fix relative input path

Signed-off-by: Alexey Roytman <[email protected]>

data-processing-lib/python/Makefile

@@ -46,6 +46,7 @@ image::
 # it seems when running multiple ray launch tests in a single pytest run there is some sort of ray.init() duplication.
 # pytest-forked was tried, but then we get SIGABRT in pytest when running the s3 tests, some of which are skipped.. 
 # TODO: the following fails. Why? source venv/bin/activate; export PYTHONPATH=../src; cd test; $(PYTEST) . 
+.PHONY: test
 test:: venv
  @# Help: Use the already-built virtual environment to run pytest on the test directory. 
  source venv/bin/activate; export PYTHONPATH=../src; cd test; $(PYTEST) data_processing_tests/data_access;

data-processing-lib/python/src/data_processing/data_access/data_access_local.py

@@ -54,8 +54,8 @@ def __init__(
  self.input_folder = None
  self.output_folder = None
  else:
- self.input_folder = local_config["input_folder"]
- self.output_folder = local_config["output_folder"]
+ self.input_folder = os.path.abspath(local_config["input_folder"])
+ self.output_folder = os.path.abspath(local_config["output_folder"])
  self.d_sets = d_sets
  self.checkpoint = checkpoint
  self.m_files = m_files

data-processing-lib/python/test/data_processing_tests/data_access/data_access_local_test.py

@@ -441,6 +441,15 @@ def test_get_output_location(self):
  out_path = self.dal.get_output_location(in_path)
  assert out_path == os.path.join(self.dal.output_folder, "path", "to", "f.parquet")
 
+ path_dict = {
+ "input_folder": os.path.join("..", "input_guf"),
+ "output_folder": os.path.join(os.sep, "tmp", "output_guf"),
+ }
+ dal = DataAccessLocal(path_dict)
+ in_path = os.path.abspath(os.path.join("..", "input_guf", "path", "to", "f.parquet"))
+ out_path = dal.get_output_location(in_path)
+ assert out_path == os.path.join(dal.output_folder, "path", "to", "f.parquet")
+
 
 class TestSavePyarrowTable(TestInit):