X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/26174557d40f4643b8c506c0cdfa66503b18544e..1479cedd5fb5504058e9cb1f4664474a5335d64b:/crunch_scripts/grep

diff --git a/crunch_scripts/grep b/crunch_scripts/grep
index 908cea2048..a84c0f671c 100755
--- a/crunch_scripts/grep
+++ b/crunch_scripts/grep
@@ -1,21 +1,24 @@
 #!/usr/bin/env python
+# Copyright (C) The Arvados Authors. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0
 
 import arvados
-import string
+import re
 
 arvados.job_setup.one_task_per_input_file(if_sequence=0, and_end_task=True)
 
 this_job = arvados.current_job()
 this_task = arvados.current_task()
 this_task_input = this_task['parameters']['input']
-search_string = this_job['script_parameters']['pattern']
+pattern = re.compile(this_job['script_parameters']['pattern'])
 
 input_file = list(arvados.CollectionReader(this_task_input).all_files())[0]
 out = arvados.CollectionWriter()
 out.set_current_file_name(input_file.decompressed_name())
 out.set_current_stream_name(input_file.stream_name())
 for line in input_file.readlines():
-    if 0 <= string.find(line, search_string):
+    if pattern.search(line):
         out.write(line)
 
 this_task.set_output(out.finish())