revert the datasource tool sanitation, set default # for export

scripts/grt/export.py

@@ -135,7 +135,7 @@ def main(argv):
                         help="Set the logging level", default='warning')
     parser.add_argument("-b", "--batch-size", type=int, default=1000,
                         help="Batch size for sql queries")
-    parser.add_argument("-m", "--max-records", type=int, default=0,
+    parser.add_argument("-m", "--max-records", type=int, default=5000000,
                         help="Maximum number of records to include in a single report. This option should ONLY be used when reporting historical data. Setting this may require running GRT multiple times to capture all historical logs.")
     populate_config_args(parser)
 

scripts/grt/grt.yml.sample

@@ -21,23 +21,6 @@ sanitization:
     tools:
         - __SET_METADATA__
         - upload1
-        - ucsc_table_direct1
-        - ucsc_table_direct_archaea1
-        - ebi_sra_main
-        - modENCODEfly
-        - intermine
-        - flymine
-        - modmine
-        - mousemine
-        - ratmine
-        - yeastmine
-        - modENCODEworm
-        - wormbase
-        - zebrafishmine
-        - eupathdb
-        - hbvar
-        - genomespace_importer
-        - genomespace_exporter
     # Or you can blacklist individual parameters from being submitted, e.g. if
     # you have API keys as a tool parameter.
     tool_params: