add more vcfanno args

--output-path
--chunk-size

cravat/oc.py

@@ -6,7 +6,7 @@
 from cravat.cravat_report import parser as report_parser
 from cravat.vcfanno import vcfanno
 import sys
-from pathlib import Path
+import pathlib
 
 root_p = argparse.ArgumentParser(
     description="Open-CRAVAT genomic variant interpreter. https://github.com/KarchinLab/open-cravat"
@@ -240,9 +240,16 @@
                        type = int,
                        help = 'Number of CPU threads to use')
 vcfanno_p.add_argument('--temp-dir',
-                       type = Path,
-                       default = Path('temp-vcfanno'),
+                       type = pathlib.Path,
+                       default = pathlib.Path('temp-vcfanno'),
                        help = 'Temporary directory for working files')
+vcfanno_p.add_argument('-o','--output-path',
+                       type = pathlib.Path,
+                       help = 'Output vcf path (gzipped). Defaults to input_path.oc.vcf.gz')
+vcfanno_p.add_argument('--chunk-size',
+                       type = int,
+                       default = 10**4,
+                       help = 'Number of lines to annotate in each thread before syncing to disk. Affects performance.')
 vcfanno_p.set_defaults(func=vcfanno)
 
 def main():

cravat/vcfanno.py

@@ -397,7 +397,10 @@ def process(self):
 
 def vcfanno(args):
     input_path = pathlib.Path(args.input_path)
-    output_path = pathlib.Path(str(input_path)+'.oc.vcf.gz')
+    if args.output_path is not None:
+        output_path = args.output_path
+    else:
+        output_path = pathlib.Path(str(input_path)+'.oc.vcf.gz')
     handler = logging.StreamHandler(sys.stdout)
     handler.setLevel(logging.DEBUG)
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
@@ -413,7 +416,8 @@ def vcfanno(args):
         output_path = str(output_path),
         temp_dir = args.temp_dir,
         processors = args.threads if args.threads else mp.cpu_count(),
-        chunk_size=10**4,
-        chunk_log_frequency=50,
-        annotators=args.annotators)
+        chunk_size= args.chunk_size,
+        chunk_log_frequency = 50,
+        annotators = args.annotators,
+        )
     anno.process()