Replace 7z binary call with a python lib: py7zr. Fix symlink index issue.

Author: catileptic

ingestors/packages/__init__.py

@@ -1,8 +1,10 @@
 import bz2
 import gzip
+import py7zr
 import shutil
 import tarfile
 from pathlib import PurePath
+from py7zr.exceptions import ArchiveError
 
 from ingestors.ingestor import Ingestor
 from ingestors.support.package import PackageSupport
@@ -24,9 +26,11 @@ def unpack(self, file_path, entity, temp_dir):
                 *pure_file_path.parts[1:-1], reconstructed_filename
             )
 
-        self.exec_command(
-            "7z", "x", str(pure_file_path), "-y", "-r", "-bb0", "-bd", f"-oc:{temp_dir}"
-        )
+        try:
+            with py7zr.SevenZipFile(str(pure_file_path), mode='r') as extractor:
+                extractor.extractall(path=temp_dir)
+        except ArchiveError as e:
+            raise ProcessingException(f"Error: {e}")
 
 
 class SingleFilePackageIngestor(PackageSupport, Ingestor):

pyproject.toml

@@ -50,7 +50,8 @@ dependencies = [
     # servicelayer extras requirements
     "boto3 (>=1.11.9,<2.0.0)",
     "grpcio (>=1.32.0,<2.0.0)",
-    "google-cloud-storage (>=1.31.0,<3.0.0)"
+    "google-cloud-storage (>=1.31.0,<3.0.0)",
+    "py7zr (==1.0.0)",
 ]
 
 [project.scripts]

requirements.txt

@@ -15,7 +15,7 @@ fingerprints==1.2.3
 fasttext==0.9.2
 pika==1.3.2
 nomenklatura==3.15.2
-
+py7zr==1.0.0
 # Development
 pytest==8.2.0
 pytest-cov==5.0.0