WIP: Use regex for job-id lookup

dask_jobqueue/core.py

@@ -2,6 +2,7 @@
 
 import logging
 import math
+import re
 import shlex
 import subprocess
 import sys
@@ -138,6 +139,7 @@ class JobQueueCluster(Cluster):
     cancel_command = None
     scheduler_name = ''
     _adaptive_options = {'worker_key': lambda ws: _job_id_from_worker_name(ws.name)}
+    job_id_regexp = r'(?P<job_id>\d+)'
 
     def __init__(self,
                  name=None,
@@ -407,5 +409,16 @@ def _del_pending_jobs(self):
         return jobs
 
     def _job_id_from_submit_output(self, out):
-        raise NotImplementedError('_job_id_from_submit_output must be implemented when JobQueueCluster is '
-                                  'inherited. It should convert the stdout from submit_command to the job id')
+        msg = ('Could not parse job id from submission command output. Job id '
+               'regexp is {}, submission command output is: {}'.format(
+                    self.job_id_regexp, out))
+
+        match = re.search(self.job_id_regexp, out)
+        if match is None:
+            raise ValueError(msg)
+
+        job_id = match.group('job_id')
+        if job_id is None:
+            raise ValueError(msg)
+
+        return job_id

dask_jobqueue/lsf.py

@@ -102,9 +102,6 @@ def __init__(self, queue=None, project=None, ncpus=None, mem=None, walltime=None
 
         logger.debug("Job script: \n %s" % self.job_script())
 
-    def _job_id_from_submit_output(self, out):
-        return out.split('<')[1].split('>')[0].strip()
-
     def _submit_job(self, script_filename):
         piped_cmd = [self.submit_command + ' ' + script_filename + ' 2> /dev/null']
         return self._call(piped_cmd, shell=True)

dask_jobqueue/moab.py

@@ -42,6 +42,3 @@ class MoabCluster(PBSCluster):
     submit_command = 'msub'
     cancel_command = 'canceljob'
     scheduler_name = 'moab'
-
-    def _job_id_from_submit_output(self, out):
-        return out.strip()

dask_jobqueue/pbs.py

@@ -101,9 +101,6 @@ def __init__(self, queue=None, project=None, resource_spec=None, walltime=None,
 
         logger.debug("Job script: \n %s" % self.job_script())
 
-    def _job_id_from_submit_output(self, out):
-        return out.split('.')[0].strip()
-
 
 def pbs_format_bytes_ceil(n):
     """ Format bytes as text.

dask_jobqueue/sge.py

@@ -78,6 +78,3 @@ def __init__(self, queue=None, project=None, resource_spec=None, walltime=None,
         self.job_header = header_template % config
 
         logger.debug("Job script: \n %s" % self.job_script())
-
-    def _job_id_from_submit_output(self, out):
-        return out.strip()

dask_jobqueue/slurm.py

@@ -102,9 +102,6 @@ def __init__(self, queue=None, project=None, walltime=None, job_cpu=None, job_me
 
         logger.debug("Job script: \n %s" % self.job_script())
 
-    def _job_id_from_submit_output(self, out):
-        return out.split(';')[0].strip()
-
 
 def slurm_format_bytes_ceil(n):
     """ Format bytes as text.

dask_jobqueue/tests/test_jobqueue_core.py

@@ -44,3 +44,50 @@ def test_forward_ip():
     with PBSCluster(walltime='00:02:00', processes=4, cores=8, memory='28GB',
                     name='dask-worker') as cluster:
         assert cluster.local_cluster.scheduler.ip == default_ip
+
+
+@pytest.mark.parametrize('Cluster', [PBSCluster, MoabCluster, SLURMCluster,
+                                     SGECluster, LSFCluster])
+@pytest.mark.parametrize(
+    'qsub_return_string',
+    ['{job_id}.admin01',
+     'Request {job_id}.asdf was sumbitted to queue: standard.',
+     'sbatch: Submitted batch job {job_id}',
+     '{job_id};cluster',
+     'Job <{job_id}> is submitted to default queue <normal>.',
+     '{job_id}'])
+def test_job_id_from_qsub(Cluster, qsub_return_string):
+    original_job_id = '654321'
+    qsub_return_string = qsub_return_string.format(job_id=original_job_id)
+    with Cluster(walltime='00:02:00', processes=4, cores=8, memory='28GB',
+                 name='dask-worker') as cluster:
+        assert (original_job_id
+                == cluster._job_id_from_submit_output(qsub_return_string))
+
+
+@pytest.mark.parametrize('Cluster', [PBSCluster, MoabCluster, SLURMCluster,
+                                     SGECluster, LSFCluster])
+@pytest.mark.parametrize(
+    'qsub_return_string',
+    ['Request {job_id}.asdf was sumbitted to queue: standard.',
+     'sbatch: Submitted batch job {job_id}',
+     '{job_id};cluster',
+     'Job <{job_id}> is submitted to default queue <normal>.',
+     '{job_id}',
+     pytest.param('{job_id}.admin01', marks=pytest.mark.xfail)])
+def test_job_id_error_handling(Cluster, qsub_return_string):
+
+    # test for broken regexp
+    with Cluster(walltime='00:02:00', processes=4, cores=8, memory='28GB',
+                 name='dask-worker') as cluster:
+        with pytest.raises(ValueError, match="Could not parse job id"):
+            cluster.job_id_regexp = r'(?P<job_id>XXXX)'
+            return_string = qsub_return_string.format(job_id='654321')
+            cluster._job_id_from_submit_output(return_string)
+
+    # test for missing job_id  (Will fail for return string w/ number.)
+    with Cluster(walltime='00:02:00', processes=4, cores=8, memory='28GB',
+                 name='dask-worker') as cluster:
+        with pytest.raises(ValueError, match="Could not parse job id"):
+            return_string = qsub_return_string.format(job_id='XXXXX')
+            cluster._job_id_from_submit_output(return_string)

docs/index.rst

@@ -285,5 +285,4 @@ problems are the following:
   We use submit command stdout to parse the job_id corresponding to the
   launched group of worker. If the parsing fails, then dask-jobqueue won't work
   as expected and may throw exceptions. You can have a look at the parsing
-  function in every ``JobQueueCluster`` implementation, see
-  ``_job_id_from_submit_output`` function.
+  function ``JobQueueCluster._job_id_from_submit_output``.