chore(apt): issue warning on missing decompression tool

The apt cache data can be compressed. To work with the decompressed
data, decompression tooling is needed. Instead of silently ignoring the
case where a utility is missing, we now issue a warning. This informs
the user about the missing tool and potential implications.

Closes: #150
Signed-off-by: Felix Moessbauer <felix.moessbauer@siemens.com>

Author: fmoessbauer

src/debsbom/apt/cache.py

@@ -10,7 +10,11 @@
 import logging
 from pathlib import Path
 
-from ..util.compression import find_compressed_file_variants, stream_compressed_file
+from ..util.compression import (
+    CompressionToolMissing,
+    find_compressed_file_variants,
+    stream_compressed_file,
+)
 from ..dpkg.package import BinaryPackage, SourcePackage
 from .. import HAS_PYTHON_APT
 
@@ -169,6 +173,8 @@ def _parse_sources(
                 # pass the filename of a compressed file when using apt_pkg
                 sources_raw = Packages.iter_paragraphs(content, use_apt_pkg=False)
                 yield from Repository._make_srcpkgs(sources_raw, srcpkg_filter)
+        except CompressionToolMissing as e:
+            logger.warning(f'{e}: skipping path "{compressed_variant}"')
         except (FileNotFoundError, IndexError, RuntimeError):
             logger.debug(f"Missing apt cache sources: {sources_file}")
 
@@ -191,6 +197,8 @@ def _parse_packages(
                 packages_raw = Packages.iter_paragraphs(content, use_apt_pkg=False)
                 logger.debug(f"Parsing apt cache binary packages: {packages_file}")
                 yield from Repository._make_binpkgs(packages_raw, binpkg_filter)
+        except CompressionToolMissing as e:
+            logger.warning(f'{e}: skipping path "{compressed_variant}"')
         except (FileNotFoundError, IndexError, RuntimeError):
             logger.debug(f"Missing apt cache packages: {packages_file}")
 

src/debsbom/util/compression.py

@@ -5,9 +5,19 @@
 from collections import namedtuple
 from collections.abc import Iterable
 from pathlib import Path
+import shutil
 import subprocess
 
 
+class CompressionToolMissing(RuntimeError):
+    """
+    Error indicating that a needed compression / decompression tool is missing.
+    """
+
+    def __init__(self, tool):
+        super().__init__(f'Compression tool "{tool}" missing')
+
+
 class Compression:
 
     Format = namedtuple("compression", "tool compress extract fileext")
@@ -53,11 +63,14 @@ def stream_compressed_file(path: Path) -> Iterable[str]:
     """Streams the decompressed content of a compressed file."""
     try:
         comp = Compression.from_ext(path.suffix)
+        tool = shutil.which(comp.tool)
+        if not tool:
+            raise CompressionToolMissing(comp.tool)
     except ValueError:
         comp = Compression.NONE
 
     compressor = subprocess.Popen(
-        [comp.tool] + comp.extract + [path],
+        [tool] + comp.extract + [path],
         stdout=subprocess.PIPE,
         text=True,
     )