X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/6b4f035a93296d8d39c674fe4fdc181dadd98e78..f888eee63ff962201154114efae87f3342ec2aa7:/crunch_scripts/grep

diff --git a/crunch_scripts/grep b/crunch_scripts/grep
old mode 100644
new mode 100755
index 6392e0c9e7..65120a5cc3
--- a/crunch_scripts/grep
+++ b/crunch_scripts/grep
@@ -1,20 +1,21 @@
 #!/usr/bin/env python
 
 import arvados
+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_task['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.name())
+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 string.find(line, search_string):
+    if pattern.search(line):
         out.write(line)
 
 this_task.set_output(out.finish())