zipstrain 0.2.11__tar.gz → 0.2.16__tar.gz

{zipstrain-0.2.11 → zipstrain-0.2.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: zipstrain
-Version: 0.2.11
+Version: 0.2.16
 Summary: 
 Author: ParsaGhadermazi
 Author-email: 54489047+ParsaGhadermazi@users.noreply.github.com

{zipstrain-0.2.11 → zipstrain-0.2.16}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "zipstrain"
-version = "0.2.11"
+version = "0.2.16"
 description = ""
 authors = [
     {name = "ParsaGhadermazi",email = "54489047+ParsaGhadermazi@users.noreply.github.com"}

{zipstrain-0.2.11 → zipstrain-0.2.16}/src/zipstrain/task_manager.py

@@ -523,7 +523,7 @@ class ProfileTaskGenerator(TaskGenerator):
                 "bed-file": FileInput(self.profile_bed_file),
                 "gene-range-table": FileInput(self.gene_range_file),
                 "genome-length-file": FileInput(self.genome_length_file),
-                "num-threads": IntInput(self.num_procs),
+                "num-workers": IntInput(self.num_procs),
                 "breadth-min-cov": IntInput(self.breadth_min_cov),
                 }
                 expected_outputs ={
@@ -720,7 +720,7 @@ class LocalBatch(Batch):
 
     def __init__(self, tasks, id, run_dir, expected_outputs) -> None:
         super().__init__(tasks, id, run_dir, expected_outputs)
-        self._script = self.TEMPLATE_CMD + "\nset -o pipefail\n"
+        self._script = self.TEMPLATE_CMD + "\nset -euo pipefail\n"
         self._proc: asyncio.subprocess.Process | None = None 
 
 
@@ -759,14 +759,18 @@ class LocalBatch(Batch):
             except asyncio.CancelledError:
                 if self._proc and self._proc.returncode is None:
                     self._proc.terminate()
-                    await write_file(self.batch_dir / f"{self.id}.err", Messages.CANCELLED_BY_USER, self.file_semaphore)
+                    await write_file(self.batch_dir / f"{self.id}.err", err_bytes.decode(), self.file_semaphore)
 
-                raise
+                raise Exception
             
 
             await write_file(self.batch_dir / f"{self.id}.out", out_bytes.decode(), self.file_semaphore)
             await write_file(self.batch_dir / f"{self.id}.err", err_bytes.decode(), self.file_semaphore)
 
+            if self._proc.returncode != 0:
+                error=err_bytes.decode()
+                raise RuntimeError(f"Batch script failed with error:\n{error}")
+            
             if self._proc.returncode == 0 and self.outputs_ready():
                 self.cleanup()
                 self._status = Status.SUCCESS.value
@@ -814,7 +818,7 @@ class SlurmBatch(Batch):
         super().__init__(tasks, id, run_dir, expected_outputs)
         self._check_slurm_works()
         self.slurm_config = slurm_config
-        self._script = self.TEMPLATE_CMD + self.slurm_config.to_slurm_args() + "\nset -o pipefail\n"
+        self._script = self.TEMPLATE_CMD + self.slurm_config.to_slurm_args() + "\nset -euo pipefail\n"
         self._job_id = None
 
     def _check_slurm_works(self) -> None:
@@ -1454,7 +1458,7 @@ class ProfileBamTask(Task):
 
         - gene-range-table: A BED file specifying the gene ranges for the sample.
 
-        - num-threads: The number of threads to use for processing.
+        - num-workers: The number of concurrent workers to use for processing.
 
         - genome-length-file: A file containing the lengths of the genomes in the reference fasta.
 
@@ -1477,7 +1481,8 @@ class ProfileBamTask(Task):
     --stb-file <stb-file> \
     --num-workers <num-workers> \
     --output-dir .
-    mv input.bam.parquet <sample-name>.parquet
+    mv input_profile.parquet <sample-name>.parquet
+    mv input_genome_stats.parquet <sample-name>_genome_stats.parquet
     samtools idxstats <bam-file> |  awk '$3 > 0 {print $1}' > <sample-name>.parquet.scaffolds
     """