ENH: run: Abort if dataset is dirty

This prevents problematic cases where the user has uncommitted changes
to files and doesn't realize that the run will take the files from
HEAD.  It also prevents unnecessary work in scenarios like the one
described in ReproNimgh-447 where the dirty check on the remote side will fail
due to subdataset modifications.

Closes ReproNim#447.

reproman/support/jobs/orchestrators.py

@@ -484,6 +484,10 @@ def __init__(self, resource, submission_type, job_spec=None,
         if self._resurrection:
             self.head = self.job_spec.get("head")
         else:
+            if self.ds.repo.dirty:
+                raise OrchestratorError("Local dataset {} is dirty. "
+                                        "Save or discard uncommitted changes"
+                                        .format(self.ds.path))
             self._configure_repo()
             self.head = self.ds.repo.get_hexsha()
             _datalad_check_container(self.ds, self.job_spec)

reproman/support/jobs/tests/test_orchestrators.py

@@ -408,6 +408,14 @@ def test_orc_datalad_pair(job_spec, dataset, shell):
 @pytest.mark.integration
 def test_orc_datalad_abort_if_dirty(job_spec, dataset, shell):
     with chpwd(dataset.path):
+        # We abort if the local dataset is dirty.
+        create_tree(dataset.path, {"local-dirt": ""})
+        with pytest.raises(OrchestratorError) as exc:
+            orcs.DataladPairOrchestrator(
+                shell, submission_type="local", job_spec=job_spec)
+        assert "dirty" in str(exc.value)
+        os.unlink("local-dirt")
+
         orc0 = orcs.DataladPairOrchestrator(
             shell, submission_type="local", job_spec=job_spec)
         # Run one job so that we create the remote repository.