python, ruby: Remove collapsed files after reading (#128)

* merge: Add parse_and_remove_one_collapsed()

* python: Use parse_and_remove_one_collapsed()

Fixes a regression: we didn't remove old collapsed files.

* ruby: Use parse_and_remove_one_collapsed()

Fixes same bug from Python.

Author: Jongy

gprofiler/merge.py

@@ -7,6 +7,7 @@
 import random
 import re
 from collections import Counter, defaultdict
+from pathlib import Path
 from typing import Iterable, Optional, Tuple
 
 from gprofiler.docker_client import DockerClient
@@ -53,6 +54,15 @@ def parse_one_collapsed(collapsed: str, add_comm: Optional[str] = None) -> Stack
     return stacks
 
 
+def parse_and_remove_one_collapsed(collapsed: Path, add_comm: Optional[str] = None) -> StackToSampleCount:
+    """
+    Parse a stack-collapsed file and remove it.
+    """
+    data = collapsed.read_text()
+    collapsed.unlink()
+    return parse_one_collapsed(data, add_comm)
+
+
 def parse_many_collapsed(text: str) -> ProcessToStackSampleCounters:
     """
     Parse a stack-collapsed listing where stacks are prefixed with the command and pid/tid of their

gprofiler/python.py

@@ -15,7 +15,7 @@
 
 from gprofiler.exceptions import CalledProcessError, ProcessStoppedException, StopEventSetException
 from gprofiler.log import get_logger_adapter
-from gprofiler.merge import parse_many_collapsed, parse_one_collapsed
+from gprofiler.merge import parse_and_remove_one_collapsed, parse_many_collapsed
 from gprofiler.profiler_base import ProfilerBase, ProfilerInterface
 from gprofiler.types import ProcessToStackSampleCounters
 from gprofiler.utils import (
@@ -66,7 +66,7 @@ def _profile_process(self, process: Process):
             raise StopEventSetException
 
         logger.info(f"Finished profiling process {process.pid} with py-spy")
-        return parse_one_collapsed(Path(local_output_path).read_text(), comm)
+        return parse_and_remove_one_collapsed(Path(local_output_path), comm)
 
     def _find_python_processes_to_profile(self) -> List[Process]:
         filtered_procs = []

gprofiler/ruby.py

@@ -11,7 +11,7 @@
 
 from gprofiler.exceptions import ProcessStoppedException, StopEventSetException
 from gprofiler.log import get_logger_adapter
-from gprofiler.merge import parse_one_collapsed
+from gprofiler.merge import parse_and_remove_one_collapsed
 from gprofiler.profiler_base import ProfilerBase
 from gprofiler.types import ProcessToStackSampleCounters
 from gprofiler.utils import pgrep_maps, random_prefix, resource_path, run_process
@@ -58,7 +58,7 @@ def _profile_process(self, process: Process):
             raise StopEventSetException
 
         logger.info(f"Finished profiling process {process.pid} with rbspy")
-        return parse_one_collapsed(Path(local_output_path).read_text(), comm)
+        return parse_and_remove_one_collapsed(Path(local_output_path), comm)
 
     def snapshot(self) -> ProcessToStackSampleCounters:
         processes_to_profile = _find_ruby_processes()