All tests are working

Author: charles-cowart

sequence_processing_pipeline/GenPrepFileJob.py

@@ -1,8 +1,8 @@
 from sequence_processing_pipeline.Job import Job
 from sequence_processing_pipeline.PipelineError import PipelineError
 from os import makedirs, symlink
-from os.path import join, exists, basename
-from shutil import copy
+from os.path import isdir, join, exists, basename
+from shutil import copy, copytree
 from functools import partial
 from collections import defaultdict
 from metapool import (demux_sample_sheet, parse_prep,
@@ -54,8 +54,32 @@ def __init__(self, run_dir, convert_job_path, qc_job_path, output_path,
         else:
             self.is_restart = False
 
-            makedirs(reports_dir)
-            copy(self.reports_path, reports_dir)
+            """
+            With copytree(src, dst), src must be an existing directory and dst
+            must be a path that doesn't already exist.
+            src cannot be a file. it must be a directory.
+
+            when using copytree to copy a directory, dst must be the path to
+            the directory where you want the copy PLUS the name of the copied
+            directory. To give dst the same directory name as src you would
+            then need to split() the folder name off the end of src and append
+            it to dst to get a proper value. copytree() DOES NOT put a copy
+            of src in dst. More like it copies the entire contents of src
+            recursively into dst, however dst cannot already exist so you
+            can't use it to copy the contents of a directory into an existing
+            directory.
+
+            This means that if src is a file and not a directory, you will
+            need to use copy() to copy the file instead. It also means that
+            you will need to make reports_dir manually.
+            """
+
+            if isdir(self.reports_path):
+                copytree(self.reports_path, reports_dir)
+            else:
+                # assume self.reports_path is a file.
+                makedirs(reports_dir)
+                copy(self.reports_path, reports_dir)
 
         # extracting from either convert_job_path or qc_job_path should
         # produce equal results.

sequence_processing_pipeline/NuQCJob.py

@@ -118,7 +118,7 @@ def __init__(self, fastq_root_dir, output_path, sample_sheet_path,
 
         self._validate_project_data()
 
-    def hack_helper(self):
+    def contains_bx_metadata(self):
         # get list of raw compressed fastq files. only consider R1 and R2
         # reads.
 
@@ -458,7 +458,7 @@ def _generate_mmi_filter_cmds(self, working_dir):
         # read the first line of the compressed fastq file and see if it
         # contains optional BX metadata. If not it will return False, other
         # wise True.
-        apply_bx = self.hack_helper()
+        apply_bx = self.contains_bx_metadata()
 
         # the default setting.
         tags = ""

sequence_processing_pipeline/tests/test_NuQCJob.py

@@ -10,6 +10,7 @@
 from os import makedirs, remove
 from metapool import load_sample_sheet
 from os import walk
+import gzip
 
 
 class TestNuQCJob(unittest.TestCase):
@@ -73,10 +74,11 @@ def setUp(self):
             for id in ids:
                 fr_fp = join(sample_path, f"{id}_R1_001.fastq.gz")
                 rr_fp = join(sample_path, f"{id}_R2_001.fastq.gz")
-                with open(fr_fp, "w") as f:
-                    f.write("This is a forward-read file.")
-                with open(rr_fp, "w") as f:
-                    f.write("This is a reverse-read file.")
+
+                with gzip.open(fr_fp, "wb") as f:
+                    f.write(b"@my_seq_id BX:1:1101:10000:10000\n")
+                with gzip.open(rr_fp, "wb") as f:
+                    f.write(b"@my_seq_id BX:1:1101:10000:10000\n")
 
         self.feist_ids = [
             "JM-MEC__Staphylococcus_aureusstrain_BERTI-R08624",
@@ -868,7 +870,6 @@ def tearDown(self):
         if exists(self.tmp_file_path):
             remove(self.tmp_file_path)
 
-        # for test_move_trimmed_files()
         if exists(self.path("NuQCJob")):
             shutil.rmtree(self.path("NuQCJob"))