_bin_%05d' % (prefix, counter)
         collection_dict[new_bin_name] = copy.deepcopy(collection_dict[bin_name])
         collection_dict.pop(bin_name)
 
+        report.write('%s\t%s\n' % (bin_name, new_bin_name))
+
         counter += 1
+    report.close()
 
     # update tables with new bin names.
     collections_table = dbops.TablesForCollections(profile_db, anvio.__profile__version__)
     collections_table.append(collection_name, collection_dict)
 
     run.info('Rename', 'Renaming is done for %d bins in collection "%s".' % (len(collection_dict), collection_name))
+    run.info('Report', '%s' % (report_file_path))
 
 
 if __name__ == '__main__':
@@ -99,13 +114,16 @@ if __name__ == '__main__':
     parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
     parser.add_argument(*anvio.A('profile-db'), **anvio.K('profile-db'))
     parser.add_argument(*anvio.A('collection-name'), **anvio.K('collection-name'))
-    parser.add_argument('--prefix', default = None, required = True,\
+    parser.add_argument('--prefix', default = None,
                         help = "Prefix for the bin names. Must be a single word, composed\
                                 of digits and numbers. The use of the underscore character is OK,\
                                 but that's about it (fine, the use of the dash character is OK, too\
                                 but no more!). If the prefix is 'PREFIX', each bin will be renamed\
                                 as 'PREFIX_Bin_00001, PREFIX_bin_00002', and so on, in the order of\
                                 percent completion minus percent redundancy.")
+    parser.add_argument('--report-file', metavar = 'REPORT_FILE_PATH', default = None, \
+                        help = "This file will report each name change event, so you can trace back\
+                                the original names of renamed bins later.")
     parser.add_argument(*anvio.A('list-collections'), **anvio.K('list-collections'))
 
     args = parser.parse_args()